diff --git a/.nojekyll b/.nojekyll new file mode 100644 index 000000000..e69de29bb diff --git a/404.html b/404.html new file mode 100644 index 000000000..3ad9a62a9 --- /dev/null +++ b/404.html @@ -0,0 +1,1618 @@ + + + + + + + + + + + + + + + + + + + + + + + Outlines 〰️ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ +
+
+ + + +
+ + + + +
+ + +
+ +
+ + + + + + + + + +
+
+ + + +
+
+
+ + + + + + + +
+
+
+ + + +
+
+
+ + + +
+
+
+ + + +
+
+ +

404 - Not found

+ +
+
+ + + +
+ +
+ + + +
+
+
+
+ + + + + + + + + + \ No newline at end of file diff --git a/api/fsm/index.html b/api/fsm/index.html new file mode 100644 index 000000000..afce5087d --- /dev/null +++ b/api/fsm/index.html @@ -0,0 +1,4027 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + Fsm - Outlines 〰️ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + + Skip to content + + +
+
+ + + +
+ + + + +
+ + +
+ +
+ + + + + + + + + +
+
+ + + +
+
+
+ + + + + + + +
+
+
+ + + +
+
+
+ + + +
+
+
+ + + +
+
+ + + + + + + +

Fsm

+ +
+ + + + +
+ + + +
+ + + + + + + + +
+ + + +

+ CFGFSM + + +

+ + +
+

+ Bases: FSM

+ + +

FSM to generate text that is in the language of a context-free grammar.

+ +
+ Source code in outlines/fsm/fsm.py + 
190
+191
+192
+193
+194
+195
+196
+197
+198
+199
+200
+201
+202
+203
+204
+205
+206
+207
+208
+209
+210
+211
+212
+213
+214
+215
+216
+217
+218
+219
+220
+221
+222
+223
+224
+225
+226
+227
+228
+229
+230
+231
+232
+233
+234
+235
+236
+237
+238
+239
+240
+241
+242
+243
+244
+245
+246
+247
+248
+249
+250
+251
+252
+253
+254
+255
+256
+257
+258
+259
+260
+261
+262
+263
+264
+265
+266
+267
+268
+269
+270
+271
+272
+273
+274
+275
+276
+277
+278
+279
+280
+281
+282
+283
+284
+285
+286
+287
+288
+289
+290
+291
+292
+293
+294
+295
+296
+297
+298
+299
+300
+301
+302
+303
+304
+305
+306
+307
+308
+309
+310
+311
+312
+313
+314
+315
+316
+317
+318
+319
+320
+321
+322
+323
+324
+325
+326
+327
+328
+329
+330
+331
+332
+333
+334
+335
class CFGFSM(FSM):
+    """FSM to generate text that is in the language of a context-free grammar."""
+
+    def __init__(self, cfg_string: str, tokenizer):
+        self.cfg_string = cfg_string
+        self.tokenizer = tokenizer
+
+        self.parser = Lark(
+            cfg_string,
+            parser="lalr",
+            lexer="contextual",
+            propagate_positions=False,
+            maybe_placeholders=False,
+            regex=True,
+            import_paths=[grammars.GRAMMAR_PATH],
+        )
+        self.terminal_regexps = dict()
+        for terminal in self.parser.terminals:
+            if terminal.pattern is not None:
+                self.terminal_regexps[terminal.name] = terminal.pattern.to_regexp()
+        self.terminal_regexps["$END"] = tokenizer.eos_token
+
+        self.generation = ""
+        self.reset_state = False
+        self.allow_eos = False
+        self.regex_fsm: RegexFSM
+
+        self.check_last = False
+        self.proposal_last: List[int] = []
+        self.regex_fsm_last: RegexFSM
+
+    def allowed_token_ids(self, state: FSMState) -> List[int]:
+        """Generate a list of allowed tokens for the next step.
+
+        Upon initialization, the CFG incremental parser is used to determine the
+        first regex and construct the first FSM to generate the first terminal.
+
+        This FSM is used for proposals until either:
+
+        - The FSM is exhausted, and its only remaining option is the EOS
+          token, in which case we feed the generated terminal to the
+          CFG incremental parser and allow it to propose the next regex
+          corresponding to the next set of valid terminals.
+        - The current FSM can be exhausted, but the EOS token is not the only
+          remaining option. In this case we allow proposal of current terminal extensions,
+          store the current FSM and its state, then also use the CFG parser
+          to propose a new regex corresponding to terminating the current terminal
+          and starting the next one. The model can then sample from either of these sets
+          to determine whether to extend the current terminal or terminate it and start the next one.
+
+        The CFG incremental parser is allowed to propose the EOS token from any accepting state,
+        and once it is generated, the FSM will continue to always generate the EOS token.
+
+        Parameters
+        ----------
+        state
+            The current state of the FSM.
+
+        Returns
+        -------
+        A list that contains the tokens to mask.
+
+        """
+        if self.is_final_state(state):
+            return [self.tokenizer.eos_token_id]
+
+        proposal = []
+        if self.generation != "":
+            if self.check_last:
+                proposer = self.regex_fsm_last
+            else:
+                proposer = self.regex_fsm
+            proposal += proposer.allowed_token_ids(state)
+            if self.tokenizer.eos_token_id not in proposal:
+                return proposal
+            self.check_last = False
+            proposal = [x for x in proposal if x != self.tokenizer.eos_token_id]
+            if len(proposal) > 0:
+                self.check_last = True
+                self.proposal_last = proposal.copy()
+                self.regex_fsm_last = proposer
+
+        interactive = self.parser.parse_interactive(self.generation)
+        interactive.exhaust_lexer()
+
+        options = {self.terminal_regexps[x] for x in interactive.accepts()}
+        # add %ignore terminals
+        options |= {self.terminal_regexps[x] for x in self.parser.lexer_conf.ignore}
+
+        if self.terminal_regexps["$END"] in options:
+            options.remove(self.terminal_regexps["$END"])
+            if len(options) == 0:
+                return [self.tokenizer.eos_token_id]
+            self.allow_eos = True
+            options.add("")
+            assert len(options) > 1
+
+        regex_string = r"(" + r"|".join([r"(" + x + r")" for x in options]) + r")"
+        self.regex_fsm = RegexFSM(regex_string, self.tokenizer)
+        self.reset_state = True
+
+        proposal += self.regex_fsm.allowed_token_ids(self.first_state)
+        if self.allow_eos:
+            self.allow_eos = False
+        else:
+            proposal = [x for x in proposal if x != self.tokenizer.eos_token_id]
+            assert len(proposal) > 0
+        return proposal
+
+    def next_state(self, state: FSMState, token_id: int) -> FSMState:
+        """Update the state of the FSM.
+
+        Transitions the underlying regex FSM to its next state.
+        If at max tokens or EOS token, transition permanently to the final state.
+        Update stored partial generations for subsequent incremental parsing.
+
+        Parameters
+        ----------
+        state
+            The current state of the FSM.
+        token_id
+            The id of the token that was just generated.
+
+        Returns
+        -------
+        The new state of the FSM.
+        """
+        if token_id == self.tokenizer.eos_token_id:
+            return self.final_state
+
+        self.generation += self.tokenizer.decode([token_id])[0]
+
+        if self.check_last:
+            if token_id in self.proposal_last:
+                return self.regex_fsm_last.next_state(state, token_id)
+            self.check_last = False
+
+        if self.reset_state:
+            self.reset_state = False
+            state = self.first_state
+
+        return self.regex_fsm.next_state(state, token_id)
+
+    def copy(self) -> "CFGFSM":
+        """Create a copy of the FSM."""
+        return CFGFSM(self.cfg_string, self.tokenizer)
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ allowed_token_ids(state) + +

+ + +
+ +

Generate a list of allowed tokens for the next step.

+

Upon initialization, the CFG incremental parser is used to determine the +first regex and construct the first FSM to generate the first terminal.

+

This FSM is used for proposals until either:

+
    +
  • The FSM is exhausted, and its only remaining option is the EOS + token, in which case we feed the generated terminal to the + CFG incremental parser and allow it to propose the next regex + corresponding to the next set of valid terminals.
    • +
  • The current FSM can be exhausted, but the EOS token is not the only + remaining option. In this case we allow proposal of current terminal extensions, + store the current FSM and its state, then also use the CFG parser + to propose a new regex corresponding to terminating the current terminal + and starting the next one. The model can then sample from either of these sets + to determine whether to extend the current terminal or terminate it and start the next one.
    • +
+

The CFG incremental parser is allowed to propose the EOS token from any accepting state, +and once it is generated, the FSM will continue to always generate the EOS token.

+
Parameters
+

state + The current state of the FSM.

+
Returns
+

A list that contains the tokens to mask.

+ +
+ Source code in outlines/fsm/fsm.py + 
221
+222
+223
+224
+225
+226
+227
+228
+229
+230
+231
+232
+233
+234
+235
+236
+237
+238
+239
+240
+241
+242
+243
+244
+245
+246
+247
+248
+249
+250
+251
+252
+253
+254
+255
+256
+257
+258
+259
+260
+261
+262
+263
+264
+265
+266
+267
+268
+269
+270
+271
+272
+273
+274
+275
+276
+277
+278
+279
+280
+281
+282
+283
+284
+285
+286
+287
+288
+289
+290
+291
+292
+293
+294
+295
+296
+297
def allowed_token_ids(self, state: FSMState) -> List[int]:
+    """Generate a list of allowed tokens for the next step.
+
+    Upon initialization, the CFG incremental parser is used to determine the
+    first regex and construct the first FSM to generate the first terminal.
+
+    This FSM is used for proposals until either:
+
+    - The FSM is exhausted, and its only remaining option is the EOS
+      token, in which case we feed the generated terminal to the
+      CFG incremental parser and allow it to propose the next regex
+      corresponding to the next set of valid terminals.
+    - The current FSM can be exhausted, but the EOS token is not the only
+      remaining option. In this case we allow proposal of current terminal extensions,
+      store the current FSM and its state, then also use the CFG parser
+      to propose a new regex corresponding to terminating the current terminal
+      and starting the next one. The model can then sample from either of these sets
+      to determine whether to extend the current terminal or terminate it and start the next one.
+
+    The CFG incremental parser is allowed to propose the EOS token from any accepting state,
+    and once it is generated, the FSM will continue to always generate the EOS token.
+
+    Parameters
+    ----------
+    state
+        The current state of the FSM.
+
+    Returns
+    -------
+    A list that contains the tokens to mask.
+
+    """
+    if self.is_final_state(state):
+        return [self.tokenizer.eos_token_id]
+
+    proposal = []
+    if self.generation != "":
+        if self.check_last:
+            proposer = self.regex_fsm_last
+        else:
+            proposer = self.regex_fsm
+        proposal += proposer.allowed_token_ids(state)
+        if self.tokenizer.eos_token_id not in proposal:
+            return proposal
+        self.check_last = False
+        proposal = [x for x in proposal if x != self.tokenizer.eos_token_id]
+        if len(proposal) > 0:
+            self.check_last = True
+            self.proposal_last = proposal.copy()
+            self.regex_fsm_last = proposer
+
+    interactive = self.parser.parse_interactive(self.generation)
+    interactive.exhaust_lexer()
+
+    options = {self.terminal_regexps[x] for x in interactive.accepts()}
+    # add %ignore terminals
+    options |= {self.terminal_regexps[x] for x in self.parser.lexer_conf.ignore}
+
+    if self.terminal_regexps["$END"] in options:
+        options.remove(self.terminal_regexps["$END"])
+        if len(options) == 0:
+            return [self.tokenizer.eos_token_id]
+        self.allow_eos = True
+        options.add("")
+        assert len(options) > 1
+
+    regex_string = r"(" + r"|".join([r"(" + x + r")" for x in options]) + r")"
+    self.regex_fsm = RegexFSM(regex_string, self.tokenizer)
+    self.reset_state = True
+
+    proposal += self.regex_fsm.allowed_token_ids(self.first_state)
+    if self.allow_eos:
+        self.allow_eos = False
+    else:
+        proposal = [x for x in proposal if x != self.tokenizer.eos_token_id]
+        assert len(proposal) > 0
+    return proposal
+
+
+
+ +
+ + +
+ + + +

+ copy() + +

+ + +
+ +

Create a copy of the FSM.

+ +
+ Source code in outlines/fsm/fsm.py + 
333
+334
+335
def copy(self) -> "CFGFSM":
+    """Create a copy of the FSM."""
+    return CFGFSM(self.cfg_string, self.tokenizer)
+
+
+
+ +
+ + +
+ + + +

+ next_state(state, token_id) + +

+ + +
+ +

Update the state of the FSM.

+

Transitions the underlying regex FSM to its next state. +If at max tokens or EOS token, transition permanently to the final state. +Update stored partial generations for subsequent incremental parsing.

+
Parameters
+

state + The current state of the FSM. +token_id + The id of the token that was just generated.

+
Returns
+

The new state of the FSM.

+ +
+ Source code in outlines/fsm/fsm.py + 
299
+300
+301
+302
+303
+304
+305
+306
+307
+308
+309
+310
+311
+312
+313
+314
+315
+316
+317
+318
+319
+320
+321
+322
+323
+324
+325
+326
+327
+328
+329
+330
+331
def next_state(self, state: FSMState, token_id: int) -> FSMState:
+    """Update the state of the FSM.
+
+    Transitions the underlying regex FSM to its next state.
+    If at max tokens or EOS token, transition permanently to the final state.
+    Update stored partial generations for subsequent incremental parsing.
+
+    Parameters
+    ----------
+    state
+        The current state of the FSM.
+    token_id
+        The id of the token that was just generated.
+
+    Returns
+    -------
+    The new state of the FSM.
+    """
+    if token_id == self.tokenizer.eos_token_id:
+        return self.final_state
+
+    self.generation += self.tokenizer.decode([token_id])[0]
+
+    if self.check_last:
+        if token_id in self.proposal_last:
+            return self.regex_fsm_last.next_state(state, token_id)
+        self.check_last = False
+
+    if self.reset_state:
+        self.reset_state = False
+        state = self.first_state
+
+    return self.regex_fsm.next_state(state, token_id)
+
+
+
+ +
+ + + +
+ +
+ + +
+ +
+ + + +

+ FSM + + +

+ + +
+

+ Bases: Protocol

+ + +
+ Source code in outlines/fsm/fsm.py + 
17
+18
+19
+20
+21
+22
+23
+24
+25
+26
+27
+28
+29
+30
+31
+32
class FSM(Protocol):
+    first_state: FSMState = FSMState(0)
+    final_state: FSMState = FSMState(-1)
+
+    def is_final_state(self, state: FSMState) -> bool:
+        """Determine whether the current state of the FSM is a final state."""
+        return state == self.final_state
+
+    def allowed_token_ids(self, state: FSMState) -> List[int]:
+        ...
+
+    def next_state(self, state: FSMState, token_id: int) -> FSMState:
+        ...
+
+    def copy(self) -> "FSM":
+        ...
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ is_final_state(state) + +

+ + +
+ +

Determine whether the current state of the FSM is a final state.

+ +
+ Source code in outlines/fsm/fsm.py + 
21
+22
+23
def is_final_state(self, state: FSMState) -> bool:
+    """Determine whether the current state of the FSM is a final state."""
+    return state == self.final_state
+
+
+
+ +
+ + + +
+ +
+ + +
+ +
+ + + +

+ RegexFSM + + +

+ + +
+

+ Bases: FSM

+ + +

FSM to generate text that is in the language of a regular expression.

+ +
+ Source code in outlines/fsm/fsm.py + 
 91
+ 92
+ 93
+ 94
+ 95
+ 96
+ 97
+ 98
+ 99
+100
+101
+102
+103
+104
+105
+106
+107
+108
+109
+110
+111
+112
+113
+114
+115
+116
+117
+118
+119
+120
+121
+122
+123
+124
+125
+126
+127
+128
+129
+130
+131
+132
+133
+134
+135
+136
+137
+138
+139
+140
+141
+142
+143
+144
+145
+146
+147
+148
+149
+150
+151
+152
+153
+154
+155
+156
+157
+158
+159
+160
+161
+162
+163
+164
+165
+166
+167
+168
+169
+170
+171
+172
+173
+174
+175
+176
+177
+178
+179
+180
+181
+182
+183
+184
+185
+186
+187
class RegexFSM(FSM):
+    """FSM to generate text that is in the language of a regular expression."""
+
+    def __init__(self, regex_string: str, tokenizer):
+        @cache()
+        def create_states_mapping(
+            regex_string: str, cacheable_vocabulary: Tuple[Tuple[str, int]]
+        ) -> Tuple[dict, set]:
+            """Create the variables related to the mapping between states and tokens
+            The parameters of the function are used for caching purpose
+            """
+            regex_pattern = interegular.parse_pattern(regex_string)
+            regex_fsm, _ = make_deterministic_fsm(regex_pattern.to_fsm().reduce())
+            states_to_token_maps, empty_token_ids = create_fsm_index_tokenizer(
+                regex_fsm, tokenizer
+            )
+
+            # We make sure that it is possible to generate strings in the language
+            # of the regular expression with the tokens present in the model's
+            # vocabulary.
+            if not any(
+                regex_fsm.finals.intersection(v.values())
+                for v in states_to_token_maps.values()
+            ):
+                raise ValueError(
+                    "The vocabulary does not allow us to build a sequence that matches the input regex"
+                )
+
+            return states_to_token_maps, empty_token_ids
+
+        self.states_to_token_maps, self.empty_token_ids = create_states_mapping(
+            regex_string, tuple(sorted(tokenizer.vocabulary.items()))
+        )
+        self.vocabulary = tokenizer.vocabulary.values()
+        self.eos_token_id = tokenizer.eos_token_id
+
+    def allowed_token_ids(self, state: FSMState) -> List[int]:
+        """Generate a list of allowed tokens for the next step.
+
+        The initialization of the FSM builds an index which maps FSM states to a
+        map from authorized tokens to the state in which the FSM needs to move
+        if said token is generated. Therefore the authorized tokens at the
+        current state are the keys of the map returned by the value of the index
+        for current state.
+
+        If the current state is not contained in the end this means that we are
+        in a final state of the FSM. We only authorize EOS tokens in the final
+        state.
+
+        Parameters
+        ----------
+        state
+            The current state of the FSM.
+
+        Returns
+        -------
+        A list that contains the tokens to mask.
+
+        """
+        next_tokens_to_end_states = self.states_to_token_maps.get(state)
+
+        if next_tokens_to_end_states is None:
+            return [self.eos_token_id]
+        else:
+            return list(next_tokens_to_end_states.keys())
+
+    def next_state(self, state: FSMState, token_id: int) -> FSMState:
+        """Update the state of the FSM.
+
+        We use the index to determine to which state the FSM should transition
+        given the token that was just generated.
+
+        Parameters
+        ----------
+        state
+            The current state of the FSM.
+        token_id
+            The id of the token that was just generated.
+
+        Returns
+        -------
+        The new state of the FSM.
+
+        """
+        if token_id == self.eos_token_id:
+            return self.final_state
+
+        last_token_to_end_state = self.states_to_token_maps[state]
+        next_state = last_token_to_end_state.get(token_id)
+        if next_state is None:
+            return self.final_state
+
+        return FSMState(next_state)
+
+    def copy(self) -> "RegexFSM":
+        """Create a copy of the FSM."""
+        return self
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ __init__(regex_string, tokenizer) + +

+ + +
+ +
+ Source code in outlines/fsm/fsm.py + 
 94
+ 95
+ 96
+ 97
+ 98
+ 99
+100
+101
+102
+103
+104
+105
+106
+107
+108
+109
+110
+111
+112
+113
+114
+115
+116
+117
+118
+119
+120
+121
+122
+123
+124
+125
def __init__(self, regex_string: str, tokenizer):
+    @cache()
+    def create_states_mapping(
+        regex_string: str, cacheable_vocabulary: Tuple[Tuple[str, int]]
+    ) -> Tuple[dict, set]:
+        """Create the variables related to the mapping between states and tokens
+        The parameters of the function are used for caching purpose
+        """
+        regex_pattern = interegular.parse_pattern(regex_string)
+        regex_fsm, _ = make_deterministic_fsm(regex_pattern.to_fsm().reduce())
+        states_to_token_maps, empty_token_ids = create_fsm_index_tokenizer(
+            regex_fsm, tokenizer
+        )
+
+        # We make sure that it is possible to generate strings in the language
+        # of the regular expression with the tokens present in the model's
+        # vocabulary.
+        if not any(
+            regex_fsm.finals.intersection(v.values())
+            for v in states_to_token_maps.values()
+        ):
+            raise ValueError(
+                "The vocabulary does not allow us to build a sequence that matches the input regex"
+            )
+
+        return states_to_token_maps, empty_token_ids
+
+    self.states_to_token_maps, self.empty_token_ids = create_states_mapping(
+        regex_string, tuple(sorted(tokenizer.vocabulary.items()))
+    )
+    self.vocabulary = tokenizer.vocabulary.values()
+    self.eos_token_id = tokenizer.eos_token_id
+
+
+
+ +
+ + +
+ + + +

+ allowed_token_ids(state) + +

+ + +
+ +

Generate a list of allowed tokens for the next step.

+

The initialization of the FSM builds an index which maps FSM states to a +map from authorized tokens to the state in which the FSM needs to move +if said token is generated. Therefore the authorized tokens at the +current state are the keys of the map returned by the value of the index +for current state.

+

If the current state is not contained in the end this means that we are +in a final state of the FSM. We only authorize EOS tokens in the final +state.

+
Parameters
+

state + The current state of the FSM.

+
Returns
+

A list that contains the tokens to mask.

+ +
+ Source code in outlines/fsm/fsm.py + 
127
+128
+129
+130
+131
+132
+133
+134
+135
+136
+137
+138
+139
+140
+141
+142
+143
+144
+145
+146
+147
+148
+149
+150
+151
+152
+153
+154
+155
def allowed_token_ids(self, state: FSMState) -> List[int]:
+    """Generate a list of allowed tokens for the next step.
+
+    The initialization of the FSM builds an index which maps FSM states to a
+    map from authorized tokens to the state in which the FSM needs to move
+    if said token is generated. Therefore the authorized tokens at the
+    current state are the keys of the map returned by the value of the index
+    for current state.
+
+    If the current state is not contained in the end this means that we are
+    in a final state of the FSM. We only authorize EOS tokens in the final
+    state.
+
+    Parameters
+    ----------
+    state
+        The current state of the FSM.
+
+    Returns
+    -------
+    A list that contains the tokens to mask.
+
+    """
+    next_tokens_to_end_states = self.states_to_token_maps.get(state)
+
+    if next_tokens_to_end_states is None:
+        return [self.eos_token_id]
+    else:
+        return list(next_tokens_to_end_states.keys())
+
+
+
+ +
+ + +
+ + + +

+ copy() + +

+ + +
+ +

Create a copy of the FSM.

+ +
+ Source code in outlines/fsm/fsm.py + 
185
+186
+187
def copy(self) -> "RegexFSM":
+    """Create a copy of the FSM."""
+    return self
+
+
+
+ +
+ + +
+ + + +

+ next_state(state, token_id) + +

+ + +
+ +

Update the state of the FSM.

+

We use the index to determine to which state the FSM should transition +given the token that was just generated.

+
Parameters
+

state + The current state of the FSM. +token_id + The id of the token that was just generated.

+
Returns
+

The new state of the FSM.

+ +
+ Source code in outlines/fsm/fsm.py + 
157
+158
+159
+160
+161
+162
+163
+164
+165
+166
+167
+168
+169
+170
+171
+172
+173
+174
+175
+176
+177
+178
+179
+180
+181
+182
+183
def next_state(self, state: FSMState, token_id: int) -> FSMState:
+    """Update the state of the FSM.
+
+    We use the index to determine to which state the FSM should transition
+    given the token that was just generated.
+
+    Parameters
+    ----------
+    state
+        The current state of the FSM.
+    token_id
+        The id of the token that was just generated.
+
+    Returns
+    -------
+    The new state of the FSM.
+
+    """
+    if token_id == self.eos_token_id:
+        return self.final_state
+
+    last_token_to_end_state = self.states_to_token_maps[state]
+    next_state = last_token_to_end_state.get(token_id)
+    if next_state is None:
+        return self.final_state
+
+    return FSMState(next_state)
+
+
+
+ +
+ + + +
+ +
+ + +
+ +
+ + + +

+ StopAtEosFSM + + +

+ + +
+

+ Bases: FSM

+ + +

FSM to generate text until EOS has been generated.

+ +
+ Source code in outlines/fsm/fsm.py + 
35
+36
+37
+38
+39
+40
+41
+42
+43
+44
+45
+46
+47
+48
+49
+50
+51
+52
+53
+54
+55
+56
+57
+58
+59
+60
+61
+62
+63
+64
+65
+66
+67
+68
+69
+70
+71
+72
+73
+74
+75
+76
+77
+78
+79
+80
+81
+82
+83
+84
+85
+86
+87
+88
class StopAtEosFSM(FSM):
+    """FSM to generate text until EOS has been generated."""
+
+    def __init__(self, tokenizer: "Tokenizer"):
+        self.eos_token_id = tokenizer.eos_token_id
+        self.vocabulary = tokenizer.vocabulary.values()
+
+    def allowed_token_ids(self, state: FSMState) -> List[int]:
+        """Generate a list of allowed tokens for the next step.
+
+        When in the initial state we allow every token to be generated.
+        In the final state the only allowed token is `stop_token_id`.
+
+        Parameters
+        ----------
+        state
+            The current state of the FSM.
+
+        Returns
+        -------
+        A list that contains the tokens to mask.
+
+        """
+        if self.is_final_state(state):
+            return [self.eos_token_id]
+        return list(self.vocabulary)
+
+    def next_state(self, state: FSMState, token_id: int) -> FSMState:
+        """Update the state of the FSM.
+
+        The FSM stays in the initial state `0` unless the specified stop token
+        has been generated or the maximum number of tokens has been reached. In
+        which case the FSM moves to the final state `-1`.
+
+        Parameters
+        ----------
+        state
+            The current state of the FSM.
+        token_id
+            The id of the token that was just generated.
+
+        Returns
+        -------
+        The new state of the FSM.
+
+        """
+        if token_id == self.eos_token_id:
+            return self.final_state
+
+        return self.first_state
+
+    def copy(self) -> "StopAtEosFSM":
+        """Create a copy of the FSM."""
+        return self
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ allowed_token_ids(state) + +

+ + +
+ +

Generate a list of allowed tokens for the next step.

+

When in the initial state we allow every token to be generated. +In the final state the only allowed token is stop_token_id.

+
Parameters
+

state + The current state of the FSM.

+
Returns
+

A list that contains the tokens to mask.

+ +
+ Source code in outlines/fsm/fsm.py + 
42
+43
+44
+45
+46
+47
+48
+49
+50
+51
+52
+53
+54
+55
+56
+57
+58
+59
+60
def allowed_token_ids(self, state: FSMState) -> List[int]:
+    """Generate a list of allowed tokens for the next step.
+
+    When in the initial state we allow every token to be generated.
+    In the final state the only allowed token is `stop_token_id`.
+
+    Parameters
+    ----------
+    state
+        The current state of the FSM.
+
+    Returns
+    -------
+    A list that contains the tokens to mask.
+
+    """
+    if self.is_final_state(state):
+        return [self.eos_token_id]
+    return list(self.vocabulary)
+
+
+
+ +
+ + +
+ + + +

+ copy() + +

+ + +
+ +

Create a copy of the FSM.

+ +
+ Source code in outlines/fsm/fsm.py + 
86
+87
+88
def copy(self) -> "StopAtEosFSM":
+    """Create a copy of the FSM."""
+    return self
+
+
+
+ +
+ + +
+ + + +

+ next_state(state, token_id) + +

+ + +
+ +

Update the state of the FSM.

+

The FSM stays in the initial state 0 unless the specified stop token +has been generated or the maximum number of tokens has been reached. In +which case the FSM moves to the final state -1.

+
Parameters
+

state + The current state of the FSM. +token_id + The id of the token that was just generated.

+
Returns
+

The new state of the FSM.

+ +
+ Source code in outlines/fsm/fsm.py + 
62
+63
+64
+65
+66
+67
+68
+69
+70
+71
+72
+73
+74
+75
+76
+77
+78
+79
+80
+81
+82
+83
+84
def next_state(self, state: FSMState, token_id: int) -> FSMState:
+    """Update the state of the FSM.
+
+    The FSM stays in the initial state `0` unless the specified stop token
+    has been generated or the maximum number of tokens has been reached. In
+    which case the FSM moves to the final state `-1`.
+
+    Parameters
+    ----------
+    state
+        The current state of the FSM.
+    token_id
+        The id of the token that was just generated.
+
+    Returns
+    -------
+    The new state of the FSM.
+
+    """
+    if token_id == self.eos_token_id:
+        return self.final_state
+
+    return self.first_state
+
+
+
+ +
+ + + +
+ +
+ + +
+ + + + +
+ +
+ +
+ + + + + + + + + + + + + + + + + + + + +
+
+ + + +
+ +
+ + + +
+
+
+
+ + + + + + + + + + \ No newline at end of file diff --git a/api/index.html b/api/index.html new file mode 100644 index 000000000..3e4acf600 --- /dev/null +++ b/api/index.html @@ -0,0 +1,1723 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + API Reference - Outlines 〰️ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + + Skip to content + + +
+
+ + + +
+ + + + +
+ + +
+ +
+ + + + + + + + + +
+
+ + + +
+
+
+ + + + + + + +
+
+
+ + + +
+
+
+ + + +
+
+
+ + + +
+
+ + + + + + + +

API Reference

+ + + + + + + + + + + + + + + + + + + + +
+
+ + + +
+ +
+ + + +
+
+
+
+ + + + + + + + + + \ No newline at end of file diff --git a/api/json_schema/index.html b/api/json_schema/index.html new file mode 100644 index 000000000..8f3bde5da --- /dev/null +++ b/api/json_schema/index.html @@ -0,0 +1,2606 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + Json schema - Outlines 〰️ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + + Skip to content + + +
+
+ + + +
+ + + + +
+ + +
+ +
+ + + + + + + + + +
+
+ + + +
+
+
+ + + + + + + +
+
+
+ + + +
+
+
+ + + +
+
+
+ + + +
+
+ + + + + + + +

Json schema

+ +
+ + + + +
+ + + +
+ + + + + + + + + + +
+ + + +

+ build_regex_from_schema(schema, whitespace_pattern=None) + +

+ + +
+ +

Turn a JSON schema into a regex that matches any JSON object that follows + this schema.

+

JSON Schema is a declarative language that allows to annotate JSON documents + with types and descriptions. These schemas can be generated from any Python + datastructure that has type annotation: namedtuples, dataclasses, Pydantic + models. And by ensuring that the generation respects the schema we ensure + that the output can be parsed into these objects. + This function parses the provided schema and builds a generation schedule which + mixes deterministic generation (fixed strings), and sampling with constraints.

+

Parameters

+
+

schema + A string that represents a JSON Schema. + whitespace_pattern + Pattern to use for JSON syntactic whitespace (doesn't impact string literals) + Example: allow only a single space or newline with whitespace_pattern=r"[ +]?"

+

Returns

+
+

A generation schedule. A list of strings that represent the JSON + schema's structure and regular expression that define the structure of + the fields.

+

References

+
+

.. [0] JSON Schema. https://json-schema.org/

+ +
+ Source code in outlines/fsm/json_schema.py + 
41
+42
+43
+44
+45
+46
+47
+48
+49
+50
+51
+52
+53
+54
+55
+56
+57
+58
+59
+60
+61
+62
+63
+64
+65
+66
+67
+68
+69
+70
+71
+72
+73
+74
+75
+76
+77
+78
+79
+80
+81
+82
+83
def build_regex_from_schema(schema: str, whitespace_pattern: Optional[str] = None):
+    """Turn a JSON schema into a regex that matches any JSON object that follows
+    this schema.
+
+    JSON Schema is a declarative language that allows to annotate JSON documents
+    with types and descriptions. These schemas can be generated from any Python
+    datastructure that has type annotation: namedtuples, dataclasses, Pydantic
+    models. And by ensuring that the generation respects the schema we ensure
+    that the output can be parsed into these objects.
+    This function parses the provided schema and builds a generation schedule which
+    mixes deterministic generation (fixed strings), and sampling with constraints.
+
+    Parameters
+    ----------
+    schema
+        A string that represents a JSON Schema.
+    whitespace_pattern
+        Pattern to use for JSON syntactic whitespace (doesn't impact string literals)
+        Example: allow only a single space or newline with `whitespace_pattern=r"[\n ]?"`
+
+    Returns
+    -------
+    A generation schedule. A list of strings that represent the JSON
+    schema's structure and regular expression that define the structure of
+    the fields.
+
+    References
+    ----------
+    .. [0] JSON Schema. https://json-schema.org/
+
+    """
+
+    schema = json.loads(schema)
+    Validator.check_schema(schema)
+
+    # Build reference resolver
+    schema = Resource(contents=schema, specification=DRAFT202012)
+    uri = schema.id() if schema.id() is not None else ""
+    registry = Registry().with_resource(uri=uri, resource=schema)
+    resolver = registry.resolver()
+
+    content = schema.contents
+    return to_regex(resolver, content, whitespace_pattern)
+
+
+
+ +
+ + +
+ + + +

+ get_schema_from_signature(fn) + +

+ + +
+ +

Turn a function signature into a JSON schema.

+

Every JSON object valid to the output JSON Schema can be passed +to fn using the ** unpacking syntax.

+ +
+ Source code in outlines/fsm/json_schema.py + 
355
+356
+357
+358
+359
+360
+361
+362
+363
+364
+365
+366
+367
+368
+369
+370
+371
+372
def get_schema_from_signature(fn: Callable) -> str:
+    """Turn a function signature into a JSON schema.
+
+    Every JSON object valid to the output JSON Schema can be passed
+    to `fn` using the ** unpacking syntax.
+
+    """
+    signature = inspect.signature(fn)
+    arguments = {}
+    for name, arg in signature.parameters.items():
+        if arg.annotation == inspect._empty:
+            raise ValueError("Each argument must have a type annotation")
+        else:
+            arguments[name] = (arg.annotation, ...)
+
+    model = create_model("Arguments", **arguments)
+
+    return model.model_json_schema()
+
+
+
+ +
+ + +
+ + + +

+ to_regex(resolver, instance, whitespace_pattern=None) + +

+ + +
+ +

Translate a JSON Schema instance into a regex that validates the schema.

+

Note

+
+

Many features of JSON schema are missing: + - Handle additionalProperties keyword + - Handle types defined as a list + - Handle constraints on numbers + - Handle special patterns: date, uri, etc.

+

This does not support recursive definitions.

+

Parameters

+
+

resolver + An object that resolves references to other instances within a schema + instance + The instance to translate + whitespace_pattern + Pattern to use for JSON syntactic whitespace (doesn't impact string literals) + Example: allow only a single space or newline with whitespace_pattern=r"[ +]?"

+ +
+ Source code in outlines/fsm/json_schema.py + 
 98
+ 99
+100
+101
+102
+103
+104
+105
+106
+107
+108
+109
+110
+111
+112
+113
+114
+115
+116
+117
+118
+119
+120
+121
+122
+123
+124
+125
+126
+127
+128
+129
+130
+131
+132
+133
+134
+135
+136
+137
+138
+139
+140
+141
+142
+143
+144
+145
+146
+147
+148
+149
+150
+151
+152
+153
+154
+155
+156
+157
+158
+159
+160
+161
+162
+163
+164
+165
+166
+167
+168
+169
+170
+171
+172
+173
+174
+175
+176
+177
+178
+179
+180
+181
+182
+183
+184
+185
+186
+187
+188
+189
+190
+191
+192
+193
+194
+195
+196
+197
+198
+199
+200
+201
+202
+203
+204
+205
+206
+207
+208
+209
+210
+211
+212
+213
+214
+215
+216
+217
+218
+219
+220
+221
+222
+223
+224
+225
+226
+227
+228
+229
+230
+231
+232
+233
+234
+235
+236
+237
+238
+239
+240
+241
+242
+243
+244
+245
+246
+247
+248
+249
+250
+251
+252
+253
+254
+255
+256
+257
+258
+259
+260
+261
+262
+263
+264
+265
+266
+267
+268
+269
+270
+271
+272
+273
+274
+275
+276
+277
+278
+279
+280
+281
+282
+283
+284
+285
+286
+287
+288
+289
+290
+291
+292
+293
+294
+295
+296
+297
+298
+299
+300
+301
+302
+303
+304
+305
+306
+307
+308
+309
+310
+311
+312
+313
+314
+315
+316
+317
+318
+319
+320
+321
+322
+323
+324
+325
+326
+327
+328
+329
+330
+331
+332
+333
+334
+335
+336
+337
+338
+339
+340
+341
+342
+343
+344
+345
+346
+347
+348
+349
+350
+351
+352
def to_regex(
+    resolver: Resolver, instance: dict, whitespace_pattern: Optional[str] = None
+):
+    """Translate a JSON Schema instance into a regex that validates the schema.
+
+    Note
+    ----
+    Many features of JSON schema are missing:
+    - Handle `additionalProperties` keyword
+    - Handle types defined as a list
+    - Handle constraints on numbers
+    - Handle special patterns: `date`, `uri`, etc.
+
+    This does not support recursive definitions.
+
+    Parameters
+    ----------
+    resolver
+        An object that resolves references to other instances within a schema
+    instance
+        The instance to translate
+    whitespace_pattern
+        Pattern to use for JSON syntactic whitespace (doesn't impact string literals)
+        Example: allow only a single space or newline with `whitespace_pattern=r"[\n ]?"`
+    """
+
+    # set whitespace pattern
+    if whitespace_pattern is None:
+        whitespace_pattern = WHITESPACE
+
+    if "properties" in instance:
+        regex = ""
+        regex += r"\{"
+        properties = instance["properties"]
+        required_properties = instance.get("required", [])
+        is_required = [item in required_properties for item in properties]
+        # If at least one property is required, we include the one in the lastest position
+        # without any comma.
+        # For each property before it (optional or required), we add with a comma after the property.
+        # For each property after it (optional), we add with a comma before the property.
+        if any(is_required):
+            last_required_pos = max([i for i, value in enumerate(is_required) if value])
+            for i, (name, value) in enumerate(properties.items()):
+                subregex = f'{whitespace_pattern}"{name}"{whitespace_pattern}:{whitespace_pattern}'
+                subregex += to_regex(resolver, value, whitespace_pattern)
+                if i < last_required_pos:
+                    subregex = f"{subregex}{whitespace_pattern},"
+                elif i > last_required_pos:
+                    subregex = f"{whitespace_pattern},{subregex}"
+                regex += subregex if is_required[i] else f"({subregex})?"
+        # If no property is required, we have to create a possible pattern for each property in which
+        # it's the last one necessarilly present. Then, we add the others as optional before and after
+        # following the same strategy as described above.
+        # The whole block is made optional to allow the case in which no property is returned.
+        else:
+            property_subregexes = []
+            for i, (name, value) in enumerate(properties.items()):
+                subregex = f'{whitespace_pattern}"{name}"{whitespace_pattern}:{whitespace_pattern}'
+                subregex += to_regex(resolver, value, whitespace_pattern)
+                property_subregexes.append(subregex)
+            possible_patterns = []
+            for i in range(len(property_subregexes)):
+                pattern = ""
+                for subregex in property_subregexes[:i]:
+                    pattern += f"({subregex}{whitespace_pattern},)?"
+                pattern += property_subregexes[i]
+                for subregex in property_subregexes[i + 1 :]:
+                    pattern += f"({whitespace_pattern},{subregex})?"
+                possible_patterns.append(pattern)
+            regex += f"({'|'.join(possible_patterns)})?"
+
+        regex += f"{whitespace_pattern}" + r"\}"
+
+        return regex
+
+    # To validate against allOf, the given data must be valid against all of the
+    # given subschemas.
+    elif "allOf" in instance:
+        subregexes = [
+            to_regex(resolver, t, whitespace_pattern) for t in instance["allOf"]
+        ]
+        subregexes_str = [f"{subregex}" for subregex in subregexes]
+        return rf"({''.join(subregexes_str)})"
+
+    # To validate against `anyOf`, the given data must be valid against
+    # any (one or more) of the given subschemas.
+    elif "anyOf" in instance:
+        subregexes = [
+            to_regex(resolver, t, whitespace_pattern) for t in instance["anyOf"]
+        ]
+        return rf"({'|'.join(subregexes)})"
+
+    # To validate against oneOf, the given data must be valid against exactly
+    # one of the given subschemas.
+    elif "oneOf" in instance:
+        subregexes = [
+            to_regex(resolver, t, whitespace_pattern) for t in instance["oneOf"]
+        ]
+
+        xor_patterns = []
+        # json schema validation ensured there is no overlapping schemas in oneOf
+        for subregex in subregexes:
+            other_subregexes = filter(lambda r: r != subregex, subregexes)
+            other_subregexes_str = "|".join([f"{s}" for s in other_subregexes])
+            negative_lookahead = f"(?!.*({other_subregexes_str}))"
+            xor_patterns.append(f"({subregex}){negative_lookahead}")
+
+        return rf"({'|'.join(xor_patterns)})"
+
+    # The enum keyword is used to restrict a value to a fixed set of values. It
+    # must be an array with at least one element, where each element is unique.
+    elif "enum" in instance:
+        choices = []
+        for choice in instance["enum"]:
+            if type(choice) in [int, float, bool, None]:
+                choices.append(re.escape(str(choice)))
+            elif type(choice) == str:
+                choices.append(f'"{re.escape(choice)}"')
+
+        return f"({'|'.join(choices)})"
+
+    elif "$ref" in instance:
+        path = f"{instance['$ref']}"
+        instance = resolver.lookup(path).contents
+        return to_regex(resolver, instance, whitespace_pattern)
+
+    # The type keyword may either be a string or an array:
+    # - If it's a string, it is the name of one of the basic types.
+    # - If it is an array, it must be an array of strings, where each string is
+    # the name of one of the basic types, and each element is unique. In this
+    # case, the JSON snippet is valid if it matches any of the given types.
+    elif "type" in instance:
+        instance_type = instance["type"]
+        if instance_type == "string":
+            if "maxLength" in instance or "minLength" in instance:
+                max_items = instance.get("maxLength", "")
+                min_items = instance.get("minLength", "")
+                try:
+                    if int(max_items) < int(min_items):
+                        raise ValueError(
+                            "maxLength must be greater than or equal to minLength"
+                        )
+                except ValueError:
+                    pass
+                return f'"{STRING_INNER}{{{min_items},{max_items}}}"'
+            elif "pattern" in instance:
+                pattern = instance["pattern"]
+                if pattern[0] == "^" and pattern[-1] == "$":
+                    return rf'(^"{pattern[1:-1]}"$)'
+                else:
+                    return rf'("{pattern}")'
+            elif "format" in instance:
+                format = instance["format"]
+                if format == "date-time":
+                    return format_to_regex["date-time"]
+                elif format == "uuid":
+                    return format_to_regex["uuid"]
+                elif format == "date":
+                    return format_to_regex["date"]
+                elif format == "time":
+                    return format_to_regex["time"]
+                else:
+                    raise NotImplementedError(
+                        f"Format {format} is not supported by Outlines"
+                    )
+            else:
+                return type_to_regex["string"]
+
+        elif instance_type == "number":
+            return type_to_regex["number"]
+
+        elif instance_type == "integer":
+            return type_to_regex["integer"]
+
+        elif instance_type == "array":
+            num_repeats = _get_num_items_pattern(
+                instance.get("minItems"), instance.get("maxItems"), whitespace_pattern
+            )
+            if num_repeats is None:
+                return rf"\[{whitespace_pattern}\]"
+
+            allow_empty = "?" if int(instance.get("minItems", 0)) == 0 else ""
+
+            if "items" in instance:
+                items_regex = to_regex(resolver, instance["items"], whitespace_pattern)
+                return rf"\[{whitespace_pattern}(({items_regex})(,{whitespace_pattern}({items_regex})){num_repeats}){allow_empty}{whitespace_pattern}\]"
+            else:
+                # Here we need to make the choice to exclude generating list of objects
+                # if the specification of the object is not given, even though a JSON
+                # object that contains an object here would be valid under the specification.
+                types = [
+                    {"type": "boolean"},
+                    {"type": "null"},
+                    {"type": "number"},
+                    {"type": "integer"},
+                    {"type": "string"},
+                ]
+                regexes = [to_regex(resolver, t, whitespace_pattern) for t in types]
+                return rf"\[{whitespace_pattern}({'|'.join(regexes)})(,{whitespace_pattern}({'|'.join(regexes)})){num_repeats}){allow_empty}{whitespace_pattern}\]"
+
+        elif instance_type == "object":
+            # pattern for json object with values defined by instance["additionalProperties"]
+            # enforces value type constraints recursively, "minProperties", and "maxProperties"
+            # doesn't enforce "required", "dependencies", "propertyNames" "any/all/on Of"
+            num_repeats = _get_num_items_pattern(
+                instance.get("minProperties"),
+                instance.get("maxProperties"),
+                whitespace_pattern,
+            )
+            if num_repeats is None:
+                return rf"\{{{whitespace_pattern}\}}"
+
+            allow_empty = "?" if int(instance.get("minProperties", 0)) == 0 else ""
+
+            value_pattern = to_regex(
+                resolver, instance["additionalProperties"], whitespace_pattern
+            )
+            key_value_pattern = (
+                f"{STRING}{whitespace_pattern}:{whitespace_pattern}{value_pattern}"
+            )
+            key_value_successor_pattern = (
+                f"{whitespace_pattern},{whitespace_pattern}{key_value_pattern}"
+            )
+            multiple_key_value_pattern = f"({key_value_pattern}({key_value_successor_pattern}){num_repeats}){allow_empty}"
+
+            return (
+                r"\{"
+                + whitespace_pattern
+                + multiple_key_value_pattern
+                + whitespace_pattern
+                + r"\}"
+            )
+
+        elif instance_type == "boolean":
+            return type_to_regex["boolean"]
+
+        elif instance_type == "null":
+            return type_to_regex["null"]
+
+        elif isinstance(instance_type, list):
+            # Here we need to make the choice to exclude generating an object
+            # if the specification of the object is not give, even though a JSON
+            # object that contains an object here would be valid under the specification.
+            regexes = [
+                to_regex(resolver, {"type": t}, whitespace_pattern)
+                for t in instance_type
+                if t != "object"
+            ]
+            return rf"({'|'.join(regexes)})"
+
+    raise NotImplementedError(
+        f"""Could not translate the instance {instance} to a
+    regular expression. Make sure it is valid to the JSON Schema specification. If
+    it is, please open an issue on the Outlines repository"""
+    )
+
+
+
+ +
+ + + +
+ +
+ +
+ + + + + + + + + + + + + + + + + + + + +
+
+ + + +
+ +
+ + + +
+
+
+
+ + + + + + + + + + \ No newline at end of file diff --git a/api/models/index.html b/api/models/index.html new file mode 100644 index 000000000..3350515ed --- /dev/null +++ b/api/models/index.html @@ -0,0 +1,4846 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + Models - Outlines 〰️ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + + Skip to content + + +
+
+ + + +
+ + + + +
+ + +
+ +
+ + + + + + + + + +
+
+ + + +
+
+
+ + + + + + + +
+
+
+ + + +
+
+
+ + + +
+
+
+ + + +
+
+ + + + + + + +

Models

+ +
+ + + + +
+ + + +
+ + + + + + + + +
+ + + +

+ Transformer + + +

+ + +
+ + +

Represents a transformers model.

+ +
+ Source code in outlines/models/transformers.py + 
 58
+ 59
+ 60
+ 61
+ 62
+ 63
+ 64
+ 65
+ 66
+ 67
+ 68
+ 69
+ 70
+ 71
+ 72
+ 73
+ 74
+ 75
+ 76
+ 77
+ 78
+ 79
+ 80
+ 81
+ 82
+ 83
+ 84
+ 85
+ 86
+ 87
+ 88
+ 89
+ 90
+ 91
+ 92
+ 93
+ 94
+ 95
+ 96
+ 97
+ 98
+ 99
+100
+101
+102
+103
+104
+105
+106
+107
+108
+109
+110
+111
+112
+113
+114
+115
+116
+117
+118
+119
class Transformer:
+    """Represents a `transformers` model."""
+
+    def __init__(
+        self,
+        model: "PreTrainedModel",
+        tokenizer: "PreTrainedTokenizer",
+    ):
+        self.device = model.device
+        self.model = model
+        self.tokenizer = tokenizer
+
+    @torch.inference_mode
+    def forward(
+        self,
+        input_ids: torch.LongTensor,
+        attention_mask: torch.LongTensor,
+        past_key_values: Optional[Tuple] = None,
+    ) -> Tuple[torch.FloatTensor, Optional[KVCacheType]]:
+        """Compute a forward pass through the transformer model.
+
+        Parameters
+        ----------
+        input_ids
+            The input token ids.  Must be one or two dimensional.
+        attention_mask
+            The attention mask.  Must be one or two dimensional.
+        past_key_values
+            A tuple of tuples containing the cached key and value tensors for each
+            attention head.
+
+        Returns
+        -------
+        The computed logits and the new cached key and value tensors.
+
+        """
+        assert 0 < input_ids.ndim < 3
+
+        if past_key_values:
+            input_ids = input_ids[..., -1].unsqueeze(-1)
+
+        output = self.model(
+            input_ids,
+            attention_mask=attention_mask,
+            return_dict=True,
+            output_attentions=False,
+            output_hidden_states=False,
+            past_key_values=past_key_values,
+        )
+
+        return output.logits, output.past_key_values
+
+    def __call__(
+        self,
+        input_ids: torch.LongTensor,
+        attention_mask: torch.LongTensor,
+        past_key_values: Optional[Tuple] = None,
+    ) -> torch.FloatTensor:
+        logits, kv_cache = self.forward(input_ids, attention_mask, past_key_values)
+        next_token_logits = logits[..., -1, :]
+
+        return next_token_logits, kv_cache
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ forward(input_ids, attention_mask, past_key_values=None) + +

+ + +
+ +

Compute a forward pass through the transformer model.

+
Parameters
+

input_ids + The input token ids. Must be one or two dimensional. +attention_mask + The attention mask. Must be one or two dimensional. +past_key_values + A tuple of tuples containing the cached key and value tensors for each + attention head.

+
Returns
+

The computed logits and the new cached key and value tensors.

+ +
+ Source code in outlines/models/transformers.py + 
 70
+ 71
+ 72
+ 73
+ 74
+ 75
+ 76
+ 77
+ 78
+ 79
+ 80
+ 81
+ 82
+ 83
+ 84
+ 85
+ 86
+ 87
+ 88
+ 89
+ 90
+ 91
+ 92
+ 93
+ 94
+ 95
+ 96
+ 97
+ 98
+ 99
+100
+101
+102
+103
+104
+105
+106
+107
+108
@torch.inference_mode
+def forward(
+    self,
+    input_ids: torch.LongTensor,
+    attention_mask: torch.LongTensor,
+    past_key_values: Optional[Tuple] = None,
+) -> Tuple[torch.FloatTensor, Optional[KVCacheType]]:
+    """Compute a forward pass through the transformer model.
+
+    Parameters
+    ----------
+    input_ids
+        The input token ids.  Must be one or two dimensional.
+    attention_mask
+        The attention mask.  Must be one or two dimensional.
+    past_key_values
+        A tuple of tuples containing the cached key and value tensors for each
+        attention head.
+
+    Returns
+    -------
+    The computed logits and the new cached key and value tensors.
+
+    """
+    assert 0 < input_ids.ndim < 3
+
+    if past_key_values:
+        input_ids = input_ids[..., -1].unsqueeze(-1)
+
+    output = self.model(
+        input_ids,
+        attention_mask=attention_mask,
+        return_dict=True,
+        output_attentions=False,
+        output_hidden_states=False,
+        past_key_values=past_key_values,
+    )
+
+    return output.logits, output.past_key_values
+
+
+
+ +
+ + + +
+ +
+ + +
+ +
+ + + +

+ TransformerTokenizer + + +

+ + +
+

+ Bases: Tokenizer

+ + +

Represents a tokenizer for models in the transformers library.

+ +
+ Source code in outlines/models/transformers.py + 
122
+123
+124
+125
+126
+127
+128
+129
+130
+131
+132
+133
+134
+135
+136
+137
+138
+139
+140
+141
+142
+143
+144
+145
+146
+147
+148
+149
+150
+151
+152
+153
+154
+155
+156
+157
+158
+159
+160
+161
+162
+163
+164
+165
+166
+167
+168
+169
+170
+171
+172
+173
+174
+175
+176
+177
+178
+179
+180
class TransformerTokenizer(Tokenizer):
+    """Represents a tokenizer for models in the `transformers` library."""
+
+    def __init__(self, model_name: str, **kwargs):
+        from transformers import AutoTokenizer
+
+        kwargs.setdefault("padding_side", "left")
+        self.model_name = model_name
+        # TODO: Do something to make this hashable?
+        self.kwargs = kwargs
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name, **kwargs)
+        self.eos_token_id = self.tokenizer.eos_token_id
+        self.eos_token = self.tokenizer.eos_token
+
+        if not self.tokenizer.pad_token_id:
+            self.tokenizer.pad_token_id = self.tokenizer.eos_token_id
+            self.pad_token_id = self.eos_token_id
+        else:
+            self.pad_token_id = self.tokenizer.pad_token_id
+            self.pad_token = self.tokenizer.pad_token
+
+        self.special_tokens = set(self.tokenizer.all_special_tokens)
+
+        self.vocabulary = self.tokenizer.get_vocab()
+        self.is_llama = isinstance(self.tokenizer, get_llama_tokenizer_types())
+
+    def encode(
+        self, prompt: Union[str, List[str]], **kwargs
+    ) -> Tuple[torch.LongTensor, torch.LongTensor]:
+        kwargs["padding"] = True
+        kwargs["return_tensors"] = "pt"
+        output = self.tokenizer(prompt, **kwargs)
+        return output["input_ids"], output["attention_mask"]
+
+    def decode(self, token_ids: torch.LongTensor) -> List[str]:
+        text = self.tokenizer.batch_decode(token_ids, skip_special_tokens=True)
+        return text
+
+    def convert_token_to_string(self, token: str) -> str:
+        from transformers.file_utils import SPIECE_UNDERLINE
+
+        string = self.tokenizer.convert_tokens_to_string([token])
+
+        if self.is_llama:
+            # A hack to handle missing spaces to HF's Llama tokenizers
+            if token.startswith(SPIECE_UNDERLINE) or token == "<0x20>":
+                return " " + string
+
+        return string
+
+    def __eq__(self, other):
+        if isinstance(other, type(self)):
+            return other.model_name == self.model_name and other.kwargs == self.kwargs
+        return NotImplemented
+
+    def __hash__(self):
+        from datasets.fingerprint import Hasher
+
+        return hash(Hasher.hash(self.tokenizer))
+
+
+ + + +
+ + + + + + + + + + + +
+ +
+ + +
+ + + +
+ + + +

+ get_llama_tokenizer_types() + +

+ + +
+ +

Get all the Llama tokenizer types/classes that need work-arounds.

+

When they can't be imported, a dummy class is created.

+ +
+ Source code in outlines/models/transformers.py + 
16
+17
+18
+19
+20
+21
+22
+23
+24
+25
+26
+27
+28
+29
+30
+31
+32
+33
+34
+35
+36
+37
+38
+39
+40
+41
+42
+43
+44
+45
+46
+47
+48
+49
+50
+51
+52
+53
+54
+55
def get_llama_tokenizer_types():
+    """Get all the Llama tokenizer types/classes that need work-arounds.
+
+    When they can't be imported, a dummy class is created.
+
+    """
+    try:
+        from transformers.models.llama import LlamaTokenizer
+    except ImportError:
+
+        class LlamaTokenizer:  # type: ignore
+            pass
+
+    try:
+        from transformers.models.llama import LlamaTokenizerFast
+    except ImportError:
+
+        class LlamaTokenizerFast:  # type: ignore
+            pass
+
+    try:
+        from transformers.models.code_llama import CodeLlamaTokenizer
+    except ImportError:
+
+        class CodeLlamaTokenizer:  # type: ignore
+            pass
+
+    try:
+        from transformers.models.code_llama import CodeLlamaTokenizerFast
+    except ImportError:
+
+        class CodeLlamaTokenizerFast:  # type: ignore
+            pass
+
+    return (
+        LlamaTokenizer,
+        LlamaTokenizerFast,
+        CodeLlamaTokenizer,
+        CodeLlamaTokenizerFast,
+    )
+
+
+
+ +
+ + +
+ + + +

+ transformers(model_name, device=None, model_kwargs={}, tokenizer_kwargs={}) + +

+ + +
+ +

Instantiate a model from the transformers library and its tokenizer.

+

Parameters

+

model_name + The name of the model as listed on Hugging Face's model page. +device + The device(s) on which the model should be loaded. This overrides + the device_map entry in model_kwargs when provided. +model_kwargs + A dictionary that contains the keyword arguments to pass to the + from_pretrained method when loading the model. +tokenizer_kwargs + A dictionary that contains the keyword arguments to pass to the + from_pretrained method when loading the tokenizer.

+

Returns

+

A TransformersModel model instance.

+ +
+ Source code in outlines/models/transformers.py + 
183
+184
+185
+186
+187
+188
+189
+190
+191
+192
+193
+194
+195
+196
+197
+198
+199
+200
+201
+202
+203
+204
+205
+206
+207
+208
+209
+210
+211
+212
+213
+214
+215
+216
+217
+218
+219
+220
+221
+222
+223
def transformers(
+    model_name: str,
+    device: Optional[str] = None,
+    model_kwargs: dict = {},
+    tokenizer_kwargs: dict = {},
+):
+    """Instantiate a model from the `transformers` library and its tokenizer.
+
+    Parameters
+    ----------
+    model_name
+        The name of the model as listed on Hugging Face's model page.
+    device
+        The device(s) on which the model should be loaded. This overrides
+        the `device_map` entry in `model_kwargs` when provided.
+    model_kwargs
+        A dictionary that contains the keyword arguments to pass to the
+        `from_pretrained` method when loading the model.
+    tokenizer_kwargs
+        A dictionary that contains the keyword arguments to pass to the
+        `from_pretrained` method when loading the tokenizer.
+
+    Returns
+    -------
+    A `TransformersModel` model instance.
+
+    """
+    try:
+        from transformers import AutoModelForCausalLM
+    except ImportError:
+        raise ImportError(
+            "The `transformers` library needs to be installed in order to use `transformers` models."
+        )
+
+    if device is not None:
+        model_kwargs["device_map"] = device
+
+    model = AutoModelForCausalLM.from_pretrained(model_name, **model_kwargs)
+    tokenizer = TransformerTokenizer(model_name, **tokenizer_kwargs)
+
+    return Transformer(model, tokenizer)
+
+
+
+ +
+ + + +
+ +
+ +
+ +
+ + + + +
+ +

Integration with OpenAI's API.

+ + + +
+ + + + + + + + +
+ + + +

+ OpenAI + + +

+ + +
+ + +

An object that represents the OpenAI API.

+ +
+ Source code in outlines/models/openai.py + 
 74
+ 75
+ 76
+ 77
+ 78
+ 79
+ 80
+ 81
+ 82
+ 83
+ 84
+ 85
+ 86
+ 87
+ 88
+ 89
+ 90
+ 91
+ 92
+ 93
+ 94
+ 95
+ 96
+ 97
+ 98
+ 99
+100
+101
+102
+103
+104
+105
+106
+107
+108
+109
+110
+111
+112
+113
+114
+115
+116
+117
+118
+119
+120
+121
+122
+123
+124
+125
+126
+127
+128
+129
+130
+131
+132
+133
+134
+135
+136
+137
+138
+139
+140
+141
+142
+143
+144
+145
+146
+147
+148
+149
+150
+151
+152
+153
+154
+155
+156
+157
+158
+159
+160
+161
+162
+163
+164
+165
+166
+167
+168
+169
+170
+171
+172
+173
+174
+175
+176
+177
+178
+179
+180
+181
+182
+183
+184
+185
+186
+187
+188
+189
+190
+191
+192
+193
+194
+195
+196
+197
+198
+199
+200
+201
+202
+203
+204
+205
+206
+207
+208
+209
+210
+211
+212
+213
+214
+215
+216
+217
+218
+219
+220
+221
+222
+223
+224
+225
+226
+227
+228
+229
+230
+231
+232
+233
+234
+235
+236
+237
+238
+239
+240
+241
+242
+243
+244
+245
+246
+247
+248
+249
+250
+251
+252
+253
+254
+255
+256
+257
+258
+259
+260
+261
+262
+263
+264
+265
+266
+267
+268
+269
+270
+271
+272
+273
+274
+275
+276
+277
+278
+279
+280
+281
+282
+283
+284
+285
+286
+287
+288
+289
+290
+291
+292
+293
+294
+295
+296
+297
+298
+299
+300
+301
+302
+303
+304
+305
+306
+307
+308
+309
+310
+311
+312
class OpenAI:
+    """An object that represents the OpenAI API."""
+
+    def __init__(
+        self,
+        model_name: str,
+        api_key: Optional[str] = None,
+        max_retries: int = 6,
+        timeout: Optional[float] = None,
+        system_prompt: Optional[str] = None,
+        config: Optional[OpenAIConfig] = None,
+    ):
+        """Create an `OpenAI` instance.
+
+        Parameters
+        ----------
+        model_name
+            Model to use, as defined in OpenAI's documentation
+        api_key
+            Secret key to use with the OpenAI API. One can also set the
+            `OPENAI_API_KEY` environment variable, or the value of
+            `openai.api_key`.
+        max_retries
+            The maximum number of retries when calls to the API fail.
+        timeout
+            Duration after which the request times out.
+        system_prompt
+            The content of the system message that precedes the user's prompt.
+        config
+            An instance of `OpenAIConfig`. Can be useful to specify some
+            parameters that cannot be set by calling this class' methods.
+
+        """
+
+        try:
+            import openai
+        except ImportError:
+            raise ImportError(
+                "The `openai` library needs to be installed in order to use Outlines' OpenAI integration."
+            )
+
+        if api_key is None:
+            if os.getenv("OPENAI_API_KEY") is not None:
+                api_key = os.getenv("OPENAI_API_KEY")
+            elif openai.api_key is not None:
+                api_key = openai.api_key
+            else:
+                raise ValueError(
+                    "You must specify an API key to use the OpenAI API integration."
+                )
+        try:
+            client = openai.OpenAI(api_key=api_key)
+            client.models.retrieve(model_name)
+        except openai.NotFoundError:
+            raise ValueError(
+                "Invalid model_name. Check openai models list at https://platform.openai.com/docs/models"
+            )
+
+        if config is not None:
+            self.config = replace(config, model=model_name)  # type: ignore
+        else:
+            self.config = OpenAIConfig(model=model_name)
+
+        # This is necesssary because of an issue with the OpenAI API.
+        # Status updates: https://github.com/openai/openai-python/issues/769
+        self.create_client = functools.partial(
+            openai.AsyncOpenAI,
+            api_key=api_key,
+            max_retries=max_retries,
+            timeout=timeout,
+        )
+
+        self.system_prompt = system_prompt
+
+        # We count the total number of prompt and generated tokens as returned
+        # by the OpenAI API, summed over all the requests performed with this
+        # model instance.
+        self.prompt_tokens = 0
+        self.completion_tokens = 0
+
+    def __call__(
+        self,
+        prompt: Union[str, List[str]],
+        max_tokens: Optional[int] = None,
+        stop_at: Optional[Union[List[str], str]] = None,
+        *,
+        temperature: float = 1.0,
+        samples: Optional[int] = None,
+    ) -> np.ndarray:
+        """Call the OpenAI API to generate text.
+
+        Parameters
+        ----------
+        prompt
+            A string or list of strings that will be used to prompt the model
+        max_tokens
+            The maximum number of tokens to generate
+        temperature
+            The value of the temperature used to sample tokens
+        samples
+            The number of completions to generate for each prompt
+        stop_at
+            Up to 4 words where the API will stop the completion.
+
+        """
+        if samples is None:
+            samples = self.config.n
+
+        config = replace(self.config, max_tokens=max_tokens, n=samples, stop=stop_at)  # type: ignore
+
+        if isinstance(stop_at, list) and len(stop_at) > 4:
+            raise NotImplementedError(
+                "The OpenAI API supports at most 4 stop sequences."
+            )
+
+        if "text-" in self.config.model:
+            raise NotImplementedError(
+                textwrap.dedent(
+                    "Most models that support the legacy completion endpoints will be "
+                    "deprecated on January 2024. Use Chat models instead.\n"
+                    "The list of chat models is available at https://platform.openai.com/docs/guides/text-generation."
+                )
+            )
+        if "gpt-" in self.config.model:
+            client = self.create_client()
+            response, prompt_tokens, completion_tokens = generate_chat(
+                prompt, self.system_prompt, client, config
+            )
+            self.prompt_tokens += prompt_tokens
+            self.completion_tokens += completion_tokens
+
+            return response
+
+    def stream(self, *args, **kwargs):
+        raise NotImplementedError(
+            "Streaming is currently not supported for the OpenAI API"
+        )
+
+    @property
+    def tokenizer(self):
+        try:
+            import tiktoken
+        except ImportError:
+            raise ImportError(
+                "The `tiktoken` library needs to be installed in order to choose `outlines.models.openai` with `is_in`"
+            )
+
+        return tiktoken.encoding_for_model(self.config.model)
+
+    def generate_choice(
+        self, prompt: str, choices: List[str], max_tokens: Optional[int] = None
+    ) -> str:
+        """Call the OpenAI API to generate one of several choices.
+
+        Parameters
+        ----------
+        prompt
+            A string or list of strings that will be used to prompt the model
+        choices
+            The list of strings between which we ask the model to choose
+        max_tokens
+            The maximum number of tokens to generate
+
+        """
+        config = replace(self.config, max_tokens=max_tokens)
+
+        greedy = False
+        decoded: List[str] = []
+        encoded_choices_left: List[List[int]] = [
+            self.tokenizer.encode(word) for word in choices
+        ]
+
+        while len(encoded_choices_left) > 0:
+            max_tokens_left = max([len(tokens) for tokens in encoded_choices_left])
+            transposed_choices_left: List[Set] = [
+                {item for item in subset if item is not None}
+                for subset in zip_longest(*encoded_choices_left)
+            ]
+
+            if not greedy:
+                mask = build_optimistic_mask(transposed_choices_left)
+            else:
+                mask = {}
+                for token in transposed_choices_left[0]:  # build greedy mask
+                    mask[token] = 100
+
+            if len(mask) == 0:
+                break
+
+            config = replace(config, logit_bias=mask, max_tokens=max_tokens_left)
+
+            client = self.create_client()
+            response, prompt_tokens, completion_tokens = generate_chat(
+                prompt, self.system_prompt, client, config
+            )
+            self.prompt_tokens += prompt_tokens
+            self.completion_tokens += completion_tokens
+
+            encoded_response = self.tokenizer.encode(response)
+
+            if encoded_response in encoded_choices_left:
+                decoded.append(response)
+                break
+            else:
+                (
+                    encoded_response,
+                    encoded_choices_left,
+                ) = find_response_choices_intersection(
+                    encoded_response, encoded_choices_left
+                )
+
+                if len(encoded_response) == 0:
+                    greedy = True  # next iteration will be "greedy"
+                    continue
+                else:
+                    decoded.append("".join(self.tokenizer.decode(encoded_response)))
+
+                    if len(encoded_choices_left) == 1:  # only one choice left
+                        choice_left = self.tokenizer.decode(encoded_choices_left[0])
+                        decoded.append(choice_left)
+                        break
+
+                    greedy = False  # after each success, stay with (or switch to) "optimistic" approach
+
+                prompt = prompt + "".join(decoded)
+
+        choice = "".join(decoded)
+
+        return choice
+
+    def generate_json(self):
+        """Call the OpenAI API to generate a JSON object."""
+        raise NotImplementedError
+
+    def __str__(self):
+        return self.__class__.__name__ + " API"
+
+    def __repr__(self):
+        return str(self.config)
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ __call__(prompt, max_tokens=None, stop_at=None, *, temperature=1.0, samples=None) + +

+ + +
+ +

Call the OpenAI API to generate text.

+
Parameters
+

prompt + A string or list of strings that will be used to prompt the model +max_tokens + The maximum number of tokens to generate +temperature + The value of the temperature used to sample tokens +samples + The number of completions to generate for each prompt +stop_at + Up to 4 words where the API will stop the completion.

+ +
+ Source code in outlines/models/openai.py + 
154
+155
+156
+157
+158
+159
+160
+161
+162
+163
+164
+165
+166
+167
+168
+169
+170
+171
+172
+173
+174
+175
+176
+177
+178
+179
+180
+181
+182
+183
+184
+185
+186
+187
+188
+189
+190
+191
+192
+193
+194
+195
+196
+197
+198
+199
+200
+201
+202
+203
+204
+205
def __call__(
+    self,
+    prompt: Union[str, List[str]],
+    max_tokens: Optional[int] = None,
+    stop_at: Optional[Union[List[str], str]] = None,
+    *,
+    temperature: float = 1.0,
+    samples: Optional[int] = None,
+) -> np.ndarray:
+    """Call the OpenAI API to generate text.
+
+    Parameters
+    ----------
+    prompt
+        A string or list of strings that will be used to prompt the model
+    max_tokens
+        The maximum number of tokens to generate
+    temperature
+        The value of the temperature used to sample tokens
+    samples
+        The number of completions to generate for each prompt
+    stop_at
+        Up to 4 words where the API will stop the completion.
+
+    """
+    if samples is None:
+        samples = self.config.n
+
+    config = replace(self.config, max_tokens=max_tokens, n=samples, stop=stop_at)  # type: ignore
+
+    if isinstance(stop_at, list) and len(stop_at) > 4:
+        raise NotImplementedError(
+            "The OpenAI API supports at most 4 stop sequences."
+        )
+
+    if "text-" in self.config.model:
+        raise NotImplementedError(
+            textwrap.dedent(
+                "Most models that support the legacy completion endpoints will be "
+                "deprecated on January 2024. Use Chat models instead.\n"
+                "The list of chat models is available at https://platform.openai.com/docs/guides/text-generation."
+            )
+        )
+    if "gpt-" in self.config.model:
+        client = self.create_client()
+        response, prompt_tokens, completion_tokens = generate_chat(
+            prompt, self.system_prompt, client, config
+        )
+        self.prompt_tokens += prompt_tokens
+        self.completion_tokens += completion_tokens
+
+        return response
+
+
+
+ +
+ + +
+ + + +

+ __init__(model_name, api_key=None, max_retries=6, timeout=None, system_prompt=None, config=None) + +

+ + +
+ +

Create an OpenAI instance.

+
Parameters
+

model_name + Model to use, as defined in OpenAI's documentation +api_key + Secret key to use with the OpenAI API. One can also set the + OPENAI_API_KEY environment variable, or the value of + openai.api_key. +max_retries + The maximum number of retries when calls to the API fail. +timeout + Duration after which the request times out. +system_prompt + The content of the system message that precedes the user's prompt. +config + An instance of OpenAIConfig. Can be useful to specify some + parameters that cannot be set by calling this class' methods.

+ +
+ Source code in outlines/models/openai.py + 
 77
+ 78
+ 79
+ 80
+ 81
+ 82
+ 83
+ 84
+ 85
+ 86
+ 87
+ 88
+ 89
+ 90
+ 91
+ 92
+ 93
+ 94
+ 95
+ 96
+ 97
+ 98
+ 99
+100
+101
+102
+103
+104
+105
+106
+107
+108
+109
+110
+111
+112
+113
+114
+115
+116
+117
+118
+119
+120
+121
+122
+123
+124
+125
+126
+127
+128
+129
+130
+131
+132
+133
+134
+135
+136
+137
+138
+139
+140
+141
+142
+143
+144
+145
+146
+147
+148
+149
+150
+151
+152
def __init__(
+    self,
+    model_name: str,
+    api_key: Optional[str] = None,
+    max_retries: int = 6,
+    timeout: Optional[float] = None,
+    system_prompt: Optional[str] = None,
+    config: Optional[OpenAIConfig] = None,
+):
+    """Create an `OpenAI` instance.
+
+    Parameters
+    ----------
+    model_name
+        Model to use, as defined in OpenAI's documentation
+    api_key
+        Secret key to use with the OpenAI API. One can also set the
+        `OPENAI_API_KEY` environment variable, or the value of
+        `openai.api_key`.
+    max_retries
+        The maximum number of retries when calls to the API fail.
+    timeout
+        Duration after which the request times out.
+    system_prompt
+        The content of the system message that precedes the user's prompt.
+    config
+        An instance of `OpenAIConfig`. Can be useful to specify some
+        parameters that cannot be set by calling this class' methods.
+
+    """
+
+    try:
+        import openai
+    except ImportError:
+        raise ImportError(
+            "The `openai` library needs to be installed in order to use Outlines' OpenAI integration."
+        )
+
+    if api_key is None:
+        if os.getenv("OPENAI_API_KEY") is not None:
+            api_key = os.getenv("OPENAI_API_KEY")
+        elif openai.api_key is not None:
+            api_key = openai.api_key
+        else:
+            raise ValueError(
+                "You must specify an API key to use the OpenAI API integration."
+            )
+    try:
+        client = openai.OpenAI(api_key=api_key)
+        client.models.retrieve(model_name)
+    except openai.NotFoundError:
+        raise ValueError(
+            "Invalid model_name. Check openai models list at https://platform.openai.com/docs/models"
+        )
+
+    if config is not None:
+        self.config = replace(config, model=model_name)  # type: ignore
+    else:
+        self.config = OpenAIConfig(model=model_name)
+
+    # This is necesssary because of an issue with the OpenAI API.
+    # Status updates: https://github.com/openai/openai-python/issues/769
+    self.create_client = functools.partial(
+        openai.AsyncOpenAI,
+        api_key=api_key,
+        max_retries=max_retries,
+        timeout=timeout,
+    )
+
+    self.system_prompt = system_prompt
+
+    # We count the total number of prompt and generated tokens as returned
+    # by the OpenAI API, summed over all the requests performed with this
+    # model instance.
+    self.prompt_tokens = 0
+    self.completion_tokens = 0
+
+
+
+ +
+ + +
+ + + +

+ generate_choice(prompt, choices, max_tokens=None) + +

+ + +
+ +

Call the OpenAI API to generate one of several choices.

+
Parameters
+

prompt + A string or list of strings that will be used to prompt the model +choices + The list of strings between which we ask the model to choose +max_tokens + The maximum number of tokens to generate

+ +
+ Source code in outlines/models/openai.py + 
223
+224
+225
+226
+227
+228
+229
+230
+231
+232
+233
+234
+235
+236
+237
+238
+239
+240
+241
+242
+243
+244
+245
+246
+247
+248
+249
+250
+251
+252
+253
+254
+255
+256
+257
+258
+259
+260
+261
+262
+263
+264
+265
+266
+267
+268
+269
+270
+271
+272
+273
+274
+275
+276
+277
+278
+279
+280
+281
+282
+283
+284
+285
+286
+287
+288
+289
+290
+291
+292
+293
+294
+295
+296
+297
+298
+299
+300
+301
+302
def generate_choice(
+    self, prompt: str, choices: List[str], max_tokens: Optional[int] = None
+) -> str:
+    """Call the OpenAI API to generate one of several choices.
+
+    Parameters
+    ----------
+    prompt
+        A string or list of strings that will be used to prompt the model
+    choices
+        The list of strings between which we ask the model to choose
+    max_tokens
+        The maximum number of tokens to generate
+
+    """
+    config = replace(self.config, max_tokens=max_tokens)
+
+    greedy = False
+    decoded: List[str] = []
+    encoded_choices_left: List[List[int]] = [
+        self.tokenizer.encode(word) for word in choices
+    ]
+
+    while len(encoded_choices_left) > 0:
+        max_tokens_left = max([len(tokens) for tokens in encoded_choices_left])
+        transposed_choices_left: List[Set] = [
+            {item for item in subset if item is not None}
+            for subset in zip_longest(*encoded_choices_left)
+        ]
+
+        if not greedy:
+            mask = build_optimistic_mask(transposed_choices_left)
+        else:
+            mask = {}
+            for token in transposed_choices_left[0]:  # build greedy mask
+                mask[token] = 100
+
+        if len(mask) == 0:
+            break
+
+        config = replace(config, logit_bias=mask, max_tokens=max_tokens_left)
+
+        client = self.create_client()
+        response, prompt_tokens, completion_tokens = generate_chat(
+            prompt, self.system_prompt, client, config
+        )
+        self.prompt_tokens += prompt_tokens
+        self.completion_tokens += completion_tokens
+
+        encoded_response = self.tokenizer.encode(response)
+
+        if encoded_response in encoded_choices_left:
+            decoded.append(response)
+            break
+        else:
+            (
+                encoded_response,
+                encoded_choices_left,
+            ) = find_response_choices_intersection(
+                encoded_response, encoded_choices_left
+            )
+
+            if len(encoded_response) == 0:
+                greedy = True  # next iteration will be "greedy"
+                continue
+            else:
+                decoded.append("".join(self.tokenizer.decode(encoded_response)))
+
+                if len(encoded_choices_left) == 1:  # only one choice left
+                    choice_left = self.tokenizer.decode(encoded_choices_left[0])
+                    decoded.append(choice_left)
+                    break
+
+                greedy = False  # after each success, stay with (or switch to) "optimistic" approach
+
+            prompt = prompt + "".join(decoded)
+
+    choice = "".join(decoded)
+
+    return choice
+
+
+
+ +
+ + +
+ + + +

+ generate_json() + +

+ + +
+ +

Call the OpenAI API to generate a JSON object.

+ +
+ Source code in outlines/models/openai.py + 
304
+305
+306
def generate_json(self):
+    """Call the OpenAI API to generate a JSON object."""
+    raise NotImplementedError
+
+
+
+ +
+ + + +
+ +
+ + +
+ +
+ + + +

+ OpenAIConfig + + + + dataclass + + +

+ + +
+ + +

Represents the parameters of the OpenAI API.

+

The information was last fetched on 2023/11/20. We document below the +properties that are specific to the OpenAI API. Not all these properties are +supported by Outlines.

+

Properties

+

model_name + The name of the model. Available models can be found on OpenAI's website. +frequence_penalty + Number between 2.0 and -2.0. Positive values penalize new tokens based on + their existing frequency in the text, +logit_bias + Modifies the likelihood of specified tokens to appear in the completion. + Number between -100 (forbid) and +100 (only allows). +n + The number of completions to return for each prompt. +presence_penalty + Similar to frequency penalty. +response_format + Specifies the format the model must output. {"type": "json_object"} + enables JSON mode. +seed + Two completions with the same seed value should return the same + completion. This is however not guaranteed. +stop + Up to 4 words where the API will stop the completion. +temperature + Number between 0 and 2. Higher values make the output more random, while + lower values make it more deterministic. +top_p + Number between 0 and 1. Parameter for nucleus sampling. +user + A unique identifier for the end-user.

+ +
+ Source code in outlines/models/openai.py + 
20
+21
+22
+23
+24
+25
+26
+27
+28
+29
+30
+31
+32
+33
+34
+35
+36
+37
+38
+39
+40
+41
+42
+43
+44
+45
+46
+47
+48
+49
+50
+51
+52
+53
+54
+55
+56
+57
+58
+59
+60
+61
+62
+63
+64
+65
+66
+67
+68
+69
+70
+71
@dataclass(frozen=True)
+class OpenAIConfig:
+    """Represents the parameters of the OpenAI API.
+
+    The information was last fetched on 2023/11/20. We document below the
+    properties that are specific to the OpenAI API. Not all these properties are
+    supported by Outlines.
+
+    Properties
+    ----------
+    model_name
+        The name of the model. Available models can be found on OpenAI's website.
+    frequence_penalty
+        Number between 2.0 and -2.0. Positive values penalize new tokens based on
+        their existing frequency in the text,
+    logit_bias
+        Modifies the likelihood of specified tokens to appear in the completion.
+        Number between -100 (forbid) and +100 (only allows).
+    n
+        The number of completions to return for each prompt.
+    presence_penalty
+        Similar to frequency penalty.
+    response_format
+        Specifies the format the model must output. `{"type": "json_object"}`
+        enables JSON mode.
+    seed
+        Two completions with the same `seed` value should return the same
+        completion. This is however not guaranteed.
+    stop
+        Up to 4 words where the API will stop the completion.
+    temperature
+        Number between 0 and 2. Higher values make the output more random, while
+        lower values make it more deterministic.
+    top_p
+        Number between 0 and 1. Parameter for nucleus sampling.
+    user
+        A unique identifier for the end-user.
+
+    """
+
+    model: str = ""
+    frequency_penalty: float = 0
+    logit_bias: Dict[int, int] = field(default_factory=dict)
+    max_tokens: Optional[int] = None
+    n: int = 1
+    presence_penalty: float = 0
+    response_format: Optional[Dict[str, str]] = None
+    seed: Optional[int] = None
+    stop: Optional[Union[str, List[str]]] = None
+    temperature: Optional[float] = None
+    top_p: int = 1
+    user: str = field(default_factory=str)
+
+
+ + + +
+ + + + + + + + + + + +
+ +
+ + +
+ + + +
+ + + +

+ build_optimistic_mask(transposed, max_mask_size=300) + +

+ + +
+ +

We build the largest mask possible.

+

Tokens are added from left to right, so if the encoded choices are e.g. +[[1,2], [3,4]], 1 and 3 will be added before 2 and 4.

+

Parameters

+

transposed + A list of lists that contain the nth token of each choice.

+ +
+ Source code in outlines/models/openai.py + 
422
+423
+424
+425
+426
+427
+428
+429
+430
+431
+432
+433
+434
+435
+436
+437
+438
+439
+440
+441
+442
+443
def build_optimistic_mask(
+    transposed: List[Set[int]], max_mask_size: int = 300
+) -> Dict[int, int]:
+    """We build the largest mask possible.
+
+    Tokens are added from left to right, so if the encoded choices are e.g.
+    `[[1,2], [3,4]]`, `1` and `3` will be added before `2` and `4`.
+
+    Parameters
+    ----------
+    transposed
+        A list of lists that contain the nth token of each choice.
+
+    """
+    mask: Dict[int, int] = {}
+    for tokens in transposed:
+        for token in tokens:
+            if len(mask) == max_mask_size:
+                return mask
+            mask[token] = 100
+
+    return mask
+
+
+
+ +
+ + +
+ + + +

+ error_handler(api_call_fn) + +

+ + +
+ +

Handle OpenAI API errors and missing API key.

+ +
+ Source code in outlines/models/openai.py + 
446
+447
+448
+449
+450
+451
+452
+453
+454
+455
+456
+457
+458
+459
+460
+461
+462
+463
+464
+465
+466
+467
+468
+469
+470
def error_handler(api_call_fn: Callable) -> Callable:
+    """Handle OpenAI API errors and missing API key."""
+
+    def call(*args, **kwargs):
+        import openai
+
+        try:
+            return api_call_fn(*args, **kwargs)
+        except (
+            openai.APITimeoutError,
+            openai.InternalServerError,
+            openai.RateLimitError,
+        ) as e:
+            raise OSError(f"Could not connect to the OpenAI API: {e}")
+        except (
+            openai.AuthenticationError,
+            openai.BadRequestError,
+            openai.ConflictError,
+            openai.PermissionDeniedError,
+            openai.NotFoundError,
+            openai.UnprocessableEntityError,
+        ) as e:
+            raise e
+
+    return call
+
+
+
+ +
+ + +
+ + + +

+ find_longest_intersection(response, choice) + +

+ + +
+ +

Find the longest intersection between the response and the choice.

+ +
+ Source code in outlines/models/openai.py + 
371
+372
+373
+374
+375
+376
+377
def find_longest_intersection(response: List[int], choice: List[int]) -> List[int]:
+    """Find the longest intersection between the response and the choice."""
+    for i, (token_r, token_c) in enumerate(zip_longest(response, choice)):
+        if token_r != token_c:
+            return response[:i]
+
+    return response
+
+
+
+ +
+ + +
+ + + +

+ find_response_choices_intersection(response, choices) + +

+ + +
+ +

Find the longest intersection between the response and the different +choices.

+

Say the response is of the form [1, 2, 3, 4, 5] and we have the choices +[[1, 2], [1, 2, 3], [6, 7, 8] then the function will return [1, 2, 3] as the +intersection, and [[]] as the list of choices left.

+

Parameters

+

response + The model's response +choices + The remaining possible choices

+

Returns

+

A tuple that contains the longest intersection between the response and the +different choices, and the choices which start with this intersection, with the +intersection removed.

+ +
+ Source code in outlines/models/openai.py + 
380
+381
+382
+383
+384
+385
+386
+387
+388
+389
+390
+391
+392
+393
+394
+395
+396
+397
+398
+399
+400
+401
+402
+403
+404
+405
+406
+407
+408
+409
+410
+411
+412
+413
+414
+415
+416
+417
+418
+419
def find_response_choices_intersection(
+    response: List[int], choices: List[List[int]]
+) -> Tuple[List[int], List[List[int]]]:
+    """Find the longest intersection between the response and the different
+    choices.
+
+    Say the response is of the form `[1, 2, 3, 4, 5]` and we have the choices
+    `[[1, 2], [1, 2, 3], [6, 7, 8]` then the function will return `[1, 2, 3]` as the
+    intersection, and `[[]]` as the list of choices left.
+
+    Parameters
+    ----------
+    response
+        The model's response
+    choices
+        The remaining possible choices
+
+    Returns
+    -------
+    A tuple that contains the longest intersection between the response and the
+    different choices, and the choices which start with this intersection, with the
+    intersection removed.
+
+    """
+    max_len_prefix = 0
+    choices_left = []
+    longest_prefix = []
+    for i, choice in enumerate(choices):
+        # Find the longest intersection between the response and the choice.
+        prefix = find_longest_intersection(response, choice)
+
+        if len(prefix) > max_len_prefix:
+            max_len_prefix = len(prefix)
+            choices_left = [choice[len(prefix) :]]
+            longest_prefix = prefix
+
+        elif len(prefix) == max_len_prefix:
+            choices_left.append(choice[len(prefix) :])
+
+    return longest_prefix, choices_left
+
+
+
+ +
+ + +
+ + + +

+ generate_chat(prompt, system_prompt, client, config) + + + async + + +

+ + +
+ +

Call OpenAI's Chat Completion API.

+

Parameters

+

prompt + The prompt we use to start the generation. Passed to the model + with the "user" role. +system_prompt + The system prompt, passed to the model with the "system" role + before the prompt. +client + The API client +config + An OpenAIConfig instance.

+

Returns

+

A tuple that contains the model's response(s) and usage statistics.

+ +
+ Source code in outlines/models/openai.py + 
315
+316
+317
+318
+319
+320
+321
+322
+323
+324
+325
+326
+327
+328
+329
+330
+331
+332
+333
+334
+335
+336
+337
+338
+339
+340
+341
+342
+343
+344
+345
+346
+347
+348
+349
+350
+351
+352
+353
+354
+355
+356
+357
+358
+359
+360
+361
+362
+363
+364
+365
@functools.partial(vectorize, signature="(),(),(),()->(s),(),()")
+async def generate_chat(
+    prompt: str,
+    system_prompt: Union[str, None],
+    client: "AsyncOpenAI",
+    config: OpenAIConfig,
+) -> Tuple[np.ndarray, int, int]:
+    """Call OpenAI's Chat Completion API.
+
+    Parameters
+    ----------
+    prompt
+        The prompt we use to start the generation. Passed to the model
+        with the "user" role.
+    system_prompt
+        The system prompt, passed to the model with the "system" role
+        before the prompt.
+    client
+        The API client
+    config
+        An `OpenAIConfig` instance.
+
+    Returns
+    -------
+    A tuple that contains the model's response(s) and usage statistics.
+
+    """
+
+    @cache()
+    async def call_api(prompt, system_prompt, config):
+        responses = await client.chat.completions.create(
+            messages=system_message + user_message,
+            **asdict(config),  # type: ignore
+        )
+        await client.close()
+
+        return responses.model_dump()
+
+    system_message = (
+        [{"role": "system", "content": system_prompt}] if system_prompt else []
+    )
+    user_message = [{"role": "user", "content": prompt}]
+
+    responses = await call_api(prompt, system_prompt, config)
+
+    results = np.array(
+        [responses["choices"][i]["message"]["content"] for i in range(config.n)]
+    )
+    usage = responses["usage"]
+
+    return results, usage["prompt_tokens"], usage["completion_tokens"]
+
+
+
+ +
+ + + +
+ +
+ +
+ + + + + + + + + + + + + + + + + + + + +
+
+ + + +
+ +
+ + + +
+
+
+
+ + + + + + + + + + \ No newline at end of file diff --git a/api/parsing/index.html b/api/parsing/index.html new file mode 100644 index 000000000..16fb41b29 --- /dev/null +++ b/api/parsing/index.html @@ -0,0 +1,3145 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + Parsing - Outlines 〰️ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + + Skip to content + + +
+
+ + + +
+ + + + +
+ + +
+ +
+ + + + + + + + + +
+
+ + + +
+
+
+ + + + + + + +
+
+
+ + + +
+
+
+ + + +
+
+
+ + + +
+
+ + + + + + + +

Parsing

+ +
+ + + + +
+ + + +
+ + + + + + + + +
+ + + +

+ PartialIndenter + + +

+ + +
+

+ Bases: Indenter

+ + +

An Indenter that doesn't reset its state every time process is called.

+ +
+ Source code in outlines/fsm/parsing.py + 
785
+786
+787
+788
+789
+790
+791
+792
+793
+794
+795
+796
+797
+798
+799
+800
+801
+802
+803
+804
+805
+806
+807
+808
+809
+810
+811
+812
+813
+814
+815
+816
+817
+818
+819
+820
+821
+822
+823
+824
+825
+826
+827
+828
+829
+830
class PartialIndenter(Indenter):
+    """An `Indenter` that doesn't reset its state every time `process` is called."""
+
+    def process(self, stream):
+        return self._process(stream)
+
+    def _process(self, stream):
+        for token in stream:
+            # These were previously *after* the `yield`, but that makes the
+            # state tracking unnecessarily convoluted.
+            if token.type in self.OPEN_PAREN_types:
+                self.paren_level += 1
+            elif token.type in self.CLOSE_PAREN_types:
+                self.paren_level -= 1
+                if self.paren_level < 0:
+                    raise UnexpectedToken(token, [])
+
+            if token.type == self.NL_type:
+                yield from self.handle_NL(token)
+            else:
+                yield token
+
+        # TODO: What do we want to do here?
+        # while len(self.indent_level) > 1:
+        #     self.indent_level.pop()
+        #     yield Token(self.DEDENT_type, "")
+
+    def accepts_token_type(self, token_type):
+        if token_type in self.CLOSE_PAREN_types and self.paren_level - 1 < 0:
+            return False
+
+        # TODO:
+        # if token_type == self.NL_type and self.paren_level == 0:
+        #     ...
+        #     return False
+
+        return True
+
+    def __copy__(self):
+        res = type(self)()
+        res.paren_level = self.paren_level
+        res.indent_level = copy(self.indent_level)
+        return res
+
+    def __repr__(self):
+        return f"{type(self).__name__}(paren_level={self.paren_level!r}, indent_level={self.indent_level!r})"
+
+
+ + + +
+ + + + + + + + + + + +
+ +
+ + +
+ +
+ + + +

+ PartialParserState + + +

+ + +
+

+ Bases: ParserState

+ + +
+ Source code in outlines/fsm/parsing.py + 
345
+346
+347
+348
+349
+350
+351
+352
+353
+354
+355
+356
+357
+358
+359
+360
+361
+362
+363
+364
+365
+366
+367
+368
+369
+370
+371
+372
+373
+374
+375
+376
+377
+378
+379
+380
+381
+382
+383
+384
+385
+386
+387
+388
+389
+390
+391
+392
+393
+394
+395
+396
+397
+398
+399
+400
+401
+402
+403
+404
+405
+406
+407
+408
+409
+410
+411
+412
+413
+414
+415
+416
+417
+418
+419
+420
+421
+422
+423
+424
+425
+426
+427
+428
+429
+430
+431
+432
+433
+434
+435
+436
+437
+438
+439
+440
+441
+442
+443
+444
+445
+446
+447
+448
+449
+450
+451
+452
+453
+454
+455
+456
+457
+458
+459
class PartialParserState(ParserState):
+    __slots__ = "use_value_stack"
+
+    def __init__(
+        self,
+        parse_conf,
+        lexer,
+        state_stack=None,
+        value_stack=None,
+        use_value_stack=False,
+    ):
+        super().__init__(
+            parse_conf, lexer, state_stack=state_stack, value_stack=value_stack
+        )
+        self.use_value_stack = use_value_stack
+
+    def feed_token(self, token, is_end=False):
+        if token.type == "partial":
+            # If none of the potential terminals can transition, we need to know now
+            current_state = self.state_stack[-1]
+            current_lexer = get_contextual_lexer(self.lexer).lexers[current_state]
+
+            # We have to feed the token and determine whether or not at least
+            # one terminal is consistent with the stack; otherwise, we'll miss
+            # invalid REDUCE cases.
+            # TODO: We should track separate parses conditional on possible
+            # token/symbol types, then we can coherently reuse the following
+            # results instead of recomputing it later.
+            can_transition = False
+            for terminal_info in token.value.terminals_and_info:
+                if terminal_info.terminal_name not in current_lexer.ignore_types:
+                    test_token = Token.new_borrow_pos(
+                        terminal_info.terminal_name, "", token
+                    )
+
+                    stack = copy(self.state_stack)
+                    try:
+                        self.feed_token_no_stack(test_token, is_end=is_end)
+                        can_transition = True
+                        break
+                    except UnexpectedToken:
+                        continue
+                    finally:
+                        self.state_stack = stack
+                else:
+                    can_transition = True
+
+            if not can_transition:
+                expected = {
+                    s
+                    for s in self.parse_conf.states[current_state].keys()
+                    if s.isupper()
+                }
+                raise UnexpectedToken(
+                    token, expected, state=self, interactive_parser=None
+                )
+
+        elif self.use_value_stack:
+            super().feed_token(token, is_end=is_end)
+        else:
+            self.feed_token_no_stack(token, is_end=is_end)
+
+    def feed_token_no_stack(self, token, is_end=False):
+        """
+        This is a copy of `ParserState.feed_token` with all the value stack
+        steps removed.  Since we're not exactly parsing in order to obtain a
+        CST or anything similar, we can avoid the growing expense of tracking
+        the parse tree.
+        """
+        state_stack = self.state_stack
+        states = self.parse_conf.states
+        end_state = self.parse_conf.end_state
+
+        while True:
+            state = state_stack[-1]
+            try:
+                action, arg = states[state][token.type]
+            except KeyError:
+                expected = {s for s in states[state].keys() if s.isupper()}
+                raise UnexpectedToken(
+                    token, expected, state=self, interactive_parser=None
+                )
+
+            assert arg != end_state
+
+            if action is Shift:
+                # shift once and return
+                assert not is_end
+                state_stack.append(arg)
+                return
+            else:
+                # reduce+shift as many times as necessary
+                rule = arg
+                size = len(rule.expansion)
+                if size:
+                    del state_stack[-size:]
+
+                _action, new_state = states[state_stack[-1]][rule.origin.name]
+                assert _action is Shift
+                state_stack.append(new_state)
+
+                if is_end and state_stack[-1] == end_state:
+                    return
+
+    def __copy__(self):
+        return type(self)(
+            self.parse_conf,
+            copy(self.lexer),
+            copy(self.state_stack),
+            deepcopy(self.value_stack),
+            use_value_stack=self.use_value_stack,
+        )
+
+    def __repr__(self):
+        return f"{type(self).__name__}(lexer={self.lexer!r}, state_stack={self.state_stack!r})"
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ feed_token_no_stack(token, is_end=False) + +

+ + +
+ +

This is a copy of ParserState.feed_token with all the value stack +steps removed. Since we're not exactly parsing in order to obtain a +CST or anything similar, we can avoid the growing expense of tracking +the parse tree.

+ +
+ Source code in outlines/fsm/parsing.py + 
407
+408
+409
+410
+411
+412
+413
+414
+415
+416
+417
+418
+419
+420
+421
+422
+423
+424
+425
+426
+427
+428
+429
+430
+431
+432
+433
+434
+435
+436
+437
+438
+439
+440
+441
+442
+443
+444
+445
+446
+447
def feed_token_no_stack(self, token, is_end=False):
+    """
+    This is a copy of `ParserState.feed_token` with all the value stack
+    steps removed.  Since we're not exactly parsing in order to obtain a
+    CST or anything similar, we can avoid the growing expense of tracking
+    the parse tree.
+    """
+    state_stack = self.state_stack
+    states = self.parse_conf.states
+    end_state = self.parse_conf.end_state
+
+    while True:
+        state = state_stack[-1]
+        try:
+            action, arg = states[state][token.type]
+        except KeyError:
+            expected = {s for s in states[state].keys() if s.isupper()}
+            raise UnexpectedToken(
+                token, expected, state=self, interactive_parser=None
+            )
+
+        assert arg != end_state
+
+        if action is Shift:
+            # shift once and return
+            assert not is_end
+            state_stack.append(arg)
+            return
+        else:
+            # reduce+shift as many times as necessary
+            rule = arg
+            size = len(rule.expansion)
+            if size:
+                del state_stack[-size:]
+
+            _action, new_state = states[state_stack[-1]][rule.origin.name]
+            assert _action is Shift
+            state_stack.append(new_state)
+
+            if is_end and state_stack[-1] == end_state:
+                return
+
+
+
+ +
+ + + +
+ +
+ + +
+ +
+ + + +

+ PartialParsingFrontend + + +

+ + +
+

+ Bases: ParsingFrontend

+ + +
+ Source code in outlines/fsm/parsing.py + 
161
+162
+163
+164
+165
+166
+167
+168
+169
+170
+171
+172
+173
+174
+175
+176
+177
+178
+179
+180
+181
+182
+183
+184
+185
+186
+187
+188
+189
+190
+191
+192
+193
+194
+195
+196
+197
+198
+199
+200
+201
+202
+203
+204
+205
+206
+207
+208
+209
+210
+211
+212
+213
+214
+215
+216
+217
+218
+219
+220
+221
+222
+223
+224
+225
+226
+227
+228
+229
+230
+231
+232
+233
+234
+235
+236
+237
+238
+239
+240
+241
+242
+243
+244
+245
+246
+247
+248
+249
+250
+251
+252
+253
+254
+255
+256
+257
+258
+259
+260
+261
+262
+263
+264
+265
+266
+267
+268
+269
+270
+271
+272
+273
+274
+275
class PartialParsingFrontend(ParsingFrontend):
+    def __init__(self, lexer_conf, parser_conf, options, parser=None):
+        assert parser_conf.parser_type == "lalr"
+
+        options._plugins["LALR_Parser"] = PartialLALRParser
+        options._plugins["BasicLexer"] = PartialBasicLexer
+        options._plugins["ContextualLexer"] = PartialContextualLexer
+        options._plugins["LexerThread"] = PartialLexerThread
+
+        super().__init__(lexer_conf, parser_conf, options, parser=parser)
+
+        if lexer_conf.postlex:
+            self.lexer = PartialPostLexConnector(self.lexer.lexer, lexer_conf.postlex)
+
+        self._termset_fsm_info = None
+        self._symbols_to_states: Optional[
+            Dict[str, Set[Tuple[ParseStateType, Action]]]
+        ] = None
+        self._reverse_shifts: Optional[
+            Dict[ParseStateType, Dict[str, Set[ParseStateType]]]
+        ] = None
+        # self._state_transition_map: Optional[
+        #     Dict[Tuple[ParseStateType, str], Set[ParseStateType]]
+        # ] = None
+
+    def _compute_maps(
+        self,
+    ):
+        """Compute state transition and symbols-to-states maps."""
+        self._reverse_shifts = {}
+        self._symbols_to_states = {}
+
+        parse_table = self.parser.parser.parse_table
+
+        for from_state, symbols_to_ops in parse_table.states.items():
+            for symbol, op in symbols_to_ops.items():
+                if op[0] == Shift:
+                    symbols_to_from_states = self._reverse_shifts.setdefault(op[1], {})
+                    symbols_to_from_states.setdefault(symbol, set()).add(from_state)
+                self._symbols_to_states.setdefault(symbol, set()).add((from_state, op))
+
+        # # TODO: This approach is very wasteful.
+        # context_lexer = get_contextual_lexer(self)
+        # self._state_transition_map = {}
+        #
+        # for from_state, transitions in parse_table.states.items():
+        #     for symbol, action in transitions.items():
+        #         # TODO: Filter non-terminals
+        #         if symbol not in context_lexer.root_lexer.terminals_by_name:
+        #             continue
+        #
+        #         if action[0] is Shift:
+        #             self._state_transition_map.setdefault(
+        #                 (from_state, symbol), set()
+        #             ).add(action[1])
+        #             continue
+        #
+        #         antecedent_state_seqs = parse_to_terminal(self, [(from_state,)], symbol)
+        #
+        #         for antecedent_state_seq in antecedent_state_seqs:
+        #             antecedent_state = antecedent_state_seq[-1]
+        #             self._state_transition_map.setdefault(
+        #                 (from_state, symbol), set()
+        #             ).add(antecedent_state)
+
+    def _compute_termset_fsm_info(self):
+        """Collect and return information about terminal symbol sets and their FSMs.
+
+        Terminal symbol sets (or "termsets") are ordered sequences of terminal
+        symbols that are used by each parser state.  Associated with each is a
+        collection of FSMs for each terminal and a single parse state FSM that is
+        the union of each terminal's FSM.
+
+        This constructs a list of tuples containing the termset, the set of
+        parse states that use the termsets, parse state FSMs, and information
+        mapping the components of the parse state FSMs to their terminal symbol
+        FSMs.
+
+        """
+        context_lexer = get_contextual_lexer(self)
+        termsets_to_fsms = {}
+        termsets_to_parse_states: Dict[Tuple[str, ...], Set[ParseStateType]] = {}
+        for parse_state, lexer in context_lexer.lexers.items():
+            scanner = lexer.scanner
+            key = tuple(term.name for term in scanner.terminals)
+            termsets_to_fsms[key] = (scanner.fsm, scanner.fsms_to_trans_finals)
+            termsets_to_parse_states.setdefault(key, set()).add(parse_state)
+
+        self._termset_fsm_info = [
+            (
+                termset,
+                frozenset(termsets_to_parse_states[termset]),
+                fsm,
+                fsms_to_trans_finals,
+            )
+            for termset, (fsm, fsms_to_trans_finals) in termsets_to_fsms.items()
+        ]
+
+    @property
+    def termset_fsm_info(self):
+        if self._termset_fsm_info is None:
+            self._compute_termset_fsm_info()
+        return self._termset_fsm_info
+
+    @property
+    def symbols_to_states(self):
+        if self._symbols_to_states is None:
+            self._compute_maps()
+        return self._symbols_to_states
+
+    @property
+    def reverse_shifts(self):
+        if self._reverse_shifts is None:
+            self._compute_maps()
+        return self._reverse_shifts
+
+
+ + + +
+ + + + + + + + + + + +
+ +
+ + +
+ +
+ + + +

+ PartialScanner + + +

+ + +
+

+ Bases: Scanner

+ + +
+ Source code in outlines/fsm/parsing.py + 
511
+512
+513
+514
+515
+516
+517
+518
+519
+520
+521
+522
+523
+524
+525
+526
+527
+528
+529
+530
+531
+532
+533
+534
+535
+536
+537
+538
+539
+540
+541
+542
+543
+544
+545
+546
+547
+548
+549
+550
+551
+552
+553
+554
+555
+556
+557
+558
+559
+560
+561
+562
+563
+564
+565
+566
+567
+568
+569
+570
+571
+572
+573
+574
+575
+576
+577
+578
+579
+580
+581
+582
+583
+584
+585
+586
+587
class PartialScanner(Scanner):
+    @classmethod
+    @lru_cache
+    def construct_terminal_fsm(cls, terminal):
+        # TODO: This should really be done at the lexer/parser level so that
+        # the lifetime of these objects is tied to the parser itself.
+        regex_str = terminal.pattern.to_regexp()
+        pattern = interegular.parse_pattern(regex_str)
+        fsm, _ = make_deterministic_fsm(pattern.to_fsm().reduce())
+        return fsm, pattern.prefix_postfix
+
+    def __init__(self, terminals, g_regex_flags, re_, use_bytes, match_whole=False):
+        self.terminals = terminals
+        self.g_regex_flags = g_regex_flags
+        self.use_bytes = use_bytes
+        self.match_whole = match_whole
+        self.allowed_types = {t.name for t in self.terminals}
+        self._mres = None
+
+        fsms = []
+        for t in self.terminals:
+            fsm, prefix_postfix = self.construct_terminal_fsm(t)
+
+            # TODO FIXME: We don't support this right now.
+            assert prefix_postfix == (0, 0)
+
+            fsms.append(fsm)
+
+        self.fsm, self.fsms_to_trans_finals = fsm_union(fsms)
+
+    def get_terminals_info(
+        self, fsm_state_seq
+    ) -> Tuple[Tuple[PartialTerminalInfo, ...], Tuple[PartialTerminalInfo, ...]]:
+        """Get the possible terminal symbols for an FSM state sequence."""
+        terminals_and_info: Tuple[PartialTerminalInfo, ...] = ()
+        final_terminals_and_info: Tuple[PartialTerminalInfo, ...] = ()
+        for i, (fsm_id, fsm_reads_more, in_final) in enumerate(
+            get_sub_fsms_from_seq(fsm_state_seq, self.fsms_to_trans_finals)
+        ):
+            terminal_name = self.terminals[fsm_id].name
+            info = PartialTerminalInfo(i, terminal_name, fsm_reads_more, in_final)
+            terminals_and_info += (info,)
+            if in_final:
+                final_terminals_and_info += (info,)
+
+        return terminals_and_info, final_terminals_and_info
+
+    def match(self, text, pos, last_fsm_state_seq: Optional[Tuple[int, ...]] = None):
+        """Determine an FSM match over `text` starting at `pos` and continuing `last_fsm_state_seq`."""
+
+        start_pos = pos
+
+        if last_fsm_state_seq:
+            assert len(last_fsm_state_seq) > 1
+            start_pos += len(last_fsm_state_seq) - 1
+            start_state = last_fsm_state_seq[-1]
+        else:
+            start_state = self.fsm.initial
+
+        text_part = text[start_pos:]
+
+        state_seq = walk_fsm(
+            self.fsm,
+            text_part,
+            start_state,
+            full_match=self.match_whole,
+        )
+
+        if not state_seq:
+            return None
+
+        if last_fsm_state_seq:
+            res = last_fsm_state_seq + tuple(state_seq)
+        else:
+            res = (start_state,) + tuple(state_seq)
+
+        return res
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ get_terminals_info(fsm_state_seq) + +

+ + +
+ +

Get the possible terminal symbols for an FSM state sequence.

+ +
+ Source code in outlines/fsm/parsing.py + 
541
+542
+543
+544
+545
+546
+547
+548
+549
+550
+551
+552
+553
+554
+555
+556
def get_terminals_info(
+    self, fsm_state_seq
+) -> Tuple[Tuple[PartialTerminalInfo, ...], Tuple[PartialTerminalInfo, ...]]:
+    """Get the possible terminal symbols for an FSM state sequence."""
+    terminals_and_info: Tuple[PartialTerminalInfo, ...] = ()
+    final_terminals_and_info: Tuple[PartialTerminalInfo, ...] = ()
+    for i, (fsm_id, fsm_reads_more, in_final) in enumerate(
+        get_sub_fsms_from_seq(fsm_state_seq, self.fsms_to_trans_finals)
+    ):
+        terminal_name = self.terminals[fsm_id].name
+        info = PartialTerminalInfo(i, terminal_name, fsm_reads_more, in_final)
+        terminals_and_info += (info,)
+        if in_final:
+            final_terminals_and_info += (info,)
+
+    return terminals_and_info, final_terminals_and_info
+
+
+
+ +
+ + +
+ + + +

+ match(text, pos, last_fsm_state_seq=None) + +

+ + +
+ +

Determine an FSM match over text starting at pos and continuing last_fsm_state_seq.

+ +
+ Source code in outlines/fsm/parsing.py + 
558
+559
+560
+561
+562
+563
+564
+565
+566
+567
+568
+569
+570
+571
+572
+573
+574
+575
+576
+577
+578
+579
+580
+581
+582
+583
+584
+585
+586
+587
def match(self, text, pos, last_fsm_state_seq: Optional[Tuple[int, ...]] = None):
+    """Determine an FSM match over `text` starting at `pos` and continuing `last_fsm_state_seq`."""
+
+    start_pos = pos
+
+    if last_fsm_state_seq:
+        assert len(last_fsm_state_seq) > 1
+        start_pos += len(last_fsm_state_seq) - 1
+        start_state = last_fsm_state_seq[-1]
+    else:
+        start_state = self.fsm.initial
+
+    text_part = text[start_pos:]
+
+    state_seq = walk_fsm(
+        self.fsm,
+        text_part,
+        start_state,
+        full_match=self.match_whole,
+    )
+
+    if not state_seq:
+        return None
+
+    if last_fsm_state_seq:
+        res = last_fsm_state_seq + tuple(state_seq)
+    else:
+        res = (start_state,) + tuple(state_seq)
+
+    return res
+
+
+
+ +
+ + + +
+ +
+ + +
+ + + +
+ + + +

+ terminals_to_fsms(lp) + +

+ + +
+ +

Construct a dict mapping terminal symbol names to their finite state machines.

+ +
+ Source code in outlines/fsm/parsing.py + 
849
+850
+851
+852
+853
+854
+855
+856
+857
+858
+859
+860
+861
+862
+863
def terminals_to_fsms(lp: PartialLark) -> Dict[str, FSM]:
+    """Construct a ``dict`` mapping terminal symbol names to their finite state machines."""
+
+    symbol_names_and_fsms = {}
+    for terminal in lp.terminals:
+        pattern = interegular.parse_pattern(terminal.pattern.to_regexp())
+        # TODO: Use `pyparser.terminals[0].pattern.flags`?
+        try:
+            fsm, _ = make_deterministic_fsm(pattern.to_fsm().reduce())
+        except Unsupported:
+            fsm = None
+
+        symbol_names_and_fsms[terminal.name] = fsm
+
+    return symbol_names_and_fsms
+
+
+
+ +
+ + + +
+ +
+ +
+ + + + + + + + + + + + + + + + + + + + +
+
+ + + +
+ +
+ + + +
+
+
+
+ + + + + + + + + + \ No newline at end of file diff --git a/api/prompts/index.html b/api/prompts/index.html new file mode 100644 index 000000000..c6a0dfad3 --- /dev/null +++ b/api/prompts/index.html @@ -0,0 +1,3160 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + Prompts - Outlines 〰️ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + + Skip to content + + +
+
+ + + +
+ + + + +
+ + +
+ +
+ + + + + + + + + +
+
+ + + +
+
+
+ + + + + + + +
+
+
+ + + +
+
+
+ + + +
+
+
+ + + +
+
+ + + + + + + +

Prompts

+ +
+ + + + +
+ + + +
+ + + + + + + + +
+ + + +

+ Prompt + + + + dataclass + + +

+ + +
+ + +

Represents a prompt function.

+

We return a Prompt class instead of a simple function so the +template defined in prompt functions can be accessed.

+ +
+ Source code in outlines/prompts.py + 
13
+14
+15
+16
+17
+18
+19
+20
+21
+22
+23
+24
+25
+26
+27
+28
+29
+30
+31
+32
+33
+34
+35
+36
+37
+38
+39
+40
+41
@dataclass
+class Prompt:
+    """Represents a prompt function.
+
+    We return a `Prompt` class instead of a simple function so the
+    template defined in prompt functions can be accessed.
+
+    """
+
+    template: str
+    signature: inspect.Signature
+
+    def __post_init__(self):
+        self.parameters: List[str] = list(self.signature.parameters.keys())
+
+    def __call__(self, *args, **kwargs) -> str:
+        """Render and return the template.
+
+        Returns
+        -------
+        The rendered template as a Python ``str``.
+
+        """
+        bound_arguments = self.signature.bind(*args, **kwargs)
+        bound_arguments.apply_defaults()
+        return render(self.template, **bound_arguments.arguments)
+
+    def __str__(self):
+        return self.template
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ __call__(*args, **kwargs) + +

+ + +
+ +

Render and return the template.

+
Returns
+

The rendered template as a Python str.

+ +
+ Source code in outlines/prompts.py + 
28
+29
+30
+31
+32
+33
+34
+35
+36
+37
+38
def __call__(self, *args, **kwargs) -> str:
+    """Render and return the template.
+
+    Returns
+    -------
+    The rendered template as a Python ``str``.
+
+    """
+    bound_arguments = self.signature.bind(*args, **kwargs)
+    bound_arguments.apply_defaults()
+    return render(self.template, **bound_arguments.arguments)
+
+
+
+ +
+ + + +
+ +
+ + +
+ + + +
+ + + +

+ get_fn_description(fn) + +

+ + +
+ +

Returns the first line of a callable's docstring.

+ +
+ Source code in outlines/prompts.py + 
229
+230
+231
+232
+233
+234
+235
+236
+237
+238
+239
+240
def get_fn_description(fn: Callable):
+    """Returns the first line of a callable's docstring."""
+    if not callable(fn):
+        raise TypeError("The `description` filter only applies to callables.")
+
+    docstring = inspect.getdoc(fn)
+    if docstring is None:
+        description = ""
+    else:
+        description = docstring.split("\n")[0].strip()
+
+    return description
+
+
+
+ +
+ + +
+ + + +

+ get_fn_name(fn) + +

+ + +
+ +

Returns the name of a callable.

+ +
+ Source code in outlines/prompts.py + 
216
+217
+218
+219
+220
+221
+222
+223
+224
+225
+226
def get_fn_name(fn: Callable):
+    """Returns the name of a callable."""
+    if not callable(fn):
+        raise TypeError("The `name` filter only applies to callables.")
+
+    if not hasattr(fn, "__name__"):
+        name = type(fn).__name__
+    else:
+        name = fn.__name__
+
+    return name
+
+
+
+ +
+ + +
+ + + +

+ get_fn_signature(fn) + +

+ + +
+ +

Return the signature of a callable.

+ +
+ Source code in outlines/prompts.py + 
258
+259
+260
+261
+262
+263
+264
+265
+266
+267
+268
+269
+270
def get_fn_signature(fn: Callable):
+    """Return the signature of a callable."""
+    if not callable(fn):
+        raise TypeError("The `source` filter only applies to callables.")
+
+    source = textwrap.dedent(inspect.getsource(fn))
+    re_search = re.search(re.compile(r"\(([^)]+)\)"), source)
+    if re_search is None:
+        signature = ""
+    else:
+        signature = re_search.group(1)
+
+    return signature
+
+
+
+ +
+ + +
+ + + +

+ get_fn_source(fn) + +

+ + +
+ +

Return the source code of a callable.

+ +
+ Source code in outlines/prompts.py + 
243
+244
+245
+246
+247
+248
+249
+250
+251
+252
+253
+254
+255
def get_fn_source(fn: Callable):
+    """Return the source code of a callable."""
+    if not callable(fn):
+        raise TypeError("The `source` filter only applies to callables.")
+
+    source = textwrap.dedent(inspect.getsource(fn))
+    re_search = re.search(re.compile(r"(\bdef\b.*)", re.DOTALL), source)
+    if re_search is not None:
+        source = re_search.group(0)
+    else:
+        raise TypeError("Could not read the function's source code")
+
+    return source
+
+
+
+ +
+ + +
+ + + +

+ get_schema_dict(model) + +

+ + +
+ +

Return a pretty-printed dictionary

+ +
+ Source code in outlines/prompts.py + 
280
+281
+282
+283
@get_schema.register(dict)
+def get_schema_dict(model: Dict):
+    """Return a pretty-printed dictionary"""
+    return json.dumps(model, indent=2)
+
+
+
+ +
+ + +
+ + + +

+ get_schema_pydantic(model) + +

+ + +
+ +

Return the schema of a Pydantic model.

+ +
+ Source code in outlines/prompts.py + 
286
+287
+288
+289
+290
+291
+292
+293
+294
+295
+296
+297
+298
+299
+300
+301
+302
@get_schema.register(type(BaseModel))
+def get_schema_pydantic(model: Type[BaseModel]):
+    """Return the schema of a Pydantic model."""
+    if not type(model) == type(BaseModel):
+        raise TypeError("The `schema` filter only applies to Pydantic models.")
+
+    if hasattr(model, "model_json_schema"):
+        def_key = "$defs"
+        raw_schema = model.model_json_schema()
+    else:  # pragma: no cover
+        def_key = "definitions"
+        raw_schema = model.schema()
+
+    definitions = raw_schema.get(def_key, None)
+    schema = parse_pydantic_schema(raw_schema, definitions)
+
+    return json.dumps(schema, indent=2)
+
+
+
+ +
+ + +
+ + + +

+ parse_pydantic_schema(raw_schema, definitions) + +

+ + +
+ +

Parse the output of Basemodel.[schema|model_json_schema]().

+

This recursively follows the references to other schemas in case +of nested models. Other schemas are stored under the "definitions" +key in the schema of the top-level model.

+ +
+ Source code in outlines/prompts.py + 
305
+306
+307
+308
+309
+310
+311
+312
+313
+314
+315
+316
+317
+318
+319
+320
+321
+322
+323
+324
+325
def parse_pydantic_schema(raw_schema, definitions):
+    """Parse the output of `Basemodel.[schema|model_json_schema]()`.
+
+    This recursively follows the references to other schemas in case
+    of nested models. Other schemas are stored under the "definitions"
+    key in the schema of the top-level model.
+
+    """
+    simple_schema = {}
+    for name, value in raw_schema["properties"].items():
+        if "description" in value:
+            simple_schema[name] = value["description"]
+        elif "$ref" in value:
+            refs = value["$ref"].split("/")
+            simple_schema[name] = parse_pydantic_schema(
+                definitions[refs[2]], definitions
+            )
+        else:
+            simple_schema[name] = f"<{name}>"
+
+    return simple_schema
+
+
+
+ +
+ + +
+ + + +

+ prompt(fn) + +

+ + +
+ +

Decorate a function that contains a prompt template.

+

This allows to define prompts in the docstring of a function and simplify their +manipulation by providing some degree of encapsulation. It uses the render +function internally to render templates.

+
+
+
+

import outlines

+

@outlines.prompt +def build_prompt(question): +... "I have a ${question}" +... +prompt = build_prompt("How are you?")

+
+
+
+

This API can also be helpful in an "agent" context where parts of the prompt +are set when the agent is initialized and never modified later. In this situation +we can partially apply the prompt function at initialization.

+
+
+
+

import outlines +import functools as ft +... +@outlines.prompt +... def solve_task(name: str, objective: str, task: str): +... '''Your name is {{name}}. +.. Your overall objective is to {{objective}}. +... Please solve the following task: {{task}} +... ''' +... +hal = ft.partial(solve_task, "HAL", "Travel to Jupiter")

+
+
+
+

Returns

+

A Prompt callable class which will render the template when called.

+ +
+ Source code in outlines/prompts.py + 
44
+45
+46
+47
+48
+49
+50
+51
+52
+53
+54
+55
+56
+57
+58
+59
+60
+61
+62
+63
+64
+65
+66
+67
+68
+69
+70
+71
+72
+73
+74
+75
+76
+77
+78
+79
+80
+81
+82
+83
+84
+85
+86
+87
+88
+89
+90
+91
def prompt(fn: Callable) -> Prompt:
+    """Decorate a function that contains a prompt template.
+
+    This allows to define prompts in the docstring of a function and simplify their
+    manipulation by providing some degree of encapsulation. It uses the `render`
+    function internally to render templates.
+
+    >>> import outlines
+    >>>
+    >>> @outlines.prompt
+    >>> def build_prompt(question):
+    ...    "I have a ${question}"
+    ...
+    >>> prompt = build_prompt("How are you?")
+
+    This API can also be helpful in an "agent" context where parts of the prompt
+    are set when the agent is initialized and never modified later. In this situation
+    we can partially apply the prompt function at initialization.
+
+    >>> import outlines
+    >>> import functools as ft
+    ...
+    >>> @outlines.prompt
+    ... def solve_task(name: str, objective: str, task: str):
+    ...     '''Your name is {{name}}.
+    ..      Your overall objective is to {{objective}}.
+    ...     Please solve the following task: {{task}}
+    ...     '''
+    ...
+    >>> hal = ft.partial(solve_task, "HAL", "Travel to Jupiter")
+
+    Returns
+    -------
+    A `Prompt` callable class which will render the template when called.
+
+    """
+
+    signature = inspect.signature(fn)
+
+    # The docstring contains the template that will be rendered to be used
+    # as a prompt to the language model.
+    docstring = fn.__doc__
+    if docstring is None:
+        raise TypeError("Could not find a template in the function's docstring.")
+
+    template = cast(str, docstring)
+
+    return Prompt(template, signature)
+
+
+
+ +
+ + +
+ + + +

+ render(template, **values) + +

+ + +
+ +

Parse a Jinaj2 template and translate it into an Outlines graph.

+

This function removes extra whitespaces and linebreaks from templates to +allow users to enter prompts more naturally than if they used Python's +constructs directly. See the examples for a detailed explanation.

+

Examples

+

Outlines follow Jinja2's syntax

+
+
+
+

import outlines +outline = outlines.render("I like {{food}} and {{sport}}", food="tomatoes", sport="tennis") +I like tomatoes and tennis

+
+
+
+

If the first line of the template is empty, render removes it

+
+
+
+

from outlines import render

+

tpl = ''' +... A new string''' +tpl +... '\nA new string' +render(tpl) +... 'a new string'

+
+
+
+

Similarly, render ignores linebreaks introduced by placing the closing quotes +underneath the text:

+
+
+
+

tpl = ''' +... A new string +... ''' +tpl +... '\nA new string\n' +render(tpl) +... 'A new string'

+
+
+
+

If you want to insert a linebreak at the end of the rendered template, you will +need to leave an empty line at the end of the template:

+
+
+
+

tpl = ''' +... A new string +... +... ''' +tpl +... '\nA new string\n\n' +render(tpl) +... 'A new string\n'

+
+
+
+

render removes the identation in docstrings. This is particularly important +when using prompt functions

+
+
+
+

tpl = ''' +... a string +... and another string''' +tpl +... '\n a string\n and another string' +render(tpl) +... 'a string\nand another string'

+
+
+
+

The indentation of the first line is assumed to be the same as the second line's

+
+
+
+

tpl = '''a string +... and another''' +tpl +... 'a string\n and another' +render(tpl) +... 'a string\nand another'

+
+
+
+

To get a different indentation for the first and the second line, we can start the +prompt on the string's second line:

+
+
+
+

tpl = ''' +... First line +... Second line''' +render(tpl) +... 'First Line\n Second Line'

+
+
+
+

Parameters

+

template + A string that contains a template written with the Jinja2 syntax. +**values + Map from the variables in the template to their value.

+

Returns

+

A string that contains the rendered template.

+ +
+ Source code in outlines/prompts.py + 
 94
+ 95
+ 96
+ 97
+ 98
+ 99
+100
+101
+102
+103
+104
+105
+106
+107
+108
+109
+110
+111
+112
+113
+114
+115
+116
+117
+118
+119
+120
+121
+122
+123
+124
+125
+126
+127
+128
+129
+130
+131
+132
+133
+134
+135
+136
+137
+138
+139
+140
+141
+142
+143
+144
+145
+146
+147
+148
+149
+150
+151
+152
+153
+154
+155
+156
+157
+158
+159
+160
+161
+162
+163
+164
+165
+166
+167
+168
+169
+170
+171
+172
+173
+174
+175
+176
+177
+178
+179
+180
+181
+182
+183
+184
+185
+186
+187
+188
+189
+190
+191
+192
+193
+194
+195
+196
+197
+198
+199
+200
+201
+202
+203
+204
+205
+206
+207
+208
+209
+210
+211
+212
+213
def render(template: str, **values: Optional[Dict[str, Any]]) -> str:
+    r"""Parse a Jinaj2 template and translate it into an Outlines graph.
+
+    This function removes extra whitespaces and linebreaks from templates to
+    allow users to enter prompts more naturally than if they used Python's
+    constructs directly. See the examples for a detailed explanation.
+
+    Examples
+    --------
+
+    Outlines follow Jinja2's syntax
+
+    >>> import outlines
+    >>> outline = outlines.render("I like {{food}} and {{sport}}", food="tomatoes", sport="tennis")
+    I like tomatoes and tennis
+
+    If the first line of the template is empty, `render` removes it
+
+    >>> from outlines import render
+    >>>
+    >>> tpl = '''
+    ... A new string'''
+    >>> tpl
+    ... '\nA new string'
+    >>> render(tpl)
+    ... 'a new string'
+
+    Similarly, `render` ignores linebreaks introduced by placing the closing quotes
+    underneath the text:
+
+    >>> tpl = '''
+    ... A new string
+    ... '''
+    >>> tpl
+    ... '\nA new string\n'
+    >>> render(tpl)
+    ... 'A new string'
+
+    If you want to insert a linebreak at the end of the rendered template, you will
+    need to leave an empty line at the end of the template:
+
+    >>> tpl = '''
+    ... A new string
+    ...
+    ... '''
+    >>> tpl
+    ... '\nA new string\n\n'
+    >>> render(tpl)
+    ... 'A new string\n'
+
+    `render` removes the identation in docstrings. This is particularly important
+    when using prompt functions
+
+    >>> tpl = '''
+    ...    a string
+    ...    and another string'''
+    >>> tpl
+    ... '\n   a string\n   and another string'
+    >>> render(tpl)
+    ... 'a string\nand another string'
+
+    The indentation of the first line is assumed to be the same as the second line's
+
+    >>> tpl = '''a string
+    ...     and another'''
+    >>> tpl
+    ... 'a string\n    and another'
+    >>> render(tpl)
+    ... 'a string\nand another'
+
+    To get a different indentation for the first and the second line, we can start the
+    prompt on the string's second line:
+
+    >>> tpl = '''
+    ... First line
+    ...   Second line'''
+    >>> render(tpl)
+    ... 'First Line\n  Second Line'
+
+    Parameters
+    ----------
+    template
+        A string that contains a template written with the Jinja2 syntax.
+    **values
+        Map from the variables in the template to their value.
+
+    Returns
+    -------
+    A string that contains the rendered template.
+
+    """
+    # Dedent, and remove extra linebreak
+    cleaned_template = inspect.cleandoc(template)
+
+    # Add linebreak if there were any extra linebreaks that
+    # `cleandoc` would have removed
+    ends_with_linebreak = template.replace(" ", "").endswith("\n\n")
+    if ends_with_linebreak:
+        cleaned_template += "\n"
+
+    # Remove extra whitespaces, except those that immediately follow a newline symbol.
+    # This is necessary to avoid introducing whitespaces after backslash `\` characters
+    # used to continue to the next line without linebreak.
+    cleaned_template = re.sub(r"(?![\r\n])(\b\s+)", " ", cleaned_template)
+
+    env = Environment(
+        trim_blocks=True,
+        lstrip_blocks=True,
+        keep_trailing_newline=True,
+        undefined=StrictUndefined,
+    )
+    env.filters["name"] = get_fn_name
+    env.filters["description"] = get_fn_description
+    env.filters["source"] = get_fn_source
+    env.filters["signature"] = get_fn_signature
+    env.filters["schema"] = get_schema
+
+    jinja_template = env.from_string(cleaned_template)
+
+    return jinja_template.render(**values)
+
+
+
+ +
+ + + +
+ +
+ +
+ + + + + + + + + + + + + + + + + + + + +
+
+ + + +
+ +
+ + + +
+
+
+
+ + + + + + + + + + \ No newline at end of file diff --git a/api/regex/index.html b/api/regex/index.html new file mode 100644 index 000000000..3e5ddd4b3 --- /dev/null +++ b/api/regex/index.html @@ -0,0 +1,1964 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + Regex - Outlines 〰️ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + + Skip to content + + +
+
+ + + +
+ + + + +
+ + +
+ +
+ + + + + + + + + +
+
+ + + +
+
+
+ + + + + + + +
+
+
+ + + +
+
+
+ + + +
+
+
+ + + +
+
+ + + + + + + +

Regex

+ +
+ + + + +
+ + + +
+ + + + + + + + + + +
+ + + +

+ regex(model, regex_str, sampler=multinomial()) + +

+ + +
+ +

Generate structured text in the language of a regular expression.

+

Parameters

+

model: + An instance of Transformer that represents a model from the + transformers library. +regex_str: + The regular expression that the output must follow. +sampler: + The sampling algorithm to use to generate token ids from the logits + distribution.

+

Returns

+

A SequenceGenerator instance that generates text constrained by the +regular expression.

+ +
+ Source code in outlines/generate/regex.py + 
14
+15
+16
+17
+18
+19
+20
+21
+22
+23
+24
+25
+26
+27
+28
+29
+30
+31
+32
+33
+34
+35
+36
+37
+38
+39
+40
@singledispatch
+def regex(model, regex_str: str, sampler: Sampler = multinomial()):
+    """Generate structured text in the language of a regular expression.
+
+    Parameters
+    ----------
+    model:
+        An instance of `Transformer` that represents a model from the
+        `transformers` library.
+    regex_str:
+        The regular expression that the output must follow.
+    sampler:
+        The sampling algorithm to use to generate token ids from the logits
+        distribution.
+
+    Returns
+    -------
+    A `SequenceGenerator` instance that generates text constrained by the
+    regular expression.
+
+    """
+    fsm = RegexFSM(regex_str, model.tokenizer)
+
+    device = model.device
+    generator = SequenceGenerator(fsm, model, sampler, device)
+
+    return generator
+
+
+
+ +
+ + + +
+ +
+ +
+ + + + + + + + + + + + + + + + + + + + +
+
+ + + +
+ +
+ + + +
+
+
+
+ + + + + + + + + + \ No newline at end of file diff --git a/api/samplers/index.html b/api/samplers/index.html new file mode 100644 index 000000000..dc3d059e1 --- /dev/null +++ b/api/samplers/index.html @@ -0,0 +1,3442 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + Samplers - Outlines 〰️ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + + Skip to content + + +
+
+ + + +
+ + + + +
+ + +
+ +
+ + + + + + + + + +
+
+ + + +
+
+
+ + + + + + + +
+
+
+ + + +
+
+
+ + + +
+
+
+ + + +
+
+ + + + + + + +

Samplers

+ +
+ + + + +
+ + + +
+ + + + + + + + +
+ + + +

+ BeamSearchSampler + + +

+ + +
+ + +

Beam Search sampling algorithm.

+

Attributes

+

samples + The number of samples taken for each input sequence.

+ +
+ Source code in outlines/samplers.py + 
235
+236
+237
+238
+239
+240
+241
+242
+243
+244
+245
+246
+247
+248
+249
+250
+251
+252
+253
+254
+255
+256
+257
+258
+259
+260
+261
+262
+263
+264
+265
+266
+267
+268
+269
+270
+271
+272
+273
+274
+275
+276
+277
+278
+279
+280
+281
+282
+283
+284
+285
+286
+287
+288
+289
+290
+291
+292
+293
+294
+295
+296
+297
+298
+299
+300
+301
+302
+303
+304
+305
+306
+307
class BeamSearchSampler:
+    """Beam Search sampling algorithm.
+
+    Attributes
+    ----------
+    samples
+        The number of samples taken for each input sequence.
+
+    """
+
+    def __init__(self, beams: int = 1):
+        self.samples = beams
+
+    def __call__(
+        self,
+        next_token_logits: torch.DoubleTensor,
+        sequence_weights: torch.DoubleTensor,
+        _,
+    ) -> Tuple[torch.DoubleTensor, torch.DoubleTensor, torch.DoubleTensor]:
+        """Call the beam search sampler.
+
+        Parameters
+        ----------
+        next_token_logits
+            A tensor of shape ``(n_seqs, vocab_size,)`` that represents the
+            probability distribution of the next token over the vocabulary.
+        sequence_weights
+            A tensor of shape ``(n_seqs,)`` that represents the cumulative
+            weight of each sequence.
+        rng
+            A random number generator.
+
+        Returns
+        -------
+        A tuple with an array that contains the ids of the sampled tokens of
+        shape ``(n_seqs, 1)``, an array that contains the ancestors of each
+        sampled id of shape ``(n_seqs,)`` and an array that contains the updated
+        cumulative weights of each sequence of shape ``(n_seqs,)``.
+
+        """
+        logprobs = torch.nn.functional.log_softmax(next_token_logits, dim=-1)
+        weights = logprobs + sequence_weights.unsqueeze(1).expand_as(next_token_logits)
+
+        # Flatten scores to (n_batch, n_samples * vocab_size)
+        # and find the top-k weights for each batch.
+        batch_size = next_token_logits.shape[0] // self.samples
+        vocab_size = next_token_logits.shape[-1]
+        weights = weights.view(batch_size, self.samples * vocab_size)
+
+        # If the weights are all equal to 0 we are at the beginning of the search
+        # and thus only need to sample from one set of token logits for each
+        # batch.
+        if torch.all(sequence_weights == 0):
+            weights = weights[:, :vocab_size]
+
+        weights, indices = torch.topk(
+            weights, self.samples, dim=1, largest=True, sorted=True
+        )
+
+        ancestors = torch.div(indices, vocab_size, rounding_mode="floor")
+        next_token_ids = indices % vocab_size
+
+        # Re-shape the weights, next_token_ids and ancestors to (n_batch * n_samples, 1)
+        first_batch_idx = torch.arange(
+            0, batch_size * self.samples, self.samples, device=next_token_logits.device
+        ).unsqueeze(1)
+        ancestors = ancestors + first_batch_idx
+
+        ancestors = ancestors.view(self.samples * batch_size)
+        weights = weights.view(self.samples * batch_size)
+        next_token_ids = next_token_ids.view(self.samples * batch_size, 1)
+
+        return next_token_ids, ancestors, weights
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ __call__(next_token_logits, sequence_weights, _) + +

+ + +
+ +

Call the beam search sampler.

+
Parameters
+

next_token_logits + A tensor of shape (n_seqs, vocab_size,) that represents the + probability distribution of the next token over the vocabulary. +sequence_weights + A tensor of shape (n_seqs,) that represents the cumulative + weight of each sequence. +rng + A random number generator.

+
Returns
+

A tuple with an array that contains the ids of the sampled tokens of +shape (n_seqs, 1), an array that contains the ancestors of each +sampled id of shape (n_seqs,) and an array that contains the updated +cumulative weights of each sequence of shape (n_seqs,).

+ +
+ Source code in outlines/samplers.py + 
248
+249
+250
+251
+252
+253
+254
+255
+256
+257
+258
+259
+260
+261
+262
+263
+264
+265
+266
+267
+268
+269
+270
+271
+272
+273
+274
+275
+276
+277
+278
+279
+280
+281
+282
+283
+284
+285
+286
+287
+288
+289
+290
+291
+292
+293
+294
+295
+296
+297
+298
+299
+300
+301
+302
+303
+304
+305
+306
+307
def __call__(
+    self,
+    next_token_logits: torch.DoubleTensor,
+    sequence_weights: torch.DoubleTensor,
+    _,
+) -> Tuple[torch.DoubleTensor, torch.DoubleTensor, torch.DoubleTensor]:
+    """Call the beam search sampler.
+
+    Parameters
+    ----------
+    next_token_logits
+        A tensor of shape ``(n_seqs, vocab_size,)`` that represents the
+        probability distribution of the next token over the vocabulary.
+    sequence_weights
+        A tensor of shape ``(n_seqs,)`` that represents the cumulative
+        weight of each sequence.
+    rng
+        A random number generator.
+
+    Returns
+    -------
+    A tuple with an array that contains the ids of the sampled tokens of
+    shape ``(n_seqs, 1)``, an array that contains the ancestors of each
+    sampled id of shape ``(n_seqs,)`` and an array that contains the updated
+    cumulative weights of each sequence of shape ``(n_seqs,)``.
+
+    """
+    logprobs = torch.nn.functional.log_softmax(next_token_logits, dim=-1)
+    weights = logprobs + sequence_weights.unsqueeze(1).expand_as(next_token_logits)
+
+    # Flatten scores to (n_batch, n_samples * vocab_size)
+    # and find the top-k weights for each batch.
+    batch_size = next_token_logits.shape[0] // self.samples
+    vocab_size = next_token_logits.shape[-1]
+    weights = weights.view(batch_size, self.samples * vocab_size)
+
+    # If the weights are all equal to 0 we are at the beginning of the search
+    # and thus only need to sample from one set of token logits for each
+    # batch.
+    if torch.all(sequence_weights == 0):
+        weights = weights[:, :vocab_size]
+
+    weights, indices = torch.topk(
+        weights, self.samples, dim=1, largest=True, sorted=True
+    )
+
+    ancestors = torch.div(indices, vocab_size, rounding_mode="floor")
+    next_token_ids = indices % vocab_size
+
+    # Re-shape the weights, next_token_ids and ancestors to (n_batch * n_samples, 1)
+    first_batch_idx = torch.arange(
+        0, batch_size * self.samples, self.samples, device=next_token_logits.device
+    ).unsqueeze(1)
+    ancestors = ancestors + first_batch_idx
+
+    ancestors = ancestors.view(self.samples * batch_size)
+    weights = weights.view(self.samples * batch_size)
+    next_token_ids = next_token_ids.view(self.samples * batch_size, 1)
+
+    return next_token_ids, ancestors, weights
+
+
+
+ +
+ + + +
+ +
+ + +
+ +
+ + + +

+ GreedySampler + + +

+ + +
+ + +

Greedy Sampling algorithm.

+

Greedy sampling consists in choosing the token with the largest +likelihood at every step.

+

We don't allow more than one sample. We could attribute this a meaning, for +instance the k-th sample represents the k-th most likely token. In which +case it would be equivalent to beam search without the sequence weights.

+

Attributes

+

samples + The number of samples taken for each input sequence.

+ +
+ Source code in outlines/samplers.py + 
19
+20
+21
+22
+23
+24
+25
+26
+27
+28
+29
+30
+31
+32
+33
+34
+35
+36
+37
+38
+39
+40
+41
+42
+43
+44
+45
+46
+47
+48
+49
+50
+51
+52
+53
+54
+55
+56
+57
+58
+59
+60
+61
+62
+63
+64
+65
+66
+67
+68
+69
+70
+71
+72
+73
+74
class GreedySampler:
+    """Greedy Sampling algorithm.
+
+    Greedy sampling consists in choosing the token with the largest
+    likelihood at every step.
+
+    We don't allow more than one sample. We could attribute this a meaning, for
+    instance the k-th sample represents the k-th most likely token. In which
+    case it would be equivalent to beam search without the sequence weights.
+
+    Attributes
+    ----------
+    samples
+        The number of samples taken for each input sequence.
+
+    """
+
+    def __init__(self):
+        self.samples = 1
+
+    def __call__(
+        self,
+        next_token_logits: torch.DoubleTensor,
+        sequence_weights: torch.DoubleTensor,
+        _,
+    ) -> torch.DoubleTensor:
+        """Call the greedy sampler.
+
+        Parameters
+        ----------
+        next_token_logits
+            A tensor of shape ``(n_seqs, vocab_size,)`` that represents the
+            probability distribution of the next token over the vocabulary.
+        sequence_weights
+            A tensor of shape ``(n_seqs,)`` that represents the cumulative
+            weight of each sequence.
+        rng
+            A random number generator.
+
+        Returns
+        -------
+        A tuple with an array that contains the ids of the sampled tokens of
+        shape ``(n_seqs, 1)``, an array that contains the ancestors of each
+        sampled id of shape ``(n_seqs,)`` and an array that contains the updated
+        cumulative weights of each sequence of shape ``(n_seqs,)``.
+
+        """
+        logprobs = torch.nn.functional.log_softmax(next_token_logits, dim=-1)
+        next_token_ids = torch.argmax(logprobs, dim=-1, keepdim=True)
+
+        ancestors = torch.arange(
+            next_token_logits.shape[0], device=next_token_logits.device
+        )
+        weights = sequence_weights + torch.gather(logprobs, 1, next_token_ids).squeeze()
+
+        return next_token_ids, ancestors, weights
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ __call__(next_token_logits, sequence_weights, _) + +

+ + +
+ +

Call the greedy sampler.

+
Parameters
+

next_token_logits + A tensor of shape (n_seqs, vocab_size,) that represents the + probability distribution of the next token over the vocabulary. +sequence_weights + A tensor of shape (n_seqs,) that represents the cumulative + weight of each sequence. +rng + A random number generator.

+
Returns
+

A tuple with an array that contains the ids of the sampled tokens of +shape (n_seqs, 1), an array that contains the ancestors of each +sampled id of shape (n_seqs,) and an array that contains the updated +cumulative weights of each sequence of shape (n_seqs,).

+ +
+ Source code in outlines/samplers.py + 
39
+40
+41
+42
+43
+44
+45
+46
+47
+48
+49
+50
+51
+52
+53
+54
+55
+56
+57
+58
+59
+60
+61
+62
+63
+64
+65
+66
+67
+68
+69
+70
+71
+72
+73
+74
def __call__(
+    self,
+    next_token_logits: torch.DoubleTensor,
+    sequence_weights: torch.DoubleTensor,
+    _,
+) -> torch.DoubleTensor:
+    """Call the greedy sampler.
+
+    Parameters
+    ----------
+    next_token_logits
+        A tensor of shape ``(n_seqs, vocab_size,)`` that represents the
+        probability distribution of the next token over the vocabulary.
+    sequence_weights
+        A tensor of shape ``(n_seqs,)`` that represents the cumulative
+        weight of each sequence.
+    rng
+        A random number generator.
+
+    Returns
+    -------
+    A tuple with an array that contains the ids of the sampled tokens of
+    shape ``(n_seqs, 1)``, an array that contains the ancestors of each
+    sampled id of shape ``(n_seqs,)`` and an array that contains the updated
+    cumulative weights of each sequence of shape ``(n_seqs,)``.
+
+    """
+    logprobs = torch.nn.functional.log_softmax(next_token_logits, dim=-1)
+    next_token_ids = torch.argmax(logprobs, dim=-1, keepdim=True)
+
+    ancestors = torch.arange(
+        next_token_logits.shape[0], device=next_token_logits.device
+    )
+    weights = sequence_weights + torch.gather(logprobs, 1, next_token_ids).squeeze()
+
+    return next_token_ids, ancestors, weights
+
+
+
+ +
+ + + +
+ +
+ + +
+ +
+ + + +

+ MultinomialSampler + + +

+ + +
+ + +

Multinomial sampling algorithm.

+

Multinomial sampling consists in randomly sampling the next token assuming +its distribution is a Categorical distribution parametrized by the +next-token logits.

+

Attributes

+

samples + The number of samples taken for each input sequence.

+ +
+ Source code in outlines/samplers.py + 
 80
+ 81
+ 82
+ 83
+ 84
+ 85
+ 86
+ 87
+ 88
+ 89
+ 90
+ 91
+ 92
+ 93
+ 94
+ 95
+ 96
+ 97
+ 98
+ 99
+100
+101
+102
+103
+104
+105
+106
+107
+108
+109
+110
+111
+112
+113
+114
+115
+116
+117
+118
+119
+120
+121
+122
+123
+124
+125
+126
+127
+128
+129
+130
+131
+132
+133
+134
+135
+136
+137
+138
+139
+140
+141
+142
+143
+144
+145
+146
+147
+148
+149
+150
+151
+152
+153
+154
class MultinomialSampler:
+    """Multinomial sampling algorithm.
+
+    Multinomial sampling consists in randomly sampling the next token assuming
+    its distribution is a Categorical distribution parametrized by the
+    next-token logits.
+
+
+    Attributes
+    ----------
+    samples
+        The number of samples taken for each input sequence.
+
+    """
+
+    def __init__(
+        self,
+        samples: int = 1,
+        *,
+        top_k: Optional[int] = None,
+        top_p: Optional[float] = None,
+        temperature: Optional[float] = None,
+    ):
+        self.samples = samples
+
+        self.logits_processors = []
+        if top_k is not None:
+            self.logits_processors.append(keep_top_k_logits(top_k))
+        elif top_p is not None:
+            self.logits_processors.append(keep_top_p_logits(top_p))
+
+        if temperature is not None:
+            self.logits_processors.append(rescale_logits(temperature))
+
+    def __call__(
+        self,
+        next_token_logits: torch.DoubleTensor,
+        sequence_weights: torch.DoubleTensor,
+        rng: torch.Generator,
+    ) -> Tuple[torch.DoubleTensor, torch.DoubleTensor, torch.DoubleTensor]:
+        """Call the multinomial sampler.
+
+        Parameters
+        ----------
+        next_token_logits
+            A tensor of shape ``(n_seqs, vocab_size,)`` that represents the
+            probability distribution of the next token over the vocabulary.
+        sequence_weights
+            A tensor of shape ``(n_seqs,)`` that represents the cumulative
+            weight of each sequence.
+        rng
+            A random number generator.
+
+        Returns
+        -------
+        A tuple with an array that contains the ids of the sampled tokens of
+        shape ``(n_seqs, 1)``, an array that contains the ancestors of each
+        sampled id of shape ``(n_seqs,)`` and an array that contains the updated
+        cumulative weights of each sequence of shape ``(n_seqs,)``.
+
+        """
+        altered_next_token_logits = next_token_logits
+        for logit_processor in self.logits_processors:
+            altered_next_token_logits = logit_processor(next_token_logits)
+
+        probs = torch.nn.functional.softmax(altered_next_token_logits, dim=-1)
+        next_token_ids = torch.multinomial(probs, num_samples=1, generator=rng)
+
+        logprobs = torch.nn.functional.log_softmax(altered_next_token_logits, dim=-1)
+        ancestors = torch.arange(
+            altered_next_token_logits.shape[0], device=next_token_logits.device
+        )
+        weights = sequence_weights + torch.gather(logprobs, 1, next_token_ids).squeeze()
+
+        return next_token_ids, ancestors, weights
+
+
+ + + +
+ + + + + + + + + + +
+ + + +

+ __call__(next_token_logits, sequence_weights, rng) + +

+ + +
+ +

Call the multinomial sampler.

+
Parameters
+

next_token_logits + A tensor of shape (n_seqs, vocab_size,) that represents the + probability distribution of the next token over the vocabulary. +sequence_weights + A tensor of shape (n_seqs,) that represents the cumulative + weight of each sequence. +rng + A random number generator.

+
Returns
+

A tuple with an array that contains the ids of the sampled tokens of +shape (n_seqs, 1), an array that contains the ancestors of each +sampled id of shape (n_seqs,) and an array that contains the updated +cumulative weights of each sequence of shape (n_seqs,).

+ +
+ Source code in outlines/samplers.py + 
114
+115
+116
+117
+118
+119
+120
+121
+122
+123
+124
+125
+126
+127
+128
+129
+130
+131
+132
+133
+134
+135
+136
+137
+138
+139
+140
+141
+142
+143
+144
+145
+146
+147
+148
+149
+150
+151
+152
+153
+154
def __call__(
+    self,
+    next_token_logits: torch.DoubleTensor,
+    sequence_weights: torch.DoubleTensor,
+    rng: torch.Generator,
+) -> Tuple[torch.DoubleTensor, torch.DoubleTensor, torch.DoubleTensor]:
+    """Call the multinomial sampler.
+
+    Parameters
+    ----------
+    next_token_logits
+        A tensor of shape ``(n_seqs, vocab_size,)`` that represents the
+        probability distribution of the next token over the vocabulary.
+    sequence_weights
+        A tensor of shape ``(n_seqs,)`` that represents the cumulative
+        weight of each sequence.
+    rng
+        A random number generator.
+
+    Returns
+    -------
+    A tuple with an array that contains the ids of the sampled tokens of
+    shape ``(n_seqs, 1)``, an array that contains the ancestors of each
+    sampled id of shape ``(n_seqs,)`` and an array that contains the updated
+    cumulative weights of each sequence of shape ``(n_seqs,)``.
+
+    """
+    altered_next_token_logits = next_token_logits
+    for logit_processor in self.logits_processors:
+        altered_next_token_logits = logit_processor(next_token_logits)
+
+    probs = torch.nn.functional.softmax(altered_next_token_logits, dim=-1)
+    next_token_ids = torch.multinomial(probs, num_samples=1, generator=rng)
+
+    logprobs = torch.nn.functional.log_softmax(altered_next_token_logits, dim=-1)
+    ancestors = torch.arange(
+        altered_next_token_logits.shape[0], device=next_token_logits.device
+    )
+    weights = sequence_weights + torch.gather(logprobs, 1, next_token_ids).squeeze()
+
+    return next_token_ids, ancestors, weights
+
+
+
+ +
+ + + +
+ +
+ + +
+ + + +
+ + + +

+ keep_top_k_logits(k) + +

+ + +
+ +

Build a function that masks logits values smaller than the top k ones.

+

Parameters

+

k + The ranking below which logit values are replaced by -math.inf.

+ +
+ Source code in outlines/samplers.py + 
160
+161
+162
+163
+164
+165
+166
+167
+168
+169
+170
+171
+172
+173
+174
+175
+176
+177
def keep_top_k_logits(k: int) -> Callable[[torch.Tensor], torch.Tensor]:
+    """Build a function that masks logits values smaller than the top `k` ones.
+
+    Parameters
+    ----------
+    k
+        The ranking below which logit values are replaced by `-math.inf`.
+
+    """
+    if not isinstance(k, int) or k < 1:
+        raise ValueError(f"`k` must be a strictly positive integers, got {k} instead.")
+
+    def logits_processor(logits: torch.Tensor) -> torch.Tensor:
+        num_to_keep = min(k, logits.size(-1))
+        mask_idx = logits < torch.topk(logits, num_to_keep)[0][..., -1, None]
+        return logits.masked_fill(mask_idx, -math.inf)
+
+    return logits_processor
+
+
+
+ +
+ + +
+ + + +

+ keep_top_p_logits(p) + +

+ + +
+ +

Build a function that masks the lowest probability tokens whose +cumulative probability is below a certain threshold.

+

Parameters

+

p + The value of the threshold. We keep the highest probability tokens whose + cumulative distribution is greater than or equal to p and mask the + others. Its value must be between 0 (excluded) and 1 (included).

+ +
+ Source code in outlines/samplers.py + 
180
+181
+182
+183
+184
+185
+186
+187
+188
+189
+190
+191
+192
+193
+194
+195
+196
+197
+198
+199
+200
+201
+202
+203
+204
+205
+206
+207
def keep_top_p_logits(p: float) -> Callable[[torch.Tensor], torch.Tensor]:
+    """Build a function that masks the lowest probability tokens whose
+    cumulative probability is below a certain threshold.
+
+    Parameters
+    ----------
+    p
+        The value of the threshold. We keep the highest probability tokens whose
+        cumulative distribution is greater than or equal to `p` and mask the
+        others. Its value must be between 0 (excluded) and 1 (included).
+
+    """
+    if p <= 0.0 or p > 1.0:
+        raise ValueError(
+            f"`p` must be a floating point number between 0 (excluded) and 1 (included), got {p} instead."
+        )
+
+    def logits_processor(logits: torch.Tensor) -> torch.Tensor:
+        sorted_logits, sorted_idx = torch.sort(logits, descending=False)
+        cumulative_probabilties = torch.nn.functional.softmax(
+            sorted_logits, dim=-1
+        ).cumsum(dim=-1)
+
+        sorted_masked_idx = cumulative_probabilties <= (1 - p)
+        mask_idx = torch.scatter(sorted_masked_idx, 1, sorted_idx, sorted_masked_idx)
+        return logits.masked_fill(mask_idx, -math.inf)
+
+    return logits_processor
+
+
+
+ +
+ + +
+ + + +

+ rescale_logits(temperature) + +

+ + +
+ +

Build a function that rescales the token probabilities exponentially.

+

Parameters

+

temperature + The value by which we rescale the logits.

+ +
+ Source code in outlines/samplers.py + 
210
+211
+212
+213
+214
+215
+216
+217
+218
+219
+220
+221
+222
+223
+224
+225
+226
+227
+228
+229
+230
+231
+232
def rescale_logits(temperature: float) -> Callable[[torch.Tensor], torch.Tensor]:
+    """Build a function that rescales the token probabilities exponentially.
+
+    Parameters
+    ----------
+    temperature
+        The value by which we rescale the logits.
+
+    """
+
+    if not isinstance(temperature, float) or temperature < 0.0:
+        raise ValueError(
+            f"`temperature` must be a strictly negative floating point number, got {temperature} instead."
+        )
+    elif temperature == 0.0:
+        raise ValueError(
+            "Please use the greedy sampler instead of setting the temperature to 0."
+        )
+
+    def logits_processor(logits: torch.Tensor) -> torch.Tensor:
+        return logits / temperature
+
+    return logits_processor
+
+
+
+ +
+ + + +
+ +
+ +
+ + + + + + + + + + + + + + + + + + + + +
+
+ + + +
+ +
+ + + +
+
+
+
+ + + + + + + + + + \ No newline at end of file diff --git a/assets/_mkdocstrings.css b/assets/_mkdocstrings.css new file mode 100644 index 000000000..4b7d98b83 --- /dev/null +++ b/assets/_mkdocstrings.css @@ -0,0 +1,109 @@ + +/* Avoid breaking parameter names, etc. in table cells. */ +.doc-contents td code { + word-break: normal !important; +} + +/* No line break before first paragraph of descriptions. */ +.doc-md-description, +.doc-md-description>p:first-child { + display: inline; +} + +/* Max width for docstring sections tables. */ +.doc .md-typeset__table, +.doc .md-typeset__table table { + display: table !important; + width: 100%; +} + +.doc .md-typeset__table tr { + display: table-row; +} + +/* Defaults in Spacy table style. */ +.doc-param-default { + float: right; +} + +/* Symbols in Navigation and ToC. */ +:root, +[data-md-color-scheme="default"] { + --doc-symbol-attribute-fg-color: #953800; + --doc-symbol-function-fg-color: #8250df; + --doc-symbol-method-fg-color: #8250df; + --doc-symbol-class-fg-color: #0550ae; + --doc-symbol-module-fg-color: #5cad0f; + + --doc-symbol-attribute-bg-color: #9538001a; + --doc-symbol-function-bg-color: #8250df1a; + --doc-symbol-method-bg-color: #8250df1a; + --doc-symbol-class-bg-color: #0550ae1a; + --doc-symbol-module-bg-color: #5cad0f1a; +} + +[data-md-color-scheme="slate"] { + --doc-symbol-attribute-fg-color: #ffa657; + --doc-symbol-function-fg-color: #d2a8ff; + --doc-symbol-method-fg-color: #d2a8ff; + --doc-symbol-class-fg-color: #79c0ff; + --doc-symbol-module-fg-color: #baff79; + + --doc-symbol-attribute-bg-color: #ffa6571a; + --doc-symbol-function-bg-color: #d2a8ff1a; + --doc-symbol-method-bg-color: #d2a8ff1a; + --doc-symbol-class-bg-color: #79c0ff1a; + --doc-symbol-module-bg-color: #baff791a; +} + +code.doc-symbol { + border-radius: .1rem; + font-size: .85em; + padding: 0 .3em; + font-weight: bold; +} + +code.doc-symbol-attribute { + color: var(--doc-symbol-attribute-fg-color); + background-color: var(--doc-symbol-attribute-bg-color); +} + +code.doc-symbol-attribute::after { + content: "attr"; +} + +code.doc-symbol-function { + color: var(--doc-symbol-function-fg-color); + background-color: var(--doc-symbol-function-bg-color); +} + +code.doc-symbol-function::after { + content: "func"; +} + +code.doc-symbol-method { + color: var(--doc-symbol-method-fg-color); + background-color: var(--doc-symbol-method-bg-color); +} + +code.doc-symbol-method::after { + content: "meth"; +} + +code.doc-symbol-class { + color: var(--doc-symbol-class-fg-color); + background-color: var(--doc-symbol-class-bg-color); +} + +code.doc-symbol-class::after { + content: "class"; +} + +code.doc-symbol-module { + color: var(--doc-symbol-module-fg-color); + background-color: var(--doc-symbol-module-bg-color); +} + +code.doc-symbol-module::after { + content: "mod"; +} \ No newline at end of file diff --git a/assets/images/dottxt.png b/assets/images/dottxt.png new file mode 100644 index 000000000..1bdf8cb61 Binary files /dev/null and b/assets/images/dottxt.png differ diff --git a/assets/images/favicon.png b/assets/images/favicon.png new file mode 100644 index 000000000..1cf13b9f9 Binary files /dev/null and b/assets/images/favicon.png differ diff --git a/assets/images/logo.png b/assets/images/logo.png new file mode 100644 index 000000000..9a9f234a7 Binary files /dev/null and b/assets/images/logo.png differ diff --git a/assets/images/normal_computing.jpg b/assets/images/normal_computing.jpg new file mode 100644 index 000000000..a71483a68 Binary files /dev/null and b/assets/images/normal_computing.jpg differ diff --git a/assets/images/social/api/fsm.png b/assets/images/social/api/fsm.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/api/fsm.png differ diff --git a/assets/images/social/api/index.png b/assets/images/social/api/index.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/api/index.png differ diff --git a/assets/images/social/api/json_schema.png b/assets/images/social/api/json_schema.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/api/json_schema.png differ diff --git a/assets/images/social/api/models.png b/assets/images/social/api/models.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/api/models.png differ diff --git a/assets/images/social/api/parsing.png b/assets/images/social/api/parsing.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/api/parsing.png differ diff --git a/assets/images/social/api/prompts.png b/assets/images/social/api/prompts.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/api/prompts.png differ diff --git a/assets/images/social/api/regex.png b/assets/images/social/api/regex.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/api/regex.png differ diff --git a/assets/images/social/api/samplers.png b/assets/images/social/api/samplers.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/api/samplers.png differ diff --git a/assets/images/social/blog/archive/2024.png b/assets/images/social/blog/archive/2024.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/blog/archive/2024.png differ diff --git a/assets/images/social/blog/category/roadmap.png b/assets/images/social/blog/category/roadmap.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/blog/category/roadmap.png differ diff --git a/assets/images/social/blog/index.png b/assets/images/social/blog/index.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/blog/index.png differ diff --git a/assets/images/social/blog/posts/roadmap-2024.png b/assets/images/social/blog/posts/roadmap-2024.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/blog/posts/roadmap-2024.png differ diff --git a/assets/images/social/community/contribute.png b/assets/images/social/community/contribute.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/community/contribute.png differ diff --git a/assets/images/social/community/feedback.png b/assets/images/social/community/feedback.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/community/feedback.png differ diff --git a/assets/images/social/community/index.png b/assets/images/social/community/index.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/community/index.png differ diff --git a/assets/images/social/cookbook/chain_of_density.png b/assets/images/social/cookbook/chain_of_density.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/cookbook/chain_of_density.png differ diff --git a/assets/images/social/cookbook/classification.png b/assets/images/social/cookbook/classification.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/cookbook/classification.png differ diff --git a/assets/images/social/cookbook/dating_profiles.png b/assets/images/social/cookbook/dating_profiles.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/cookbook/dating_profiles.png differ diff --git a/assets/images/social/cookbook/extraction.png b/assets/images/social/cookbook/extraction.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/cookbook/extraction.png differ diff --git a/assets/images/social/cookbook/index.png b/assets/images/social/cookbook/index.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/cookbook/index.png differ diff --git a/assets/images/social/cookbook/models_playing_chess.png b/assets/images/social/cookbook/models_playing_chess.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/cookbook/models_playing_chess.png differ diff --git a/assets/images/social/index.png b/assets/images/social/index.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/index.png differ diff --git a/assets/images/social/installation.png b/assets/images/social/installation.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/installation.png differ diff --git a/assets/images/social/licence.png b/assets/images/social/licence.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/licence.png differ diff --git a/assets/images/social/quickstart.png b/assets/images/social/quickstart.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/quickstart.png differ diff --git a/assets/images/social/reference/cfg.png b/assets/images/social/reference/cfg.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/cfg.png differ diff --git a/assets/images/social/reference/choices.png b/assets/images/social/reference/choices.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/choices.png differ diff --git a/assets/images/social/reference/functions.png b/assets/images/social/reference/functions.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/functions.png differ diff --git a/assets/images/social/reference/index.png b/assets/images/social/reference/index.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/index.png differ diff --git a/assets/images/social/reference/json.png b/assets/images/social/reference/json.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/json.png differ diff --git a/assets/images/social/reference/models/llamacpp.png b/assets/images/social/reference/models/llamacpp.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/models/llamacpp.png differ diff --git a/assets/images/social/reference/models/openai.png b/assets/images/social/reference/models/openai.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/models/openai.png differ diff --git a/assets/images/social/reference/prompting.png b/assets/images/social/reference/prompting.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/prompting.png differ diff --git a/assets/images/social/reference/regex.png b/assets/images/social/reference/regex.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/regex.png differ diff --git a/assets/images/social/reference/samplers.png b/assets/images/social/reference/samplers.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/samplers.png differ diff --git a/assets/images/social/reference/text.png b/assets/images/social/reference/text.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/text.png differ diff --git a/assets/images/social/reference/types.png b/assets/images/social/reference/types.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/types.png differ diff --git a/assets/images/social/reference/vllm.png b/assets/images/social/reference/vllm.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/reference/vllm.png differ diff --git a/assets/images/social/welcome.png b/assets/images/social/welcome.png new file mode 100644 index 000000000..34d83e753 Binary files /dev/null and b/assets/images/social/welcome.png differ diff --git a/assets/javascripts/bundle.8fd75fb4.min.js b/assets/javascripts/bundle.8fd75fb4.min.js new file mode 100644 index 000000000..2f2f130e2 --- /dev/null +++ b/assets/javascripts/bundle.8fd75fb4.min.js @@ -0,0 +1,29 @@ +"use strict";(()=>{var _i=Object.create;var br=Object.defineProperty;var Ai=Object.getOwnPropertyDescriptor;var Ci=Object.getOwnPropertyNames,Ft=Object.getOwnPropertySymbols,ki=Object.getPrototypeOf,vr=Object.prototype.hasOwnProperty,eo=Object.prototype.propertyIsEnumerable;var Zr=(e,t,r)=>t in e?br(e,t,{enumerable:!0,configurable:!0,writable:!0,value:r}):e[t]=r,F=(e,t)=>{for(var r in t||(t={}))vr.call(t,r)&&Zr(e,r,t[r]);if(Ft)for(var r of Ft(t))eo.call(t,r)&&Zr(e,r,t[r]);return e};var to=(e,t)=>{var r={};for(var o in e)vr.call(e,o)&&t.indexOf(o)<0&&(r[o]=e[o]);if(e!=null&&Ft)for(var o of Ft(e))t.indexOf(o)<0&&eo.call(e,o)&&(r[o]=e[o]);return r};var gr=(e,t)=>()=>(t||e((t={exports:{}}).exports,t),t.exports);var Hi=(e,t,r,o)=>{if(t&&typeof t=="object"||typeof t=="function")for(let n of Ci(t))!vr.call(e,n)&&n!==r&&br(e,n,{get:()=>t[n],enumerable:!(o=Ai(t,n))||o.enumerable});return e};var jt=(e,t,r)=>(r=e!=null?_i(ki(e)):{},Hi(t||!e||!e.__esModule?br(r,"default",{value:e,enumerable:!0}):r,e));var ro=(e,t,r)=>new Promise((o,n)=>{var i=c=>{try{a(r.next(c))}catch(p){n(p)}},s=c=>{try{a(r.throw(c))}catch(p){n(p)}},a=c=>c.done?o(c.value):Promise.resolve(c.value).then(i,s);a((r=r.apply(e,t)).next())});var no=gr((xr,oo)=>{(function(e,t){typeof xr=="object"&&typeof oo!="undefined"?t():typeof define=="function"&&define.amd?define(t):t()})(xr,function(){"use strict";function e(r){var o=!0,n=!1,i=null,s={text:!0,search:!0,url:!0,tel:!0,email:!0,password:!0,number:!0,date:!0,month:!0,week:!0,time:!0,datetime:!0,"datetime-local":!0};function a(C){return!!(C&&C!==document&&C.nodeName!=="HTML"&&C.nodeName!=="BODY"&&"classList"in C&&"contains"in C.classList)}function c(C){var ct=C.type,Ne=C.tagName;return!!(Ne==="INPUT"&&s[ct]&&!C.readOnly||Ne==="TEXTAREA"&&!C.readOnly||C.isContentEditable)}function p(C){C.classList.contains("focus-visible")||(C.classList.add("focus-visible"),C.setAttribute("data-focus-visible-added",""))}function l(C){C.hasAttribute("data-focus-visible-added")&&(C.classList.remove("focus-visible"),C.removeAttribute("data-focus-visible-added"))}function f(C){C.metaKey||C.altKey||C.ctrlKey||(a(r.activeElement)&&p(r.activeElement),o=!0)}function u(C){o=!1}function h(C){a(C.target)&&(o||c(C.target))&&p(C.target)}function w(C){a(C.target)&&(C.target.classList.contains("focus-visible")||C.target.hasAttribute("data-focus-visible-added"))&&(n=!0,window.clearTimeout(i),i=window.setTimeout(function(){n=!1},100),l(C.target))}function A(C){document.visibilityState==="hidden"&&(n&&(o=!0),Z())}function Z(){document.addEventListener("mousemove",J),document.addEventListener("mousedown",J),document.addEventListener("mouseup",J),document.addEventListener("pointermove",J),document.addEventListener("pointerdown",J),document.addEventListener("pointerup",J),document.addEventListener("touchmove",J),document.addEventListener("touchstart",J),document.addEventListener("touchend",J)}function te(){document.removeEventListener("mousemove",J),document.removeEventListener("mousedown",J),document.removeEventListener("mouseup",J),document.removeEventListener("pointermove",J),document.removeEventListener("pointerdown",J),document.removeEventListener("pointerup",J),document.removeEventListener("touchmove",J),document.removeEventListener("touchstart",J),document.removeEventListener("touchend",J)}function J(C){C.target.nodeName&&C.target.nodeName.toLowerCase()==="html"||(o=!1,te())}document.addEventListener("keydown",f,!0),document.addEventListener("mousedown",u,!0),document.addEventListener("pointerdown",u,!0),document.addEventListener("touchstart",u,!0),document.addEventListener("visibilitychange",A,!0),Z(),r.addEventListener("focus",h,!0),r.addEventListener("blur",w,!0),r.nodeType===Node.DOCUMENT_FRAGMENT_NODE&&r.host?r.host.setAttribute("data-js-focus-visible",""):r.nodeType===Node.DOCUMENT_NODE&&(document.documentElement.classList.add("js-focus-visible"),document.documentElement.setAttribute("data-js-focus-visible",""))}if(typeof window!="undefined"&&typeof document!="undefined"){window.applyFocusVisiblePolyfill=e;var t;try{t=new CustomEvent("focus-visible-polyfill-ready")}catch(r){t=document.createEvent("CustomEvent"),t.initCustomEvent("focus-visible-polyfill-ready",!1,!1,{})}window.dispatchEvent(t)}typeof document!="undefined"&&e(document)})});var zr=gr((kt,Vr)=>{/*! + * clipboard.js v2.0.11 + * https://clipboardjs.com/ + * + * Licensed MIT © Zeno Rocha + */(function(t,r){typeof kt=="object"&&typeof Vr=="object"?Vr.exports=r():typeof define=="function"&&define.amd?define([],r):typeof kt=="object"?kt.ClipboardJS=r():t.ClipboardJS=r()})(kt,function(){return function(){var e={686:function(o,n,i){"use strict";i.d(n,{default:function(){return Li}});var s=i(279),a=i.n(s),c=i(370),p=i.n(c),l=i(817),f=i.n(l);function u(D){try{return document.execCommand(D)}catch(M){return!1}}var h=function(M){var O=f()(M);return u("cut"),O},w=h;function A(D){var M=document.documentElement.getAttribute("dir")==="rtl",O=document.createElement("textarea");O.style.fontSize="12pt",O.style.border="0",O.style.padding="0",O.style.margin="0",O.style.position="absolute",O.style[M?"right":"left"]="-9999px";var I=window.pageYOffset||document.documentElement.scrollTop;return O.style.top="".concat(I,"px"),O.setAttribute("readonly",""),O.value=D,O}var Z=function(M,O){var I=A(M);O.container.appendChild(I);var W=f()(I);return u("copy"),I.remove(),W},te=function(M){var O=arguments.length>1&&arguments[1]!==void 0?arguments[1]:{container:document.body},I="";return typeof M=="string"?I=Z(M,O):M instanceof HTMLInputElement&&!["text","search","url","tel","password"].includes(M==null?void 0:M.type)?I=Z(M.value,O):(I=f()(M),u("copy")),I},J=te;function C(D){"@babel/helpers - typeof";return typeof Symbol=="function"&&typeof Symbol.iterator=="symbol"?C=function(O){return typeof O}:C=function(O){return O&&typeof Symbol=="function"&&O.constructor===Symbol&&O!==Symbol.prototype?"symbol":typeof O},C(D)}var ct=function(){var M=arguments.length>0&&arguments[0]!==void 0?arguments[0]:{},O=M.action,I=O===void 0?"copy":O,W=M.container,K=M.target,Ce=M.text;if(I!=="copy"&&I!=="cut")throw new Error('Invalid "action" value, use either "copy" or "cut"');if(K!==void 0)if(K&&C(K)==="object"&&K.nodeType===1){if(I==="copy"&&K.hasAttribute("disabled"))throw new Error('Invalid "target" attribute. Please use "readonly" instead of "disabled" attribute');if(I==="cut"&&(K.hasAttribute("readonly")||K.hasAttribute("disabled")))throw new Error(`Invalid "target" attribute. You can't cut text from elements with "readonly" or "disabled" attributes`)}else throw new Error('Invalid "target" value, use a valid Element');if(Ce)return J(Ce,{container:W});if(K)return I==="cut"?w(K):J(K,{container:W})},Ne=ct;function Pe(D){"@babel/helpers - typeof";return typeof Symbol=="function"&&typeof Symbol.iterator=="symbol"?Pe=function(O){return typeof O}:Pe=function(O){return O&&typeof Symbol=="function"&&O.constructor===Symbol&&O!==Symbol.prototype?"symbol":typeof O},Pe(D)}function xi(D,M){if(!(D instanceof M))throw new TypeError("Cannot call a class as a function")}function Xr(D,M){for(var O=0;O0&&arguments[0]!==void 0?arguments[0]:{};this.action=typeof W.action=="function"?W.action:this.defaultAction,this.target=typeof W.target=="function"?W.target:this.defaultTarget,this.text=typeof W.text=="function"?W.text:this.defaultText,this.container=Pe(W.container)==="object"?W.container:document.body}},{key:"listenClick",value:function(W){var K=this;this.listener=p()(W,"click",function(Ce){return K.onClick(Ce)})}},{key:"onClick",value:function(W){var K=W.delegateTarget||W.currentTarget,Ce=this.action(K)||"copy",It=Ne({action:Ce,container:this.container,target:this.target(K),text:this.text(K)});this.emit(It?"success":"error",{action:Ce,text:It,trigger:K,clearSelection:function(){K&&K.focus(),window.getSelection().removeAllRanges()}})}},{key:"defaultAction",value:function(W){return hr("action",W)}},{key:"defaultTarget",value:function(W){var K=hr("target",W);if(K)return document.querySelector(K)}},{key:"defaultText",value:function(W){return hr("text",W)}},{key:"destroy",value:function(){this.listener.destroy()}}],[{key:"copy",value:function(W){var K=arguments.length>1&&arguments[1]!==void 0?arguments[1]:{container:document.body};return J(W,K)}},{key:"cut",value:function(W){return w(W)}},{key:"isSupported",value:function(){var W=arguments.length>0&&arguments[0]!==void 0?arguments[0]:["copy","cut"],K=typeof W=="string"?[W]:W,Ce=!!document.queryCommandSupported;return K.forEach(function(It){Ce=Ce&&!!document.queryCommandSupported(It)}),Ce}}]),O}(a()),Li=Mi},828:function(o){var n=9;if(typeof Element!="undefined"&&!Element.prototype.matches){var i=Element.prototype;i.matches=i.matchesSelector||i.mozMatchesSelector||i.msMatchesSelector||i.oMatchesSelector||i.webkitMatchesSelector}function s(a,c){for(;a&&a.nodeType!==n;){if(typeof a.matches=="function"&&a.matches(c))return a;a=a.parentNode}}o.exports=s},438:function(o,n,i){var s=i(828);function a(l,f,u,h,w){var A=p.apply(this,arguments);return l.addEventListener(u,A,w),{destroy:function(){l.removeEventListener(u,A,w)}}}function c(l,f,u,h,w){return typeof l.addEventListener=="function"?a.apply(null,arguments):typeof u=="function"?a.bind(null,document).apply(null,arguments):(typeof l=="string"&&(l=document.querySelectorAll(l)),Array.prototype.map.call(l,function(A){return a(A,f,u,h,w)}))}function p(l,f,u,h){return function(w){w.delegateTarget=s(w.target,f),w.delegateTarget&&h.call(l,w)}}o.exports=c},879:function(o,n){n.node=function(i){return i!==void 0&&i instanceof HTMLElement&&i.nodeType===1},n.nodeList=function(i){var s=Object.prototype.toString.call(i);return i!==void 0&&(s==="[object NodeList]"||s==="[object HTMLCollection]")&&"length"in i&&(i.length===0||n.node(i[0]))},n.string=function(i){return typeof i=="string"||i instanceof String},n.fn=function(i){var s=Object.prototype.toString.call(i);return s==="[object Function]"}},370:function(o,n,i){var s=i(879),a=i(438);function c(u,h,w){if(!u&&!h&&!w)throw new Error("Missing required arguments");if(!s.string(h))throw new TypeError("Second argument must be a String");if(!s.fn(w))throw new TypeError("Third argument must be a Function");if(s.node(u))return p(u,h,w);if(s.nodeList(u))return l(u,h,w);if(s.string(u))return f(u,h,w);throw new TypeError("First argument must be a String, HTMLElement, HTMLCollection, or NodeList")}function p(u,h,w){return u.addEventListener(h,w),{destroy:function(){u.removeEventListener(h,w)}}}function l(u,h,w){return Array.prototype.forEach.call(u,function(A){A.addEventListener(h,w)}),{destroy:function(){Array.prototype.forEach.call(u,function(A){A.removeEventListener(h,w)})}}}function f(u,h,w){return a(document.body,u,h,w)}o.exports=c},817:function(o){function n(i){var s;if(i.nodeName==="SELECT")i.focus(),s=i.value;else if(i.nodeName==="INPUT"||i.nodeName==="TEXTAREA"){var a=i.hasAttribute("readonly");a||i.setAttribute("readonly",""),i.select(),i.setSelectionRange(0,i.value.length),a||i.removeAttribute("readonly"),s=i.value}else{i.hasAttribute("contenteditable")&&i.focus();var c=window.getSelection(),p=document.createRange();p.selectNodeContents(i),c.removeAllRanges(),c.addRange(p),s=c.toString()}return s}o.exports=n},279:function(o){function n(){}n.prototype={on:function(i,s,a){var c=this.e||(this.e={});return(c[i]||(c[i]=[])).push({fn:s,ctx:a}),this},once:function(i,s,a){var c=this;function p(){c.off(i,p),s.apply(a,arguments)}return p._=s,this.on(i,p,a)},emit:function(i){var s=[].slice.call(arguments,1),a=((this.e||(this.e={}))[i]||[]).slice(),c=0,p=a.length;for(c;c{"use strict";/*! + * escape-html + * Copyright(c) 2012-2013 TJ Holowaychuk + * Copyright(c) 2015 Andreas Lubbe + * Copyright(c) 2015 Tiancheng "Timothy" Gu + * MIT Licensed + */var Va=/["'&<>]/;qn.exports=za;function za(e){var t=""+e,r=Va.exec(t);if(!r)return t;var o,n="",i=0,s=0;for(i=r.index;i0&&i[i.length-1])&&(p[0]===6||p[0]===2)){r=0;continue}if(p[0]===3&&(!i||p[1]>i[0]&&p[1]=e.length&&(e=void 0),{value:e&&e[o++],done:!e}}};throw new TypeError(t?"Object is not iterable.":"Symbol.iterator is not defined.")}function V(e,t){var r=typeof Symbol=="function"&&e[Symbol.iterator];if(!r)return e;var o=r.call(e),n,i=[],s;try{for(;(t===void 0||t-- >0)&&!(n=o.next()).done;)i.push(n.value)}catch(a){s={error:a}}finally{try{n&&!n.done&&(r=o.return)&&r.call(o)}finally{if(s)throw s.error}}return i}function z(e,t,r){if(r||arguments.length===2)for(var o=0,n=t.length,i;o1||a(u,h)})})}function a(u,h){try{c(o[u](h))}catch(w){f(i[0][3],w)}}function c(u){u.value instanceof ot?Promise.resolve(u.value.v).then(p,l):f(i[0][2],u)}function p(u){a("next",u)}function l(u){a("throw",u)}function f(u,h){u(h),i.shift(),i.length&&a(i[0][0],i[0][1])}}function so(e){if(!Symbol.asyncIterator)throw new TypeError("Symbol.asyncIterator is not defined.");var t=e[Symbol.asyncIterator],r;return t?t.call(e):(e=typeof ue=="function"?ue(e):e[Symbol.iterator](),r={},o("next"),o("throw"),o("return"),r[Symbol.asyncIterator]=function(){return this},r);function o(i){r[i]=e[i]&&function(s){return new Promise(function(a,c){s=e[i](s),n(a,c,s.done,s.value)})}}function n(i,s,a,c){Promise.resolve(c).then(function(p){i({value:p,done:a})},s)}}function k(e){return typeof e=="function"}function pt(e){var t=function(o){Error.call(o),o.stack=new Error().stack},r=e(t);return r.prototype=Object.create(Error.prototype),r.prototype.constructor=r,r}var Wt=pt(function(e){return function(r){e(this),this.message=r?r.length+` errors occurred during unsubscription: +`+r.map(function(o,n){return n+1+") "+o.toString()}).join(` + `):"",this.name="UnsubscriptionError",this.errors=r}});function Ve(e,t){if(e){var r=e.indexOf(t);0<=r&&e.splice(r,1)}}var Ie=function(){function e(t){this.initialTeardown=t,this.closed=!1,this._parentage=null,this._finalizers=null}return e.prototype.unsubscribe=function(){var t,r,o,n,i;if(!this.closed){this.closed=!0;var s=this._parentage;if(s)if(this._parentage=null,Array.isArray(s))try{for(var a=ue(s),c=a.next();!c.done;c=a.next()){var p=c.value;p.remove(this)}}catch(A){t={error:A}}finally{try{c&&!c.done&&(r=a.return)&&r.call(a)}finally{if(t)throw t.error}}else s.remove(this);var l=this.initialTeardown;if(k(l))try{l()}catch(A){i=A instanceof Wt?A.errors:[A]}var f=this._finalizers;if(f){this._finalizers=null;try{for(var u=ue(f),h=u.next();!h.done;h=u.next()){var w=h.value;try{co(w)}catch(A){i=i!=null?i:[],A instanceof Wt?i=z(z([],V(i)),V(A.errors)):i.push(A)}}}catch(A){o={error:A}}finally{try{h&&!h.done&&(n=u.return)&&n.call(u)}finally{if(o)throw o.error}}}if(i)throw new Wt(i)}},e.prototype.add=function(t){var r;if(t&&t!==this)if(this.closed)co(t);else{if(t instanceof e){if(t.closed||t._hasParent(this))return;t._addParent(this)}(this._finalizers=(r=this._finalizers)!==null&&r!==void 0?r:[]).push(t)}},e.prototype._hasParent=function(t){var r=this._parentage;return r===t||Array.isArray(r)&&r.includes(t)},e.prototype._addParent=function(t){var r=this._parentage;this._parentage=Array.isArray(r)?(r.push(t),r):r?[r,t]:t},e.prototype._removeParent=function(t){var r=this._parentage;r===t?this._parentage=null:Array.isArray(r)&&Ve(r,t)},e.prototype.remove=function(t){var r=this._finalizers;r&&Ve(r,t),t instanceof e&&t._removeParent(this)},e.EMPTY=function(){var t=new e;return t.closed=!0,t}(),e}();var Er=Ie.EMPTY;function Dt(e){return e instanceof Ie||e&&"closed"in e&&k(e.remove)&&k(e.add)&&k(e.unsubscribe)}function co(e){k(e)?e():e.unsubscribe()}var ke={onUnhandledError:null,onStoppedNotification:null,Promise:void 0,useDeprecatedSynchronousErrorHandling:!1,useDeprecatedNextContext:!1};var lt={setTimeout:function(e,t){for(var r=[],o=2;o0},enumerable:!1,configurable:!0}),t.prototype._trySubscribe=function(r){return this._throwIfClosed(),e.prototype._trySubscribe.call(this,r)},t.prototype._subscribe=function(r){return this._throwIfClosed(),this._checkFinalizedStatuses(r),this._innerSubscribe(r)},t.prototype._innerSubscribe=function(r){var o=this,n=this,i=n.hasError,s=n.isStopped,a=n.observers;return i||s?Er:(this.currentObservers=null,a.push(r),new Ie(function(){o.currentObservers=null,Ve(a,r)}))},t.prototype._checkFinalizedStatuses=function(r){var o=this,n=o.hasError,i=o.thrownError,s=o.isStopped;n?r.error(i):s&&r.complete()},t.prototype.asObservable=function(){var r=new j;return r.source=this,r},t.create=function(r,o){return new vo(r,o)},t}(j);var vo=function(e){se(t,e);function t(r,o){var n=e.call(this)||this;return n.destination=r,n.source=o,n}return t.prototype.next=function(r){var o,n;(n=(o=this.destination)===null||o===void 0?void 0:o.next)===null||n===void 0||n.call(o,r)},t.prototype.error=function(r){var o,n;(n=(o=this.destination)===null||o===void 0?void 0:o.error)===null||n===void 0||n.call(o,r)},t.prototype.complete=function(){var r,o;(o=(r=this.destination)===null||r===void 0?void 0:r.complete)===null||o===void 0||o.call(r)},t.prototype._subscribe=function(r){var o,n;return(n=(o=this.source)===null||o===void 0?void 0:o.subscribe(r))!==null&&n!==void 0?n:Er},t}(v);var St={now:function(){return(St.delegate||Date).now()},delegate:void 0};var Ot=function(e){se(t,e);function t(r,o,n){r===void 0&&(r=1/0),o===void 0&&(o=1/0),n===void 0&&(n=St);var i=e.call(this)||this;return i._bufferSize=r,i._windowTime=o,i._timestampProvider=n,i._buffer=[],i._infiniteTimeWindow=!0,i._infiniteTimeWindow=o===1/0,i._bufferSize=Math.max(1,r),i._windowTime=Math.max(1,o),i}return t.prototype.next=function(r){var o=this,n=o.isStopped,i=o._buffer,s=o._infiniteTimeWindow,a=o._timestampProvider,c=o._windowTime;n||(i.push(r),!s&&i.push(a.now()+c)),this._trimBuffer(),e.prototype.next.call(this,r)},t.prototype._subscribe=function(r){this._throwIfClosed(),this._trimBuffer();for(var o=this._innerSubscribe(r),n=this,i=n._infiniteTimeWindow,s=n._buffer,a=s.slice(),c=0;c0?e.prototype.requestAsyncId.call(this,r,o,n):(r.actions.push(this),r._scheduled||(r._scheduled=ut.requestAnimationFrame(function(){return r.flush(void 0)})))},t.prototype.recycleAsyncId=function(r,o,n){var i;if(n===void 0&&(n=0),n!=null?n>0:this.delay>0)return e.prototype.recycleAsyncId.call(this,r,o,n);var s=r.actions;o!=null&&((i=s[s.length-1])===null||i===void 0?void 0:i.id)!==o&&(ut.cancelAnimationFrame(o),r._scheduled=void 0)},t}(zt);var yo=function(e){se(t,e);function t(){return e!==null&&e.apply(this,arguments)||this}return t.prototype.flush=function(r){this._active=!0;var o=this._scheduled;this._scheduled=void 0;var n=this.actions,i;r=r||n.shift();do if(i=r.execute(r.state,r.delay))break;while((r=n[0])&&r.id===o&&n.shift());if(this._active=!1,i){for(;(r=n[0])&&r.id===o&&n.shift();)r.unsubscribe();throw i}},t}(qt);var de=new yo(xo);var L=new j(function(e){return e.complete()});function Kt(e){return e&&k(e.schedule)}function _r(e){return e[e.length-1]}function Je(e){return k(_r(e))?e.pop():void 0}function Ae(e){return Kt(_r(e))?e.pop():void 0}function Qt(e,t){return typeof _r(e)=="number"?e.pop():t}var dt=function(e){return e&&typeof e.length=="number"&&typeof e!="function"};function Yt(e){return k(e==null?void 0:e.then)}function Bt(e){return k(e[ft])}function Gt(e){return Symbol.asyncIterator&&k(e==null?void 0:e[Symbol.asyncIterator])}function Jt(e){return new TypeError("You provided "+(e!==null&&typeof e=="object"?"an invalid object":"'"+e+"'")+" where a stream was expected. You can provide an Observable, Promise, ReadableStream, Array, AsyncIterable, or Iterable.")}function Di(){return typeof Symbol!="function"||!Symbol.iterator?"@@iterator":Symbol.iterator}var Xt=Di();function Zt(e){return k(e==null?void 0:e[Xt])}function er(e){return ao(this,arguments,function(){var r,o,n,i;return Ut(this,function(s){switch(s.label){case 0:r=e.getReader(),s.label=1;case 1:s.trys.push([1,,9,10]),s.label=2;case 2:return[4,ot(r.read())];case 3:return o=s.sent(),n=o.value,i=o.done,i?[4,ot(void 0)]:[3,5];case 4:return[2,s.sent()];case 5:return[4,ot(n)];case 6:return[4,s.sent()];case 7:return s.sent(),[3,2];case 8:return[3,10];case 9:return r.releaseLock(),[7];case 10:return[2]}})})}function tr(e){return k(e==null?void 0:e.getReader)}function N(e){if(e instanceof j)return e;if(e!=null){if(Bt(e))return Ni(e);if(dt(e))return Vi(e);if(Yt(e))return zi(e);if(Gt(e))return Eo(e);if(Zt(e))return qi(e);if(tr(e))return Ki(e)}throw Jt(e)}function Ni(e){return new j(function(t){var r=e[ft]();if(k(r.subscribe))return r.subscribe(t);throw new TypeError("Provided object does not correctly implement Symbol.observable")})}function Vi(e){return new j(function(t){for(var r=0;r=2;return function(o){return o.pipe(e?g(function(n,i){return e(n,i,o)}):ce,ye(1),r?Qe(t):jo(function(){return new or}))}}function $r(e){return e<=0?function(){return L}:x(function(t,r){var o=[];t.subscribe(S(r,function(n){o.push(n),e=2,!0))}function le(e){e===void 0&&(e={});var t=e.connector,r=t===void 0?function(){return new v}:t,o=e.resetOnError,n=o===void 0?!0:o,i=e.resetOnComplete,s=i===void 0?!0:i,a=e.resetOnRefCountZero,c=a===void 0?!0:a;return function(p){var l,f,u,h=0,w=!1,A=!1,Z=function(){f==null||f.unsubscribe(),f=void 0},te=function(){Z(),l=u=void 0,w=A=!1},J=function(){var C=l;te(),C==null||C.unsubscribe()};return x(function(C,ct){h++,!A&&!w&&Z();var Ne=u=u!=null?u:r();ct.add(function(){h--,h===0&&!A&&!w&&(f=Pr(J,c))}),Ne.subscribe(ct),!l&&h>0&&(l=new it({next:function(Pe){return Ne.next(Pe)},error:function(Pe){A=!0,Z(),f=Pr(te,n,Pe),Ne.error(Pe)},complete:function(){w=!0,Z(),f=Pr(te,s),Ne.complete()}}),N(C).subscribe(l))})(p)}}function Pr(e,t){for(var r=[],o=2;oe.next(document)),e}function R(e,t=document){return Array.from(t.querySelectorAll(e))}function P(e,t=document){let r=me(e,t);if(typeof r=="undefined")throw new ReferenceError(`Missing element: expected "${e}" to be present`);return r}function me(e,t=document){return t.querySelector(e)||void 0}function Re(){var e,t,r,o;return(o=(r=(t=(e=document.activeElement)==null?void 0:e.shadowRoot)==null?void 0:t.activeElement)!=null?r:document.activeElement)!=null?o:void 0}var la=T(d(document.body,"focusin"),d(document.body,"focusout")).pipe(be(1),q(void 0),m(()=>Re()||document.body),B(1));function vt(e){return la.pipe(m(t=>e.contains(t)),Y())}function Vo(e,t){return T(d(e,"mouseenter").pipe(m(()=>!0)),d(e,"mouseleave").pipe(m(()=>!1))).pipe(t?be(t):ce,q(!1))}function Ue(e){return{x:e.offsetLeft,y:e.offsetTop}}function zo(e){return T(d(window,"load"),d(window,"resize")).pipe(Me(0,de),m(()=>Ue(e)),q(Ue(e)))}function ir(e){return{x:e.scrollLeft,y:e.scrollTop}}function et(e){return T(d(e,"scroll"),d(window,"resize")).pipe(Me(0,de),m(()=>ir(e)),q(ir(e)))}function qo(e,t){if(typeof t=="string"||typeof t=="number")e.innerHTML+=t.toString();else if(t instanceof Node)e.appendChild(t);else if(Array.isArray(t))for(let r of t)qo(e,r)}function E(e,t,...r){let o=document.createElement(e);if(t)for(let n of Object.keys(t))typeof t[n]!="undefined"&&(typeof t[n]!="boolean"?o.setAttribute(n,t[n]):o.setAttribute(n,""));for(let n of r)qo(o,n);return o}function ar(e){if(e>999){let t=+((e-950)%1e3>99);return`${((e+1e-6)/1e3).toFixed(t)}k`}else return e.toString()}function gt(e){let t=E("script",{src:e});return H(()=>(document.head.appendChild(t),T(d(t,"load"),d(t,"error").pipe(b(()=>Ar(()=>new ReferenceError(`Invalid script: ${e}`))))).pipe(m(()=>{}),_(()=>document.head.removeChild(t)),ye(1))))}var Ko=new v,ma=H(()=>typeof ResizeObserver=="undefined"?gt("https://unpkg.com/resize-observer-polyfill"):$(void 0)).pipe(m(()=>new ResizeObserver(e=>{for(let t of e)Ko.next(t)})),b(e=>T(qe,$(e)).pipe(_(()=>e.disconnect()))),B(1));function pe(e){return{width:e.offsetWidth,height:e.offsetHeight}}function Ee(e){return ma.pipe(y(t=>t.observe(e)),b(t=>Ko.pipe(g(({target:r})=>r===e),_(()=>t.unobserve(e)),m(()=>pe(e)))),q(pe(e)))}function xt(e){return{width:e.scrollWidth,height:e.scrollHeight}}function sr(e){let t=e.parentElement;for(;t&&(e.scrollWidth<=t.scrollWidth&&e.scrollHeight<=t.scrollHeight);)t=(e=t).parentElement;return t?e:void 0}var Qo=new v,fa=H(()=>$(new IntersectionObserver(e=>{for(let t of e)Qo.next(t)},{threshold:0}))).pipe(b(e=>T(qe,$(e)).pipe(_(()=>e.disconnect()))),B(1));function yt(e){return fa.pipe(y(t=>t.observe(e)),b(t=>Qo.pipe(g(({target:r})=>r===e),_(()=>t.unobserve(e)),m(({isIntersecting:r})=>r))))}function Yo(e,t=16){return et(e).pipe(m(({y:r})=>{let o=pe(e),n=xt(e);return r>=n.height-o.height-t}),Y())}var cr={drawer:P("[data-md-toggle=drawer]"),search:P("[data-md-toggle=search]")};function Bo(e){return cr[e].checked}function Be(e,t){cr[e].checked!==t&&cr[e].click()}function We(e){let t=cr[e];return d(t,"change").pipe(m(()=>t.checked),q(t.checked))}function ua(e,t){switch(e.constructor){case HTMLInputElement:return e.type==="radio"?/^Arrow/.test(t):!0;case HTMLSelectElement:case HTMLTextAreaElement:return!0;default:return e.isContentEditable}}function da(){return T(d(window,"compositionstart").pipe(m(()=>!0)),d(window,"compositionend").pipe(m(()=>!1))).pipe(q(!1))}function Go(){let e=d(window,"keydown").pipe(g(t=>!(t.metaKey||t.ctrlKey)),m(t=>({mode:Bo("search")?"search":"global",type:t.key,claim(){t.preventDefault(),t.stopPropagation()}})),g(({mode:t,type:r})=>{if(t==="global"){let o=Re();if(typeof o!="undefined")return!ua(o,r)}return!0}),le());return da().pipe(b(t=>t?L:e))}function ve(){return new URL(location.href)}function st(e,t=!1){if(G("navigation.instant")&&!t){let r=E("a",{href:e.href});document.body.appendChild(r),r.click(),r.remove()}else location.href=e.href}function Jo(){return new v}function Xo(){return location.hash.slice(1)}function Zo(e){let t=E("a",{href:e});t.addEventListener("click",r=>r.stopPropagation()),t.click()}function ha(e){return T(d(window,"hashchange"),e).pipe(m(Xo),q(Xo()),g(t=>t.length>0),B(1))}function en(e){return ha(e).pipe(m(t=>me(`[id="${t}"]`)),g(t=>typeof t!="undefined"))}function At(e){let t=matchMedia(e);return nr(r=>t.addListener(()=>r(t.matches))).pipe(q(t.matches))}function tn(){let e=matchMedia("print");return T(d(window,"beforeprint").pipe(m(()=>!0)),d(window,"afterprint").pipe(m(()=>!1))).pipe(q(e.matches))}function Ur(e,t){return e.pipe(b(r=>r?t():L))}function Wr(e,t){return new j(r=>{let o=new XMLHttpRequest;return o.open("GET",`${e}`),o.responseType="blob",o.addEventListener("load",()=>{o.status>=200&&o.status<300?(r.next(o.response),r.complete()):r.error(new Error(o.statusText))}),o.addEventListener("error",()=>{r.error(new Error("Network error"))}),o.addEventListener("abort",()=>{r.complete()}),typeof(t==null?void 0:t.progress$)!="undefined"&&(o.addEventListener("progress",n=>{var i;if(n.lengthComputable)t.progress$.next(n.loaded/n.total*100);else{let s=(i=o.getResponseHeader("Content-Length"))!=null?i:0;t.progress$.next(n.loaded/+s*100)}}),t.progress$.next(5)),o.send(),()=>o.abort()})}function De(e,t){return Wr(e,t).pipe(b(r=>r.text()),m(r=>JSON.parse(r)),B(1))}function rn(e,t){let r=new DOMParser;return Wr(e,t).pipe(b(o=>o.text()),m(o=>r.parseFromString(o,"text/html")),B(1))}function on(e,t){let r=new DOMParser;return Wr(e,t).pipe(b(o=>o.text()),m(o=>r.parseFromString(o,"text/xml")),B(1))}function nn(){return{x:Math.max(0,scrollX),y:Math.max(0,scrollY)}}function an(){return T(d(window,"scroll",{passive:!0}),d(window,"resize",{passive:!0})).pipe(m(nn),q(nn()))}function sn(){return{width:innerWidth,height:innerHeight}}function cn(){return d(window,"resize",{passive:!0}).pipe(m(sn),q(sn()))}function pn(){return Q([an(),cn()]).pipe(m(([e,t])=>({offset:e,size:t})),B(1))}function pr(e,{viewport$:t,header$:r}){let o=t.pipe(X("size")),n=Q([o,r]).pipe(m(()=>Ue(e)));return Q([r,t,n]).pipe(m(([{height:i},{offset:s,size:a},{x:c,y:p}])=>({offset:{x:s.x-c,y:s.y-p+i},size:a})))}function ba(e){return d(e,"message",t=>t.data)}function va(e){let t=new v;return t.subscribe(r=>e.postMessage(r)),t}function ln(e,t=new Worker(e)){let r=ba(t),o=va(t),n=new v;n.subscribe(o);let i=o.pipe(ee(),oe(!0));return n.pipe(ee(),$e(r.pipe(U(i))),le())}var ga=P("#__config"),Et=JSON.parse(ga.textContent);Et.base=`${new URL(Et.base,ve())}`;function we(){return Et}function G(e){return Et.features.includes(e)}function ge(e,t){return typeof t!="undefined"?Et.translations[e].replace("#",t.toString()):Et.translations[e]}function Te(e,t=document){return P(`[data-md-component=${e}]`,t)}function ne(e,t=document){return R(`[data-md-component=${e}]`,t)}function xa(e){let t=P(".md-typeset > :first-child",e);return d(t,"click",{once:!0}).pipe(m(()=>P(".md-typeset",e)),m(r=>({hash:__md_hash(r.innerHTML)})))}function mn(e){if(!G("announce.dismiss")||!e.childElementCount)return L;if(!e.hidden){let t=P(".md-typeset",e);__md_hash(t.innerHTML)===__md_get("__announce")&&(e.hidden=!0)}return H(()=>{let t=new v;return t.subscribe(({hash:r})=>{e.hidden=!0,__md_set("__announce",r)}),xa(e).pipe(y(r=>t.next(r)),_(()=>t.complete()),m(r=>F({ref:e},r)))})}function ya(e,{target$:t}){return t.pipe(m(r=>({hidden:r!==e})))}function fn(e,t){let r=new v;return r.subscribe(({hidden:o})=>{e.hidden=o}),ya(e,t).pipe(y(o=>r.next(o)),_(()=>r.complete()),m(o=>F({ref:e},o)))}function Ct(e,t){return t==="inline"?E("div",{class:"md-tooltip md-tooltip--inline",id:e,role:"tooltip"},E("div",{class:"md-tooltip__inner md-typeset"})):E("div",{class:"md-tooltip",id:e,role:"tooltip"},E("div",{class:"md-tooltip__inner md-typeset"}))}function un(e,t){if(t=t?`${t}_annotation_${e}`:void 0,t){let r=t?`#${t}`:void 0;return E("aside",{class:"md-annotation",tabIndex:0},Ct(t),E("a",{href:r,class:"md-annotation__index",tabIndex:-1},E("span",{"data-md-annotation-id":e})))}else return E("aside",{class:"md-annotation",tabIndex:0},Ct(t),E("span",{class:"md-annotation__index",tabIndex:-1},E("span",{"data-md-annotation-id":e})))}function dn(e){return E("button",{class:"md-clipboard md-icon",title:ge("clipboard.copy"),"data-clipboard-target":`#${e} > code`})}function Dr(e,t){let r=t&2,o=t&1,n=Object.keys(e.terms).filter(c=>!e.terms[c]).reduce((c,p)=>[...c,E("del",null,p)," "],[]).slice(0,-1),i=we(),s=new URL(e.location,i.base);G("search.highlight")&&s.searchParams.set("h",Object.entries(e.terms).filter(([,c])=>c).reduce((c,[p])=>`${c} ${p}`.trim(),""));let{tags:a}=we();return E("a",{href:`${s}`,class:"md-search-result__link",tabIndex:-1},E("article",{class:"md-search-result__article md-typeset","data-md-score":e.score.toFixed(2)},r>0&&E("div",{class:"md-search-result__icon md-icon"}),r>0&&E("h1",null,e.title),r<=0&&E("h2",null,e.title),o>0&&e.text.length>0&&e.text,e.tags&&e.tags.map(c=>{let p=a?c in a?`md-tag-icon md-tag--${a[c]}`:"md-tag-icon":"";return E("span",{class:`md-tag ${p}`},c)}),o>0&&n.length>0&&E("p",{class:"md-search-result__terms"},ge("search.result.term.missing"),": ",...n)))}function hn(e){let t=e[0].score,r=[...e],o=we(),n=r.findIndex(l=>!`${new URL(l.location,o.base)}`.includes("#")),[i]=r.splice(n,1),s=r.findIndex(l=>l.scoreDr(l,1)),...c.length?[E("details",{class:"md-search-result__more"},E("summary",{tabIndex:-1},E("div",null,c.length>0&&c.length===1?ge("search.result.more.one"):ge("search.result.more.other",c.length))),...c.map(l=>Dr(l,1)))]:[]];return E("li",{class:"md-search-result__item"},p)}function bn(e){return E("ul",{class:"md-source__facts"},Object.entries(e).map(([t,r])=>E("li",{class:`md-source__fact md-source__fact--${t}`},typeof r=="number"?ar(r):r)))}function Nr(e){let t=`tabbed-control tabbed-control--${e}`;return E("div",{class:t,hidden:!0},E("button",{class:"tabbed-button",tabIndex:-1,"aria-hidden":"true"}))}function vn(e){return E("div",{class:"md-typeset__scrollwrap"},E("div",{class:"md-typeset__table"},e))}function Ea(e){let t=we(),r=new URL(`../${e.version}/`,t.base);return E("li",{class:"md-version__item"},E("a",{href:`${r}`,class:"md-version__link"},e.title))}function gn(e,t){return E("div",{class:"md-version"},E("button",{class:"md-version__current","aria-label":ge("select.version")},t.title),E("ul",{class:"md-version__list"},e.map(Ea)))}var wa=0;function Ta(e,t){document.body.append(e);let{width:r}=pe(e);e.style.setProperty("--md-tooltip-width",`${r}px`),e.remove();let o=sr(t),n=typeof o!="undefined"?et(o):$({x:0,y:0}),i=T(vt(t),Vo(t)).pipe(Y());return Q([i,n]).pipe(m(([s,a])=>{let{x:c,y:p}=Ue(t),l=pe(t),f=t.closest("table");return f&&t.parentElement&&(c+=f.offsetLeft+t.parentElement.offsetLeft,p+=f.offsetTop+t.parentElement.offsetTop),{active:s,offset:{x:c-a.x+l.width/2-r/2,y:p-a.y+l.height+8}}}))}function Ge(e){let t=e.title;if(!t.length)return L;let r=`__tooltip_${wa++}`,o=Ct(r,"inline"),n=P(".md-typeset",o);return n.innerHTML=t,H(()=>{let i=new v;return i.subscribe({next({offset:s}){o.style.setProperty("--md-tooltip-x",`${s.x}px`),o.style.setProperty("--md-tooltip-y",`${s.y}px`)},complete(){o.style.removeProperty("--md-tooltip-x"),o.style.removeProperty("--md-tooltip-y")}}),T(i.pipe(g(({active:s})=>s)),i.pipe(be(250),g(({active:s})=>!s))).subscribe({next({active:s}){s?(e.insertAdjacentElement("afterend",o),e.setAttribute("aria-describedby",r),e.removeAttribute("title")):(o.remove(),e.removeAttribute("aria-describedby"),e.setAttribute("title",t))},complete(){o.remove(),e.removeAttribute("aria-describedby"),e.setAttribute("title",t)}}),i.pipe(Me(16,de)).subscribe(({active:s})=>{o.classList.toggle("md-tooltip--active",s)}),i.pipe(_t(125,de),g(()=>!!e.offsetParent),m(()=>e.offsetParent.getBoundingClientRect()),m(({x:s})=>s)).subscribe({next(s){s?o.style.setProperty("--md-tooltip-0",`${-s}px`):o.style.removeProperty("--md-tooltip-0")},complete(){o.style.removeProperty("--md-tooltip-0")}}),Ta(o,e).pipe(y(s=>i.next(s)),_(()=>i.complete()),m(s=>F({ref:e},s)))}).pipe(ze(ie))}function Sa(e,t){let r=H(()=>Q([zo(e),et(t)])).pipe(m(([{x:o,y:n},i])=>{let{width:s,height:a}=pe(e);return{x:o-i.x+s/2,y:n-i.y+a/2}}));return vt(e).pipe(b(o=>r.pipe(m(n=>({active:o,offset:n})),ye(+!o||1/0))))}function xn(e,t,{target$:r}){let[o,n]=Array.from(e.children);return H(()=>{let i=new v,s=i.pipe(ee(),oe(!0));return i.subscribe({next({offset:a}){e.style.setProperty("--md-tooltip-x",`${a.x}px`),e.style.setProperty("--md-tooltip-y",`${a.y}px`)},complete(){e.style.removeProperty("--md-tooltip-x"),e.style.removeProperty("--md-tooltip-y")}}),yt(e).pipe(U(s)).subscribe(a=>{e.toggleAttribute("data-md-visible",a)}),T(i.pipe(g(({active:a})=>a)),i.pipe(be(250),g(({active:a})=>!a))).subscribe({next({active:a}){a?e.prepend(o):o.remove()},complete(){e.prepend(o)}}),i.pipe(Me(16,de)).subscribe(({active:a})=>{o.classList.toggle("md-tooltip--active",a)}),i.pipe(_t(125,de),g(()=>!!e.offsetParent),m(()=>e.offsetParent.getBoundingClientRect()),m(({x:a})=>a)).subscribe({next(a){a?e.style.setProperty("--md-tooltip-0",`${-a}px`):e.style.removeProperty("--md-tooltip-0")},complete(){e.style.removeProperty("--md-tooltip-0")}}),d(n,"click").pipe(U(s),g(a=>!(a.metaKey||a.ctrlKey))).subscribe(a=>{a.stopPropagation(),a.preventDefault()}),d(n,"mousedown").pipe(U(s),ae(i)).subscribe(([a,{active:c}])=>{var p;if(a.button!==0||a.metaKey||a.ctrlKey)a.preventDefault();else if(c){a.preventDefault();let l=e.parentElement.closest(".md-annotation");l instanceof HTMLElement?l.focus():(p=Re())==null||p.blur()}}),r.pipe(U(s),g(a=>a===o),Ye(125)).subscribe(()=>e.focus()),Sa(e,t).pipe(y(a=>i.next(a)),_(()=>i.complete()),m(a=>F({ref:e},a)))})}function Oa(e){return e.tagName==="CODE"?R(".c, .c1, .cm",e):[e]}function Ma(e){let t=[];for(let r of Oa(e)){let o=[],n=document.createNodeIterator(r,NodeFilter.SHOW_TEXT);for(let i=n.nextNode();i;i=n.nextNode())o.push(i);for(let i of o){let s;for(;s=/(\(\d+\))(!)?/.exec(i.textContent);){let[,a,c]=s;if(typeof c=="undefined"){let p=i.splitText(s.index);i=p.splitText(a.length),t.push(p)}else{i.textContent=a,t.push(i);break}}}}return t}function yn(e,t){t.append(...Array.from(e.childNodes))}function lr(e,t,{target$:r,print$:o}){let n=t.closest("[id]"),i=n==null?void 0:n.id,s=new Map;for(let a of Ma(t)){let[,c]=a.textContent.match(/\((\d+)\)/);me(`:scope > li:nth-child(${c})`,e)&&(s.set(c,un(c,i)),a.replaceWith(s.get(c)))}return s.size===0?L:H(()=>{let a=new v,c=a.pipe(ee(),oe(!0)),p=[];for(let[l,f]of s)p.push([P(".md-typeset",f),P(`:scope > li:nth-child(${l})`,e)]);return o.pipe(U(c)).subscribe(l=>{e.hidden=!l,e.classList.toggle("md-annotation-list",l);for(let[f,u]of p)l?yn(f,u):yn(u,f)}),T(...[...s].map(([,l])=>xn(l,t,{target$:r}))).pipe(_(()=>a.complete()),le())})}function En(e){if(e.nextElementSibling){let t=e.nextElementSibling;if(t.tagName==="OL")return t;if(t.tagName==="P"&&!t.children.length)return En(t)}}function wn(e,t){return H(()=>{let r=En(e);return typeof r!="undefined"?lr(r,e,t):L})}var Tn=jt(zr());var La=0;function Sn(e){if(e.nextElementSibling){let t=e.nextElementSibling;if(t.tagName==="OL")return t;if(t.tagName==="P"&&!t.children.length)return Sn(t)}}function _a(e){return Ee(e).pipe(m(({width:t})=>({scrollable:xt(e).width>t})),X("scrollable"))}function On(e,t){let{matches:r}=matchMedia("(hover)"),o=H(()=>{let n=new v,i=n.pipe($r(1));n.subscribe(({scrollable:c})=>{c&&r?e.setAttribute("tabindex","0"):e.removeAttribute("tabindex")});let s=[];if(Tn.default.isSupported()&&(e.closest(".copy")||G("content.code.copy")&&!e.closest(".no-copy"))){let c=e.closest("pre");c.id=`__code_${La++}`;let p=dn(c.id);c.insertBefore(p,e),G("content.tooltips")&&s.push(Ge(p))}let a=e.closest(".highlight");if(a instanceof HTMLElement){let c=Sn(a);if(typeof c!="undefined"&&(a.classList.contains("annotate")||G("content.code.annotate"))){let p=lr(c,e,t);s.push(Ee(a).pipe(U(i),m(({width:l,height:f})=>l&&f),Y(),b(l=>l?p:L)))}}return _a(e).pipe(y(c=>n.next(c)),_(()=>n.complete()),m(c=>F({ref:e},c)),$e(...s))});return G("content.lazy")?yt(e).pipe(g(n=>n),ye(1),b(()=>o)):o}function Aa(e,{target$:t,print$:r}){let o=!0;return T(t.pipe(m(n=>n.closest("details:not([open])")),g(n=>e===n),m(()=>({action:"open",reveal:!0}))),r.pipe(g(n=>n||!o),y(()=>o=e.open),m(n=>({action:n?"open":"close"}))))}function Mn(e,t){return H(()=>{let r=new v;return r.subscribe(({action:o,reveal:n})=>{e.toggleAttribute("open",o==="open"),n&&e.scrollIntoView()}),Aa(e,t).pipe(y(o=>r.next(o)),_(()=>r.complete()),m(o=>F({ref:e},o)))})}var Ln=".node circle,.node ellipse,.node path,.node polygon,.node rect{fill:var(--md-mermaid-node-bg-color);stroke:var(--md-mermaid-node-fg-color)}marker{fill:var(--md-mermaid-edge-color)!important}.edgeLabel .label rect{fill:#0000}.label{color:var(--md-mermaid-label-fg-color);font-family:var(--md-mermaid-font-family)}.label foreignObject{line-height:normal;overflow:visible}.label div .edgeLabel{color:var(--md-mermaid-label-fg-color)}.edgeLabel,.edgeLabel rect,.label div .edgeLabel{background-color:var(--md-mermaid-label-bg-color)}.edgeLabel,.edgeLabel rect{fill:var(--md-mermaid-label-bg-color);color:var(--md-mermaid-edge-color)}.edgePath .path,.flowchart-link{stroke:var(--md-mermaid-edge-color);stroke-width:.05rem}.edgePath .arrowheadPath{fill:var(--md-mermaid-edge-color);stroke:none}.cluster rect{fill:var(--md-default-fg-color--lightest);stroke:var(--md-default-fg-color--lighter)}.cluster span{color:var(--md-mermaid-label-fg-color);font-family:var(--md-mermaid-font-family)}g #flowchart-circleEnd,g #flowchart-circleStart,g #flowchart-crossEnd,g #flowchart-crossStart,g #flowchart-pointEnd,g #flowchart-pointStart{stroke:none}g.classGroup line,g.classGroup rect{fill:var(--md-mermaid-node-bg-color);stroke:var(--md-mermaid-node-fg-color)}g.classGroup text{fill:var(--md-mermaid-label-fg-color);font-family:var(--md-mermaid-font-family)}.classLabel .box{fill:var(--md-mermaid-label-bg-color);background-color:var(--md-mermaid-label-bg-color);opacity:1}.classLabel .label{fill:var(--md-mermaid-label-fg-color);font-family:var(--md-mermaid-font-family)}.node .divider{stroke:var(--md-mermaid-node-fg-color)}.relation{stroke:var(--md-mermaid-edge-color)}.cardinality{fill:var(--md-mermaid-label-fg-color);font-family:var(--md-mermaid-font-family)}.cardinality text{fill:inherit!important}defs #classDiagram-compositionEnd,defs #classDiagram-compositionStart,defs #classDiagram-dependencyEnd,defs #classDiagram-dependencyStart,defs #classDiagram-extensionEnd,defs #classDiagram-extensionStart{fill:var(--md-mermaid-edge-color)!important;stroke:var(--md-mermaid-edge-color)!important}defs #classDiagram-aggregationEnd,defs #classDiagram-aggregationStart{fill:var(--md-mermaid-label-bg-color)!important;stroke:var(--md-mermaid-edge-color)!important}g.stateGroup rect{fill:var(--md-mermaid-node-bg-color);stroke:var(--md-mermaid-node-fg-color)}g.stateGroup .state-title{fill:var(--md-mermaid-label-fg-color)!important;font-family:var(--md-mermaid-font-family)}g.stateGroup .composit{fill:var(--md-mermaid-label-bg-color)}.nodeLabel,.nodeLabel p{color:var(--md-mermaid-label-fg-color);font-family:var(--md-mermaid-font-family)}.node circle.state-end,.node circle.state-start,.start-state{fill:var(--md-mermaid-edge-color);stroke:none}.end-state-inner,.end-state-outer{fill:var(--md-mermaid-edge-color)}.end-state-inner,.node circle.state-end{stroke:var(--md-mermaid-label-bg-color)}.transition{stroke:var(--md-mermaid-edge-color)}[id^=state-fork] rect,[id^=state-join] rect{fill:var(--md-mermaid-edge-color)!important;stroke:none!important}.statediagram-cluster.statediagram-cluster .inner{fill:var(--md-default-bg-color)}.statediagram-cluster rect{fill:var(--md-mermaid-node-bg-color);stroke:var(--md-mermaid-node-fg-color)}.statediagram-state rect.divider{fill:var(--md-default-fg-color--lightest);stroke:var(--md-default-fg-color--lighter)}defs #statediagram-barbEnd{stroke:var(--md-mermaid-edge-color)}.attributeBoxEven,.attributeBoxOdd{fill:var(--md-mermaid-node-bg-color);stroke:var(--md-mermaid-node-fg-color)}.entityBox{fill:var(--md-mermaid-label-bg-color);stroke:var(--md-mermaid-node-fg-color)}.entityLabel{fill:var(--md-mermaid-label-fg-color);font-family:var(--md-mermaid-font-family)}.relationshipLabelBox{fill:var(--md-mermaid-label-bg-color);fill-opacity:1;background-color:var(--md-mermaid-label-bg-color);opacity:1}.relationshipLabel{fill:var(--md-mermaid-label-fg-color)}.relationshipLine{stroke:var(--md-mermaid-edge-color)}defs #ONE_OR_MORE_END *,defs #ONE_OR_MORE_START *,defs #ONLY_ONE_END *,defs #ONLY_ONE_START *,defs #ZERO_OR_MORE_END *,defs #ZERO_OR_MORE_START *,defs #ZERO_OR_ONE_END *,defs #ZERO_OR_ONE_START *{stroke:var(--md-mermaid-edge-color)!important}defs #ZERO_OR_MORE_END circle,defs #ZERO_OR_MORE_START circle{fill:var(--md-mermaid-label-bg-color)}.actor{fill:var(--md-mermaid-sequence-actor-bg-color);stroke:var(--md-mermaid-sequence-actor-border-color)}text.actor>tspan{fill:var(--md-mermaid-sequence-actor-fg-color);font-family:var(--md-mermaid-font-family)}line{stroke:var(--md-mermaid-sequence-actor-line-color)}.actor-man circle,.actor-man line{fill:var(--md-mermaid-sequence-actorman-bg-color);stroke:var(--md-mermaid-sequence-actorman-line-color)}.messageLine0,.messageLine1{stroke:var(--md-mermaid-sequence-message-line-color)}.note{fill:var(--md-mermaid-sequence-note-bg-color);stroke:var(--md-mermaid-sequence-note-border-color)}.loopText,.loopText>tspan,.messageText,.noteText>tspan{stroke:none;font-family:var(--md-mermaid-font-family)!important}.messageText{fill:var(--md-mermaid-sequence-message-fg-color)}.loopText,.loopText>tspan{fill:var(--md-mermaid-sequence-loop-fg-color)}.noteText>tspan{fill:var(--md-mermaid-sequence-note-fg-color)}#arrowhead path{fill:var(--md-mermaid-sequence-message-line-color);stroke:none}.loopLine{fill:var(--md-mermaid-sequence-loop-bg-color);stroke:var(--md-mermaid-sequence-loop-border-color)}.labelBox{fill:var(--md-mermaid-sequence-label-bg-color);stroke:none}.labelText,.labelText>span{fill:var(--md-mermaid-sequence-label-fg-color);font-family:var(--md-mermaid-font-family)}.sequenceNumber{fill:var(--md-mermaid-sequence-number-fg-color)}rect.rect{fill:var(--md-mermaid-sequence-box-bg-color);stroke:none}rect.rect+text.text{fill:var(--md-mermaid-sequence-box-fg-color)}defs #sequencenumber{fill:var(--md-mermaid-sequence-number-bg-color)!important}";var qr,ka=0;function Ha(){return typeof mermaid=="undefined"||mermaid instanceof Element?gt("https://unpkg.com/mermaid@10.7.0/dist/mermaid.min.js"):$(void 0)}function _n(e){return e.classList.remove("mermaid"),qr||(qr=Ha().pipe(y(()=>mermaid.initialize({startOnLoad:!1,themeCSS:Ln,sequence:{actorFontSize:"16px",messageFontSize:"16px",noteFontSize:"16px"}})),m(()=>{}),B(1))),qr.subscribe(()=>ro(this,null,function*(){e.classList.add("mermaid");let t=`__mermaid_${ka++}`,r=E("div",{class:"mermaid"}),o=e.textContent,{svg:n,fn:i}=yield mermaid.render(t,o),s=r.attachShadow({mode:"closed"});s.innerHTML=n,e.replaceWith(r),i==null||i(s)})),qr.pipe(m(()=>({ref:e})))}var An=E("table");function Cn(e){return e.replaceWith(An),An.replaceWith(vn(e)),$({ref:e})}function $a(e){let t=e.find(r=>r.checked)||e[0];return T(...e.map(r=>d(r,"change").pipe(m(()=>P(`label[for="${r.id}"]`))))).pipe(q(P(`label[for="${t.id}"]`)),m(r=>({active:r})))}function kn(e,{viewport$:t,target$:r}){let o=P(".tabbed-labels",e),n=R(":scope > input",e),i=Nr("prev");e.append(i);let s=Nr("next");return e.append(s),H(()=>{let a=new v,c=a.pipe(ee(),oe(!0));Q([a,Ee(e)]).pipe(U(c),Me(1,de)).subscribe({next([{active:p},l]){let f=Ue(p),{width:u}=pe(p);e.style.setProperty("--md-indicator-x",`${f.x}px`),e.style.setProperty("--md-indicator-width",`${u}px`);let h=ir(o);(f.xh.x+l.width)&&o.scrollTo({left:Math.max(0,f.x-16),behavior:"smooth"})},complete(){e.style.removeProperty("--md-indicator-x"),e.style.removeProperty("--md-indicator-width")}}),Q([et(o),Ee(o)]).pipe(U(c)).subscribe(([p,l])=>{let f=xt(o);i.hidden=p.x<16,s.hidden=p.x>f.width-l.width-16}),T(d(i,"click").pipe(m(()=>-1)),d(s,"click").pipe(m(()=>1))).pipe(U(c)).subscribe(p=>{let{width:l}=pe(o);o.scrollBy({left:l*p,behavior:"smooth"})}),r.pipe(U(c),g(p=>n.includes(p))).subscribe(p=>p.click()),o.classList.add("tabbed-labels--linked");for(let p of n){let l=P(`label[for="${p.id}"]`);l.replaceChildren(E("a",{href:`#${l.htmlFor}`,tabIndex:-1},...Array.from(l.childNodes))),d(l.firstElementChild,"click").pipe(U(c),g(f=>!(f.metaKey||f.ctrlKey)),y(f=>{f.preventDefault(),f.stopPropagation()})).subscribe(()=>{history.replaceState({},"",`#${l.htmlFor}`),l.click()})}return G("content.tabs.link")&&a.pipe(Le(1),ae(t)).subscribe(([{active:p},{offset:l}])=>{let f=p.innerText.trim();if(p.hasAttribute("data-md-switching"))p.removeAttribute("data-md-switching");else{let u=e.offsetTop-l.y;for(let w of R("[data-tabs]"))for(let A of R(":scope > input",w)){let Z=P(`label[for="${A.id}"]`);if(Z!==p&&Z.innerText.trim()===f){Z.setAttribute("data-md-switching",""),A.click();break}}window.scrollTo({top:e.offsetTop-u});let h=__md_get("__tabs")||[];__md_set("__tabs",[...new Set([f,...h])])}}),a.pipe(U(c)).subscribe(()=>{for(let p of R("audio, video",e))p.pause()}),$a(n).pipe(y(p=>a.next(p)),_(()=>a.complete()),m(p=>F({ref:e},p)))}).pipe(ze(ie))}function Hn(e,{viewport$:t,target$:r,print$:o}){return T(...R(".annotate:not(.highlight)",e).map(n=>wn(n,{target$:r,print$:o})),...R("pre:not(.mermaid) > code",e).map(n=>On(n,{target$:r,print$:o})),...R("pre.mermaid",e).map(n=>_n(n)),...R("table:not([class])",e).map(n=>Cn(n)),...R("details",e).map(n=>Mn(n,{target$:r,print$:o})),...R("[data-tabs]",e).map(n=>kn(n,{viewport$:t,target$:r})),...R("[title]",e).filter(()=>G("content.tooltips")).map(n=>Ge(n)))}function Ra(e,{alert$:t}){return t.pipe(b(r=>T($(!0),$(!1).pipe(Ye(2e3))).pipe(m(o=>({message:r,active:o})))))}function $n(e,t){let r=P(".md-typeset",e);return H(()=>{let o=new v;return o.subscribe(({message:n,active:i})=>{e.classList.toggle("md-dialog--active",i),r.textContent=n}),Ra(e,t).pipe(y(n=>o.next(n)),_(()=>o.complete()),m(n=>F({ref:e},n)))})}function Pa({viewport$:e}){if(!G("header.autohide"))return $(!1);let t=e.pipe(m(({offset:{y:n}})=>n),Ke(2,1),m(([n,i])=>[nMath.abs(i-n.y)>100),m(([,[n]])=>n),Y()),o=We("search");return Q([e,o]).pipe(m(([{offset:n},i])=>n.y>400&&!i),Y(),b(n=>n?r:$(!1)),q(!1))}function Rn(e,t){return H(()=>Q([Ee(e),Pa(t)])).pipe(m(([{height:r},o])=>({height:r,hidden:o})),Y((r,o)=>r.height===o.height&&r.hidden===o.hidden),B(1))}function Pn(e,{header$:t,main$:r}){return H(()=>{let o=new v,n=o.pipe(ee(),oe(!0));o.pipe(X("active"),je(t)).subscribe(([{active:s},{hidden:a}])=>{e.classList.toggle("md-header--shadow",s&&!a),e.hidden=a});let i=fe(R("[title]",e)).pipe(g(()=>G("content.tooltips")),re(s=>Ge(s)));return r.subscribe(o),t.pipe(U(n),m(s=>F({ref:e},s)),$e(i.pipe(U(n))))})}function Ia(e,{viewport$:t,header$:r}){return pr(e,{viewport$:t,header$:r}).pipe(m(({offset:{y:o}})=>{let{height:n}=pe(e);return{active:o>=n}}),X("active"))}function In(e,t){return H(()=>{let r=new v;r.subscribe({next({active:n}){e.classList.toggle("md-header__title--active",n)},complete(){e.classList.remove("md-header__title--active")}});let o=me(".md-content h1");return typeof o=="undefined"?L:Ia(o,t).pipe(y(n=>r.next(n)),_(()=>r.complete()),m(n=>F({ref:e},n)))})}function Fn(e,{viewport$:t,header$:r}){let o=r.pipe(m(({height:i})=>i),Y()),n=o.pipe(b(()=>Ee(e).pipe(m(({height:i})=>({top:e.offsetTop,bottom:e.offsetTop+i})),X("bottom"))));return Q([o,n,t]).pipe(m(([i,{top:s,bottom:a},{offset:{y:c},size:{height:p}}])=>(p=Math.max(0,p-Math.max(0,s-c,i)-Math.max(0,p+c-a)),{offset:s-i,height:p,active:s-i<=c})),Y((i,s)=>i.offset===s.offset&&i.height===s.height&&i.active===s.active))}function Fa(e){let t=__md_get("__palette")||{index:e.findIndex(o=>matchMedia(o.getAttribute("data-md-color-media")).matches)},r=Math.max(0,Math.min(t.index,e.length-1));return $(...e).pipe(re(o=>d(o,"change").pipe(m(()=>o))),q(e[r]),m(o=>({index:e.indexOf(o),color:{media:o.getAttribute("data-md-color-media"),scheme:o.getAttribute("data-md-color-scheme"),primary:o.getAttribute("data-md-color-primary"),accent:o.getAttribute("data-md-color-accent")}})),B(1))}function jn(e){let t=R("input",e),r=E("meta",{name:"theme-color"});document.head.appendChild(r);let o=E("meta",{name:"color-scheme"});document.head.appendChild(o);let n=At("(prefers-color-scheme: light)");return H(()=>{let i=new v;return i.subscribe(s=>{if(document.body.setAttribute("data-md-color-switching",""),s.color.media==="(prefers-color-scheme)"){let a=matchMedia("(prefers-color-scheme: light)"),c=document.querySelector(a.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");s.color.scheme=c.getAttribute("data-md-color-scheme"),s.color.primary=c.getAttribute("data-md-color-primary"),s.color.accent=c.getAttribute("data-md-color-accent")}for(let[a,c]of Object.entries(s.color))document.body.setAttribute(`data-md-color-${a}`,c);for(let a=0;a{let s=Te("header"),a=window.getComputedStyle(s);return o.content=a.colorScheme,a.backgroundColor.match(/\d+/g).map(c=>(+c).toString(16).padStart(2,"0")).join("")})).subscribe(s=>r.content=`#${s}`),i.pipe(Oe(ie)).subscribe(()=>{document.body.removeAttribute("data-md-color-switching")}),Fa(t).pipe(U(n.pipe(Le(1))),at(),y(s=>i.next(s)),_(()=>i.complete()),m(s=>F({ref:e},s)))})}function Un(e,{progress$:t}){return H(()=>{let r=new v;return r.subscribe(({value:o})=>{e.style.setProperty("--md-progress-value",`${o}`)}),t.pipe(y(o=>r.next({value:o})),_(()=>r.complete()),m(o=>({ref:e,value:o})))})}var Kr=jt(zr());function ja(e){e.setAttribute("data-md-copying","");let t=e.closest("[data-copy]"),r=t?t.getAttribute("data-copy"):e.innerText;return e.removeAttribute("data-md-copying"),r.trimEnd()}function Wn({alert$:e}){Kr.default.isSupported()&&new j(t=>{new Kr.default("[data-clipboard-target], [data-clipboard-text]",{text:r=>r.getAttribute("data-clipboard-text")||ja(P(r.getAttribute("data-clipboard-target")))}).on("success",r=>t.next(r))}).pipe(y(t=>{t.trigger.focus()}),m(()=>ge("clipboard.copied"))).subscribe(e)}function Dn(e,t){return e.protocol=t.protocol,e.hostname=t.hostname,e}function Ua(e,t){let r=new Map;for(let o of R("url",e)){let n=P("loc",o),i=[Dn(new URL(n.textContent),t)];r.set(`${i[0]}`,i);for(let s of R("[rel=alternate]",o)){let a=s.getAttribute("href");a!=null&&i.push(Dn(new URL(a),t))}}return r}function mr(e){return on(new URL("sitemap.xml",e)).pipe(m(t=>Ua(t,new URL(e))),he(()=>$(new Map)))}function Wa(e,t){if(!(e.target instanceof Element))return L;let r=e.target.closest("a");if(r===null)return L;if(r.target||e.metaKey||e.ctrlKey)return L;let o=new URL(r.href);return o.search=o.hash="",t.has(`${o}`)?(e.preventDefault(),$(new URL(r.href))):L}function Nn(e){let t=new Map;for(let r of R(":scope > *",e.head))t.set(r.outerHTML,r);return t}function Vn(e){for(let t of R("[href], [src]",e))for(let r of["href","src"]){let o=t.getAttribute(r);if(o&&!/^(?:[a-z]+:)?\/\//i.test(o)){t[r]=t[r];break}}return $(e)}function Da(e){for(let o of["[data-md-component=announce]","[data-md-component=container]","[data-md-component=header-topic]","[data-md-component=outdated]","[data-md-component=logo]","[data-md-component=skip]",...G("navigation.tabs.sticky")?["[data-md-component=tabs]"]:[]]){let n=me(o),i=me(o,e);typeof n!="undefined"&&typeof i!="undefined"&&n.replaceWith(i)}let t=Nn(document);for(let[o,n]of Nn(e))t.has(o)?t.delete(o):document.head.appendChild(n);for(let o of t.values())o.remove();let r=Te("container");return Fe(R("script",r)).pipe(b(o=>{let n=e.createElement("script");if(o.src){for(let i of o.getAttributeNames())n.setAttribute(i,o.getAttribute(i));return o.replaceWith(n),new j(i=>{n.onload=()=>i.complete()})}else return n.textContent=o.textContent,o.replaceWith(n),L}),ee(),oe(e))}function zn({location$:e,viewport$:t,progress$:r}){let o=we();if(location.protocol==="file:")return L;let n=mr(o.base);$(document).subscribe(Vn);let i=d(document.body,"click").pipe(je(n),b(([c,p])=>Wa(c,p)),le()),s=d(window,"popstate").pipe(m(ve),le());i.pipe(ae(t)).subscribe(([c,{offset:p}])=>{history.replaceState(p,""),history.pushState(null,"",c)}),T(i,s).subscribe(e);let a=e.pipe(X("pathname"),b(c=>rn(c,{progress$:r}).pipe(he(()=>(st(c,!0),L)))),b(Vn),b(Da),le());return T(a.pipe(ae(e,(c,p)=>p)),e.pipe(X("pathname"),b(()=>e),X("hash")),e.pipe(Y((c,p)=>c.pathname===p.pathname&&c.hash===p.hash),b(()=>i),y(()=>history.back()))).subscribe(c=>{var p,l;history.state!==null||!c.hash?window.scrollTo(0,(l=(p=history.state)==null?void 0:p.y)!=null?l:0):(history.scrollRestoration="auto",Zo(c.hash),history.scrollRestoration="manual")}),e.subscribe(()=>{history.scrollRestoration="manual"}),d(window,"beforeunload").subscribe(()=>{history.scrollRestoration="auto"}),t.pipe(X("offset"),be(100)).subscribe(({offset:c})=>{history.replaceState(c,"")}),a}var Qn=jt(Kn());function Yn(e){let t=e.separator.split("|").map(n=>n.replace(/(\(\?[!=<][^)]+\))/g,"").length===0?"\uFFFD":n).join("|"),r=new RegExp(t,"img"),o=(n,i,s)=>`${i}${s}`;return n=>{n=n.replace(/[\s*+\-:~^]+/g," ").trim();let i=new RegExp(`(^|${e.separator}|)(${n.replace(/[|\\{}()[\]^$+*?.-]/g,"\\$&").replace(r,"|")})`,"img");return s=>(0,Qn.default)(s).replace(i,o).replace(/<\/mark>(\s+)]*>/img,"$1")}}function Ht(e){return e.type===1}function fr(e){return e.type===3}function Bn(e,t){let r=ln(e);return T($(location.protocol!=="file:"),We("search")).pipe(He(o=>o),b(()=>t)).subscribe(({config:o,docs:n})=>r.next({type:0,data:{config:o,docs:n,options:{suggest:G("search.suggest")}}})),r}function Gn({document$:e}){let t=we(),r=De(new URL("../versions.json",t.base)).pipe(he(()=>L)),o=r.pipe(m(n=>{let[,i]=t.base.match(/([^/]+)\/?$/);return n.find(({version:s,aliases:a})=>s===i||a.includes(i))||n[0]}));r.pipe(m(n=>new Map(n.map(i=>[`${new URL(`../${i.version}/`,t.base)}`,i]))),b(n=>d(document.body,"click").pipe(g(i=>!i.metaKey&&!i.ctrlKey),ae(o),b(([i,s])=>{if(i.target instanceof Element){let a=i.target.closest("a");if(a&&!a.target&&n.has(a.href)){let c=a.href;return!i.target.closest(".md-version")&&n.get(c)===s?L:(i.preventDefault(),$(c))}}return L}),b(i=>{let{version:s}=n.get(i);return mr(new URL(i)).pipe(m(a=>{let p=ve().href.replace(t.base,"");return a.has(p.split("#")[0])?new URL(`../${s}/${p}`,t.base):new URL(i)}))})))).subscribe(n=>st(n,!0)),Q([r,o]).subscribe(([n,i])=>{P(".md-header__topic").appendChild(gn(n,i))}),e.pipe(b(()=>o)).subscribe(n=>{var s;let i=__md_get("__outdated",sessionStorage);if(i===null){i=!0;let a=((s=t.version)==null?void 0:s.default)||"latest";Array.isArray(a)||(a=[a]);e:for(let c of a)for(let p of n.aliases.concat(n.version))if(new RegExp(c,"i").test(p)){i=!1;break e}__md_set("__outdated",i,sessionStorage)}if(i)for(let a of ne("outdated"))a.hidden=!1})}function Ka(e,{worker$:t}){let{searchParams:r}=ve();r.has("q")&&(Be("search",!0),e.value=r.get("q"),e.focus(),We("search").pipe(He(i=>!i)).subscribe(()=>{let i=ve();i.searchParams.delete("q"),history.replaceState({},"",`${i}`)}));let o=vt(e),n=T(t.pipe(He(Ht)),d(e,"keyup"),o).pipe(m(()=>e.value),Y());return Q([n,o]).pipe(m(([i,s])=>({value:i,focus:s})),B(1))}function Jn(e,{worker$:t}){let r=new v,o=r.pipe(ee(),oe(!0));Q([t.pipe(He(Ht)),r],(i,s)=>s).pipe(X("value")).subscribe(({value:i})=>t.next({type:2,data:i})),r.pipe(X("focus")).subscribe(({focus:i})=>{i&&Be("search",i)}),d(e.form,"reset").pipe(U(o)).subscribe(()=>e.focus());let n=P("header [for=__search]");return d(n,"click").subscribe(()=>e.focus()),Ka(e,{worker$:t}).pipe(y(i=>r.next(i)),_(()=>r.complete()),m(i=>F({ref:e},i)),B(1))}function Xn(e,{worker$:t,query$:r}){let o=new v,n=Yo(e.parentElement).pipe(g(Boolean)),i=e.parentElement,s=P(":scope > :first-child",e),a=P(":scope > :last-child",e);We("search").subscribe(l=>a.setAttribute("role",l?"list":"presentation")),o.pipe(ae(r),Ir(t.pipe(He(Ht)))).subscribe(([{items:l},{value:f}])=>{switch(l.length){case 0:s.textContent=f.length?ge("search.result.none"):ge("search.result.placeholder");break;case 1:s.textContent=ge("search.result.one");break;default:let u=ar(l.length);s.textContent=ge("search.result.other",u)}});let c=o.pipe(y(()=>a.innerHTML=""),b(({items:l})=>T($(...l.slice(0,10)),$(...l.slice(10)).pipe(Ke(4),jr(n),b(([f])=>f)))),m(hn),le());return c.subscribe(l=>a.appendChild(l)),c.pipe(re(l=>{let f=me("details",l);return typeof f=="undefined"?L:d(f,"toggle").pipe(U(o),m(()=>f))})).subscribe(l=>{l.open===!1&&l.offsetTop<=i.scrollTop&&i.scrollTo({top:l.offsetTop})}),t.pipe(g(fr),m(({data:l})=>l)).pipe(y(l=>o.next(l)),_(()=>o.complete()),m(l=>F({ref:e},l)))}function Qa(e,{query$:t}){return t.pipe(m(({value:r})=>{let o=ve();return o.hash="",r=r.replace(/\s+/g,"+").replace(/&/g,"%26").replace(/=/g,"%3D"),o.search=`q=${r}`,{url:o}}))}function Zn(e,t){let r=new v,o=r.pipe(ee(),oe(!0));return r.subscribe(({url:n})=>{e.setAttribute("data-clipboard-text",e.href),e.href=`${n}`}),d(e,"click").pipe(U(o)).subscribe(n=>n.preventDefault()),Qa(e,t).pipe(y(n=>r.next(n)),_(()=>r.complete()),m(n=>F({ref:e},n)))}function ei(e,{worker$:t,keyboard$:r}){let o=new v,n=Te("search-query"),i=T(d(n,"keydown"),d(n,"focus")).pipe(Oe(ie),m(()=>n.value),Y());return o.pipe(je(i),m(([{suggest:a},c])=>{let p=c.split(/([\s-]+)/);if(a!=null&&a.length&&p[p.length-1]){let l=a[a.length-1];l.startsWith(p[p.length-1])&&(p[p.length-1]=l)}else p.length=0;return p})).subscribe(a=>e.innerHTML=a.join("").replace(/\s/g," ")),r.pipe(g(({mode:a})=>a==="search")).subscribe(a=>{switch(a.type){case"ArrowRight":e.innerText.length&&n.selectionStart===n.value.length&&(n.value=e.innerText);break}}),t.pipe(g(fr),m(({data:a})=>a)).pipe(y(a=>o.next(a)),_(()=>o.complete()),m(()=>({ref:e})))}function ti(e,{index$:t,keyboard$:r}){let o=we();try{let n=Bn(o.search,t),i=Te("search-query",e),s=Te("search-result",e);d(e,"click").pipe(g(({target:c})=>c instanceof Element&&!!c.closest("a"))).subscribe(()=>Be("search",!1)),r.pipe(g(({mode:c})=>c==="search")).subscribe(c=>{let p=Re();switch(c.type){case"Enter":if(p===i){let l=new Map;for(let f of R(":first-child [href]",s)){let u=f.firstElementChild;l.set(f,parseFloat(u.getAttribute("data-md-score")))}if(l.size){let[[f]]=[...l].sort(([,u],[,h])=>h-u);f.click()}c.claim()}break;case"Escape":case"Tab":Be("search",!1),i.blur();break;case"ArrowUp":case"ArrowDown":if(typeof p=="undefined")i.focus();else{let l=[i,...R(":not(details) > [href], summary, details[open] [href]",s)],f=Math.max(0,(Math.max(0,l.indexOf(p))+l.length+(c.type==="ArrowUp"?-1:1))%l.length);l[f].focus()}c.claim();break;default:i!==Re()&&i.focus()}}),r.pipe(g(({mode:c})=>c==="global")).subscribe(c=>{switch(c.type){case"f":case"s":case"/":i.focus(),i.select(),c.claim();break}});let a=Jn(i,{worker$:n});return T(a,Xn(s,{worker$:n,query$:a})).pipe($e(...ne("search-share",e).map(c=>Zn(c,{query$:a})),...ne("search-suggest",e).map(c=>ei(c,{worker$:n,keyboard$:r}))))}catch(n){return e.hidden=!0,qe}}function ri(e,{index$:t,location$:r}){return Q([t,r.pipe(q(ve()),g(o=>!!o.searchParams.get("h")))]).pipe(m(([o,n])=>Yn(o.config)(n.searchParams.get("h"))),m(o=>{var s;let n=new Map,i=document.createNodeIterator(e,NodeFilter.SHOW_TEXT);for(let a=i.nextNode();a;a=i.nextNode())if((s=a.parentElement)!=null&&s.offsetHeight){let c=a.textContent,p=o(c);p.length>c.length&&n.set(a,p)}for(let[a,c]of n){let{childNodes:p}=E("span",null,c);a.replaceWith(...Array.from(p))}return{ref:e,nodes:n}}))}function Ya(e,{viewport$:t,main$:r}){let o=e.closest(".md-grid"),n=o.offsetTop-o.parentElement.offsetTop;return Q([r,t]).pipe(m(([{offset:i,height:s},{offset:{y:a}}])=>(s=s+Math.min(n,Math.max(0,a-i))-n,{height:s,locked:a>=i+n})),Y((i,s)=>i.height===s.height&&i.locked===s.locked))}function Qr(e,o){var n=o,{header$:t}=n,r=to(n,["header$"]);let i=P(".md-sidebar__scrollwrap",e),{y:s}=Ue(i);return H(()=>{let a=new v,c=a.pipe(ee(),oe(!0)),p=a.pipe(Me(0,de));return p.pipe(ae(t)).subscribe({next([{height:l},{height:f}]){i.style.height=`${l-2*s}px`,e.style.top=`${f}px`},complete(){i.style.height="",e.style.top=""}}),p.pipe(He()).subscribe(()=>{for(let l of R(".md-nav__link--active[href]",e)){if(!l.clientHeight)continue;let f=l.closest(".md-sidebar__scrollwrap");if(typeof f!="undefined"){let u=l.offsetTop-f.offsetTop,{height:h}=pe(f);f.scrollTo({top:u-h/2})}}}),fe(R("label[tabindex]",e)).pipe(re(l=>d(l,"click").pipe(Oe(ie),m(()=>l),U(c)))).subscribe(l=>{let f=P(`[id="${l.htmlFor}"]`);P(`[aria-labelledby="${l.id}"]`).setAttribute("aria-expanded",`${f.checked}`)}),Ya(e,r).pipe(y(l=>a.next(l)),_(()=>a.complete()),m(l=>F({ref:e},l)))})}function oi(e,t){if(typeof t!="undefined"){let r=`https://api.github.com/repos/${e}/${t}`;return Lt(De(`${r}/releases/latest`).pipe(he(()=>L),m(o=>({version:o.tag_name})),Qe({})),De(r).pipe(he(()=>L),m(o=>({stars:o.stargazers_count,forks:o.forks_count})),Qe({}))).pipe(m(([o,n])=>F(F({},o),n)))}else{let r=`https://api.github.com/users/${e}`;return De(r).pipe(m(o=>({repositories:o.public_repos})),Qe({}))}}function ni(e,t){let r=`https://${e}/api/v4/projects/${encodeURIComponent(t)}`;return De(r).pipe(he(()=>L),m(({star_count:o,forks_count:n})=>({stars:o,forks:n})),Qe({}))}function ii(e){let t=e.match(/^.+github\.com\/([^/]+)\/?([^/]+)?/i);if(t){let[,r,o]=t;return oi(r,o)}if(t=e.match(/^.+?([^/]*gitlab[^/]+)\/(.+?)\/?$/i),t){let[,r,o]=t;return ni(r,o)}return L}var Ba;function Ga(e){return Ba||(Ba=H(()=>{let t=__md_get("__source",sessionStorage);if(t)return $(t);if(ne("consent").length){let o=__md_get("__consent");if(!(o&&o.github))return L}return ii(e.href).pipe(y(o=>__md_set("__source",o,sessionStorage)))}).pipe(he(()=>L),g(t=>Object.keys(t).length>0),m(t=>({facts:t})),B(1)))}function ai(e){let t=P(":scope > :last-child",e);return H(()=>{let r=new v;return r.subscribe(({facts:o})=>{t.appendChild(bn(o)),t.classList.add("md-source__repository--active")}),Ga(e).pipe(y(o=>r.next(o)),_(()=>r.complete()),m(o=>F({ref:e},o)))})}function Ja(e,{viewport$:t,header$:r}){return Ee(document.body).pipe(b(()=>pr(e,{header$:r,viewport$:t})),m(({offset:{y:o}})=>({hidden:o>=10})),X("hidden"))}function si(e,t){return H(()=>{let r=new v;return r.subscribe({next({hidden:o}){e.hidden=o},complete(){e.hidden=!1}}),(G("navigation.tabs.sticky")?$({hidden:!1}):Ja(e,t)).pipe(y(o=>r.next(o)),_(()=>r.complete()),m(o=>F({ref:e},o)))})}function Xa(e,{viewport$:t,header$:r}){let o=new Map,n=R(".md-nav__link",e);for(let a of n){let c=decodeURIComponent(a.hash.substring(1)),p=me(`[id="${c}"]`);typeof p!="undefined"&&o.set(a,p)}let i=r.pipe(X("height"),m(({height:a})=>{let c=Te("main"),p=P(":scope > :first-child",c);return a+.8*(p.offsetTop-c.offsetTop)}),le());return Ee(document.body).pipe(X("height"),b(a=>H(()=>{let c=[];return $([...o].reduce((p,[l,f])=>{for(;c.length&&o.get(c[c.length-1]).tagName>=f.tagName;)c.pop();let u=f.offsetTop;for(;!u&&f.parentElement;)f=f.parentElement,u=f.offsetTop;let h=f.offsetParent;for(;h;h=h.offsetParent)u+=h.offsetTop;return p.set([...c=[...c,l]].reverse(),u)},new Map))}).pipe(m(c=>new Map([...c].sort(([,p],[,l])=>p-l))),je(i),b(([c,p])=>t.pipe(Rr(([l,f],{offset:{y:u},size:h})=>{let w=u+h.height>=Math.floor(a.height);for(;f.length;){let[,A]=f[0];if(A-p=u&&!w)f=[l.pop(),...f];else break}return[l,f]},[[],[...c]]),Y((l,f)=>l[0]===f[0]&&l[1]===f[1])))))).pipe(m(([a,c])=>({prev:a.map(([p])=>p),next:c.map(([p])=>p)})),q({prev:[],next:[]}),Ke(2,1),m(([a,c])=>a.prev.length{let i=new v,s=i.pipe(ee(),oe(!0));if(i.subscribe(({prev:a,next:c})=>{for(let[p]of c)p.classList.remove("md-nav__link--passed"),p.classList.remove("md-nav__link--active");for(let[p,[l]]of a.entries())l.classList.add("md-nav__link--passed"),l.classList.toggle("md-nav__link--active",p===a.length-1)}),G("toc.follow")){let a=T(t.pipe(be(1),m(()=>{})),t.pipe(be(250),m(()=>"smooth")));i.pipe(g(({prev:c})=>c.length>0),je(o.pipe(Oe(ie))),ae(a)).subscribe(([[{prev:c}],p])=>{let[l]=c[c.length-1];if(l.offsetHeight){let f=sr(l);if(typeof f!="undefined"){let u=l.offsetTop-f.offsetTop,{height:h}=pe(f);f.scrollTo({top:u-h/2,behavior:p})}}})}return G("navigation.tracking")&&t.pipe(U(s),X("offset"),be(250),Le(1),U(n.pipe(Le(1))),at({delay:250}),ae(i)).subscribe(([,{prev:a}])=>{let c=ve(),p=a[a.length-1];if(p&&p.length){let[l]=p,{hash:f}=new URL(l.href);c.hash!==f&&(c.hash=f,history.replaceState({},"",`${c}`))}else c.hash="",history.replaceState({},"",`${c}`)}),Xa(e,{viewport$:t,header$:r}).pipe(y(a=>i.next(a)),_(()=>i.complete()),m(a=>F({ref:e},a)))})}function Za(e,{viewport$:t,main$:r,target$:o}){let n=t.pipe(m(({offset:{y:s}})=>s),Ke(2,1),m(([s,a])=>s>a&&a>0),Y()),i=r.pipe(m(({active:s})=>s));return Q([i,n]).pipe(m(([s,a])=>!(s&&a)),Y(),U(o.pipe(Le(1))),oe(!0),at({delay:250}),m(s=>({hidden:s})))}function pi(e,{viewport$:t,header$:r,main$:o,target$:n}){let i=new v,s=i.pipe(ee(),oe(!0));return i.subscribe({next({hidden:a}){e.hidden=a,a?(e.setAttribute("tabindex","-1"),e.blur()):e.removeAttribute("tabindex")},complete(){e.style.top="",e.hidden=!0,e.removeAttribute("tabindex")}}),r.pipe(U(s),X("height")).subscribe(({height:a})=>{e.style.top=`${a+16}px`}),d(e,"click").subscribe(a=>{a.preventDefault(),window.scrollTo({top:0})}),Za(e,{viewport$:t,main$:o,target$:n}).pipe(y(a=>i.next(a)),_(()=>i.complete()),m(a=>F({ref:e},a)))}function li({document$:e}){e.pipe(b(()=>R(".md-ellipsis")),re(t=>yt(t).pipe(U(e.pipe(Le(1))),g(r=>r),m(()=>t),ye(1))),g(t=>t.offsetWidth{let r=t.innerText,o=t.closest("a")||t;return o.title=r,Ge(o).pipe(U(e.pipe(Le(1))),_(()=>o.removeAttribute("title")))})).subscribe(),e.pipe(b(()=>R(".md-status")),re(t=>Ge(t))).subscribe()}function mi({document$:e,tablet$:t}){e.pipe(b(()=>R(".md-toggle--indeterminate")),y(r=>{r.indeterminate=!0,r.checked=!1}),re(r=>d(r,"change").pipe(Fr(()=>r.classList.contains("md-toggle--indeterminate")),m(()=>r))),ae(t)).subscribe(([r,o])=>{r.classList.remove("md-toggle--indeterminate"),o&&(r.checked=!1)})}function es(){return/(iPad|iPhone|iPod)/.test(navigator.userAgent)}function fi({document$:e}){e.pipe(b(()=>R("[data-md-scrollfix]")),y(t=>t.removeAttribute("data-md-scrollfix")),g(es),re(t=>d(t,"touchstart").pipe(m(()=>t)))).subscribe(t=>{let r=t.scrollTop;r===0?t.scrollTop=1:r+t.offsetHeight===t.scrollHeight&&(t.scrollTop=r-1)})}function ui({viewport$:e,tablet$:t}){Q([We("search"),t]).pipe(m(([r,o])=>r&&!o),b(r=>$(r).pipe(Ye(r?400:100))),ae(e)).subscribe(([r,{offset:{y:o}}])=>{if(r)document.body.setAttribute("data-md-scrolllock",""),document.body.style.top=`-${o}px`;else{let n=-1*parseInt(document.body.style.top,10);document.body.removeAttribute("data-md-scrolllock"),document.body.style.top="",n&&window.scrollTo(0,n)}})}Object.entries||(Object.entries=function(e){let t=[];for(let r of Object.keys(e))t.push([r,e[r]]);return t});Object.values||(Object.values=function(e){let t=[];for(let r of Object.keys(e))t.push(e[r]);return t});typeof Element!="undefined"&&(Element.prototype.scrollTo||(Element.prototype.scrollTo=function(e,t){typeof e=="object"?(this.scrollLeft=e.left,this.scrollTop=e.top):(this.scrollLeft=e,this.scrollTop=t)}),Element.prototype.replaceWith||(Element.prototype.replaceWith=function(...e){let t=this.parentNode;if(t){e.length===0&&t.removeChild(this);for(let r=e.length-1;r>=0;r--){let o=e[r];typeof o=="string"?o=document.createTextNode(o):o.parentNode&&o.parentNode.removeChild(o),r?t.insertBefore(this.previousSibling,o):t.replaceChild(o,this)}}}));function ts(){return location.protocol==="file:"?gt(`${new URL("search/search_index.js",Yr.base)}`).pipe(m(()=>__index),B(1)):De(new URL("search/search_index.json",Yr.base))}document.documentElement.classList.remove("no-js");document.documentElement.classList.add("js");var rt=No(),Rt=Jo(),wt=en(Rt),Br=Go(),_e=pn(),ur=At("(min-width: 960px)"),hi=At("(min-width: 1220px)"),bi=tn(),Yr=we(),vi=document.forms.namedItem("search")?ts():qe,Gr=new v;Wn({alert$:Gr});var Jr=new v;G("navigation.instant")&&zn({location$:Rt,viewport$:_e,progress$:Jr}).subscribe(rt);var di;((di=Yr.version)==null?void 0:di.provider)==="mike"&&Gn({document$:rt});T(Rt,wt).pipe(Ye(125)).subscribe(()=>{Be("drawer",!1),Be("search",!1)});Br.pipe(g(({mode:e})=>e==="global")).subscribe(e=>{switch(e.type){case"p":case",":let t=me("link[rel=prev]");typeof t!="undefined"&&st(t);break;case"n":case".":let r=me("link[rel=next]");typeof r!="undefined"&&st(r);break;case"Enter":let o=Re();o instanceof HTMLLabelElement&&o.click()}});li({document$:rt});mi({document$:rt,tablet$:ur});fi({document$:rt});ui({viewport$:_e,tablet$:ur});var tt=Rn(Te("header"),{viewport$:_e}),$t=rt.pipe(m(()=>Te("main")),b(e=>Fn(e,{viewport$:_e,header$:tt})),B(1)),rs=T(...ne("consent").map(e=>fn(e,{target$:wt})),...ne("dialog").map(e=>$n(e,{alert$:Gr})),...ne("header").map(e=>Pn(e,{viewport$:_e,header$:tt,main$:$t})),...ne("palette").map(e=>jn(e)),...ne("progress").map(e=>Un(e,{progress$:Jr})),...ne("search").map(e=>ti(e,{index$:vi,keyboard$:Br})),...ne("source").map(e=>ai(e))),os=H(()=>T(...ne("announce").map(e=>mn(e)),...ne("content").map(e=>Hn(e,{viewport$:_e,target$:wt,print$:bi})),...ne("content").map(e=>G("search.highlight")?ri(e,{index$:vi,location$:Rt}):L),...ne("header-title").map(e=>In(e,{viewport$:_e,header$:tt})),...ne("sidebar").map(e=>e.getAttribute("data-md-type")==="navigation"?Ur(hi,()=>Qr(e,{viewport$:_e,header$:tt,main$:$t})):Ur(ur,()=>Qr(e,{viewport$:_e,header$:tt,main$:$t}))),...ne("tabs").map(e=>si(e,{viewport$:_e,header$:tt})),...ne("toc").map(e=>ci(e,{viewport$:_e,header$:tt,main$:$t,target$:wt})),...ne("top").map(e=>pi(e,{viewport$:_e,header$:tt,main$:$t,target$:wt})))),gi=rt.pipe(b(()=>os),$e(rs),B(1));gi.subscribe();window.document$=rt;window.location$=Rt;window.target$=wt;window.keyboard$=Br;window.viewport$=_e;window.tablet$=ur;window.screen$=hi;window.print$=bi;window.alert$=Gr;window.progress$=Jr;window.component$=gi;})(); +//# sourceMappingURL=bundle.8fd75fb4.min.js.map + diff --git a/assets/javascripts/bundle.8fd75fb4.min.js.map b/assets/javascripts/bundle.8fd75fb4.min.js.map new file mode 100644 index 000000000..1a287892a --- /dev/null +++ b/assets/javascripts/bundle.8fd75fb4.min.js.map @@ -0,0 +1,7 @@ +{ + "version": 3, + "sources": ["node_modules/focus-visible/dist/focus-visible.js", "node_modules/clipboard/dist/clipboard.js", "node_modules/escape-html/index.js", "src/templates/assets/javascripts/bundle.ts", "node_modules/rxjs/node_modules/tslib/tslib.es6.js", "node_modules/rxjs/src/internal/util/isFunction.ts", "node_modules/rxjs/src/internal/util/createErrorClass.ts", "node_modules/rxjs/src/internal/util/UnsubscriptionError.ts", "node_modules/rxjs/src/internal/util/arrRemove.ts", "node_modules/rxjs/src/internal/Subscription.ts", "node_modules/rxjs/src/internal/config.ts", "node_modules/rxjs/src/internal/scheduler/timeoutProvider.ts", "node_modules/rxjs/src/internal/util/reportUnhandledError.ts", "node_modules/rxjs/src/internal/util/noop.ts", "node_modules/rxjs/src/internal/NotificationFactories.ts", "node_modules/rxjs/src/internal/util/errorContext.ts", "node_modules/rxjs/src/internal/Subscriber.ts", "node_modules/rxjs/src/internal/symbol/observable.ts", "node_modules/rxjs/src/internal/util/identity.ts", "node_modules/rxjs/src/internal/util/pipe.ts", "node_modules/rxjs/src/internal/Observable.ts", "node_modules/rxjs/src/internal/util/lift.ts", "node_modules/rxjs/src/internal/operators/OperatorSubscriber.ts", "node_modules/rxjs/src/internal/scheduler/animationFrameProvider.ts", "node_modules/rxjs/src/internal/util/ObjectUnsubscribedError.ts", "node_modules/rxjs/src/internal/Subject.ts", "node_modules/rxjs/src/internal/scheduler/dateTimestampProvider.ts", "node_modules/rxjs/src/internal/ReplaySubject.ts", "node_modules/rxjs/src/internal/scheduler/Action.ts", "node_modules/rxjs/src/internal/scheduler/intervalProvider.ts", "node_modules/rxjs/src/internal/scheduler/AsyncAction.ts", "node_modules/rxjs/src/internal/Scheduler.ts", "node_modules/rxjs/src/internal/scheduler/AsyncScheduler.ts", "node_modules/rxjs/src/internal/scheduler/async.ts", "node_modules/rxjs/src/internal/scheduler/AnimationFrameAction.ts", "node_modules/rxjs/src/internal/scheduler/AnimationFrameScheduler.ts", "node_modules/rxjs/src/internal/scheduler/animationFrame.ts", "node_modules/rxjs/src/internal/observable/empty.ts", "node_modules/rxjs/src/internal/util/isScheduler.ts", "node_modules/rxjs/src/internal/util/args.ts", "node_modules/rxjs/src/internal/util/isArrayLike.ts", "node_modules/rxjs/src/internal/util/isPromise.ts", "node_modules/rxjs/src/internal/util/isInteropObservable.ts", "node_modules/rxjs/src/internal/util/isAsyncIterable.ts", "node_modules/rxjs/src/internal/util/throwUnobservableError.ts", "node_modules/rxjs/src/internal/symbol/iterator.ts", "node_modules/rxjs/src/internal/util/isIterable.ts", "node_modules/rxjs/src/internal/util/isReadableStreamLike.ts", "node_modules/rxjs/src/internal/observable/innerFrom.ts", "node_modules/rxjs/src/internal/util/executeSchedule.ts", "node_modules/rxjs/src/internal/operators/observeOn.ts", "node_modules/rxjs/src/internal/operators/subscribeOn.ts", "node_modules/rxjs/src/internal/scheduled/scheduleObservable.ts", "node_modules/rxjs/src/internal/scheduled/schedulePromise.ts", "node_modules/rxjs/src/internal/scheduled/scheduleArray.ts", "node_modules/rxjs/src/internal/scheduled/scheduleIterable.ts", "node_modules/rxjs/src/internal/scheduled/scheduleAsyncIterable.ts", "node_modules/rxjs/src/internal/scheduled/scheduleReadableStreamLike.ts", "node_modules/rxjs/src/internal/scheduled/scheduled.ts", "node_modules/rxjs/src/internal/observable/from.ts", "node_modules/rxjs/src/internal/observable/of.ts", "node_modules/rxjs/src/internal/observable/throwError.ts", "node_modules/rxjs/src/internal/util/EmptyError.ts", "node_modules/rxjs/src/internal/util/isDate.ts", "node_modules/rxjs/src/internal/operators/map.ts", "node_modules/rxjs/src/internal/util/mapOneOrManyArgs.ts", "node_modules/rxjs/src/internal/util/argsArgArrayOrObject.ts", "node_modules/rxjs/src/internal/util/createObject.ts", "node_modules/rxjs/src/internal/observable/combineLatest.ts", "node_modules/rxjs/src/internal/operators/mergeInternals.ts", "node_modules/rxjs/src/internal/operators/mergeMap.ts", "node_modules/rxjs/src/internal/operators/mergeAll.ts", "node_modules/rxjs/src/internal/operators/concatAll.ts", "node_modules/rxjs/src/internal/observable/concat.ts", "node_modules/rxjs/src/internal/observable/defer.ts", "node_modules/rxjs/src/internal/observable/fromEvent.ts", "node_modules/rxjs/src/internal/observable/fromEventPattern.ts", "node_modules/rxjs/src/internal/observable/timer.ts", "node_modules/rxjs/src/internal/observable/merge.ts", "node_modules/rxjs/src/internal/observable/never.ts", "node_modules/rxjs/src/internal/util/argsOrArgArray.ts", "node_modules/rxjs/src/internal/operators/filter.ts", "node_modules/rxjs/src/internal/observable/zip.ts", "node_modules/rxjs/src/internal/operators/audit.ts", "node_modules/rxjs/src/internal/operators/auditTime.ts", "node_modules/rxjs/src/internal/operators/bufferCount.ts", "node_modules/rxjs/src/internal/operators/catchError.ts", "node_modules/rxjs/src/internal/operators/scanInternals.ts", "node_modules/rxjs/src/internal/operators/combineLatest.ts", "node_modules/rxjs/src/internal/operators/combineLatestWith.ts", "node_modules/rxjs/src/internal/operators/debounceTime.ts", "node_modules/rxjs/src/internal/operators/defaultIfEmpty.ts", "node_modules/rxjs/src/internal/operators/take.ts", "node_modules/rxjs/src/internal/operators/ignoreElements.ts", "node_modules/rxjs/src/internal/operators/mapTo.ts", "node_modules/rxjs/src/internal/operators/delayWhen.ts", "node_modules/rxjs/src/internal/operators/delay.ts", "node_modules/rxjs/src/internal/operators/distinctUntilChanged.ts", "node_modules/rxjs/src/internal/operators/distinctUntilKeyChanged.ts", "node_modules/rxjs/src/internal/operators/throwIfEmpty.ts", "node_modules/rxjs/src/internal/operators/endWith.ts", "node_modules/rxjs/src/internal/operators/finalize.ts", "node_modules/rxjs/src/internal/operators/first.ts", "node_modules/rxjs/src/internal/operators/takeLast.ts", "node_modules/rxjs/src/internal/operators/merge.ts", "node_modules/rxjs/src/internal/operators/mergeWith.ts", "node_modules/rxjs/src/internal/operators/repeat.ts", "node_modules/rxjs/src/internal/operators/scan.ts", "node_modules/rxjs/src/internal/operators/share.ts", "node_modules/rxjs/src/internal/operators/shareReplay.ts", "node_modules/rxjs/src/internal/operators/skip.ts", "node_modules/rxjs/src/internal/operators/skipUntil.ts", "node_modules/rxjs/src/internal/operators/startWith.ts", "node_modules/rxjs/src/internal/operators/switchMap.ts", "node_modules/rxjs/src/internal/operators/takeUntil.ts", "node_modules/rxjs/src/internal/operators/takeWhile.ts", "node_modules/rxjs/src/internal/operators/tap.ts", "node_modules/rxjs/src/internal/operators/throttle.ts", "node_modules/rxjs/src/internal/operators/throttleTime.ts", "node_modules/rxjs/src/internal/operators/withLatestFrom.ts", "node_modules/rxjs/src/internal/operators/zip.ts", "node_modules/rxjs/src/internal/operators/zipWith.ts", "src/templates/assets/javascripts/browser/document/index.ts", "src/templates/assets/javascripts/browser/element/_/index.ts", "src/templates/assets/javascripts/browser/element/focus/index.ts", "src/templates/assets/javascripts/browser/element/hover/index.ts", "src/templates/assets/javascripts/browser/element/offset/_/index.ts", "src/templates/assets/javascripts/browser/element/offset/content/index.ts", "src/templates/assets/javascripts/utilities/h/index.ts", "src/templates/assets/javascripts/utilities/round/index.ts", "src/templates/assets/javascripts/browser/script/index.ts", "src/templates/assets/javascripts/browser/element/size/_/index.ts", "src/templates/assets/javascripts/browser/element/size/content/index.ts", "src/templates/assets/javascripts/browser/element/visibility/index.ts", "src/templates/assets/javascripts/browser/toggle/index.ts", "src/templates/assets/javascripts/browser/keyboard/index.ts", "src/templates/assets/javascripts/browser/location/_/index.ts", "src/templates/assets/javascripts/browser/location/hash/index.ts", "src/templates/assets/javascripts/browser/media/index.ts", "src/templates/assets/javascripts/browser/request/index.ts", "src/templates/assets/javascripts/browser/viewport/offset/index.ts", "src/templates/assets/javascripts/browser/viewport/size/index.ts", "src/templates/assets/javascripts/browser/viewport/_/index.ts", "src/templates/assets/javascripts/browser/viewport/at/index.ts", "src/templates/assets/javascripts/browser/worker/index.ts", "src/templates/assets/javascripts/_/index.ts", "src/templates/assets/javascripts/components/_/index.ts", "src/templates/assets/javascripts/components/announce/index.ts", "src/templates/assets/javascripts/components/consent/index.ts", "src/templates/assets/javascripts/templates/tooltip/index.tsx", "src/templates/assets/javascripts/templates/annotation/index.tsx", "src/templates/assets/javascripts/templates/clipboard/index.tsx", "src/templates/assets/javascripts/templates/search/index.tsx", "src/templates/assets/javascripts/templates/source/index.tsx", "src/templates/assets/javascripts/templates/tabbed/index.tsx", "src/templates/assets/javascripts/templates/table/index.tsx", "src/templates/assets/javascripts/templates/version/index.tsx", "src/templates/assets/javascripts/components/tooltip/index.ts", "src/templates/assets/javascripts/components/content/annotation/_/index.ts", "src/templates/assets/javascripts/components/content/annotation/list/index.ts", "src/templates/assets/javascripts/components/content/annotation/block/index.ts", "src/templates/assets/javascripts/components/content/code/_/index.ts", "src/templates/assets/javascripts/components/content/details/index.ts", "src/templates/assets/javascripts/components/content/mermaid/index.css", "src/templates/assets/javascripts/components/content/mermaid/index.ts", "src/templates/assets/javascripts/components/content/table/index.ts", "src/templates/assets/javascripts/components/content/tabs/index.ts", "src/templates/assets/javascripts/components/content/_/index.ts", "src/templates/assets/javascripts/components/dialog/index.ts", "src/templates/assets/javascripts/components/header/_/index.ts", "src/templates/assets/javascripts/components/header/title/index.ts", "src/templates/assets/javascripts/components/main/index.ts", "src/templates/assets/javascripts/components/palette/index.ts", "src/templates/assets/javascripts/components/progress/index.ts", "src/templates/assets/javascripts/integrations/clipboard/index.ts", "src/templates/assets/javascripts/integrations/sitemap/index.ts", "src/templates/assets/javascripts/integrations/instant/index.ts", "src/templates/assets/javascripts/integrations/search/highlighter/index.ts", "src/templates/assets/javascripts/integrations/search/worker/message/index.ts", "src/templates/assets/javascripts/integrations/search/worker/_/index.ts", "src/templates/assets/javascripts/integrations/version/index.ts", "src/templates/assets/javascripts/components/search/query/index.ts", "src/templates/assets/javascripts/components/search/result/index.ts", "src/templates/assets/javascripts/components/search/share/index.ts", "src/templates/assets/javascripts/components/search/suggest/index.ts", "src/templates/assets/javascripts/components/search/_/index.ts", "src/templates/assets/javascripts/components/search/highlight/index.ts", "src/templates/assets/javascripts/components/sidebar/index.ts", "src/templates/assets/javascripts/components/source/facts/github/index.ts", "src/templates/assets/javascripts/components/source/facts/gitlab/index.ts", "src/templates/assets/javascripts/components/source/facts/_/index.ts", "src/templates/assets/javascripts/components/source/_/index.ts", "src/templates/assets/javascripts/components/tabs/index.ts", "src/templates/assets/javascripts/components/toc/index.ts", "src/templates/assets/javascripts/components/top/index.ts", "src/templates/assets/javascripts/patches/ellipsis/index.ts", "src/templates/assets/javascripts/patches/indeterminate/index.ts", "src/templates/assets/javascripts/patches/scrollfix/index.ts", "src/templates/assets/javascripts/patches/scrolllock/index.ts", "src/templates/assets/javascripts/polyfills/index.ts"], + "sourcesContent": ["(function (global, factory) {\n typeof exports === 'object' && typeof module !== 'undefined' ? factory() :\n typeof define === 'function' && define.amd ? define(factory) :\n (factory());\n}(this, (function () { 'use strict';\n\n /**\n * Applies the :focus-visible polyfill at the given scope.\n * A scope in this case is either the top-level Document or a Shadow Root.\n *\n * @param {(Document|ShadowRoot)} scope\n * @see https://github.com/WICG/focus-visible\n */\n function applyFocusVisiblePolyfill(scope) {\n var hadKeyboardEvent = true;\n var hadFocusVisibleRecently = false;\n var hadFocusVisibleRecentlyTimeout = null;\n\n var inputTypesAllowlist = {\n text: true,\n search: true,\n url: true,\n tel: true,\n email: true,\n password: true,\n number: true,\n date: true,\n month: true,\n week: true,\n time: true,\n datetime: true,\n 'datetime-local': true\n };\n\n /**\n * Helper function for legacy browsers and iframes which sometimes focus\n * elements like document, body, and non-interactive SVG.\n * @param {Element} el\n */\n function isValidFocusTarget(el) {\n if (\n el &&\n el !== document &&\n el.nodeName !== 'HTML' &&\n el.nodeName !== 'BODY' &&\n 'classList' in el &&\n 'contains' in el.classList\n ) {\n return true;\n }\n return false;\n }\n\n /**\n * Computes whether the given element should automatically trigger the\n * `focus-visible` class being added, i.e. whether it should always match\n * `:focus-visible` when focused.\n * @param {Element} el\n * @return {boolean}\n */\n function focusTriggersKeyboardModality(el) {\n var type = el.type;\n var tagName = el.tagName;\n\n if (tagName === 'INPUT' && inputTypesAllowlist[type] && !el.readOnly) {\n return true;\n }\n\n if (tagName === 'TEXTAREA' && !el.readOnly) {\n return true;\n }\n\n if (el.isContentEditable) {\n return true;\n }\n\n return false;\n }\n\n /**\n * Add the `focus-visible` class to the given element if it was not added by\n * the author.\n * @param {Element} el\n */\n function addFocusVisibleClass(el) {\n if (el.classList.contains('focus-visible')) {\n return;\n }\n el.classList.add('focus-visible');\n el.setAttribute('data-focus-visible-added', '');\n }\n\n /**\n * Remove the `focus-visible` class from the given element if it was not\n * originally added by the author.\n * @param {Element} el\n */\n function removeFocusVisibleClass(el) {\n if (!el.hasAttribute('data-focus-visible-added')) {\n return;\n }\n el.classList.remove('focus-visible');\n el.removeAttribute('data-focus-visible-added');\n }\n\n /**\n * If the most recent user interaction was via the keyboard;\n * and the key press did not include a meta, alt/option, or control key;\n * then the modality is keyboard. Otherwise, the modality is not keyboard.\n * Apply `focus-visible` to any current active element and keep track\n * of our keyboard modality state with `hadKeyboardEvent`.\n * @param {KeyboardEvent} e\n */\n function onKeyDown(e) {\n if (e.metaKey || e.altKey || e.ctrlKey) {\n return;\n }\n\n if (isValidFocusTarget(scope.activeElement)) {\n addFocusVisibleClass(scope.activeElement);\n }\n\n hadKeyboardEvent = true;\n }\n\n /**\n * If at any point a user clicks with a pointing device, ensure that we change\n * the modality away from keyboard.\n * This avoids the situation where a user presses a key on an already focused\n * element, and then clicks on a different element, focusing it with a\n * pointing device, while we still think we're in keyboard modality.\n * @param {Event} e\n */\n function onPointerDown(e) {\n hadKeyboardEvent = false;\n }\n\n /**\n * On `focus`, add the `focus-visible` class to the target if:\n * - the target received focus as a result of keyboard navigation, or\n * - the event target is an element that will likely require interaction\n * via the keyboard (e.g. a text box)\n * @param {Event} e\n */\n function onFocus(e) {\n // Prevent IE from focusing the document or HTML element.\n if (!isValidFocusTarget(e.target)) {\n return;\n }\n\n if (hadKeyboardEvent || focusTriggersKeyboardModality(e.target)) {\n addFocusVisibleClass(e.target);\n }\n }\n\n /**\n * On `blur`, remove the `focus-visible` class from the target.\n * @param {Event} e\n */\n function onBlur(e) {\n if (!isValidFocusTarget(e.target)) {\n return;\n }\n\n if (\n e.target.classList.contains('focus-visible') ||\n e.target.hasAttribute('data-focus-visible-added')\n ) {\n // To detect a tab/window switch, we look for a blur event followed\n // rapidly by a visibility change.\n // If we don't see a visibility change within 100ms, it's probably a\n // regular focus change.\n hadFocusVisibleRecently = true;\n window.clearTimeout(hadFocusVisibleRecentlyTimeout);\n hadFocusVisibleRecentlyTimeout = window.setTimeout(function() {\n hadFocusVisibleRecently = false;\n }, 100);\n removeFocusVisibleClass(e.target);\n }\n }\n\n /**\n * If the user changes tabs, keep track of whether or not the previously\n * focused element had .focus-visible.\n * @param {Event} e\n */\n function onVisibilityChange(e) {\n if (document.visibilityState === 'hidden') {\n // If the tab becomes active again, the browser will handle calling focus\n // on the element (Safari actually calls it twice).\n // If this tab change caused a blur on an element with focus-visible,\n // re-apply the class when the user switches back to the tab.\n if (hadFocusVisibleRecently) {\n hadKeyboardEvent = true;\n }\n addInitialPointerMoveListeners();\n }\n }\n\n /**\n * Add a group of listeners to detect usage of any pointing devices.\n * These listeners will be added when the polyfill first loads, and anytime\n * the window is blurred, so that they are active when the window regains\n * focus.\n */\n function addInitialPointerMoveListeners() {\n document.addEventListener('mousemove', onInitialPointerMove);\n document.addEventListener('mousedown', onInitialPointerMove);\n document.addEventListener('mouseup', onInitialPointerMove);\n document.addEventListener('pointermove', onInitialPointerMove);\n document.addEventListener('pointerdown', onInitialPointerMove);\n document.addEventListener('pointerup', onInitialPointerMove);\n document.addEventListener('touchmove', onInitialPointerMove);\n document.addEventListener('touchstart', onInitialPointerMove);\n document.addEventListener('touchend', onInitialPointerMove);\n }\n\n function removeInitialPointerMoveListeners() {\n document.removeEventListener('mousemove', onInitialPointerMove);\n document.removeEventListener('mousedown', onInitialPointerMove);\n document.removeEventListener('mouseup', onInitialPointerMove);\n document.removeEventListener('pointermove', onInitialPointerMove);\n document.removeEventListener('pointerdown', onInitialPointerMove);\n document.removeEventListener('pointerup', onInitialPointerMove);\n document.removeEventListener('touchmove', onInitialPointerMove);\n document.removeEventListener('touchstart', onInitialPointerMove);\n document.removeEventListener('touchend', onInitialPointerMove);\n }\n\n /**\n * When the polfyill first loads, assume the user is in keyboard modality.\n * If any event is received from a pointing device (e.g. mouse, pointer,\n * touch), turn off keyboard modality.\n * This accounts for situations where focus enters the page from the URL bar.\n * @param {Event} e\n */\n function onInitialPointerMove(e) {\n // Work around a Safari quirk that fires a mousemove on whenever the\n // window blurs, even if you're tabbing out of the page. \u00AF\\_(\u30C4)_/\u00AF\n if (e.target.nodeName && e.target.nodeName.toLowerCase() === 'html') {\n return;\n }\n\n hadKeyboardEvent = false;\n removeInitialPointerMoveListeners();\n }\n\n // For some kinds of state, we are interested in changes at the global scope\n // only. For example, global pointer input, global key presses and global\n // visibility change should affect the state at every scope:\n document.addEventListener('keydown', onKeyDown, true);\n document.addEventListener('mousedown', onPointerDown, true);\n document.addEventListener('pointerdown', onPointerDown, true);\n document.addEventListener('touchstart', onPointerDown, true);\n document.addEventListener('visibilitychange', onVisibilityChange, true);\n\n addInitialPointerMoveListeners();\n\n // For focus and blur, we specifically care about state changes in the local\n // scope. This is because focus / blur events that originate from within a\n // shadow root are not re-dispatched from the host element if it was already\n // the active element in its own scope:\n scope.addEventListener('focus', onFocus, true);\n scope.addEventListener('blur', onBlur, true);\n\n // We detect that a node is a ShadowRoot by ensuring that it is a\n // DocumentFragment and also has a host property. This check covers native\n // implementation and polyfill implementation transparently. If we only cared\n // about the native implementation, we could just check if the scope was\n // an instance of a ShadowRoot.\n if (scope.nodeType === Node.DOCUMENT_FRAGMENT_NODE && scope.host) {\n // Since a ShadowRoot is a special kind of DocumentFragment, it does not\n // have a root element to add a class to. So, we add this attribute to the\n // host element instead:\n scope.host.setAttribute('data-js-focus-visible', '');\n } else if (scope.nodeType === Node.DOCUMENT_NODE) {\n document.documentElement.classList.add('js-focus-visible');\n document.documentElement.setAttribute('data-js-focus-visible', '');\n }\n }\n\n // It is important to wrap all references to global window and document in\n // these checks to support server-side rendering use cases\n // @see https://github.com/WICG/focus-visible/issues/199\n if (typeof window !== 'undefined' && typeof document !== 'undefined') {\n // Make the polyfill helper globally available. This can be used as a signal\n // to interested libraries that wish to coordinate with the polyfill for e.g.,\n // applying the polyfill to a shadow root:\n window.applyFocusVisiblePolyfill = applyFocusVisiblePolyfill;\n\n // Notify interested libraries of the polyfill's presence, in case the\n // polyfill was loaded lazily:\n var event;\n\n try {\n event = new CustomEvent('focus-visible-polyfill-ready');\n } catch (error) {\n // IE11 does not support using CustomEvent as a constructor directly:\n event = document.createEvent('CustomEvent');\n event.initCustomEvent('focus-visible-polyfill-ready', false, false, {});\n }\n\n window.dispatchEvent(event);\n }\n\n if (typeof document !== 'undefined') {\n // Apply the polyfill to the global document, so that no JavaScript\n // coordination is required to use the polyfill in the top-level document:\n applyFocusVisiblePolyfill(document);\n }\n\n})));\n", "/*!\n * clipboard.js v2.0.11\n * https://clipboardjs.com/\n *\n * Licensed MIT \u00A9 Zeno Rocha\n */\n(function webpackUniversalModuleDefinition(root, factory) {\n\tif(typeof exports === 'object' && typeof module === 'object')\n\t\tmodule.exports = factory();\n\telse if(typeof define === 'function' && define.amd)\n\t\tdefine([], factory);\n\telse if(typeof exports === 'object')\n\t\texports[\"ClipboardJS\"] = factory();\n\telse\n\t\troot[\"ClipboardJS\"] = factory();\n})(this, function() {\nreturn /******/ (function() { // webpackBootstrap\n/******/ \tvar __webpack_modules__ = ({\n\n/***/ 686:\n/***/ (function(__unused_webpack_module, __webpack_exports__, __webpack_require__) {\n\n\"use strict\";\n\n// EXPORTS\n__webpack_require__.d(__webpack_exports__, {\n \"default\": function() { return /* binding */ clipboard; }\n});\n\n// EXTERNAL MODULE: ./node_modules/tiny-emitter/index.js\nvar tiny_emitter = __webpack_require__(279);\nvar tiny_emitter_default = /*#__PURE__*/__webpack_require__.n(tiny_emitter);\n// EXTERNAL MODULE: ./node_modules/good-listener/src/listen.js\nvar listen = __webpack_require__(370);\nvar listen_default = /*#__PURE__*/__webpack_require__.n(listen);\n// EXTERNAL MODULE: ./node_modules/select/src/select.js\nvar src_select = __webpack_require__(817);\nvar select_default = /*#__PURE__*/__webpack_require__.n(src_select);\n;// CONCATENATED MODULE: ./src/common/command.js\n/**\n * Executes a given operation type.\n * @param {String} type\n * @return {Boolean}\n */\nfunction command(type) {\n try {\n return document.execCommand(type);\n } catch (err) {\n return false;\n }\n}\n;// CONCATENATED MODULE: ./src/actions/cut.js\n\n\n/**\n * Cut action wrapper.\n * @param {String|HTMLElement} target\n * @return {String}\n */\n\nvar ClipboardActionCut = function ClipboardActionCut(target) {\n var selectedText = select_default()(target);\n command('cut');\n return selectedText;\n};\n\n/* harmony default export */ var actions_cut = (ClipboardActionCut);\n;// CONCATENATED MODULE: ./src/common/create-fake-element.js\n/**\n * Creates a fake textarea element with a value.\n * @param {String} value\n * @return {HTMLElement}\n */\nfunction createFakeElement(value) {\n var isRTL = document.documentElement.getAttribute('dir') === 'rtl';\n var fakeElement = document.createElement('textarea'); // Prevent zooming on iOS\n\n fakeElement.style.fontSize = '12pt'; // Reset box model\n\n fakeElement.style.border = '0';\n fakeElement.style.padding = '0';\n fakeElement.style.margin = '0'; // Move element out of screen horizontally\n\n fakeElement.style.position = 'absolute';\n fakeElement.style[isRTL ? 'right' : 'left'] = '-9999px'; // Move element to the same position vertically\n\n var yPosition = window.pageYOffset || document.documentElement.scrollTop;\n fakeElement.style.top = \"\".concat(yPosition, \"px\");\n fakeElement.setAttribute('readonly', '');\n fakeElement.value = value;\n return fakeElement;\n}\n;// CONCATENATED MODULE: ./src/actions/copy.js\n\n\n\n/**\n * Create fake copy action wrapper using a fake element.\n * @param {String} target\n * @param {Object} options\n * @return {String}\n */\n\nvar fakeCopyAction = function fakeCopyAction(value, options) {\n var fakeElement = createFakeElement(value);\n options.container.appendChild(fakeElement);\n var selectedText = select_default()(fakeElement);\n command('copy');\n fakeElement.remove();\n return selectedText;\n};\n/**\n * Copy action wrapper.\n * @param {String|HTMLElement} target\n * @param {Object} options\n * @return {String}\n */\n\n\nvar ClipboardActionCopy = function ClipboardActionCopy(target) {\n var options = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : {\n container: document.body\n };\n var selectedText = '';\n\n if (typeof target === 'string') {\n selectedText = fakeCopyAction(target, options);\n } else if (target instanceof HTMLInputElement && !['text', 'search', 'url', 'tel', 'password'].includes(target === null || target === void 0 ? void 0 : target.type)) {\n // If input type doesn't support `setSelectionRange`. Simulate it. https://developer.mozilla.org/en-US/docs/Web/API/HTMLInputElement/setSelectionRange\n selectedText = fakeCopyAction(target.value, options);\n } else {\n selectedText = select_default()(target);\n command('copy');\n }\n\n return selectedText;\n};\n\n/* harmony default export */ var actions_copy = (ClipboardActionCopy);\n;// CONCATENATED MODULE: ./src/actions/default.js\nfunction _typeof(obj) { \"@babel/helpers - typeof\"; if (typeof Symbol === \"function\" && typeof Symbol.iterator === \"symbol\") { _typeof = function _typeof(obj) { return typeof obj; }; } else { _typeof = function _typeof(obj) { return obj && typeof Symbol === \"function\" && obj.constructor === Symbol && obj !== Symbol.prototype ? \"symbol\" : typeof obj; }; } return _typeof(obj); }\n\n\n\n/**\n * Inner function which performs selection from either `text` or `target`\n * properties and then executes copy or cut operations.\n * @param {Object} options\n */\n\nvar ClipboardActionDefault = function ClipboardActionDefault() {\n var options = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : {};\n // Defines base properties passed from constructor.\n var _options$action = options.action,\n action = _options$action === void 0 ? 'copy' : _options$action,\n container = options.container,\n target = options.target,\n text = options.text; // Sets the `action` to be performed which can be either 'copy' or 'cut'.\n\n if (action !== 'copy' && action !== 'cut') {\n throw new Error('Invalid \"action\" value, use either \"copy\" or \"cut\"');\n } // Sets the `target` property using an element that will be have its content copied.\n\n\n if (target !== undefined) {\n if (target && _typeof(target) === 'object' && target.nodeType === 1) {\n if (action === 'copy' && target.hasAttribute('disabled')) {\n throw new Error('Invalid \"target\" attribute. Please use \"readonly\" instead of \"disabled\" attribute');\n }\n\n if (action === 'cut' && (target.hasAttribute('readonly') || target.hasAttribute('disabled'))) {\n throw new Error('Invalid \"target\" attribute. You can\\'t cut text from elements with \"readonly\" or \"disabled\" attributes');\n }\n } else {\n throw new Error('Invalid \"target\" value, use a valid Element');\n }\n } // Define selection strategy based on `text` property.\n\n\n if (text) {\n return actions_copy(text, {\n container: container\n });\n } // Defines which selection strategy based on `target` property.\n\n\n if (target) {\n return action === 'cut' ? actions_cut(target) : actions_copy(target, {\n container: container\n });\n }\n};\n\n/* harmony default export */ var actions_default = (ClipboardActionDefault);\n;// CONCATENATED MODULE: ./src/clipboard.js\nfunction clipboard_typeof(obj) { \"@babel/helpers - typeof\"; if (typeof Symbol === \"function\" && typeof Symbol.iterator === \"symbol\") { clipboard_typeof = function _typeof(obj) { return typeof obj; }; } else { clipboard_typeof = function _typeof(obj) { return obj && typeof Symbol === \"function\" && obj.constructor === Symbol && obj !== Symbol.prototype ? \"symbol\" : typeof obj; }; } return clipboard_typeof(obj); }\n\nfunction _classCallCheck(instance, Constructor) { if (!(instance instanceof Constructor)) { throw new TypeError(\"Cannot call a class as a function\"); } }\n\nfunction _defineProperties(target, props) { for (var i = 0; i < props.length; i++) { var descriptor = props[i]; descriptor.enumerable = descriptor.enumerable || false; descriptor.configurable = true; if (\"value\" in descriptor) descriptor.writable = true; Object.defineProperty(target, descriptor.key, descriptor); } }\n\nfunction _createClass(Constructor, protoProps, staticProps) { if (protoProps) _defineProperties(Constructor.prototype, protoProps); if (staticProps) _defineProperties(Constructor, staticProps); return Constructor; }\n\nfunction _inherits(subClass, superClass) { if (typeof superClass !== \"function\" && superClass !== null) { throw new TypeError(\"Super expression must either be null or a function\"); } subClass.prototype = Object.create(superClass && superClass.prototype, { constructor: { value: subClass, writable: true, configurable: true } }); if (superClass) _setPrototypeOf(subClass, superClass); }\n\nfunction _setPrototypeOf(o, p) { _setPrototypeOf = Object.setPrototypeOf || function _setPrototypeOf(o, p) { o.__proto__ = p; return o; }; return _setPrototypeOf(o, p); }\n\nfunction _createSuper(Derived) { var hasNativeReflectConstruct = _isNativeReflectConstruct(); return function _createSuperInternal() { var Super = _getPrototypeOf(Derived), result; if (hasNativeReflectConstruct) { var NewTarget = _getPrototypeOf(this).constructor; result = Reflect.construct(Super, arguments, NewTarget); } else { result = Super.apply(this, arguments); } return _possibleConstructorReturn(this, result); }; }\n\nfunction _possibleConstructorReturn(self, call) { if (call && (clipboard_typeof(call) === \"object\" || typeof call === \"function\")) { return call; } return _assertThisInitialized(self); }\n\nfunction _assertThisInitialized(self) { if (self === void 0) { throw new ReferenceError(\"this hasn't been initialised - super() hasn't been called\"); } return self; }\n\nfunction _isNativeReflectConstruct() { if (typeof Reflect === \"undefined\" || !Reflect.construct) return false; if (Reflect.construct.sham) return false; if (typeof Proxy === \"function\") return true; try { Date.prototype.toString.call(Reflect.construct(Date, [], function () {})); return true; } catch (e) { return false; } }\n\nfunction _getPrototypeOf(o) { _getPrototypeOf = Object.setPrototypeOf ? Object.getPrototypeOf : function _getPrototypeOf(o) { return o.__proto__ || Object.getPrototypeOf(o); }; return _getPrototypeOf(o); }\n\n\n\n\n\n\n/**\n * Helper function to retrieve attribute value.\n * @param {String} suffix\n * @param {Element} element\n */\n\nfunction getAttributeValue(suffix, element) {\n var attribute = \"data-clipboard-\".concat(suffix);\n\n if (!element.hasAttribute(attribute)) {\n return;\n }\n\n return element.getAttribute(attribute);\n}\n/**\n * Base class which takes one or more elements, adds event listeners to them,\n * and instantiates a new `ClipboardAction` on each click.\n */\n\n\nvar Clipboard = /*#__PURE__*/function (_Emitter) {\n _inherits(Clipboard, _Emitter);\n\n var _super = _createSuper(Clipboard);\n\n /**\n * @param {String|HTMLElement|HTMLCollection|NodeList} trigger\n * @param {Object} options\n */\n function Clipboard(trigger, options) {\n var _this;\n\n _classCallCheck(this, Clipboard);\n\n _this = _super.call(this);\n\n _this.resolveOptions(options);\n\n _this.listenClick(trigger);\n\n return _this;\n }\n /**\n * Defines if attributes would be resolved using internal setter functions\n * or custom functions that were passed in the constructor.\n * @param {Object} options\n */\n\n\n _createClass(Clipboard, [{\n key: \"resolveOptions\",\n value: function resolveOptions() {\n var options = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : {};\n this.action = typeof options.action === 'function' ? options.action : this.defaultAction;\n this.target = typeof options.target === 'function' ? options.target : this.defaultTarget;\n this.text = typeof options.text === 'function' ? options.text : this.defaultText;\n this.container = clipboard_typeof(options.container) === 'object' ? options.container : document.body;\n }\n /**\n * Adds a click event listener to the passed trigger.\n * @param {String|HTMLElement|HTMLCollection|NodeList} trigger\n */\n\n }, {\n key: \"listenClick\",\n value: function listenClick(trigger) {\n var _this2 = this;\n\n this.listener = listen_default()(trigger, 'click', function (e) {\n return _this2.onClick(e);\n });\n }\n /**\n * Defines a new `ClipboardAction` on each click event.\n * @param {Event} e\n */\n\n }, {\n key: \"onClick\",\n value: function onClick(e) {\n var trigger = e.delegateTarget || e.currentTarget;\n var action = this.action(trigger) || 'copy';\n var text = actions_default({\n action: action,\n container: this.container,\n target: this.target(trigger),\n text: this.text(trigger)\n }); // Fires an event based on the copy operation result.\n\n this.emit(text ? 'success' : 'error', {\n action: action,\n text: text,\n trigger: trigger,\n clearSelection: function clearSelection() {\n if (trigger) {\n trigger.focus();\n }\n\n window.getSelection().removeAllRanges();\n }\n });\n }\n /**\n * Default `action` lookup function.\n * @param {Element} trigger\n */\n\n }, {\n key: \"defaultAction\",\n value: function defaultAction(trigger) {\n return getAttributeValue('action', trigger);\n }\n /**\n * Default `target` lookup function.\n * @param {Element} trigger\n */\n\n }, {\n key: \"defaultTarget\",\n value: function defaultTarget(trigger) {\n var selector = getAttributeValue('target', trigger);\n\n if (selector) {\n return document.querySelector(selector);\n }\n }\n /**\n * Allow fire programmatically a copy action\n * @param {String|HTMLElement} target\n * @param {Object} options\n * @returns Text copied.\n */\n\n }, {\n key: \"defaultText\",\n\n /**\n * Default `text` lookup function.\n * @param {Element} trigger\n */\n value: function defaultText(trigger) {\n return getAttributeValue('text', trigger);\n }\n /**\n * Destroy lifecycle.\n */\n\n }, {\n key: \"destroy\",\n value: function destroy() {\n this.listener.destroy();\n }\n }], [{\n key: \"copy\",\n value: function copy(target) {\n var options = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : {\n container: document.body\n };\n return actions_copy(target, options);\n }\n /**\n * Allow fire programmatically a cut action\n * @param {String|HTMLElement} target\n * @returns Text cutted.\n */\n\n }, {\n key: \"cut\",\n value: function cut(target) {\n return actions_cut(target);\n }\n /**\n * Returns the support of the given action, or all actions if no action is\n * given.\n * @param {String} [action]\n */\n\n }, {\n key: \"isSupported\",\n value: function isSupported() {\n var action = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : ['copy', 'cut'];\n var actions = typeof action === 'string' ? [action] : action;\n var support = !!document.queryCommandSupported;\n actions.forEach(function (action) {\n support = support && !!document.queryCommandSupported(action);\n });\n return support;\n }\n }]);\n\n return Clipboard;\n}((tiny_emitter_default()));\n\n/* harmony default export */ var clipboard = (Clipboard);\n\n/***/ }),\n\n/***/ 828:\n/***/ (function(module) {\n\nvar DOCUMENT_NODE_TYPE = 9;\n\n/**\n * A polyfill for Element.matches()\n */\nif (typeof Element !== 'undefined' && !Element.prototype.matches) {\n var proto = Element.prototype;\n\n proto.matches = proto.matchesSelector ||\n proto.mozMatchesSelector ||\n proto.msMatchesSelector ||\n proto.oMatchesSelector ||\n proto.webkitMatchesSelector;\n}\n\n/**\n * Finds the closest parent that matches a selector.\n *\n * @param {Element} element\n * @param {String} selector\n * @return {Function}\n */\nfunction closest (element, selector) {\n while (element && element.nodeType !== DOCUMENT_NODE_TYPE) {\n if (typeof element.matches === 'function' &&\n element.matches(selector)) {\n return element;\n }\n element = element.parentNode;\n }\n}\n\nmodule.exports = closest;\n\n\n/***/ }),\n\n/***/ 438:\n/***/ (function(module, __unused_webpack_exports, __webpack_require__) {\n\nvar closest = __webpack_require__(828);\n\n/**\n * Delegates event to a selector.\n *\n * @param {Element} element\n * @param {String} selector\n * @param {String} type\n * @param {Function} callback\n * @param {Boolean} useCapture\n * @return {Object}\n */\nfunction _delegate(element, selector, type, callback, useCapture) {\n var listenerFn = listener.apply(this, arguments);\n\n element.addEventListener(type, listenerFn, useCapture);\n\n return {\n destroy: function() {\n element.removeEventListener(type, listenerFn, useCapture);\n }\n }\n}\n\n/**\n * Delegates event to a selector.\n *\n * @param {Element|String|Array} [elements]\n * @param {String} selector\n * @param {String} type\n * @param {Function} callback\n * @param {Boolean} useCapture\n * @return {Object}\n */\nfunction delegate(elements, selector, type, callback, useCapture) {\n // Handle the regular Element usage\n if (typeof elements.addEventListener === 'function') {\n return _delegate.apply(null, arguments);\n }\n\n // Handle Element-less usage, it defaults to global delegation\n if (typeof type === 'function') {\n // Use `document` as the first parameter, then apply arguments\n // This is a short way to .unshift `arguments` without running into deoptimizations\n return _delegate.bind(null, document).apply(null, arguments);\n }\n\n // Handle Selector-based usage\n if (typeof elements === 'string') {\n elements = document.querySelectorAll(elements);\n }\n\n // Handle Array-like based usage\n return Array.prototype.map.call(elements, function (element) {\n return _delegate(element, selector, type, callback, useCapture);\n });\n}\n\n/**\n * Finds closest match and invokes callback.\n *\n * @param {Element} element\n * @param {String} selector\n * @param {String} type\n * @param {Function} callback\n * @return {Function}\n */\nfunction listener(element, selector, type, callback) {\n return function(e) {\n e.delegateTarget = closest(e.target, selector);\n\n if (e.delegateTarget) {\n callback.call(element, e);\n }\n }\n}\n\nmodule.exports = delegate;\n\n\n/***/ }),\n\n/***/ 879:\n/***/ (function(__unused_webpack_module, exports) {\n\n/**\n * Check if argument is a HTML element.\n *\n * @param {Object} value\n * @return {Boolean}\n */\nexports.node = function(value) {\n return value !== undefined\n && value instanceof HTMLElement\n && value.nodeType === 1;\n};\n\n/**\n * Check if argument is a list of HTML elements.\n *\n * @param {Object} value\n * @return {Boolean}\n */\nexports.nodeList = function(value) {\n var type = Object.prototype.toString.call(value);\n\n return value !== undefined\n && (type === '[object NodeList]' || type === '[object HTMLCollection]')\n && ('length' in value)\n && (value.length === 0 || exports.node(value[0]));\n};\n\n/**\n * Check if argument is a string.\n *\n * @param {Object} value\n * @return {Boolean}\n */\nexports.string = function(value) {\n return typeof value === 'string'\n || value instanceof String;\n};\n\n/**\n * Check if argument is a function.\n *\n * @param {Object} value\n * @return {Boolean}\n */\nexports.fn = function(value) {\n var type = Object.prototype.toString.call(value);\n\n return type === '[object Function]';\n};\n\n\n/***/ }),\n\n/***/ 370:\n/***/ (function(module, __unused_webpack_exports, __webpack_require__) {\n\nvar is = __webpack_require__(879);\nvar delegate = __webpack_require__(438);\n\n/**\n * Validates all params and calls the right\n * listener function based on its target type.\n *\n * @param {String|HTMLElement|HTMLCollection|NodeList} target\n * @param {String} type\n * @param {Function} callback\n * @return {Object}\n */\nfunction listen(target, type, callback) {\n if (!target && !type && !callback) {\n throw new Error('Missing required arguments');\n }\n\n if (!is.string(type)) {\n throw new TypeError('Second argument must be a String');\n }\n\n if (!is.fn(callback)) {\n throw new TypeError('Third argument must be a Function');\n }\n\n if (is.node(target)) {\n return listenNode(target, type, callback);\n }\n else if (is.nodeList(target)) {\n return listenNodeList(target, type, callback);\n }\n else if (is.string(target)) {\n return listenSelector(target, type, callback);\n }\n else {\n throw new TypeError('First argument must be a String, HTMLElement, HTMLCollection, or NodeList');\n }\n}\n\n/**\n * Adds an event listener to a HTML element\n * and returns a remove listener function.\n *\n * @param {HTMLElement} node\n * @param {String} type\n * @param {Function} callback\n * @return {Object}\n */\nfunction listenNode(node, type, callback) {\n node.addEventListener(type, callback);\n\n return {\n destroy: function() {\n node.removeEventListener(type, callback);\n }\n }\n}\n\n/**\n * Add an event listener to a list of HTML elements\n * and returns a remove listener function.\n *\n * @param {NodeList|HTMLCollection} nodeList\n * @param {String} type\n * @param {Function} callback\n * @return {Object}\n */\nfunction listenNodeList(nodeList, type, callback) {\n Array.prototype.forEach.call(nodeList, function(node) {\n node.addEventListener(type, callback);\n });\n\n return {\n destroy: function() {\n Array.prototype.forEach.call(nodeList, function(node) {\n node.removeEventListener(type, callback);\n });\n }\n }\n}\n\n/**\n * Add an event listener to a selector\n * and returns a remove listener function.\n *\n * @param {String} selector\n * @param {String} type\n * @param {Function} callback\n * @return {Object}\n */\nfunction listenSelector(selector, type, callback) {\n return delegate(document.body, selector, type, callback);\n}\n\nmodule.exports = listen;\n\n\n/***/ }),\n\n/***/ 817:\n/***/ (function(module) {\n\nfunction select(element) {\n var selectedText;\n\n if (element.nodeName === 'SELECT') {\n element.focus();\n\n selectedText = element.value;\n }\n else if (element.nodeName === 'INPUT' || element.nodeName === 'TEXTAREA') {\n var isReadOnly = element.hasAttribute('readonly');\n\n if (!isReadOnly) {\n element.setAttribute('readonly', '');\n }\n\n element.select();\n element.setSelectionRange(0, element.value.length);\n\n if (!isReadOnly) {\n element.removeAttribute('readonly');\n }\n\n selectedText = element.value;\n }\n else {\n if (element.hasAttribute('contenteditable')) {\n element.focus();\n }\n\n var selection = window.getSelection();\n var range = document.createRange();\n\n range.selectNodeContents(element);\n selection.removeAllRanges();\n selection.addRange(range);\n\n selectedText = selection.toString();\n }\n\n return selectedText;\n}\n\nmodule.exports = select;\n\n\n/***/ }),\n\n/***/ 279:\n/***/ (function(module) {\n\nfunction E () {\n // Keep this empty so it's easier to inherit from\n // (via https://github.com/lipsmack from https://github.com/scottcorgan/tiny-emitter/issues/3)\n}\n\nE.prototype = {\n on: function (name, callback, ctx) {\n var e = this.e || (this.e = {});\n\n (e[name] || (e[name] = [])).push({\n fn: callback,\n ctx: ctx\n });\n\n return this;\n },\n\n once: function (name, callback, ctx) {\n var self = this;\n function listener () {\n self.off(name, listener);\n callback.apply(ctx, arguments);\n };\n\n listener._ = callback\n return this.on(name, listener, ctx);\n },\n\n emit: function (name) {\n var data = [].slice.call(arguments, 1);\n var evtArr = ((this.e || (this.e = {}))[name] || []).slice();\n var i = 0;\n var len = evtArr.length;\n\n for (i; i < len; i++) {\n evtArr[i].fn.apply(evtArr[i].ctx, data);\n }\n\n return this;\n },\n\n off: function (name, callback) {\n var e = this.e || (this.e = {});\n var evts = e[name];\n var liveEvents = [];\n\n if (evts && callback) {\n for (var i = 0, len = evts.length; i < len; i++) {\n if (evts[i].fn !== callback && evts[i].fn._ !== callback)\n liveEvents.push(evts[i]);\n }\n }\n\n // Remove event from queue to prevent memory leak\n // Suggested by https://github.com/lazd\n // Ref: https://github.com/scottcorgan/tiny-emitter/commit/c6ebfaa9bc973b33d110a84a307742b7cf94c953#commitcomment-5024910\n\n (liveEvents.length)\n ? e[name] = liveEvents\n : delete e[name];\n\n return this;\n }\n};\n\nmodule.exports = E;\nmodule.exports.TinyEmitter = E;\n\n\n/***/ })\n\n/******/ \t});\n/************************************************************************/\n/******/ \t// The module cache\n/******/ \tvar __webpack_module_cache__ = {};\n/******/ \t\n/******/ \t// The require function\n/******/ \tfunction __webpack_require__(moduleId) {\n/******/ \t\t// Check if module is in cache\n/******/ \t\tif(__webpack_module_cache__[moduleId]) {\n/******/ \t\t\treturn __webpack_module_cache__[moduleId].exports;\n/******/ \t\t}\n/******/ \t\t// Create a new module (and put it into the cache)\n/******/ \t\tvar module = __webpack_module_cache__[moduleId] = {\n/******/ \t\t\t// no module.id needed\n/******/ \t\t\t// no module.loaded needed\n/******/ \t\t\texports: {}\n/******/ \t\t};\n/******/ \t\n/******/ \t\t// Execute the module function\n/******/ \t\t__webpack_modules__[moduleId](module, module.exports, __webpack_require__);\n/******/ \t\n/******/ \t\t// Return the exports of the module\n/******/ \t\treturn module.exports;\n/******/ \t}\n/******/ \t\n/************************************************************************/\n/******/ \t/* webpack/runtime/compat get default export */\n/******/ \t!function() {\n/******/ \t\t// getDefaultExport function for compatibility with non-harmony modules\n/******/ \t\t__webpack_require__.n = function(module) {\n/******/ \t\t\tvar getter = module && module.__esModule ?\n/******/ \t\t\t\tfunction() { return module['default']; } :\n/******/ \t\t\t\tfunction() { return module; };\n/******/ \t\t\t__webpack_require__.d(getter, { a: getter });\n/******/ \t\t\treturn getter;\n/******/ \t\t};\n/******/ \t}();\n/******/ \t\n/******/ \t/* webpack/runtime/define property getters */\n/******/ \t!function() {\n/******/ \t\t// define getter functions for harmony exports\n/******/ \t\t__webpack_require__.d = function(exports, definition) {\n/******/ \t\t\tfor(var key in definition) {\n/******/ \t\t\t\tif(__webpack_require__.o(definition, key) && !__webpack_require__.o(exports, key)) {\n/******/ \t\t\t\t\tObject.defineProperty(exports, key, { enumerable: true, get: definition[key] });\n/******/ \t\t\t\t}\n/******/ \t\t\t}\n/******/ \t\t};\n/******/ \t}();\n/******/ \t\n/******/ \t/* webpack/runtime/hasOwnProperty shorthand */\n/******/ \t!function() {\n/******/ \t\t__webpack_require__.o = function(obj, prop) { return Object.prototype.hasOwnProperty.call(obj, prop); }\n/******/ \t}();\n/******/ \t\n/************************************************************************/\n/******/ \t// module exports must be returned from runtime so entry inlining is disabled\n/******/ \t// startup\n/******/ \t// Load entry module and return exports\n/******/ \treturn __webpack_require__(686);\n/******/ })()\n.default;\n});", "/*!\n * escape-html\n * Copyright(c) 2012-2013 TJ Holowaychuk\n * Copyright(c) 2015 Andreas Lubbe\n * Copyright(c) 2015 Tiancheng \"Timothy\" Gu\n * MIT Licensed\n */\n\n'use strict';\n\n/**\n * Module variables.\n * @private\n */\n\nvar matchHtmlRegExp = /[\"'&<>]/;\n\n/**\n * Module exports.\n * @public\n */\n\nmodule.exports = escapeHtml;\n\n/**\n * Escape special characters in the given string of html.\n *\n * @param {string} string The string to escape for inserting into HTML\n * @return {string}\n * @public\n */\n\nfunction escapeHtml(string) {\n var str = '' + string;\n var match = matchHtmlRegExp.exec(str);\n\n if (!match) {\n return str;\n }\n\n var escape;\n var html = '';\n var index = 0;\n var lastIndex = 0;\n\n for (index = match.index; index < str.length; index++) {\n switch (str.charCodeAt(index)) {\n case 34: // \"\n escape = '"';\n break;\n case 38: // &\n escape = '&';\n break;\n case 39: // '\n escape = ''';\n break;\n case 60: // <\n escape = '<';\n break;\n case 62: // >\n escape = '>';\n break;\n default:\n continue;\n }\n\n if (lastIndex !== index) {\n html += str.substring(lastIndex, index);\n }\n\n lastIndex = index + 1;\n html += escape;\n }\n\n return lastIndex !== index\n ? html + str.substring(lastIndex, index)\n : html;\n}\n", "/*\n * Copyright (c) 2016-2024 Martin Donath \n *\n * Permission is hereby granted, free of charge, to any person obtaining a copy\n * of this software and associated documentation files (the \"Software\"), to\n * deal in the Software without restriction, including without limitation the\n * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or\n * sell copies of the Software, and to permit persons to whom the Software is\n * furnished to do so, subject to the following conditions:\n *\n * The above copyright notice and this permission notice shall be included in\n * all copies or substantial portions of the Software.\n *\n * THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\n * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\n * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL THE\n * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\n * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING\n * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS\n * IN THE SOFTWARE.\n */\n\nimport \"focus-visible\"\n\nimport {\n EMPTY,\n NEVER,\n Observable,\n Subject,\n defer,\n delay,\n filter,\n map,\n merge,\n mergeWith,\n shareReplay,\n switchMap\n} from \"rxjs\"\n\nimport { configuration, feature } from \"./_\"\nimport {\n at,\n getActiveElement,\n getOptionalElement,\n requestJSON,\n setLocation,\n setToggle,\n watchDocument,\n watchKeyboard,\n watchLocation,\n watchLocationTarget,\n watchMedia,\n watchPrint,\n watchScript,\n watchViewport\n} from \"./browser\"\nimport {\n getComponentElement,\n getComponentElements,\n mountAnnounce,\n mountBackToTop,\n mountConsent,\n mountContent,\n mountDialog,\n mountHeader,\n mountHeaderTitle,\n mountPalette,\n mountProgress,\n mountSearch,\n mountSearchHiglight,\n mountSidebar,\n mountSource,\n mountTableOfContents,\n mountTabs,\n watchHeader,\n watchMain\n} from \"./components\"\nimport {\n SearchIndex,\n setupClipboardJS,\n setupInstantNavigation,\n setupVersionSelector\n} from \"./integrations\"\nimport {\n patchEllipsis,\n patchIndeterminate,\n patchScrollfix,\n patchScrolllock\n} from \"./patches\"\nimport \"./polyfills\"\n\n/* ----------------------------------------------------------------------------\n * Functions - @todo refactor\n * ------------------------------------------------------------------------- */\n\n/**\n * Fetch search index\n *\n * @returns Search index observable\n */\nfunction fetchSearchIndex(): Observable {\n if (location.protocol === \"file:\") {\n return watchScript(\n `${new URL(\"search/search_index.js\", config.base)}`\n )\n .pipe(\n // @ts-ignore - @todo fix typings\n map(() => __index),\n shareReplay(1)\n )\n } else {\n return requestJSON(\n new URL(\"search/search_index.json\", config.base)\n )\n }\n}\n\n/* ----------------------------------------------------------------------------\n * Application\n * ------------------------------------------------------------------------- */\n\n/* Yay, JavaScript is available */\ndocument.documentElement.classList.remove(\"no-js\")\ndocument.documentElement.classList.add(\"js\")\n\n/* Set up navigation observables and subjects */\nconst document$ = watchDocument()\nconst location$ = watchLocation()\nconst target$ = watchLocationTarget(location$)\nconst keyboard$ = watchKeyboard()\n\n/* Set up media observables */\nconst viewport$ = watchViewport()\nconst tablet$ = watchMedia(\"(min-width: 960px)\")\nconst screen$ = watchMedia(\"(min-width: 1220px)\")\nconst print$ = watchPrint()\n\n/* Retrieve search index, if search is enabled */\nconst config = configuration()\nconst index$ = document.forms.namedItem(\"search\")\n ? fetchSearchIndex()\n : NEVER\n\n/* Set up Clipboard.js integration */\nconst alert$ = new Subject()\nsetupClipboardJS({ alert$ })\n\n/* Set up progress indicator */\nconst progress$ = new Subject()\n\n/* Set up instant navigation, if enabled */\nif (feature(\"navigation.instant\"))\n setupInstantNavigation({ location$, viewport$, progress$ })\n .subscribe(document$)\n\n/* Set up version selector */\nif (config.version?.provider === \"mike\")\n setupVersionSelector({ document$ })\n\n/* Always close drawer and search on navigation */\nmerge(location$, target$)\n .pipe(\n delay(125)\n )\n .subscribe(() => {\n setToggle(\"drawer\", false)\n setToggle(\"search\", false)\n })\n\n/* Set up global keyboard handlers */\nkeyboard$\n .pipe(\n filter(({ mode }) => mode === \"global\")\n )\n .subscribe(key => {\n switch (key.type) {\n\n /* Go to previous page */\n case \"p\":\n case \",\":\n const prev = getOptionalElement(\"link[rel=prev]\")\n if (typeof prev !== \"undefined\")\n setLocation(prev)\n break\n\n /* Go to next page */\n case \"n\":\n case \".\":\n const next = getOptionalElement(\"link[rel=next]\")\n if (typeof next !== \"undefined\")\n setLocation(next)\n break\n\n /* Expand navigation, see https://bit.ly/3ZjG5io */\n case \"Enter\":\n const active = getActiveElement()\n if (active instanceof HTMLLabelElement)\n active.click()\n }\n })\n\n/* Set up patches */\npatchEllipsis({ document$ })\npatchIndeterminate({ document$, tablet$ })\npatchScrollfix({ document$ })\npatchScrolllock({ viewport$, tablet$ })\n\n/* Set up header and main area observable */\nconst header$ = watchHeader(getComponentElement(\"header\"), { viewport$ })\nconst main$ = document$\n .pipe(\n map(() => getComponentElement(\"main\")),\n switchMap(el => watchMain(el, { viewport$, header$ })),\n shareReplay(1)\n )\n\n/* Set up control component observables */\nconst control$ = merge(\n\n /* Consent */\n ...getComponentElements(\"consent\")\n .map(el => mountConsent(el, { target$ })),\n\n /* Dialog */\n ...getComponentElements(\"dialog\")\n .map(el => mountDialog(el, { alert$ })),\n\n /* Header */\n ...getComponentElements(\"header\")\n .map(el => mountHeader(el, { viewport$, header$, main$ })),\n\n /* Color palette */\n ...getComponentElements(\"palette\")\n .map(el => mountPalette(el)),\n\n /* Progress bar */\n ...getComponentElements(\"progress\")\n .map(el => mountProgress(el, { progress$ })),\n\n /* Search */\n ...getComponentElements(\"search\")\n .map(el => mountSearch(el, { index$, keyboard$ })),\n\n /* Repository information */\n ...getComponentElements(\"source\")\n .map(el => mountSource(el))\n)\n\n/* Set up content component observables */\nconst content$ = defer(() => merge(\n\n /* Announcement bar */\n ...getComponentElements(\"announce\")\n .map(el => mountAnnounce(el)),\n\n /* Content */\n ...getComponentElements(\"content\")\n .map(el => mountContent(el, { viewport$, target$, print$ })),\n\n /* Search highlighting */\n ...getComponentElements(\"content\")\n .map(el => feature(\"search.highlight\")\n ? mountSearchHiglight(el, { index$, location$ })\n : EMPTY\n ),\n\n /* Header title */\n ...getComponentElements(\"header-title\")\n .map(el => mountHeaderTitle(el, { viewport$, header$ })),\n\n /* Sidebar */\n ...getComponentElements(\"sidebar\")\n .map(el => el.getAttribute(\"data-md-type\") === \"navigation\"\n ? at(screen$, () => mountSidebar(el, { viewport$, header$, main$ }))\n : at(tablet$, () => mountSidebar(el, { viewport$, header$, main$ }))\n ),\n\n /* Navigation tabs */\n ...getComponentElements(\"tabs\")\n .map(el => mountTabs(el, { viewport$, header$ })),\n\n /* Table of contents */\n ...getComponentElements(\"toc\")\n .map(el => mountTableOfContents(el, {\n viewport$, header$, main$, target$\n })),\n\n /* Back-to-top button */\n ...getComponentElements(\"top\")\n .map(el => mountBackToTop(el, { viewport$, header$, main$, target$ }))\n))\n\n/* Set up component observables */\nconst component$ = document$\n .pipe(\n switchMap(() => content$),\n mergeWith(control$),\n shareReplay(1)\n )\n\n/* Subscribe to all components */\ncomponent$.subscribe()\n\n/* ----------------------------------------------------------------------------\n * Exports\n * ------------------------------------------------------------------------- */\n\nwindow.document$ = document$ /* Document observable */\nwindow.location$ = location$ /* Location subject */\nwindow.target$ = target$ /* Location target observable */\nwindow.keyboard$ = keyboard$ /* Keyboard observable */\nwindow.viewport$ = viewport$ /* Viewport observable */\nwindow.tablet$ = tablet$ /* Media tablet observable */\nwindow.screen$ = screen$ /* Media screen observable */\nwindow.print$ = print$ /* Media print observable */\nwindow.alert$ = alert$ /* Alert subject */\nwindow.progress$ = progress$ /* Progress indicator subject */\nwindow.component$ = component$ /* Component observable */\n", "/*! *****************************************************************************\r\nCopyright (c) Microsoft Corporation.\r\n\r\nPermission to use, copy, modify, and/or distribute this software for any\r\npurpose with or without fee is hereby granted.\r\n\r\nTHE SOFTWARE IS PROVIDED \"AS IS\" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH\r\nREGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY\r\nAND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT,\r\nINDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM\r\nLOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR\r\nOTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR\r\nPERFORMANCE OF THIS SOFTWARE.\r\n***************************************************************************** */\r\n/* global Reflect, Promise */\r\n\r\nvar extendStatics = function(d, b) {\r\n extendStatics = Object.setPrototypeOf ||\r\n ({ __proto__: [] } instanceof Array && function (d, b) { d.__proto__ = b; }) ||\r\n function (d, b) { for (var p in b) if (Object.prototype.hasOwnProperty.call(b, p)) d[p] = b[p]; };\r\n return extendStatics(d, b);\r\n};\r\n\r\nexport function __extends(d, b) {\r\n if (typeof b !== \"function\" && b !== null)\r\n throw new TypeError(\"Class extends value \" + String(b) + \" is not a constructor or null\");\r\n extendStatics(d, b);\r\n function __() { this.constructor = d; }\r\n d.prototype = b === null ? Object.create(b) : (__.prototype = b.prototype, new __());\r\n}\r\n\r\nexport var __assign = function() {\r\n __assign = Object.assign || function __assign(t) {\r\n for (var s, i = 1, n = arguments.length; i < n; i++) {\r\n s = arguments[i];\r\n for (var p in s) if (Object.prototype.hasOwnProperty.call(s, p)) t[p] = s[p];\r\n }\r\n return t;\r\n }\r\n return __assign.apply(this, arguments);\r\n}\r\n\r\nexport function __rest(s, e) {\r\n var t = {};\r\n for (var p in s) if (Object.prototype.hasOwnProperty.call(s, p) && e.indexOf(p) < 0)\r\n t[p] = s[p];\r\n if (s != null && typeof Object.getOwnPropertySymbols === \"function\")\r\n for (var i = 0, p = Object.getOwnPropertySymbols(s); i < p.length; i++) {\r\n if (e.indexOf(p[i]) < 0 && Object.prototype.propertyIsEnumerable.call(s, p[i]))\r\n t[p[i]] = s[p[i]];\r\n }\r\n return t;\r\n}\r\n\r\nexport function __decorate(decorators, target, key, desc) {\r\n var c = arguments.length, r = c < 3 ? target : desc === null ? desc = Object.getOwnPropertyDescriptor(target, key) : desc, d;\r\n if (typeof Reflect === \"object\" && typeof Reflect.decorate === \"function\") r = Reflect.decorate(decorators, target, key, desc);\r\n else for (var i = decorators.length - 1; i >= 0; i--) if (d = decorators[i]) r = (c < 3 ? d(r) : c > 3 ? d(target, key, r) : d(target, key)) || r;\r\n return c > 3 && r && Object.defineProperty(target, key, r), r;\r\n}\r\n\r\nexport function __param(paramIndex, decorator) {\r\n return function (target, key) { decorator(target, key, paramIndex); }\r\n}\r\n\r\nexport function __metadata(metadataKey, metadataValue) {\r\n if (typeof Reflect === \"object\" && typeof Reflect.metadata === \"function\") return Reflect.metadata(metadataKey, metadataValue);\r\n}\r\n\r\nexport function __awaiter(thisArg, _arguments, P, generator) {\r\n function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }\r\n return new (P || (P = Promise))(function (resolve, reject) {\r\n function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }\r\n function rejected(value) { try { step(generator[\"throw\"](value)); } catch (e) { reject(e); } }\r\n function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }\r\n step((generator = generator.apply(thisArg, _arguments || [])).next());\r\n });\r\n}\r\n\r\nexport function __generator(thisArg, body) {\r\n var _ = { label: 0, sent: function() { if (t[0] & 1) throw t[1]; return t[1]; }, trys: [], ops: [] }, f, y, t, g;\r\n return g = { next: verb(0), \"throw\": verb(1), \"return\": verb(2) }, typeof Symbol === \"function\" && (g[Symbol.iterator] = function() { return this; }), g;\r\n function verb(n) { return function (v) { return step([n, v]); }; }\r\n function step(op) {\r\n if (f) throw new TypeError(\"Generator is already executing.\");\r\n while (_) try {\r\n if (f = 1, y && (t = op[0] & 2 ? y[\"return\"] : op[0] ? y[\"throw\"] || ((t = y[\"return\"]) && t.call(y), 0) : y.next) && !(t = t.call(y, op[1])).done) return t;\r\n if (y = 0, t) op = [op[0] & 2, t.value];\r\n switch (op[0]) {\r\n case 0: case 1: t = op; break;\r\n case 4: _.label++; return { value: op[1], done: false };\r\n case 5: _.label++; y = op[1]; op = [0]; continue;\r\n case 7: op = _.ops.pop(); _.trys.pop(); continue;\r\n default:\r\n if (!(t = _.trys, t = t.length > 0 && t[t.length - 1]) && (op[0] === 6 || op[0] === 2)) { _ = 0; continue; }\r\n if (op[0] === 3 && (!t || (op[1] > t[0] && op[1] < t[3]))) { _.label = op[1]; break; }\r\n if (op[0] === 6 && _.label < t[1]) { _.label = t[1]; t = op; break; }\r\n if (t && _.label < t[2]) { _.label = t[2]; _.ops.push(op); break; }\r\n if (t[2]) _.ops.pop();\r\n _.trys.pop(); continue;\r\n }\r\n op = body.call(thisArg, _);\r\n } catch (e) { op = [6, e]; y = 0; } finally { f = t = 0; }\r\n if (op[0] & 5) throw op[1]; return { value: op[0] ? op[1] : void 0, done: true };\r\n }\r\n}\r\n\r\nexport var __createBinding = Object.create ? (function(o, m, k, k2) {\r\n if (k2 === undefined) k2 = k;\r\n Object.defineProperty(o, k2, { enumerable: true, get: function() { return m[k]; } });\r\n}) : (function(o, m, k, k2) {\r\n if (k2 === undefined) k2 = k;\r\n o[k2] = m[k];\r\n});\r\n\r\nexport function __exportStar(m, o) {\r\n for (var p in m) if (p !== \"default\" && !Object.prototype.hasOwnProperty.call(o, p)) __createBinding(o, m, p);\r\n}\r\n\r\nexport function __values(o) {\r\n var s = typeof Symbol === \"function\" && Symbol.iterator, m = s && o[s], i = 0;\r\n if (m) return m.call(o);\r\n if (o && typeof o.length === \"number\") return {\r\n next: function () {\r\n if (o && i >= o.length) o = void 0;\r\n return { value: o && o[i++], done: !o };\r\n }\r\n };\r\n throw new TypeError(s ? \"Object is not iterable.\" : \"Symbol.iterator is not defined.\");\r\n}\r\n\r\nexport function __read(o, n) {\r\n var m = typeof Symbol === \"function\" && o[Symbol.iterator];\r\n if (!m) return o;\r\n var i = m.call(o), r, ar = [], e;\r\n try {\r\n while ((n === void 0 || n-- > 0) && !(r = i.next()).done) ar.push(r.value);\r\n }\r\n catch (error) { e = { error: error }; }\r\n finally {\r\n try {\r\n if (r && !r.done && (m = i[\"return\"])) m.call(i);\r\n }\r\n finally { if (e) throw e.error; }\r\n }\r\n return ar;\r\n}\r\n\r\n/** @deprecated */\r\nexport function __spread() {\r\n for (var ar = [], i = 0; i < arguments.length; i++)\r\n ar = ar.concat(__read(arguments[i]));\r\n return ar;\r\n}\r\n\r\n/** @deprecated */\r\nexport function __spreadArrays() {\r\n for (var s = 0, i = 0, il = arguments.length; i < il; i++) s += arguments[i].length;\r\n for (var r = Array(s), k = 0, i = 0; i < il; i++)\r\n for (var a = arguments[i], j = 0, jl = a.length; j < jl; j++, k++)\r\n r[k] = a[j];\r\n return r;\r\n}\r\n\r\nexport function __spreadArray(to, from, pack) {\r\n if (pack || arguments.length === 2) for (var i = 0, l = from.length, ar; i < l; i++) {\r\n if (ar || !(i in from)) {\r\n if (!ar) ar = Array.prototype.slice.call(from, 0, i);\r\n ar[i] = from[i];\r\n }\r\n }\r\n return to.concat(ar || Array.prototype.slice.call(from));\r\n}\r\n\r\nexport function __await(v) {\r\n return this instanceof __await ? (this.v = v, this) : new __await(v);\r\n}\r\n\r\nexport function __asyncGenerator(thisArg, _arguments, generator) {\r\n if (!Symbol.asyncIterator) throw new TypeError(\"Symbol.asyncIterator is not defined.\");\r\n var g = generator.apply(thisArg, _arguments || []), i, q = [];\r\n return i = {}, verb(\"next\"), verb(\"throw\"), verb(\"return\"), i[Symbol.asyncIterator] = function () { return this; }, i;\r\n function verb(n) { if (g[n]) i[n] = function (v) { return new Promise(function (a, b) { q.push([n, v, a, b]) > 1 || resume(n, v); }); }; }\r\n function resume(n, v) { try { step(g[n](v)); } catch (e) { settle(q[0][3], e); } }\r\n function step(r) { r.value instanceof __await ? Promise.resolve(r.value.v).then(fulfill, reject) : settle(q[0][2], r); }\r\n function fulfill(value) { resume(\"next\", value); }\r\n function reject(value) { resume(\"throw\", value); }\r\n function settle(f, v) { if (f(v), q.shift(), q.length) resume(q[0][0], q[0][1]); }\r\n}\r\n\r\nexport function __asyncDelegator(o) {\r\n var i, p;\r\n return i = {}, verb(\"next\"), verb(\"throw\", function (e) { throw e; }), verb(\"return\"), i[Symbol.iterator] = function () { return this; }, i;\r\n function verb(n, f) { i[n] = o[n] ? function (v) { return (p = !p) ? { value: __await(o[n](v)), done: n === \"return\" } : f ? f(v) : v; } : f; }\r\n}\r\n\r\nexport function __asyncValues(o) {\r\n if (!Symbol.asyncIterator) throw new TypeError(\"Symbol.asyncIterator is not defined.\");\r\n var m = o[Symbol.asyncIterator], i;\r\n return m ? m.call(o) : (o = typeof __values === \"function\" ? __values(o) : o[Symbol.iterator](), i = {}, verb(\"next\"), verb(\"throw\"), verb(\"return\"), i[Symbol.asyncIterator] = function () { return this; }, i);\r\n function verb(n) { i[n] = o[n] && function (v) { return new Promise(function (resolve, reject) { v = o[n](v), settle(resolve, reject, v.done, v.value); }); }; }\r\n function settle(resolve, reject, d, v) { Promise.resolve(v).then(function(v) { resolve({ value: v, done: d }); }, reject); }\r\n}\r\n\r\nexport function __makeTemplateObject(cooked, raw) {\r\n if (Object.defineProperty) { Object.defineProperty(cooked, \"raw\", { value: raw }); } else { cooked.raw = raw; }\r\n return cooked;\r\n};\r\n\r\nvar __setModuleDefault = Object.create ? (function(o, v) {\r\n Object.defineProperty(o, \"default\", { enumerable: true, value: v });\r\n}) : function(o, v) {\r\n o[\"default\"] = v;\r\n};\r\n\r\nexport function __importStar(mod) {\r\n if (mod && mod.__esModule) return mod;\r\n var result = {};\r\n if (mod != null) for (var k in mod) if (k !== \"default\" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);\r\n __setModuleDefault(result, mod);\r\n return result;\r\n}\r\n\r\nexport function __importDefault(mod) {\r\n return (mod && mod.__esModule) ? mod : { default: mod };\r\n}\r\n\r\nexport function __classPrivateFieldGet(receiver, state, kind, f) {\r\n if (kind === \"a\" && !f) throw new TypeError(\"Private accessor was defined without a getter\");\r\n if (typeof state === \"function\" ? receiver !== state || !f : !state.has(receiver)) throw new TypeError(\"Cannot read private member from an object whose class did not declare it\");\r\n return kind === \"m\" ? f : kind === \"a\" ? f.call(receiver) : f ? f.value : state.get(receiver);\r\n}\r\n\r\nexport function __classPrivateFieldSet(receiver, state, value, kind, f) {\r\n if (kind === \"m\") throw new TypeError(\"Private method is not writable\");\r\n if (kind === \"a\" && !f) throw new TypeError(\"Private accessor was defined without a setter\");\r\n if (typeof state === \"function\" ? receiver !== state || !f : !state.has(receiver)) throw new TypeError(\"Cannot write private member to an object whose class did not declare it\");\r\n return (kind === \"a\" ? f.call(receiver, value) : f ? f.value = value : state.set(receiver, value)), value;\r\n}\r\n", "/**\n * Returns true if the object is a function.\n * @param value The value to check\n */\nexport function isFunction(value: any): value is (...args: any[]) => any {\n return typeof value === 'function';\n}\n", "/**\n * Used to create Error subclasses until the community moves away from ES5.\n *\n * This is because compiling from TypeScript down to ES5 has issues with subclassing Errors\n * as well as other built-in types: https://github.com/Microsoft/TypeScript/issues/12123\n *\n * @param createImpl A factory function to create the actual constructor implementation. The returned\n * function should be a named function that calls `_super` internally.\n */\nexport function createErrorClass(createImpl: (_super: any) => any): T {\n const _super = (instance: any) => {\n Error.call(instance);\n instance.stack = new Error().stack;\n };\n\n const ctorFunc = createImpl(_super);\n ctorFunc.prototype = Object.create(Error.prototype);\n ctorFunc.prototype.constructor = ctorFunc;\n return ctorFunc;\n}\n", "import { createErrorClass } from './createErrorClass';\n\nexport interface UnsubscriptionError extends Error {\n readonly errors: any[];\n}\n\nexport interface UnsubscriptionErrorCtor {\n /**\n * @deprecated Internal implementation detail. Do not construct error instances.\n * Cannot be tagged as internal: https://github.com/ReactiveX/rxjs/issues/6269\n */\n new (errors: any[]): UnsubscriptionError;\n}\n\n/**\n * An error thrown when one or more errors have occurred during the\n * `unsubscribe` of a {@link Subscription}.\n */\nexport const UnsubscriptionError: UnsubscriptionErrorCtor = createErrorClass(\n (_super) =>\n function UnsubscriptionErrorImpl(this: any, errors: (Error | string)[]) {\n _super(this);\n this.message = errors\n ? `${errors.length} errors occurred during unsubscription:\n${errors.map((err, i) => `${i + 1}) ${err.toString()}`).join('\\n ')}`\n : '';\n this.name = 'UnsubscriptionError';\n this.errors = errors;\n }\n);\n", "/**\n * Removes an item from an array, mutating it.\n * @param arr The array to remove the item from\n * @param item The item to remove\n */\nexport function arrRemove(arr: T[] | undefined | null, item: T) {\n if (arr) {\n const index = arr.indexOf(item);\n 0 <= index && arr.splice(index, 1);\n }\n}\n", "import { isFunction } from './util/isFunction';\nimport { UnsubscriptionError } from './util/UnsubscriptionError';\nimport { SubscriptionLike, TeardownLogic, Unsubscribable } from './types';\nimport { arrRemove } from './util/arrRemove';\n\n/**\n * Represents a disposable resource, such as the execution of an Observable. A\n * Subscription has one important method, `unsubscribe`, that takes no argument\n * and just disposes the resource held by the subscription.\n *\n * Additionally, subscriptions may be grouped together through the `add()`\n * method, which will attach a child Subscription to the current Subscription.\n * When a Subscription is unsubscribed, all its children (and its grandchildren)\n * will be unsubscribed as well.\n *\n * @class Subscription\n */\nexport class Subscription implements SubscriptionLike {\n /** @nocollapse */\n public static EMPTY = (() => {\n const empty = new Subscription();\n empty.closed = true;\n return empty;\n })();\n\n /**\n * A flag to indicate whether this Subscription has already been unsubscribed.\n */\n public closed = false;\n\n private _parentage: Subscription[] | Subscription | null = null;\n\n /**\n * The list of registered finalizers to execute upon unsubscription. Adding and removing from this\n * list occurs in the {@link #add} and {@link #remove} methods.\n */\n private _finalizers: Exclude[] | null = null;\n\n /**\n * @param initialTeardown A function executed first as part of the finalization\n * process that is kicked off when {@link #unsubscribe} is called.\n */\n constructor(private initialTeardown?: () => void) {}\n\n /**\n * Disposes the resources held by the subscription. May, for instance, cancel\n * an ongoing Observable execution or cancel any other type of work that\n * started when the Subscription was created.\n * @return {void}\n */\n unsubscribe(): void {\n let errors: any[] | undefined;\n\n if (!this.closed) {\n this.closed = true;\n\n // Remove this from it's parents.\n const { _parentage } = this;\n if (_parentage) {\n this._parentage = null;\n if (Array.isArray(_parentage)) {\n for (const parent of _parentage) {\n parent.remove(this);\n }\n } else {\n _parentage.remove(this);\n }\n }\n\n const { initialTeardown: initialFinalizer } = this;\n if (isFunction(initialFinalizer)) {\n try {\n initialFinalizer();\n } catch (e) {\n errors = e instanceof UnsubscriptionError ? e.errors : [e];\n }\n }\n\n const { _finalizers } = this;\n if (_finalizers) {\n this._finalizers = null;\n for (const finalizer of _finalizers) {\n try {\n execFinalizer(finalizer);\n } catch (err) {\n errors = errors ?? [];\n if (err instanceof UnsubscriptionError) {\n errors = [...errors, ...err.errors];\n } else {\n errors.push(err);\n }\n }\n }\n }\n\n if (errors) {\n throw new UnsubscriptionError(errors);\n }\n }\n }\n\n /**\n * Adds a finalizer to this subscription, so that finalization will be unsubscribed/called\n * when this subscription is unsubscribed. If this subscription is already {@link #closed},\n * because it has already been unsubscribed, then whatever finalizer is passed to it\n * will automatically be executed (unless the finalizer itself is also a closed subscription).\n *\n * Closed Subscriptions cannot be added as finalizers to any subscription. Adding a closed\n * subscription to a any subscription will result in no operation. (A noop).\n *\n * Adding a subscription to itself, or adding `null` or `undefined` will not perform any\n * operation at all. (A noop).\n *\n * `Subscription` instances that are added to this instance will automatically remove themselves\n * if they are unsubscribed. Functions and {@link Unsubscribable} objects that you wish to remove\n * will need to be removed manually with {@link #remove}\n *\n * @param teardown The finalization logic to add to this subscription.\n */\n add(teardown: TeardownLogic): void {\n // Only add the finalizer if it's not undefined\n // and don't add a subscription to itself.\n if (teardown && teardown !== this) {\n if (this.closed) {\n // If this subscription is already closed,\n // execute whatever finalizer is handed to it automatically.\n execFinalizer(teardown);\n } else {\n if (teardown instanceof Subscription) {\n // We don't add closed subscriptions, and we don't add the same subscription\n // twice. Subscription unsubscribe is idempotent.\n if (teardown.closed || teardown._hasParent(this)) {\n return;\n }\n teardown._addParent(this);\n }\n (this._finalizers = this._finalizers ?? []).push(teardown);\n }\n }\n }\n\n /**\n * Checks to see if a this subscription already has a particular parent.\n * This will signal that this subscription has already been added to the parent in question.\n * @param parent the parent to check for\n */\n private _hasParent(parent: Subscription) {\n const { _parentage } = this;\n return _parentage === parent || (Array.isArray(_parentage) && _parentage.includes(parent));\n }\n\n /**\n * Adds a parent to this subscription so it can be removed from the parent if it\n * unsubscribes on it's own.\n *\n * NOTE: THIS ASSUMES THAT {@link _hasParent} HAS ALREADY BEEN CHECKED.\n * @param parent The parent subscription to add\n */\n private _addParent(parent: Subscription) {\n const { _parentage } = this;\n this._parentage = Array.isArray(_parentage) ? (_parentage.push(parent), _parentage) : _parentage ? [_parentage, parent] : parent;\n }\n\n /**\n * Called on a child when it is removed via {@link #remove}.\n * @param parent The parent to remove\n */\n private _removeParent(parent: Subscription) {\n const { _parentage } = this;\n if (_parentage === parent) {\n this._parentage = null;\n } else if (Array.isArray(_parentage)) {\n arrRemove(_parentage, parent);\n }\n }\n\n /**\n * Removes a finalizer from this subscription that was previously added with the {@link #add} method.\n *\n * Note that `Subscription` instances, when unsubscribed, will automatically remove themselves\n * from every other `Subscription` they have been added to. This means that using the `remove` method\n * is not a common thing and should be used thoughtfully.\n *\n * If you add the same finalizer instance of a function or an unsubscribable object to a `Subscription` instance\n * more than once, you will need to call `remove` the same number of times to remove all instances.\n *\n * All finalizer instances are removed to free up memory upon unsubscription.\n *\n * @param teardown The finalizer to remove from this subscription\n */\n remove(teardown: Exclude): void {\n const { _finalizers } = this;\n _finalizers && arrRemove(_finalizers, teardown);\n\n if (teardown instanceof Subscription) {\n teardown._removeParent(this);\n }\n }\n}\n\nexport const EMPTY_SUBSCRIPTION = Subscription.EMPTY;\n\nexport function isSubscription(value: any): value is Subscription {\n return (\n value instanceof Subscription ||\n (value && 'closed' in value && isFunction(value.remove) && isFunction(value.add) && isFunction(value.unsubscribe))\n );\n}\n\nfunction execFinalizer(finalizer: Unsubscribable | (() => void)) {\n if (isFunction(finalizer)) {\n finalizer();\n } else {\n finalizer.unsubscribe();\n }\n}\n", "import { Subscriber } from './Subscriber';\nimport { ObservableNotification } from './types';\n\n/**\n * The {@link GlobalConfig} object for RxJS. It is used to configure things\n * like how to react on unhandled errors.\n */\nexport const config: GlobalConfig = {\n onUnhandledError: null,\n onStoppedNotification: null,\n Promise: undefined,\n useDeprecatedSynchronousErrorHandling: false,\n useDeprecatedNextContext: false,\n};\n\n/**\n * The global configuration object for RxJS, used to configure things\n * like how to react on unhandled errors. Accessible via {@link config}\n * object.\n */\nexport interface GlobalConfig {\n /**\n * A registration point for unhandled errors from RxJS. These are errors that\n * cannot were not handled by consuming code in the usual subscription path. For\n * example, if you have this configured, and you subscribe to an observable without\n * providing an error handler, errors from that subscription will end up here. This\n * will _always_ be called asynchronously on another job in the runtime. This is because\n * we do not want errors thrown in this user-configured handler to interfere with the\n * behavior of the library.\n */\n onUnhandledError: ((err: any) => void) | null;\n\n /**\n * A registration point for notifications that cannot be sent to subscribers because they\n * have completed, errored or have been explicitly unsubscribed. By default, next, complete\n * and error notifications sent to stopped subscribers are noops. However, sometimes callers\n * might want a different behavior. For example, with sources that attempt to report errors\n * to stopped subscribers, a caller can configure RxJS to throw an unhandled error instead.\n * This will _always_ be called asynchronously on another job in the runtime. This is because\n * we do not want errors thrown in this user-configured handler to interfere with the\n * behavior of the library.\n */\n onStoppedNotification: ((notification: ObservableNotification, subscriber: Subscriber) => void) | null;\n\n /**\n * The promise constructor used by default for {@link Observable#toPromise toPromise} and {@link Observable#forEach forEach}\n * methods.\n *\n * @deprecated As of version 8, RxJS will no longer support this sort of injection of a\n * Promise constructor. If you need a Promise implementation other than native promises,\n * please polyfill/patch Promise as you see appropriate. Will be removed in v8.\n */\n Promise?: PromiseConstructorLike;\n\n /**\n * If true, turns on synchronous error rethrowing, which is a deprecated behavior\n * in v6 and higher. This behavior enables bad patterns like wrapping a subscribe\n * call in a try/catch block. It also enables producer interference, a nasty bug\n * where a multicast can be broken for all observers by a downstream consumer with\n * an unhandled error. DO NOT USE THIS FLAG UNLESS IT'S NEEDED TO BUY TIME\n * FOR MIGRATION REASONS.\n *\n * @deprecated As of version 8, RxJS will no longer support synchronous throwing\n * of unhandled errors. All errors will be thrown on a separate call stack to prevent bad\n * behaviors described above. Will be removed in v8.\n */\n useDeprecatedSynchronousErrorHandling: boolean;\n\n /**\n * If true, enables an as-of-yet undocumented feature from v5: The ability to access\n * `unsubscribe()` via `this` context in `next` functions created in observers passed\n * to `subscribe`.\n *\n * This is being removed because the performance was severely problematic, and it could also cause\n * issues when types other than POJOs are passed to subscribe as subscribers, as they will likely have\n * their `this` context overwritten.\n *\n * @deprecated As of version 8, RxJS will no longer support altering the\n * context of next functions provided as part of an observer to Subscribe. Instead,\n * you will have access to a subscription or a signal or token that will allow you to do things like\n * unsubscribe and test closed status. Will be removed in v8.\n */\n useDeprecatedNextContext: boolean;\n}\n", "import type { TimerHandle } from './timerHandle';\ntype SetTimeoutFunction = (handler: () => void, timeout?: number, ...args: any[]) => TimerHandle;\ntype ClearTimeoutFunction = (handle: TimerHandle) => void;\n\ninterface TimeoutProvider {\n setTimeout: SetTimeoutFunction;\n clearTimeout: ClearTimeoutFunction;\n delegate:\n | {\n setTimeout: SetTimeoutFunction;\n clearTimeout: ClearTimeoutFunction;\n }\n | undefined;\n}\n\nexport const timeoutProvider: TimeoutProvider = {\n // When accessing the delegate, use the variable rather than `this` so that\n // the functions can be called without being bound to the provider.\n setTimeout(handler: () => void, timeout?: number, ...args) {\n const { delegate } = timeoutProvider;\n if (delegate?.setTimeout) {\n return delegate.setTimeout(handler, timeout, ...args);\n }\n return setTimeout(handler, timeout, ...args);\n },\n clearTimeout(handle) {\n const { delegate } = timeoutProvider;\n return (delegate?.clearTimeout || clearTimeout)(handle as any);\n },\n delegate: undefined,\n};\n", "import { config } from '../config';\nimport { timeoutProvider } from '../scheduler/timeoutProvider';\n\n/**\n * Handles an error on another job either with the user-configured {@link onUnhandledError},\n * or by throwing it on that new job so it can be picked up by `window.onerror`, `process.on('error')`, etc.\n *\n * This should be called whenever there is an error that is out-of-band with the subscription\n * or when an error hits a terminal boundary of the subscription and no error handler was provided.\n *\n * @param err the error to report\n */\nexport function reportUnhandledError(err: any) {\n timeoutProvider.setTimeout(() => {\n const { onUnhandledError } = config;\n if (onUnhandledError) {\n // Execute the user-configured error handler.\n onUnhandledError(err);\n } else {\n // Throw so it is picked up by the runtime's uncaught error mechanism.\n throw err;\n }\n });\n}\n", "/* tslint:disable:no-empty */\nexport function noop() { }\n", "import { CompleteNotification, NextNotification, ErrorNotification } from './types';\n\n/**\n * A completion object optimized for memory use and created to be the\n * same \"shape\" as other notifications in v8.\n * @internal\n */\nexport const COMPLETE_NOTIFICATION = (() => createNotification('C', undefined, undefined) as CompleteNotification)();\n\n/**\n * Internal use only. Creates an optimized error notification that is the same \"shape\"\n * as other notifications.\n * @internal\n */\nexport function errorNotification(error: any): ErrorNotification {\n return createNotification('E', undefined, error) as any;\n}\n\n/**\n * Internal use only. Creates an optimized next notification that is the same \"shape\"\n * as other notifications.\n * @internal\n */\nexport function nextNotification(value: T) {\n return createNotification('N', value, undefined) as NextNotification;\n}\n\n/**\n * Ensures that all notifications created internally have the same \"shape\" in v8.\n *\n * TODO: This is only exported to support a crazy legacy test in `groupBy`.\n * @internal\n */\nexport function createNotification(kind: 'N' | 'E' | 'C', value: any, error: any) {\n return {\n kind,\n value,\n error,\n };\n}\n", "import { config } from '../config';\n\nlet context: { errorThrown: boolean; error: any } | null = null;\n\n/**\n * Handles dealing with errors for super-gross mode. Creates a context, in which\n * any synchronously thrown errors will be passed to {@link captureError}. Which\n * will record the error such that it will be rethrown after the call back is complete.\n * TODO: Remove in v8\n * @param cb An immediately executed function.\n */\nexport function errorContext(cb: () => void) {\n if (config.useDeprecatedSynchronousErrorHandling) {\n const isRoot = !context;\n if (isRoot) {\n context = { errorThrown: false, error: null };\n }\n cb();\n if (isRoot) {\n const { errorThrown, error } = context!;\n context = null;\n if (errorThrown) {\n throw error;\n }\n }\n } else {\n // This is the general non-deprecated path for everyone that\n // isn't crazy enough to use super-gross mode (useDeprecatedSynchronousErrorHandling)\n cb();\n }\n}\n\n/**\n * Captures errors only in super-gross mode.\n * @param err the error to capture\n */\nexport function captureError(err: any) {\n if (config.useDeprecatedSynchronousErrorHandling && context) {\n context.errorThrown = true;\n context.error = err;\n }\n}\n", "import { isFunction } from './util/isFunction';\nimport { Observer, ObservableNotification } from './types';\nimport { isSubscription, Subscription } from './Subscription';\nimport { config } from './config';\nimport { reportUnhandledError } from './util/reportUnhandledError';\nimport { noop } from './util/noop';\nimport { nextNotification, errorNotification, COMPLETE_NOTIFICATION } from './NotificationFactories';\nimport { timeoutProvider } from './scheduler/timeoutProvider';\nimport { captureError } from './util/errorContext';\n\n/**\n * Implements the {@link Observer} interface and extends the\n * {@link Subscription} class. While the {@link Observer} is the public API for\n * consuming the values of an {@link Observable}, all Observers get converted to\n * a Subscriber, in order to provide Subscription-like capabilities such as\n * `unsubscribe`. Subscriber is a common type in RxJS, and crucial for\n * implementing operators, but it is rarely used as a public API.\n *\n * @class Subscriber\n */\nexport class Subscriber extends Subscription implements Observer {\n /**\n * A static factory for a Subscriber, given a (potentially partial) definition\n * of an Observer.\n * @param next The `next` callback of an Observer.\n * @param error The `error` callback of an\n * Observer.\n * @param complete The `complete` callback of an\n * Observer.\n * @return A Subscriber wrapping the (partially defined)\n * Observer represented by the given arguments.\n * @nocollapse\n * @deprecated Do not use. Will be removed in v8. There is no replacement for this\n * method, and there is no reason to be creating instances of `Subscriber` directly.\n * If you have a specific use case, please file an issue.\n */\n static create(next?: (x?: T) => void, error?: (e?: any) => void, complete?: () => void): Subscriber {\n return new SafeSubscriber(next, error, complete);\n }\n\n /** @deprecated Internal implementation detail, do not use directly. Will be made internal in v8. */\n protected isStopped: boolean = false;\n /** @deprecated Internal implementation detail, do not use directly. Will be made internal in v8. */\n protected destination: Subscriber | Observer; // this `any` is the escape hatch to erase extra type param (e.g. R)\n\n /**\n * @deprecated Internal implementation detail, do not use directly. Will be made internal in v8.\n * There is no reason to directly create an instance of Subscriber. This type is exported for typings reasons.\n */\n constructor(destination?: Subscriber | Observer) {\n super();\n if (destination) {\n this.destination = destination;\n // Automatically chain subscriptions together here.\n // if destination is a Subscription, then it is a Subscriber.\n if (isSubscription(destination)) {\n destination.add(this);\n }\n } else {\n this.destination = EMPTY_OBSERVER;\n }\n }\n\n /**\n * The {@link Observer} callback to receive notifications of type `next` from\n * the Observable, with a value. The Observable may call this method 0 or more\n * times.\n * @param {T} [value] The `next` value.\n * @return {void}\n */\n next(value?: T): void {\n if (this.isStopped) {\n handleStoppedNotification(nextNotification(value), this);\n } else {\n this._next(value!);\n }\n }\n\n /**\n * The {@link Observer} callback to receive notifications of type `error` from\n * the Observable, with an attached `Error`. Notifies the Observer that\n * the Observable has experienced an error condition.\n * @param {any} [err] The `error` exception.\n * @return {void}\n */\n error(err?: any): void {\n if (this.isStopped) {\n handleStoppedNotification(errorNotification(err), this);\n } else {\n this.isStopped = true;\n this._error(err);\n }\n }\n\n /**\n * The {@link Observer} callback to receive a valueless notification of type\n * `complete` from the Observable. Notifies the Observer that the Observable\n * has finished sending push-based notifications.\n * @return {void}\n */\n complete(): void {\n if (this.isStopped) {\n handleStoppedNotification(COMPLETE_NOTIFICATION, this);\n } else {\n this.isStopped = true;\n this._complete();\n }\n }\n\n unsubscribe(): void {\n if (!this.closed) {\n this.isStopped = true;\n super.unsubscribe();\n this.destination = null!;\n }\n }\n\n protected _next(value: T): void {\n this.destination.next(value);\n }\n\n protected _error(err: any): void {\n try {\n this.destination.error(err);\n } finally {\n this.unsubscribe();\n }\n }\n\n protected _complete(): void {\n try {\n this.destination.complete();\n } finally {\n this.unsubscribe();\n }\n }\n}\n\n/**\n * This bind is captured here because we want to be able to have\n * compatibility with monoid libraries that tend to use a method named\n * `bind`. In particular, a library called Monio requires this.\n */\nconst _bind = Function.prototype.bind;\n\nfunction bind any>(fn: Fn, thisArg: any): Fn {\n return _bind.call(fn, thisArg);\n}\n\n/**\n * Internal optimization only, DO NOT EXPOSE.\n * @internal\n */\nclass ConsumerObserver implements Observer {\n constructor(private partialObserver: Partial>) {}\n\n next(value: T): void {\n const { partialObserver } = this;\n if (partialObserver.next) {\n try {\n partialObserver.next(value);\n } catch (error) {\n handleUnhandledError(error);\n }\n }\n }\n\n error(err: any): void {\n const { partialObserver } = this;\n if (partialObserver.error) {\n try {\n partialObserver.error(err);\n } catch (error) {\n handleUnhandledError(error);\n }\n } else {\n handleUnhandledError(err);\n }\n }\n\n complete(): void {\n const { partialObserver } = this;\n if (partialObserver.complete) {\n try {\n partialObserver.complete();\n } catch (error) {\n handleUnhandledError(error);\n }\n }\n }\n}\n\nexport class SafeSubscriber extends Subscriber {\n constructor(\n observerOrNext?: Partial> | ((value: T) => void) | null,\n error?: ((e?: any) => void) | null,\n complete?: (() => void) | null\n ) {\n super();\n\n let partialObserver: Partial>;\n if (isFunction(observerOrNext) || !observerOrNext) {\n // The first argument is a function, not an observer. The next\n // two arguments *could* be observers, or they could be empty.\n partialObserver = {\n next: (observerOrNext ?? undefined) as (((value: T) => void) | undefined),\n error: error ?? undefined,\n complete: complete ?? undefined,\n };\n } else {\n // The first argument is a partial observer.\n let context: any;\n if (this && config.useDeprecatedNextContext) {\n // This is a deprecated path that made `this.unsubscribe()` available in\n // next handler functions passed to subscribe. This only exists behind a flag\n // now, as it is *very* slow.\n context = Object.create(observerOrNext);\n context.unsubscribe = () => this.unsubscribe();\n partialObserver = {\n next: observerOrNext.next && bind(observerOrNext.next, context),\n error: observerOrNext.error && bind(observerOrNext.error, context),\n complete: observerOrNext.complete && bind(observerOrNext.complete, context),\n };\n } else {\n // The \"normal\" path. Just use the partial observer directly.\n partialObserver = observerOrNext;\n }\n }\n\n // Wrap the partial observer to ensure it's a full observer, and\n // make sure proper error handling is accounted for.\n this.destination = new ConsumerObserver(partialObserver);\n }\n}\n\nfunction handleUnhandledError(error: any) {\n if (config.useDeprecatedSynchronousErrorHandling) {\n captureError(error);\n } else {\n // Ideal path, we report this as an unhandled error,\n // which is thrown on a new call stack.\n reportUnhandledError(error);\n }\n}\n\n/**\n * An error handler used when no error handler was supplied\n * to the SafeSubscriber -- meaning no error handler was supplied\n * do the `subscribe` call on our observable.\n * @param err The error to handle\n */\nfunction defaultErrorHandler(err: any) {\n throw err;\n}\n\n/**\n * A handler for notifications that cannot be sent to a stopped subscriber.\n * @param notification The notification being sent\n * @param subscriber The stopped subscriber\n */\nfunction handleStoppedNotification(notification: ObservableNotification, subscriber: Subscriber) {\n const { onStoppedNotification } = config;\n onStoppedNotification && timeoutProvider.setTimeout(() => onStoppedNotification(notification, subscriber));\n}\n\n/**\n * The observer used as a stub for subscriptions where the user did not\n * pass any arguments to `subscribe`. Comes with the default error handling\n * behavior.\n */\nexport const EMPTY_OBSERVER: Readonly> & { closed: true } = {\n closed: true,\n next: noop,\n error: defaultErrorHandler,\n complete: noop,\n};\n", "/**\n * Symbol.observable or a string \"@@observable\". Used for interop\n *\n * @deprecated We will no longer be exporting this symbol in upcoming versions of RxJS.\n * Instead polyfill and use Symbol.observable directly *or* use https://www.npmjs.com/package/symbol-observable\n */\nexport const observable: string | symbol = (() => (typeof Symbol === 'function' && Symbol.observable) || '@@observable')();\n", "/**\n * This function takes one parameter and just returns it. Simply put,\n * this is like `(x: T): T => x`.\n *\n * ## Examples\n *\n * This is useful in some cases when using things like `mergeMap`\n *\n * ```ts\n * import { interval, take, map, range, mergeMap, identity } from 'rxjs';\n *\n * const source$ = interval(1000).pipe(take(5));\n *\n * const result$ = source$.pipe(\n * map(i => range(i)),\n * mergeMap(identity) // same as mergeMap(x => x)\n * );\n *\n * result$.subscribe({\n * next: console.log\n * });\n * ```\n *\n * Or when you want to selectively apply an operator\n *\n * ```ts\n * import { interval, take, identity } from 'rxjs';\n *\n * const shouldLimit = () => Math.random() < 0.5;\n *\n * const source$ = interval(1000);\n *\n * const result$ = source$.pipe(shouldLimit() ? take(5) : identity);\n *\n * result$.subscribe({\n * next: console.log\n * });\n * ```\n *\n * @param x Any value that is returned by this function\n * @returns The value passed as the first parameter to this function\n */\nexport function identity(x: T): T {\n return x;\n}\n", "import { identity } from './identity';\nimport { UnaryFunction } from '../types';\n\nexport function pipe(): typeof identity;\nexport function pipe(fn1: UnaryFunction): UnaryFunction;\nexport function pipe(fn1: UnaryFunction, fn2: UnaryFunction): UnaryFunction;\nexport function pipe(fn1: UnaryFunction, fn2: UnaryFunction, fn3: UnaryFunction): UnaryFunction;\nexport function pipe(\n fn1: UnaryFunction,\n fn2: UnaryFunction,\n fn3: UnaryFunction,\n fn4: UnaryFunction\n): UnaryFunction;\nexport function pipe(\n fn1: UnaryFunction,\n fn2: UnaryFunction,\n fn3: UnaryFunction,\n fn4: UnaryFunction,\n fn5: UnaryFunction\n): UnaryFunction;\nexport function pipe(\n fn1: UnaryFunction,\n fn2: UnaryFunction,\n fn3: UnaryFunction,\n fn4: UnaryFunction,\n fn5: UnaryFunction,\n fn6: UnaryFunction\n): UnaryFunction;\nexport function pipe(\n fn1: UnaryFunction,\n fn2: UnaryFunction,\n fn3: UnaryFunction,\n fn4: UnaryFunction,\n fn5: UnaryFunction,\n fn6: UnaryFunction,\n fn7: UnaryFunction\n): UnaryFunction;\nexport function pipe(\n fn1: UnaryFunction,\n fn2: UnaryFunction,\n fn3: UnaryFunction,\n fn4: UnaryFunction,\n fn5: UnaryFunction,\n fn6: UnaryFunction,\n fn7: UnaryFunction,\n fn8: UnaryFunction\n): UnaryFunction;\nexport function pipe(\n fn1: UnaryFunction,\n fn2: UnaryFunction,\n fn3: UnaryFunction,\n fn4: UnaryFunction,\n fn5: UnaryFunction,\n fn6: UnaryFunction,\n fn7: UnaryFunction,\n fn8: UnaryFunction,\n fn9: UnaryFunction\n): UnaryFunction;\nexport function pipe(\n fn1: UnaryFunction,\n fn2: UnaryFunction,\n fn3: UnaryFunction,\n fn4: UnaryFunction,\n fn5: UnaryFunction,\n fn6: UnaryFunction,\n fn7: UnaryFunction,\n fn8: UnaryFunction,\n fn9: UnaryFunction,\n ...fns: UnaryFunction[]\n): UnaryFunction;\n\n/**\n * pipe() can be called on one or more functions, each of which can take one argument (\"UnaryFunction\")\n * and uses it to return a value.\n * It returns a function that takes one argument, passes it to the first UnaryFunction, and then\n * passes the result to the next one, passes that result to the next one, and so on. \n */\nexport function pipe(...fns: Array>): UnaryFunction {\n return pipeFromArray(fns);\n}\n\n/** @internal */\nexport function pipeFromArray(fns: Array>): UnaryFunction {\n if (fns.length === 0) {\n return identity as UnaryFunction;\n }\n\n if (fns.length === 1) {\n return fns[0];\n }\n\n return function piped(input: T): R {\n return fns.reduce((prev: any, fn: UnaryFunction) => fn(prev), input as any);\n };\n}\n", "import { Operator } from './Operator';\nimport { SafeSubscriber, Subscriber } from './Subscriber';\nimport { isSubscription, Subscription } from './Subscription';\nimport { TeardownLogic, OperatorFunction, Subscribable, Observer } from './types';\nimport { observable as Symbol_observable } from './symbol/observable';\nimport { pipeFromArray } from './util/pipe';\nimport { config } from './config';\nimport { isFunction } from './util/isFunction';\nimport { errorContext } from './util/errorContext';\n\n/**\n * A representation of any set of values over any amount of time. This is the most basic building block\n * of RxJS.\n *\n * @class Observable\n */\nexport class Observable implements Subscribable {\n /**\n * @deprecated Internal implementation detail, do not use directly. Will be made internal in v8.\n */\n source: Observable | undefined;\n\n /**\n * @deprecated Internal implementation detail, do not use directly. Will be made internal in v8.\n */\n operator: Operator | undefined;\n\n /**\n * @constructor\n * @param {Function} subscribe the function that is called when the Observable is\n * initially subscribed to. This function is given a Subscriber, to which new values\n * can be `next`ed, or an `error` method can be called to raise an error, or\n * `complete` can be called to notify of a successful completion.\n */\n constructor(subscribe?: (this: Observable, subscriber: Subscriber) => TeardownLogic) {\n if (subscribe) {\n this._subscribe = subscribe;\n }\n }\n\n // HACK: Since TypeScript inherits static properties too, we have to\n // fight against TypeScript here so Subject can have a different static create signature\n /**\n * Creates a new Observable by calling the Observable constructor\n * @owner Observable\n * @method create\n * @param {Function} subscribe? the subscriber function to be passed to the Observable constructor\n * @return {Observable} a new observable\n * @nocollapse\n * @deprecated Use `new Observable()` instead. Will be removed in v8.\n */\n static create: (...args: any[]) => any = (subscribe?: (subscriber: Subscriber) => TeardownLogic) => {\n return new Observable(subscribe);\n };\n\n /**\n * Creates a new Observable, with this Observable instance as the source, and the passed\n * operator defined as the new observable's operator.\n * @method lift\n * @param operator the operator defining the operation to take on the observable\n * @return a new observable with the Operator applied\n * @deprecated Internal implementation detail, do not use directly. Will be made internal in v8.\n * If you have implemented an operator using `lift`, it is recommended that you create an\n * operator by simply returning `new Observable()` directly. See \"Creating new operators from\n * scratch\" section here: https://rxjs.dev/guide/operators\n */\n lift(operator?: Operator): Observable {\n const observable = new Observable();\n observable.source = this;\n observable.operator = operator;\n return observable;\n }\n\n subscribe(observerOrNext?: Partial> | ((value: T) => void)): Subscription;\n /** @deprecated Instead of passing separate callback arguments, use an observer argument. Signatures taking separate callback arguments will be removed in v8. Details: https://rxjs.dev/deprecations/subscribe-arguments */\n subscribe(next?: ((value: T) => void) | null, error?: ((error: any) => void) | null, complete?: (() => void) | null): Subscription;\n /**\n * Invokes an execution of an Observable and registers Observer handlers for notifications it will emit.\n *\n * Use it when you have all these Observables, but still nothing is happening.\n *\n * `subscribe` is not a regular operator, but a method that calls Observable's internal `subscribe` function. It\n * might be for example a function that you passed to Observable's constructor, but most of the time it is\n * a library implementation, which defines what will be emitted by an Observable, and when it be will emitted. This means\n * that calling `subscribe` is actually the moment when Observable starts its work, not when it is created, as it is often\n * the thought.\n *\n * Apart from starting the execution of an Observable, this method allows you to listen for values\n * that an Observable emits, as well as for when it completes or errors. You can achieve this in two\n * of the following ways.\n *\n * The first way is creating an object that implements {@link Observer} interface. It should have methods\n * defined by that interface, but note that it should be just a regular JavaScript object, which you can create\n * yourself in any way you want (ES6 class, classic function constructor, object literal etc.). In particular, do\n * not attempt to use any RxJS implementation details to create Observers - you don't need them. Remember also\n * that your object does not have to implement all methods. If you find yourself creating a method that doesn't\n * do anything, you can simply omit it. Note however, if the `error` method is not provided and an error happens,\n * it will be thrown asynchronously. Errors thrown asynchronously cannot be caught using `try`/`catch`. Instead,\n * use the {@link onUnhandledError} configuration option or use a runtime handler (like `window.onerror` or\n * `process.on('error)`) to be notified of unhandled errors. Because of this, it's recommended that you provide\n * an `error` method to avoid missing thrown errors.\n *\n * The second way is to give up on Observer object altogether and simply provide callback functions in place of its methods.\n * This means you can provide three functions as arguments to `subscribe`, where the first function is equivalent\n * of a `next` method, the second of an `error` method and the third of a `complete` method. Just as in case of an Observer,\n * if you do not need to listen for something, you can omit a function by passing `undefined` or `null`,\n * since `subscribe` recognizes these functions by where they were placed in function call. When it comes\n * to the `error` function, as with an Observer, if not provided, errors emitted by an Observable will be thrown asynchronously.\n *\n * You can, however, subscribe with no parameters at all. This may be the case where you're not interested in terminal events\n * and you also handled emissions internally by using operators (e.g. using `tap`).\n *\n * Whichever style of calling `subscribe` you use, in both cases it returns a Subscription object.\n * This object allows you to call `unsubscribe` on it, which in turn will stop the work that an Observable does and will clean\n * up all resources that an Observable used. Note that cancelling a subscription will not call `complete` callback\n * provided to `subscribe` function, which is reserved for a regular completion signal that comes from an Observable.\n *\n * Remember that callbacks provided to `subscribe` are not guaranteed to be called asynchronously.\n * It is an Observable itself that decides when these functions will be called. For example {@link of}\n * by default emits all its values synchronously. Always check documentation for how given Observable\n * will behave when subscribed and if its default behavior can be modified with a `scheduler`.\n *\n * #### Examples\n *\n * Subscribe with an {@link guide/observer Observer}\n *\n * ```ts\n * import { of } from 'rxjs';\n *\n * const sumObserver = {\n * sum: 0,\n * next(value) {\n * console.log('Adding: ' + value);\n * this.sum = this.sum + value;\n * },\n * error() {\n * // We actually could just remove this method,\n * // since we do not really care about errors right now.\n * },\n * complete() {\n * console.log('Sum equals: ' + this.sum);\n * }\n * };\n *\n * of(1, 2, 3) // Synchronously emits 1, 2, 3 and then completes.\n * .subscribe(sumObserver);\n *\n * // Logs:\n * // 'Adding: 1'\n * // 'Adding: 2'\n * // 'Adding: 3'\n * // 'Sum equals: 6'\n * ```\n *\n * Subscribe with functions ({@link deprecations/subscribe-arguments deprecated})\n *\n * ```ts\n * import { of } from 'rxjs'\n *\n * let sum = 0;\n *\n * of(1, 2, 3).subscribe(\n * value => {\n * console.log('Adding: ' + value);\n * sum = sum + value;\n * },\n * undefined,\n * () => console.log('Sum equals: ' + sum)\n * );\n *\n * // Logs:\n * // 'Adding: 1'\n * // 'Adding: 2'\n * // 'Adding: 3'\n * // 'Sum equals: 6'\n * ```\n *\n * Cancel a subscription\n *\n * ```ts\n * import { interval } from 'rxjs';\n *\n * const subscription = interval(1000).subscribe({\n * next(num) {\n * console.log(num)\n * },\n * complete() {\n * // Will not be called, even when cancelling subscription.\n * console.log('completed!');\n * }\n * });\n *\n * setTimeout(() => {\n * subscription.unsubscribe();\n * console.log('unsubscribed!');\n * }, 2500);\n *\n * // Logs:\n * // 0 after 1s\n * // 1 after 2s\n * // 'unsubscribed!' after 2.5s\n * ```\n *\n * @param {Observer|Function} observerOrNext (optional) Either an observer with methods to be called,\n * or the first of three possible handlers, which is the handler for each value emitted from the subscribed\n * Observable.\n * @param {Function} error (optional) A handler for a terminal event resulting from an error. If no error handler is provided,\n * the error will be thrown asynchronously as unhandled.\n * @param {Function} complete (optional) A handler for a terminal event resulting from successful completion.\n * @return {Subscription} a subscription reference to the registered handlers\n * @method subscribe\n */\n subscribe(\n observerOrNext?: Partial> | ((value: T) => void) | null,\n error?: ((error: any) => void) | null,\n complete?: (() => void) | null\n ): Subscription {\n const subscriber = isSubscriber(observerOrNext) ? observerOrNext : new SafeSubscriber(observerOrNext, error, complete);\n\n errorContext(() => {\n const { operator, source } = this;\n subscriber.add(\n operator\n ? // We're dealing with a subscription in the\n // operator chain to one of our lifted operators.\n operator.call(subscriber, source)\n : source\n ? // If `source` has a value, but `operator` does not, something that\n // had intimate knowledge of our API, like our `Subject`, must have\n // set it. We're going to just call `_subscribe` directly.\n this._subscribe(subscriber)\n : // In all other cases, we're likely wrapping a user-provided initializer\n // function, so we need to catch errors and handle them appropriately.\n this._trySubscribe(subscriber)\n );\n });\n\n return subscriber;\n }\n\n /** @internal */\n protected _trySubscribe(sink: Subscriber): TeardownLogic {\n try {\n return this._subscribe(sink);\n } catch (err) {\n // We don't need to return anything in this case,\n // because it's just going to try to `add()` to a subscription\n // above.\n sink.error(err);\n }\n }\n\n /**\n * Used as a NON-CANCELLABLE means of subscribing to an observable, for use with\n * APIs that expect promises, like `async/await`. You cannot unsubscribe from this.\n *\n * **WARNING**: Only use this with observables you *know* will complete. If the source\n * observable does not complete, you will end up with a promise that is hung up, and\n * potentially all of the state of an async function hanging out in memory. To avoid\n * this situation, look into adding something like {@link timeout}, {@link take},\n * {@link takeWhile}, or {@link takeUntil} amongst others.\n *\n * #### Example\n *\n * ```ts\n * import { interval, take } from 'rxjs';\n *\n * const source$ = interval(1000).pipe(take(4));\n *\n * async function getTotal() {\n * let total = 0;\n *\n * await source$.forEach(value => {\n * total += value;\n * console.log('observable -> ' + value);\n * });\n *\n * return total;\n * }\n *\n * getTotal().then(\n * total => console.log('Total: ' + total)\n * );\n *\n * // Expected:\n * // 'observable -> 0'\n * // 'observable -> 1'\n * // 'observable -> 2'\n * // 'observable -> 3'\n * // 'Total: 6'\n * ```\n *\n * @param next a handler for each value emitted by the observable\n * @return a promise that either resolves on observable completion or\n * rejects with the handled error\n */\n forEach(next: (value: T) => void): Promise;\n\n /**\n * @param next a handler for each value emitted by the observable\n * @param promiseCtor a constructor function used to instantiate the Promise\n * @return a promise that either resolves on observable completion or\n * rejects with the handled error\n * @deprecated Passing a Promise constructor will no longer be available\n * in upcoming versions of RxJS. This is because it adds weight to the library, for very\n * little benefit. If you need this functionality, it is recommended that you either\n * polyfill Promise, or you create an adapter to convert the returned native promise\n * to whatever promise implementation you wanted. Will be removed in v8.\n */\n forEach(next: (value: T) => void, promiseCtor: PromiseConstructorLike): Promise;\n\n forEach(next: (value: T) => void, promiseCtor?: PromiseConstructorLike): Promise {\n promiseCtor = getPromiseCtor(promiseCtor);\n\n return new promiseCtor((resolve, reject) => {\n const subscriber = new SafeSubscriber({\n next: (value) => {\n try {\n next(value);\n } catch (err) {\n reject(err);\n subscriber.unsubscribe();\n }\n },\n error: reject,\n complete: resolve,\n });\n this.subscribe(subscriber);\n }) as Promise;\n }\n\n /** @internal */\n protected _subscribe(subscriber: Subscriber): TeardownLogic {\n return this.source?.subscribe(subscriber);\n }\n\n /**\n * An interop point defined by the es7-observable spec https://github.com/zenparsing/es-observable\n * @method Symbol.observable\n * @return {Observable} this instance of the observable\n */\n [Symbol_observable]() {\n return this;\n }\n\n /* tslint:disable:max-line-length */\n pipe(): Observable;\n pipe(op1: OperatorFunction): Observable;\n pipe(op1: OperatorFunction, op2: OperatorFunction): Observable;\n pipe(op1: OperatorFunction, op2: OperatorFunction, op3: OperatorFunction): Observable;\n pipe(\n op1: OperatorFunction,\n op2: OperatorFunction,\n op3: OperatorFunction,\n op4: OperatorFunction\n ): Observable;\n pipe(\n op1: OperatorFunction,\n op2: OperatorFunction,\n op3: OperatorFunction,\n op4: OperatorFunction,\n op5: OperatorFunction\n ): Observable;\n pipe(\n op1: OperatorFunction,\n op2: OperatorFunction,\n op3: OperatorFunction,\n op4: OperatorFunction,\n op5: OperatorFunction,\n op6: OperatorFunction\n ): Observable;\n pipe(\n op1: OperatorFunction,\n op2: OperatorFunction,\n op3: OperatorFunction,\n op4: OperatorFunction,\n op5: OperatorFunction,\n op6: OperatorFunction,\n op7: OperatorFunction\n ): Observable;\n pipe(\n op1: OperatorFunction,\n op2: OperatorFunction,\n op3: OperatorFunction,\n op4: OperatorFunction,\n op5: OperatorFunction,\n op6: OperatorFunction,\n op7: OperatorFunction,\n op8: OperatorFunction\n ): Observable;\n pipe(\n op1: OperatorFunction,\n op2: OperatorFunction,\n op3: OperatorFunction,\n op4: OperatorFunction,\n op5: OperatorFunction,\n op6: OperatorFunction,\n op7: OperatorFunction,\n op8: OperatorFunction,\n op9: OperatorFunction\n ): Observable;\n pipe(\n op1: OperatorFunction,\n op2: OperatorFunction,\n op3: OperatorFunction,\n op4: OperatorFunction,\n op5: OperatorFunction,\n op6: OperatorFunction,\n op7: OperatorFunction,\n op8: OperatorFunction,\n op9: OperatorFunction,\n ...operations: OperatorFunction[]\n ): Observable;\n /* tslint:enable:max-line-length */\n\n /**\n * Used to stitch together functional operators into a chain.\n * @method pipe\n * @return {Observable} the Observable result of all of the operators having\n * been called in the order they were passed in.\n *\n * ## Example\n *\n * ```ts\n * import { interval, filter, map, scan } from 'rxjs';\n *\n * interval(1000)\n * .pipe(\n * filter(x => x % 2 === 0),\n * map(x => x + x),\n * scan((acc, x) => acc + x)\n * )\n * .subscribe(x => console.log(x));\n * ```\n */\n pipe(...operations: OperatorFunction[]): Observable {\n return pipeFromArray(operations)(this);\n }\n\n /* tslint:disable:max-line-length */\n /** @deprecated Replaced with {@link firstValueFrom} and {@link lastValueFrom}. Will be removed in v8. Details: https://rxjs.dev/deprecations/to-promise */\n toPromise(): Promise;\n /** @deprecated Replaced with {@link firstValueFrom} and {@link lastValueFrom}. Will be removed in v8. Details: https://rxjs.dev/deprecations/to-promise */\n toPromise(PromiseCtor: typeof Promise): Promise;\n /** @deprecated Replaced with {@link firstValueFrom} and {@link lastValueFrom}. Will be removed in v8. Details: https://rxjs.dev/deprecations/to-promise */\n toPromise(PromiseCtor: PromiseConstructorLike): Promise;\n /* tslint:enable:max-line-length */\n\n /**\n * Subscribe to this Observable and get a Promise resolving on\n * `complete` with the last emission (if any).\n *\n * **WARNING**: Only use this with observables you *know* will complete. If the source\n * observable does not complete, you will end up with a promise that is hung up, and\n * potentially all of the state of an async function hanging out in memory. To avoid\n * this situation, look into adding something like {@link timeout}, {@link take},\n * {@link takeWhile}, or {@link takeUntil} amongst others.\n *\n * @method toPromise\n * @param [promiseCtor] a constructor function used to instantiate\n * the Promise\n * @return A Promise that resolves with the last value emit, or\n * rejects on an error. If there were no emissions, Promise\n * resolves with undefined.\n * @deprecated Replaced with {@link firstValueFrom} and {@link lastValueFrom}. Will be removed in v8. Details: https://rxjs.dev/deprecations/to-promise\n */\n toPromise(promiseCtor?: PromiseConstructorLike): Promise {\n promiseCtor = getPromiseCtor(promiseCtor);\n\n return new promiseCtor((resolve, reject) => {\n let value: T | undefined;\n this.subscribe(\n (x: T) => (value = x),\n (err: any) => reject(err),\n () => resolve(value)\n );\n }) as Promise;\n }\n}\n\n/**\n * Decides between a passed promise constructor from consuming code,\n * A default configured promise constructor, and the native promise\n * constructor and returns it. If nothing can be found, it will throw\n * an error.\n * @param promiseCtor The optional promise constructor to passed by consuming code\n */\nfunction getPromiseCtor(promiseCtor: PromiseConstructorLike | undefined) {\n return promiseCtor ?? config.Promise ?? Promise;\n}\n\nfunction isObserver(value: any): value is Observer {\n return value && isFunction(value.next) && isFunction(value.error) && isFunction(value.complete);\n}\n\nfunction isSubscriber(value: any): value is Subscriber {\n return (value && value instanceof Subscriber) || (isObserver(value) && isSubscription(value));\n}\n", "import { Observable } from '../Observable';\nimport { Subscriber } from '../Subscriber';\nimport { OperatorFunction } from '../types';\nimport { isFunction } from './isFunction';\n\n/**\n * Used to determine if an object is an Observable with a lift function.\n */\nexport function hasLift(source: any): source is { lift: InstanceType['lift'] } {\n return isFunction(source?.lift);\n}\n\n/**\n * Creates an `OperatorFunction`. Used to define operators throughout the library in a concise way.\n * @param init The logic to connect the liftedSource to the subscriber at the moment of subscription.\n */\nexport function operate(\n init: (liftedSource: Observable, subscriber: Subscriber) => (() => void) | void\n): OperatorFunction {\n return (source: Observable) => {\n if (hasLift(source)) {\n return source.lift(function (this: Subscriber, liftedSource: Observable) {\n try {\n return init(liftedSource, this);\n } catch (err) {\n this.error(err);\n }\n });\n }\n throw new TypeError('Unable to lift unknown Observable type');\n };\n}\n", "import { Subscriber } from '../Subscriber';\n\n/**\n * Creates an instance of an `OperatorSubscriber`.\n * @param destination The downstream subscriber.\n * @param onNext Handles next values, only called if this subscriber is not stopped or closed. Any\n * error that occurs in this function is caught and sent to the `error` method of this subscriber.\n * @param onError Handles errors from the subscription, any errors that occur in this handler are caught\n * and send to the `destination` error handler.\n * @param onComplete Handles completion notification from the subscription. Any errors that occur in\n * this handler are sent to the `destination` error handler.\n * @param onFinalize Additional teardown logic here. This will only be called on teardown if the\n * subscriber itself is not already closed. This is called after all other teardown logic is executed.\n */\nexport function createOperatorSubscriber(\n destination: Subscriber,\n onNext?: (value: T) => void,\n onComplete?: () => void,\n onError?: (err: any) => void,\n onFinalize?: () => void\n): Subscriber {\n return new OperatorSubscriber(destination, onNext, onComplete, onError, onFinalize);\n}\n\n/**\n * A generic helper for allowing operators to be created with a Subscriber and\n * use closures to capture necessary state from the operator function itself.\n */\nexport class OperatorSubscriber extends Subscriber {\n /**\n * Creates an instance of an `OperatorSubscriber`.\n * @param destination The downstream subscriber.\n * @param onNext Handles next values, only called if this subscriber is not stopped or closed. Any\n * error that occurs in this function is caught and sent to the `error` method of this subscriber.\n * @param onError Handles errors from the subscription, any errors that occur in this handler are caught\n * and send to the `destination` error handler.\n * @param onComplete Handles completion notification from the subscription. Any errors that occur in\n * this handler are sent to the `destination` error handler.\n * @param onFinalize Additional finalization logic here. This will only be called on finalization if the\n * subscriber itself is not already closed. This is called after all other finalization logic is executed.\n * @param shouldUnsubscribe An optional check to see if an unsubscribe call should truly unsubscribe.\n * NOTE: This currently **ONLY** exists to support the strange behavior of {@link groupBy}, where unsubscription\n * to the resulting observable does not actually disconnect from the source if there are active subscriptions\n * to any grouped observable. (DO NOT EXPOSE OR USE EXTERNALLY!!!)\n */\n constructor(\n destination: Subscriber,\n onNext?: (value: T) => void,\n onComplete?: () => void,\n onError?: (err: any) => void,\n private onFinalize?: () => void,\n private shouldUnsubscribe?: () => boolean\n ) {\n // It's important - for performance reasons - that all of this class's\n // members are initialized and that they are always initialized in the same\n // order. This will ensure that all OperatorSubscriber instances have the\n // same hidden class in V8. This, in turn, will help keep the number of\n // hidden classes involved in property accesses within the base class as\n // low as possible. If the number of hidden classes involved exceeds four,\n // the property accesses will become megamorphic and performance penalties\n // will be incurred - i.e. inline caches won't be used.\n //\n // The reasons for ensuring all instances have the same hidden class are\n // further discussed in this blog post from Benedikt Meurer:\n // https://benediktmeurer.de/2018/03/23/impact-of-polymorphism-on-component-based-frameworks-like-react/\n super(destination);\n this._next = onNext\n ? function (this: OperatorSubscriber, value: T) {\n try {\n onNext(value);\n } catch (err) {\n destination.error(err);\n }\n }\n : super._next;\n this._error = onError\n ? function (this: OperatorSubscriber, err: any) {\n try {\n onError(err);\n } catch (err) {\n // Send any errors that occur down stream.\n destination.error(err);\n } finally {\n // Ensure finalization.\n this.unsubscribe();\n }\n }\n : super._error;\n this._complete = onComplete\n ? function (this: OperatorSubscriber) {\n try {\n onComplete();\n } catch (err) {\n // Send any errors that occur down stream.\n destination.error(err);\n } finally {\n // Ensure finalization.\n this.unsubscribe();\n }\n }\n : super._complete;\n }\n\n unsubscribe() {\n if (!this.shouldUnsubscribe || this.shouldUnsubscribe()) {\n const { closed } = this;\n super.unsubscribe();\n // Execute additional teardown if we have any and we didn't already do so.\n !closed && this.onFinalize?.();\n }\n }\n}\n", "import { Subscription } from '../Subscription';\n\ninterface AnimationFrameProvider {\n schedule(callback: FrameRequestCallback): Subscription;\n requestAnimationFrame: typeof requestAnimationFrame;\n cancelAnimationFrame: typeof cancelAnimationFrame;\n delegate:\n | {\n requestAnimationFrame: typeof requestAnimationFrame;\n cancelAnimationFrame: typeof cancelAnimationFrame;\n }\n | undefined;\n}\n\nexport const animationFrameProvider: AnimationFrameProvider = {\n // When accessing the delegate, use the variable rather than `this` so that\n // the functions can be called without being bound to the provider.\n schedule(callback) {\n let request = requestAnimationFrame;\n let cancel: typeof cancelAnimationFrame | undefined = cancelAnimationFrame;\n const { delegate } = animationFrameProvider;\n if (delegate) {\n request = delegate.requestAnimationFrame;\n cancel = delegate.cancelAnimationFrame;\n }\n const handle = request((timestamp) => {\n // Clear the cancel function. The request has been fulfilled, so\n // attempting to cancel the request upon unsubscription would be\n // pointless.\n cancel = undefined;\n callback(timestamp);\n });\n return new Subscription(() => cancel?.(handle));\n },\n requestAnimationFrame(...args) {\n const { delegate } = animationFrameProvider;\n return (delegate?.requestAnimationFrame || requestAnimationFrame)(...args);\n },\n cancelAnimationFrame(...args) {\n const { delegate } = animationFrameProvider;\n return (delegate?.cancelAnimationFrame || cancelAnimationFrame)(...args);\n },\n delegate: undefined,\n};\n", "import { createErrorClass } from './createErrorClass';\n\nexport interface ObjectUnsubscribedError extends Error {}\n\nexport interface ObjectUnsubscribedErrorCtor {\n /**\n * @deprecated Internal implementation detail. Do not construct error instances.\n * Cannot be tagged as internal: https://github.com/ReactiveX/rxjs/issues/6269\n */\n new (): ObjectUnsubscribedError;\n}\n\n/**\n * An error thrown when an action is invalid because the object has been\n * unsubscribed.\n *\n * @see {@link Subject}\n * @see {@link BehaviorSubject}\n *\n * @class ObjectUnsubscribedError\n */\nexport const ObjectUnsubscribedError: ObjectUnsubscribedErrorCtor = createErrorClass(\n (_super) =>\n function ObjectUnsubscribedErrorImpl(this: any) {\n _super(this);\n this.name = 'ObjectUnsubscribedError';\n this.message = 'object unsubscribed';\n }\n);\n", "import { Operator } from './Operator';\nimport { Observable } from './Observable';\nimport { Subscriber } from './Subscriber';\nimport { Subscription, EMPTY_SUBSCRIPTION } from './Subscription';\nimport { Observer, SubscriptionLike, TeardownLogic } from './types';\nimport { ObjectUnsubscribedError } from './util/ObjectUnsubscribedError';\nimport { arrRemove } from './util/arrRemove';\nimport { errorContext } from './util/errorContext';\n\n/**\n * A Subject is a special type of Observable that allows values to be\n * multicasted to many Observers. Subjects are like EventEmitters.\n *\n * Every Subject is an Observable and an Observer. You can subscribe to a\n * Subject, and you can call next to feed values as well as error and complete.\n */\nexport class Subject extends Observable implements SubscriptionLike {\n closed = false;\n\n private currentObservers: Observer[] | null = null;\n\n /** @deprecated Internal implementation detail, do not use directly. Will be made internal in v8. */\n observers: Observer[] = [];\n /** @deprecated Internal implementation detail, do not use directly. Will be made internal in v8. */\n isStopped = false;\n /** @deprecated Internal implementation detail, do not use directly. Will be made internal in v8. */\n hasError = false;\n /** @deprecated Internal implementation detail, do not use directly. Will be made internal in v8. */\n thrownError: any = null;\n\n /**\n * Creates a \"subject\" by basically gluing an observer to an observable.\n *\n * @nocollapse\n * @deprecated Recommended you do not use. Will be removed at some point in the future. Plans for replacement still under discussion.\n */\n static create: (...args: any[]) => any = (destination: Observer, source: Observable): AnonymousSubject => {\n return new AnonymousSubject(destination, source);\n };\n\n constructor() {\n // NOTE: This must be here to obscure Observable's constructor.\n super();\n }\n\n /** @deprecated Internal implementation detail, do not use directly. Will be made internal in v8. */\n lift(operator: Operator): Observable {\n const subject = new AnonymousSubject(this, this);\n subject.operator = operator as any;\n return subject as any;\n }\n\n /** @internal */\n protected _throwIfClosed() {\n if (this.closed) {\n throw new ObjectUnsubscribedError();\n }\n }\n\n next(value: T) {\n errorContext(() => {\n this._throwIfClosed();\n if (!this.isStopped) {\n if (!this.currentObservers) {\n this.currentObservers = Array.from(this.observers);\n }\n for (const observer of this.currentObservers) {\n observer.next(value);\n }\n }\n });\n }\n\n error(err: any) {\n errorContext(() => {\n this._throwIfClosed();\n if (!this.isStopped) {\n this.hasError = this.isStopped = true;\n this.thrownError = err;\n const { observers } = this;\n while (observers.length) {\n observers.shift()!.error(err);\n }\n }\n });\n }\n\n complete() {\n errorContext(() => {\n this._throwIfClosed();\n if (!this.isStopped) {\n this.isStopped = true;\n const { observers } = this;\n while (observers.length) {\n observers.shift()!.complete();\n }\n }\n });\n }\n\n unsubscribe() {\n this.isStopped = this.closed = true;\n this.observers = this.currentObservers = null!;\n }\n\n get observed() {\n return this.observers?.length > 0;\n }\n\n /** @internal */\n protected _trySubscribe(subscriber: Subscriber): TeardownLogic {\n this._throwIfClosed();\n return super._trySubscribe(subscriber);\n }\n\n /** @internal */\n protected _subscribe(subscriber: Subscriber): Subscription {\n this._throwIfClosed();\n this._checkFinalizedStatuses(subscriber);\n return this._innerSubscribe(subscriber);\n }\n\n /** @internal */\n protected _innerSubscribe(subscriber: Subscriber) {\n const { hasError, isStopped, observers } = this;\n if (hasError || isStopped) {\n return EMPTY_SUBSCRIPTION;\n }\n this.currentObservers = null;\n observers.push(subscriber);\n return new Subscription(() => {\n this.currentObservers = null;\n arrRemove(observers, subscriber);\n });\n }\n\n /** @internal */\n protected _checkFinalizedStatuses(subscriber: Subscriber) {\n const { hasError, thrownError, isStopped } = this;\n if (hasError) {\n subscriber.error(thrownError);\n } else if (isStopped) {\n subscriber.complete();\n }\n }\n\n /**\n * Creates a new Observable with this Subject as the source. You can do this\n * to create custom Observer-side logic of the Subject and conceal it from\n * code that uses the Observable.\n * @return {Observable} Observable that the Subject casts to\n */\n asObservable(): Observable {\n const observable: any = new Observable();\n observable.source = this;\n return observable;\n }\n}\n\n/**\n * @class AnonymousSubject\n */\nexport class AnonymousSubject extends Subject {\n constructor(\n /** @deprecated Internal implementation detail, do not use directly. Will be made internal in v8. */\n public destination?: Observer,\n source?: Observable\n ) {\n super();\n this.source = source;\n }\n\n next(value: T) {\n this.destination?.next?.(value);\n }\n\n error(err: any) {\n this.destination?.error?.(err);\n }\n\n complete() {\n this.destination?.complete?.();\n }\n\n /** @internal */\n protected _subscribe(subscriber: Subscriber): Subscription {\n return this.source?.subscribe(subscriber) ?? EMPTY_SUBSCRIPTION;\n }\n}\n", "import { TimestampProvider } from '../types';\n\ninterface DateTimestampProvider extends TimestampProvider {\n delegate: TimestampProvider | undefined;\n}\n\nexport const dateTimestampProvider: DateTimestampProvider = {\n now() {\n // Use the variable rather than `this` so that the function can be called\n // without being bound to the provider.\n return (dateTimestampProvider.delegate || Date).now();\n },\n delegate: undefined,\n};\n", "import { Subject } from './Subject';\nimport { TimestampProvider } from './types';\nimport { Subscriber } from './Subscriber';\nimport { Subscription } from './Subscription';\nimport { dateTimestampProvider } from './scheduler/dateTimestampProvider';\n\n/**\n * A variant of {@link Subject} that \"replays\" old values to new subscribers by emitting them when they first subscribe.\n *\n * `ReplaySubject` has an internal buffer that will store a specified number of values that it has observed. Like `Subject`,\n * `ReplaySubject` \"observes\" values by having them passed to its `next` method. When it observes a value, it will store that\n * value for a time determined by the configuration of the `ReplaySubject`, as passed to its constructor.\n *\n * When a new subscriber subscribes to the `ReplaySubject` instance, it will synchronously emit all values in its buffer in\n * a First-In-First-Out (FIFO) manner. The `ReplaySubject` will also complete, if it has observed completion; and it will\n * error if it has observed an error.\n *\n * There are two main configuration items to be concerned with:\n *\n * 1. `bufferSize` - This will determine how many items are stored in the buffer, defaults to infinite.\n * 2. `windowTime` - The amount of time to hold a value in the buffer before removing it from the buffer.\n *\n * Both configurations may exist simultaneously. So if you would like to buffer a maximum of 3 values, as long as the values\n * are less than 2 seconds old, you could do so with a `new ReplaySubject(3, 2000)`.\n *\n * ### Differences with BehaviorSubject\n *\n * `BehaviorSubject` is similar to `new ReplaySubject(1)`, with a couple of exceptions:\n *\n * 1. `BehaviorSubject` comes \"primed\" with a single value upon construction.\n * 2. `ReplaySubject` will replay values, even after observing an error, where `BehaviorSubject` will not.\n *\n * @see {@link Subject}\n * @see {@link BehaviorSubject}\n * @see {@link shareReplay}\n */\nexport class ReplaySubject extends Subject {\n private _buffer: (T | number)[] = [];\n private _infiniteTimeWindow = true;\n\n /**\n * @param bufferSize The size of the buffer to replay on subscription\n * @param windowTime The amount of time the buffered items will stay buffered\n * @param timestampProvider An object with a `now()` method that provides the current timestamp. This is used to\n * calculate the amount of time something has been buffered.\n */\n constructor(\n private _bufferSize = Infinity,\n private _windowTime = Infinity,\n private _timestampProvider: TimestampProvider = dateTimestampProvider\n ) {\n super();\n this._infiniteTimeWindow = _windowTime === Infinity;\n this._bufferSize = Math.max(1, _bufferSize);\n this._windowTime = Math.max(1, _windowTime);\n }\n\n next(value: T): void {\n const { isStopped, _buffer, _infiniteTimeWindow, _timestampProvider, _windowTime } = this;\n if (!isStopped) {\n _buffer.push(value);\n !_infiniteTimeWindow && _buffer.push(_timestampProvider.now() + _windowTime);\n }\n this._trimBuffer();\n super.next(value);\n }\n\n /** @internal */\n protected _subscribe(subscriber: Subscriber): Subscription {\n this._throwIfClosed();\n this._trimBuffer();\n\n const subscription = this._innerSubscribe(subscriber);\n\n const { _infiniteTimeWindow, _buffer } = this;\n // We use a copy here, so reentrant code does not mutate our array while we're\n // emitting it to a new subscriber.\n const copy = _buffer.slice();\n for (let i = 0; i < copy.length && !subscriber.closed; i += _infiniteTimeWindow ? 1 : 2) {\n subscriber.next(copy[i] as T);\n }\n\n this._checkFinalizedStatuses(subscriber);\n\n return subscription;\n }\n\n private _trimBuffer() {\n const { _bufferSize, _timestampProvider, _buffer, _infiniteTimeWindow } = this;\n // If we don't have an infinite buffer size, and we're over the length,\n // use splice to truncate the old buffer values off. Note that we have to\n // double the size for instances where we're not using an infinite time window\n // because we're storing the values and the timestamps in the same array.\n const adjustedBufferSize = (_infiniteTimeWindow ? 1 : 2) * _bufferSize;\n _bufferSize < Infinity && adjustedBufferSize < _buffer.length && _buffer.splice(0, _buffer.length - adjustedBufferSize);\n\n // Now, if we're not in an infinite time window, remove all values where the time is\n // older than what is allowed.\n if (!_infiniteTimeWindow) {\n const now = _timestampProvider.now();\n let last = 0;\n // Search the array for the first timestamp that isn't expired and\n // truncate the buffer up to that point.\n for (let i = 1; i < _buffer.length && (_buffer[i] as number) <= now; i += 2) {\n last = i;\n }\n last && _buffer.splice(0, last + 1);\n }\n }\n}\n", "import { Scheduler } from '../Scheduler';\nimport { Subscription } from '../Subscription';\nimport { SchedulerAction } from '../types';\n\n/**\n * A unit of work to be executed in a `scheduler`. An action is typically\n * created from within a {@link SchedulerLike} and an RxJS user does not need to concern\n * themselves about creating and manipulating an Action.\n *\n * ```ts\n * class Action extends Subscription {\n * new (scheduler: Scheduler, work: (state?: T) => void);\n * schedule(state?: T, delay: number = 0): Subscription;\n * }\n * ```\n *\n * @class Action\n */\nexport class Action extends Subscription {\n constructor(scheduler: Scheduler, work: (this: SchedulerAction, state?: T) => void) {\n super();\n }\n /**\n * Schedules this action on its parent {@link SchedulerLike} for execution. May be passed\n * some context object, `state`. May happen at some point in the future,\n * according to the `delay` parameter, if specified.\n * @param {T} [state] Some contextual data that the `work` function uses when\n * called by the Scheduler.\n * @param {number} [delay] Time to wait before executing the work, where the\n * time unit is implicit and defined by the Scheduler.\n * @return {void}\n */\n public schedule(state?: T, delay: number = 0): Subscription {\n return this;\n }\n}\n", "import type { TimerHandle } from './timerHandle';\ntype SetIntervalFunction = (handler: () => void, timeout?: number, ...args: any[]) => TimerHandle;\ntype ClearIntervalFunction = (handle: TimerHandle) => void;\n\ninterface IntervalProvider {\n setInterval: SetIntervalFunction;\n clearInterval: ClearIntervalFunction;\n delegate:\n | {\n setInterval: SetIntervalFunction;\n clearInterval: ClearIntervalFunction;\n }\n | undefined;\n}\n\nexport const intervalProvider: IntervalProvider = {\n // When accessing the delegate, use the variable rather than `this` so that\n // the functions can be called without being bound to the provider.\n setInterval(handler: () => void, timeout?: number, ...args) {\n const { delegate } = intervalProvider;\n if (delegate?.setInterval) {\n return delegate.setInterval(handler, timeout, ...args);\n }\n return setInterval(handler, timeout, ...args);\n },\n clearInterval(handle) {\n const { delegate } = intervalProvider;\n return (delegate?.clearInterval || clearInterval)(handle as any);\n },\n delegate: undefined,\n};\n", "import { Action } from './Action';\nimport { SchedulerAction } from '../types';\nimport { Subscription } from '../Subscription';\nimport { AsyncScheduler } from './AsyncScheduler';\nimport { intervalProvider } from './intervalProvider';\nimport { arrRemove } from '../util/arrRemove';\nimport { TimerHandle } from './timerHandle';\n\nexport class AsyncAction extends Action {\n public id: TimerHandle | undefined;\n public state?: T;\n // @ts-ignore: Property has no initializer and is not definitely assigned\n public delay: number;\n protected pending: boolean = false;\n\n constructor(protected scheduler: AsyncScheduler, protected work: (this: SchedulerAction, state?: T) => void) {\n super(scheduler, work);\n }\n\n public schedule(state?: T, delay: number = 0): Subscription {\n if (this.closed) {\n return this;\n }\n\n // Always replace the current state with the new state.\n this.state = state;\n\n const id = this.id;\n const scheduler = this.scheduler;\n\n //\n // Important implementation note:\n //\n // Actions only execute once by default, unless rescheduled from within the\n // scheduled callback. This allows us to implement single and repeat\n // actions via the same code path, without adding API surface area, as well\n // as mimic traditional recursion but across asynchronous boundaries.\n //\n // However, JS runtimes and timers distinguish between intervals achieved by\n // serial `setTimeout` calls vs. a single `setInterval` call. An interval of\n // serial `setTimeout` calls can be individually delayed, which delays\n // scheduling the next `setTimeout`, and so on. `setInterval` attempts to\n // guarantee the interval callback will be invoked more precisely to the\n // interval period, regardless of load.\n //\n // Therefore, we use `setInterval` to schedule single and repeat actions.\n // If the action reschedules itself with the same delay, the interval is not\n // canceled. If the action doesn't reschedule, or reschedules with a\n // different delay, the interval will be canceled after scheduled callback\n // execution.\n //\n if (id != null) {\n this.id = this.recycleAsyncId(scheduler, id, delay);\n }\n\n // Set the pending flag indicating that this action has been scheduled, or\n // has recursively rescheduled itself.\n this.pending = true;\n\n this.delay = delay;\n // If this action has already an async Id, don't request a new one.\n this.id = this.id ?? this.requestAsyncId(scheduler, this.id, delay);\n\n return this;\n }\n\n protected requestAsyncId(scheduler: AsyncScheduler, _id?: TimerHandle, delay: number = 0): TimerHandle {\n return intervalProvider.setInterval(scheduler.flush.bind(scheduler, this), delay);\n }\n\n protected recycleAsyncId(_scheduler: AsyncScheduler, id?: TimerHandle, delay: number | null = 0): TimerHandle | undefined {\n // If this action is rescheduled with the same delay time, don't clear the interval id.\n if (delay != null && this.delay === delay && this.pending === false) {\n return id;\n }\n // Otherwise, if the action's delay time is different from the current delay,\n // or the action has been rescheduled before it's executed, clear the interval id\n if (id != null) {\n intervalProvider.clearInterval(id);\n }\n\n return undefined;\n }\n\n /**\n * Immediately executes this action and the `work` it contains.\n * @return {any}\n */\n public execute(state: T, delay: number): any {\n if (this.closed) {\n return new Error('executing a cancelled action');\n }\n\n this.pending = false;\n const error = this._execute(state, delay);\n if (error) {\n return error;\n } else if (this.pending === false && this.id != null) {\n // Dequeue if the action didn't reschedule itself. Don't call\n // unsubscribe(), because the action could reschedule later.\n // For example:\n // ```\n // scheduler.schedule(function doWork(counter) {\n // /* ... I'm a busy worker bee ... */\n // var originalAction = this;\n // /* wait 100ms before rescheduling the action */\n // setTimeout(function () {\n // originalAction.schedule(counter + 1);\n // }, 100);\n // }, 1000);\n // ```\n this.id = this.recycleAsyncId(this.scheduler, this.id, null);\n }\n }\n\n protected _execute(state: T, _delay: number): any {\n let errored: boolean = false;\n let errorValue: any;\n try {\n this.work(state);\n } catch (e) {\n errored = true;\n // HACK: Since code elsewhere is relying on the \"truthiness\" of the\n // return here, we can't have it return \"\" or 0 or false.\n // TODO: Clean this up when we refactor schedulers mid-version-8 or so.\n errorValue = e ? e : new Error('Scheduled action threw falsy error');\n }\n if (errored) {\n this.unsubscribe();\n return errorValue;\n }\n }\n\n unsubscribe() {\n if (!this.closed) {\n const { id, scheduler } = this;\n const { actions } = scheduler;\n\n this.work = this.state = this.scheduler = null!;\n this.pending = false;\n\n arrRemove(actions, this);\n if (id != null) {\n this.id = this.recycleAsyncId(scheduler, id, null);\n }\n\n this.delay = null!;\n super.unsubscribe();\n }\n }\n}\n", "import { Action } from './scheduler/Action';\nimport { Subscription } from './Subscription';\nimport { SchedulerLike, SchedulerAction } from './types';\nimport { dateTimestampProvider } from './scheduler/dateTimestampProvider';\n\n/**\n * An execution context and a data structure to order tasks and schedule their\n * execution. Provides a notion of (potentially virtual) time, through the\n * `now()` getter method.\n *\n * Each unit of work in a Scheduler is called an `Action`.\n *\n * ```ts\n * class Scheduler {\n * now(): number;\n * schedule(work, delay?, state?): Subscription;\n * }\n * ```\n *\n * @class Scheduler\n * @deprecated Scheduler is an internal implementation detail of RxJS, and\n * should not be used directly. Rather, create your own class and implement\n * {@link SchedulerLike}. Will be made internal in v8.\n */\nexport class Scheduler implements SchedulerLike {\n public static now: () => number = dateTimestampProvider.now;\n\n constructor(private schedulerActionCtor: typeof Action, now: () => number = Scheduler.now) {\n this.now = now;\n }\n\n /**\n * A getter method that returns a number representing the current time\n * (at the time this function was called) according to the scheduler's own\n * internal clock.\n * @return {number} A number that represents the current time. May or may not\n * have a relation to wall-clock time. May or may not refer to a time unit\n * (e.g. milliseconds).\n */\n public now: () => number;\n\n /**\n * Schedules a function, `work`, for execution. May happen at some point in\n * the future, according to the `delay` parameter, if specified. May be passed\n * some context object, `state`, which will be passed to the `work` function.\n *\n * The given arguments will be processed an stored as an Action object in a\n * queue of actions.\n *\n * @param {function(state: ?T): ?Subscription} work A function representing a\n * task, or some unit of work to be executed by the Scheduler.\n * @param {number} [delay] Time to wait before executing the work, where the\n * time unit is implicit and defined by the Scheduler itself.\n * @param {T} [state] Some contextual data that the `work` function uses when\n * called by the Scheduler.\n * @return {Subscription} A subscription in order to be able to unsubscribe\n * the scheduled work.\n */\n public schedule(work: (this: SchedulerAction, state?: T) => void, delay: number = 0, state?: T): Subscription {\n return new this.schedulerActionCtor(this, work).schedule(state, delay);\n }\n}\n", "import { Scheduler } from '../Scheduler';\nimport { Action } from './Action';\nimport { AsyncAction } from './AsyncAction';\nimport { TimerHandle } from './timerHandle';\n\nexport class AsyncScheduler extends Scheduler {\n public actions: Array> = [];\n /**\n * A flag to indicate whether the Scheduler is currently executing a batch of\n * queued actions.\n * @type {boolean}\n * @internal\n */\n public _active: boolean = false;\n /**\n * An internal ID used to track the latest asynchronous task such as those\n * coming from `setTimeout`, `setInterval`, `requestAnimationFrame`, and\n * others.\n * @type {any}\n * @internal\n */\n public _scheduled: TimerHandle | undefined;\n\n constructor(SchedulerAction: typeof Action, now: () => number = Scheduler.now) {\n super(SchedulerAction, now);\n }\n\n public flush(action: AsyncAction): void {\n const { actions } = this;\n\n if (this._active) {\n actions.push(action);\n return;\n }\n\n let error: any;\n this._active = true;\n\n do {\n if ((error = action.execute(action.state, action.delay))) {\n break;\n }\n } while ((action = actions.shift()!)); // exhaust the scheduler queue\n\n this._active = false;\n\n if (error) {\n while ((action = actions.shift()!)) {\n action.unsubscribe();\n }\n throw error;\n }\n }\n}\n", "import { AsyncAction } from './AsyncAction';\nimport { AsyncScheduler } from './AsyncScheduler';\n\n/**\n *\n * Async Scheduler\n *\n * Schedule task as if you used setTimeout(task, duration)\n *\n * `async` scheduler schedules tasks asynchronously, by putting them on the JavaScript\n * event loop queue. It is best used to delay tasks in time or to schedule tasks repeating\n * in intervals.\n *\n * If you just want to \"defer\" task, that is to perform it right after currently\n * executing synchronous code ends (commonly achieved by `setTimeout(deferredTask, 0)`),\n * better choice will be the {@link asapScheduler} scheduler.\n *\n * ## Examples\n * Use async scheduler to delay task\n * ```ts\n * import { asyncScheduler } from 'rxjs';\n *\n * const task = () => console.log('it works!');\n *\n * asyncScheduler.schedule(task, 2000);\n *\n * // After 2 seconds logs:\n * // \"it works!\"\n * ```\n *\n * Use async scheduler to repeat task in intervals\n * ```ts\n * import { asyncScheduler } from 'rxjs';\n *\n * function task(state) {\n * console.log(state);\n * this.schedule(state + 1, 1000); // `this` references currently executing Action,\n * // which we reschedule with new state and delay\n * }\n *\n * asyncScheduler.schedule(task, 3000, 0);\n *\n * // Logs:\n * // 0 after 3s\n * // 1 after 4s\n * // 2 after 5s\n * // 3 after 6s\n * ```\n */\n\nexport const asyncScheduler = new AsyncScheduler(AsyncAction);\n\n/**\n * @deprecated Renamed to {@link asyncScheduler}. Will be removed in v8.\n */\nexport const async = asyncScheduler;\n", "import { AsyncAction } from './AsyncAction';\nimport { AnimationFrameScheduler } from './AnimationFrameScheduler';\nimport { SchedulerAction } from '../types';\nimport { animationFrameProvider } from './animationFrameProvider';\nimport { TimerHandle } from './timerHandle';\n\nexport class AnimationFrameAction extends AsyncAction {\n constructor(protected scheduler: AnimationFrameScheduler, protected work: (this: SchedulerAction, state?: T) => void) {\n super(scheduler, work);\n }\n\n protected requestAsyncId(scheduler: AnimationFrameScheduler, id?: TimerHandle, delay: number = 0): TimerHandle {\n // If delay is greater than 0, request as an async action.\n if (delay !== null && delay > 0) {\n return super.requestAsyncId(scheduler, id, delay);\n }\n // Push the action to the end of the scheduler queue.\n scheduler.actions.push(this);\n // If an animation frame has already been requested, don't request another\n // one. If an animation frame hasn't been requested yet, request one. Return\n // the current animation frame request id.\n return scheduler._scheduled || (scheduler._scheduled = animationFrameProvider.requestAnimationFrame(() => scheduler.flush(undefined)));\n }\n\n protected recycleAsyncId(scheduler: AnimationFrameScheduler, id?: TimerHandle, delay: number = 0): TimerHandle | undefined {\n // If delay exists and is greater than 0, or if the delay is null (the\n // action wasn't rescheduled) but was originally scheduled as an async\n // action, then recycle as an async action.\n if (delay != null ? delay > 0 : this.delay > 0) {\n return super.recycleAsyncId(scheduler, id, delay);\n }\n // If the scheduler queue has no remaining actions with the same async id,\n // cancel the requested animation frame and set the scheduled flag to\n // undefined so the next AnimationFrameAction will request its own.\n const { actions } = scheduler;\n if (id != null && actions[actions.length - 1]?.id !== id) {\n animationFrameProvider.cancelAnimationFrame(id as number);\n scheduler._scheduled = undefined;\n }\n // Return undefined so the action knows to request a new async id if it's rescheduled.\n return undefined;\n }\n}\n", "import { AsyncAction } from './AsyncAction';\nimport { AsyncScheduler } from './AsyncScheduler';\n\nexport class AnimationFrameScheduler extends AsyncScheduler {\n public flush(action?: AsyncAction): void {\n this._active = true;\n // The async id that effects a call to flush is stored in _scheduled.\n // Before executing an action, it's necessary to check the action's async\n // id to determine whether it's supposed to be executed in the current\n // flush.\n // Previous implementations of this method used a count to determine this,\n // but that was unsound, as actions that are unsubscribed - i.e. cancelled -\n // are removed from the actions array and that can shift actions that are\n // scheduled to be executed in a subsequent flush into positions at which\n // they are executed within the current flush.\n const flushId = this._scheduled;\n this._scheduled = undefined;\n\n const { actions } = this;\n let error: any;\n action = action || actions.shift()!;\n\n do {\n if ((error = action.execute(action.state, action.delay))) {\n break;\n }\n } while ((action = actions[0]) && action.id === flushId && actions.shift());\n\n this._active = false;\n\n if (error) {\n while ((action = actions[0]) && action.id === flushId && actions.shift()) {\n action.unsubscribe();\n }\n throw error;\n }\n }\n}\n", "import { AnimationFrameAction } from './AnimationFrameAction';\nimport { AnimationFrameScheduler } from './AnimationFrameScheduler';\n\n/**\n *\n * Animation Frame Scheduler\n *\n * Perform task when `window.requestAnimationFrame` would fire\n *\n * When `animationFrame` scheduler is used with delay, it will fall back to {@link asyncScheduler} scheduler\n * behaviour.\n *\n * Without delay, `animationFrame` scheduler can be used to create smooth browser animations.\n * It makes sure scheduled task will happen just before next browser content repaint,\n * thus performing animations as efficiently as possible.\n *\n * ## Example\n * Schedule div height animation\n * ```ts\n * // html:
\n * import { animationFrameScheduler } from 'rxjs';\n *\n * const div = document.querySelector('div');\n *\n * animationFrameScheduler.schedule(function(height) {\n * div.style.height = height + \"px\";\n *\n * this.schedule(height + 1); // `this` references currently executing Action,\n * // which we reschedule with new state\n * }, 0, 0);\n *\n * // You will see a div element growing in height\n * ```\n */\n\nexport const animationFrameScheduler = new AnimationFrameScheduler(AnimationFrameAction);\n\n/**\n * @deprecated Renamed to {@link animationFrameScheduler}. Will be removed in v8.\n */\nexport const animationFrame = animationFrameScheduler;\n", "import { Observable } from '../Observable';\nimport { SchedulerLike } from '../types';\n\n/**\n * A simple Observable that emits no items to the Observer and immediately\n * emits a complete notification.\n *\n * Just emits 'complete', and nothing else.\n *\n * ![](empty.png)\n *\n * A simple Observable that only emits the complete notification. It can be used\n * for composing with other Observables, such as in a {@link mergeMap}.\n *\n * ## Examples\n *\n * Log complete notification\n *\n * ```ts\n * import { EMPTY } from 'rxjs';\n *\n * EMPTY.subscribe({\n * next: () => console.log('Next'),\n * complete: () => console.log('Complete!')\n * });\n *\n * // Outputs\n * // Complete!\n * ```\n *\n * Emit the number 7, then complete\n *\n * ```ts\n * import { EMPTY, startWith } from 'rxjs';\n *\n * const result = EMPTY.pipe(startWith(7));\n * result.subscribe(x => console.log(x));\n *\n * // Outputs\n * // 7\n * ```\n *\n * Map and flatten only odd numbers to the sequence `'a'`, `'b'`, `'c'`\n *\n * ```ts\n * import { interval, mergeMap, of, EMPTY } from 'rxjs';\n *\n * const interval$ = interval(1000);\n * const result = interval$.pipe(\n * mergeMap(x => x % 2 === 1 ? of('a', 'b', 'c') : EMPTY),\n * );\n * result.subscribe(x => console.log(x));\n *\n * // Results in the following to the console:\n * // x is equal to the count on the interval, e.g. (0, 1, 2, 3, ...)\n * // x will occur every 1000ms\n * // if x % 2 is equal to 1, print a, b, c (each on its own)\n * // if x % 2 is not equal to 1, nothing will be output\n * ```\n *\n * @see {@link Observable}\n * @see {@link NEVER}\n * @see {@link of}\n * @see {@link throwError}\n */\nexport const EMPTY = new Observable((subscriber) => subscriber.complete());\n\n/**\n * @param scheduler A {@link SchedulerLike} to use for scheduling\n * the emission of the complete notification.\n * @deprecated Replaced with the {@link EMPTY} constant or {@link scheduled} (e.g. `scheduled([], scheduler)`). Will be removed in v8.\n */\nexport function empty(scheduler?: SchedulerLike) {\n return scheduler ? emptyScheduled(scheduler) : EMPTY;\n}\n\nfunction emptyScheduled(scheduler: SchedulerLike) {\n return new Observable((subscriber) => scheduler.schedule(() => subscriber.complete()));\n}\n", "import { SchedulerLike } from '../types';\nimport { isFunction } from './isFunction';\n\nexport function isScheduler(value: any): value is SchedulerLike {\n return value && isFunction(value.schedule);\n}\n", "import { SchedulerLike } from '../types';\nimport { isFunction } from './isFunction';\nimport { isScheduler } from './isScheduler';\n\nfunction last(arr: T[]): T | undefined {\n return arr[arr.length - 1];\n}\n\nexport function popResultSelector(args: any[]): ((...args: unknown[]) => unknown) | undefined {\n return isFunction(last(args)) ? args.pop() : undefined;\n}\n\nexport function popScheduler(args: any[]): SchedulerLike | undefined {\n return isScheduler(last(args)) ? args.pop() : undefined;\n}\n\nexport function popNumber(args: any[], defaultValue: number): number {\n return typeof last(args) === 'number' ? args.pop()! : defaultValue;\n}\n", "export const isArrayLike = ((x: any): x is ArrayLike => x && typeof x.length === 'number' && typeof x !== 'function');", "import { isFunction } from \"./isFunction\";\n\n/**\n * Tests to see if the object is \"thennable\".\n * @param value the object to test\n */\nexport function isPromise(value: any): value is PromiseLike {\n return isFunction(value?.then);\n}\n", "import { InteropObservable } from '../types';\nimport { observable as Symbol_observable } from '../symbol/observable';\nimport { isFunction } from './isFunction';\n\n/** Identifies an input as being Observable (but not necessary an Rx Observable) */\nexport function isInteropObservable(input: any): input is InteropObservable {\n return isFunction(input[Symbol_observable]);\n}\n", "import { isFunction } from './isFunction';\n\nexport function isAsyncIterable(obj: any): obj is AsyncIterable {\n return Symbol.asyncIterator && isFunction(obj?.[Symbol.asyncIterator]);\n}\n", "/**\n * Creates the TypeError to throw if an invalid object is passed to `from` or `scheduled`.\n * @param input The object that was passed.\n */\nexport function createInvalidObservableTypeError(input: any) {\n // TODO: We should create error codes that can be looked up, so this can be less verbose.\n return new TypeError(\n `You provided ${\n input !== null && typeof input === 'object' ? 'an invalid object' : `'${input}'`\n } where a stream was expected. You can provide an Observable, Promise, ReadableStream, Array, AsyncIterable, or Iterable.`\n );\n}\n", "export function getSymbolIterator(): symbol {\n if (typeof Symbol !== 'function' || !Symbol.iterator) {\n return '@@iterator' as any;\n }\n\n return Symbol.iterator;\n}\n\nexport const iterator = getSymbolIterator();\n", "import { iterator as Symbol_iterator } from '../symbol/iterator';\nimport { isFunction } from './isFunction';\n\n/** Identifies an input as being an Iterable */\nexport function isIterable(input: any): input is Iterable {\n return isFunction(input?.[Symbol_iterator]);\n}\n", "import { ReadableStreamLike } from '../types';\nimport { isFunction } from './isFunction';\n\nexport async function* readableStreamLikeToAsyncGenerator(readableStream: ReadableStreamLike): AsyncGenerator {\n const reader = readableStream.getReader();\n try {\n while (true) {\n const { value, done } = await reader.read();\n if (done) {\n return;\n }\n yield value!;\n }\n } finally {\n reader.releaseLock();\n }\n}\n\nexport function isReadableStreamLike(obj: any): obj is ReadableStreamLike {\n // We don't want to use instanceof checks because they would return\n // false for instances from another Realm, like an