Merge pull request #126 from yarikoptic/enh-codespell

Add codespell workflow, config and fix some typos

.codespellrc

@@ -0,0 +1,4 @@
+[codespell]
+skip = .git,*.pdf,*.svg,venvs
+#
+# ignore-words-list =

.github/workflows/codespell.yml

@@ -0,0 +1,22 @@
+---
+name: Codespell
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2

.pre-commit-config.yaml

@@ -4,3 +4,8 @@ repos:
     hooks:
     - id: black
       language_version: python3.7
+
+- repo: https://github.com/codespell-project/codespell
+  rev: v2.2.5
+  hooks:
+  - id: codespell

bep028spec.md

@@ -360,7 +360,7 @@ Each Entity (as a record or a top-level entity) has the following fields:
   <tr>
    <td><code>wasGeneratedBy</code>
    </td>
-   <td>OPTIONAL. UUID. Identifier of the activity which generated this entity (the corresponding Activity must be defined with its own Activty record).
+   <td>OPTIONAL. UUID. Identifier of the activity which generated this entity (the corresponding Activity must be defined with its own Activity record).
    </td>
   </tr>
   <tr>
@@ -555,7 +555,7 @@ An example of this can be [fMRIPrep](https://fmriprep.org/en/stable/index.html),
 
 The most simplistic way you can think of is to have this container "black-boxed" in your workflow. You basically record the calling of this container (`command` section) and the output (see the outputs section from fMRIPrep)
 
-"prov:Activty": [
+"prov:Activity": [
 
   	{
 

bids_prov/afni/afni_parser.py

@@ -76,10 +76,10 @@ def find_param(cmd_args_remain: list) -> dict:
     for arg_remain in cmd_args_remain:
         if arg_remain.startswith("-"):
             if arg_remain != cmd_args_remain[-1]:
-                succesor = cmd_args_remain[cmd_args_remain.index(arg_remain) + 1]
-                if not succesor.startswith("-"):
-                    param_dic[arg_remain] = succesor
-                    cmd_args_remain.remove(succesor)
+                successor = cmd_args_remain[cmd_args_remain.index(arg_remain) + 1]
+                if not successor.startswith("-"):
+                    param_dic[arg_remain] = successor
+                    cmd_args_remain.remove(successor)
                 else:
                     param_dic[arg_remain] = True
             else:
@@ -88,15 +88,15 @@ def find_param(cmd_args_remain: list) -> dict:
     return param_dic
 
 
-def build_records(commands_bloc: list, agent_id: str, verbose: bool = False):
+def build_records(commands_block: list, agent_id: str, verbose: bool = False):
     """
     Build the `records` field for the final .jsonld file,
     from commands lines grouped by stage (e.g. `Registration`, `Post-stats`)
 
     Parameters
     ----------
 
-    commands_bloc : list of str
+    commands_block : list of str
         all commands extracted from afni file
     agent_id : int
         random uuid for software agent (here afni)
@@ -115,7 +115,7 @@ def build_records(commands_bloc: list, agent_id: str, verbose: bool = False):
 
     bloc_act = []
 
-    for (bloc, cmd) in commands_bloc:
+    for (block, cmd) in commands_block:
         cmd_s = re.split(" |=", cmd)
         a_name = cmd_s[0]
         cmd_args_remain = cmd_s[1:]
@@ -232,7 +232,7 @@ def build_records(commands_bloc: list, agent_id: str, verbose: bool = False):
                     # "derivedFrom": input_id,
                 }
             )
-        bloc_act.append((bloc, activity["@id"]))
+        bloc_act.append((block, activity["@id"]))
 
         records["Activities"].append(activity)
         if verbose:
@@ -294,23 +294,23 @@ def readlines(input_file: str) -> list:
 
     # commands = [cmd for cmd in commands if not any(
     #     cmd.startswith(begin) for begin in dropline_begin)]
-    regex_bloc = re.compile(r'# =+ ([^=]+) =+')
-    commands_bloc = []
-    bloc = ""
+    regex_block = re.compile(r'# =+ ([^=]+) =+')
+    commands_block = []
+    block = ""
     for cmd in commands:
         if cmd.startswith("# ==="):
-            bloc = regex_bloc.match(cmd).groups()[0] if regex_bloc.match(cmd) is not None else "bloc ..."
+            block = regex_block.match(cmd).groups()[0] if regex_block.match(cmd) is not None else "block ..."
 
         if not any(cmd.startswith(begin) for begin in dropline_begin):
-            commands_bloc.append((bloc, cmd))
+            commands_block.append((block, cmd))
 
-    commands_bloc = [(bloc, re.sub(r"\s+", " ", cmd))
-                     for (bloc, cmd) in commands_bloc]  # drop multiple space between args
+    commands_block = [(block, re.sub(r"\s+", " ", cmd))
+                     for (block, cmd) in commands_block]  # drop multiple space between args
 
-    commands_bloc = [(bloc, cmd)
-                     for (bloc, cmd) in commands_bloc if cmd]  # drop empty commands
+    commands_block = [(block, cmd)
+                     for (block, cmd) in commands_block if cmd]  # drop empty commands
 
-    return commands_bloc
+    return commands_block
 
 
 def get_activities_by_ids(graph, ids):
@@ -425,7 +425,7 @@ def get_extern_entities_from_activities(graph, activities, id_fusion_activity):
 
 
 def afni_to_bids_prov(filename: str, context_url=CONTEXT_URL, output_file=None,
-                      soft_ver='afni24', indent=2, verbose=True, with_blocs=True) -> bool:
+                      soft_ver='afni24', indent=2, verbose=True, with_blocks=True) -> bool:
     """
     afni parser
 
@@ -438,55 +438,55 @@ def afni_to_bids_prov(filename: str, context_url=CONTEXT_URL, output_file=None,
     output_file : str
         name of output parsed file with extension json.ld
     soft_ver:str
-        version of sofware afni
+        version of software afni
     indent : int
         number of indentation in jsonld
     verbose : bool
         True to have more verbosity
-    with_blocs : bool
+    with_blocks : bool
         To retrieve or not the results of the parser in block mode and not only for each command
 
     Returns
     -------
     bool
         Write the json-ld to the location indicated in output_file.
-        If `with_blocs` is True, it generates the file to the location indicated in output_file.
+        If `with_blocks` is True, it generates the file to the location indicated in output_file.
     """
-    commands_bloc = readlines(filename)
+    commands_block = readlines(filename)
 
     graph, agent_id = get_default_graph(label="AFNI", context_url=context_url, soft_ver=soft_ver)
-    records, bloc_act = build_records(commands_bloc, agent_id, verbose=verbose)
+    records, bloc_act = build_records(commands_block, agent_id, verbose=verbose)
 
     graph["Records"].update(records)
     compute_sha_256_entity(graph["Records"]["Entities"])
 
-    if with_blocs:
+    if with_blocks:
         bl_name = list(OrderedDict.fromkeys(bl for (bl, id) in bloc_act))
-        blocs = [{
+        blocks = [{
             "bloc_name": bl,
             "act_ids": [id_ for (b, id_) in bloc_act if b == bl]} for bl in bl_name]
 
-        graph_bloc = copy.deepcopy(graph)
-        activities_blocs = []
-        entities_blocs = []
-        for bloc in blocs:
-            activities = get_activities_by_ids(graph_bloc, bloc["act_ids"])
-            fus_activities = fusion_activities(activities, bloc["bloc_name"])
+        graph_block = copy.deepcopy(graph)
+        activities_blocks = []
+        entities_blocks = []
+        for block in blocks:
+            activities = get_activities_by_ids(graph_block, block["act_ids"])
+            fus_activities = fusion_activities(activities, block["bloc_name"])
             ext_entities = get_extern_entities_from_activities(
-                graph_bloc, activities, fus_activities["@id"])
+                graph_block, activities, fus_activities["@id"])
             for ent in ext_entities:
-                if ent["@id"] not in entities_blocs:
-                    entities_blocs.append(ent)
+                if ent["@id"] not in entities_blocks:
+                    entities_blocks.append(ent)
 
             for ent_used in fus_activities["Used"]:
                 if ent_used not in [id_["@id"] for id_ in ext_entities]:
                     fus_activities["Used"].remove(ent_used)
-            activities_blocs.append(fus_activities)
+            activities_blocks.append(fus_activities)
 
-        graph_bloc["Records"]["Activities"] = activities_blocs
-        graph_bloc["Records"]["Entities"] = entities_blocs
+        graph_block["Records"]["Activities"] = activities_blocks
+        graph_block["Records"]["Entities"] = entities_blocks
 
-        return writing_jsonld(graph_bloc, indent, output_file)
+        return writing_jsonld(graph_block, indent, output_file)
 
     return writing_jsonld(graph, indent, output_file)
 

bids_prov/fsl/fsl_parser.py

@@ -37,7 +37,7 @@
     ]
 )
 
-# tags used to detect outputs from cammand lines
+# tags used to detect outputs from command lines
 # eg. convert_xfm -inverse -omat highres2example_func.mat example_func2highres.mat
 OUTPUT_TAGS = frozenset(
     [
@@ -141,14 +141,14 @@ def readlines(filename: str) -> Mapping[str, List[str]]:
 #     return None
 
 
-def _get_kwarg(serie,  with_value=True):
+def _get_kwarg(series,  with_value=True):
     """
-    Get the named arguments (kwarg) from a column ("Used", "GeneratedBy", "ParametersValue" or "ParametersNoValue" ) of the dataframe coming frome in description_functions.json
+    Get the named arguments (kwarg) from a column ("Used", "GeneratedBy", "ParametersValue" or "ParametersNoValue" ) of the dataframe coming from in description_functions.json
 
     Parameters
     ----------
 
-    serie : pandas series
+    series : pandas series
         A list of the command arguments description.
     with_value : boolean
         A bool to specify if values are expected or not, in order to dicrimine "ParametersValue" (with_value=True), and "ParametersNoValue" (with_value=False)
@@ -162,7 +162,7 @@ def _get_kwarg(serie,  with_value=True):
     arg_list = []
 
     add_argument_list = []
-    for u_arg in serie:
+    for u_arg in series:
         if type(u_arg) == dict:
             # parser.add_argument(u_arg["name"], nargs='+', action='append')
             if "Nargs" in u_arg:
@@ -199,14 +199,14 @@ def _get_kwarg(serie,  with_value=True):
     return add_argument_list, arg_list
 
 
-def _get_arg(serie, arg_rest):
+def _get_arg(series, arg_rest):
     """
-    Get the ordinal arguments from a column ("Used", "GeneratedBy") of the dataframe coming from in description_functions.json. _get_arg shoud be used when all named arguments are removed from the initial command.   
+    Get the ordinal arguments from a column ("Used", "GeneratedBy") of the dataframe coming from in description_functions.json. _get_arg should be used when all named arguments are removed from the initial command.   
 
     Parameters
     ----------
 
-    serie : pandas series
+    series : pandas series
         A list of the command arguments description.
     arg_rest : string of the command, (without all the named argument used in description_functions.json)
 
@@ -217,7 +217,7 @@ def _get_arg(serie, arg_rest):
 
     arg_list = []
     arg_purge = [arg for arg in arg_rest if not arg.startswith("-")]
-    for u_arg in serie:
+    for u_arg in series:
         if type(u_arg) == int:
             # print("arg_purge", type(arg_purge), arg_purge, u_arg)
             if u_arg < len(arg_purge):

bids_prov/tests/test_afni_parser.py

@@ -63,7 +63,7 @@ def test_readlines():
                              "3dTcat -prefix $output_dir/pb00.$subj.r01.tcat ./afni_voxelwise_p0001/sub-01_task-tonecounting_bold.nii.gz'[0..$]'",
                              "3dToutcount -automask -fraction -polort 2 -legendre pb00.$subj.r$run.tcat+orig > outcount.r$run.1D"
                              ]
-        commands = [cmd.strip() for (bloc, cmd) in commands]
+        commands = [cmd.strip() for (block, cmd) in commands]
         # Replace multi (>=2 ) blank space to one
         commands = [re.sub(r"\s{2,}", " ", cmd) for cmd in commands]
         expected_commands = [cmd.strip() for cmd in expected_commands]

code_of_conduct.md

@@ -5,7 +5,7 @@
 We as members, contributors, and leaders pledge to make participation in our
 community a harassment-free experience for everyone, regardless of age, body
 size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
+identity and expression, level of experience, education, socioeconomic status,
 nationality, personal appearance, race, religion, or sexual identity
 and orientation.