Merge pull request #52 from jiaaro/master

delete python 2 compatibility stuff and add cython

.travis.yml

@@ -8,7 +8,7 @@ python:
   - "3.6"
 install:
   - pip install django==${DJANGO}
-  - "pip install psycopg2 git+https://github.com/mediapredict/[email protected] future==0.16.0"
+  - "pip install psycopg2 git+https://github.com/mediapredict/[email protected] cython"
   - "pip install ."
 addons:
   postgresql: "9.3"

README.md

@@ -201,9 +201,16 @@ Arrays:
 
 ### Functions
 
-- `timestamp(YYYY-MM-DD)` this is a helper function which generates the unix timestamp corresponding to the date entered. When the daffodil is evaluated the timestamp is functionally a number, but this lets you write the daffodil in a way that is easier to read and understand. 
-
-Example: people who began `mystudy` after halloween 2017: `mystudy__started >= timestamp(2017-10-31)`
+- `timestamp(YYYY-MM-DD)` or `timestamp(YYYY-MM-DD HH:MM)` this is a helper function which generates the unix timestamp corresponding to the date (and optionally, time) entered. When the daffodil is evaluated the datetime is functionally a number, but this lets you write the daffodil in a way that is easier to read and understand. If hours and minutes are entered they are interpreted as 24 hour time UTC.
+
+Examples:
+- people who began `mystudy` after halloween 2017:
+  `mystudy__started >= timestamp(2017-10-31)`
+- people who participated in `balloonstudy` while the Macy's thanksgiving day parade was on tv (Nov 23, 9AM to 12PM Eastern time):
+  ```
+  balloonstudy__started >= timestamp(2017-11-23 2:00)
+  balloonstudy__started < timestamp(2017-11-23 17:00)
+  ```
 
 ### Comparison operators
 

daffodil/__init__.py → daffodil/__init__.pyx

@@ -1,6 +1,6 @@
+from .parser import Daffodil
 from .predicate import DictionaryPredicateDelegate
 from .hstore_predicate import HStoreQueryDelegate
 from .pretty_print import PrettyPrintDelegate
 from .key_expectation_delegate import KeyExpectationDelegate
 from .simulation_delegate import SimulationMatchingDelegate
-from .parser import Daffodil

daffodil/base_delegate.py

@@ -1,29 +1 @@
-from builtins import object
-
-
-class BaseDaffodilDelegate(object):
-
-    def mk_any(self, children):
-        raise NotImplementedError()
-
-    def mk_all(self, children):
-        raise NotImplementedError()
-
-    def mk_not_any(self, children):
-        raise NotImplementedError()
-
-    def mk_not_all(self, children):
-        raise NotImplementedError()
-
-    def mk_test(self, test_str):
-        raise NotImplementedError()
-
-    def mk_comment(self, comment, is_inline):
-        raise NotImplementedError()
-
-    def mk_cmp(self, key, val, test):
-        raise NotImplementedError()
-
-    def call(self, predicate, iterable):
-        raise NotImplementedError()
-
+from .parser import BaseDaffodilDelegate

daffodil/django_integration.py

@@ -1,4 +1,3 @@
-from builtins import str
 from django.core.exceptions import ValidationError
 from daffodil import Daffodil
 from daffodil.exceptions import ParseError
@@ -8,4 +7,4 @@ def validate_daffodil_fltr(value):
     try:
         Daffodil(value)
     except ParseError as e:
-        raise ValidationError("Invalid Daffodil filter. %s" % str(e))
+        raise ValidationError("Invalid Daffodil filter. %s" % str(e))

daffodil/hstore_predicate.py → daffodil/hstore_predicate.pyx

@@ -1,10 +1,5 @@
-from future import standard_library
-standard_library.install_aliases()
-from builtins import str
-from past.builtins import basestring
 from collections import UserString
-
-from .base_delegate import BaseDaffodilDelegate
+from .parser cimport Token, BaseDaffodilDelegate
 
 
 RE_CASE = "CASE WHEN ({0}->'{1}' ~ E'"
@@ -29,7 +24,7 @@ def breaks_optimizer(expr):
     return (
         expr.daff_test in {"!=", "!in"} or
         (expr.daff_test == "?=" and expr.daff_val == False) or
-        (expr.daff_test == "=" and isinstance(expr.daff_val, basestring))
+        (expr.daff_test == "=" and isinstance(expr.daff_val, str))
     )
 
 def escape_string_sql(s):
@@ -40,9 +35,10 @@ def make_sql_array(*strings):
         ",".join(escape_string_sql(s) for s in strings)
     )
 
-class HStoreQueryDelegate(BaseDaffodilDelegate):
+cdef class HStoreQueryDelegate(BaseDaffodilDelegate):
+    cdef public str field
 
-    def __init__(self, hstore_field_name):
+    def __cinit__(self, hstore_field_name):
         self.field = hstore_field_name
 
     def mk_any(self, children):
@@ -125,7 +121,7 @@ def mk_test(self, daff_test_str):
             if test_str == "!=":
                 test_fn.is_NE_test = True
             elif test_str == "=":
-                test_fn = lambda k, v, t: "({0} {1}))".format(k, v) if t == basestring else "{0} {1} {2}".format(k, test_str, v)
+                test_fn = lambda k, v, t: "({0} {1}))".format(k, v) if t == str else "{0} {1} {2}".format(k, test_str, v)
                 test_fn.is_EQ_test = True
             elif test_str == "!in":
                 test_fn.is_NOT_IN_test = True
@@ -136,7 +132,14 @@ def mk_test(self, daff_test_str):
         test_fn.test_str = daff_test_str
         return test_fn
 
-    def mk_cmp(self, key, val, test):
+    cdef mk_cmp(self, Token key, Token test, Token val):
+        return self._mk_cmp(
+            key.content,
+            val,
+            self.mk_test(test.content)
+        )
+
+    def _mk_cmp(self, key, val, test):
         val = val.content
         daff_key = key
         daff_test = test.test_str
@@ -160,7 +163,7 @@ def mk_cmp(self, key, val, test):
                 # if its cast - exclude those not matching type
                 key_format = key_format % (" NOT " + type_check[0] + " OR " if cast else "")
 
-            elif is_eq_test and _type == basestring:
+            elif is_eq_test and _type == str:
                 # here we convert '=' to '@>'
                 # instead of:
                 #   (hs_data->'univisionlanguage1') = 'both'
@@ -187,12 +190,12 @@ def mk_cmp(self, key, val, test):
 
     def cond_cast(self, val):
         def escape_single_quote(val):
-            if isinstance(val, basestring):
+            if isinstance(val, str):
                 return val.replace("'", "''")
             return val
 
         def format_list(lst):
-            delimiter = "'" if isinstance(lst[0], basestring) else ""
+            delimiter = "'" if isinstance(lst[0], str) else ""
             formatted_list = ",".join(
                 ["{1}{0}{1}".format(escape_single_quote(elem), delimiter) for elem in lst]
             )
@@ -225,7 +228,7 @@ def get_cast_attr(val, attr=None):
                 "type_check": lambda v: NUMERIC_TYPE_CHECK,
             },
             {
-                "type": basestring,
+                "type": str,
                 "cast": lambda v: "",
                 "value": lambda v: "'{}'".format(escape_single_quote(v)),
                 "type_check": lambda v: ["", ""],
@@ -242,4 +245,4 @@ def get_cast_attr(val, attr=None):
 
 
     def call(self, predicate, queryset):
-        return queryset.extra(where=[predicate]) if predicate else queryset
+        return queryset.extra(where=[predicate]) if predicate else queryset

daffodil/key_expectation_delegate.py → daffodil/key_expectation_delegate.pyx

@@ -1,7 +1,7 @@
-from .base_delegate import BaseDaffodilDelegate
+from .parser cimport Token, BaseDaffodilDelegate
 
 
-class KeyExpectationDelegate(BaseDaffodilDelegate):
+cdef class KeyExpectationDelegate(BaseDaffodilDelegate):
     """
     Determines which keys in a daffodil are required in data dictionaries 
     in order to match and which keys have to be omitted to match. 
@@ -42,7 +42,14 @@ def mk_test(self, test_str):
     def mk_comment(self, comment, is_inline):
         return set(), set()
 
-    def mk_cmp(self, key, val, test):
+    cdef mk_cmp(self, Token key, Token test, Token val):
+        return self._mk_cmp(
+            key.content,
+            val,
+            self.mk_test(test.content)
+        )
+
+    def _mk_cmp(self, key, val, test):
         val = val.content
         if test == "?=" and val is False:
             return set(), {key}

daffodil/parser.pxd

@@ -0,0 +1,40 @@
+cdef class Token:
+    cpdef public object content
+
+cdef class TimeStamp(Token):
+    cpdef public str raw_content
+
+cdef class GroupStart(Token): pass
+cdef class GroupEnd(Token): pass
+cdef class LineComment(Token): pass
+cdef class TrailingComment(Token): pass
+cdef class Operator(Token): pass
+cdef class String(Token): pass
+cdef class Number(Token): pass
+cdef class Boolean(Token): pass
+cdef class ArrayStart(Token): pass
+cdef class ArrayEnd(Token): pass
+
+cdef class _ArrayToken(Token):
+    cpdef public object raw_content
+
+cdef class BaseDaffodilDelegate:
+    cdef mk_cmp(self, Token key, Token test, Token val)
+
+cdef class DaffodilParser:
+    cdef public str src
+    cdef public tokens
+    cdef int pos, end
+
+    cdef str char(self, int offset=*)
+    cdef str chars(self, int n, pos=*)
+    cdef consume_whitespace(self, bint newlines=*)
+    cdef str read_quoted_string(self)
+
+
+cdef object _read_val(tokens)
+
+cdef class Daffodil:
+    cdef public DaffodilParser parse_result
+    cdef public BaseDaffodilDelegate delegate
+    cdef public object keys, predicate