diff options
| -rw-r--r-- | pyparsing/core.py | 24 | ||||
| -rw-r--r-- | pyparsing/helpers.py | 15 | ||||
| -rw-r--r-- | pyparsing/results.py | 5 | ||||
| -rw-r--r-- | pyparsing/unicode.py | 37 | ||||
| -rw-r--r-- | pyparsing/util.py | 6 |
5 files changed, 50 insertions, 37 deletions
diff --git a/pyparsing/core.py b/pyparsing/core.py index b61a8f8..1bb13b8 100644 --- a/pyparsing/core.py +++ b/pyparsing/core.py @@ -407,7 +407,7 @@ class ParserElement(ABC): def __init__(self, savelist: bool = False): self.parseAction: List[ParseAction] = list() - self.failAction = None + self.failAction: OptionalType[ParseFailAction] = None self.customName = None self._defaultName = None self.resultsName = None @@ -428,7 +428,9 @@ class ParserElement(ABC): self.modalResults = True # custom debug actions self.debugActions: Tuple[ - DebugStartAction, DebugSuccessAction, DebugExceptionAction + OptionalType[DebugStartAction], + OptionalType[DebugSuccessAction], + OptionalType[DebugExceptionAction], ] = (None, None, None) self.re = None # avoid redundant calls to preParse @@ -461,7 +463,7 @@ class ParserElement(ABC): cpy.parseAction = self.parseAction[:] cpy.ignoreExprs = self.ignoreExprs[:] if self.copyDefaultWhiteChars: - cpy.whiteChars = ParserElement.DEFAULT_WHITE_CHARS + cpy.whiteChars = set(ParserElement.DEFAULT_WHITE_CHARS) return cpy def set_results_name( @@ -855,7 +857,7 @@ class ParserElement(ABC): _parse = _parseNoCache @staticmethod - def reset_cache() -> NoReturn: + def reset_cache() -> None: ParserElement.packrat_cache.clear() ParserElement.packrat_cache_stats[:] = [0] * len( ParserElement.packrat_cache_stats @@ -866,7 +868,7 @@ class ParserElement(ABC): _left_recursion_enabled = False @staticmethod - def disable_memoization() -> NoReturn: + def disable_memoization() -> None: """ Disables active Packrat or Left Recursion parsing and their memoization @@ -882,7 +884,7 @@ class ParserElement(ABC): @staticmethod def enable_left_recursion( cache_size_limit: OptionalType[int] = None, *, force=False - ) -> NoReturn: + ) -> None: """ Enables "bounded recursion" parsing, which allows for both direct and indirect left-recursion. During parsing, left-recursive :class:`Forward` elements are @@ -928,7 +930,7 @@ class ParserElement(ABC): ParserElement._left_recursion_enabled = True @staticmethod - def enable_packrat(cache_size_limit: int = 128, *, force: bool = False) -> NoReturn: + def enable_packrat(cache_size_limit: int = 128, *, force: bool = False) -> None: """ Enables "packrat" parsing, which adds memoizing to the parsing logic. Repeated parse attempts at the same string location (which happens @@ -1169,7 +1171,7 @@ class ParserElement(ABC): def search_string( self, instring: str, max_matches: int = _MAX_INT, *, maxMatches: int = _MAX_INT - ) -> List[ParseResults]: + ) -> ParseResults: """ Another extension to :class:`scan_string`, simplifying the access to the tokens found to match the given parse expression. May be called with optional @@ -1205,7 +1207,7 @@ class ParserElement(ABC): def split( self, instring: str, - maxsplit: bool = _MAX_INT, + maxsplit: int = _MAX_INT, include_separators: bool = False, *, includeSeparators=False, @@ -3565,8 +3567,8 @@ class And(ParseExpression): def _generateDefaultName(self): return "-" - def __init__(self, exprs: IterableType[ParserElement], savelist: bool = True): - exprs: List["ParserElement"] = list(exprs) + def __init__(self, exprs_arg: IterableType[ParserElement], savelist: bool = True): + exprs: List["ParserElement"] = list(exprs_arg) if exprs and Ellipsis in exprs: tmp = [] for i, expr in enumerate(exprs): diff --git a/pyparsing/helpers.py b/pyparsing/helpers.py index 03cf695..6b7b909 100644 --- a/pyparsing/helpers.py +++ b/pyparsing/helpers.py @@ -665,7 +665,12 @@ class OpAssoc(Enum): InfixNotationOperatorSpec = Tuple[ - Union[ParserElement, str], int, OpAssoc, OptionalType[ParseAction] + Union[ + ParserElement, str, Tuple[Union[ParserElement, str], Union[ParserElement, str]] + ], + int, + OpAssoc, + OptionalType[ParseAction], ] @@ -765,6 +770,9 @@ def infix_notation( "if numterms=3, opExpr must be a tuple or list of two expressions" ) opExpr1, opExpr2 = opExpr + term_name = "{}{} term".format(opExpr1, opExpr2) + else: + term_name = "{} term".format(opExpr) if not 1 <= arity <= 3: raise ValueError("operator must be unary (1), binary (2), or ternary (3)") @@ -772,8 +780,7 @@ def infix_notation( if rightLeftAssoc not in (OpAssoc.LEFT, OpAssoc.RIGHT): raise ValueError("operator must indicate right or left associativity") - termName = "%s term" % opExpr if arity < 3 else "%s%s term" % opExpr - thisExpr = Forward().set_name(termName) + thisExpr = Forward().set_name(term_name) if rightLeftAssoc is OpAssoc.LEFT: if arity == 1: matchExpr = _FB(lastExpr + opExpr) + Group( @@ -816,7 +823,7 @@ def infix_notation( matchExpr.set_parse_action(*pa) else: matchExpr.set_parse_action(pa) - thisExpr <<= matchExpr.set_name(termName) | lastExpr + thisExpr <<= matchExpr.set_name(term_name) | lastExpr lastExpr = thisExpr ret <<= lastExpr return ret diff --git a/pyparsing/results.py b/pyparsing/results.py index 172074d..3d52fbb 100644 --- a/pyparsing/results.py +++ b/pyparsing/results.py @@ -3,9 +3,10 @@ from collections.abc import MutableMapping, Mapping, MutableSequence import pprint from weakref import ref as wkref +from typing import Tuple, Any str_type = (str, bytes) -_generator_type = type((x for x in ())) +_generator_type = type((_ for _ in ())) class _ParseResultsWithOffset: @@ -70,7 +71,7 @@ class ParseResults: - year: 1999 """ - _null_values = (None, "", [], ()) + _null_values: Tuple[Any, ...] = (None, "", [], ()) __slots__ = [ "_name", diff --git a/pyparsing/unicode.py b/pyparsing/unicode.py index f41d2a0..cbf6865 100644 --- a/pyparsing/unicode.py +++ b/pyparsing/unicode.py @@ -2,6 +2,7 @@ import sys from itertools import filterfalse +from typing import List, Tuple class _lazyclassproperty: @@ -39,7 +40,7 @@ class unicode_set: pass """ - _ranges = [] + _ranges: List[Tuple[int, ...]] = [] @classmethod def _get_chars_for_ranges(cls): @@ -95,30 +96,30 @@ class pyparsing_unicode(unicode_set): A namespace class for defining common language unicode_sets. """ - _ranges = [(32, sys.maxunicode)] + _ranges: List[Tuple[int, ...]] = [(32, sys.maxunicode)] class Latin1(unicode_set): "Unicode set for Latin-1 Unicode Character Range" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x0020, 0x007E), (0x00A0, 0x00FF), ] class LatinA(unicode_set): "Unicode set for Latin-A Unicode Character Range" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x0100, 0x017F), ] class LatinB(unicode_set): "Unicode set for Latin-B Unicode Character Range" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x0180, 0x024F), ] class Greek(unicode_set): "Unicode set for Greek Unicode Character Ranges" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x0342, 0x0345), (0x0370, 0x0377), (0x037A, 0x037F), @@ -158,7 +159,7 @@ class pyparsing_unicode(unicode_set): class Cyrillic(unicode_set): "Unicode set for Cyrillic Unicode Character Range" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x0400, 0x052F), (0x1C80, 0x1C88), (0x1D2B,), @@ -171,7 +172,7 @@ class pyparsing_unicode(unicode_set): class Chinese(unicode_set): "Unicode set for Chinese Unicode Character Range" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x2E80, 0x2E99), (0x2E9B, 0x2EF3), (0x31C0, 0x31E3), @@ -194,18 +195,18 @@ class pyparsing_unicode(unicode_set): class Japanese(unicode_set): "Unicode set for Japanese Unicode Character Range, combining Kanji, Hiragana, and Katakana ranges" - _ranges = [] + _ranges: List[Tuple[int, ...]] = [] class Kanji(unicode_set): "Unicode set for Kanji Unicode Character Range" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x4E00, 0x9FBF), (0x3000, 0x303F), ] class Hiragana(unicode_set): "Unicode set for Hiragana Unicode Character Range" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x3041, 0x3096), (0x3099, 0x30A0), (0x30FC,), @@ -217,7 +218,7 @@ class pyparsing_unicode(unicode_set): class Katakana(unicode_set): "Unicode set for Katakana Unicode Character Range" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x3099, 0x309C), (0x30A0, 0x30FF), (0x31F0, 0x31FF), @@ -231,7 +232,7 @@ class pyparsing_unicode(unicode_set): class Hangul(unicode_set): "Unicode set for Hangul (Korean) Unicode Character Range" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x1100, 0x11FF), (0x302E, 0x302F), (0x3131, 0x318E), @@ -251,17 +252,17 @@ class pyparsing_unicode(unicode_set): Korean = Hangul - class CJK(Chinese, Japanese, Korean): + class CJK(Chinese, Japanese, Hangul): "Unicode set for combined Chinese, Japanese, and Korean (CJK) Unicode Character Range" pass class Thai(unicode_set): "Unicode set for Thai Unicode Character Range" - _ranges = [(0x0E01, 0x0E3A), (0x0E3F, 0x0E5B)] + _ranges: List[Tuple[int, ...]] = [(0x0E01, 0x0E3A), (0x0E3F, 0x0E5B)] class Arabic(unicode_set): "Unicode set for Arabic Unicode Character Range" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x0600, 0x061B), (0x061E, 0x06FF), (0x0700, 0x077F), @@ -269,7 +270,7 @@ class pyparsing_unicode(unicode_set): class Hebrew(unicode_set): "Unicode set for Hebrew Unicode Character Range" - _ranges = [ + _ranges: List[Tuple[int, ...]] = [ (0x0591, 0x05C7), (0x05D0, 0x05EA), (0x05EF, 0x05F4), @@ -283,7 +284,7 @@ class pyparsing_unicode(unicode_set): class Devanagari(unicode_set): "Unicode set for Devanagari Unicode Character Range" - _ranges = [(0x0900, 0x097F), (0xA8E0, 0xA8FF)] + _ranges: List[Tuple[int, ...]] = [(0x0900, 0x097F), (0xA8E0, 0xA8FF)] pyparsing_unicode.Japanese._ranges = ( diff --git a/pyparsing/util.py b/pyparsing/util.py index bbbfcd5..004476d 100644 --- a/pyparsing/util.py +++ b/pyparsing/util.py @@ -4,6 +4,8 @@ import types import collections import itertools from functools import lru_cache +from typing import List + _bslash = chr(92) @@ -11,8 +13,8 @@ _bslash = chr(92) class __config_flags: """Internal class for defining compatibility and debugging flags""" - _all_names = [] - _fixed_names = [] + _all_names: List[str] = [] + _fixed_names: List[str] = [] _type_desc = "configuration" @classmethod |