moparisthebest/SickRage
1
0
Fork 0
mirror of https://github.com/moparisthebest/SickRage synced 2024-12-13 11:32:20 -05:00
Code Issues Releases Wiki Activity

Reverted new regex changes, not compatible with enough platforms to warrent keeping.

Browse Source
This commit is contained in:
echel0n 2014-05-31 06:16:18 -07:00
parent c5811791d0
commit 893574b2ed
17 changed files with 6 additions and 43762 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
lib/regex/Python25/__init__.py
View File

@ -1 +0,0 @@

BIN
lib/regex/Python25/_regex.pyd
View File

Binary file not shown.

1
lib/regex/Python26/__init__.py
View File

@ -1 +0,0 @@

BIN
lib/regex/Python26/_regex.pyd
View File

Binary file not shown.

BIN
lib/regex/Python26/_regex.so
View File

Binary file not shown.

1
lib/regex/Python27/__init__.py
View File

@ -1 +0,0 @@

BIN
lib/regex/Python27/_regex.pyd
View File

Binary file not shown.

BIN
lib/regex/Python27/_regex.so
View File

Binary file not shown.

1
lib/regex/__init__.py
View File

@ -1 +0,0 @@

22557
lib/regex/_regex.c
View File

File diff suppressed because it is too large Load Diff

228
lib/regex/_regex.h
View File

@ -1,228 +0,0 @@
/*
* Secret Labs' Regular Expression Engine
*
* regular expression matching engine
*
* Copyright (c) 1997-2001 by Secret Labs AB. All rights reserved.
*
* NOTE: This file is generated by regex.py. If you need
* to change anything in here, edit regex.py and run it.
*
* 2010-01-16 mrab Re-written
*/
/* Supports Unicode version 6.3.0. */
#define RE_MAGIC 20100116
#include "_regex_unicode.h"
/* Operators. */
#define RE_OP_FAILURE 0
#define RE_OP_SUCCESS 1
#define RE_OP_ANY 2
#define RE_OP_ANY_ALL 3
#define RE_OP_ANY_ALL_REV 4
#define RE_OP_ANY_REV 5
#define RE_OP_ANY_U 6
#define RE_OP_ANY_U_REV 7
#define RE_OP_ATOMIC 8
#define RE_OP_BOUNDARY 9
#define RE_OP_BRANCH 10
#define RE_OP_CALL_REF 11
#define RE_OP_CHARACTER 12
#define RE_OP_CHARACTER_IGN 13
#define RE_OP_CHARACTER_IGN_REV 14
#define RE_OP_CHARACTER_REV 15
#define RE_OP_DEFAULT_BOUNDARY 16
#define RE_OP_DEFAULT_END_OF_WORD 17
#define RE_OP_DEFAULT_START_OF_WORD 18
#define RE_OP_END 19
#define RE_OP_END_OF_LINE 20
#define RE_OP_END_OF_LINE_U 21
#define RE_OP_END_OF_STRING 22
#define RE_OP_END_OF_STRING_LINE 23
#define RE_OP_END_OF_STRING_LINE_U 24
#define RE_OP_END_OF_WORD 25
#define RE_OP_FUZZY 26
#define RE_OP_GRAPHEME_BOUNDARY 27
#define RE_OP_GREEDY_REPEAT 28
#define RE_OP_GROUP 29
#define RE_OP_GROUP_CALL 30
#define RE_OP_GROUP_EXISTS 31
#define RE_OP_LAZY_REPEAT 32
#define RE_OP_LOOKAROUND 33
#define RE_OP_NEXT 34
#define RE_OP_PROPERTY 35
#define RE_OP_PROPERTY_IGN 36
#define RE_OP_PROPERTY_IGN_REV 37
#define RE_OP_PROPERTY_REV 38
#define RE_OP_RANGE 39
#define RE_OP_RANGE_IGN 40
#define RE_OP_RANGE_IGN_REV 41
#define RE_OP_RANGE_REV 42
#define RE_OP_REF_GROUP 43
#define RE_OP_REF_GROUP_FLD 44
#define RE_OP_REF_GROUP_FLD_REV 45
#define RE_OP_REF_GROUP_IGN 46
#define RE_OP_REF_GROUP_IGN_REV 47
#define RE_OP_REF_GROUP_REV 48
#define RE_OP_SEARCH_ANCHOR 49
#define RE_OP_SET_DIFF 50
#define RE_OP_SET_DIFF_IGN 51
#define RE_OP_SET_DIFF_IGN_REV 52
#define RE_OP_SET_DIFF_REV 53
#define RE_OP_SET_INTER 54
#define RE_OP_SET_INTER_IGN 55
#define RE_OP_SET_INTER_IGN_REV 56
#define RE_OP_SET_INTER_REV 57
#define RE_OP_SET_SYM_DIFF 58
#define RE_OP_SET_SYM_DIFF_IGN 59
#define RE_OP_SET_SYM_DIFF_IGN_REV 60
#define RE_OP_SET_SYM_DIFF_REV 61
#define RE_OP_SET_UNION 62
#define RE_OP_SET_UNION_IGN 63
#define RE_OP_SET_UNION_IGN_REV 64
#define RE_OP_SET_UNION_REV 65
#define RE_OP_START_OF_LINE 66
#define RE_OP_START_OF_LINE_U 67
#define RE_OP_START_OF_STRING 68
#define RE_OP_START_OF_WORD 69
#define RE_OP_STRING 70
#define RE_OP_STRING_FLD 71
#define RE_OP_STRING_FLD_REV 72
#define RE_OP_STRING_IGN 73
#define RE_OP_STRING_IGN_REV 74
#define RE_OP_STRING_REV 75
#define RE_OP_STRING_SET 76
#define RE_OP_STRING_SET_FLD 77
#define RE_OP_STRING_SET_FLD_REV 78
#define RE_OP_STRING_SET_IGN 79
#define RE_OP_STRING_SET_IGN_REV 80
#define RE_OP_STRING_SET_REV 81
#define RE_OP_BODY_END 82
#define RE_OP_BODY_START 83
#define RE_OP_END_FUZZY 84
#define RE_OP_END_GREEDY_REPEAT 85
#define RE_OP_END_GROUP 86
#define RE_OP_END_LAZY_REPEAT 87
#define RE_OP_GREEDY_REPEAT_ONE 88
#define RE_OP_GROUP_RETURN 89
#define RE_OP_LAZY_REPEAT_ONE 90
#define RE_OP_MATCH_BODY 91
#define RE_OP_MATCH_TAIL 92
#define RE_OP_START_GROUP 93
char* re_op_text[] = {
"RE_OP_FAILURE",
"RE_OP_SUCCESS",
"RE_OP_ANY",
"RE_OP_ANY_ALL",
"RE_OP_ANY_ALL_REV",
"RE_OP_ANY_REV",
"RE_OP_ANY_U",
"RE_OP_ANY_U_REV",
"RE_OP_ATOMIC",
"RE_OP_BOUNDARY",
"RE_OP_BRANCH",
"RE_OP_CALL_REF",
"RE_OP_CHARACTER",
"RE_OP_CHARACTER_IGN",
"RE_OP_CHARACTER_IGN_REV",
"RE_OP_CHARACTER_REV",
"RE_OP_DEFAULT_BOUNDARY",
"RE_OP_DEFAULT_END_OF_WORD",
"RE_OP_DEFAULT_START_OF_WORD",
"RE_OP_END",
"RE_OP_END_OF_LINE",
"RE_OP_END_OF_LINE_U",
"RE_OP_END_OF_STRING",
"RE_OP_END_OF_STRING_LINE",
"RE_OP_END_OF_STRING_LINE_U",
"RE_OP_END_OF_WORD",
"RE_OP_FUZZY",
"RE_OP_GRAPHEME_BOUNDARY",
"RE_OP_GREEDY_REPEAT",
"RE_OP_GROUP",
"RE_OP_GROUP_CALL",
"RE_OP_GROUP_EXISTS",
"RE_OP_LAZY_REPEAT",
"RE_OP_LOOKAROUND",
"RE_OP_NEXT",
"RE_OP_PROPERTY",
"RE_OP_PROPERTY_IGN",
"RE_OP_PROPERTY_IGN_REV",
"RE_OP_PROPERTY_REV",
"RE_OP_RANGE",
"RE_OP_RANGE_IGN",
"RE_OP_RANGE_IGN_REV",
"RE_OP_RANGE_REV",
"RE_OP_REF_GROUP",
"RE_OP_REF_GROUP_FLD",
"RE_OP_REF_GROUP_FLD_REV",
"RE_OP_REF_GROUP_IGN",
"RE_OP_REF_GROUP_IGN_REV",
"RE_OP_REF_GROUP_REV",
"RE_OP_SEARCH_ANCHOR",
"RE_OP_SET_DIFF",
"RE_OP_SET_DIFF_IGN",
"RE_OP_SET_DIFF_IGN_REV",
"RE_OP_SET_DIFF_REV",
"RE_OP_SET_INTER",
"RE_OP_SET_INTER_IGN",
"RE_OP_SET_INTER_IGN_REV",
"RE_OP_SET_INTER_REV",
"RE_OP_SET_SYM_DIFF",
"RE_OP_SET_SYM_DIFF_IGN",
"RE_OP_SET_SYM_DIFF_IGN_REV",
"RE_OP_SET_SYM_DIFF_REV",
"RE_OP_SET_UNION",
"RE_OP_SET_UNION_IGN",
"RE_OP_SET_UNION_IGN_REV",
"RE_OP_SET_UNION_REV",
"RE_OP_START_OF_LINE",
"RE_OP_START_OF_LINE_U",
"RE_OP_START_OF_STRING",
"RE_OP_START_OF_WORD",
"RE_OP_STRING",
"RE_OP_STRING_FLD",
"RE_OP_STRING_FLD_REV",
"RE_OP_STRING_IGN",
"RE_OP_STRING_IGN_REV",
"RE_OP_STRING_REV",
"RE_OP_STRING_SET",
"RE_OP_STRING_SET_FLD",
"RE_OP_STRING_SET_FLD_REV",
"RE_OP_STRING_SET_IGN",
"RE_OP_STRING_SET_IGN_REV",
"RE_OP_STRING_SET_REV",
"RE_OP_BODY_END",
"RE_OP_BODY_START",
"RE_OP_END_FUZZY",
"RE_OP_END_GREEDY_REPEAT",
"RE_OP_END_GROUP",
"RE_OP_END_LAZY_REPEAT",
"RE_OP_GREEDY_REPEAT_ONE",
"RE_OP_GROUP_RETURN",
"RE_OP_LAZY_REPEAT_ONE",
"RE_OP_MATCH_BODY",
"RE_OP_MATCH_TAIL",
"RE_OP_START_GROUP",
};
#define RE_FLAG_ASCII 0x80
#define RE_FLAG_BESTMATCH 0x1000
#define RE_FLAG_DEBUG 0x200
#define RE_FLAG_DOTALL 0x10
#define RE_FLAG_ENHANCEMATCH 0x8000
#define RE_FLAG_FULLCASE 0x4000
#define RE_FLAG_IGNORECASE 0x2
#define RE_FLAG_LOCALE 0x4
#define RE_FLAG_MULTILINE 0x8
#define RE_FLAG_REVERSE 0x400
#define RE_FLAG_TEMPLATE 0x1
#define RE_FLAG_UNICODE 0x20
#define RE_FLAG_VERBOSE 0x40
#define RE_FLAG_VERSION0 0x2000
#define RE_FLAG_VERSION1 0x100
#define RE_FLAG_WORD 0x800

4086
lib/regex/_regex_core.py
View File

File diff suppressed because it is too large Load Diff

12748
lib/regex/_regex_unicode.c
View File

File diff suppressed because it is too large Load Diff

218
lib/regex/_regex_unicode.h
View File

@ -1,218 +0,0 @@
typedef unsigned char RE_UINT8;
typedef signed char RE_INT8;
typedef unsigned short RE_UINT16;
typedef signed short RE_INT16;
typedef unsigned int RE_UINT32;
typedef signed int RE_INT32;
typedef unsigned char BOOL;
enum {FALSE, TRUE};
#define RE_ASCII_MAX 0x7F
#define RE_LOCALE_MAX 0xFF
#define RE_UNICODE_MAX 0x10FFFF
#define RE_MAX_CASES 4
#define RE_MAX_FOLDED 3
typedef struct RE_Property {
RE_UINT16 name;
RE_UINT8 id;
RE_UINT8 value_set;
} RE_Property;
typedef struct RE_PropertyValue {
RE_UINT16 name;
RE_UINT8 value_set;
RE_UINT8 id;
} RE_PropertyValue;
typedef RE_UINT32 (*RE_GetPropertyFunc)(RE_UINT32 ch);
#define RE_PROP_GC 0x0
#define RE_PROP_CASED 0xA
#define RE_PROP_UPPERCASE 0x9
#define RE_PROP_LOWERCASE 0x8
#define RE_PROP_C 30
#define RE_PROP_L 31
#define RE_PROP_M 32
#define RE_PROP_N 33
#define RE_PROP_P 34
#define RE_PROP_S 35
#define RE_PROP_Z 36
#define RE_PROP_ASSIGNED 38
#define RE_PROP_CASEDLETTER 37
#define RE_PROP_CN 0
#define RE_PROP_LU 1
#define RE_PROP_LL 2
#define RE_PROP_LT 3
#define RE_PROP_LM 4
#define RE_PROP_LO 5
#define RE_PROP_MN 6
#define RE_PROP_ME 7
#define RE_PROP_MC 8
#define RE_PROP_ND 9
#define RE_PROP_NL 10
#define RE_PROP_NO 11
#define RE_PROP_ZS 12
#define RE_PROP_ZL 13
#define RE_PROP_ZP 14
#define RE_PROP_CC 15
#define RE_PROP_CF 16
#define RE_PROP_CO 17
#define RE_PROP_CS 18
#define RE_PROP_PD 19
#define RE_PROP_PS 20
#define RE_PROP_PE 21
#define RE_PROP_PC 22
#define RE_PROP_PO 23
#define RE_PROP_SM 24
#define RE_PROP_SC 25
#define RE_PROP_SK 26
#define RE_PROP_SO 27
#define RE_PROP_PI 28
#define RE_PROP_PF 29
#define RE_PROP_C_MASK 0x00078001
#define RE_PROP_L_MASK 0x0000003E
#define RE_PROP_M_MASK 0x000001C0
#define RE_PROP_N_MASK 0x00000E00
#define RE_PROP_P_MASK 0x30F80000
#define RE_PROP_S_MASK 0x0F000000
#define RE_PROP_Z_MASK 0x00007000
#define RE_PROP_ALNUM 0x460001
#define RE_PROP_ALPHA 0x070001
#define RE_PROP_ANY 0x470001
#define RE_PROP_ASCII 0x010001
#define RE_PROP_BLANK 0x480001
#define RE_PROP_CNTRL 0x00000F
#define RE_PROP_DIGIT 0x000009
#define RE_PROP_GRAPH 0x490001
#define RE_PROP_LOWER 0x080001
#define RE_PROP_PRINT 0x4A0001
#define RE_PROP_SPACE 0x190001
#define RE_PROP_UPPER 0x090001
#define RE_PROP_WORD 0x4B0001
#define RE_PROP_XDIGIT 0x4C0001
#define RE_BREAK_OTHER 0
#define RE_BREAK_DOUBLEQUOTE 1
#define RE_BREAK_SINGLEQUOTE 2
#define RE_BREAK_HEBREWLETTER 3
#define RE_BREAK_CR 4
#define RE_BREAK_LF 5
#define RE_BREAK_NEWLINE 6
#define RE_BREAK_EXTEND 7
#define RE_BREAK_REGIONALINDICATOR 8
#define RE_BREAK_FORMAT 9
#define RE_BREAK_KATAKANA 10
#define RE_BREAK_ALETTER 11
#define RE_BREAK_MIDLETTER 12
#define RE_BREAK_MIDNUM 13
#define RE_BREAK_MIDNUMLET 14
#define RE_BREAK_NUMERIC 15
#define RE_BREAK_EXTENDNUMLET 16
#define RE_GBREAK_OTHER 0
#define RE_GBREAK_CR 1
#define RE_GBREAK_LF 2
#define RE_GBREAK_CONTROL 3
#define RE_GBREAK_EXTEND 4
#define RE_GBREAK_REGIONALINDICATOR 5
#define RE_GBREAK_SPACINGMARK 6
#define RE_GBREAK_L 7
#define RE_GBREAK_V 8
#define RE_GBREAK_T 9
#define RE_GBREAK_LV 10
#define RE_GBREAK_LVT 11
#define RE_GBREAK_PREPEND 12
extern char* re_strings[1160];
extern RE_Property re_properties[143];
extern RE_PropertyValue re_property_values[1251];
extern RE_UINT16 re_expand_on_folding[104];
extern RE_GetPropertyFunc re_get_property[77];
RE_UINT32 re_get_general_category(RE_UINT32 ch);
RE_UINT32 re_get_block(RE_UINT32 ch);
RE_UINT32 re_get_script(RE_UINT32 ch);
RE_UINT32 re_get_word_break(RE_UINT32 ch);
RE_UINT32 re_get_grapheme_cluster_break(RE_UINT32 ch);
RE_UINT32 re_get_sentence_break(RE_UINT32 ch);
RE_UINT32 re_get_math(RE_UINT32 ch);
RE_UINT32 re_get_alphabetic(RE_UINT32 ch);
RE_UINT32 re_get_lowercase(RE_UINT32 ch);
RE_UINT32 re_get_uppercase(RE_UINT32 ch);
RE_UINT32 re_get_cased(RE_UINT32 ch);
RE_UINT32 re_get_case_ignorable(RE_UINT32 ch);
RE_UINT32 re_get_changes_when_lowercased(RE_UINT32 ch);
RE_UINT32 re_get_changes_when_uppercased(RE_UINT32 ch);
RE_UINT32 re_get_changes_when_titlecased(RE_UINT32 ch);
RE_UINT32 re_get_changes_when_casefolded(RE_UINT32 ch);
RE_UINT32 re_get_changes_when_casemapped(RE_UINT32 ch);
RE_UINT32 re_get_id_start(RE_UINT32 ch);
RE_UINT32 re_get_id_continue(RE_UINT32 ch);
RE_UINT32 re_get_xid_start(RE_UINT32 ch);
RE_UINT32 re_get_xid_continue(RE_UINT32 ch);
RE_UINT32 re_get_default_ignorable_code_point(RE_UINT32 ch);
RE_UINT32 re_get_grapheme_extend(RE_UINT32 ch);
RE_UINT32 re_get_grapheme_base(RE_UINT32 ch);
RE_UINT32 re_get_grapheme_link(RE_UINT32 ch);
RE_UINT32 re_get_white_space(RE_UINT32 ch);
RE_UINT32 re_get_bidi_control(RE_UINT32 ch);
RE_UINT32 re_get_join_control(RE_UINT32 ch);
RE_UINT32 re_get_dash(RE_UINT32 ch);
RE_UINT32 re_get_hyphen(RE_UINT32 ch);
RE_UINT32 re_get_quotation_mark(RE_UINT32 ch);
RE_UINT32 re_get_terminal_punctuation(RE_UINT32 ch);
RE_UINT32 re_get_other_math(RE_UINT32 ch);
RE_UINT32 re_get_hex_digit(RE_UINT32 ch);
RE_UINT32 re_get_ascii_hex_digit(RE_UINT32 ch);
RE_UINT32 re_get_other_alphabetic(RE_UINT32 ch);
RE_UINT32 re_get_ideographic(RE_UINT32 ch);
RE_UINT32 re_get_diacritic(RE_UINT32 ch);
RE_UINT32 re_get_extender(RE_UINT32 ch);
RE_UINT32 re_get_other_lowercase(RE_UINT32 ch);
RE_UINT32 re_get_other_uppercase(RE_UINT32 ch);
RE_UINT32 re_get_noncharacter_code_point(RE_UINT32 ch);
RE_UINT32 re_get_other_grapheme_extend(RE_UINT32 ch);
RE_UINT32 re_get_ids_binary_operator(RE_UINT32 ch);
RE_UINT32 re_get_ids_trinary_operator(RE_UINT32 ch);
RE_UINT32 re_get_radical(RE_UINT32 ch);
RE_UINT32 re_get_unified_ideograph(RE_UINT32 ch);
RE_UINT32 re_get_other_default_ignorable_code_point(RE_UINT32 ch);
RE_UINT32 re_get_deprecated(RE_UINT32 ch);
RE_UINT32 re_get_soft_dotted(RE_UINT32 ch);
RE_UINT32 re_get_logical_order_exception(RE_UINT32 ch);
RE_UINT32 re_get_other_id_start(RE_UINT32 ch);
RE_UINT32 re_get_other_id_continue(RE_UINT32 ch);
RE_UINT32 re_get_sterm(RE_UINT32 ch);
RE_UINT32 re_get_variation_selector(RE_UINT32 ch);
RE_UINT32 re_get_pattern_white_space(RE_UINT32 ch);
RE_UINT32 re_get_pattern_syntax(RE_UINT32 ch);
RE_UINT32 re_get_hangul_syllable_type(RE_UINT32 ch);
RE_UINT32 re_get_bidi_class(RE_UINT32 ch);
RE_UINT32 re_get_canonical_combining_class(RE_UINT32 ch);
RE_UINT32 re_get_decomposition_type(RE_UINT32 ch);
RE_UINT32 re_get_east_asian_width(RE_UINT32 ch);
RE_UINT32 re_get_joining_group(RE_UINT32 ch);
RE_UINT32 re_get_joining_type(RE_UINT32 ch);
RE_UINT32 re_get_line_break(RE_UINT32 ch);
RE_UINT32 re_get_numeric_type(RE_UINT32 ch);
RE_UINT32 re_get_numeric_value(RE_UINT32 ch);
RE_UINT32 re_get_bidi_mirrored(RE_UINT32 ch);
RE_UINT32 re_get_indic_matra_category(RE_UINT32 ch);
RE_UINT32 re_get_indic_syllabic_category(RE_UINT32 ch);
RE_UINT32 re_get_alphanumeric(RE_UINT32 ch);
RE_UINT32 re_get_any(RE_UINT32 ch);
RE_UINT32 re_get_blank(RE_UINT32 ch);
RE_UINT32 re_get_graph(RE_UINT32 ch);
RE_UINT32 re_get_print(RE_UINT32 ch);
RE_UINT32 re_get_word(RE_UINT32 ch);
RE_UINT32 re_get_xdigit(RE_UINT32 ch);
int re_get_all_cases(RE_UINT32 ch, RE_UINT32* codepoints);
RE_UINT32 re_get_simple_case_folding(RE_UINT32 ch);
int re_get_full_case_folding(RE_UINT32 ch, RE_UINT32* codepoints);

684
lib/regex/regex.py
View File

@ -1,684 +0,0 @@
#
# Secret Labs' Regular Expression Engine
#
# Copyright (c) 1998-2001 by Secret Labs AB. All rights reserved.
#
# This version of the SRE library can be redistributed under CNRI's
# Python 1.6 license. For any other use, please contact Secret Labs
# AB (info@pythonware.com).
#
# Portions of this engine have been developed in cooperation with
# CNRI. Hewlett-Packard provided funding for 1.6 integration and
# other compatibility work.
#
# 2010-01-16 mrab Python front-end re-written and extended
r"""Support for regular expressions (RE).
This module provides regular expression matching operations similar to those
found in Perl. It supports both 8-bit and Unicode strings; both the pattern and
the strings being processed can contain null bytes and characters outside the
US ASCII range.
Regular expressions can contain both special and ordinary characters. Most
ordinary characters, like "A", "a", or "0", are the simplest regular
expressions; they simply match themselves. You can concatenate ordinary
characters, so last matches the string 'last'.
There are a few differences between the old (legacy) behaviour and the new
(enhanced) behaviour, which are indicated by VERSION0 or VERSION1.
The special characters are:
"." Matches any character except a newline.
"^" Matches the start of the string.
"$" Matches the end of the string or just before the
newline at the end of the string.
"*" Matches 0 or more (greedy) repetitions of the preceding
RE. Greedy means that it will match as many repetitions
as possible.
"+" Matches 1 or more (greedy) repetitions of the preceding
RE.
"?" Matches 0 or 1 (greedy) of the preceding RE.
*?,+?,?? Non-greedy versions of the previous three special
characters.
*+,++,?+ Possessive versions of the previous three special
characters.
{m,n} Matches from m to n repetitions of the preceding RE.
{m,n}? Non-greedy version of the above.
{m,n}+ Possessive version of the above.
{...} Fuzzy matching constraints.
"\\" Either escapes special characters or signals a special
sequence.
[...] Indicates a set of characters. A "^" as the first
character indicates a complementing set.
"|" A|B, creates an RE that will match either A or B.
(...) Matches the RE inside the parentheses. The contents are
captured and can be retrieved or matched later in the
string.
(?flags-flags) VERSION1: Sets/clears the flags for the remainder of
the group or pattern; VERSION0: Sets the flags for the
entire pattern.
(?:...) Non-capturing version of regular parentheses.
(?>...) Atomic non-capturing version of regular parentheses.
(?flags-flags:...) Non-capturing version of regular parentheses with local
flags.
(?P<name>...) The substring matched by the group is accessible by
name.
(?<name>...) The substring matched by the group is accessible by
name.
(?P=name) Matches the text matched earlier by the group named
name.
(?#...) A comment; ignored.
(?=...) Matches if ... matches next, but doesn't consume the
string.
(?!...) Matches if ... doesn't match next.
(?<=...) Matches if preceded by ....
(?<!...) Matches if not preceded by ....
(?(id)yes|no) Matches yes pattern if group id matched, the (optional)
no pattern otherwise.
(?|...|...) (?|A|B), creates an RE that will match either A or B,
but reuses capture group numbers across the
alternatives.
The fuzzy matching constraints are: "i" to permit insertions, "d" to permit
deletions, "s" to permit substitutions, "e" to permit any of these. Limits are
optional with "<=" and "<". If any type of error is provided then any type not
provided is not permitted.
A cost equation may be provided.
Examples:
(?:fuzzy){i<=2}
(?:fuzzy){i<=1,s<=2,d<=1,1i+1s+1d<3}
VERSION1: Set operators are supported, and a set can include nested sets. The
set operators, in order of increasing precedence, are:
|| Set union ("x||y" means "x or y").
~~ (double tilde) Symmetric set difference ("x~~y" means "x or y, but not
both").
&& Set intersection ("x&&y" means "x and y").
-- (double dash) Set difference ("x--y" means "x but not y").
Implicit union, ie, simple juxtaposition like in [ab], has the highest
precedence.
VERSION0 and VERSION1:
The special sequences consist of "\\" and a character from the list below. If
the ordinary character is not on the list, then the resulting RE will match the
second character.
\number Matches the contents of the group of the same number if
number is no more than 2 digits, otherwise the character
with the 3-digit octal code.
\a Matches the bell character.
\A Matches only at the start of the string.
\b Matches the empty string, but only at the start or end of a
word.
\B Matches the empty string, but not at the start or end of a
word.
\d Matches any decimal digit; equivalent to the set [0-9] when
matching a bytestring or a Unicode string with the ASCII
flag, or the whole range of Unicode digits when matching a
Unicode string.
\D Matches any non-digit character; equivalent to [^\d].
\f Matches the formfeed character.
\g<name> Matches the text matched by the group named name.
\G Matches the empty string, but only at the position where
the search started.
\L<name> Named list. The list is provided as a keyword argument.
\m Matches the empty string, but only at the start of a word.
\M Matches the empty string, but only at the end of a word.
\n Matches the newline character.
\N{name} Matches the named character.
\p{name=value} Matches the character if its property has the specified
value.
\P{name=value} Matches the character if its property hasn't the specified
value.
\r Matches the carriage-return character.
\s Matches any whitespace character; equivalent to
[ \t\n\r\f\v].
\S Matches any non-whitespace character; equivalent to [^\s].
\t Matches the tab character.
\uXXXX Matches the Unicode codepoint with 4-digit hex code XXXX.
\UXXXXXXXX Matches the Unicode codepoint with 8-digit hex code
XXXXXXXX.
\v Matches the vertical tab character.
\w Matches any alphanumeric character; equivalent to
[a-zA-Z0-9_] when matching a bytestring or a Unicode string
with the ASCII flag, or the whole range of Unicode
alphanumeric characters (letters plus digits plus
underscore) when matching a Unicode string. With LOCALE, it
will match the set [0-9_] plus characters defined as
letters for the current locale.
\W Matches the complement of \w; equivalent to [^\w].
\xXX Matches the character with 2-digit hex code XX.
\X Matches a grapheme.
\Z Matches only at the end of the string.
\\ Matches a literal backslash.
This module exports the following functions:
match Match a regular expression pattern at the beginning of a string.
fullmatch Match a regular expression pattern against all of a string.
search Search a string for the presence of a pattern.
sub Substitute occurrences of a pattern found in a string using a
template string.
subf Substitute occurrences of a pattern found in a string using a
format string.
subn Same as sub, but also return the number of substitutions made.
subfn Same as subf, but also return the number of substitutions made.
split Split a string by the occurrences of a pattern. VERSION1: will
split at zero-width match; VERSION0: won't split at zero-width
match.
splititer Return an iterator yielding the parts of a split string.
findall Find all occurrences of a pattern in a string.
finditer Return an iterator yielding a match object for each match.
compile Compile a pattern into a Pattern object.
purge Clear the regular expression cache.
escape Backslash all non-alphanumerics or special characters in a
string.
Most of the functions support a concurrent parameter: if True, the GIL will be
released during matching, allowing other Python threads to run concurrently. If
the string changes during matching, the behaviour is undefined. This parameter
is not needed when working on the builtin (immutable) string classes.
Some of the functions in this module take flags as optional parameters. Most of
these flags can also be set within an RE:
A a ASCII Make \w, \W, \b, \B, \d, and \D match the
corresponding ASCII character categories. Default
when matching a bytestring.
B b BESTMATCH Find the best fuzzy match (default is first).
D DEBUG Print the parsed pattern.
F f FULLCASE Use full case-folding when performing
case-insensitive matching in Unicode.
I i IGNORECASE Perform case-insensitive matching.
L L LOCALE Make \w, \W, \b, \B, \d, and \D dependent on the
current locale. (One byte per character only.)
M m MULTILINE "^" matches the beginning of lines (after a newline)
as well as the string. "$" matches the end of lines
(before a newline) as well as the end of the string.
E e ENHANCEMATCH Attempt to improve the fit after finding the first
fuzzy match.
R r REVERSE Searches backwards.
S s DOTALL "." matches any character at all, including the
newline.
U u UNICODE Make \w, \W, \b, \B, \d, and \D dependent on the
Unicode locale. Default when matching a Unicode
string.
V0 V0 VERSION0 Turn on the old legacy behaviour.
V1 V1 VERSION1 Turn on the new enhanced behaviour. This flag
includes the FULLCASE flag.
W w WORD Make \b and \B work with default Unicode word breaks
and make ".", "^" and "$" work with Unicode line
breaks.
X x VERBOSE Ignore whitespace and comments for nicer looking REs.
This module also defines an exception 'error'.
"""
# Public symbols.
__all__ = ["compile", "escape", "findall", "finditer", "fullmatch", "match",
"purge", "search", "split", "splititer", "sub", "subf", "subfn", "subn",
"template", "Scanner", "A", "ASCII", "B", "BESTMATCH", "D", "DEBUG", "E",
"ENHANCEMATCH", "S", "DOTALL", "F", "FULLCASE", "I", "IGNORECASE", "L",
"LOCALE", "M", "MULTILINE", "R", "REVERSE", "T", "TEMPLATE", "U", "UNICODE",
"V0", "VERSION0", "V1", "VERSION1", "X", "VERBOSE", "W", "WORD", "error",
"Regex"]
__version__ = "2.4.45"
# --------------------------------------------------------------------
# Public interface.
def match(pattern, string, flags=0, pos=None, endpos=None, partial=False,
concurrent=None, **kwargs):
"""Try to apply the pattern at the start of the string, returning a match
object, or None if no match was found."""
return _compile(pattern, flags, kwargs).match(string, pos, endpos,
concurrent, partial)
def fullmatch(pattern, string, flags=0, pos=None, endpos=None, partial=False,
concurrent=None, **kwargs):
"""Try to apply the pattern against all of the string, returning a match
object, or None if no match was found."""
return _compile(pattern, flags, kwargs).fullmatch(string, pos, endpos,
concurrent, partial)
def search(pattern, string, flags=0, pos=None, endpos=None, partial=False,
concurrent=None, **kwargs):
"""Search through string looking for a match to the pattern, returning a
match object, or None if no match was found."""
return _compile(pattern, flags, kwargs).search(string, pos, endpos,
concurrent, partial)
def sub(pattern, repl, string, count=0, flags=0, pos=None, endpos=None,
concurrent=None, **kwargs):
"""Return the string obtained by replacing the leftmost (or rightmost with a
reverse pattern) non-overlapping occurrences of the pattern in string by the
replacement repl. repl can be either a string or a callable; if a string,
backslash escapes in it are processed; if a callable, it's passed the match
object and must return a replacement string to be used."""
return _compile(pattern, flags, kwargs).sub(repl, string, count, pos,
endpos, concurrent)
def subf(pattern, format, string, count=0, flags=0, pos=None, endpos=None,
concurrent=None, **kwargs):
"""Return the string obtained by replacing the leftmost (or rightmost with a
reverse pattern) non-overlapping occurrences of the pattern in string by the
replacement format. format can be either a string or a callable; if a string,
it's treated as a format string; if a callable, it's passed the match object
and must return a replacement string to be used."""
return _compile(pattern, flags, kwargs).subf(format, string, count, pos,
endpos, concurrent)
def subn(pattern, repl, string, count=0, flags=0, pos=None, endpos=None,
concurrent=None, **kwargs):
"""Return a 2-tuple containing (new_string, number). new_string is the string
obtained by replacing the leftmost (or rightmost with a reverse pattern)
non-overlapping occurrences of the pattern in the source string by the
replacement repl. number is the number of substitutions that were made. repl
can be either a string or a callable; if a string, backslash escapes in it
are processed; if a callable, it's passed the match object and must return a
replacement string to be used."""
return _compile(pattern, flags, kwargs).subn(repl, string, count, pos,
endpos, concurrent)
def subfn(pattern, format, string, count=0, flags=0, pos=None, endpos=None,
concurrent=None, **kwargs):
"""Return a 2-tuple containing (new_string, number). new_string is the string
obtained by replacing the leftmost (or rightmost with a reverse pattern)
non-overlapping occurrences of the pattern in the source string by the
replacement format. number is the number of substitutions that were made. format
can be either a string or a callable; if a string, it's treated as a format
string; if a callable, it's passed the match object and must return a
replacement string to be used."""
return _compile(pattern, flags, kwargs).subfn(format, string, count, pos,
endpos, concurrent)
def split(pattern, string, maxsplit=0, flags=0, concurrent=None, **kwargs):
"""Split the source string by the occurrences of the pattern, returning a
list containing the resulting substrings. If capturing parentheses are used
in pattern, then the text of all groups in the pattern are also returned as
part of the resulting list. If maxsplit is nonzero, at most maxsplit splits
occur, and the remainder of the string is returned as the final element of
the list."""
return _compile(pattern, flags, kwargs).split(string, maxsplit, concurrent)
def splititer(pattern, string, maxsplit=0, flags=0, concurrent=None, **kwargs):
"Return an iterator yielding the parts of a split string."
return _compile(pattern, flags, kwargs).splititer(string, maxsplit,
concurrent)
def findall(pattern, string, flags=0, pos=None, endpos=None, overlapped=False,
concurrent=None, **kwargs):
"""Return a list of all matches in the string. The matches may be overlapped
if overlapped is True. If one or more groups are present in the pattern,
return a list of groups; this will be a list of tuples if the pattern has
more than one group. Empty matches are included in the result."""
return _compile(pattern, flags, kwargs).findall(string, pos, endpos,
overlapped, concurrent)
def finditer(pattern, string, flags=0, pos=None, endpos=None, overlapped=False,
partial=False, concurrent=None, **kwargs):
"""Return an iterator over all matches in the string. The matches may be
overlapped if overlapped is True. For each match, the iterator returns a
match object. Empty matches are included in the result."""
return _compile(pattern, flags, kwargs).finditer(string, pos, endpos,
overlapped, concurrent, partial)
def compile(pattern, flags=0, **kwargs):
"Compile a regular expression pattern, returning a pattern object."
return _compile(pattern, flags, kwargs)
def purge():
"Clear the regular expression cache"
_cache.clear()
def template(pattern, flags=0):
"Compile a template pattern, returning a pattern object."
return _compile(pattern, flags | TEMPLATE)
def escape(pattern, special_only=False):
"Escape all non-alphanumeric characters or special characters in pattern."
if isinstance(pattern, unicode):
s = []
if special_only:
for c in pattern:
if c in _METACHARS:
s.append(u"\\")
s.append(c)
elif c == u"\x00":
s.append(u"\\000")
else:
s.append(c)
else:
for c in pattern:
if c in _ALNUM:
s.append(c)
elif c == u"\x00":
s.append(u"\\000")
else:
s.append(u"\\")
s.append(c)
return u"".join(s)
else:
s = []
if special_only:
for c in pattern:
if c in _METACHARS:
s.append("\\")
s.append(c)
elif c == "\x00":
s.append("\\000")
else:
s.append(c)
else:
for c in pattern:
if c in _ALNUM:
s.append(c)
elif c == "\x00":
s.append("\\000")
else:
s.append("\\")
s.append(c)
return "".join(s)
# --------------------------------------------------------------------
# Internals.
import _regex_core
import sys
if sys.version_info < (2, 6):
from Python25 import _regex
elif sys.version_info < (2, 7):
from Python26 import _regex
else:
from Python27 import _regex
from threading import RLock as _RLock
from _regex_core import *
from _regex_core import (_ALL_VERSIONS, _ALL_ENCODINGS, _FirstSetError,
_UnscopedFlagSet, _check_group_features, _compile_firstset,
_compile_replacement, _flatten_code, _fold_case, _get_required_string,
_parse_pattern, _shrink_cache)
from _regex_core import (ALNUM as _ALNUM, Info as _Info, OP as _OP, Source as
_Source, Fuzzy as _Fuzzy)
# Version 0 is the old behaviour, compatible with the original 're' module.
# Version 1 is the new behaviour, which differs slightly.
DEFAULT_VERSION = VERSION0
_METACHARS = frozenset("()[]{}?*+|^$\\.")
_regex_core.DEFAULT_VERSION = DEFAULT_VERSION
# Caches for the patterns and replacements.
_cache = {}
_cache_lock = _RLock()
_named_args = {}
_replacement_cache = {}
# Maximum size of the cache.
_MAXCACHE = 500
_MAXREPCACHE = 500
def _compile(pattern, flags=0, kwargs={}):
"Compiles a regular expression to a PatternObject."
try:
# Do we know what keyword arguments are needed?
args_key = pattern, type(pattern), flags
args_needed = _named_args[args_key]
# Are we being provided with its required keyword arguments?
args_supplied = set()
if args_needed:
for k, v in args_needed:
try:
args_supplied.add((k, frozenset(kwargs[k])))
except KeyError:
raise error("missing named list")
args_supplied = frozenset(args_supplied)
# Have we already seen this regular expression and named list?
pattern_key = (pattern, type(pattern), flags, args_supplied,
DEFAULT_VERSION)
return _cache[pattern_key]
except KeyError:
# It's a new pattern, or new named list for a known pattern.
pass
# Guess the encoding from the class of the pattern string.
if isinstance(pattern, unicode):
guess_encoding = UNICODE
elif isinstance(pattern, str):
guess_encoding = ASCII
elif isinstance(pattern, _pattern_type):
if flags:
raise ValueError("can't process flags argument with a compiled pattern")
return pattern
else:
raise TypeError("first argument must be a string or compiled pattern")
# Set the default version in the core code in case it has been changed.
_regex_core.DEFAULT_VERSION = DEFAULT_VERSION
caught_exception = None
global_flags = flags
while True:
try:
source = _Source(pattern)
info = _Info(global_flags, source.char_type, kwargs)
info.guess_encoding = guess_encoding
source.ignore_space = bool(info.flags & VERBOSE)
parsed = _parse_pattern(source, info)
break
except _UnscopedFlagSet:
# Remember the global flags for the next attempt.
global_flags = info.global_flags
except error, e:
caught_exception = e
if caught_exception:
raise error(str(caught_exception))
if not source.at_end():
raise error("trailing characters in pattern at position %d" % source.pos)
# Check the global flags for conflicts.
version = (info.flags & _ALL_VERSIONS) or DEFAULT_VERSION
if version not in (0, VERSION0, VERSION1):
raise ValueError("VERSION0 and VERSION1 flags are mutually incompatible")
if (info.flags & _ALL_ENCODINGS) not in (0, ASCII, LOCALE, UNICODE):
raise ValueError("ASCII, LOCALE and UNICODE flags are mutually incompatible")
if not (info.flags & _ALL_ENCODINGS):
if isinstance(pattern, unicode):
info.flags |= UNICODE
else:
info.flags |= ASCII
reverse = bool(info.flags & REVERSE)
fuzzy = isinstance(parsed, _Fuzzy)
# Should we print the parsed pattern?
if flags & DEBUG:
parsed.dump(indent=0, reverse=reverse)
# Fix the group references.
parsed.fix_groups(reverse, False)
# Optimise the parsed pattern.
parsed = parsed.optimise(info)
parsed = parsed.pack_characters(info)
# Get the required string.
req_offset, req_chars, req_flags = _get_required_string(parsed, info.flags)
# Build the named lists.
named_lists = {}
named_list_indexes = [None] * len(info.named_lists_used)
args_needed = set()
for key, index in info.named_lists_used.items():
name, case_flags = key
values = frozenset(kwargs[name])
if case_flags:
items = frozenset(_fold_case(info, v) for v in values)
else:
items = values
named_lists[name] = values
named_list_indexes[index] = items
args_needed.add((name, values))
# Check the features of the groups.
_check_group_features(info, parsed)
# Compile the parsed pattern. The result is a list of tuples.
code = parsed.compile(reverse)
# Is there a group call to the pattern as a whole?
key = (0, reverse, fuzzy)
ref = info.call_refs.get(key)
if ref is not None:
code = [(_OP.CALL_REF, ref)] + code + [(_OP.END, )]
# Add the final 'success' opcode.
code += [(_OP.SUCCESS, )]
# Compile the additional copies of the groups that we need.
for group, rev, fuz in info.additional_groups:
code += group.compile(rev, fuz)
# Flatten the code into a list of ints.
code = _flatten_code(code)
if not parsed.has_simple_start():
# Get the first set, if possible.
try:
fs_code = _compile_firstset(info, parsed.get_firstset(reverse))
fs_code = _flatten_code(fs_code)
code = fs_code + code
except _FirstSetError:
pass
# The named capture groups.
index_group = dict((v, n) for n, v in info.group_index.items())
# Create the PatternObject.
#
# Local flags like IGNORECASE affect the code generation, but aren't needed
# by the PatternObject itself. Conversely, global flags like LOCALE _don't_
# affect the code generation but _are_ needed by the PatternObject.
compiled_pattern = _regex.compile(pattern, info.flags | version, code,
info.group_index, index_group, named_lists, named_list_indexes,
req_offset, req_chars, req_flags, info.group_count)
# Do we need to reduce the size of the cache?
if len(_cache) >= _MAXCACHE:
_cache_lock.acquire()
try:
_shrink_cache(_cache, _named_args, _MAXCACHE)
finally:
_cache_lock.release()
args_needed = frozenset(args_needed)
# Store this regular expression and named list.
pattern_key = (pattern, type(pattern), flags, args_needed, DEFAULT_VERSION)
_cache[pattern_key] = compiled_pattern
# Store what keyword arguments are needed.
_named_args[args_key] = args_needed
return compiled_pattern
def _compile_replacement_helper(pattern, template):
"Compiles a replacement template."
# This function is called by the _regex module.
# Have we seen this before?
key = pattern.pattern, pattern.flags, template
compiled = _replacement_cache.get(key)
if compiled is not None:
return compiled
if len(_replacement_cache) >= _MAXREPCACHE:
_replacement_cache.clear()
is_unicode = isinstance(template, unicode)
source = _Source(template)
if is_unicode:
def make_string(char_codes):
return u"".join(unichr(c) for c in char_codes)
else:
def make_string(char_codes):
return "".join(chr(c) for c in char_codes)
compiled = []
literal = []
while True:
ch = source.get()
if not ch:
break
if ch == "\\":
# '_compile_replacement' will return either an int group reference
# or a string literal. It returns items (plural) in order to handle
# a 2-character literal (an invalid escape sequence).
is_group, items = _compile_replacement(source, pattern, is_unicode)
if is_group:
# It's a group, so first flush the literal.
if literal:
compiled.append(make_string(literal))
literal = []
compiled.extend(items)
else:
literal.extend(items)
else:
literal.append(ord(ch))
# Flush the literal.
if literal:
compiled.append(make_string(literal))
_replacement_cache[key] = compiled
return compiled
# We define _pattern_type here after all the support objects have been defined.
_pattern_type = type(_compile("", 0, {}))
# We'll define an alias for the 'compile' function so that the repr of a
# pattern object is eval-able.
Regex = compile
# Register myself for pickling.
import copy_reg as _copy_reg
def _pickle(p):
return _compile, (p.pattern, p.flags)
_copy_reg.pickle(_pattern_type, _pickle, _compile)
if not hasattr(str, "format"):
# Strings don't have the .format method (below Python 2.6).
while True:
_start = __doc__.find(" subf")
if _start < 0:
break
_end = __doc__.find("\n", _start) + 1
while __doc__.startswith(" ", _end):
_end = __doc__.find("\n", _end) + 1
__doc__ = __doc__[ : _start] + __doc__[_end : ]
__all__ = [_name for _name in __all__ if not _name.startswith("subf")]
del _start, _end
del subf, subfn

3230
lib/regex/test_regex.py
View File

File diff suppressed because it is too large Load Diff

13
sickbeard/name_parser/parser.py
View File

@ -24,7 +24,6 @@ import regexes
import sickbeard import sickbeard
from sickbeard import logger, helpers, scene_numbering from sickbeard import logger, helpers, scene_numbering
from regex import regex
from dateutil import parser from dateutil import parser
nameparser_lock = threading.Lock() nameparser_lock = threading.Lock()
@ -104,8 +103,8 @@ class NameParser(object):
for regex_type, regex_pattern in regexItem.items(): for regex_type, regex_pattern in regexItem.items():
for (cur_pattern_name, cur_pattern) in regex_pattern: for (cur_pattern_name, cur_pattern) in regex_pattern:
try: try:
cur_regex = regex.compile(cur_pattern, regex.V1 | regex.VERBOSE | regex.IGNORECASE | regex.BESTMATCH) cur_regex = re.compile(cur_pattern, re.VERBOSE | re.IGNORECASE)
except regex.error, errormsg: except re.error, errormsg:
logger.log(u"WARNING: Invalid episode_pattern, %s. %s" % (errormsg, cur_pattern)) logger.log(u"WARNING: Invalid episode_pattern, %s. %s" % (errormsg, cur_pattern))
else: else:
self.compiled_regexes[(regex_type,cur_pattern_name)] = cur_regex self.compiled_regexes[(regex_type,cur_pattern_name)] = cur_regex
@ -116,7 +115,7 @@ class NameParser(object):
result = ParseResult(name) result = ParseResult(name)
for (cur_regex_type, cur_regex_name), cur_regex in self.compiled_regexes.items(): for (cur_regex_type, cur_regex_name), cur_regex in self.compiled_regexes.items():
match = cur_regex.fullmatch(name) match = cur_regex.match(name)
if not match: if not match:
continue continue
@ -185,8 +184,8 @@ class NameParser(object):
tmp_extra_info = match.group('extra_info') tmp_extra_info = match.group('extra_info')
# Show.S04.Special or Show.S05.Part.2.Extras is almost certainly not every episode in the season # Show.S04.Special or Show.S05.Part.2.Extras is almost certainly not every episode in the season
if tmp_extra_info and cur_regex_name == 'season_only' and regex.search( if tmp_extra_info and cur_regex_name == 'season_only' and re.search(
r'([. _-]|^)(special|extra)s?\w*([. _-]|$)', tmp_extra_info, regex.I): r'([. _-]|^)(special|extra)s?\w*([. _-]|$)', tmp_extra_info, re.I):
continue continue
result.extra_info = tmp_extra_info result.extra_info = tmp_extra_info
@ -286,7 +285,7 @@ class NameParser(object):
# break it into parts if there are any (dirname, file name, extension) # break it into parts if there are any (dirname, file name, extension)
dir_name, file_name = os.path.split(name) dir_name, file_name = os.path.split(name)
ext_match = regex.match('(.*)\.\w{3,4}$', file_name) ext_match = re.match('(.*)\.\w{3,4}$', file_name)
if ext_match and self.file_name: if ext_match and self.file_name:
base_file_name = ext_match.group(1) base_file_name = ext_match.group(1)
else: else: