diff options
Diffstat (limited to 'Lib/sre_constants.py')
| -rw-r--r-- | Lib/sre_constants.py | 308 |
1 files changed, 156 insertions, 152 deletions
diff --git a/Lib/sre_constants.py b/Lib/sre_constants.py index 8e613cb..69224e2 100644 --- a/Lib/sre_constants.py +++ b/Lib/sre_constants.py @@ -13,152 +13,157 @@ # update when constants are added or removed -MAGIC = 20171005 +MAGIC = 20031017 -from _sre import MAXREPEAT, MAXGROUPS +try: + from _sre import MAXREPEAT +except ImportError: + import _sre + MAXREPEAT = _sre.MAXREPEAT = 65535 # SRE standard exception (access as sre.error) # should this really be here? class error(Exception): - """Exception raised for invalid regular expressions. - - Attributes: - - msg: The unformatted error message - pattern: The regular expression pattern - pos: The index in the pattern where compilation failed (may be None) - lineno: The line corresponding to pos (may be None) - colno: The column corresponding to pos (may be None) - """ - - __module__ = 're' - - def __init__(self, msg, pattern=None, pos=None): - self.msg = msg - self.pattern = pattern - self.pos = pos - if pattern is not None and pos is not None: - msg = '%s at position %d' % (msg, pos) - if isinstance(pattern, str): - newline = '\n' - else: - newline = b'\n' - self.lineno = pattern.count(newline, 0, pos) + 1 - self.colno = pos - pattern.rfind(newline, 0, pos) - if newline in pattern: - msg = '%s (line %d, column %d)' % (msg, self.lineno, self.colno) - else: - self.lineno = self.colno = None - super().__init__(msg) - - -class _NamedIntConstant(int): - def __new__(cls, value, name): - self = super(_NamedIntConstant, cls).__new__(cls, value) - self.name = name - return self - - def __repr__(self): - return self.name - -MAXREPEAT = _NamedIntConstant(MAXREPEAT, 'MAXREPEAT') - -def _makecodes(names): - names = names.strip().split() - items = [_NamedIntConstant(i, name) for i, name in enumerate(names)] - globals().update({item.name: item for item in items}) - return items + pass # operators -# failure=0 success=1 (just because it looks better that way :-) -OPCODES = _makecodes(""" - FAILURE SUCCESS - - ANY ANY_ALL - ASSERT ASSERT_NOT - AT - BRANCH - CALL - CATEGORY - CHARSET BIGCHARSET - GROUPREF GROUPREF_EXISTS - IN - INFO - JUMP - LITERAL - MARK - MAX_UNTIL - MIN_UNTIL - NOT_LITERAL - NEGATE - RANGE - REPEAT - REPEAT_ONE - SUBPATTERN - MIN_REPEAT_ONE - - GROUPREF_IGNORE - IN_IGNORE - LITERAL_IGNORE - NOT_LITERAL_IGNORE - GROUPREF_LOC_IGNORE - IN_LOC_IGNORE - LITERAL_LOC_IGNORE - NOT_LITERAL_LOC_IGNORE - - GROUPREF_UNI_IGNORE - IN_UNI_IGNORE - LITERAL_UNI_IGNORE - NOT_LITERAL_UNI_IGNORE - RANGE_UNI_IGNORE - - MIN_REPEAT MAX_REPEAT -""") -del OPCODES[-2:] # remove MIN_REPEAT and MAX_REPEAT +FAILURE = "failure" +SUCCESS = "success" + +ANY = "any" +ANY_ALL = "any_all" +ASSERT = "assert" +ASSERT_NOT = "assert_not" +AT = "at" +BIGCHARSET = "bigcharset" +BRANCH = "branch" +CALL = "call" +CATEGORY = "category" +CHARSET = "charset" +GROUPREF = "groupref" +GROUPREF_IGNORE = "groupref_ignore" +GROUPREF_EXISTS = "groupref_exists" +IN = "in" +IN_IGNORE = "in_ignore" +INFO = "info" +JUMP = "jump" +LITERAL = "literal" +LITERAL_IGNORE = "literal_ignore" +MARK = "mark" +MAX_REPEAT = "max_repeat" +MAX_UNTIL = "max_until" +MIN_REPEAT = "min_repeat" +MIN_UNTIL = "min_until" +NEGATE = "negate" +NOT_LITERAL = "not_literal" +NOT_LITERAL_IGNORE = "not_literal_ignore" +RANGE = "range" +REPEAT = "repeat" +REPEAT_ONE = "repeat_one" +SUBPATTERN = "subpattern" +MIN_REPEAT_ONE = "min_repeat_one" # positions -ATCODES = _makecodes(""" - AT_BEGINNING AT_BEGINNING_LINE AT_BEGINNING_STRING - AT_BOUNDARY AT_NON_BOUNDARY - AT_END AT_END_LINE AT_END_STRING - - AT_LOC_BOUNDARY AT_LOC_NON_BOUNDARY - - AT_UNI_BOUNDARY AT_UNI_NON_BOUNDARY -""") +AT_BEGINNING = "at_beginning" +AT_BEGINNING_LINE = "at_beginning_line" +AT_BEGINNING_STRING = "at_beginning_string" +AT_BOUNDARY = "at_boundary" +AT_NON_BOUNDARY = "at_non_boundary" +AT_END = "at_end" +AT_END_LINE = "at_end_line" +AT_END_STRING = "at_end_string" +AT_LOC_BOUNDARY = "at_loc_boundary" +AT_LOC_NON_BOUNDARY = "at_loc_non_boundary" +AT_UNI_BOUNDARY = "at_uni_boundary" +AT_UNI_NON_BOUNDARY = "at_uni_non_boundary" # categories -CHCODES = _makecodes(""" - CATEGORY_DIGIT CATEGORY_NOT_DIGIT - CATEGORY_SPACE CATEGORY_NOT_SPACE - CATEGORY_WORD CATEGORY_NOT_WORD - CATEGORY_LINEBREAK CATEGORY_NOT_LINEBREAK - - CATEGORY_LOC_WORD CATEGORY_LOC_NOT_WORD - - CATEGORY_UNI_DIGIT CATEGORY_UNI_NOT_DIGIT - CATEGORY_UNI_SPACE CATEGORY_UNI_NOT_SPACE - CATEGORY_UNI_WORD CATEGORY_UNI_NOT_WORD - CATEGORY_UNI_LINEBREAK CATEGORY_UNI_NOT_LINEBREAK -""") +CATEGORY_DIGIT = "category_digit" +CATEGORY_NOT_DIGIT = "category_not_digit" +CATEGORY_SPACE = "category_space" +CATEGORY_NOT_SPACE = "category_not_space" +CATEGORY_WORD = "category_word" +CATEGORY_NOT_WORD = "category_not_word" +CATEGORY_LINEBREAK = "category_linebreak" +CATEGORY_NOT_LINEBREAK = "category_not_linebreak" +CATEGORY_LOC_WORD = "category_loc_word" +CATEGORY_LOC_NOT_WORD = "category_loc_not_word" +CATEGORY_UNI_DIGIT = "category_uni_digit" +CATEGORY_UNI_NOT_DIGIT = "category_uni_not_digit" +CATEGORY_UNI_SPACE = "category_uni_space" +CATEGORY_UNI_NOT_SPACE = "category_uni_not_space" +CATEGORY_UNI_WORD = "category_uni_word" +CATEGORY_UNI_NOT_WORD = "category_uni_not_word" +CATEGORY_UNI_LINEBREAK = "category_uni_linebreak" +CATEGORY_UNI_NOT_LINEBREAK = "category_uni_not_linebreak" + +OPCODES = [ + + # failure=0 success=1 (just because it looks better that way :-) + FAILURE, SUCCESS, + + ANY, ANY_ALL, + ASSERT, ASSERT_NOT, + AT, + BRANCH, + CALL, + CATEGORY, + CHARSET, BIGCHARSET, + GROUPREF, GROUPREF_EXISTS, GROUPREF_IGNORE, + IN, IN_IGNORE, + INFO, + JUMP, + LITERAL, LITERAL_IGNORE, + MARK, + MAX_UNTIL, + MIN_UNTIL, + NOT_LITERAL, NOT_LITERAL_IGNORE, + NEGATE, + RANGE, + REPEAT, + REPEAT_ONE, + SUBPATTERN, + MIN_REPEAT_ONE +] + +ATCODES = [ + AT_BEGINNING, AT_BEGINNING_LINE, AT_BEGINNING_STRING, AT_BOUNDARY, + AT_NON_BOUNDARY, AT_END, AT_END_LINE, AT_END_STRING, + AT_LOC_BOUNDARY, AT_LOC_NON_BOUNDARY, AT_UNI_BOUNDARY, + AT_UNI_NON_BOUNDARY +] + +CHCODES = [ + CATEGORY_DIGIT, CATEGORY_NOT_DIGIT, CATEGORY_SPACE, + CATEGORY_NOT_SPACE, CATEGORY_WORD, CATEGORY_NOT_WORD, + CATEGORY_LINEBREAK, CATEGORY_NOT_LINEBREAK, CATEGORY_LOC_WORD, + CATEGORY_LOC_NOT_WORD, CATEGORY_UNI_DIGIT, CATEGORY_UNI_NOT_DIGIT, + CATEGORY_UNI_SPACE, CATEGORY_UNI_NOT_SPACE, CATEGORY_UNI_WORD, + CATEGORY_UNI_NOT_WORD, CATEGORY_UNI_LINEBREAK, + CATEGORY_UNI_NOT_LINEBREAK +] + +def makedict(list): + d = {} + i = 0 + for item in list: + d[item] = i + i = i + 1 + return d + +OPCODES = makedict(OPCODES) +ATCODES = makedict(ATCODES) +CHCODES = makedict(CHCODES) # replacement operations for "ignore case" mode OP_IGNORE = { + GROUPREF: GROUPREF_IGNORE, + IN: IN_IGNORE, LITERAL: LITERAL_IGNORE, - NOT_LITERAL: NOT_LITERAL_IGNORE, -} - -OP_LOCALE_IGNORE = { - LITERAL: LITERAL_LOC_IGNORE, - NOT_LITERAL: NOT_LITERAL_LOC_IGNORE, -} - -OP_UNICODE_IGNORE = { - LITERAL: LITERAL_UNI_IGNORE, - NOT_LITERAL: NOT_LITERAL_UNI_IGNORE, + NOT_LITERAL: NOT_LITERAL_IGNORE } AT_MULTILINE = { @@ -204,10 +209,9 @@ SRE_FLAG_IGNORECASE = 2 # case insensitive SRE_FLAG_LOCALE = 4 # honour system locale SRE_FLAG_MULTILINE = 8 # treat target as multiline string SRE_FLAG_DOTALL = 16 # treat target as a single string -SRE_FLAG_UNICODE = 32 # use unicode "locale" +SRE_FLAG_UNICODE = 32 # use unicode locale SRE_FLAG_VERBOSE = 64 # ignore whitespace and comments SRE_FLAG_DEBUG = 128 # debugging -SRE_FLAG_ASCII = 256 # use ascii "locale" # flags for INFO primitive SRE_INFO_PREFIX = 1 # has prefix @@ -216,11 +220,12 @@ SRE_INFO_CHARSET = 4 # pattern starts with character from given set if __name__ == "__main__": def dump(f, d, prefix): - items = sorted(d) - for item in items: - f.write("#define %s_%s %d\n" % (prefix, item, item)) - with open("sre_constants.h", "w") as f: - f.write("""\ + items = d.items() + items.sort(key=lambda a: a[1]) + for k, v in items: + f.write("#define %s_%s %s\n" % (prefix, k.upper(), v)) + f = open("sre_constants.h", "w") + f.write("""\ /* * Secret Labs' Regular Expression Engine * @@ -236,24 +241,23 @@ if __name__ == "__main__": """) - f.write("#define SRE_MAGIC %d\n" % MAGIC) + f.write("#define SRE_MAGIC %d\n" % MAGIC) - dump(f, OPCODES, "SRE_OP") - dump(f, ATCODES, "SRE") - dump(f, CHCODES, "SRE") + dump(f, OPCODES, "SRE_OP") + dump(f, ATCODES, "SRE") + dump(f, CHCODES, "SRE") - f.write("#define SRE_FLAG_TEMPLATE %d\n" % SRE_FLAG_TEMPLATE) - f.write("#define SRE_FLAG_IGNORECASE %d\n" % SRE_FLAG_IGNORECASE) - f.write("#define SRE_FLAG_LOCALE %d\n" % SRE_FLAG_LOCALE) - f.write("#define SRE_FLAG_MULTILINE %d\n" % SRE_FLAG_MULTILINE) - f.write("#define SRE_FLAG_DOTALL %d\n" % SRE_FLAG_DOTALL) - f.write("#define SRE_FLAG_UNICODE %d\n" % SRE_FLAG_UNICODE) - f.write("#define SRE_FLAG_VERBOSE %d\n" % SRE_FLAG_VERBOSE) - f.write("#define SRE_FLAG_DEBUG %d\n" % SRE_FLAG_DEBUG) - f.write("#define SRE_FLAG_ASCII %d\n" % SRE_FLAG_ASCII) + f.write("#define SRE_FLAG_TEMPLATE %d\n" % SRE_FLAG_TEMPLATE) + f.write("#define SRE_FLAG_IGNORECASE %d\n" % SRE_FLAG_IGNORECASE) + f.write("#define SRE_FLAG_LOCALE %d\n" % SRE_FLAG_LOCALE) + f.write("#define SRE_FLAG_MULTILINE %d\n" % SRE_FLAG_MULTILINE) + f.write("#define SRE_FLAG_DOTALL %d\n" % SRE_FLAG_DOTALL) + f.write("#define SRE_FLAG_UNICODE %d\n" % SRE_FLAG_UNICODE) + f.write("#define SRE_FLAG_VERBOSE %d\n" % SRE_FLAG_VERBOSE) - f.write("#define SRE_INFO_PREFIX %d\n" % SRE_INFO_PREFIX) - f.write("#define SRE_INFO_LITERAL %d\n" % SRE_INFO_LITERAL) - f.write("#define SRE_INFO_CHARSET %d\n" % SRE_INFO_CHARSET) + f.write("#define SRE_INFO_PREFIX %d\n" % SRE_INFO_PREFIX) + f.write("#define SRE_INFO_LITERAL %d\n" % SRE_INFO_LITERAL) + f.write("#define SRE_INFO_CHARSET %d\n" % SRE_INFO_CHARSET) - print("done") + f.close() + print "done" |