Issue #22434: Constants in sre_constants are now named constants (enum-like).

This commit is contained in:
Serhiy Storchaka 2014-11-09 20:48:36 +02:00
parent bf764a1912
commit c7f7d3897e
4 changed files with 127 additions and 186 deletions

View File

@ -13,7 +13,6 @@
import _sre
import sre_parse
from sre_constants import *
from _sre import MAXREPEAT
assert _sre.MAGIC == MAGIC, "SRE module mismatch"
@ -38,65 +37,65 @@ def _compile(code, pattern, flags):
for op, av in pattern:
if op in LITERAL_CODES:
if flags & SRE_FLAG_IGNORECASE:
emit(OPCODES[OP_IGNORE[op]])
emit(OP_IGNORE[op])
emit(_sre.getlower(av, flags))
else:
emit(OPCODES[op])
emit(op)
emit(av)
elif op is IN:
if flags & SRE_FLAG_IGNORECASE:
emit(OPCODES[OP_IGNORE[op]])
emit(OP_IGNORE[op])
def fixup(literal, flags=flags):
return _sre.getlower(literal, flags)
else:
emit(OPCODES[op])
emit(op)
fixup = None
skip = _len(code); emit(0)
_compile_charset(av, flags, code, fixup)
code[skip] = _len(code) - skip
elif op is ANY:
if flags & SRE_FLAG_DOTALL:
emit(OPCODES[ANY_ALL])
emit(ANY_ALL)
else:
emit(OPCODES[ANY])
emit(ANY)
elif op in REPEATING_CODES:
if flags & SRE_FLAG_TEMPLATE:
raise error("internal: unsupported template operator")
elif _simple(av) and op is not REPEAT:
if op is MAX_REPEAT:
emit(OPCODES[REPEAT_ONE])
emit(REPEAT_ONE)
else:
emit(OPCODES[MIN_REPEAT_ONE])
emit(MIN_REPEAT_ONE)
skip = _len(code); emit(0)
emit(av[0])
emit(av[1])
_compile(code, av[2], flags)
emit(OPCODES[SUCCESS])
emit(SUCCESS)
code[skip] = _len(code) - skip
else:
emit(OPCODES[REPEAT])
emit(REPEAT)
skip = _len(code); emit(0)
emit(av[0])
emit(av[1])
_compile(code, av[2], flags)
code[skip] = _len(code) - skip
if op is MAX_REPEAT:
emit(OPCODES[MAX_UNTIL])
emit(MAX_UNTIL)
else:
emit(OPCODES[MIN_UNTIL])
emit(MIN_UNTIL)
elif op is SUBPATTERN:
if av[0]:
emit(OPCODES[MARK])
emit(MARK)
emit((av[0]-1)*2)
# _compile_info(code, av[1], flags)
_compile(code, av[1], flags)
if av[0]:
emit(OPCODES[MARK])
emit(MARK)
emit((av[0]-1)*2+1)
elif op in SUCCESS_CODES:
emit(OPCODES[op])
emit(op)
elif op in ASSERT_CODES:
emit(OPCODES[op])
emit(op)
skip = _len(code); emit(0)
if av[0] >= 0:
emit(0) # look ahead
@ -106,57 +105,57 @@ def _compile(code, pattern, flags):
raise error("look-behind requires fixed-width pattern")
emit(lo) # look behind
_compile(code, av[1], flags)
emit(OPCODES[SUCCESS])
emit(SUCCESS)
code[skip] = _len(code) - skip
elif op is CALL:
emit(OPCODES[op])
emit(op)
skip = _len(code); emit(0)
_compile(code, av, flags)
emit(OPCODES[SUCCESS])
emit(SUCCESS)
code[skip] = _len(code) - skip
elif op is AT:
emit(OPCODES[op])
emit(op)
if flags & SRE_FLAG_MULTILINE:
av = AT_MULTILINE.get(av, av)
if flags & SRE_FLAG_LOCALE:
av = AT_LOCALE.get(av, av)
elif flags & SRE_FLAG_UNICODE:
av = AT_UNICODE.get(av, av)
emit(ATCODES[av])
emit(av)
elif op is BRANCH:
emit(OPCODES[op])
emit(op)
tail = []
tailappend = tail.append
for av in av[1]:
skip = _len(code); emit(0)
# _compile_info(code, av, flags)
_compile(code, av, flags)
emit(OPCODES[JUMP])
emit(JUMP)
tailappend(_len(code)); emit(0)
code[skip] = _len(code) - skip
emit(0) # end of branch
for tail in tail:
code[tail] = _len(code) - tail
elif op is CATEGORY:
emit(OPCODES[op])
emit(op)
if flags & SRE_FLAG_LOCALE:
av = CH_LOCALE[av]
elif flags & SRE_FLAG_UNICODE:
av = CH_UNICODE[av]
emit(CHCODES[av])
emit(av)
elif op is GROUPREF:
if flags & SRE_FLAG_IGNORECASE:
emit(OPCODES[OP_IGNORE[op]])
emit(OP_IGNORE[op])
else:
emit(OPCODES[op])
emit(op)
emit(av-1)
elif op is GROUPREF_EXISTS:
emit(OPCODES[op])
emit(op)
emit(av[0]-1)
skipyes = _len(code); emit(0)
_compile(code, av[1], flags)
if av[2]:
emit(OPCODES[JUMP])
emit(JUMP)
skipno = _len(code); emit(0)
code[skipyes] = _len(code) - skipyes + 1
_compile(code, av[2], flags)
@ -170,7 +169,7 @@ def _compile_charset(charset, flags, code, fixup=None):
# compile charset subprogram
emit = code.append
for op, av in _optimize_charset(charset, fixup):
emit(OPCODES[op])
emit(op)
if op is NEGATE:
pass
elif op is LITERAL:
@ -184,14 +183,14 @@ def _compile_charset(charset, flags, code, fixup=None):
code.extend(av)
elif op is CATEGORY:
if flags & SRE_FLAG_LOCALE:
emit(CHCODES[CH_LOCALE[av]])
emit(CH_LOCALE[av])
elif flags & SRE_FLAG_UNICODE:
emit(CHCODES[CH_UNICODE[av]])
emit(CH_UNICODE[av])
else:
emit(CHCODES[av])
emit(av)
else:
raise error("internal: unsupported set operator")
emit(OPCODES[FAILURE])
emit(FAILURE)
def _optimize_charset(charset, fixup):
# internal: optimize character set
@ -414,7 +413,7 @@ def _compile_info(code, pattern, flags):
## print "*** CHARSET", charset
# add an info block
emit = code.append
emit(OPCODES[INFO])
emit(INFO)
skip = len(code); emit(0)
# literal flag
mask = 0
@ -460,7 +459,7 @@ def _code(p, flags):
# compile the pattern
_compile(code, p.data, flags)
code.append(OPCODES[SUCCESS])
code.append(SUCCESS)
return code
@ -475,7 +474,7 @@ def compile(p, flags=0):
code = _code(p, flags)
# print code
# print(code)
# map in either direction
groupindex = p.pattern.groupdict

View File

@ -23,138 +23,81 @@ from _sre import MAXREPEAT, MAXGROUPS
class error(Exception):
pass
class _NamedIntConstant(int):
def __new__(cls, value, name):
self = super(_NamedIntConstant, cls).__new__(cls, value)
self.name = name
return self
def __str__(self):
return self.name
__repr__ = __str__
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
# operators
# failure=0 success=1 (just because it looks better that way :-)
OPCODES = _makecodes("""
FAILURE SUCCESS
FAILURE = "failure"
SUCCESS = "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
RANGE_IGNORE
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"
RANGE_IGNORE = "range_ignore"
REPEAT = "repeat"
REPEAT_ONE = "repeat_one"
SUBPATTERN = "subpattern"
MIN_REPEAT_ONE = "min_repeat_one"
MIN_REPEAT MAX_REPEAT
""")
del OPCODES[-2:] # remove MIN_REPEAT and MAX_REPEAT
# positions
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"
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
""")
# categories
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"
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
""")
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,
RANGE_IGNORE,
]
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 = {
@ -220,9 +163,9 @@ SRE_INFO_CHARSET = 4 # pattern starts with character from given set
if __name__ == "__main__":
def dump(f, d, prefix):
items = sorted(d.items(), key=lambda a: a[1])
for k, v in items:
f.write("#define %s_%s %s\n" % (prefix, k.upper(), v))
items = sorted(d)
for item in items:
f.write("#define %s_%s %d\n" % (prefix, item, item))
f = open("sre_constants.h", "w")
f.write("""\
/*

View File

@ -13,7 +13,6 @@
# XXX: show string offset and offending character for all errors
from sre_constants import *
from _sre import MAXREPEAT
SPECIAL_CHARS = ".\\[{()*+?^$|"
REPEAT_CHARS = "*+?{"
@ -103,24 +102,24 @@ class SubPattern:
nl = True
seqtypes = (tuple, list)
for op, av in self.data:
print(level*" " + op, end='')
print(level*" " + str(op), end='')
if op == IN:
# member sublanguage
print()
for op, a in av:
print((level+1)*" " + op, a)
print((level+1)*" " + str(op), a)
elif op == BRANCH:
print()
for i, a in enumerate(av[1]):
if i:
print(level*" " + "or")
print(level*" " + "OR")
a.dump(level+1)
elif op == GROUPREF_EXISTS:
condgroup, item_yes, item_no = av
print('', condgroup)
item_yes.dump(level+1)
if item_no:
print(level*" " + "else")
print(level*" " + "ELSE")
item_no.dump(level+1)
elif isinstance(av, seqtypes):
nl = False

View File

@ -1285,22 +1285,22 @@ class ReTests(unittest.TestCase):
with captured_stdout() as out:
re.compile(pat, re.DEBUG)
dump = '''\
subpattern 1
literal 46
subpattern None
branch
in
literal 99
literal 104
or
literal 112
literal 121
subpattern None
groupref_exists 1
at at_end
else
literal 58
literal 32
SUBPATTERN 1
LITERAL 46
SUBPATTERN None
BRANCH
IN
LITERAL 99
LITERAL 104
OR
LITERAL 112
LITERAL 121
SUBPATTERN None
GROUPREF_EXISTS 1
AT AT_END
ELSE
LITERAL 58
LITERAL 32
'''
self.assertEqual(out.getvalue(), dump)
# Debug output is output again even a second time (bypassing