- actually enabled charset anchors in the engine (still not
used by the code generator) - changed max repeat value in engine (to match earlier array fix) - added experimental "which part matched?" mechanism to sre; see http://hem.passagen.se/eff/2000_07_01_bot-archive.htm#416954 or python-dev for details.
This commit is contained in:
parent
b19948b7fb
commit
7cafe4d7e4
31
Lib/sre.py
31
Lib/sre.py
|
@ -155,3 +155,34 @@ def _pickle(p):
|
|||
return _compile, (p.pattern, p.flags)
|
||||
|
||||
copy_reg.pickle(type(_compile("")), _pickle, _compile)
|
||||
|
||||
# --------------------------------------------------------------------
|
||||
# experimental stuff (see python-dev discussions for details)
|
||||
|
||||
class Scanner:
|
||||
def __init__(self, lexicon):
|
||||
self.lexicon = lexicon
|
||||
p = []
|
||||
for phrase, action in lexicon:
|
||||
p.append("(?:%s)(?P#%d)" % (phrase, len(p)))
|
||||
self.scanner = sre.compile("|".join(p))
|
||||
def scan(self, string):
|
||||
result = []
|
||||
append = result.append
|
||||
match = self.scanner.match
|
||||
i = 0
|
||||
while 1:
|
||||
m = match(string, i)
|
||||
if not m:
|
||||
break
|
||||
j = m.end()
|
||||
if i == j:
|
||||
break
|
||||
action = self.lexicon[m.index][1]
|
||||
if callable(action):
|
||||
self.match = match
|
||||
action = action(self, m.group())
|
||||
if action is not None:
|
||||
append(action)
|
||||
i = j
|
||||
return result, string[i:]
|
||||
|
|
|
@ -208,7 +208,7 @@ def _compile(code, pattern, flags):
|
|||
else:
|
||||
emit(OPCODES[op])
|
||||
emit(av-1)
|
||||
elif op is MARK:
|
||||
elif op in (MARK, INDEX):
|
||||
emit(OPCODES[op])
|
||||
emit(av)
|
||||
else:
|
||||
|
|
|
@ -33,6 +33,7 @@ GROUP = "group"
|
|||
GROUP_IGNORE = "group_ignore"
|
||||
IN = "in"
|
||||
IN_IGNORE = "in_ignore"
|
||||
INDEX = "index"
|
||||
INFO = "info"
|
||||
JUMP = "jump"
|
||||
LITERAL = "literal"
|
||||
|
@ -90,6 +91,7 @@ OPCODES = [
|
|||
CATEGORY,
|
||||
CHARSET,
|
||||
GROUP, GROUP_IGNORE,
|
||||
INDEX,
|
||||
IN, IN_IGNORE,
|
||||
INFO,
|
||||
JUMP,
|
||||
|
|
|
@ -451,6 +451,23 @@ def _parse(source, state):
|
|||
if gid is None:
|
||||
raise error, "unknown group name"
|
||||
subpattern.append((GROUP, gid))
|
||||
elif source.match("#"):
|
||||
index = ""
|
||||
while 1:
|
||||
char = source.get()
|
||||
if char is None:
|
||||
raise error, "unterminated index"
|
||||
if char == ")":
|
||||
break
|
||||
index = index + char
|
||||
try:
|
||||
index = int(index)
|
||||
if index < 0 or index > MAXREPEAT:
|
||||
raise ValueError
|
||||
except ValueError:
|
||||
raise error, "illegal index"
|
||||
subpattern.append((INDEX, index))
|
||||
continue
|
||||
else:
|
||||
char = source.get()
|
||||
if char is None:
|
||||
|
|
|
@ -21,6 +21,7 @@
|
|||
* 00-06-29 fl fixed split, added more scanner features (0.9.2)
|
||||
* 00-06-30 fl added fast search optimization (0.9.3)
|
||||
* 00-06-30 fl added assert (lookahead) primitives, etc (0.9.4)
|
||||
* 00-07-02 fl added charset optimizations, etc (0.9.5)
|
||||
*
|
||||
* Copyright (c) 1997-2000 by Secret Labs AB. All rights reserved.
|
||||
*
|
||||
|
@ -31,7 +32,7 @@
|
|||
|
||||
#ifndef SRE_RECURSIVE
|
||||
|
||||
char copyright[] = " SRE 0.9.4 Copyright (c) 1997-2000 by Secret Labs AB ";
|
||||
char copyright[] = " SRE 0.9.5 Copyright (c) 1997-2000 by Secret Labs AB ";
|
||||
|
||||
#include "Python.h"
|
||||
|
||||
|
@ -587,6 +588,14 @@ SRE_MATCH(SRE_STATE* state, SRE_CODE* pattern)
|
|||
pattern++;
|
||||
break;
|
||||
|
||||
case SRE_OP_INDEX:
|
||||
/* set index */
|
||||
/* args: <index> */
|
||||
TRACE(("%8d: set index %d\n", PTR(ptr), pattern[0]));
|
||||
state->index = pattern[0];
|
||||
pattern++;
|
||||
break;
|
||||
|
||||
case SRE_OP_JUMP:
|
||||
case SRE_OP_INFO:
|
||||
/* jump forward */
|
||||
|
@ -810,7 +819,7 @@ SRE_MATCH(SRE_STATE* state, SRE_CODE* pattern)
|
|||
/* match maximum number of items, pushing alternate end
|
||||
points to the stack */
|
||||
|
||||
while (pattern[2] == 32767 || count < (int) pattern[2]) {
|
||||
while (pattern[2] == 65535 || count < (int) pattern[2]) {
|
||||
state->stackbase = stack;
|
||||
i = SRE_MATCH(state, pattern + 3);
|
||||
state->stackbase = stackbase; /* rewind */
|
||||
|
@ -980,10 +989,12 @@ SRE_SEARCH(SRE_STATE* state, SRE_CODE* pattern)
|
|||
}
|
||||
|
||||
if (flags & SRE_INFO_PREFIX) {
|
||||
/* pattern starts with a known prefix */
|
||||
prefix_len = pattern[5];
|
||||
prefix = pattern + 6;
|
||||
overlap = prefix + prefix_len - 1;
|
||||
} else if (flags & SRE_INFO_CHARSET)
|
||||
/* pattern starts with a character from a known set */
|
||||
charset = pattern + 5;
|
||||
|
||||
pattern += 1 + pattern[1];
|
||||
|
@ -1042,7 +1053,6 @@ SRE_SEARCH(SRE_STATE* state, SRE_CODE* pattern)
|
|||
if (status != 0)
|
||||
break;
|
||||
}
|
||||
#if 0
|
||||
} else if (charset) {
|
||||
/* pattern starts with a character from a known set */
|
||||
for (;;) {
|
||||
|
@ -1057,7 +1067,6 @@ SRE_SEARCH(SRE_STATE* state, SRE_CODE* pattern)
|
|||
if (status != 0)
|
||||
break;
|
||||
}
|
||||
#endif
|
||||
} else
|
||||
/* general case */
|
||||
while (ptr <= end) {
|
||||
|
@ -1204,6 +1213,8 @@ state_init(SRE_STATE* state, PatternObject* pattern, PyObject* args)
|
|||
for (i = 0; i < SRE_MARK_SIZE; i++)
|
||||
state->mark[i] = NULL;
|
||||
|
||||
state->index = -1;
|
||||
|
||||
state->stack = NULL;
|
||||
state->stackbase = 0;
|
||||
state->stacksize = 0;
|
||||
|
@ -1286,6 +1297,8 @@ pattern_new_match(PatternObject* pattern, SRE_STATE* state,
|
|||
} else
|
||||
match->mark[j+2] = match->mark[j+3] = -1; /* undefined */
|
||||
|
||||
match->index = state->index;
|
||||
|
||||
return (PyObject*) match;
|
||||
|
||||
} else if (status < 0) {
|
||||
|
@ -1887,6 +1900,15 @@ match_getattr(MatchObject* self, char* name)
|
|||
if (!strcmp(name, "endpos"))
|
||||
return Py_BuildValue("i", 0); /* FIXME */
|
||||
|
||||
if (!strcmp(name, "index")) {
|
||||
/* experimental */
|
||||
if (self->index < 0) {
|
||||
Py_INCREF(Py_None);
|
||||
return Py_None;
|
||||
} else
|
||||
return Py_BuildValue("i", self->index);
|
||||
}
|
||||
|
||||
PyErr_SetString(PyExc_AttributeError, name);
|
||||
return NULL;
|
||||
}
|
||||
|
|
|
@ -33,6 +33,7 @@ typedef struct {
|
|||
PyObject_HEAD
|
||||
PyObject* string; /* link to the target string */
|
||||
PatternObject* pattern; /* link to the regex (pattern) object */
|
||||
int index; /* last index marker seen by the engine (-1 if none) */
|
||||
int groups; /* number of groups (start/end marks) */
|
||||
int mark[2];
|
||||
} MatchObject;
|
||||
|
@ -57,6 +58,7 @@ typedef struct {
|
|||
/* character size */
|
||||
int charsize;
|
||||
/* registers */
|
||||
int index;
|
||||
int lastmark;
|
||||
void* mark[SRE_MARK_SIZE];
|
||||
/* backtracking stack */
|
||||
|
|
|
@ -23,21 +23,22 @@
|
|||
#define SRE_OP_CHARSET 9
|
||||
#define SRE_OP_GROUP 10
|
||||
#define SRE_OP_GROUP_IGNORE 11
|
||||
#define SRE_OP_IN 12
|
||||
#define SRE_OP_IN_IGNORE 13
|
||||
#define SRE_OP_INFO 14
|
||||
#define SRE_OP_JUMP 15
|
||||
#define SRE_OP_LITERAL 16
|
||||
#define SRE_OP_LITERAL_IGNORE 17
|
||||
#define SRE_OP_MARK 18
|
||||
#define SRE_OP_MAX_REPEAT 19
|
||||
#define SRE_OP_MAX_REPEAT_ONE 20
|
||||
#define SRE_OP_MIN_REPEAT 21
|
||||
#define SRE_OP_NOT_LITERAL 22
|
||||
#define SRE_OP_NOT_LITERAL_IGNORE 23
|
||||
#define SRE_OP_NEGATE 24
|
||||
#define SRE_OP_RANGE 25
|
||||
#define SRE_OP_REPEAT 26
|
||||
#define SRE_OP_INDEX 12
|
||||
#define SRE_OP_IN 13
|
||||
#define SRE_OP_IN_IGNORE 14
|
||||
#define SRE_OP_INFO 15
|
||||
#define SRE_OP_JUMP 16
|
||||
#define SRE_OP_LITERAL 17
|
||||
#define SRE_OP_LITERAL_IGNORE 18
|
||||
#define SRE_OP_MARK 19
|
||||
#define SRE_OP_MAX_REPEAT 20
|
||||
#define SRE_OP_MAX_REPEAT_ONE 21
|
||||
#define SRE_OP_MIN_REPEAT 22
|
||||
#define SRE_OP_NOT_LITERAL 23
|
||||
#define SRE_OP_NOT_LITERAL_IGNORE 24
|
||||
#define SRE_OP_NEGATE 25
|
||||
#define SRE_OP_RANGE 26
|
||||
#define SRE_OP_REPEAT 27
|
||||
#define SRE_AT_BEGINNING 0
|
||||
#define SRE_AT_BEGINNING_LINE 1
|
||||
#define SRE_AT_BOUNDARY 2
|
||||
|
|
Loading…
Reference in New Issue