Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commit1fee1bf

Browse files
committed
Fix regex back-references that are directly quantified with *.
The syntax "\n*", that is a backref with a * quantifier directly appliedto it, has never worked correctly in Spencer's library. This has been anopen bug in the Tcl bug tracker since 2005:https://sourceforge.net/tracker/index.php?func=detail&aid=1115587&group_id=10894&atid=110894The core of the problem is in parseqatom(), which first changes "\n*" to"\n+|" and then applies repeat() to the NFA representing the backref atom.repeat() thinks that any arc leading into its "rp" argument is part of thesub-NFA to be repeated. Unfortunately, since parseqatom() already createdthe arc that was intended to represent the empty bypass around "\n+", thisarc gets moved too, so that it now leads into the state loop created byrepeat(). Thus, what was supposed to be an "empty" bypass gets turned intosomething that represents zero or more repetitions of the NFA representingthe backref atom. In the original example, in place of^([bc])\1*$we now have something that acts like^([bc])(\1+|[bc]*)$At runtime, the branch involving the actual backref fails, as it's supposedto, but then the other branch succeeds anyway.We could no doubt fix this by some rearrangement of the operations inparseqatom(), but that code is plenty ugly already, and what's more thewhole business of converting "x*" to "x+|" probably needs to go away to fixanother problem I'll mention in a moment. Instead, this patch suppressesthe *-conversion when the target is a simple backref atom, leaving the caseof m == 0 to be handled at runtime. This makes the patch in regcomp.c aone-liner, at the cost of having to tweak cbrdissect() a little. In theevent I went a bit further than that and rewrote cbrdissect() to check allthe string-length-related conditions before it starts comparing characters.It seems a bit stupid to possibly iterate through many copies of ann-character backreference, only to fail at the end because the targetstring's length isn't a multiple of n --- we could have found that outbefore starting. The existing coding could only be a win if integerdivision is hugely expensive compared to character comparison, but I don'tknow of any modern machine where that might be true.This does not fix all the problems with quantified back-references. Inparticular, the code is still broken for back-references that appear withina larger expression that is quantified (so that direct insertion of thequantification limits into the BACKREF node doesn't apply). I think fixingthat will take some major surgery on the NFA code, specifically introducingan explicit iteration node type instead of trying to transform iterationinto concatenation of modified regexps.Back-patch to all supported branches. In HEAD, also add a regression testcase for this. (It may seem a bit silly to create a regression test filefor just one test case; but I'm expecting that we will soon import a wholebunch of regex regression tests from Tcl, so might as well create theinfrastructure now.)
1 parentf559846 commit1fee1bf

File tree

2 files changed

+52
-29
lines changed

2 files changed

+52
-29
lines changed

‎src/backend/regex/regcomp.c‎

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1080,8 +1080,12 @@ parseqatom(struct vars * v,
10801080
NOERR();
10811081
}
10821082

1083-
/* it's quantifier time; first, turn x{0,...} into x{1,...}|empty */
1084-
if (m==0)
1083+
/*
1084+
* It's quantifier time. If the atom is just a BACKREF, we'll let it deal
1085+
* with quantifiers internally. Otherwise, the first step is to turn
1086+
* x{0,...} into x{1,...}|empty
1087+
*/
1088+
if (m==0&&atomtype!=BACKREF)
10851089
{
10861090
EMPTYARC(s2,atom->end);/* the bypass */
10871091
assert(PREF(qprefer)!=0);

‎src/backend/regex/regexec.c‎

Lines changed: 46 additions & 27 deletions
Original file line numberDiff line numberDiff line change
@@ -716,7 +716,7 @@ cdissect(struct vars * v,
716716
case'|':/* alternation */
717717
assert(t->left!=NULL);
718718
returncaltdissect(v,t,begin,end);
719-
case'b':/* backref -- shouldn't be calling us! */
719+
case'b':/* backreference */
720720
assert(t->left==NULL&&t->right==NULL);
721721
returncbrdissect(v,t,begin,end);
722722
case'.':/* concatenation */
@@ -973,12 +973,12 @@ cbrdissect(struct vars * v,
973973
chr*begin,/* beginning of relevant substring */
974974
chr*end)/* end of same */
975975
{
976-
inti;
977976
intn=t->subno;
978-
size_tlen;
979-
chr*paren;
977+
size_tnumreps;
978+
size_ttlen;
979+
size_tbrlen;
980+
chr*brstring;
980981
chr*p;
981-
chr*stop;
982982
intmin=t->min;
983983
intmax=t->max;
984984

@@ -989,46 +989,65 @@ cbrdissect(struct vars * v,
989989

990990
MDEBUG(("cbackref n%d %d{%d-%d}\n",t->retry,n,min,max));
991991

992+
/* get the backreferenced string */
992993
if (v->pmatch[n].rm_so==-1)
993994
returnREG_NOMATCH;
994-
paren=v->start+v->pmatch[n].rm_so;
995-
len=v->pmatch[n].rm_eo-v->pmatch[n].rm_so;
995+
brstring=v->start+v->pmatch[n].rm_so;
996+
brlen=v->pmatch[n].rm_eo-v->pmatch[n].rm_so;
996997

997998
/* no room to maneuver -- retries are pointless */
998999
if (v->mem[t->retry])
9991000
returnREG_NOMATCH;
10001001
v->mem[t->retry]=1;
10011002

1002-
/* special-case zero-length string */
1003-
if (len==0)
1003+
/* special cases for zero-length strings */
1004+
if (brlen==0)
1005+
{
1006+
/*
1007+
* matches only if target is zero length, but any number of
1008+
* repetitions can be considered to be present
1009+
*/
1010+
if (begin==end&&min <=max)
1011+
{
1012+
MDEBUG(("cbackref matched trivially\n"));
1013+
returnREG_OKAY;
1014+
}
1015+
returnREG_NOMATCH;
1016+
}
1017+
if (begin==end)
10041018
{
1005-
if (begin==end)
1019+
/* matches only if zero repetitions are okay */
1020+
if (min==0)
1021+
{
1022+
MDEBUG(("cbackref matched trivially\n"));
10061023
returnREG_OKAY;
1024+
}
10071025
returnREG_NOMATCH;
10081026
}
10091027

1010-
/* and too-short string */
1011-
assert(end >=begin);
1012-
if ((size_t) (end-begin)<len)
1028+
/*
1029+
* check target length to see if it could possibly be an allowed number of
1030+
* repetitions of brstring
1031+
*/
1032+
assert(end>begin);
1033+
tlen=end-begin;
1034+
if (tlen %brlen!=0)
1035+
returnREG_NOMATCH;
1036+
numreps=tlen /brlen;
1037+
if (numreps<min|| (numreps>max&&max!=INFINITY))
10131038
returnREG_NOMATCH;
1014-
stop=end-len;
10151039

1016-
/*count occurrences */
1017-
i=0;
1018-
for (p=begin;p <=stop&& (i<max||max==INFINITY);p+=len)
1040+
/*okay, compare the actual string contents */
1041+
p=begin;
1042+
while (numreps-->0)
10191043
{
1020-
if ((*v->g->compare) (paren,p,len)!=0)
1021-
break;
1022-
i++;
1044+
if ((*v->g->compare) (brstring,p,brlen)!=0)
1045+
returnREG_NOMATCH;
1046+
p+=brlen;
10231047
}
1024-
MDEBUG(("cbackref found %d\n",i));
10251048

1026-
/* and sort it out */
1027-
if (p!=end)/* didn't consume all of it */
1028-
returnREG_NOMATCH;
1029-
if (min <=i&& (i <=max||max==INFINITY))
1030-
returnREG_OKAY;
1031-
returnREG_NOMATCH;/* out of range */
1049+
MDEBUG(("cbackref matched\n"));
1050+
returnREG_OKAY;
10321051
}
10331052

10341053
/*

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp