diff options
| author | Yves Orton <demerphq@gmail.com> | 2016-05-10 09:44:31 +0200 |
|---|---|---|
| committer | Yves Orton <demerphq@gmail.com> | 2016-05-10 09:51:20 +0200 |
| commit | da7cf1cc7cedc01f35ceb6724e8260c3b0ee0d12 (patch) | |
| tree | 91ca2477b746d3956427c607988642b77ef22855 /regcomp.c | |
| parent | 1bda7a749022793a1a7ec1719cdd3d5b12feba7a (diff) | |
| download | perl-da7cf1cc7cedc01f35ceb6724e8260c3b0ee0d12.tar.gz | |
fix #128109 - do not move RExC_open_parens[0] in reginsert
In d5a00e4af6b155495be31a35728b8fef8e671ebe I merged GOSUB and GOSTART,
part of which involved making RExC_open_parens[0] refer to the start of
the pattern, and RExC_close_parens[0] referring to the end of the pattern.
This tripped up in reginsert in a subtle way, the start of the pattern
cannot and should not move in reginsert(). Unlike a paren that might
be at the start of the pattern which should move when something is inserted
in front of it, the start is a fixed point and should never move.
This patches fixes this up, and adds an assert to check that reginsert()
is not called once study_chunk() starts, as reginsert() does not adjust
RExC_recurse.
This was noticed by hv while debugging [perl #128085], thanks hugo!
Diffstat (limited to 'regcomp.c')
| -rw-r--r-- | regcomp.c | 13 |
1 files changed, 11 insertions, 2 deletions
@@ -222,6 +222,7 @@ struct RExC_state_t { #endif bool seen_unfolded_sharp_s; bool strict; + bool study_started; }; #define RExC_flags (pRExC_state->flags) @@ -288,6 +289,7 @@ struct RExC_state_t { #define RExC_frame_last (pRExC_state->frame_last) #define RExC_frame_count (pRExC_state->frame_count) #define RExC_strict (pRExC_state->strict) +#define RExC_study_started (pRExC_state->study_started) /* Heuristic check on the complexity of the pattern: if TOO_NAUGHTY, we set * a flag to disable back-off on the fixed/floating substrings - if it's @@ -4102,6 +4104,7 @@ S_study_chunk(pTHX_ RExC_state_t *pRExC_state, regnode **scanp, GET_RE_DEBUG_FLAGS_DECL; PERL_ARGS_ASSERT_STUDY_CHUNK; + RExC_study_started= 1; if ( depth == 0 ) { @@ -6877,6 +6880,7 @@ Perl_re_op_compile(pTHX_ SV ** const patternp, int pat_count, RExC_contains_locale = 0; RExC_contains_i = 0; RExC_strict = cBOOL(pm_flags & RXf_PMf_STRICT); + RExC_study_started = 0; pRExC_state->runtime_code_qr = NULL; RExC_frame_head= NULL; RExC_frame_last= NULL; @@ -18235,7 +18239,9 @@ S_reginsert(pTHX_ RExC_state_t *pRExC_state, U8 op, regnode *opnd, U32 depth) RExC_size += size; return; } - + assert(!RExC_study_started); /* I believe we should never use reginsert once we have started + studying. If this is wrong then we need to adjust RExC_recurse + below like we do with RExC_open_parens/RExC_close_parens. */ src = RExC_emit; RExC_emit += size; dst = RExC_emit; @@ -18246,7 +18252,10 @@ S_reginsert(pTHX_ RExC_state_t *pRExC_state, U8 op, regnode *opnd, U32 depth) * iow it is 1 more than the number of parens seen in * the pattern so far. */ for ( paren=0 ; paren < RExC_npar ; paren++ ) { - if ( RExC_open_parens[paren] >= opnd ) { + /* note, RExC_open_parens[0] is the start of the + * regex, it can't move. RExC_close_parens[0] is the end + * of the regex, it *can* move. */ + if ( paren && RExC_open_parens[paren] >= opnd ) { /*DEBUG_PARSE_FMT("open"," - %d",size);*/ RExC_open_parens[paren] += size; } else { |