Re: [PATCH] preg_match(_all) support for capturing offsets

I will take a look at this soon, thanks. On Thu, 06 Jun 2002, David Brown wrote: > Hi Andrei, all: > > (This is a re-send of a previous message that received no replies; my > apologies if you've already seen/considered it) > > In a previous patch > (http://news.php.net/article.php?group=php.dev&article=84281), support > was added to preg_split for capturing offsets along with matches. The > attached patch adds similar support to preg_match and preg_match_all via > a new PREG_MATCH_OFFSET_CAPTURE flag. > > The code handles capturing offsets for both subpattern matches and whole > pattern matches, using the previously-added add_offset_pair helper function. > > The flag is a new fourth (and optional) parameter for preg_match, and > are or'd into the existing 'order' parameter for preg_match_all, above > PREG_SET_ORDER and PREG_PATTERN_ORDER. > > The patch below is diffed against the CVS head - humbly sumbitted for > application, rejection, suggestions, or extensive flaming. :) > > > Thanks in advance, > > - Dave > dave@codewhore.org > > > --- ext/pcre/php_pcre.c.orig Tue Jun 4 13:02:50 2002 > +++ ext/pcre/php_pcre.c Tue Jun 4 13:12:10 2002 > @@ -35,7 +35,9 @@ > #define PREG_PATTERN_ORDER 0 > #define PREG_SET_ORDER 1 > > -#define PREG_SPLIT_NO_EMPTY (1<<0) > +#define PREG_MATCH_OFFSET_CAPTURE (1<<2) > + > +#define PREG_SPLIT_NO_EMPTY (1<<0) > #define PREG_SPLIT_DELIM_CAPTURE (1<<1) > #define PREG_SPLIT_OFFSET_CAPTURE (1<<2) > > @@ -99,6 +101,7 @@ > > REGISTER_LONG_CONSTANT("PREG_PATTERN_ORDER", PREG_PATTERN_ORDER, CONST_CS | > CONST_PERSISTENT); > REGISTER_LONG_CONSTANT("PREG_SET_ORDER", PREG_SET_ORDER, CONST_CS | > CONST_PERSISTENT); > + REGISTER_LONG_CONSTANT("PREG_MATCH_OFFSET_CAPTURE", PREG_MATCH_OFFSET_CAPTURE, > CONST_CS | CONST_PERSISTENT); > REGISTER_LONG_CONSTANT("PREG_SPLIT_NO_EMPTY", PREG_SPLIT_NO_EMPTY, CONST_CS | > CONST_PERSISTENT); > REGISTER_LONG_CONSTANT("PREG_SPLIT_DELIM_CAPTURE", PREG_SPLIT_DELIM_CAPTURE, > CONST_CS | CONST_PERSISTENT); > REGISTER_LONG_CONSTANT("PREG_SPLIT_OFFSET_CAPTURE", PREG_SPLIT_OFFSET_CAPTURE, > CONST_CS | CONST_PERSISTENT); > @@ -310,6 +313,24 @@ > } > /* }}} */ > > +/* {{{ add_offset_pair > + */ > +static inline void add_offset_pair(zval *result, char *str, int len, int offset) > +{ > + zval *match_pair; > + > + ALLOC_ZVAL(match_pair); > + array_init(match_pair); > + INIT_PZVAL(match_pair); > + > + /* Add (match, offset) to the return value */ > + add_next_index_stringl(match_pair, str, len, 1); > + add_next_index_long(match_pair, offset); > + > + zend_hash_next_index_insert(Z_ARRVAL_P(result), &match_pair, sizeof(zval *), NULL); > +} > +/* }}} */ > + > /* {{{ php_pcre_match > */ > static void php_pcre_match(INTERNAL_FUNCTION_PARAMETERS, int global) > @@ -335,6 +356,7 @@ > int matched; /* Has anything matched */ > int i; > int subpats_order_val = 0; /* Integer value of subpats_order */ > + int offset_capture = 0; /* If offsets should be captured */ > int g_notempty = 0; /* If the match should not be empty */ > const char **stringlist; /* Used to hold list of subpatterns */ > char *match; /* The current match */ > @@ -363,11 +385,17 @@ > > /* Make sure subpats_order is a number */ > convert_to_long_ex(subpats_order); > - subpats_order_val = Z_LVAL_PP(subpats_order); > - if (subpats_order_val < PREG_PATTERN_ORDER || > - subpats_order_val > PREG_SET_ORDER) { > - zend_error(E_WARNING, "Wrong value for parameter 4 in call to > preg_match_all()"); > - } > + offset_capture = (Z_LVAL_PP(subpats_order) & PREG_MATCH_OFFSET_CAPTURE); > + > + if (global) { > + subpats_order_val = (Z_LVAL_PP(subpats_order) & 1UL); > + > + if ((subpats_order_val < PREG_PATTERN_ORDER) || > + (subpats_order_val > PREG_SET_ORDER)) { > + zend_error(E_WARNING, "Wrong value for parameter 4 in call to > preg_match_all()"); > + } > + } > + > break; > > default: > @@ -442,8 +470,13 @@ > if (subpats_order_val == PREG_PATTERN_ORDER) { > /* For each subpattern, insert it into the appropriate array. */ > for (i = 0; i < count; i++) { > - add_next_index_stringl(match_sets[i], (char *)stringlist[i], > - offsets[(i<<1)+1] - offsets[i<<1], 1); > + if (offset_capture) { > + add_offset_pair(match_sets[i], (char *)stringlist[i], > + offsets[(i<<1)+1] - offsets[i<<1], offsets[i<<1]); > + } else { > + add_next_index_stringl(match_sets[i], (char *)stringlist[i], > + offsets[(i<<1)+1] - offsets[i<<1], 1); > + } > } > /* > * If the number of captured subpatterns on this run is > @@ -463,8 +496,13 @@ > > /* Add all the subpatterns to it */ > for (i = 0; i < count; i++) { > - add_next_index_stringl(result_set, (char *)stringlist[i], > - offsets[(i<<1)+1] - offsets[i<<1], 1); > + if (offset_capture) { > + add_offset_pair(result_set, (char *)stringlist[i], > + offsets[(i<<1)+1] - offsets[i<<1], offsets[i<<1]); > + } else { > + add_next_index_stringl(result_set, (char *)stringlist[i], > + offsets[(i<<1)+1] - offsets[i<<1], 1); > + } > } > /* And add it to the output array */ > zend_hash_next_index_insert(Z_ARRVAL_PP(subpats), &result_set, > @@ -474,8 +512,13 @@ > else { /* single pattern matching */ > /* For each subpattern, insert it into the subpatterns array. */ > for (i = 0; i < count; i++) { > - add_next_index_stringl((*subpats), (char *)stringlist[i], > - offsets[(i<<1)+1] - offsets[i<<1], 1); > + if (offset_capture) { > + add_offset_pair((*subpats), (char *)stringlist[i], > + offsets[(i<<1)+1] - offsets[i<<1], offsets[i<<1]); > + } else { > + add_next_index_stringl((*subpats), (char *)stringlist[i], > + offsets[(i<<1)+1] - offsets[i<<1], 1); > + } > } > } > > @@ -518,7 +561,7 @@ > } > /* }}} */ > > -/* {{{ proto int preg_match(string pattern, string subject [, array subpatterns]) > +/* {{{ proto int preg_match(string pattern, string subject [, array matches [, int flags]]) > Perform a Perl-style regular expression match */ > PHP_FUNCTION(preg_match) > { > @@ -1063,21 +1106,6 @@ > preg_replace_impl(INTERNAL_FUNCTION_PARAM_PASSTHRU, 1); > } > /* }}} */ > - > -static inline void add_offset_pair(zval *result, char *str, int len, int offset) > -{ > - zval *match_pair; > - > - ALLOC_ZVAL(match_pair); > - array_init(match_pair); > - INIT_PZVAL(match_pair); > - > - /* Add (match, offset) to the return value */ > - add_next_index_stringl(match_pair, str, len, 1); > - add_next_index_long(match_pair, offset); > - > - zend_hash_next_index_insert(Z_ARRVAL_P(result), &match_pair, sizeof(zval *), NULL); > -} > > /* {{{ proto array preg_split(string pattern, string subject [, int limit [, int flags]]) > Split string into an array using a perl-style regular expression as a delimiter */ > -Andrei http://www.gravitonic.com/ * DOS is, quite possibly, the worst text-adventure game ever. *