note 81247 added to function.preg-match-all

Here's a function to identical to preg_match_all with the offset flag enabled, except it allows you to search through data while ignoring other data that matches a certain pattern. An example use is to search through html data with all the tags removed, you can see which text is next to others, and get the matches of your search pattern in the original data before the tags were stripped. RETURNS: false on 0 matches found an array identical to default array returned with preg_match_all() with the PREG_OFFSET_CAPTURE flag enabled, except there is extra item in match array which gives the match including the ignored data ie: [0] match that doesn't include ignored data [1] offset of match in original data ($hay) [2] match that does include ignored data <?php function preg_match_ignore_pat($searchPat, $ignorePat, $hay) { $matches = preg_match_all($ignorePat, $hay, $out); if ($matches && !empty($out[0])) { $splitArr = preg_split($ignorePat, $hay, -1, PREG_SPLIT_OFFSET_CAPTURE); $splitArr2 = preg_split($ignorePat, $hay); $searchHay = implode('', $splitArr2); $findPhrase = preg_match_all($searchPat, $searchHay, $phraseOut, PREG_OFFSET_CAPTURE); //phrase was found if ($findPhrase && !empty($phraseOut[0])) { //make offArr $newOff = 0; foreach ($splitArr as $k => $pieceInfo) { $offArr[$newOff] = $pieceInfo[1]; $newOff = $newOff + strlen($pieceInfo[0]); } //find real offsets of matches of found phrase in haystack foreach ($phraseOut as $subKey => $subArr) { foreach ($subArr as $matchInfo) { //newMatchRealOff = closestRealOff + (newMatchNewOff - closestNewOff) //find real off, start of match $newOff_start = $matchInfo[1]; $x = $newOff_start + 1; do { $x--; } while(!array_key_exists($x, $offArr)); $realOff_start = $offArr[$x] + ($newOff_start - $x); //find real off, end of match $newOff_end = ($matchInfo[1] + strlen($matchInfo[0]))-1; $x = $newOff_end + 1; do { $x--; } while(!array_key_exists($x, $offArr)); $realOff_end = $offArr[$x] + ($newOff_end - $x); $len = ($realOff_end - $realOff_start) + 1; //out array $pOut[$subKey][] = array($matchInfo[0], $realOff_start, substr($hay, $realOff_start, $len)); } } return $pOut; } else { //phrase wasn't found return false; } } else { //the ignore data is not present in the haystack, so search through it normally with preg_match_all $matches = preg_match_all($searchPat, $hay, $out, PREG_OFFSET_CAPTURE); if ($matches && !empty($out[0])) { return $out; } else { return false; } } } #example use 1 echo '<pre>'; $ignoreDataPat = '~<[^>]+>~'; $searchPat = '~this\s*(?P<first>hello)\s*(?P<second>whatever)\s*man~i'; $hay = '<b>this</b> hello <span id="this"> what<html tag>ever </span> man whatever'; $arr = preg_match_ignore_pat($searchPat, $ignoreDataPat, $hay); print_r($arr); echo '</pre>'; */ ?> ---- Server IP: 209.41.74.194 Probable Submitter: 68.53.235.219 ---- Manual Page -- http://www.php.net/manual/en/function.preg-match-all.php Edit -- https://master.php.net/note/edit/81247 Del: integrated -- https://master.php.net/note/delete/81247/integrated Del: useless -- https://master.php.net/note/delete/81247/useless Del: bad code -- https://master.php.net/note/delete/81247/bad+code Del: spam -- https://master.php.net/note/delete/81247/spam Del: non-english -- https://master.php.net/note/delete/81247/non-english Del: in docs -- https://master.php.net/note/delete/81247/in+docs Del: other reasons-- https://master.php.net/note/delete/81247 Reject -- https://master.php.net/note/reject/81247 Search -- https://master.php.net/manage/user-notes.php