note 43476 added to ref.pdf

I've been looking for a way to extract plain text from PDF documents (needed to search for text inside 'em). Not being able to find one I wrote the needed functions myself. here you go folks. <?php function pdf2string ($sourceFile) { $textArray = array (); $objStart = 0; $fp = fopen ($sourceFile, 'rb'); $content = fread ($fp, filesize ($sourceFile)); fclose ($fp); $searchTagStart = chr(13).chr(10).'stream'; $searchTagStartLenght = strlen ($searchTagStart); while ((($objStart = strpos ($content, $searchTagStart, $objStart)) && ($objEnd = strpos ($content, 'endstream', $objStart+1)))) { $data = substr ($content, $objStart + $searchTagStartLenght + 2, $objEnd - ($objStart + $searchTagStartLenght) - 2); $data = @gzuncompress ($data); if ($data !== FALSE && strpos ($data, 'BT') !== FALSE && strpos ($data, 'ET') !== FALSE) { $textArray [] = ExtractText ($data); } $objStart = $objStart < $objEnd ? $objEnd : $objStart + 1; } return $textArray; } function ExtractText ($postScriptData) { while ((($textStart = strpos ($postScriptData, '(', $textStart)) && ($textEnd = strpos ($postScriptData, ')', $textStart + 1)) && substr ($postScriptData, $textEnd - 1) != '\\')) { $plainText .= substr ($postScriptData, $textStart + 1, $textEnd - $textStart - 1); if (substr ($postScriptData, $textEnd + 1, 1) == ']') //this adds quite some additional spaces between the words { $plainText .= ' '; } $textStart = $textStart < $textEnd ? $textEnd : $textStart + 1; } return stripslashes ($plainText); } ?> ---- Manual Page -- http://www.php.net/manual/en/ref.pdf.php Edit -- http://master.php.net/manage/user-notes.php?action=edit+43476 Delete -- http://master.php.net/manage/user-notes.php?action=delete+43476&report=yes Reject -- http://master.php.net/manage/user-notes.php?action=reject+43476&report=yes Search -- http://master.php.net/manage/user-notes.php