/**
* @access private
*/
protected static function pdf2text($filename)
{
if (!extension_loaded('zlib')) {
return '';
}
$pdf = new PDF2Text();
$pdf->setFilename($filename);
try {
$pdf->decodePDF();
} catch (Exception $e) {
return '';
}
$content = $pdf->output();
if ($content == '') {
// try with different multibyte setting
$pdf->setUnicode(true);
$pdf->decodePDF();
$content = $pdf->output();
}
return $content;
}
public function uploadfiles()
{
$data = array();
//$tid = (isset($_GET['tid'])?addslashes($_GET['tid']):die('no ID'));
$t = isset($_GET['t']) ? addslashes($_GET['t']) : die('no t');
$dc = new InputFileModel();
if (isset($_GET['files'])) {
$error = false;
$files = array();
$uploaddir = $dc->upload_location;
$arrSuc = array();
$arrSucAsli = array();
foreach ($_FILES as $file) {
$f = new InputFileModel();
$q = "INSERT INTO {$f->table_name} SET file_folder_id = '0',file_author = '" . Account::getMyID() . "'";
global $db;
$fid = $db->qid($q);
$f->getByID($fid);
if ($fid) {
$newname = $fid;
$f->file_url = basename($file['name']);
$ext = end(explode(".", $file['name']));
$f->file_ext = $ext;
$f->file_filename = $fid . "." . $ext;
$f->file_date = leap_mysqldate();
if (move_uploaded_file($file['tmp_name'], $uploaddir . $f->file_filename)) {
$files[] = $uploaddir . $file['name'];
$f->file_size = filesize($uploaddir . $f->file_filename);
if ($f->file_ext == "pdf") {
$a = new PDF2Text();
$a->setFilename($uploaddir . $f->file_filename);
$a->decodePDF();
$f->file_isi = preg_replace("/\r|\n/", " ", $a->output());
//the path to the PDF file
$strPDF = $uploaddir . $f->file_filename;
$thumb = $uploaddir . "thumbs/" . $fid . ".jpg";
exec("convert \"{$strPDF}[0]\" \"{$thumb}\"");
}
// if pdf
$arrSuc[] = $f->file_filename;
$arrSucAsli[] = "<div id='file_" . $fid . "_{$t}' class='mlt_item'>" . $f->file_url . " <i onclick=\"deleteFromList_{$t}('" . $f->file_filename . "');\" class='glyphicon glyphicon-remove'></i></div>";
$f->load = 1;
$f->save();
if (isset($_SESSION['target_id']['obj'])) {
$target = get_class($_SESSION['target_id']['obj']);
} else {
$target = "inputfile_unknown";
}
PortalFileLogger::save2log($uploaddir . $f->file_filename, $target, $f->file_url);
} else {
$error = true;
}
}
}
$data = $error ? array('error' => 'There was an error uploading your files') : array('files' => $files, 'ftext' => implode(",", $arrSuc), 'ftextAsli' => implode(" ", $arrSucAsli));
} else {
$data = array('success' => 'Form was submitted', 'formData' => $_POST);
}
echo json_encode($data);
}
private function pdfToText($filename)
{
//The PDF2Text class is HUGE. Magical black box. See file for citations
require_once "class.pdf2text.php";
$a = new PDF2Text();
$a->setFilename($filename);
$a->decodePDF();
return $a->output();
}
protected function execute(array $arguments = array(), array $options = array())
{
$file = $arguments['pdf-file'];
$this->logLine(sprintf('Extracting text from pdf file: %s', $file), nbLogger::COMMENT);
$pdf2text = new PDF2Text();
$pdf2text->setFilename($file);
$pdf2text->setUnicode(isset($options['unicode']));
$pdf2text->decodePDF();
$output = $pdf2text->output();
file_put_contents(sprintf('%s.txt', $file), $output);
$this->logLine('Text extracted!', nbLogger::COMMENT);
}
/**
* @access private
*/
protected static function pdf2text($filename)
{
$pdf = new PDF2Text();
$pdf->setFilename($filename);
$pdf->decodePDF();
$content = $pdf->output();
if ($content == '') {
// try with different multibyte setting
$pdf->setUnicode(true);
$pdf->decodePDF();
$content = $pdf->output();
}
return $content;
}
require_once "../../conn/connect.php";
$id = "";
if (isset($_GET['id'])) {
$id = $_GET['id'];
}
$sql = " SELECT * \n\t\t\t FROM DOCUMENTO D\n\t\t\t INNER JOIN TIPO T ON (D.TIPO_ID = T.TIPO_ID)\n\t\t\t INNER JOIN DEPARTAMENTO DE ON (D.DEPA_ID = DE.DEPA_ID)\n\t\t\t WHERE DOCU_ID = {$id} ";
$params = array();
$options = array("Scrollable" => SQLSRV_CURSOR_KEYSET);
$resultado = sqlsrv_query($conn, $sql, $params, $options);
$fila = sqlsrv_fetch_object($resultado);
$total = sqlsrv_num_rows($resultado);
//si es pdf
if ($fila->TIPO_ID == 1) {
require_once "../../lib/pdf2text.php";
$ruta = $fila->DOCU_LINK;
$a = new PDF2Text();
$a->setFilename($ruta);
$a->decodePDF();
$contentIndexed .= $a->output() . "\n\n";
$contentIndexed = ereg_replace(chr(12), "\r\n{new_page}\r\n", ereg_replace("\n", "\r\n", $contentIndexed));
// Enumeramos los patrones por el número de página que corresponde.
$arrContent = explode("\r\n{new_page}\r\n", $contentIndexed);
$arrayPaginas = $arrContent;
// Lo guardamos porque luego lo usaremos para guardar el archivo o en base de datos.
$contentIndexed2 = "{1}";
$xCount = 2;
foreach ($arrContent as $page) {
$contentIndexed2 .= trim($page) . "\r\n{" . $xCount . "}\r\n";
$xCount++;
}
$contentIndexed = $contentIndexed2;
public function uploadfiles()
{
$data = array();
$tid = isset($_GET['tid']) ? addslashes($_GET['tid']) : die('no ID');
$t = isset($_GET['t']) ? addslashes($_GET['t']) : die('no t');
$dc = new DocumentsPortal();
if (isset($_GET['files'])) {
$error_size = 0;
$error = false;
$files = array();
$uploaddir = $dc->upload_location;
foreach ($_FILES as $file) {
$f = new DocumentsPortal();
$q = "INSERT INTO {$f->table_name} SET file_folder_id = '{$tid}',file_author = '" . Account::getMyID() . "'";
global $db;
$fid = $db->qid($q);
$f->getByID($fid);
if ($fid) {
$newname = $fid;
$f->file_url = basename($file['name']);
$ext = end(explode(".", $file['name']));
$f->file_ext = $ext;
$f->file_filename = $fid . "." . $ext;
$f->file_date = leap_mysqldate();
// if pdf
//cek size
$size_awal = $file['size'];
if (move_uploaded_file($file['tmp_name'], $uploaddir . $f->file_filename)) {
$files[] = $uploaddir . $file['name'];
$f->file_size = filesize($uploaddir . $f->file_filename);
//size akhir
$size_akhir = $f->file_size;
//cek apakah tengah2 gagal
if ($size_awal != $size_akhir) {
//hapus file corrupt
unlink($uploaddir . $f->file_filename);
//delete file corrupt di db
$f->delete($fid);
$error = true;
$error_size = 1;
} else {
if ($f->file_ext == "pdf") {
$a = new PDF2Text();
$a->setFilename($uploaddir . $f->file_filename);
$a->decodePDF();
$f->file_isi = preg_replace("/\r|\n/", " ", $a->output());
//the path to the PDF file
$strPDF = $uploaddir . $f->file_filename;
$thumb = $uploaddir . "thumbs/" . $fid . ".jpg";
putenv("PATH=/usr/local/bin:/usr/bin:/bin");
putenv("MAGICK_TEMPDIR=/tmp");
exec("convert \"{$strPDF}[0]\" \"{$thumb}\"");
}
$f->load = 1;
$f->save();
//log
BLogger::addLog("file_id = {$fid}, filename = " . $f->file_url, "upload_file");
}
//else cek size
} else {
$error = true;
$f->delete($fid);
}
}
}
$data = $error ? array('error' => 'There was an error uploading your files') : array('files' => $files);
} else {
$data = array('success' => 'Form was submitted', 'formData' => $_POST);
}
if ($error_size) {
$data['err_size'] = 1;
}
//$data['fil'] = $_FILES;
echo json_encode($data);
}
$entries = @rar_list($rar_file);
foreach ($entries as $entry) {
$sDta .= $entry->getName() . "\\r\\n";
}
// getName | getPackedSize | getUnpackedSize
@rar_close($rar_file);
$sData = '"type":"archive","text":"' . $sDta . ' "';
$sMsg .= "contentsSucces";
} else {
$sMsg .= "contentsFail";
}
}
} else {
if ($sExt == "pdf") {
include 'class.pdf2text.php';
$oPdf = new PDF2Text();
$oPdf->setFilename($sSFile);
$oPdf->decodePDF();
$sCnt = str_replace(array("\n", "\r", "\t"), array("\\n", "\\n", ""), substr($oPdf->output(), 0, PREVIEW_BYTES));
$sData = '"type":"ascii","text":"' . $sCnt . ' "';
$sMsg .= "contentsSucces";
} else {
if ($sExt == "doc") {
//////////////////////////////
// does not seem to be possible
//////////////////////////////
} else {
$oHnd = fopen($sSFile, "r");
$sCnt = preg_replace(array("/\n/", "/\r/", "/\t/"), array("\\n", "\\r", "\\t"), addslashes(fread($oHnd, 600)));
fclose($oHnd);
$sData = '"type":"ascii","text":"' . $sCnt . '"';
public function save(Doctrine_Connection $conn = null)
{
if ($this->isNew()) {
$this->changeUri();
if ($this->getMimeType() == 'application/pdf') {
$pdf = new PDF2Text();
$pdf->setFilename($this->getFullURI());
$content = '';
try {
$pdf->decodePDF();
$content = $pdf->output();
if ($content == '') {
// try with different multibyte setting
$pdf->setUnicode(true);
$pdf->decodePDF();
$content = $pdf->output();
}
} catch (Exception $e) {
}
if ($content != '') {
$this->setExtractedInfo(utf8_encode($content));
}
}
if ($this->getMimeType() == 'text/plain') {
$content = file_get_contents($this->getFullURI());
$this->setExtractedInfo(utf8_encode($content));
}
}
parent::save($conn);
}
/**
* Read PDf content
*
* @param string $file_name
* @return string
*/
public static function readPdfFile($file_name)
{
$a = new PDF2Text();
$a->setFilename(self::TEMP_FOLDER . $file_name);
$a->decodePDF();
return $a->output();
}
// Host name
$username = "";
// Mysql username
$password = "";
// Mysql password
$db_name = "";
// Database name
$tbl_name = "";
// Table name
$file_name = $_FILES['pdf']['name'];
$filename = explode(".", $file_name);
$column_name = $filename[0];
ini_set('max_execution_time', 300);
include 'pdf2text.php';
include 'stem_code.php';
$a = new PDF2Text();
$a->setFilename($file_name);
$a->decodePDF();
$stringput = $a->output();
$stringput = strtolower($stringput);
$allword_count = explode(" ", $stringput);
$wordarray = array();
$wordarrays = array();
foreach ($allword_count as $key => $val) {
array_push($wordarrays, $val);
}
/*Stemming Code*/
foreach ($wordarrays as $key => $word) {
$stem = PorterStemmer::Stem($word);
array_push($wordarray, $stem);
}
function evt__cuadro__procesar($datos)
{
//$this->dep('datos')->tabla('norma')->cargar($datos);
//$datos2=$this->dep('datos')->tabla('norma')->get();
//$fp_imagen = $this->dep('datos')->tabla('norma')->get_blob('pdf');
$a = new PDF2Text();
$path = $_SERVER['DOCUMENT_ROOT'] . "/68.pdf";
$a->setFilename($path);
$a->decodePDF();
$texto = $a->output();
// $z=strlen($texto);
$prueba = var_export($texto, true) . PHP_EOL;
// $prueba=str_replace(".","",$prueba);
// $prueba=str_replace(":","",$prueba);
// $prueba=str_replace('\"',"",$prueba);
// $prueba=str_replace('ó',"",$prueba);
$buscar = array('á', 'é', 'í', 'ó', 'ú', 'ñ', 'ü');
$remplzr = array('a', 'e', 'i', 'o', 'u', 'n', 'u');
$prueba2 = str_replace($buscar, $remplzr, $prueba);
//echo (substr($prueba2, 1000,2000));exit();
$buscar = array('/[^A-z0-9-<>]/', '/[-]+/', '/<[^>]*>/');
//$buscar = array('/[a-zA-Z0-9]/', '/[-]+/', '/<[^>]*>/');
$remplzr = array(' ', '-', '');
$prueba2 = preg_replace($buscar, $remplzr, $prueba);
echo substr($prueba2, 0, 1000);
exit;
echo substr($prueba3, 0, 1000);
exit;
//$prueba=str_replace('\á',"a",$prueba);
//$prueba=str_replace('ó',"o",$prueba);
// $a = array('.','á','ó');
// $b = array('','a','o');
// echo str_replace($a,$b,$prueba) ;
//$prueba=ereg_replace("[óòôõºö]","o",$prueba);
echo substr($prueba3, 1000, 2000);
exit;
//$sql="update norma set palabras_clave='".$prueba."' where id_norma=211";
print_r($sql);
toba::db('designa')->consultar($sql);
//print_r($z);exit();
$z = strlen($texto);
//echo (substr($texto,0,10));
//echo strrchr($texto,"a");
//exit;
print_r($z);
exit;
//$sql="update norma set palabras_clave='".$a->output()."' where id_norma=211";
//toba::db('designa')->consultar($sql);
$texto2 = str_replace("ó", "o", $texto);
exit;
print_r($z);
exit;
$texto = str_replace("\\'", "", $texto);
//eliminamos las comillas simples
$texto = str_replace('\\"', "", $texto);
//eliminamos las comillas dobles
$texto = str_replace('\\“', "", $texto);
$texto2 = str_replace("ó", "o", $texto);
$texto = str_replace(array('á', 'à', 'ä', 'â', 'ª', 'Á', 'À', 'Â', 'Ä'), array('a', 'a', 'a', 'a', 'a', 'A', 'A', 'A', 'A'), $texto);
$texto = str_replace(array('ó', 'ò', 'ö', 'ô', 'Ó', 'Ò', 'Ö', 'Ô'), array('o', 'o', 'o', 'o', 'O', 'O', 'O', 'O'), $texto);
if (isset($fp_imagen)) {
$temp_nombre = md5(uniqid(time())) . '.pdf';
$temp_archivo = toba::proyecto()->get_www_temp($temp_nombre);
$temp_fp = fopen($temp_archivo['path'], 'w');
stream_copy_to_stream($fp_imagen, $temp_fp);
$a = new PDF2Text();
}
}
public function uploadfiles()
{
//apakah ada file
$adafile = isset($_GET['adafile']) ? $_GET['adafile'] : '';
//cek if ada file
if ($adafile) {
$if = new InputFileModel();
$uploadpath = $if->upload_location;
if (file_exists($uploadpath . $adafile)) {
//delete old file
if (unlink($uploadpath . $adafile)) {
$arrf = $if->getWhere("file_filename = '{$adafile}' LIMIT 0,1");
if (count($arrf) > 0) {
$if->delete($arrf[0]->file_id);
}
//delete from log
PortalFileLogger::deleteFileLog($uploadpath . $adafile);
/*if(file_exists(_PHOTOPATH.'thumbnail/' . $adafile))
{
//delete old thumb file
unlink(_PHOTOPATH.'thumbnail/' . $adafile);
}*/
}
}
}
$data = array();
//$tid = (isset($_GET['tid'])?addslashes($_GET['tid']):die('no ID'));
$t = isset($_GET['t']) ? addslashes($_GET['t']) : die('no t');
$data['files'] = $_GET['files'];
$data['bool'] = 0;
$dc = new InputFileModel();
if (isset($_GET['files'])) {
$error = false;
$files = array();
$uploaddir = $dc->upload_location;
foreach ($_FILES as $file) {
$f = new InputFileModel();
$q = "INSERT INTO {$f->table_name} SET file_folder_id = '0',file_author = '" . Account::getMyID() . "'";
global $db;
$fid = $db->qid($q);
$f->getByID($fid);
if ($fid) {
$newname = $fid;
$f->file_url = basename($file['name']);
$ext = end(explode(".", $file['name']));
$f->file_ext = $ext;
$f->file_filename = $fid . "." . $ext;
$f->file_date = leap_mysqldate();
// if pdf
if (move_uploaded_file($file['tmp_name'], $uploaddir . $f->file_filename)) {
$files[] = $uploaddir . $file['name'];
$f->file_size = filesize($uploaddir . $f->file_filename);
if ($f->file_ext == "pdf") {
$a = new PDF2Text();
$a->setFilename($uploaddir . $f->file_filename);
$a->decodePDF();
$f->file_isi = preg_replace("/\r|\n/", " ", $a->output());
//the path to the PDF file
$strPDF = $uploaddir . $f->file_filename;
$thumb = $uploaddir . "thumbs/" . $fid . ".jpg";
exec("convert \"{$strPDF}[0]\" \"{$thumb}\"");
}
$f->load = 1;
$data['bool'] = $f->save();
$data['isImage'] = Leap\View\InputFile::isImage($f->file_filename);
$data['filename'] = $f->file_filename;
if (isset($_SESSION['target_id']['obj'])) {
$target = get_class($_SESSION['target_id']['obj']);
} else {
$target = "inputfile_unknown";
}
PortalFileLogger::save2log($uploaddir . $f->file_filename, $target, $f->file_url);
die(json_encode($data));
} else {
$error = true;
}
}
}
$data = $error ? array('error' => 'There was an error uploading your files') : array('files' => $files);
} else {
$data = array('success' => 'Form was submitted', 'formData' => $_POST);
}
echo json_encode($data);
}
/**
* Index posts stored in $this->unindexedPosts
*
* @since 1.0
*/
function index()
{
global $wp_filesystem, $searchwp;
$this->check_for_parallel_indexer();
if (is_array($this->unindexedPosts) && count($this->unindexedPosts)) {
do_action('searchwp_indexer_pre_chunk', $this->unindexedPosts);
// all of the IDs to index have not been indexed, proceed with indexing them
while (($unindexedPost = current($this->unindexedPosts)) !== false) {
$this->setPost($unindexedPost);
// log the attempt
$count = get_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'attempts', true);
if ($count == false) {
$count = 0;
} else {
$count = intval($count);
}
$count++;
// increment our counter to prevent the indexer getting stuck on a gigantic PDF
update_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'attempts', $count);
do_action('searchwp_log', 'Attempt ' . $count . ' at indexing ' . $this->post->ID);
// if we breached the maximum number of attempts, flag it to skip
$this->maxAttemptsToIndex = absint(apply_filters('searchwp_max_index_attempts', $this->maxAttemptsToIndex));
if (intval($count) > $this->maxAttemptsToIndex) {
do_action('searchwp_log', 'Too many indexing attempts on ' . $this->post->ID . ' (' . $this->maxAttemptsToIndex . ') - skipping');
// flag it to be skipped
update_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'skip', true);
} else {
// check to see if we're running a second pass on terms
$termCache = get_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'terms', true);
if (!is_array($termCache)) {
do_action('searchwp_index_post', $this->post);
// if it's an attachment, we want the permalink
$slug = $this->post->post_type == 'attachment' ? str_replace(get_bloginfo('wpurl'), '', get_permalink($this->post->ID)) : '';
// we allow users to override the extracted content from documents, if they have done so this flag is set
$skipDocProcessing = get_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'skip_doc_processing', true);
$omitDocProcessing = apply_filters('searchwp_omit_document_processing', false);
if (!$skipDocProcessing && !$omitDocProcessing) {
// if it's a PDF we need to populate our Custom Field with it's content
if ($this->post->post_mime_type == 'application/pdf') {
// grab the filename of the PDF
$filename = get_attached_file($this->post->ID);
// allow for external PDF content extraction
$pdfContent = apply_filters('searchwp_external_pdf_processing', '', $filename, $this->post->ID);
// only try to extract content if the external processing has not provided the PDF content we're looking for
if (empty($pdfContent)) {
// PdfParser runs only on 5.3+ but SearchWP runs on 5.2+
if (version_compare(PHP_VERSION, '5.3', '>=')) {
include_once $searchwp->dir . '/vendor/pdfparser-bootloader.php';
}
// a wrapper class was conditionally included if we're running PHP 5.3+ so let's try that
if (class_exists('SearchWP_PdfParser')) {
// try PdfParser first
$parser = new SearchWP_PdfParser();
$parser = $parser->init();
$pdf = $parser->parseFile($filename);
$text = $pdf->getText();
$pdfContent = trim(str_replace("\n", " ", $text));
}
// try PDF2Text
if (empty($pdfContent)) {
if (!class_exists('PDF2Text')) {
include_once $searchwp->dir . '/includes/class.pdf2text.php';
}
$pdfParser = new PDF2Text();
$pdfParser->setFilename($filename);
$pdfParser->decodePDF();
$pdfContent = $pdfParser->output();
$pdfContent = trim(str_replace("\n", " ", $pdfContent));
}
// check to see if the first pass produced nothing or concatenated strings
$fullContentLength = strlen($pdfContent);
$numberOfSpaces = substr_count($pdfContent, ' ');
if (empty($pdfContent) || $numberOfSpaces / $fullContentLength * 100 < 10) {
WP_Filesystem();
$filecontent = $wp_filesystem->exists($filename) ? $wp_filesystem->get_contents($filename) : '';
if (false != strpos($filecontent, 'trailer')) {
if (!class_exists('pdf_readstream')) {
include_once $searchwp->dir . '/includes/class.pdfreadstream.php';
}
$pdfContent = '';
$pdf = new pdf(get_attached_file($this->post->ID));
$pages = $pdf->get_pages();
if (!empty($pages)) {
while (list($nr, $page) = each($pages)) {
$pdfContent .= $page->get_text();
}
}
} else {
// empty out the content so wacky concatenations are not indexed
$pdfContent = '';
// flag it for further review
update_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'review', true);
update_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'skip', true);
}
}
}
$pdfContent = trim($pdfContent);
if (!empty($pdfContent)) {
$pdfContent = sanitize_text_field($pdfContent);
delete_post_meta($this->post->ID, SEARCHWP_PREFIX . 'content');
update_post_meta($this->post->ID, SEARCHWP_PREFIX . 'content', $pdfContent);
}
} elseif ($this->post->post_mime_type == 'text/plain') {
// if it's plain text, index it's content
WP_Filesystem();
$filename = get_attached_file($this->post->ID);
$textContent = $wp_filesystem->exists($filename) ? $wp_filesystem->get_contents($filename) : '';
$textContent = str_replace("\n", " ", $textContent);
if (!empty($textContent)) {
$textContent = sanitize_text_field($textContent);
update_post_meta($this->post->ID, SEARCHWP_PREFIX . 'content', $textContent);
}
} else {
// all other file types
}
}
$postTerms = array();
$postTerms['title'] = $this->indexTitle();
$postTerms['slug'] = $this->indexSlug(str_replace('/', ' ', $slug));
$postTerms['content'] = $this->indexContent();
$postTerms['excerpt'] = $this->indexExcerpt();
if (apply_filters('searchwp_index_comments', true)) {
$postTerms['comments'] = $this->indexComments();
}
// index taxonomies
$taxonomies = get_object_taxonomies($this->post->post_type);
if (!empty($taxonomies)) {
while (($taxonomy = current($taxonomies)) !== false) {
$terms = get_the_terms($this->post->ID, $taxonomy);
if (!empty($terms)) {
$postTerms['taxonomy'][$taxonomy] = $this->indexTaxonomyTerms($taxonomy, $terms);
}
next($taxonomies);
}
reset($taxonomies);
}
// index custom fields
$customFields = apply_filters('searchwp_get_custom_fields', get_post_custom($this->post->ID), $this->post->ID);
if (!empty($customFields)) {
while (($customFieldValue = current($customFields)) !== false) {
$customFieldName = key($customFields);
// there are a few useless (when it comes to search) WordPress core custom fields, so let's exclude them by default
$omitWpMetadata = apply_filters('searchwp_omit_wp_metadata', array('_edit_lock', '_wp_page_template', '_edit_last', '_wp_old_slug'));
$excludedCustomFieldKeys = apply_filters('searchwp_excluded_custom_fields', array('_' . SEARCHWP_PREFIX . 'indexed', '_' . SEARCHWP_PREFIX . 'attempts', '_' . SEARCHWP_PREFIX . 'terms', '_' . SEARCHWP_PREFIX . 'last_index', '_' . SEARCHWP_PREFIX . 'skip', '_' . SEARCHWP_PREFIX . 'skip_doc_processing', '_' . SEARCHWP_PREFIX . 'review'));
// merge the two arrays of keys if possible
if (is_array($omitWpMetadata) && is_array($excludedCustomFieldKeys)) {
$excluded_meta_keys = array_merge($omitWpMetadata, $excludedCustomFieldKeys);
} elseif (is_array($omitWpMetadata)) {
$excluded_meta_keys = $omitWpMetadata;
} else {
$excluded_meta_keys = $excludedCustomFieldKeys;
}
$excluded_meta_keys = is_array($excluded_meta_keys) ? array_unique($excluded_meta_keys) : array();
// allow developers to conditionally omit specific custom fields
$omit_this_custom_field = apply_filters("searchwp_omit_meta_key", false, $customFieldName, $this->post);
$omit_this_custom_field = apply_filters("searchwp_omit_meta_key_{$customFieldName}", $omit_this_custom_field, $this->post);
if (!in_array($customFieldName, $excluded_meta_keys) && !$omit_this_custom_field) {
// allow devs to swap out their own content
// e.g. parsing ACF Relationship fields (that store only post IDs) to actually retrieve that content at runtime
$customFieldValue = apply_filters('searchwp_custom_fields', $customFieldValue, $customFieldName, $this->post);
$customFieldValue = apply_filters("searchwp_custom_field_{$customFieldName}", $customFieldValue, $this->post);
$postTerms['customfield'][$customFieldName] = $this->indexCustomField($customFieldName, $customFieldValue);
}
next($customFields);
}
reset($customFields);
}
// allow developer to store arbitrary information a la Custom Fields (without them actually being Custom Fields)
$extraMetadata = apply_filters("searchwp_extra_metadata", false, $this->post);
if ($extraMetadata) {
if (is_array($extraMetadata)) {
foreach ($extraMetadata as $extraMetadataKey => $extraMetadataValue) {
// TODO: make sure there are no collisions?
// while( isset( $postTerms['customfield'][$extraMetadataKey] ) ) {
// $extraMetadataKey .= '_';
// }
$postTerms['customfield'][$extraMetadataKey] = $this->indexCustomField($extraMetadataKey, $extraMetadataValue);
}
}
}
// we need to break out the terms from all of this content
$termCountBreakout = array();
if (is_array($postTerms) && count($postTerms)) {
foreach ($postTerms as $type => $terms) {
switch ($type) {
case 'title':
case 'slug':
case 'content':
case 'excerpt':
case 'comments':
if (is_array($terms) && count($terms)) {
foreach ($terms as $term) {
$termCountBreakout[$term['term']][$type] = $term['count'];
}
}
break;
case 'taxonomy':
case 'customfield':
if (is_array($terms) && count($terms)) {
foreach ($terms as $name => $nameTerms) {
if (is_array($nameTerms) && count($nameTerms)) {
foreach ($nameTerms as $nameTerm) {
$termCountBreakout[$nameTerm['term']][$type][$name] = $nameTerm['count'];
}
}
}
}
break;
}
}
}
} else {
$termCountBreakout = $termCache;
// if there was a term cache, this repeated processing doesn't count, so decrement it
delete_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'attempts');
delete_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'skip');
}
// unless the term chunk limit says otherwise, we're going to flag this as being OK to log as indexed
$flagAsIndexed = true;
// we now have a multidimensional array of terms with counts per type in $termCountBreakout
// if the term count is huge, we need to split up this process so as to avoid
// hitting upper PHP execution time limits (term insertion is heavy), so we'll chunk the array of terms
$termChunkMax = 500;
// try to set a better default based on php.ini's memory_limit
$memoryLimit = ini_get('memory_limit');
if (preg_match('/^(\\d+)(.)$/', $memoryLimit, $matches)) {
if ($matches[2] == 'M') {
$termChunkMax = (int) $matches[1] * 15;
// 15 terms per MB RAM
} else {
// memory was set in K...
$termChunkMax = 100;
}
}
$termChunkLimit = apply_filters('searchwp_process_term_limit', $termChunkMax);
if (count($termCountBreakout) > $termChunkLimit) {
$acceptableTermCountBreakout = array_slice($termCountBreakout, 0, $termChunkLimit);
// if we haven't pulled all of the terms, we can't consider this post indexed...
if ($termChunkLimit < count($termCountBreakout) - 1) {
$flagAsIndexed = false;
// save the term breakout so we don't have to do it again
$remainingTerms = array_slice($termCountBreakout, $termChunkLimit + 1);
update_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'terms', $remainingTerms);
}
// set the acceptable breakout as the main breakout
$termCountBreakout = $acceptableTermCountBreakout;
}
$this->recordPostTerms($termCountBreakout);
unset($termCountBreakout);
// flag the post as indexed
if ($flagAsIndexed) {
// clean up our stored term array if necessary
if ($termCache) {
delete_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'terms');
}
// clean up the attempt counter
delete_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'attempts');
delete_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'skip');
update_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'indexed', true);
update_post_meta($this->post->ID, '_' . SEARCHWP_PREFIX . 'last_index', current_time('timestamp'));
}
}
next($this->unindexedPosts);
}
reset($this->unindexedPosts);
do_action('searchwp_indexer_post_chunk');
}
}
/**
* @deprecated
*
* Fallback to pure PHP library on IT-hosting (#1409).
* @return string
*/
protected function _pdf2text($pdf_file)
{
# TODO: error, PDF2Text echoes to screen - messes up header() call.
require_once __DIR__ . '/../class.pdf2text.php';
$pdf = new PDF2Text();
$pdf->setFilename($pdf_file);
$pdf->decodePDF();
$result = $pdf->output();
// Fix floating 's' 'th' ',' etc - English locale-specific.
$result = preg_replace('#(\\w)\\ss\\s#', '$1s ', $result);
$result = preg_replace('#\\sth\\s\\w#', ' th$1', $result);
$result = preg_replace('#\\s([,\\.;])#', '$1', $result);
// Concatenate lines starting with lowercase letters.
$result = preg_replace('#\\s+([a-z])#', ' $1', $result);
$result = str_replace(' ', ' ', $result);
// A crude conversion to HTML.
#$html = preg_replace('#([\w\. ])\n(\r)?\n(\w)#ms', '$1<br>$2', $result);
$html = str_replace(array("\n\n\n", "\n\n", "\n"), '<br>', $result);
return $html;
}
function __construct()
{
//
parent::__construct();
//
if ($this->sAction) {
switch ($this->sAction) {
case "fileList":
// retreive file list
$sDir = isset($_POST["folder"]) ? $_POST["folder"] : "/";
$aFiles = array();
$listing = tntbase_get_path_contents($sDir, true);
foreach ($listing as $file => $prop) {
$oFNfo = $this->getFileInfo(array("file" => $file, "type" => $prop));
$aFiles[] = $oFNfo;
}
$this->aReturn['msg'] .= "fileListing";
$this->aReturn['data'] = $aFiles;
break;
case "duplicate":
// duplicate file
$sCRegx = "/(?<=(_copy))([0-9])+(?=(\\.))/";
$sNRegx = "/(\\.)(?=[A-Za-z0-9]+\$)/";
$oMtch = preg_match($sCRegx, $this->sSFile, $aMatches);
if (count($aMatches) > 0) {
$sNewFile = preg_replace($sCRegx, intval($aMatches[0]) + 1, $this->sSFile);
} else {
$sNewFile = preg_replace($sNRegx, "_copy0.", $this->sSFile);
}
while (file_exists($sNewFile)) {
// $$ there could be a quicker way
$oMtch = preg_match($sCRegx, $sNewFile, $aMatches);
$sNewFile = preg_replace($sCRegx, intval($aMatches[0]) + 1, $sNewFile);
}
if (copy($this->sSFile, $sNewFile)) {
$oFNfo = $this->fileInfo($sNewFile);
$this->aReturn['data'] = $oFNfo;
$this->aReturn['msg'] .= "duplicated#" . $sNewFile;
} else {
$this->aReturn['error'] = "notduplicated#" . $sNewFile;
}
break;
case "swfUpload":
// swf file upload
if ($this->sAction == "swfUpload") {
foreach ($_GET as $k => $v) {
$_POST[$k] = $v;
}
}
case "upload":
// file upload
$sElName = $this->sAction == "upload" ? "fileToUpload" : "Filedata";
if (!empty($_FILES[$sElName]["error"])) {
switch ($_FILES[$sElName]["error"]) {
case "1":
$sErr = "uploadErr1";
break;
case "2":
$sErr = "uploadErr2";
break;
case "3":
$sErr = "uploadErr3";
break;
case "4":
$sErr = "uploadErr4";
break;
case "6":
$sErr = "uploadErr6";
break;
case "7":
$sErr = "uploadErr7";
break;
case "8":
$sErr = "uploadErr8";
break;
default:
$sErr = "uploadErr";
}
} else {
if (empty($_FILES[$sElName]["tmp_name"]) || $_FILES[$sElName]["tmp_name"] == "none") {
$this->aReturn['error'] = "No file was uploaded..";
} else {
$sFolder = $_POST["folder"];
$this->aReturn['msg'] .= "sFolder_" . $sFolder;
$sPath = $sFolder;
$sDeny = $_POST["deny"];
$sAllow = $_POST["allow"];
$sResize = $_POST["resize"];
$oFile = $_FILES[$sElName];
$sFile = $oFile["name"];
$sMime = array_pop(preg_split("/\\./", $sFile));
//mime_content_type($sDir.$file); //$oFile["type"]; //
//
$iRpt = 1;
$sFileTo = $sPath . $oFile["name"];
while (file_exists($sFileTo)) {
$aFile = explode(".", $oFile["name"]);
$aFile[0] .= "_" . $iRpt++;
$sFile = implode(".", $aFile);
$sFileTo = $sPath . $sFile;
}
$sFileTo = $this->sConnBse . $sFileTo;
move_uploaded_file($oFile["tmp_name"], $sFileTo);
$oFNfo = $this->fileInfo($sFileTo);
$bAllow = $sAllow == "";
$sFileExt = array_pop(explode(".", $sFile));
if ($oFNfo) {
$this->aReturn['msg'] .= $iRpt === 1 ? 'fileUploaded' : 'fileExistsrenamed';
// check if file is allowed in this session $$$$$$todo: check SFB_DENY
foreach (explode("|", $sAllow) as $sAllowExt) {
if ($sAllowExt == $sFileExt) {
$bAllow = true;
break;
}
}
foreach (explode("|", $sDeny) as $sDenyExt) {
if ($sDenyExt == $sFileExt) {
$bAllow = false;
break;
}
}
} else {
$bAllow = false;
}
if (!$bAllow) {
$this->aReturn['error'] = "uploadNotallowed#" . $sFileExt;
@unlink($sFileTo);
} else {
if ($sResize && $sResize != "null" && $sResize != "undefined" && ($sMime == "jpeg" || $sMime == "jpg")) {
$aResize = explode(",", $sResize);
$iToW = $aResize[0];
$iToH = $aResize[1];
list($iW, $iH) = getimagesize($sFileTo);
$fXrs = $iToW / $iW;
$fYrs = $iToH / $iH;
if (false) {
//just resize
$fRsz = min($fXrs, $fYrs);
if ($fRsz < 1) {
$iNW = intval($iW * $fRsz);
$iNH = intval($iH * $fRsz);
$oImgN = imagecreatetruecolor($iNW, $iNH);
$oImg = imagecreatefromjpeg($sFileTo);
imagecopyresampled($oImgN, $oImg, 0, 0, 0, 0, $iNW, $iNH, $iW, $iH);
imagejpeg($oImgN, $sFileTo);
}
} else {
// crop after resize
$fRsz = max($fXrs, $fYrs);
//if ($fRsz<1) {
if ($fXrs < 1 || $fYrs < 1) {
$iNW = intval($iW * $fRsz);
$iNH = intval($iH * $fRsz);
$iFrX = $iNW > $iToW ? ($iNW - $iToW) / 2 : 0;
$iFrY = $iNH > $iToH ? ($iNH - $iToH) / 2 : 0;
$iFrW = $iNW > $iToW ? $iToW * (1 / $fRsz) : $iW;
$iFrH = $iNH > $iToH ? $iToH * (1 / $fRsz) : $iH;
$oImgN = imagecreatetruecolor($iToW, $iToH);
$oImg = imagecreatefromjpeg($sFileTo);
imagecopyresampled($oImgN, $oImg, 0, 0, $iFrX, $iFrY, $iToW, $iToH, $iFrW, $iFrH);
imagejpeg($oImgN, $sFileTo);
}
}
$oFNfo = $this->fileInfo($sFileTo);
}
$this->aReturn['data'] = $oFNfo;
}
}
}
break;
case "delete":
// file delete
if (count($_POST) != 3 || !isset($_POST["folder"]) || !isset($_POST["file"])) {
exit("ku ka");
}
if (is_file($this->sSFile)) {
if (@unlink($this->sSFile)) {
$this->aReturn['msg'] .= "fileDeleted";
} else {
$this->aReturn['error'] .= "fileNotdeleted";
}
} else {
if (@rmdir($this->sSFile)) {
$this->aReturn['msg'] .= "folderDeleted";
} else {
$this->aReturn['error'] .= "folderNotdeleted";
}
}
break;
case "download":
// file force download
$sZeFile = $this->sConnBse . $this->sSFile;
if (file_exists($sZeFile)) {
ob_start();
$sType = "application/octet-stream";
header("Cache-Control: public, must-revalidate");
header("Pragma: hack");
header("Content-Type: " . $this->sSFile);
header("Content-Length: " . (string) filesize($sZeFile));
header('Content-Disposition: attachment; filename="' . array_pop(explode("/", $sZeFile)) . '"');
header("Content-Transfer-Encoding: binary\n");
ob_end_clean();
readfile($sZeFile);
exit;
}
break;
case "read":
// read txt file contents
$sExt = strtolower(array_pop(explode('.', $this->sSFile)));
//
// install extensions and add to php.ini
// - extension=php_zip.dll
if ($sExt == "zip") {
$sDta = "";
if (!function_exists("zip_open")) {
$sErr .= "php_zip not installed or enabled";
} else {
if ($zip = @zip_open(getcwd() . "/" . $this->sSFile)) {
//
while ($zip_entry = @zip_read($zip)) {
$sDta .= @zip_entry_name($zip_entry) . "\\r\\n";
}
// zip_entry_filesize | zip_entry_compressedsize | zip_entry_compressionmethod
@zip_close($zip);
$this->aReturn['data'] = array('type' => 'archive', 'text' => $sDta);
}
}
} else {
if ($sExt == "rar") {
// - extension=php_rar.dll
if (!function_exists("rar_open")) {
$sMsg .= "php_rar not installed or enabled";
} else {
if ($rar_file = @rar_open(getcwd() . "/" . $this->sSFile)) {
$entries = @rar_list($rar_file);
foreach ($entries as $entry) {
$sDta .= $entry->getName() . "\\r\\n";
}
// getName | getPackedSize | getUnpackedSize
@rar_close($rar_file);
$this->aReturn['data'] = array('type' => 'archive', 'text' => $sDta);
}
}
} else {
if ($sExt == "pdf") {
include 'class.pdf2text.php';
$oPdf = new PDF2Text();
$oPdf->setFilename($this->sSFile);
$oPdf->decodePDF();
$sCnt = str_replace(array("\n", "\r", "\t"), array("\\n", "\\n", ""), substr($oPdf->output(), 0, PREVIEW_BYTES));
$this->aReturn['data'] = array('type' => 'ascii', 'text' => $sCnt);
} else {
if ($sExt == "doc") {
//////////////////////////////
// does not seem to be possible
//////////////////////////////
} else {
$oHnd = fopen($this->sSFile, "r");
$sCnt = preg_replace(array("/\n/", "/\r/", "/\t/"), array("\\n", "\\r", "\\t"), addslashes(fread($oHnd, 600)));
fclose($oHnd);
$this->aReturn['data'] = array('type' => 'ascii', 'text' => $sCnt);
}
}
}
}
$this->aReturn['msg'] .= count($this->aReturn['data']) ? 'contentsSucces' : 'contentsFail';
break;
case "rename":
// rename file
if (isset($_POST["file"]) && isset($_POST["nfile"])) {
$sFile = $_POST["file"];
$sNFile = $_POST["nfile"];
$sFileExt = array_pop(preg_split("/\\./", $sFile));
$sNFileExt = array_pop(preg_split("/\\./", $sNFile));
$sNSFile = str_replace($sFile, $sNFile, $this->sSFile);
if (@filetype($this->sSFile) == "file" && $sFileExt != $sNFileExt) {
$this->aReturn['error'] .= "filenameNoext";
// } else if (!preg_match("/^\w+(\.\w+)*$/",$sNFile)) {
} else {
if (!preg_match('=^[^/?*;:{}\\\\]+\\.[^/?*;:{}\\\\]+$=', $sNFile)) {
$this->aReturn['error'] .= "filenamInvalid";
} else {
if ($sFile == $sNFile) {
$this->aReturn['msg'] .= "filenameNochange";
} else {
if ($sNFile == "") {
$this->aReturn['error'] .= "filenameNothing";
} else {
if (file_exists($sNSFile)) {
$this->aReturn['error'] .= "filenameExists";
} else {
if (@rename($this->sSFile, $sNSFile)) {
$this->aReturn['msg'] .= "filenameSucces";
} else {
$this->aReturn['error'] .= "filenameFailed";
}
}
}
}
}
}
}
break;
case "addFolder":
// add folder
if (isset($_POST["folder"])) {
$sFolderName = isset($_POST["foldername"]) ? $_POST["foldername"] : "new folder";
$iRpt = 1;
$sFolder = $this->sConnBse . $_POST["folder"] . $sFolderName;
while (file_exists($sFolder)) {
$sFolder = $this->sConnBse . $_POST["folder"] . $sFolderName . $iRpt++;
}
if (mkdir($sFolder)) {
$this->aReturn['msg'] .= "folderCreated";
$oFNfo = $this->fileInfo($sFolder);
if ($oFNfo) {
$this->aReturn['data'] = $oFNfo;
} else {
$this->aReturn['error'] .= "folderFailed";
}
} else {
$this->aReturn['error'] .= "folderFailed";
}
}
break;
case "moveFiles":
// move files
if (isset($_POST["file"]) && isset($_POST["folder"]) && isset($_POST["nfolder"])) {
//
$sFolder = $_POST["folder"];
$sNFolder = $_POST["nfolder"];
$aFiles = explode(",", $_POST["file"]);
$aMoved = array();
$aNotMoved = array();
for ($i = 0; $i < count($this->aFiles); $i++) {
$sFile = $aFiles[$i];
$this->sSFile = $this->aFiles[$i];
$sNSFile = str_replace($sFile, $sNFolder . "/" . $sFile, $this->sSFile);
if (file_exists($sNSFile)) {
$this->aReturn['error'] .= "filemoveExists[" . $this->sSFile . " " . $sNSFile . "] ";
$aNotMoved[] = $sFile;
} else {
if (@rename($this->sSFile, $sNSFile)) {
$this->aReturn['msg'] .= "filemoveSucces";
$aMoved[] = $sFile;
} else {
$this->aReturn['error'] .= "filemoveFailed";
$aNotMoved[] = $sFile;
}
}
}
$this->aReturn['data'] = array('moved' => $aMoved, 'notmoved' => $aNotMoved, 'newfolder' => $sNFolder);
}
break;
}
$this->returnJSON($this->aReturn);
}
}
<?php
include 'PDF2Text.php';
$a = new PDF2Text();
$a->setFilename('x.pdf');
$a->decodePDF();
$extracted_plaintext = $a->output();
//cuenta el numero de palabras en el texto
echo "<br><br>Hay " . str_word_count($extracted_plaintext, 0) . " palabras en la cadena <br><br>'{$extracted_plaintext}'";
//guardo las palabras en un array
$array_cadena = str_word_count($extracted_plaintext, 1);
//saco cada elemento del array
foreach ($array_cadena as $palabra) {
echo $palabra . " ";
}
<?php
$note_id = "";
$pdfContent = "";
$note_title = "";
if (isset($_GET['id']) && $_GET['id'] != "") {
$note_id = $_GET['id'];
$sql = "select mn_note_path,mn_note_title,mn_note_uploaded_by,mn_note_created_date from mn_note where mn_note_id={$note_id} limit 0,1";
$data = $objDB->select($sql);
if ($data && !empty($data)) {
$note_title = $data[0]['mn_note_title'];
$name = $data[0]['mn_note_path'];
$filePath = 'notes/pdf/' . $name;
if (file_exists($filePath)) {
include 'libs/class.pdf2text.php';
$pdfObj = new PDF2Text();
$pdfObj->setFilename($filePath);
$pdfObj->setFilename;
$pdfObj->decodePDF();
$pdfContent = $pdfObj->output();
$total_char = strlen($pdfContent);
$fourty_percent_char = $total_char * 40 / 100;
$pdfContent = tokenTruncate($pdfContent, $fourty_percent_char) . "<span>…More</span>";
}
} else {
header("Location:index.php?p=browesnotes&err=file_not_found");
}
}
if ($pdfContent != "") {
$table = 'mn_user';
$key = 'mn_user_id';
$currentObject = $objects[$i];
// Check if an object includes data stream.
if (preg_match("#stream(.*)endstream#ismU", $currentObject, $stream)) {
$stream = ltrim($stream[1]);
// Check object parameters and look for text data.
$options = getObjectOptions($currentObject);
if (!(empty($options["Length1"]) && empty($options["Type"]) && empty($options["Subtype"]))) {
continue;
}
// So, we have text data. Decode it.
$data = getDecodedStream($stream, $options);
if (strlen($data)) {
if (preg_match_all("#BT(.*)ET#ismU", $data, $textContainers)) {
$textContainers = @$textContainers[1];
getDirtyTexts($texts, $textContainers);
} else {
getCharTransformations($transformations, $data);
}
}
}
}
// Analyze text blocks taking into account character transformations and return results.
return getTextUsingTransformations($texts, $transformations);
}
include dirname(__FILE__) . '/../../kernel/pdf2text.php';
$a = new PDF2Text();
$a->setFilename(dirname(__FILE__) . '/../../../InformDovidka.pdf');
//grab the test file at http://www.newyorklivearts.org/Videographer_RFP.pdf
$a->decodePDF();
// echo $a->output();
echo pdf3text(dirname(__FILE__) . '/../../../InformDovidka.pdf');
/**
* Extract plain text from PDF
*
* @since 2.5
* @param $post_id integer The post ID of the PDF in the Media library
*
* @return string The contents of the PDF
*/
function extract_pdf_text( $post_id ) {
global $wp_filesystem, $searchwp;
$pdf_post = get_post( absint( $post_id ) );
// make sure it's a PDF
if ( 'application/pdf' !== $pdf_post->post_mime_type ) {
return '';
}
// grab the filename of the PDF
$filename = get_attached_file( absint( $post_id ) );
// make sure the file exists locally
if ( ! file_exists( $filename ) ) {
return '';
}
// PdfParser runs only on 5.3+ but SearchWP runs on 5.2+
if ( version_compare( PHP_VERSION, '5.3', '>=' ) ) {
/** @noinspection PhpIncludeInspection */
include_once( $searchwp->dir . '/vendor/pdfparser-bootloader.php' );
// a wrapper class was conditionally included if we're running PHP 5.3+ so let's try that
if ( class_exists( 'SearchWP_PdfParser' ) ) {
/** @noinspection PhpIncludeInspection */
include_once( $searchwp->dir . '/vendor/pdfparser/vendor/autoload.php' );
// try PdfParser first
$parser = new SearchWP_PdfParser();
$parser = $parser->init();
try {
$pdf = $parser->parseFile( $filename );
$pdfContent = $pdf->getText();
} catch (Exception $e) {
do_action( 'searchwp_log', 'PDF parsing failed: ' . $e->getMessage() );
return false;
}
}
}
// try PDF2Text
if ( empty( $pdfContent ) ) {
if ( ! class_exists( 'PDF2Text' ) ) {
/** @noinspection PhpIncludeInspection */
include_once( $searchwp->dir . '/vendor/class.pdf2text.php' );
}
$pdfParser = new PDF2Text();
$pdfParser->setFilename( $filename );
$pdfParser->decodePDF();
$pdfContent = $pdfParser->output();
$pdfContent = trim( str_replace( "\n", ' ', $pdfContent ) );
}
// check to see if the first pass produced nothing or concatenated strings
$fullContentLength = strlen( $pdfContent );
$numberOfSpaces = substr_count( $pdfContent, ' ' );
if ( empty( $pdfContent ) || ( ( $numberOfSpaces / $fullContentLength ) * 100 < 10 ) ) {
WP_Filesystem();
if ( method_exists( $wp_filesystem, 'exists' ) && method_exists( $wp_filesystem, 'get_contents' ) ) {
$filecontent = $wp_filesystem->exists( $filename ) ? $wp_filesystem->get_contents( $filename ) : '';
} else {
$filecontent = '';
}
if ( false != strpos( $filecontent, 'trailer' ) ) {
if ( ! class_exists( 'pdf_readstream' ) ) {
/** @noinspection PhpIncludeInspection */
include_once( $searchwp->dir . '/vendor/class.pdfreadstream.php' );
}
$pdfContent = '';
$pdf = new pdf( get_attached_file( $this->post->ID ) );
$pages = $pdf->get_pages();
if ( ! empty( $pages ) ) {
/** @noinspection PhpUnusedLocalVariableInspection */
while ( list( $nr, $page ) = each( $pages ) ) {
if ( method_exists( $page, 'get_text' ) ) {
$pdfContent .= $page->get_text();
}
}
}
} else {
// empty out the content so wacky concatenations are not indexed
$pdfContent = false;
}
}
return $pdfContent;
}
function pdf_to_text($filename)
{
$a = new PDF2Text();
$a->setFilename($filename);
$a->decodePDF();
return $a->output();
}
<?php
include 'class.pdf2text.php';
$a = new PDF2Text();
$a->setFilename('hello.pdf');
$a->decodePDF();
echo $a->output();
