extraction-interface: develop/models/extractapp.php comparison

comparison develop/models/extractapp.php @ 40:2e938dc046db extractapp

load,save xml file with topic, etc.

author	Zoe Hong <zhong@mpiwg-berlin.mpg.de>
date	Tue, 10 Mar 2015 13:46:16 +0100
parents	8347776a44fc
children	533a6c39c128

comparison

equal deleted inserted replaced

-:8347776a44fc
+:2e938dc046db
 $this->SetSectionId($_urlvalues);
 }
 public function GetTextFromFileId($_postdata) {
-/*
-if ($this->current_fileId != 0) {
-$this->file_id = $this->current_fileId;
-} else {
-$this->file_id = $_postdata['fileId'];
-}
-*/
 $this->file_id = $_postdata['fileId'];
 $branch_id = $_postdata['branchId'];
 $section_id = $_postdata['sectionId'];
 $this->branch_id = $branch_id;
 $this->user_id = $_postdata['userId'];
 $this->section_id = $section_id;
 $this->section_name = $_postdata['sectionName'];
 $this->book_id = $_postdata['bookId'];
 $this->book_name = $_postdata['bookName'];
 // get from URL with file_id
 $lg_text_url = $this->get_text_from_fileId_url.$this->file_id;
-$lg_text = file_get_contents($lg_text_url);
+//$lg_text = file_get_contents($lg_text_url);
+// --- parsing meta data
+$lg_text = $this->ParseMetaData($lg_text_url);
+// ----
 $stringInput = $lg_text;
 $stringInput = preg_replace("/ /u", "○", $stringInput);
 $stringInput = preg_replace("/\n/u", "<br>", $stringInput);
 $stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"review_index_xml_images.php?books_id=".$bookId."&pages=\\1&entry=0\" target=\"_bookImg\">\\1</a>】", $stringInput);
 $this->lg_text = $lg_text;
 }
 public function GetTextFromSectionId($_postdata) {
 $section_id = $_postdata['sectionId'];
 $this->section_id = $section_id;
 $this->user_id = $_postdata['userId'];
 $this->section_name = $_postdata['sectionName'];
 $this->book_id = $_postdata['bookId'];
 $this->book_name = $_postdata['bookName'];
 // get from URL with file_id
 $lg_text_url = $this->get_text_from_sectionId_url.$section_id;
 $lg_text = file_get_contents($lg_text_url);
 $stringInput = $lg_text;
 $stringInput = preg_replace("/<(.*?)>/u", "○", $stringInput);
 $stringInput = preg_replace("/ /u", "○", $stringInput);
 $this->book_id = $_postdata['bookId'];
 }
 if ($_postdata['currentFileId']) {
 $this->current_fileId = $_postdata['currentFileId'];
 }
+if ($_postdata['taglistArray']) {
+$this->taglist_infile = json_decode($_postdata['taglistArray']);
+}
+if ($_postdata['book_meta']) {
+$this->book_meta = json_decode($_postdata['book_meta']);
+}
 }
 public function InitData($_postdata) {
 $file_id = $_postdata['fileId'];
 $branch_id = $_postdata['branchId'];
 }
 */
+// TODO: comparison not correct
 private function Taglist_infileUpToDate($taglistArray) {
 // compare $this->taglist_infile is the same as $taglistArray
 $taglist_infile = $this->taglist_infile;
 if (count($taglist_infile) != count($taglistArray)) {
 return false;
 }
 foreach ($taglistArray as $row_indb) {
+$cnt = 0;
 foreach ($taglist_infile as $row) {
 //$taglistArray: array( $row['id'], $row['name'], $row['tag'], $row['color'] )
 if ($row[0] == $row_indb[0] && $row[1] == $row_indb[1] && $row[2] == $row_indb[2] && $row[3] == $row_indb[3]) {
 } else {
-return false;
+$cnt ++;
 }
+}
+if ($cnt == count($row)) {
+return false;
 }
 }
 return true;
 }
 // === for tagging ===
 //$taglistArray = $this->GetTaglistArray();
 //for GetTaglistByTopicID:
 $taglistArray = $this->GetTaglistByTopicID($this->GetTopic());
+$data['taglist_infile'] = $this->taglist_infile;
 // TODO: check if taglist_infile is up-to-date
+/*
 if ( !$this->Taglist_infileUpToDate($taglistArray)) {
 $data['taglist_infile'] = $this->taglist_infile;
-}
+} else {
+$data['taglist_infile'] = "";
+}
+*/
+// book_meta
+$data['book_meta'] = $this->book_meta;
 // topic list
 $topiclistArray = $this->GetTopiclistArray();
 }
 }
+private function AppendMetaData($text_content) {
+$text = '<?xml version="1.0" encoding="UTF-8"?>';
+$text .= "\n<text>\n";
+// topic
+$text .= "<topic>".$this->topic."</topic>\n";
+// book meta data
+$book = $this->book_meta;
+foreach ($book as $b) {
+$text .= "<book>\n";
+$text .= "<title>".$b[0]."</title>\n";
+$text .= "<author>".$b[1]."</author>\n";
+$text .= "<year>".$b[2]."</year>\n";
+$text .= "<pagenumber>".$b[3]."</pagenumber>\n";
+$text .= "</book>\n";
+}
+// taglist
+$taglist = $this->taglist_infile;
+foreach ($taglist as $tagitem) {
+$text .= "<tagitem>\n";
+$text .= "<id>".$tagitem[0]."</id>\n";
+$text .= "<name>".$tagitem[1]."</name>\n";
+$text .= "<tag>".$tagitem[2]."</tag>\n";
+$text .= "<color>".$tagitem[3]."</color>\n";
+$text .= "</tagitem>\n";
+}
+// text_content
+$text .= $text_content;
+$text .= "\n</text>";
+return $text;
+}
 public function SaveFullTextToLGService($_postdata) {
 // save tagged text (full text) by Jorge's API to lg service
 // --------
 if ($_postdata['text']){
 if (get_magic_quotes_gpc()) {
 $require = stripslashes($_postdata['text']);
 } else {
 $require = $_postdata['text'];
 }
 $require = preg_replace("/【<a(.*?)>(.*?)<\/a>】/u", "【\\2】", $require);
 $require = preg_replace('/&amp;/u', "&", $require);
 $require = preg_replace("/○/u", " ", $require);
 $require = preg_replace("/<br>/u", "\n", $require);
-$require = preg_replace("/<br>/u", "\n", $require);
+//$require = preg_replace("/<br>/u", "\n", $require);
+// TODO: append metadata at the beginning of file
+if ($_postdata['branchId'] == 0) {
+// -- new branch case
+$require = "<text_content>\n".$require."</text_content>\n";
+}
+$require = $this->AppendMetaData($require);
 //saving in my local machine in developing phrase
 file_put_contents("data/parsing_files/".$_postdata['sectionId'].".txt", $require);
 }
 // ------
 curl_setopt($ch, CURLOPT_HTTPHEADER, array(
 'Content-type: multipart/form-data;charset=utf-8'
 ));
 // execute the request
-$output = curl_exec($ch);
+// **** commended to DEBUG ***
+//$output = curl_exec($ch);
+// *****
 // output the profile information - includes the header
 //echo($output) . PHP_EOL;
 // close curl resource to free up system resources
 private function ParseMetaData($filename) {
 $text = file_get_contents($filename);
 $xml = simplexml_load_string($text) or die("Error: Cannot load from xml string");
-$this->topic = $xml->topic; // set topic id
+$this->topic = (string)$xml->topic; // set topic id
 // get taglist in file
-$taglist_infile = $xml->taglist;
+$taglist_infile = $xml->tagitem;
 $taglistArray = array();
 foreach ($taglist_infile as $row) {
-array_push($taglistArray, array((string)$row->id, (string)$row->name, (string)$row->tag, (string)$row->color));
+array_push($taglistArray, array((string)$row->id,(string)$row->name,(string)$row->tag,(string)$row->color ));
 }
-$this->taglist_infile = $taglistArray;
+if ($taglistArray) {
+$this->taglist_infile = $taglistArray;
-// TODO: get meta data of book
+}
-$this->book_meta = $xml->book;
+// get book meta data
+$book_meta = $xml->book;
+$book_metaArray = array();
+foreach ($book_meta as $row) {
+//array_push($book_metaArray, array('title'=>(string)$row->title,'author'=>(string)$row->author,'year'=>(string)$row->year,'pagenumber'=>(string)$row->pagenumber ));
+array_push($book_metaArray, array((string)$row->title,(string)$row->author,(string)$row->year,(string)$row->pagenumber ));
+}
+if ($book_metaArray) {
+$this->book_meta = $book_metaArray;
+}
 // echo $taglist->name.", ".$taglist->tag."," .$taglist->color;
 // --- detect if the taglist set is up-to-date or not ---
+$contentString = (string)$xml->text_content->asXML();
+//$removed_str = array("<text_content>","</text_content>");
-$contentString = $xml->text_content->asXML();
+//$new_contentString = str_replace($removed_str, "", $contentString);
 return $contentString;
 }
 private function GetSectionContent() {
 $section_id = $this->GetSectionId();
 $contentString="";
 $data_path = $this->GetDataPath();
 if ( file_exists($data_path."parsing_files/".$section_id.".txt") ) {
 $filename = $data_path."parsing_files/".$section_id.".txt";
-// --- parsing meta data
+// --- parsing meta data
 $stringInput = $this->ParseMetaData($filename);
 // ----
 // if the text is from file system
 $stringInput = preg_replace("/ /u", "○", $stringInput);

Mercurial > hg > extraction-interface

comparison develop/models/extractapp.php @ 40:2e938dc046db extractapp