extraction-interface: models/extractapp.php comparison

comparison models/extractapp.php @ 115:507070df62e6 extractapp

add escape rule for regular expression

author	Calvin Yeh <cyeh@mpiwg-berlin.mpg.de>
date	Thu, 28 Sep 2017 17:13:39 +0200
parents	7bdbc7fc7936
children

comparison

equal deleted inserted replaced

-:7d6a107c37da
+:507070df62e6
 $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=".$this->book_id."&pages=\\1&entry=0\" target=\"_bookImg\">\\1</a>】", $stringInput);
+$stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"#\">\\1</a>】", $stringInput);
 $lg_text = $stringInput;
 $this->lg_text = $lg_text;
 }
 $book_meta->level2 = $b['level2'];
 $book_meta->period = $b['period'];
 $book_meta->dynasty = $b['dynasty'];
 $book_meta->start_year = $b['start_year'];
 $book_meta->end_year = $b['end_year'];
+$book_meta->book_year = $b['book_year'];
+$book_meta->edition_year = $b['edition_year'];
 $book_meta->line = $b['line'];
 $book_meta->volume = $b['volume'];
 $book_meta->author = $b['author'];
 $book_meta->edition = $b['edition'];
 $book_meta->in_jibengujiku = $b['in_jibengujiku'];
 $book_meta->admin_type = $b['admin_type'];
+$book_meta->book_year = $b['book_year'];
+$book_meta->edition_year = $b['edition_year'];
 $coordinates = $section_meta['section']['coordinates_books'];
 $book_meta->x = $coordinates['x'];
 $book_meta->y = $coordinates['y'];
 $book_meta->place_name = $coordinates['place_name'];
 $stringInput = $lg_text;
 $stringInput = preg_replace("/<(.*?)>/u", "○", $stringInput);
 $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=".$this->book_id."&pages=\\1&entry=0\" target=\"_bookImg\">\\1</a>】", $stringInput);
+$stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"#\">\\1</a>】", $stringInput);
 $lg_text = $stringInput;
 $this->lg_text = $lg_text;
 }
 $this->section_id = $_id;
 //$this->branch_id = 1;   // local test sets branch_id to 1
 $this->messages['debug'] .= "[Debug] from my local"."<br>";
 $this->lg_text = $this->GetSectionContent();
 }
 public function SetInfoFromPreviousPage($_postdata) {
 /**
 * Get information from post data passsed by the previous page, and set variables in $this.
 * The previous page could be:
 if (isset($_postdata['book_meta'])) {
 $this->book_meta = json_decode($_postdata['book_meta']);
 }
 }
 private function TaglistSubsetIn($list1, $list2) {    // $l1 is a subset of $l2 or not
 // l1 and l2: array( $row['id'], $row['name'], $row['tag'], $row['color'] )
 $cnt_list1 = count($list1);
 $cnt_list2 = count($list2);
 $this->lg_text = $lg_text;
 }
 public function StartTagging() {
 /**
 * This is the main method for tagging text. It passes all the information to "views/Extractapp/TaggingText.php" view.
 * The information contain the text string, taglist array, wordlis array, topic, etc.
 */
 $require = $postdata['text'];
 }
 $require = preg_replace("/【<a(.*?)>(.*?)<\/a>】/u", "【\\2】", $require);
 $require = preg_replace('/&amp;/u', "&", $require);
-$require = preg_replace('/&nbsp;/u', " ", $require); //avoiding invaild xml format
+$require = preg_replace('/&nbsp;/u', " ", $require);
+$require = preg_replace('/<font [^><]*>/u', "", $require);
+$require = preg_replace('/<\/font>/u', "", $require);
+$require = preg_replace('/ style="background-color: transparent;"/u', "", $require);
 $require = preg_replace("/○/u", " ", $require);
 $require = preg_replace("/<br>/u", "\n", $require);
 $require = preg_replace("/<br>/u", "\n", $require);
 file_put_contents("data/parsing_files/".$postdata['filename'].".txt", $require);
 }
 }
 public function UpdateInfoResponsedFromLGService($response) {
 /**
 *
 */
 $text .= "<level2>".$book->level2."</level2>\n";
 $text .= "<period>".$book->period."</period>\n";
 $text .= "<dynasty>".$book->dynasty."</dynasty>\n";
 $text .= "<start_year>".$book->start_year."</start_year>\n";
 $text .= "<end_year>".$book->end_year."</end_year>\n";
+$text .= "<book_year>".$book->book_year."</book_year>\n";
+$text .= "<edition_year>".$book->edition_year."</edition_year>\n";
 $text .= "<line>".$book->line."</line>\n";
 $text .= "<volume>".$book->volume."</volume>\n";
 $text .= "<author>".$book->author."</author>\n";
 $text .= "<edition>".$book->edition."</edition>\n";
 $text .= "<in_jibengujiku>".$book->in_jibengujiku."</in_jibengujiku>\n";
 $require = $_postdata['text'];
 }
 $require = preg_replace("/【<a(.*?)>(.*?)<\/a>】/u", "【\\2】", $require);
 $require = preg_replace('/&amp;/u', "&", $require);
-$require = preg_replace('/&nbsp;/u', " ", $require);   //avoiding invaild xml format
+$require = preg_replace('/&nbsp;/u', " ", $require);
+$require = preg_replace('/<font [^><]*>/u', "", $require);
+$require = preg_replace('/<\/font>/u', "", $require);
+$require = preg_replace('/ style="background-color: transparent;"/u', "", $require);
 $require = preg_replace("/○/u", " ", $require);
 $require = preg_replace("/<br(.*?)>/u", "\n", $require);
 //$require = preg_replace("/<br>/u", "\n", $require);
 $require = "<text_content>".$require."</text_content>\n";
 array_push($filenames, $row['regex_filename']);
 }
 return $filenames;
 }
 public function LoadSmartRegex($topic_id) {
 // Load regex file based on current topic. Only shows the regex in this topic --
 $filenames = $this->GetRegexFilenameById($topic_id);
 }
 echo json_encode($returnArray);
 return;
 }
 public function SaveSmartRegex($_postdata) {
 if ($_postdata['text']){
 // --- update topic_regex_relation table ---
 $topic_id = $_postdata['topic_id'];
 file_put_contents( $data_path."regex_files/".$_postdata['filename'].".txt", $require);
 }
 }
 private function GetTableArray($_taglistArray, $_topic_tag, $_content) {
 $outputTableArray = array();
 $outputTableArray[0]=array();
 $outputTableArray[0][1]=array();
 foreach ( $_taglistArray as $value ) {
 $outputTableArray[0][0][$value[2]] = $value[1];
 $outputTableArray[0][1][$value[2]] = $value[1]."(Title)";
 }
-$outputTableArray[0]["other"] = "其他";
+//remove other, full columns
+//$outputTableArray[0]["other"] = "其他";
 $outputTableArray[0]["page"] = "頁數";
-$outputTableArray[0]["full"] = "全文";
+//$outputTableArray[0]["full"] = "全文";
 // id, name, tag, color in _taglistArray
 foreach ( $_taglistArray as $tagValue ) {
 $tag_name = $tagValue[2];   // $tagValue[2] is tag_name
 $content = preg_replace("/<\/".$tag_name.">○*<".$tag_name.">/u", "", $_content);
 $count=0;
 $pageNow=NULL;
 foreach ( $contentLineArray as $value ) {
 $count++;
 $recordString = $value;
-$otherString = $recordString;
+//$otherString = $recordString;
 //echo $recordString."<br>\n";
 // find hyper link in pattern with <a>...</a>
 if ( preg_match("/【<a(.*?)>(.*?)<\/a>】/u", $recordString, $matches) ) {
 $pageNow = $matches[2];
 }
 foreach ( $_taglistArray as $tagValue ) {
 $tag_name = $tagValue[2];   // $tagValue[2] is tag_name
 if ( preg_match_all("/<".$tag_name.">(.*?)<\/".$tag_name.">/u", $recordString, $matches, PREG_SET_ORDER) ) {
 foreach ( $matches as $matchesValue ) {
 } else {
 $outputTableArray[$count][0][$tag_name] = $matchesValue[1];
 }
 }
 }
-$otherString = preg_replace("/<".$tag_name.">(.*?)<\/".$tag_name.">/u", "　", $otherString);
+//$otherString = preg_replace("/<".$tag_name.">(.*?)<\/".$tag_name.">/u", "　", $otherString);
 }
 }
-$otherString = preg_replace("/○/u", "", $otherString);
-$outputTableArray[$count]["other"] = $otherString;
+//$otherString = preg_replace("/○/u", "", $otherString);
+//$outputTableArray[$count]["other"] = $otherString;
 $outputTableArray[$count]["page"] = $pageNow;
-$value = preg_replace("/>/u", "&gt;", $value);
+//$value = preg_replace("/>/u", "&gt;", $value);
-$value = preg_replace("/</u", "&lt;", $value);
+//$value = preg_replace("/</u", "&lt;", $value);
-$outputTableArray[$count]["full"] = $value;
+//$outputTableArray[$count]["full"] = $value;
 }
 foreach ( $outputTableArray as $arrayIndex => $arrayValue ) {
 $this->GetSQLValueString($tag, "text"),
 $this->GetSQLValueString($color, "text"),
 $this->GetSQLValueString($date, "date"),
 $this->GetSQLValueString($id, "int"));
 $result = mysql_query($query);
+if (!$result) {
+echo 0;
+}
 }
 }
 $data['tag_others'] = $tag_others;
 return $data;
 }
 public function UpdateTagsInTopic($_postdata) {
 $topic_id = $_postdata['topic_id'];
 $tag_ids = json_decode(str_replace('\\', '', $_postdata['ids']));
 // update topic_tag_relation by tags_ids array as `tag_id` and topic_id as `topic_id`
 }
 }
 private function GetTaglistByTopicId($topic_id) {
 $taglistArray = array();
 // select taglist ids from topic_tag_relation table
 $query = sprintf("SELECT * FROM `TopicTagRelation` WHERE `topicId`='%s'", $topic_id);
 $result = mysql_query($query);
 //array_push($topiclistArray, array('id'=>$row['id'],'tag'=>$row['tag'],'name_en'=>$row['name_en'],'name_ch'=>$row['name_ch'],'name_pinyin'=>$row['name_pinyin'],));
 array_push($topiclistArray, array('id'=>$row['id'],'tag'=>$row['tag'],'name_en'=>$row['nameEn'],'name_ch'=>$row['nameCh'],'name_pinyin'=>$row['namePinyin'],));
 }
 return $topiclistArray;
 }
 private function GetTopicTag($topic_id) {
 $result = $this->GetTopicById($topic_id);
 $row = mysql_fetch_assoc($result);
 $tag = $row['tag'];
 // ----
 // if the text is from file system
 $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>】", $stringInput);
+$stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"#\">\\1</a>】", $stringInput);
 $this->branch_id = 1;   // testing at local
 } else {
 $query = sprintf("SELECT `content`, `line`, `books_id` FROM `contents` WHERE `books_id`=\"%s\" AND `line`>=%d AND `line`<=%d", $bookId, $startPage, $endPage);
 // the text is from database
 $stringInput = $contentString;
 $stringInput = preg_replace("/<(.*?)>/u", "○", $stringInput);
 $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>】", $stringInput);
+$stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"#\">\\1</a>】", $stringInput);
 }
 return $stringInput;
 }

Mercurial > hg > extraction-interface

comparison models/extractapp.php @ 115:507070df62e6 extractapp