Mercurial > hg > extraction-interface
view models/extractapp.php @ 89:e681d693240e extractapp
new: generated regex to SmartRegex
author | Zoe Hong <zhong@mpiwg-berlin.mpg.de> |
---|---|
date | Wed, 03 Jun 2015 16:54:09 +0200 |
parents | fb5049fc5dd7 |
children | 94ad33739fa4 |
line wrap: on
line source
<?php /* * extractapp.php * This file is part of Extraction-interface. * * Extraction-interface is free software: you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation, either version 3 of the License, or * (at your option) any later version. * * Extraction-interface is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with Extraction-interface. If not, see <http://www.gnu.org/licenses/>. */ /** * ExtractappModel class is extended from the BaseModel class. * This is where we implement the functions/models to prepare data that been sent to views. * ExtractappModel is notified by Extractapp controller when there has been a change in its state, * and produces the output/data to the corresponding view in "views/Extractapp/". * */ class ExtractappModel extends BaseModel{ protected $section_id = 0, $data_path, $file_id = 0, $current_fileId=0, $branch_id = 0, $user_id = 0, $lg_text = "", $topic, $taglist_infile = "", $book_meta = "", $book_dynasty = ""; public $messages = array('info'=>"",'error'=>"",'warning'=>"",'debug'=>""); public function SetTextFromFileId() { // remove $_postdata as input /** * Get text content from LGService by $this->file_id. * After preprocessing the text string (replace space to circle symbol, link for page number, etc), * set $this->lg_text to the processed text gotten from LGService. */ /* $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); // --- get/set text and parsing meta data from text file $lg_text = $this->ParseDataInFile($lg_text_url); $stringInput = $lg_text; $stringInput = preg_replace("/ /u", "○", $stringInput); $stringInput = preg_replace("/\n/u", "<br>", $stringInput); $stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"review_index_xml_images.php?books_id=".$this->book_id."&pages=\\1&entry=0\" target=\"_bookImg\">\\1</a>】", $stringInput); $lg_text = $stringInput; $this->lg_text = $lg_text; } public function SetBookMetadataBySectionId() { // get book_meta from $$this->get_section_metadata_by_sectionId_url $section_meta_url = $this->get_section_metadata_by_sectionId_url.$this->section_id; $section_meta = json_decode(file_get_contents($section_meta_url), true); $b = $section_meta['section']['book']; $this->book_name = $b['name']; $this->book_id = $b['id']; /* $book_meta = array(); array_push($book_meta, array($b['id'],$b['name'],$b['level1'],$b['level2'], $b['period'],$b['dynasty'], $b['start_year'], $b['end_year'],$b['line'], $b['volume'],$b['author'], $b['edition'],$b['in_jibengujiku'], $b['admin_type'])); // missing author,year,pagenumber */ /* $book_meta = array('id'=>$b['id'],'name'=>$b['name'],'level1'=>$b['level1'],'level2'=>$b['level2'], 'period'=>$b['period'],'dynasty'=>$b['dynasty'],'start_year'=>$b['start_year'], 'end_year'=>$b['end_year'],'line'=>$b['line'], 'volume'=>$b['volume'],'author'=>$b['author'],'edition'=>$b['edition'], 'in_jibengujiku'=>$b['in_jibengujiku'],'admin_type'=>$b['admin_type']); // missing author,year,pagenumber */ $book_meta->id = $b['id']; $book_meta->name = $b['name']; $book_meta->level1 = $b['level1']; $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->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']; $coordinates = $section_meta['section']['coordinates_books']; $book_meta->x = $coordinates['x']; $book_meta->y = $coordinates['y']; $book_meta->place_name = $coordinates['place_name']; $this->book_meta = $book_meta; } public function SetTextFromSectionId() { // remove $_postdata as input /** * Get text content from LGService by $this->section_id. * After preprocessing the text string (replace space to circle symbol, link for page number, etc), * set $this->lg_text to the processed text gotten from LGService. */ /* $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_url = $this->get_text_from_sectionId_url.$this->section_id; $lg_text = file_get_contents($lg_text_url); $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); $lg_text = $stringInput; $this->lg_text = $lg_text; } // This is only used on localhost public function SetTextFromLocal($_id){ $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 $this. * The previous page could be: * * (1) LGService: the first time user enters Extraction-interface, which should linked from LGService. * * (2) Extraction-interface itself: changing topic then continue to tag, saving text to LGService, reload the text from LGService. * */ if (isset($_postdata['fileId'])) { $this->file_id = $_postdata['fileId']; } if (isset($_postdata['sectionId'])) { $this->section_id = $_postdata['sectionId']; } if (isset($_postdata['text'])) { $this->lg_text = $_postdata['text']; } if (isset($_postdata['branchId'])) { $this->branch_id = $_postdata['branchId']; } if (isset($_postdata['userId'])) { $this->user_id = $_postdata['userId']; } if (isset($_postdata['topic_id'])) { $this->topic = $_postdata['topic_id']; } if (isset($_postdata['sectionName'])) { $this->section_name = $_postdata['sectionName']; } if (isset($_postdata['bookName'])) { $this->book_name = $_postdata['bookName']; } if (isset($_postdata['bookId'])) { $this->book_id = $_postdata['bookId']; } if (isset($_postdata['currentFileId'])) { $this->current_fileId = $_postdata['currentFileId']; } if (isset($_postdata['taglistArray'])) { $this->taglist_infile = json_decode($_postdata['taglistArray']); } 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); if ($cnt_list1 > $cnt_list2) { return false; } foreach ($list1 as $v1) { $cnt = 0; foreach ($list2 as $v2) { $num_field = count($v2); $matched = true; for ($i=0; $i < $num_field; $i++) { if ($v1[$i] != $v2[$i]) { $matched = false; break; } } if (!$matched) { // not match with this v2 $cnt += 1; } else { break; } } if ($cnt == $cnt_list2) { return false; } } return true; } // === for tagging === 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. */ $section_id = $this->section_id; $stringInput = $this->lg_text; $data = array(); // data array to be passed to view //$taglistArray = $this->GetTaglistArray(); //for GetTaglistByTopicId: $taglistArray = $this->GetTaglistByTopicId($this->GetTopic()); // $this->taglist_infile is set (1) from file or (2) from _postdata['taglistArray'] which comes from frontend that user decided // $this->taglist_infile is the most up-to-date taglist decided by user. Should be written into file. if( $this->TaglistSubsetIn($this->taglist_infile, $taglistArray) ) { // TaglistSubsetIn($l1,$l2): $l1 is a subset of $l2 or not $this->taglist_infile = ""; } $data['taglist_infile'] = $this->taglist_infile; // if taglist_infile == "" means taglist in file is up-to-date (will use taglist in db), otherwise means the taglist in file // book_meta $data['book_meta'] = $this->book_meta; // topic list $topiclistArray = $this->GetTopiclistArray(); $wordlistArray = $this->GetWordlistArray(); $data['stringInput'] = $stringInput; $data['taglistArray'] = $taglistArray; $data['wordlistArray'] = $wordlistArray; $data['section_id'] = $section_id; $data['topiclistArray'] = $topiclistArray; $data['default_topic_id'] = $this->GetTopic(); $topic_id = $this->GetTopic(); $data['topic_tag'] = $this->GetTopicTag($topic_id); $data['topic_name'] = $this->GetTopicName($topic_id); $data['topic_tag_ch'] = $this->GetTopicTagName($topic_id); $data['info'] = array('file_id'=>$this->file_id, 'user_id'=>$this->user_id, 'branch_id'=>$this->branch_id, 'section_id'=>$this->section_id, 'book_id'=>$this->book_id, 'book_name'=>$this->book_name,'section_name'=>$this->section_name, 'period'=>$this->book_meta->period, 'current_fileId'=>$this->current_fileId); $this->messages['debug'] .= "[Debug] "; $this->messages['debug'] .= "file_id=".$this->file_id.", section_id=".$this->section_id; $this->messages['debug'] .= ", user_id=".$this->user_id.", branch_id=".$this->branch_id.", topic_id=".$this->topic; $this->messages['debug'] .= ", book_id=".$this->book_id.", book_name=".$this->book_name.", section_name=".$this->section_name; $this->messages['debug'] .= ", current_fileId=".$this->current_fileId."<br>"; $this->messages['info'] .= "[Info] book name: ".$this->book_name; $this->messages['info'] .= ", section id: ". $this->section_id; $this->messages['info'] .= ", branch id: ".$this->branch_id; $this->messages['info'] .= ", file id: ".$this->file_id; $this->messages['info'] .= ", period: ".$this->book_meta->period; $this->messages['info'] .= "<br>"; $data['messages'] = $this->messages; return $data; } public function SaveFullText($postdata) { // locally if ($postdata['text']){ $date = date('Y_m_d_H_i_s', time()); if ( file_exists("data/parsing_files/".$postdata['filename'].".txt") ) { $oldFile = file_get_contents("data/parsing_files/".$postdata['filename'].".txt"); file_put_contents("data/parsing_files/".$postdata['filename']."_".$date.".txt", $oldFile); } if (get_magic_quotes_gpc()) { $require = stripslashes($postdata['text']); } else { $require = $postdata['text']; } $require = preg_replace("/【<a(.*?)>(.*?)<\/a>】/u", "【\\2】", $require); $require = preg_replace('/&/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) { /** * */ if (isset($response["file"])) { $response_file = $response["file"]; } if (isset($response["branch"])) { $response_branch = $response["branch"]; } $status = (string)$response["status"]; if ($status == "ok") { $this->messages['info'] .= "[Info] Saving success. <br>"; $this->file_id = (string)$response_file["id"]; $this->branch_id = (string)$response_branch["id"]; } else if ($status == "error") { // saving not success $this->messages['error'] .= "[Error] Saving Failed! ".(string)$response["message"]."<br>"; $this->messages['warning'] .= "[Warning] Please check branch ".$this->branch_id." in LGService, and modify from the latest version."; $response_currentFile = $response["currentFile"]; $this->current_fileId = (string)$response_currentFile["id"]; } } public function ReloadSetting() { if ($this->current_fileId != 0) { $this->file_id = $this->current_fileId; $this->current_fileId = 0; } } // This is only called by SaveFullTextToLGService() private function AppendMetadata($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; $text .= "<book>\n"; $text .= "<id>".$book->id."</id>\n"; $text .= "<name>".$book->name."</name>\n"; $text .= "<level1>".$book->level1."</level1>\n"; $text .= "<level2>".$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"; $text .= "<line>".$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"; $text .= "<admin_type>".$book->admin_type."</admin_type>\n"; $text .= "<place_name>".$book->place_name."</place_name>\n"; $text .= "<x>".$book->x."</x>\n"; $text .= "<y>".$book->y."</y>\n"; $text .= "</book>\n"; // --- section info --- $text .= "<section>\n"; $text .= "<id>".$this->section_id."</id>\n"; $text .= "<name>".$this->section_name."</name>\n"; $text .= "</section>\n"; // ---- taglist --- // $taglist = $this->taglist_infile; // obtain the latest taglist from db $taglist = $this->GetTaglistByTopicId($this->GetTopic()); 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 .= "</text>"; // ---- return $text; } public function SaveFullTextToLGService($_postdata) { /** * It saves the full tagged text string in postdata to LGService. * The responses returned by LGService will later be handled in */ // -------- global $AT_LOCAL; if ($_postdata['text']){ $date = date('Y_m_d_H_i_s', time()); if ( file_exists("data/parsing_files/".$_postdata['sectionId'].".txt") ) { $oldFile = file_get_contents("data/parsing_files/".$_postdata['sectionId'].".txt"); //saving in my local machine in developing phrase if ($AT_LOCAL) { file_put_contents("data/parsing_files/".$_postdata['sectionId']."_".$date.".txt", $oldFile); } } if (get_magic_quotes_gpc()) { $require = stripslashes($_postdata['text']); } else { $require = $_postdata['text']; } $require = preg_replace("/【<a(.*?)>(.*?)<\/a>】/u", "【\\2】", $require); $require = preg_replace('/&/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"; /* if ($_postdata['branchId'] == 0) { // -- new branch case $require = "<text_content>".$require."</text_content>\n"; } */ $require = $this->AppendMetadata($require); //saving in my local machine in developing phrase if ($AT_LOCAL) { file_put_contents("data/parsing_files/".$_postdata['sectionId'].".txt", $require); } } // ------ if ($_postdata['branchId'] != 0) { // -- exiting branch case $postfields = array( "text" => $require, "branchId" => $_postdata['branchId'], "userId" => $_postdata['userId'], "userPreviousFileId" => $_postdata['fileId'], ); $save_url = $this->save_to_LGService_url; } else { // -- new branch case // echo "saveNew!"; $user_id = "0"; if ($_postdata['userId']) { $user_id = $_postdata['userId']; } $postfields = array( "text" => $require, "sectionId" => $_postdata['sectionId'], "userId" => $user_id, "label" => $_postdata['label'], ); $save_url = $this->save_new_to_LGService_url; } // set up the curl resource $ch = curl_init(); curl_setopt($ch, CURLOPT_URL, $save_url); curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); curl_setopt($ch, CURLOPT_CUSTOMREQUEST, "POST"); curl_setopt($ch, CURLOPT_POST, true); curl_setopt($ch, CURLOPT_POSTFIELDS, $postfields); //curl_setopt($ch, CURLOPT_HEADER, true); curl_setopt($ch, CURLOPT_HTTPHEADER, array( 'Content-type: multipart/form-data;charset=utf-8' )); if (!$AT_LOCAL) { // execute the request $output = curl_exec($ch); } // output the profile information - includes the header //echo($output) . PHP_EOL; // close curl resource to free up system resources curl_close($ch); $response = json_decode($output, true); return $response; } // --- for regex ---- private function GetRegexFilenameById($topic_id) { $query = sprintf("SELECT regex_filename FROM `topic_regex_relation` WHERE topic_id=\"%s\"", $topic_id); $result = mysql_query($query); if (!$result) { return json_encode("Failed during selecting topic_regex_relation table."); } $filenames = array(); while ($row = mysql_fetch_assoc($result)) { array_push($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); // Get regex file from filesystem ---- $data_path = "./data/"; // get the current file path, which is getcwd(), and concatenate with "/data/" $returnArray = array(); $files1 = scandir($data_path."regex_files"); foreach ( $files1 as $file ) { if ( $file != "." && $file != ".." && $file != ".DS_Store") { foreach ($filenames as $filename) { if ($file == $filename) { $returnArray[preg_replace("/\.txt/", "", $file)] = file_get_contents( $data_path."regex_files/".$file ); break; } } } } echo json_encode($returnArray); return; } public function SaveSmartRegex($_postdata) { if ($_postdata['text']){ // --- update topic_regex_relation table --- $topic_id = $_postdata['topic_id']; $filename = $_postdata['filename'].'.txt'; // check if already existing a record for this regex file $query = "SELECT * FROM topic_regex_relation WHERE topic_id=".$topic_id." AND regex_filename='".$filename."'"; $result = mysql_query($query); if (!$result) { echo json_encode("ErrorDB"); } while ($row = mysql_fetch_assoc($result)) { if ($row && !$_postdata['forcesave']) { // promt user a comfirm to force saving or not echo json_encode("ForceSave"); return; } } if (!$_postdata['forcesave']) { $query = "INSERT INTO topic_regex_relation (topic_id, regex_filename) VALUES (".$topic_id.",'".$filename."')"; $result = mysql_query($query); if (!$result) { echo json_encode("ErrorDB"); } } // --- write to filesystem --- /* $date = date('Y_m_d_H_i_s', time()); if ( file_exists("regex_files/".$_POST['filename'].".txt") ) { $oldFile = file_get_contents("regex_files/".$_POST['filename'].".txt"); file_put_contents("regex_files/".$_POST['filename']."_".$date.".txt", $oldFile); } */ $data_path = "./data/"; // get the current file path, which is getcwd(), and concatenate with "/data/" if (get_magic_quotes_gpc()) { $require = stripslashes($_postdata['text']); } else { $require = $_postdata['text']; } 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][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"; $outputTableArray[0]["page"] = "頁數"; $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); $content = preg_replace("/<".$tag_name.">[ ]*<\/".$tag_name.">/u", "", $_content); } $contentLineArray = explode( "<br>", $content ); $count=0; $pageNow=NULL; foreach ( $contentLineArray as $value ) { $count++; $recordString = $value; $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 ) { $matchesValue[1] = preg_replace("/○/u", "", $matchesValue[1]); if ( preg_match_all("/〈(.*?)〉/u", $matchesValue[1], $matches2, PREG_SET_ORDER) ) { foreach ( $matches2 as $matches2Value ) { if ( isset($outputTableArray[$count][0][$tag_name]) ) { $outputTableArray[$count][0][$tag_name] .= ";".$matches2Value[1]; } else { $outputTableArray[$count][0][$tag_name] = $matches2Value[1]; } } } else { if ( isset($outputTableArray[$count][0][$tag_name]) ) { $outputTableArray[$count][0][$tag_name] .= ";".$matchesValue[1]; } else { $outputTableArray[$count][0][$tag_name] = $matchesValue[1]; } } } $otherString = preg_replace("/<".$tag_name.">(.*?)<\/".$tag_name.">/u", " ", $otherString); } } $otherString = preg_replace("/○/u", "", $otherString); $outputTableArray[$count]["other"] = $otherString; $outputTableArray[$count]["page"] = $pageNow; $value = preg_replace("/>/u", ">", $value); $value = preg_replace("/</u", "<", $value); $outputTableArray[$count]["full"] = $value; } foreach ( $outputTableArray as $arrayIndex => $arrayValue ) { // output each row which the topic tag // e.g. the original version is for 'person' if ( !isset($arrayValue[0][$_topic_tag]) ) { unset($outputTableArray[$arrayIndex]); } } // ----- return $outputTableArray; } // === for export table === public function ExportTable($postdata, $isFromFile) { if ($isFromFile) { $content = $this->lg_text; $topic = $this->topic; $section_id = $this->section_id; $sectionName = $this->section_name; $bookId = $this->book_id; $bookName = $this->book_name; $taglistArray = $this->taglist_infile; } else { $content = $postdata['content']; $topic = $postdata['topic']; $section_id = $postdata['sectionId']; $sectionName = $postdata['sectionName']; $bookId = $postdata['bookId']; $bookName = $postdata['bookName']; //$taglistArray = $this->GetTaglistArray(); $taglistArray = $this->GetTaglistByTopicId($topic); } // ===== $topic_tag = $this->GetTopicTag($topic); // input data: taglistArray, topic_tag, content; output: outputTableArray $outputTableArray = $this->GetTableArray($taglistArray, $topic_tag, $content); // data for view $data = array(); $data['outputTableArray'] = $outputTableArray; $data['bookId'] = $bookId; $data['section_id'] = $section_id; $data['bookName'] = $bookName; $data['sectionName'] = $sectionName; return $data; } // === for manage tag list === public function EditTaglist($_postdata) { /** */ $query = "SELECT AUTO_INCREMENT FROM INFORMATION_SCHEMA.TABLES WHERE TABLE_NAME='taglist'"; $result = mysql_query($query); if (!$result) { echo json_encode(mysql_error()); } $row = mysql_fetch_assoc($result); $largest_id = $row['AUTO_INCREMENT']-1; $topic_id = $_postdata['topic_id']; $result = $this->GetTaglistByTopicId($topic_id); $taglistArray = array(); foreach ($result as $row) { $taglistArray[$row[0]] = array($row[1], $row[2], $row[3]); //$taglistArray[$row['id']] = array($row['name'], $row['tag'], $row['color']); } $topic_tag_name = $this->GetTopicTag($topic_id); $query = "SELECT id FROM taglist WHERE taglist.tag='".$topic_tag_name."'"; $result = mysql_query($query); if (!$result) { echo json_encode(mysql_error()); } $row = mysql_fetch_assoc($result); $topic_tag_id = $row['id']; $data = array(); $data['taglistArray'] = $taglistArray; $data['topic_id'] = $topic_id; $data['largest_id'] = $largest_id; $data['topic_tag_id'] = $topic_tag_id; return $data; } private function GetTag($_postdata) { if (get_magic_quotes_gpc()) { $id = stripslashes($_postdata['id']); $name = stripslashes($_postdata['name']); $tag = stripslashes($_postdata['tag']); $color = stripslashes($_postdata['color']); } else { $id = $_postdata['id']; $name = $_postdata['name']; $tag = $_postdata['tag']; $color = $_postdata['color']; } return array($id, $name, $tag, $color); } public function NewTagElement($postdata) { if ($postdata['id']){ list($id, $name, $tag, $color) = $this->GetTag($postdata); $query1 = sprintf("INSERT INTO `taglist` (`id`, `name`, `tag`, `color`, `systemName`) VALUES (%s, %s, %s, %s, %s)", $this->GetSQLValueString($id, "int"), $this->GetSQLValueString($name, "text"), $this->GetSQLValueString($tag, "text"), $this->GetSQLValueString($color, "text"), $this->GetSQLValueString($this->systemNAME, "text")); $result1 = mysql_query($query1); // add it to topic_tag_relation table $topic_id = $postdata['topic_id']; // tag_id is $id; $query = sprintf("INSERT INTO `topic_tag_relation` (`topic_id`,`tag_id`) VALUES (%s,%s)", $topic_id, $id); $result = mysql_query($query); if (!$result) { echo json_encode("error when insert into topic_tag_relation table"); } } } public function SaveTagElement($postdata) { if ($postdata['id']){ list($id, $name, $tag, $color) = $this->GetTag($postdata); $query = sprintf("UPDATE taglist SET `name`=%s, `tag`=%s, `color`=%s WHERE `id`=%s", $this->GetSQLValueString($name, "text"), $this->GetSQLValueString($tag, "text"), $this->GetSQLValueString($color, "text"), $this->GetSQLValueString($id, "int")); $result = mysql_query($query); } } public function DeleteTag($postdata) { if ($postdata['id']) { $queryInsert = sprintf("DELETE FROM `taglist` WHERE `id` = %s", stripslashes($postdata['id'])); $resultInsert = mysql_query($queryInsert); } } // === for config topic === public function ConfigTagsInTopic($postdata) { /** * */ $topic = $postdata['topic']; $result = $this->GetTopicById($topic); $row = mysql_fetch_assoc($result); $topic_name_en = $row['name_en']; $topic_name_ch = $row['name_ch']; $topic_name_pinyin = $row['name_pinyin']; /* $query = "SELECT taglist.*, topic_tag_relation.topic_id FROM taglist LEFT JOIN topic_tag_relation ON taglist.id = topic_tag_relation.tag_id ORDER BY `topic_id`"; $result = mysql_query($query); if (!$result) { return json_encode("Failed during selecting/joining taglist and topic_tag_relation table."); } $taglistArray = array(); while ($row = mysql_fetch_assoc($result)) { array_push($taglistArray, array('id'=>$row['id'],'name'=>$row['name'], 'tag'=>$row['tag'], 'color'=>$row['color'], 'topic_id'=>$row['topic_id']) ); } */ // ------ $query = "SELECT taglist.*, topic_tag_relation.topic_id FROM taglist LEFT JOIN topic_tag_relation ON taglist.id = topic_tag_relation.tag_id ORDER BY `topic_id`"; $result = mysql_query($query); if (!$result) { return json_encode("Failed during selecting/joining taglist and topic_tag_relation table."); } $tag_intopic = array(); $tag_others = array(); $tag_tmp_others = array(); while ($row = mysql_fetch_assoc($result)) { if ($row['topic_id'] == $topic) { array_push($tag_intopic, array('id'=>$row['id'],'name'=>$row['name'], 'tag'=>$row['tag'], 'color'=>$row['color'], 'topic_id'=>$row['topic_id'])); } else { array_push($tag_tmp_others, array('id'=>$row['id'],'name'=>$row['name'], 'tag'=>$row['tag'], 'color'=>$row['color'], 'topic_id'=>$row['topic_id'])); } } // --- check if there's any duplicated tags in tag_tmp_others. remove the duplicated tags $num_others = count($tag_tmp_others); for ($i=0; $i < $num_others; $i++) { $cnt = 0; for ($j=$i+1; $j < $num_others; $j++) { if ($tag_tmp_others[$i]['tag'] == $tag_tmp_others[$j]['tag']) { break; } else { $cnt++; } } if ($cnt == ($num_others-$i-1) ) { $row = $tag_tmp_others[$i]; array_push($tag_others, array('id'=>$row['id'],'name'=>$row['name'], 'tag'=>$row['tag'], 'color'=>$row['color'], 'topic_id'=>$row['topic_id']) ); } } // --- remove duplicated tags in tag_others that is duplicated with tags in tag_intopic $tag_tmp_others = $tag_others; $tag_others = array(); foreach ($tag_tmp_others as $tmp) { $cnt = 0; foreach ($tag_intopic as $intopic) { if ($tmp['tag'] == $intopic['tag']) { break; } else { $cnt ++; } } if ($cnt == count($tag_intopic)) { // not appear in $tag_intopic array_push($tag_others, $tmp); } } // ----- $data = array(); //$data['taglistArray'] = $taglistArray; $data['topic'] = $topic; $data['topic_name'] = array('name_en'=>$topic_name_en,'name_ch'=>$topic_name_ch,'name_pinyin'=>$topic_name_pinyin); $data['tag_intopic'] = $tag_intopic; $data['tag_others'] = $tag_others; return $data; } public function UpdateTagsInTopic($_postdata) { $topic_id = $_postdata['topic_id']; $tag_ids = json_decode(str_replace('\\', '', $_postdata['ids'])); // update topic_tag_relation by tags_ids array as `tag_id` and topic_id as `topic_id` // --- add new topic_tag_relation --- foreach ($tag_ids as $tag_id) { $query = "SELECT * FROM topic_tag_relation WHERE tag_id=".$tag_id; $result = mysql_query($query); if (!$result) { echo json_encode("error when select from topic_tag_relation"); } $topic_tag = array(); $flag = false; while ($row = mysql_fetch_assoc($result)) { if ($row['topic_id'] == $topic_id) { $flag = true; break; } } if (!$flag) { // insert a row into topic_tag_relation table $queryUpdate = "INSERT INTO topic_tag_relation (topic_id, tag_id) VALUES (".$topic_id.",".$tag_id.")"; $resultUpdate = mysql_query($queryUpdate); if (!$resultUpdate) { return json_encode("error when insert topic_tag_relation table"); } } } // --- remove tags from this topic --- $query = "SELECT * FROM topic_tag_relation WHERE topic_id=".$topic_id; $result = mysql_query($query); if (!$result) { echo json_encode("error when select from topic_tag_relation"); } while ($row = mysql_fetch_assoc($result)) { $cnt = 0; foreach ($tag_ids as $tag_id) { if ($row['tag_id'] == $tag_id) { break; } else { $cnt ++; } } $_id = $row['id']; if ($cnt == count($tag_ids)) { // delete row with (topic_id, tag_ids) $queryDelete = "DELETE FROM topic_tag_relation WHERE id=".$_id; $resultDelete = mysql_query($queryDelete); if (!$resultDelete) { echo json_encode("error when delete from topic_tag_relation"); } } } /* $query = "SELECT * FROM topic_tag_relation"; $result = mysql_query($query); if (!$result) { echo json_encode("error when select from topic_tag_relation"); } $topic_tag = array(); while ($row = mysql_fetch_assoc($result)) { array_push($topic_tag, array('tag_id'=>$row['tag_id'], 'topic_id'=>$row['topic_id'])); } foreach ($topic_tag as $value) { $flag = false; foreach ($tag_ids as $tag_id) { if ($value['tag_id'] == $tag_id) { //update its topic_id to $topic_id $queryUpdate = "UPDATE topic_tag_relation SET topic_id=".$topic_id." WHERE tag_id=".$tag_id; $resultUpdate = mysql_query($queryUpdate); if (!$resultUpdate) { return json_encode("error when update topic_tag_relation table"); } $flag = true; break; } } if (!$flag && $value['topic_id'] == $topic_id) { // set its topic_id to 0, indicating unsigned $queryUpdate = "UPDATE topic_tag_relation SET topic_id=0 WHERE tag_id=".$value['tag_id']; $resultUpdate = mysql_query($queryUpdate); if (!$resultUpdate) { return json_encode("error when update topic_tag_relation table"); } } } */ } private function GetTaglistByTopicId($topic_id) { $taglistArray = array(); // select taglist ids from topic_tag_relation table $query = sprintf("SELECT * FROM `topic_tag_relation` WHERE `topic_id`='%s'", $topic_id); $result = mysql_query($query); if (!$result) { return json_encode("Failed during selecting topic_tag_relation table."); } $taglist_ids = array(); while ($row = mysql_fetch_assoc($result)) { array_push($taglist_ids, $row['tag_id']); } // select taglist by tag ids foreach ($taglist_ids as $tag_id) { $query = sprintf("SELECT * FROM `taglist` WHERE `id`='%s'", $tag_id); $result = mysql_query($query); if (!$result) { echo mysql_error(); return json_encode("Failed during selecting taglist table."); } $row = mysql_fetch_assoc($result); array_push($taglistArray, array( $row['id'], $row['name'], $row['tag'], $row['color'] )); } return $taglistArray; } public function SetTopic($topic) { $this->topic = $topic; } private function GetTopic() { return $this->topic; } private function GetTopiclistArray() { $topiclistArray = array(); $result = $this->GetTopicList(); while ($row = mysql_fetch_assoc($result)) { //array_push($topiclistArray, array('id'=>$row['id'],'name'=>$row['name'],'tag'=>$row['tag'])); array_push($topiclistArray, array('id'=>$row['id'],'tag'=>$row['tag'],'name_en'=>$row['name_en'],'name_ch'=>$row['name_ch'],'name_pinyin'=>$row['name_pinyin'],)); } return $topiclistArray; } private function GetTopicTag($topic_id) { $result = $this->GetTopicById($topic_id); $row = mysql_fetch_assoc($result); $tag = $row['tag']; return $tag; } private function GetTopicName($topic_id) { $result = $this->GetTopicById($topic_id); $row = mysql_fetch_assoc($result); //$name = $row['name']; $name = array('name_en'=>$row['name_en'], 'name_ch'=>$row['name_ch'], 'name_pinyin'=>$row['name_pinyin']); return $name; } private function GetTopicTagName($topic_id) { $topic_tag = $this->GetTopicTag($topic_id); $query = "SELECT * FROM `taglist` WHERE tag='".$topic_tag."'"; $result = mysql_query($query); $row = mysql_fetch_assoc($result); return $row['name']; } // =========================== // === for manage wordlist === public function EditWordlist() { /** * EditWordlist shows the wordlist in a new window. * User can view each one of the wordlist and edit it, also s/he can create a new wordlist here. */ $result = $this->GetWordlist(); $wordlistArray = array(); while ($row = mysql_fetch_assoc($result)) { $wordlistArray[$row['id']] = $row['name']; } $data = array(); $data['wordlistArray'] = $wordlistArray; return $data; } public function AddNewList($postdata) { if ($postdata['text']){ if (get_magic_quotes_gpc()) { $name = stripslashes($postdata['text']); } else { $name = $postdata['text']; } $query1 = sprintf("INSERT INTO `wordlist` (`name`, `systemName`) VALUES (%s, %s)", $this->GetSQLValueString($name, "text"), $this->GetSQLValueString($this->systemNAME, "text")); $result1 = mysql_query($query1); file_put_contents( "data/wordlist/".mysql_insert_id().".txt", "(empty now)"); } } public function SaveWordlist($postdata) { if ($postdata['text']){ $date = date('Y_m_d_H_i_s', time()); if ( file_exists("data/wordlist/".$postdata['filename'].".txt") ) { $filename = "data/wordlist/".$postdata['filename']."_".$date.".txt"; $oldFile = file_get_contents("data/wordlist/".$postdata['filename'].".txt"); file_put_contents($filename, $oldFile); } /*else { $filename = "data/wordlist/".$postdata['filename'].".txt"; } */ if (get_magic_quotes_gpc()) { $require = stripslashes($postdata['text']); } else { $require = $postdata['text']; } $require = preg_replace("/<br>/u", "<br>", $require); file_put_contents("data/wordlist/".$postdata['filename'].".txt", $require); } /* if ($postdata['text']){ $date = date('Y_m_d_H_i_s', time()); if ( file_exists("data/wordlist/".$postdata['filename'].".txt") ) { $oldFile = file_get_contents("data/wordlist/".$postdata['filename'].".txt"); file_put_contents("data/wordlist/".$postdata['filename']."_".$date.".txt", $oldFile); } if (get_magic_quotes_gpc()) { $require = stripslashes($postdata['text']); } else { $require = $postdata['text']; } // $require = preg_replace("/<br>/u", "", $require); file_put_contents("data/wordlist/".$postdata['filename'].".txt", $require); } */ } // ======================================= private function sortFunction($a,$b) { return strlen($b)-strlen($a); } private function GetSectionId() { if (is_numeric($this->section_id)) { return $this->section_id; } else { return json_encode("Error: No section id"); } } private function GetSectionInfo() { $section_id = $this->GetSectionId(); if (!is_numeric($section_id)){ return $section_id; } $result = $this->GetSectionsById($section_id); while ($row = mysql_fetch_assoc($result)) { $bookId=$row['books_id']; $startPage=$row['start_page']; $endPage=$row['end_page']; $sectionName = $row['name']; } $data = array(); $data['bookId'] = $bookId; $data['startPage'] = $startPage; $data['endPage'] = $endPage; $data['sectionName'] = $sectionName; return $data; } private function ParseDataInFile($filename) { $text = file_get_contents($filename); $xml = simplexml_load_string($text); //or die("Error: Cannot load from xml string"); if (!$xml) { // when file created by section_id, read the plain text from file_get_contents return $text; } $this->topic = (string)$xml->topic; // set topic id // get taglist in file $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 )); } if ($taglistArray) { $this->taglist_infile = $taglistArray; } // --- get book meta data from file, replaced by SetBookMetaDataBySectionId(), which retrives book meta data from LGService /* $book_meta = $xml->book; $book_metaArray = array(); foreach ($book_meta as $row) { array_push($book_metaArray, array((string)$row->id,(string)$row->name,(string)$row->level1,(string)$row->level2, (string)$row->period,(string)$row->dynasty,(string)$row->start_year,(string)$row->end_year,(string)$row->line, (string)$row->volume,(string)$row->author,(string)$row->edition,(string)$row->in_jibengujiku,(string)$row->admin_type )); } if ($book_metaArray) { $this->book_meta = $book_metaArray; } */ // ----- // TODO: get section_id, section_name from file if ($this->section_id == 0 && isset($xml->section)) { if ($xml->section) { $this->section_id = (string)$xml->section->id; $this->section_name = (string)$xml->section->name; } } // book meta data if (!isset($this->book_id) && isset($xml->book)) { $this->book_id = (string)$xml->book->id; $this->book_name = (string)$xml->book->name; } $contentString = (string)($xml->text_content->asXML()); $removed_str = array("<text_content>","</text_content>"); $new_contentString = str_replace($removed_str, "", $contentString); return $new_contentString; } private function GetSectionContent() { /** This is only been called by SetTextFromLocal(). */ $section_id = $this->GetSectionId(); $section_info = $this->GetSectionInfo(); $bookId = $section_info['bookId']; $startPage = $section_info['startPage']; $endPage = $section_info['endPage']; $this->section_name = $section_info['sectionName']; $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 $stringInput = $this->ParseDataInFile($filename); // ---- // 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); $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); $result = mysql_query($query); if (!$result) { return json_encode("Failed during selecting content table."); } while ($row = mysql_fetch_assoc($result)) { $contentString.="【".$row['line']."】".$row['content']."\n"; } // 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); } /* // get book_meta from books table in db on localhost $book_meta = array(); $books_result = $this->GetBooksById($bookId); while ($row = mysql_fetch_assoc($books_result)) { array_push($book_meta, array($row['id'],$row['name'],$row['author'],(string)$row['start_year'],(string)$row['line'],(string)$row['dynasty'])); // use 'start_year' as year, 'line' is pagenumber } $this->book_meta = $book_meta; */ return $stringInput; } private function GetDataPath() { return getcwd()."/data/"; // get the current file path, which is getcwd(), and concatenate with "/data/" } private function GetTaglistArray() { $taglistArray = array(); $result = $this->GetTaglist(); while ($row = mysql_fetch_assoc($result)) { array_push($taglistArray, array( $row['id'], $row['name'], $row['tag'], $row['color'] )); } return $taglistArray; } private function GetWordlistArray() { $wordlistArray=""; $result = $this->GetWordlist(); while ($row = mysql_fetch_assoc($result)) { $listString = file_get_contents("data/wordlist/".$row['id'].".txt"); $listString = preg_replace("/<div>/u", "\n", $listString); $listString = preg_replace("/<\/div>/u", "", $listString); $listString = preg_replace("/<span(.*?)>/u", "", $listString); $listString = preg_replace("/<\/span>/u", "", $listString); //$listString = preg_replace("/\n/u", "|", $listString); $wordlistArray2 = explode( "\n", $listString ); //usort($wordlistArray2,'sortFunction'); foreach ( $wordlistArray2 as $index=>$value ) { $wordlistArray2[$index] = implode("○?", preg_split("/(?<!^)(?!$)/u", $value)); } foreach ( $wordlistArray2 as $index=>$value ) { if ($value=="") unset($wordlistArray2[$index]); } $listString = implode("|", $wordlistArray2); if ( $listString[0]=="|" ) $listString = substr($listString, 1); $wordlistArray[] = array( $row['id'], $row['name'], $listString ); } return $wordlistArray; } private function GetBooksInfo($bookId) { $result = $this->GetSectionsById($bookId); while ($row = mysql_fetch_assoc($result)) { $bookName = $row['name']; } $data = array(); $data['bookName'] = $bookName; return $data; } } ?>