Merge pull request #254 from FriendsOfREDAXO/url2

Url Addon Version 2 hinzugefügt
FriendsOfREDAXO · Apr 7, 2020 · 9b35bb7 · 9b35bb7
2 parents 7f290c8 + 439abff
commit 9b35bb7
Show file tree

Hide file tree

Showing 44 changed files with 775 additions and 320 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,6 +1,8 @@
 # Änderungen von search_it
 
-- bei schrittweiser Indexierung sind die Artikel in der Ausgabe verlinkt
+## Version 6.7.0 (2020-04-02)
+- URLs aus dem URL Addon (>= 2.0) können indexiert werden. @TobiasKrais
+- bei schrittweiser Indexierung sind die Artikel in der Ausgabe verlinkt @alexplusde
 - minimale PHP Version ergänzt @staabm
 - install.sql -> install.php
 - wird eine Tabelle oder Spalte gelöscht, die in "zusätzliche Datenquelle" angegeben ist und neuindexiert -> woops #222 thx @alexplusde

diff --git a/README.md b/README.md
@@ -53,4 +53,5 @@ https://github.com/FriendsOfREDAXO
 Search it basiert auf: [RexSearch (Xong) für REDAXO 4](https://github.com/xong/rexsearch)  
 [Norbert Micheel](https://github.com/tyrant88/) Portierung für R5 und aktiven Entwicklung
 [Alexander Walther](https://github.com/skerbis) Dokumentation und Hilfe  
-[und weitere Entwickler...](https://github.com/FriendsOfREDAXO/search_it/graphs/contributors)
+[Tobias Krais](https://github.com/tobiaskrais) URL Addon (>= 2.0) Support
+[und weitere Entwickler...](https://github.com/FriendsOfREDAXO/search_it/graphs/contributors)
diff --git a/boot.php b/boot.php
@@ -8,6 +8,13 @@
         define('SEARCH_IT_ART_NOTOK',5);
         define('SEARCH_IT_ART_404',6);
 
+        define('SEARCH_IT_URL_EXCLUDED',0);
+        define('SEARCH_IT_URL_GENERATED',2);
+        define('SEARCH_IT_URL_REDIRECT',3);
+        define('SEARCH_IT_URL_ERROR',4);
+        define('SEARCH_IT_URL_NOTOK',5);
+        define('SEARCH_IT_URL_404',6);
+
         define('SEARCH_IT_FILE_NOEXIST',0);
         define('SEARCH_IT_FILE_XPDFERR_OPENSRC',1);
         define('SEARCH_IT_FILE_XPDFERR_OPENDEST',2);

diff --git a/functions/functions_search_it.php b/functions/functions_search_it.php
@@ -3,14 +3,14 @@
 function search_it_getArticles($cats = false) {
     $si = rex_addon::get('search_it');
 
-    $whereCats = array();
+    $whereCats = [];
     if(is_array($cats)){
         foreach($cats as $catID) {
             $whereCats[] = "path LIKE '%|" . $catID . "|%'";
         }
     }
 
-    $return = array();
+    $return = [];
     $query = 'SELECT id,name,path FROM '.rex::getTable('article').' WHERE 1';
     if( !$si->getConfig('indexoffline') ) {
         $query .= ' AND status = 1';
@@ -31,19 +31,19 @@ function search_it_getArticles($cats = false) {
 function search_it_getCategories($_ignoreoffline = true, $_onlyIDs = false, $_cats = false) {
     $si = rex_addon::get('search_it');
 
-    $return = array();
+    $return = [];
 
     if(!empty($_cats)){
-        $whereCats = array();
-        $sqlCats = array();
+        $whereCats = [];
+        $sqlCats = [];
         if(is_array($_cats)){
             foreach($_cats as $catID){
                 $whereCats[] = "path LIKE '%|".intval($catID)."|%'";
                 $sqlCats[] = intval($catID);
             }
         }
 
-        $return = array();
+        $return = [];
         $query = 'SELECT id,catname,path FROM '.rex::getTable('article').' WHERE startarticle = 1';
         if( !$si->getConfig('indexoffline') AND $_ignoreoffline ) {
             $query .= ' AND status = 1';
@@ -94,9 +94,9 @@ function search_it_getDirs($_startDir = '', $_getSubdirs = false){
     if (@is_dir($_SERVER['DOCUMENT_ROOT'] . $_startDir)){
         $dirs2 = array_diff(scandir($_SERVER['DOCUMENT_ROOT'] . $_startDir), array('.', '..'));
     } else {
-        return array();
+        return [];
     }
-    $dirs = array();
+    $dirs = [];
     foreach ($dirs2 as $k => $dir){
         if (@is_dir($_SERVER['DOCUMENT_ROOT'] . $_startDir . '/' . $dir)) {
             $dirs[$_SERVER['DOCUMENT_ROOT'] . $_startDir . '/' . $dir] = utf8_encode($_startDir . '/' . $dir);
@@ -106,14 +106,14 @@ function search_it_getDirs($_startDir = '', $_getSubdirs = false){
         return $dirs;
     }
 
-    $return = array();
+    $return = [];
     while(!empty($dirs)){
         $dir = array_shift($dirs);
 
         $depth = substr_count($dir, '/') - $startDepth;
         if(@is_dir($_SERVER['DOCUMENT_ROOT'].$dir) AND $depth <= $si->getConfig('dirdepth')){
             $return[$_SERVER['DOCUMENT_ROOT'].$dir] = utf8_encode($dir);
-            $subdirs = array();
+            $subdirs = [];
             foreach(array_diff(scandir($_SERVER['DOCUMENT_ROOT'].$dir), array( '.', '..' )) as $subdir) {
                 if (@is_dir($_SERVER['DOCUMENT_ROOT'] . $dir . '/' . $subdir)) {
                     $subdirs[] = $dir . '/' . $subdir;
@@ -126,10 +126,10 @@ function search_it_getDirs($_startDir = '', $_getSubdirs = false){
     return $return;
 }
 
-function search_it_getFiles($_startDir = '', $_fileexts = array(), $_getSubdirs = false){
+function search_it_getFiles($_startDir = '', $_fileexts = [], $_getSubdirs = false){
     $si = rex_addon::get('search_it');
 
-    $return = array();
+    $return = [];
     $fileextPattern='';
 
     if(!empty($_fileexts)) {
@@ -142,9 +142,9 @@ function search_it_getFiles($_startDir = '', $_fileexts = array(), $_getSubdirs
     if(@is_dir($_SERVER['DOCUMENT_ROOT'].$_startDir)) {
         $dirs2 = array_diff(scandir($_SERVER['DOCUMENT_ROOT'] . $_startDir), array('.', '..'));
     } else {
-        return array();
+        return [];
     }
-    $dirs = array();
+    $dirs = [];
     foreach($dirs2 as $k => $dir){
         if(@is_dir($_SERVER['DOCUMENT_ROOT'].$_startDir.'/'.$dir)) {
             $dirs[$_SERVER['DOCUMENT_ROOT'] . $_startDir . '/' . $dir] = $_startDir . '/' . $dir;
@@ -162,7 +162,7 @@ function search_it_getFiles($_startDir = '', $_fileexts = array(), $_getSubdirs
 
         $depth = substr_count($dir, '/') - $startDepth;
         if(@is_dir($_SERVER['DOCUMENT_ROOT'].$dir) AND $depth <= $si->getConfig('dirdepth')){
-            $subdirs = array();
+            $subdirs = [];
             foreach(array_diff(scandir($_SERVER['DOCUMENT_ROOT'].$dir), array( '.', '..' )) as $subdir) {
                 if (@is_dir($_SERVER['DOCUMENT_ROOT'] . $dir . '/' . $subdir)) {
                     $subdirs[] = $dir . '/' . $subdir;
@@ -186,7 +186,7 @@ function search_it_handle_extensionpoint($_ep){
 
     $_params = $_ep->getParams();
     $_subject = $_ep->getSubject();
-    $includeColumns = is_array(rex_addon::get('search_it')->getConfig('include')) ? rex_addon::get('search_it')->getConfig('include') : array();
+    $includeColumns = is_array(rex_addon::get('search_it')->getConfig('include')) ? rex_addon::get('search_it')->getConfig('include') : [];
     $search_it = new search_it();
 
     switch($_ep->getName()){
@@ -297,14 +297,19 @@ function search_it_handle_extensionpoint($_ep){
     $search_it->deleteCache();
 }
 
-function search_it_getSettingsFormSection($id = '', $title = '&nbsp;', $elements = array(), $ownsection = 'info', $collapse = false ){
+function search_it_getSettingsFormSection($id = '', $title = '&nbsp;', $elements = [], $ownsection = 'info', $collapse = false ) {
 
     $return = '<fieldset id="'.$id.'">';
     $formElements = [];
     $fragment = new rex_fragment();
 
-    foreach($elements as $element){
-        $n = array();
+    foreach($elements as $element) {
+		if(count($element) == 0) {
+			// Skip empty elements
+			continue;
+		}
+
+        $n = [];
 
         switch($element['type']){
             // HIDDEN
@@ -440,17 +445,17 @@ function search_it_config_unserialize($_str){
         return $conf;
     }
 
-    $return = array();
+    $return = [];
     if(is_array($conf)){
         foreach(unserialize($_str) as $k => $v){
             if(is_array($v)){
-                $return[$k] = array();
+                $return[$k] = [];
                 foreach($v as $k2 => $v2) {
                     if (is_array($v2)) {
-                        $return[$k][$k2] = array();
+                        $return[$k][$k2] = [];
                         foreach ($v2 as $k3 => $v3) {
                             if (is_array($v3)) {
-                                $return[$k][$k2][$k3] = array();
+                                $return[$k][$k2][$k3] = [];
                                 foreach ($v3 as $k4 => $v4) {
                                     $return[$k][$k2][$k3][$k4] = stripslashes($v4);
                                 }
@@ -704,7 +709,7 @@ function soundex_ger($word)
     //echo "<br>code2: <b>" . $code . "</b><br />";
     // entfernen aller Codes "0" ausser am Anfang
     $codelen      = strlen($code);
-    $num          = array();
+    $num          = [];
     $num          = str_split($code);
     $phoneticcode = $num[0];
 
@@ -743,7 +748,7 @@ function search_it_search_highlighter_output($_ep){
 function search_it_search_highlighter_getHighlightedText($_subject, $_searchString, $_tags){
     preg_match_all('~(?:(\+*)"([^"]*)")|(?:(\+*)(\S+))~is', $_searchString, $matches, PREG_SET_ORDER);
 
-    $searchterms = array();
+    $searchterms = [];
     foreach ($matches as $match) {
         if (count($match) == 5) {
             // words without double quotes (foo)
@@ -770,6 +775,38 @@ function ($match){
     return $all;
 }
 
+/**
+ * Prüft ob das URL Addon in der kompatiblen Version verfügbar ist.
+ * @return bool
+ */
+function search_it_isUrlAddOnAvailable() {
+	return ( rex_addon::get('url')->isAvailable() && rex_string::versionCompare(\rex_addon::get('url')->getVersion(), '1.5', '>='));
+}
+
+/**
+ * Ermittelt den Namen der Tabelle des URL Addons
+ * @return string
+ */
+function search_it_getUrlAddOnTableName() {
+
+    if (search_it_isUrlAddOnAvailable()) {
+
+        $tableName = null;
+
+        $sql = rex_sql::factory();
+        $allTables = $sql->getTables();
+
+        foreach( $allTables as $oneTable ) {
+            if ( strpos($oneTable, \Url\UrlManagerSql::TABLE_NAME) !== false ) {
+                $tableName = $oneTable;
+                break;
+            }
+        }
+
+        return $tableName;
+    }
+}
+
 // ex reindex plugin
 function search_it_reindex_cols($_ep){
     if ($_ep->getSubject() instanceof Exception) {
@@ -778,7 +815,7 @@ function search_it_reindex_cols($_ep){
 
     $_params = $_ep->getParams();
 
-    $includeColumns = is_array(rex_addon::get('search_it')->getConfig('include')) ? rex_addon::get('search_it')->getConfig('include') : array();
+    $includeColumns = is_array(rex_addon::get('search_it')->getConfig('include')) ? rex_addon::get('search_it')->getConfig('include') : [];
     $search_it = new search_it;
 
     $didcol = false;

diff --git a/install.php b/install.php
@@ -46,5 +46,4 @@
     ->ensureColumn(new rex_sql_column('count', 'int(11)', false, '1'))
     ->setPrimaryKey('id')
     ->ensureIndex(new rex_sql_index('keyword', ['keyword', 'clang'], rex_sql_index::UNIQUE))
-    ->ensure();
-
+    ->ensure();
diff --git a/lang/de_de.lang b/lang/de_de.lang
@@ -27,6 +27,7 @@ search_it_settings_title_indexmode = Indexierung
 search_it_settings_indexoffline = Offline-Artikel indexieren
 search_it_settings_automaticindex_label = Artikel (ADD, EDIT, DELETE) automatisch (de)indexieren
 search_it_settings_reindex_cols_onforms_label = Reindexieren aller Spalten, wenn Tabellen mit YForm oder form bearbeitet werden
+search_it_settings_index_url_addon_label = URLs aus dem URL Addon (Version >=2) indexieren
 
 search_it_settings_http_authbasic = HTTP Basic AUTH ( .htaccess Passwortschutz)
 search_it_settings_http_auth_desc = Wenn ein Zugriffsschutz die Website schützt, kann hier ein Login hinterlegt werden, um die Indexierung zu ermöglichen
@@ -96,6 +97,7 @@ search_it_generate_duration = Dauer:
 search_it_generate_timeleft = Verbleibend:
 search_it_generate_articles = Artikel neu-indexieren
 search_it_generate_columns = Tabellen neu-indexieren
+search_it_generate_urls = URLs aus URL Addon neu-indexieren
 
 search_it_generate_article_excluded = nicht indexiert, Artikel wurde ausgeschlossen
 search_it_generate_article_done = indexiert
@@ -116,6 +118,7 @@ search_it_generate_media_error_pdf2 = Anderer PDF Fehlerr
 search_it_generate_media_error_output = XPDF-Fehler: Fehler beim Öffnen einer Ausgabedatei
 search_it_generate_media_error_permissions = XPDF-Fehler: PDF Rechte fehlen
 search_it_generate_media_empty = Medium is leer oder kein Inhalt konnte extrahiert werden
+search_it_generate_url_excluded = nicht indexiert, URL wurde ausgeschlossen
 
 search_it_settings_fileext_header = Datei-Inhalte durchsuchen
 search_it_settings_fileext_label = Dateiendungen (z.B. <code>txt,csv,pdf</code>)<br />(frei lassen für beliebige Dateien)

diff --git a/lang/en_gb.lang b/lang/en_gb.lang
@@ -27,6 +27,7 @@ search_it_settings_title_indexmode = Indexing
 search_it_settings_indexoffline = Index offline articles
 search_it_settings_automaticindex_label = Index and deindex articles automatically (ADD, EDIT, DELETE)
 search_it_settings_reindex_cols_onforms_label = Reindex all columns, if tables are changed through YForm or form
+search_it_settings_index_url_addon_label = Index URL addon (version >=2) URLs
 
 search_it_settings_http_authbasic = HTTP Basic AUTH ( .htaccess protection)
 search_it_settings_http_auth_desc = If the website i s protected through HTTP Basic Auth, you can put a valid login here, in order to allow indexing
@@ -96,6 +97,7 @@ search_it_generate_duration = Time:
 search_it_generate_timeleft = Remaining:
 search_it_generate_articles = reindex articles
 search_it_generate_columns = reindex tables
+search_it_generate_urls = reindex url addon urls
 
 search_it_generate_article_excluded = not indexed, article was excluded
 search_it_generate_article_done = indexed
@@ -116,6 +118,7 @@ search_it_generate_media_error_pdf2 = Other PDF Error
 search_it_generate_media_error_output = XPDF-error: Error opening an output file
 search_it_generate_media_error_permissions = XPDF-error: Error related to PDF permissions
 search_it_generate_media_empty = Media is empty or could not be extracted
+search_it_generate_url_excluded = not indexed, url was excluded
 
 search_it_settings_fileext_header = File search
 search_it_settings_fileext_label = Extensions (i.e. 'txt,csv,pdf' <br />(leave empty for any files)

diff --git a/lang/es_es.lang b/lang/es_es.lang
@@ -27,6 +27,7 @@ search_it_settings_title_indexmode = Indexación
 search_it_settings_indexoffline = Artículo sin conexión de índice
 search_it_settings_automaticindex_label = Automáticamente indexar artículos (AGREGAR, EDITAR, ELIMINAR)
 search_it_settings_reindex_cols_onforms_label = Reindexar todas las columnas al editar tablas con YForm o formulario
+search_it_settings_index_url_addon_label = Index URL addon (version >=2) URLs
 
 search_it_settings_http_authbasic = HTTP Basic AUTH (protección de contraseñas .htaccess)
 search_it_settings_http_auth_desc = Si una protección de acceso protege el sitio web, se puede almacenar un inicio de sesión aquí para permitir la indexación
@@ -96,6 +97,7 @@ search_it_generate_duration = Duración:
 search_it_generate_timeleft = Restante:
 search_it_generate_articles = Re-indexar artículos
 search_it_generate_columns = Re-index tables
+search_it_generate_urls = reindex url addon urls
 
 search_it_generate_article_excluded = No indexado, el artículo fue excluido
 search_it_generate_article_done = indexado
@@ -116,6 +118,7 @@ search_it_generate_media_error_pdf2 = Otro error de PDF
 search_it_generate_media_error_output = Error de XPDF: error al abrir un archivo de salida
 search_it_generate_media_error_permissions = Error de XPDF: faltan los derechos de PDF
 search_it_generate_media_empty = El medio está vacío o no se pudo extraer contenido
+search_it_generate_article_excluded = No indexado, el url fue excluido
 
 search_it_settings_fileext_header = Buscar contenido de archivos
 search_it_settings_fileext_label = Extensiones de archivos (por ejemplo, <code>txt, csv, pdf</code>)<br/> (déjelo en blanco para cualquier archivo)

diff --git a/lang/pt_br.lang b/lang/pt_br.lang
@@ -27,6 +27,7 @@ search_it_settings_title_indexmode = Indexação
 search_it_settings_indexoffline = Indexar artigos offline
 search_it_settings_automaticindex_label = Indexar e de-indexar artigos automaticamente (ADD, EDIT, DELETE)
 search_it_settings_reindex_cols_onforms_label = Re-indexar todas as colunas se as tabelas foram modificadas com Yform ou form
+search_it_settings_index_url_addon_label = Index URL addon (version >=2) URLs
 
 search_it_settings_http_authbasic = HTTP Basic AUTH ( .htaccess Passwortschutz)
 search_it_settings_http_auth_desc = Wenn ein Zugriffsschutz die Website schützt, kann hier ein Login hinterlegt werden, um die Indexierung zu ermöglichen
@@ -96,6 +97,7 @@ search_it_generate_duration = Tempo:
 search_it_generate_timeleft = Faltante:
 search_it_generate_articles = Re-indexar artigos
 search_it_generate_columns = Re-indexar tabelas
+search_it_generate_urls = reindex url addon urls
 
 search_it_generate_article_excluded = not indexed, article was excluded
 search_it_generate_article_done = indexed
@@ -116,6 +118,7 @@ search_it_generate_media_error_pdf2 = Other PDF Error
 search_it_generate_media_error_output = XPDF-error: Error opening an output file
 search_it_generate_media_error_permissions = XPDF-error: Error related to PDF permissions
 search_it_generate_media_empty = Media is empty or could not be extracted
+search_it_generate_article_excluded = not indexed, url was excluded
 
 search_it_settings_fileext_header = Arquivo de busva
 search_it_settings_fileext_label = Extensões (ex: 'txt,csv,pdf' <br />( deixar vazio para arquivos desejados)

diff --git a/lang/sv_se.lang b/lang/sv_se.lang
@@ -27,6 +27,7 @@ search_it_settings_title_indexmode = Indexering
 search_it_settings_indexoffline = Indexera offline artiklar
 search_it_settings_automaticindex_label = Indexera och deindexera artikel (ADD, EDIT, DELETE) automatisk
 search_it_settings_reindex_cols_onforms_label = Reindexera alla kolumner, om tabeller ändras via YForm eller form
+search_it_settings_index_url_addon_label = Index URL addon (version >=2) URLs
 
 search_it_settings_http_authbasic = HTTP Basic AUTH ( .htaccess lösenordskydd)
 search_it_settings_http_auth_desc = Om webbplatsen skyddas mot åtkomst kan en inloggning sparas här för att aktivera indexering
@@ -96,6 +97,7 @@ search_it_generate_duration = Tid:
 search_it_generate_timeleft = Förblivande tid:
 search_it_generate_articles = Nyindexera artiklar
 search_it_generate_columns = Nyindexera tabeller
+search_it_generate_urls = reindex url addon urls
 
 search_it_generate_article_excluded = not indexed, article was excluded
 search_it_generate_article_done = indexed
@@ -116,6 +118,7 @@ search_it_generate_media_error_pdf2 = Other PDF Error
 search_it_generate_media_error_output = XPDF-error: Error opening an output file
 search_it_generate_media_error_permissions = XPDF-error: Error related to PDF permissions
 search_it_generate_media_empty = Media is empty or could not be extracted
+search_it_generate_url_excluded = not indexed, url was excluded
 
 search_it_settings_fileext_header = Genomsök filinnehåll
 search_it_settings_fileext_label = Filtillägg (t.ex. 'txt,csv,pdf' <br />(lämna tomma för alla filer)