Merge remote-tracking branch 'origin/master' into docker

htroot/CrawlMonitorRemoteStart.java

@@ -61,8 +61,8 @@ record = recordIterator.next();
                 prop.put("otherCrawlStartInProgress_" + showedCrawl + "_dark", dark ? "1" : "0");
                 prop.put("otherCrawlStartInProgress_" + showedCrawl + "_cre", record.created().toString());
                 prop.put("otherCrawlStartInProgress_" + showedCrawl + "_peername", peername);
-                prop.put("otherCrawlStartInProgress_" + showedCrawl + "_startURL", record.attributes().get("startURL").toString());
-                prop.put("otherCrawlStartInProgress_" + showedCrawl + "_intention", record.attributes().get("intention").toString());
+                prop.put("otherCrawlStartInProgress_" + showedCrawl + "_startURL", record.attributes().get("startURL"));
+                prop.put("otherCrawlStartInProgress_" + showedCrawl + "_intention", record.attributes().get("intention"));
                 prop.put("otherCrawlStartInProgress_" + showedCrawl + "_generalDepth", record.attributes().get("generalDepth"));
                 prop.put("otherCrawlStartInProgress_" + showedCrawl + "_crawlingQ", ("true".equals(record.attributes().get("crawlingQ"))) ? "1" : "0");
                 showedCrawl++;
@@ -88,8 +88,8 @@ record = recordIterator.next();
                 prop.put("otherCrawlStartFinished_" + showedCrawl + "_dark", dark ? "1" : "0");
                 prop.put("otherCrawlStartFinished_" + showedCrawl + "_cre", record.created().toString());
                 prop.putHTML("otherCrawlStartFinished_" + showedCrawl + "_peername", peername);
-                prop.putHTML("otherCrawlStartFinished_" + showedCrawl + "_startURL", record.attributes().get("startURL").toString());
-                prop.put("otherCrawlStartFinished_" + showedCrawl + "_intention", record.attributes().get("intention").toString());
+                prop.putHTML("otherCrawlStartFinished_" + showedCrawl + "_startURL", record.attributes().get("startURL"));
+                prop.put("otherCrawlStartFinished_" + showedCrawl + "_intention", record.attributes().get("intention"));
                 prop.put("otherCrawlStartFinished_" + showedCrawl + "_generalDepth", record.attributes().get("generalDepth"));
                 prop.put("otherCrawlStartFinished_" + showedCrawl + "_crawlingQ", ("true".equals(record.attributes().get("crawlingQ"))) ? "1" : "0");
                 showedCrawl++;

htroot/Crawler_p.java

@@ -594,6 +594,9 @@ public static serverObjects respond(final RequestHeader header, final serverObje
                                 m.remove("generalFilter");
                                 m.remove("specificFilter");
                                 m.put("intention", post.get("intention", "").replace(',', '/'));
+                                if (successurls.size() > 0) { // just include at least one of the startURL's in case of multiple for the news service
+                                    m.put("startURL", successurls.iterator().next().toNormalform(true));
+                                }
                                 sb.peers.newsPool.publishMyNews(sb.peers.mySeed(), NewsPool.CATEGORY_CRAWL_START, m);
                             }
                         } else {

htroot/yacysearch.java

@@ -60,9 +60,7 @@
 import net.yacy.data.DidYouMean;
 import net.yacy.data.UserDB;
 import net.yacy.data.ymark.YMarkTables;
-import net.yacy.document.Document;
 import net.yacy.document.LibraryProvider;
-import net.yacy.document.Parser;
 import net.yacy.document.Tokenizer;
 import net.yacy.kelondro.data.meta.URIMetadataNode;
 import net.yacy.kelondro.util.Bitfield;
@@ -73,7 +71,6 @@
 import net.yacy.peers.EventChannel;
 import net.yacy.peers.NewsPool;
 import net.yacy.peers.graphics.ProfilingGraph;
-import net.yacy.repository.Blacklist.BlacklistType;
 import net.yacy.search.EventTracker;
 import net.yacy.search.Switchboard;
 import net.yacy.search.SwitchboardConstants;
@@ -195,6 +192,7 @@ public static serverObjects respond(
             prop.put("geoinfo", "0");
             prop.put("rss_queryenc", "");
             prop.put("meanCount", 5);
+            prop.put("eventID",""); // mandatory parameter for yacysearchtrailer/yacysearchitem includes
             return prop;
         }
 

libbuild/GitRevMavenTask/src/GitRevMavenTask.java

@@ -87,7 +87,7 @@ public void execute() throws MojoExecutionException {
                         break;
                     }
                 }
-                if (lastTag != null || distance++ > 999) {
+                if (lastTag != null || distance++ > 90999) {
                     break;
                 }
             }

libbuild/GitRevTask/GitRevTask.java

@@ -79,7 +79,7 @@ public void execute() {
 						break;
 					}
 				}
-				if (lastTag != null || distance++ > 999) break;
+				if (lastTag != null || distance++ > 90999) break;
 			}
 			walk.dispose();
 			if (lastTag == null) {

locales/cn.lng

@@ -1069,7 +1069,7 @@ Network Scanner==网络扫描器
 YaCy can scan a network segment for available http, ftp and smb server.==YaCy可扫描http, ftp 和smb服务器.
 You must first select a IP range and then, after this range is scanned,==须先指定IP范围, 再进行扫描,
 it is possible to select servers that had been found for a full-site crawl.==才有可能选择主机并将其作为全站crawl的服务器.
-No servers had been detected in the given IP range #[iprange]#. 
+#No servers had been detected in the given IP range== 
 Please enter a different IP range for another scan.==未检测到可用服务器, 请重新指定IP范围.
 Please wait...==请稍候...
 >Scan the network<==>扫描网络<
@@ -2952,7 +2952,6 @@ New Password is empty.==新密码为空.
 
 #File: ViewFile.html
 #---------------------------
-YaCy '#[clientname]#': View URL Content==YaCy '#[clientname]#': 查看文件内容
 View URL Content==查看链接内容
 >Get URL Viewer<==>获取链接浏览器<
 >URL Metadata<==>链接元数据<

locales/de.lng

@@ -1334,7 +1334,7 @@ Network Scanner==Netzwerk Scanner
 YaCy can scan a network segment for available http, ftp and smb server.==YaCy kann ein Netzwerksegment auf verfügbare HTTP, FTP und SMB Server hin absuchen.
 You must first select a IP range and then, after this range is scanned,==Sie müssen zuerst einen IP Bereich festlegen  und dann, nachdem dieser Bereich gescannt wurde,
 it is possible to select servers that had been found for a full-site crawl.==ist es möglich einen gefunden Server für eine volle Seiten Suche crawlen zu lassen.
-No servers had been detected in the given IP range #[iprange]#. 
+No servers had been detected in the given IP range==Es wurde kein Server im angegebenen IP Bereich gefunden
 Please enter a different IP range for another scan.==Bitte geben Sie einen anderen IP Bereich ein für einen weiteren Scan.
 Please wait...==Bitte warten...
 >Scan the network<==>Das Netzwerk Scannen<
@@ -3147,7 +3147,7 @@ For community support, please visit our==Für Unterstützung aus der Community,
 
 #File: Status_p.inc
 #---------------------------
-#System Status==System Status
+System Status==Systemstatus
 Unknown==unbekannt
 YaCy version:==YaCy Version:
 Uptime:==Online seit:
@@ -3493,7 +3493,6 @@ New Password is empty.==Das neue Passwort ist leer.
 
 #File: ViewFile.html
 #---------------------------
-YaCy '#[clientname]#': View URL Content==YaCy '#[clientname]#': Zeige URL Inhalte
 View URL Content==Zeige URL Inhalte
 >Get URL Viewer<==>URL Betrachter<
 "Show Metadata"=="Metadaten anzeigen"

locales/gr.lng

@@ -101,7 +101,7 @@ You do not need to provide any personal data here, but if you want to distribute
 #Yahoo!==Yahoo!
 #MSN=MSN
 Comment==Σχόλιο
-"Save"==Αποθήκευση
+"Save"=="Αποθήκευση"
 #-----------------------------
 
 #File: Connections_p.html

locales/hi.lng

@@ -1077,7 +1077,7 @@ Network Scanner==नेटवर्क स्कैनर
 YaCy can scan a network segment for available http, ftp and smb server.==YaCy उपलब्ध HTTP, FTP और किसी सर्वर के लिए एक नेटवर्क खंड स्कैन कर सकते हैं.
 You must first select a IP range and then, after this range is scanned,==इस श्रृंखला स्कैन के बाद आप पहली बार, तो एक आईपी श्रेणी का चयन करना चाहिए
 it is possible to select servers that had been found for a full-site crawl.==यह एक पूरी साइट क्रॉल के लिए पाया गया था कि सर्वर का चयन करने के लिए संभव है.
-No servers had been detected in the given IP range #[iprange]#. 
+#No servers had been detected in the given IP range==
 Please enter a different IP range for another scan.==एक और स्कैन के लिए एक अलग आईपी रेंज दर्ज करें.
 Please wait...==कृपया प्रतीक्षा करें ...
 >Scan the network<==>नेटवर्क स्कैन<

locales/it.lng

@@ -97,7 +97,7 @@ You do not need to provide any personal data here, but if you want to distribute
 #Yahoo!==Yahoo!
 #MSN=MSN
 Comment==Commento
-"Save"==Salva
+"Save"=="Salva"
 #-----------------------------
 
 #File: Connections_p.html

locales/master.lng.xlf

@@ -1587,9 +1587,6 @@
     <trans-unit id="bfcc5088" xml:space="preserve" approved="no" translate="yes">
        <source>"Submit"</source>
     </trans-unit>
-    <trans-unit id="fda7badd" xml:space="preserve" approved="no" translate="yes">
-       <source>http://www.iana.org/assignments/media-types/&lt;/a&gt;</source>
-    </trans-unit>
   </body>
 </file>
 
@@ -2117,6 +2114,9 @@
     <trans-unit id="5d032a67" xml:space="preserve" approved="no" translate="yes">
        <source>Release will be installed. Please wait.</source>
     </trans-unit>
+    <trans-unit id="3c7a4df9" xml:space="preserve" approved="no" translate="yes">
+       <source>You installed YaCy with a package manager.</source>
+    </trans-unit>    
     <trans-unit id="20240fb3" xml:space="preserve" approved="no" translate="yes">
        <source>To update YaCy, use the package manager:</source>
     </trans-unit>
@@ -2192,9 +2192,6 @@
     <trans-unit id="8713e5b1" xml:space="preserve" approved="no" translate="yes">
        <source>Last Deploy</source>
     </trans-unit>
-    <trans-unit id="3c7a4df9" xml:space="preserve" approved="no" translate="yes">
-       <source>You installed YaCy with a package manager.</source>
-    </trans-unit>
   </body>
 </file>
 
@@ -3297,8 +3294,8 @@
     <trans-unit id="e82c07f9" xml:space="preserve" approved="no" translate="yes">
        <source>it is possible to select servers that had been found for a full-site crawl.</source>
     </trans-unit>
-    <trans-unit id="ede81ac7" xml:space="preserve" approved="no" translate="yes">
-       <source>No servers had been detected in the given IP range #[iprange]#.</source>
+    <trans-unit id="9ad86623" xml:space="preserve" approved="no" translate="yes">
+       <source>No servers had been detected in the given IP range</source>
     </trans-unit>
     <trans-unit id="c8005605" xml:space="preserve" approved="no" translate="yes">
        <source>Please enter a different IP range for another scan.</source>
@@ -5518,12 +5515,9 @@
 
 <file original="Network.html"  source-language="en"  datatype="html">
   <body>
-    <trans-unit id="3e587bc4" xml:space="preserve" approved="no" translate="yes">
-       <source>YaCy '#[clientname]#': YaCy Search Network</source>
-    </trans-unit>
-    <trans-unit id="3024b1ff" xml:space="preserve" approved="no" translate="yes">
-       <source>YaCy Search Network '#[networkName]#'</source>
-    </trans-unit>
+    <trans-unit id="ff8b8258" xml:space="preserve" approved="no" translate="yes">
+       <source>YaCy Search Network</source>
+    </trans-unit>      
     <trans-unit id="1f205c10" xml:space="preserve" approved="no" translate="yes">
        <source>YaCy Network&lt;</source>
     </trans-unit>
@@ -5815,9 +5809,6 @@
     <trans-unit id="b5434abc" xml:space="preserve" approved="no" translate="yes">
        <source>&gt;DHT-in&lt;</source>
     </trans-unit>
-    <trans-unit id="ff8b8258" xml:space="preserve" approved="no" translate="yes">
-       <source>YaCy Search Network</source>
-    </trans-unit>
     <trans-unit id="31955db0" xml:space="preserve" approved="no" translate="yes">
        <source>Count of Connected Senior Peers</source>
     </trans-unit>
@@ -6752,10 +6743,19 @@
     </trans-unit>
     <trans-unit id="c6803af7" xml:space="preserve" approved="no" translate="yes">
        <source>"Set Boost Query"</source>
-    </trans-unit>
+    </trans-unit>    
     <trans-unit id="c50afe39" xml:space="preserve" approved="no" translate="yes">
        <source>field not in local index (boost has no effect)</source>
     </trans-unit>
+    <trans-unit id="ebe8bd4e" xml:space="preserve" approved="no" translate="yes">
+       <source>You can boost with vocabularies, use the field</source>
+    </trans-unit>
+    <trans-unit id="369809bc" xml:space="preserve" approved="no" translate="yes">
+       <source>with values</source>
+    </trans-unit>    
+    <trans-unit id="abdacdba" xml:space="preserve" approved="no" translate="yes">
+       <source>You can also boost on logarithmic occurrence counters of the fields</source>
+    </trans-unit>    
     <trans-unit id="af04244c" xml:space="preserve" approved="no" translate="yes">
        <source>"Set Field Boosts"</source>
     </trans-unit>
@@ -8658,9 +8658,6 @@
     <trans-unit id="a444325e" xml:space="preserve" approved="no" translate="yes">
        <source>See the page info about the url.</source>
     </trans-unit>
-    <trans-unit id="700fabc1" xml:space="preserve" approved="no" translate="yes">
-       <source>YaCy '#[clientname]#': View URL Content</source>
-    </trans-unit>
     <trans-unit id="df784dad" xml:space="preserve" approved="no" translate="yes">
        <source>View URL Content</source>
     </trans-unit>

locales/ru.lng

@@ -1131,7 +1131,6 @@ List of possible crawl start URLs==Список ссылок для провер
 #File: CrawlProfileEditor_p.html
 #---------------------------
 Crawl Profile Editor==Изменение профиля индексирования
->Crawl Profile Editor<==>Изменение профиля индексирования<
 >Crawler Steering<==>Управление индексатором<
 >Crawl Scheduler<==>Планировщик индексирования<
 >Scheduled Crawls can be modified in this table<==>Запланированное индексирование можно изменить в этой таблице<
@@ -1461,7 +1460,7 @@ Network Scanner==Сканер сети
 YaCy can scan a network segment for available http, ftp and smb server.==YaCy может сканировать такие сегменты сети как http-, ftp- и smb-серверы .
 You must first select a IP range and then, after this range is scanned,==Сначала вы должны выбрать диапазон IP-адресов, а затем диапазон сканирования.
 it is possible to select servers that had been found for a full-site crawl.==После этого можно выбрать серверы для полного индексирования сайта.
-No servers had been detected in the given IP range #[iprange]#.==Серверы не обнаружены в заданном диапазоне IP-адресов. 
+No servers had been detected in the given IP range==Серверы не обнаружены в заданном диапазоне IP-адресов 
 Please enter a different IP range for another scan.==Пожалуйста, введите другой диапазон IP-адресов, для повторного сканирования.
 Please wait...==Пожалуйста, подождите...
 >Scan the network<==>Сканирование сети<
@@ -2383,8 +2382,7 @@ The target peer is alive but did not receive your message. Sorry.==Узел по
 
 #File: Network.html
 #---------------------------
-YaCy '#[clientname]#': YaCy Search Network==YaCy '#[clientname]#': Мониторинг сети
-YaCy Search Network '#[networkName]#'==Мониторинг сети YaCy
+YaCy Search Network==Мониторинг сети YaCy
 YaCy Network<==Сеть YaCy<
 The information that is presented on this page can also be retrieved as XML.==Информация, указанная на этой странице, также может быть получена как XML.
 Click the API icon to see the XML.==Нажмите на иконку API, чтобы увидеть XML.
@@ -2876,7 +2874,6 @@ field not in local index (boost has no effect)==поля нет в локаль
 
 #File: RegexTest.html
 #---------------------------
-RegexTest==Тест регулярного выражения
 Regex Test==Тест регулярного выражения
 Test String==Тест строки
 Regular Expression==Регулярное выражение
@@ -3767,7 +3764,6 @@ Parsed Sentences==Разобранные предложения
 Parsed Tokens/Words==Разобранные маркеры/слова
 Link List==Список ссылок
 Citation Report==Отчет цитирования
->CitationReport<==>Отчет цитирования<
 "Show"=="Показать"
 Unable to find URL Entry in DB==Невозможно найти запись ссылки в базе данных.
 Invalid URL==Неправильный URL-адрес
@@ -3938,14 +3934,13 @@ Title==Заголовок
 
 #File: WatchWebStructure_p.html
 #---------------------------
-Web Structure<==Вэб-структура<
+Web Structure==Вэб-структура
 The data that is visualized here can also be retrieved in a XML file, which lists the reference relation between the domains.==Эти данные, также могут быть получены в виде XML-файла с перекрёстными ссылками между доменами.
 With a GET-property 'about' you get only reference relations about the host that you give in the argument field for 'about'.==Указав параметр "GET" 'about' вы получите только перекрёстные ссылки о хосте, которые указан в поле 'about'.
 With a GET-property 'latest' you get a list of references that had been computed during the current run-time of YaCy, and with each next call only an update to the next list of references.==Указав параметр GET" 'latest'  вы получите список ссылок вычисленных во время текущей работы YaCy, обновляющийся при каждом следующем вызове.
 Click the API icon to see the XML file.==Нажмите на иконку API для просмотра XML-файла.
 To see a list of all APIs, please visit the==Для просмотра списка всех API, пожалуйста, посетите
 API wiki page==страницу API Wiki
-Web Structure==Вэб-структура
 >Host List<==>Список хостов<
 >#[count]# outlinks==>#[count]# внешних ссылок
 host<==Хост<