svn commit: r1617058 [5/8] - in /manifoldcf/trunk: connectors/rss/connector/src/main/native2ascii/org/apache/manifoldcf/crawler/connectors/rss/ framework/ui-core/src/main/native2ascii/org/apache/manifoldcf/ui/i18n/ site/src/documentation/content/xdocs/...

mingchun Sun, 10 Aug 2014 00:46:26 -0700

Added: 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/included-connectors.xml
URL: 
http://svn.apache.org/viewvc/manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/included-connectors.xml?rev=1617058&view=auto
==============================================================================
--- 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/included-connectors.xml
 (added)
+++ 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/included-connectors.xml
 Sun Aug 10 07:45:35 2014
@@ -0,0 +1,61 @@
+<?xml version="1.0" encoding="utf-8"?>
+
+<!DOCTYPE document PUBLIC "-//APACHE//DTD Documentation V2.0//EN" 
+          "http://forrest.apache.org/dtd/document-v20.dtd";>
+
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<document> 
+
+  <header> 
+    <title></title> 
+  </header> 
+
+  <body> 
+    <section>
+      <title>è¿æ¥å¨ä¸è§</title>
+      <p>ManifoldCFæä¾å¦ä¸è¿æ¥å¨ï¼</p>
+      <p></p>
+      <table>
+        <caption>æ¯æè¿æ¥å¨</caption>
+        
<tr><th>è¿æ¥å¨å</th><th>è¿æ¥å¨å¹³å°</th><th>æå¡å¨å¹³å°</th><th>å®¢æ·ç«¯çæ¬</th><th>æå¡å¨çæ¬</th></tr>
+        <tr><td>CMIS</td><td>Java</td><td>å¤ä¸ª</td><td>CMIS 1.0</td><td>CMIS 
1.0</td></tr>
+        
<tr><td>DropBox</td><td>Java</td><td>å¤ä¸ª</td><td>1.5.3</td><td>N/A</td></tr>
+        <tr><td>Email</td><td>Java</td><td>å¤ä¸ª</td><td>Javamail 
1.4</td><td>N/A</td></tr>
+        <tr><td>File 
System</td><td>Java</td><td>Win/*NIX</td><td>N/A</td><td>N/A</td></tr>
+        <tr><td>Google 
Drive</td><td>Java</td><td>å¤ä¸ª</td><td>v2-rev64-1.14.1-beta</td><td>N/A</td></tr>
+        
<tr><td>HDFS</td><td>Java</td><td>å¤ä¸ª</td><td>2.2.0</td><td>1.1.2</td></tr>
+        <tr><td>Windowså±äº«</td><td>Java</td><td> Win, Samba, NetApp,å
¶å®NASç³»ç»</td><td>N/A</td><td>N/A</td></tr>
+        <tr><td>JDBC</td><td>Java </td><td>å¤ä¸ª</td><td>æ¯æJDBC V2, V3, 
V4;Oracle 10, JTDS 1.2, Postgresql 9.1, MySQL 
5.5çé©±å¨å¨éè¿éªè¯</td><td>å¤ä¸ª</td></tr>
+        <tr><td>Jira</td><td>Java 
</td><td>å¤ä¸ª</td><td>N/A</td><td>5.0-6.1</td></tr>
+        <tr><td>RSS</td><td>Java </td><td> N/A </td><td> N/A </td><td>Atom,RSS 
2.0åå¶å®</td></tr>
+        <tr><td>Web</td><td>Java </td><td>N/A</td><td> N/A </td><td>HTML 1.0, 
1.1, 2.0, Atom, RSS 2.0åå¶å®</td></tr>
+        <tr><td>Wiki</td><td>Java </td><td>N/A</td><td> N/A </td><td>Wiki 
1.8æä»¥ä¸</td></tr>
+        <tr><td>LiveLink (OpenText)</td><td>Java </td><td> Win </td><td> LAPI 
9.7.1 </td><td>9.2.0 - 10.2.0éè¿éªè¯</td></tr>
+        <tr><td>Solr</td><td>Java </td><td> N/A </td><td> N/A</td><td>Solr 
1.4, 3.6.2, 4.0.0, 4.1.0, 4.2.0, 4.3.0éè¿éªè¯</td></tr>
+        <tr><td>OpenSearchServer</td><td>Java </td><td> N/A </td><td> 
N/A</td><td>OpenSearchServer 1.2.1, 1.2.2, 1.2.3éè¿éªè¯</td></tr>
+        <tr><td>ElasticSearch</td><td>Java </td><td> N/A </td><td> 
N/A</td><td>ElasticSearch 0.18.3, 0.18.4, 0.18.5, 0.18.6, 
0.18.7éè¿éªè¯</td></tr>
+        <tr><td>Documentum (EMC)</td><td>Win, RedHat</td><td> Win, RedHat 
</td><td>DFC 5.3 SP5éè¿éªè¯</td><td>5.3, 
6.0å6.5æå¡å¨éè¿éªè¯</td></tr>
+        <tr><td>SharePoint (MSFT)</td><td>Java </td><td>Win</td><td> N/A 
</td><td>SharePoint 2003 (2.0), 2007 (3.0)éè¿éªè¯, æ Claim Space 
Authæ¡ä»¶ä¸éªè¯2010 (4.0)</td></tr>
+        <tr><td>Meridio (Autonomy)</td><td>Java </td><td> Win </td><td> N/A 
</td><td>Meridio 4.1, 5.0éè¿éªè¯</td></tr>
+        <tr><td>FileNet (IBM)</td><td>Java</td><td>Win, RedHat</td><td>P8 
V4.1, V4.5éè¿éªè¯</td><td>P8 V4.1, V4.5éè¿éªè¯</td></tr>
+      </table>
+    </section>
+  </body>
+</document>
+


Propchange: 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/included-connectors.xml
------------------------------------------------------------------------------
    svn:executable = *

Propchange: 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/included-connectors.xml
------------------------------------------------------------------------------
    svn:mime-type = text/plain;charse=utf-8

Added: manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/index.xml
URL: 
http://svn.apache.org/viewvc/manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/index.xml?rev=1617058&view=auto
==============================================================================
--- manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/index.xml 
(added)
+++ manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/index.xml Sun 
Aug 10 07:45:35 2014
@@ -0,0 +1,45 @@
+<?xml version="1.0" encoding="utf-8"?>
+
+<!DOCTYPE document PUBLIC "-//APACHE//DTD Documentation V2.0//EN" 
+          "http://forrest.apache.org/dtd/document-v20.dtd";>
+
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<document> 
+
+  <header> 
+    <title>æ¬¢è¿æ¥å°ManifoldCFï¼</title> 
+  </header> 
+
+  <body> 
+    <section>
+       <title>ä»ä¹æ¯ManifoldCFï¼</title>
+       
<p>ManifoldCFç±Javaç¨åºå®ç°ï¼å®å¯ä»¥æéä¿åå¨äºèç½æä¼ä¸ç½ä¸åç§æå¡å¨éçææ¡£æWebç½é¡µï¼å¹¶å°å

¶åéå°æç´¢å¼æãå¨æéææ¡£çåæ¶è¿å¨ActiveDirectoryçè®¤è¯ç³»ç»çååä¸æéææ¡£çæéä¿¡æ¯ï¼å¹¶å©ç¨è¿äºæéä¿¡æ¯å¯¹å
¶æç´¢ç»æå ä»¥éå¶ãæ¯å¦ï¼äººäºæ¡£æ¡ä»
éç±äººäºé¨æç´¢æ¶æå ä»¥æ¾ç¤ºã</p>
+       <p>ManifoldCFç°çæ¬å¯å©ç¨ä¸è¿°éç¨è¿æ¥å¨æéFileNet P8 
(IBM)ï¼Documentum (EMC)ï¼LiveLink (OpenText)ï¼Meridio (Autonomy), Windowså
±äº«(Microsoft)ï¼SharePoint 
(Microsoft)çåç¨ç³»ç»ä¿åççåç§ææ¡£ï¼å¦:CMISè¿æ¥å¨ï¼File 
Systemè¿æ¥å¨ï¼JDBCè¿æ¥å¨ï¼RSS 
Feedè¿æ¥å¨ï¼Wikiè¿æ¥å¨ï¼HTMLè¿æ¥å¨ãèä¸ï¼è¿å¯å°æéå°çææ¡£åéå°Apache
 Solrï¼QBase(æ§MetaCarta) 
GTSï¼OpenSearchServerï¼Elasticsearchãææ¯æçäº§ååè§æ 
¼ä¸è§è¯·åç§<a href="included-connectors.html">è¿é</a>ã</p>
+       <p>Apache ManifoldCFç±MetaCarta, 
Inc.å¼åï¼ä¸ºä¾ç»å¤å®¶ä¼ä¸ç»å5å¹´ååå¤å¤çå¼åï¼è°è¯ä¹åï¼2009å¹´12æå
¶æºä»£ç èµ éå°Apache Software Foundationã</p>
+    </section>
+
+    <section>
+       <title>å³äºç¬¬ä¸æ¹åå¨åº</title>
+       <p>ä¸ºçæManifoldCFå
å«çé¢ååä¸è½¯ä»¶çè¿æ¥å¨ï¼ææ¶éç¬¬ä¸æ¹è½¯ä»¶åºï¼å
æè½¯ä»¶æ¬èº«ãè½ç¶å¼åäººåéå¾å°è¿äºç¬¬ä¸æ¹è½¯ä»¶ï¼ä½å¯ä»¥ææ¡ä»¶å°ç¼è¯è¿æ¥å¨èªèº«çæºä»£ç
 å¹¶ä½ä¸ºApacheåå¸ä¹ãæä»¬è½ææå¹¶åªååå°ä½¿ä¸åéµç
§Apacheçæï¼ä½ç°ç¶ä¸ä¼ç«å³åçååã</p>
+       <p>å³äºåæ¬ç¬¬ä¸æ¹è½¯ä»¶ççææ¥éª¤ï¼è¯·åç
§Wikié¡µé¢ã</p>
+    </section>
+
+  </body>
+
+</document>

Propchange: 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/index.xml
------------------------------------------------------------------------------
    svn:executable = *

Propchange: 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/index.xml
------------------------------------------------------------------------------
    svn:mime-type = text/plain;charse=utf-8

Added: manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/javadoc.xml
URL: 
http://svn.apache.org/viewvc/manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/javadoc.xml?rev=1617058&view=auto
==============================================================================
--- manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/javadoc.xml 
(added)
+++ manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/javadoc.xml Sun 
Aug 10 07:45:35 2014
@@ -0,0 +1,64 @@
+<?xml version="1.0"?>
+
+<!DOCTYPE document PUBLIC "-//APACHE//DTD Documentation V2.0//EN" 
+          "http://forrest.apache.org/dtd/document-v20.dtd";>
+
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<document> 
+
+  <header> 
+    <title>ManifoldCF Javadoc</title> 
+  </header> 
+
+  <body> 
+    <section>
+      <title>ManifoldCF Javadoc</title>
+      <p></p>
+      <p>å³äºææ°çManifoldCFåå
¶è¿æ¥å¨çJavadocå¯éè¿ä¸è¿°é¾æ¥å ä»¥åç§</p>
+      <p><a href="../api/framework/index.html">ManifoldCFæ¡æ¶</a></p>
+      <p><a href="../api/activedirectory/index.html">Active 
Directoryæé</a></p>
+      <p><a href="../api/alfresco/index.html">Alfrescoè¿æ¥å¨</a></p>
+      <p><a href="../api/cmis/index.html">CMIS authorityè¿æ¥å¨</a></p>
+      <p><a 
href="../api/documentum/index.html">Documentumæé,è¿æ¥å¨åæ¯æå¤ç</a></p>
+      <p><a href="../api/dropbox/index.html">Dropboxè¿æ¥å¨</a></p>
+      <p><a href="../api/email/index.html">Emailè¿æ¥å¨</a></p>
+      <p><a 
href="../api/filenet/index.html">FileNetè¿æ¥å¨åæ¯æå¤ç</a></p>
+      <p><a href="../api/filesystem/index.html">File 
systemåå¨å¨åè¾åºè¿æ¥å¨</a></p>
+      <p><a href="../api/googledrive/index.html">GoogleDriveè¿æ¥å¨</a></p>
+      <p><a href="../api/gridfs/index.html">GridFSè¿æ¥å¨</a></p>
+      <p><a href="../api/gts/index.html">qBase GTSè¾åºè¿æ¥å¨</a></p>
+      <p><a 
href="../api/hdfs/index.html">HDFSåå¨å¨åè¾åºè¿æ¥å¨</a></p>
+      <p><a href="../api/jcifs/index.html">CIFSè¿æ¥å¨</a></p>
+      <p><a href="../api/jira/index.html">JIRAè¿æ¥å¨åæé</a></p>
+      <p><a href="../api/jdbc/index.html">JDBCè¿æ¥å¨</a></p>
+      <p><a 
href="../api/livelink/index.html">LiveLinkæéåè¿æ¥å¨</a></p>
+      <p><a href="../api/meridio/index.html">Meridioæéåè¿æ¥å¨</a></p>
+      <p><a 
href="../api/opensearchserver/index.html">OpenSearchServerè¾åºè¿æ¥å¨</a></p>
+      <p><a 
href="../api/elasticsearch/index.html">ElasticSearchè¾åºè¿æ¥å¨</a></p>
+      <p><a href="../api/nullauthority/index.html">Nullæé</a></p>
+      <p><a href="../api/nulloutput/index.html">Nullè¾åºè¿æ¥å¨</a></p>
+      <p><a href="../api/regexpmapper/index.html">Regular expression 
mappingè¿æ¥å¨</a></p>
+      <p><a href="../api/rss/index.html">RSSè¿æ¥å¨</a></p>
+      <p><a href="../api/sharepoint/index.html">SharePointè¿æ¥å¨</a></p>
+      <p><a href="../api/solr/index.html">Solrè¾åºè¿æ¥å¨</a></p>
+      <p><a href="../api/webcrawler/index.html">Webè¿æ¥å¨</a></p>
+      <p><a href="../api/wiki/index.html">Wikiè¿æ¥å¨</a></p>
+    </section>
+  </body>
+</document>

Propchange: 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/javadoc.xml
------------------------------------------------------------------------------
    svn:executable = *

Added: 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/performance-tuning.xml
URL: 
http://svn.apache.org/viewvc/manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/performance-tuning.xml?rev=1617058&view=auto
==============================================================================
--- 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/performance-tuning.xml
 (added)
+++ 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/performance-tuning.xml
 Sun Aug 10 07:45:35 2014
@@ -0,0 +1,170 @@
+<?xml version="1.0"?>
+
+<!DOCTYPE document PUBLIC "-//APACHE//DTD Documentation V2.0//EN" 
+          "http://forrest.apache.org/dtd/document-v20.dtd";>
+
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<document> 
+
+  <header> 
+    <title>æ§è½è°ä¼</title> 
+  </header> 
+
+  <body> 
+    <section>
+      <title>æ§è½è°ä¼</title>
+      <p></p>
+      <p>
+        ä¸ºäºè®©ManifoldCFæå¤§éåº¦çåæ¥åè½åæç, 
éäºè§£å¦ä¸å ç¹ãé¦åï¼è¦ææ¡å¦ä½è®¾ç½®é¡¹ç®ä½¿å
¶å¨æä½³ç¶æä¸è¿è¡ãæ¨è¿éäºè§£æä½³ç¡¬ä»¶éç½®ãå¦å¤ï¼æ¯«æ 
çé®ï¼æ¨éè¦å¤ææ¨æåçä¸åæä½æ¯å¦æ£å¸¸ç»æï¼ä¸ºæ¤æä»¬éè¦ä¸äºæ°æ®æ¥å
 ä»¥æ¯è¾ã
+        æ¤é¡µæ¨å¨ä¾æ¨å³äºä¸è¿°é®é¢ççæ¡ã
+      </p>
+      <section>
+        <title>æ§è½ç¸å³è®¾ç½®</title>
+        <p></p>
+        <p>
+          ManifoldCFæ§è½è°ä¼çç®æ 
å¨äºï¼æå¤§éåº¦çå©ç¨ç³»ç»çå¹¶è¡å¤çï¼å¹¶ä¿è¯ä¸åå¨ä»»ä½ç¶é¢ä½¿ç³»ç»åæ
¢ã
+          ManifoldCFæä¸ºéè¦çåºç¡æ¯æ°æ®åºï¼å 
ä¸ºå®æ¯ManifoldCFæä½¿ç¨çå¯ä¸çæä¹æ§åå¨æºå¶ãæ
å¦ä½æ£ç¡®ä½¿ç¨æ°æ®åºå°æ¯æä»¬çç¬¬ä¸ç®æ ã
+        </p>
+        <section>
+          <title>éæ©æ°æ®åº</title>
+          <p>
+            èµ·åä½¿ç¨PostgreSQLèè¿Derbyï¼å ä¸ºDerbyå¨å¤çæ»éæ¶å
·æå·²ç¥çæ§è½é®é¢ã
+            
å¨åManifoldCFé«åº¦çº¿ç¨åçç³»ç»ï¼æ°æ®åºæ»éçåçä¸è¶³ä¸ºå¥ï¼æä»¬å¯ä»¥éä½ç±å®å¼åçé£é©ï¼ä½ä¸è½å®å
¨æé¤ã
+            æ¢å¥è¯è¯´ï¼Derbyå·ææ»éåè½ï¼ä¸å¦å¨DELETEä¸ä¸ªè¡¨æ 
¼çåæ¶SELECTåä¸ä¸ªè¡¨æ 
¼ï¼æ¤æ¶Derbyè¦æ±æ¬æçå»æ£éªè¯¥æ»éã
+            æ¾ç¶ï¼æ¤å¨ä½ä¸é«æ§è½æ ¼æ ¼ä¸å¥ï¼å 
æ¤å½æ¨å¨æä¸åç¬è«æ§è½æ¶è¯·ä½¿ç¨PostgreSQLãè¯·åç§<a 
href="how-to-build-and-deploy.html">how-to-deploy</a> 
äºè§£å¦ä½å¨PostgreSQLä¸é©±å¨ManifoldCFã
+          </p>
+          <p>
+            æäºPostgreSQLçæ¬åæ ·å
·æç»ManifoldCFæ¥è¯¢çä¸è¯è®¡åçå·²ç¥é®é¢ãå½å®åçæ¶ï¼ä»»ä½å¤§å°çç¬åé½å°åå¾å¼å¸¸ç¼æ
¢ã
+            ManifoldCFæ¥å¿å¼å§åå«è®¸å¤æ¤ç±»è¦åé®é¢ï¼å¦"Query 
took more than a minute"å ä¸ç¸åºçè½¬å¨è®¡åï¼è¡¨ææ£å¨å
¨è¡¨æ«æä¸ä¸ªå¤§è¡¨æ ¼ã
+            ä»è¿ä¸ç¹ï¼ä½ åºæçä½ 
æè®¸å¨ä½¿ç¨ç³ç³ççæ¬ï¼å¦8.3.12ãç¸åï¼8.3.7, 
8.3.8,8.4.5åæ²¡æé®é¢ã
+          </p>
+        </section>
+        <section>
+          <title>æ£ç¡®éç½®PostgreSQL</title>
+          <p>
+            The key configuration changes you need to make to PostgreSQL from 
its é¢è®¾éç½® settings are intended to:
+          </p>
+          <ul>
+            <li>Set PostgreSQL up with enough database handles so that that 
will not be a bottleneck;</li>
+            <li>Make sure PostgreSQL has enough shared memory allocated to 
support the number of handles you selected;</li>
+            <li>Turn off autovacuuming.</li>
+          </ul>
+          <p>
+            The <em>postgresql.conf</em> file is where you set most of these 
options.  Some recommended settings are described in <a 
href="how-to-build-and-deploy.html">the deployment page</a>.
+            The postgresql.conf file describes the relationship between 
parameters, especially between the number of database handles and the amount of 
shared memory allocated.  This can differ significantly
+            from version to version, so it never hurts to read the text in 
that file, and understand what you are trying to achieve.
+          </p>
+          <p>
+            The number of database handles you need will depend on your 
ManifoldCF setup.  If you use the Quick Start, for instance, fewer handles are 
needed, because only one process is used.  The formula relating handle count to 
other
+            parameters of ManifoldCF is presented below.
+          </p>
+          <p></p>
+          <p>manifoldcf_db_pool_size * number_of_manifoldcf_processes &lt;= 
maximum_postgresql_database_handles - 2</p>
+          <p></p>
+          <p>
+            The number of processes you might have depends on how you deployed 
ManifoldCF.  If you used the Quick Start, you will only have one process.  But 
if you deployed in a more distributed way,
+            you will have at least a process for the agents daemon, as well as 
at one process for each web application.  If you anticipate that a command-line 
utility could be used at the same time,
+            that's one more process.  These multiply quickly, so the number of 
database handles you need to make available can get quite large, unless you 
limit the ManifoldCF pool size artificially
+            instead.
+          </p>
+          <p>Setting the parameters that control the size of the database 
connection pool is covered in the next section.</p>
+        </section>
+        <section>
+          <title>Setting the ManifoldCF database handle pool size</title>
+          <p>
+            The database handle pool size must be set correctly, or ManifoldCF 
will not perform well, and may even deadlock waiting to get a database handle.
+            The properties.xml parameter that controls this is 
<em>org.apache.manifoldcf.database.maxhandles</em>.  The formula you should use 
to properly set the value is below.
+          </p>
+          <p></p>
+          <p>worker_thread_count + delete_thread_count + 
expiration_thread_count + cleanup_thread_count + 10 &lt; 
manifoldcf_db_pool_size</p>
+          <p></p>
+        </section>
+        <section>
+          <title>Setting the number of worker, delete, and expiration 
threads</title>
+          <p>
+            The number of each variety of thread you choose depends on a 
number of factors that are specific to the kinds of tasks you expect to do.
+            First, note that constraints based on your hardware may have the 
effect of setting an upper bound on the total number of threads.  If, for 
example, memory constraints
+            on your system have the effect of limiting the number of available 
PostgreSQL handles, the total threads will also be limited as a result of 
applying the formulas already given.
+          </p>
+          <p>
+            If you do not have any such constraints, then you can choose the 
number of threads based on other hardware factors.  Typically, the number of 
processors would be what you'd consider
+            in coming up with the total thread count.  A value of between 12 
and 35 threads per processor is typical.  The optimal number for you will 
require some experimentation.
+          </p>
+          <p>The threads then have to be allocated to the worker, deletion, or 
expiration category.  If your work load does not require much in the way of 
deleting documents or expiring them,
+            it is usually adequate to retain the default of 10 deletion and 10 
expiration threads, and simply adjust the worker thread count.  The worker 
thread count parameter is <em>org.apache.manifoldcf.crawler.threads</em>.
+            See <a href="how-to-build-and-deploy.html">the deployment page</a> 
for a list of all of these parameters.
+          </p>
+        </section>
+        <section>
+          <title>Database maintenance</title>
+          <p>
+            Once you have the database and ManifoldCF configurated correctly, 
you will discover that the performance of the system gradually degrades over 
time.  This is because PostgreSQL
+            requires periodic maintenance in order to function optimally.  
This maintenance is called <em>vacuuming</em>.
+          </p>
+          <p>
+            Our recommendation is to vacuum on a schedule, and to use the 
"full" variant of the vacuum command (e.g. "VACUUM FULL").  PostgreSQL gives 
you the option of lesser
+            vacuums, some of which can be done in background, but in our 
experience these are very expensive performance-wise, and are not very helpful 
either.  "VACUUM FULL" makes a
+            complete new copy of the database, a table at a time, stored in an 
optimal way.  It is also reasonably quick, considering what it is doing.
+          </p>
+        </section>
+      </section>
+      <section>
+        <title>Some results</title>
+        <p>
+          We've run performance test on several systems.  Depending on 
hardware configuration, we've seen as fast as 57 documents per second to 16 
documents per second.  We tested with three different systems and ran the test
+          across 306,944 documents.  The table below shows the relevant 
configurations and results:
+        </p>
+        <table>
+          <tr><th>System</th><th>Processors (2+ 
Ghz)</th><th>Memory</th><th>Disk drives</th><th>Elapsed time 
(seconds)</th><th>Documents per second</th></tr>
+          <tr><td>Desktop</td><td>2</td><td>8 GB</td><td>7,200 
RPM</td><td>19,492</td><td>16</td></tr>
+          <tr><td>Laptop</td><td>2</td><td>4 GB</td><td>Samsung SSD 
RBX</td><td>9,230</td><td>33</td></tr>
+          <tr><td>Server</td><td>8</td><td>8 GB</td><td>10,000 
RPM</td><td>5,366</td><td>57</td></tr>
+        </table>
+        <p>
+          For these tests, we ran the Quick-Start example configuration from 
ManifoldCF as is, with the exception of using an external PostgreSQL database 
instead of the embedded Derby.
+          We altered the ManifoldCF and PostgreSQL configuration from their 
default settings to maximize system resource usage.  The table below shows the 
key configuration changes.
+        </p>
+        <table>
+          <tr><th>Workers</th><th>ManifoldCF DB Connections</th><th>PostgreSQL 
Connections</th><th>Max repository connections</th><th>JVM Memory</th></tr>
+          <tr><td>100</td><td>105</td><td>200</td><td>105</td><td>1024 
MB</td></tr>
+        </table>
+        <p>Additionally, we made postgresql.conf changes as shown in the table 
below:</p>
+        <table>
+          <tr><th>Parameter</th><th>Value</th></tr>
+          <tr><td>shared_buffers</td><td>1024MB</td></tr>
+          <tr><td>checkpoint_segments</td><td>300</td></tr>
+          <tr><td>maintenanceworkmem</td><td>2MB</td></tr>
+          <tr><td>tcpip_socket</td><td>true</td></tr>
+          <tr><td>max_connections</td><td>200</td></tr>
+          <tr><td>checkpoint_timeout</td><td>900</td></tr>
+          <tr><td>datestyle</td><td>ISO,European</td></tr>
+          <tr><td>autovacuum</td><td>off</td></tr>
+        </table>
+        <p>è¿éææè¶£çç»è®ºï¼for example the use of Solid State 
Drives for the laptop.  Even though addressable memory was reduced to 4 GB, the 
system processed twice as much documents than the desktop did with slower 
disks.  The other interesting fact is that the server had lower performing 
disks, but 4 times as many processors, and it was twice as fast as the 
laptop.</p>
+      </section>
+    </section>
+  </body>
+</document>
+
+
+
+
+
+
+        
\ No newline at end of file

Added: 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/programmatic-operation.xml
URL: 
http://svn.apache.org/viewvc/manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/programmatic-operation.xml?rev=1617058&view=auto
==============================================================================
--- 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/programmatic-operation.xml
 (added)
+++ 
manifoldcf/trunk/site/src/documentation/content/xdocs/zh_CN/programmatic-operation.xml
 Sun Aug 10 07:45:35 2014
@@ -0,0 +1,612 @@
+<?xml version="1.0"?>
+
+<!DOCTYPE document PUBLIC "-//APACHE//DTD Documentation V2.0//EN" 
+          "http://forrest.apache.org/dtd/document-v20.dtd";>
+
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<document> 
+
+  <header> 
+    <title>Programmatic Operation</title> 
+  </header> 
+
+  <body> 
+    <section>
+      <title>Programmatic Operation</title>
+      <p></p>
+      <p>A certain subset of ManifoldCF users want to think of ManifoldCF as 
an engine that they can poke from whatever other system they are developing.  
While
+        ManifoldCF is not precisely a document indexing engine per se, it can 
certainly be controlled programmatically.  Right now, there are three principle 
ways of
+        achieving this control.</p>
+      <p></p>
+      <section>
+        <title>Control by Servlet API</title>
+        <p></p>
+        <p>ManifoldCF provides a servlet-based JSON API that gives you the 
complete ability to define connections and jobs, and control job execution.  
You can read
+          about JSON <a href="http://www.json.org";>here</a>.  The API is 
designed to be RESTful in character.  Thus, it makes full use of the HTTP verbs
+          GET, PUT, POST, and DELETE, and represents objects as URLs.</p>
+        <section>
+          <title>URL format</title>
+          <p></p>
+          <p>The basic format of the JSON servlet resource URLs is as 
follows:</p>
+          <p></p>
+          
<p>http[s]://<em>&lt;server_and_port&gt;</em>/mcf-api-service/json/<em>&lt;resource&gt;</em></p>
+          <p></p>
+          <p>The servlet ignores request data, except when the PUT or POST 
verb is used.  In that case, the request data is presumed to be a JSON object.  
The servlet
+            responds either with an error response code (either 400 or 500) 
with an appropriate explanatory message, or with a 200 (OK), 201 (CREATED), or
+            404 (NOT FOUND) response code along with a response JSON 
object.</p>
+          <p></p>
+        </section>
+        <section>
+          <title>JSON equivalents for ManifoldCF</title>
+          <p></p>
+          <p>ManifoldCF treats certain JSON forms as equivalent, for the 
purposes of readability.  For example, the array form <strong>"foo" : [ { ... } 
]</strong> is
+            treated equivalently to <strong>"foo" : { }</strong>, whenever 
there is only one array element.  This gives a coder some flexibility as to how 
s/he encodes
+            JSON in requests.  Please also be aware that similar compressions 
will occur in the JSON responses from the API servlet, and your code must be 
able to deal
+            with this possibility.  The following table describes some of the 
equivalences:</p>
+          <p></p>
+          <p></p>
+          <p></p>
+          <table>
+            <tr><th>Form</th><th>Equivalent</th></tr>
+            <tr><td>[ { ... } ]</td><td>{ ... }</td></tr>
+            <tr><td>"foo" : { "_value_" : "bar" }</td><td>"foo" : 
"bar"</td></tr>
+            <tr><td>"_children_" : [ "foo":{ ... }, "foo":{ ... } 
]</td><td>"foo" : [ { ... }, { ... } ]</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Resources and commands</title>
+          <p></p>
+          <p>The actual available resources and commands are as follows:</p>
+          <p></p>
+          <p></p>
+          <p></p>
+          <table>
+            <tr><th>Resource</th><th>Verb</th><th>What it does</th><th>Input 
format/query args</th><th>Output format</th></tr>
+            <tr><td>authorizationdomains</td><td>GET</td><td>List all 
registered authorization 
domains</td><td>N/A</td><td>{"authorizationdomain":[<em>&lt;list_of_authorization_domain_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>outputconnectors</td><td>GET</td><td>List all registered 
output 
connectors</td><td>N/A</td><td>{"outputconnector":[<em>&lt;list_of_output_connector_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>transformationconnectors</td><td>GET</td><td>List all 
registered transformation 
connectors</td><td>N/A</td><td>{"transformationconnector":[<em>&lt;list_of_transformation_connector_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>mappingconnectors</td><td>GET</td><td>List all registered 
mapping 
connectors</td><td>N/A</td><td>{"mappingconnector":[<em>&lt;list_of_mapping_connector_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>authorityconnectors</td><td>GET</td><td>List all 
registered authority 
connectors</td><td>N/A</td><td>{"authorityconnector":[<em>&lt;list_of_authority_connector_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>repositoryconnectors</td><td>GET</td><td>List all 
registered repository 
connectors</td><td>N/A</td><td>{"repositoryconnector":[<em>&lt;list_of_repository_connector_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>authoritygroups</td><td>GET</td><td>List all authority 
groups</td><td>N/A</td><td>{"authoritygroup":[<em>&lt;list_of_authority_group_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>authoritygroups/<em>&lt;encoded_group_name&gt;</em></td><td>GET</td><td>Get
 a specific authority 
group</td><td>N/A</td><td>{"authoritygroup":<em>&lt;authority_group_object&gt;</em>}
 <strong>OR</strong> { } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>authoritygroups/<em>&lt;encoded_group_name&gt;</em></td><td>PUT</td><td>Save
 or create an authority 
group</td><td>{"authoritygroup":<em>&lt;authority_group_object&gt;</em>}</td><td>{
 } <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>authoritygroups/<em>&lt;encoded_group_name&gt;</em></td><td>DELETE</td><td>Delete
 an authority group</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>outputconnections</td><td>GET</td><td>List all output 
connections</td><td>N/A</td><td>{"outputconnection":[<em>&lt;list_of_output_connection_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>outputconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Get
 a specific output 
connection</td><td>N/A</td><td>{"outputconnection":<em>&lt;output_connection_object&gt;</em>}
 <strong>OR</strong> { } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>outputconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>PUT</td><td>Save
 or create an output 
connection</td><td>{"outputconnection":<em>&lt;output_connection_object&gt;</em>}</td><td>{
 } <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>outputconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>DELETE</td><td>Delete
 an output connection</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>status/outputconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Check
 the status of an output 
connection</td><td>N/A</td><td>{"check_result":<em>&lt;message&gt;</em>} 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>info/outputconnections/<em>&lt;encoded_connection_name&gt;</em>/<em>&lt;connector_specific_resource&gt;</em></td><td>GET</td><td>Retrieve
 arbitrary connector-specific 
resource</td><td>N/A</td><td><em>&lt;response_data&gt;</em> <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>} <strong>OR</strong> 
{"service_interruption":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>transformationconnections</td><td>GET</td><td>List all 
transformation 
connections</td><td>N/A</td><td>{"transformationconnection":[<em>&lt;list_of_transformation_connection_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>transformationconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Get
 a specific transformation 
connection</td><td>N/A</td><td>{"transformationconnection":<em>&lt;transformation_connection_object&gt;</em>}
 <strong>OR</strong> { } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>transformationconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>PUT</td><td>Save
 or create a transformation 
connection</td><td>{"outputconnection":<em>&lt;transformation_connection_object&gt;</em>}</td><td>{
 } <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>transformationconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>DELETE</td><td>Delete
 a transformation connection</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>status/transformationconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Check
 the status of a transformation 
connection</td><td>N/A</td><td>{"check_result":<em>&lt;message&gt;</em>} 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>info/transformationconnections/<em>&lt;encoded_connection_name&gt;</em>/<em>&lt;connector_specific_resource&gt;</em></td><td>GET</td><td>Retrieve
 arbitrary connector-specific 
resource</td><td>N/A</td><td><em>&lt;response_data&gt;</em> <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>} <strong>OR</strong> 
{"service_interruption":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>clearversions/<em>&lt;encoded_output_connection_name&gt;</em></td><td>PUT</td><td>Forget
 previous indexed document versions</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>clearrecords/<em>&lt;encoded_output_connection_name&gt;</em></td><td>PUT</td><td>Remove
 all previous indexing records</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>mappingconnections</td><td>GET</td><td>List all mapping 
connections</td><td>N/A</td><td>{"mappingconnection":[<em>&lt;list_of_mapping_connection_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>mappingconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Get
 a specific mapping 
connection</td><td>N/A</td><td>{"mappingconnection":<em>&lt;mapping_connection_object&gt;</em>}
 <strong>OR</strong> { } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>mappingconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>PUT</td><td>Save
 or create a mapping 
connection</td><td>{"mappingconnection":<em>&lt;mapping_connection_object&gt;</em>}</td><td>{
 } <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>mappingconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>DELETE</td><td>Delete
 a mapping connection</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>status/mappingconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Check
 the status of a mapping 
connection</td><td>N/A</td><td>{"check_result":<em>&lt;message&gt;</em>} 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>authorityconnections</td><td>GET</td><td>List all 
authority 
connections</td><td>N/A</td><td>{"authorityconnection":[<em>&lt;list_of_authority_connection_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>authorityconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Get
 a specific authority 
connection</td><td>N/A</td><td>{"authorityconnection":<em>&lt;authority_connection_object&gt;</em>}
 <strong>OR</strong> { } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>authorityconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>PUT</td><td>Save
 or create an authority 
connection</td><td>{"authorityconnection":<em>&lt;authority_connection_object&gt;</em>}</td><td>{
 } <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>authorityconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>DELETE</td><td>Delete
 an authority connection</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>status/authorityconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Check
 the status of an authority 
connection</td><td>N/A</td><td>{"check_result":<em>&lt;message&gt;</em>} 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>repositoryconnections</td><td>GET</td><td>List all 
repository 
connections</td><td>N/A</td><td>{"repositoryconnection":[<em>&lt;list_of_repository_connection_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>repositoryconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Get
 a specific repository 
connection</td><td>N/A</td><td>{"repositoryconnection":<em>&lt;repository_connection_object&gt;</em>}
 <strong>OR</strong> { } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>repositoryconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>PUT</td><td>Save
 or create a repository 
connection</td><td>{"repositoryconnection":<em>&lt;repository_connection_object&gt;</em>}</td><td>{
 } <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>repositoryconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>DELETE</td><td>Delete
 a repository connection</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>status/repositoryconnections/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Check
 the status of a repository 
connection</td><td>N/A</td><td>{"check_result":<em>&lt;message&gt;</em>} 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>info/repositoryconnections/<em>&lt;encoded_connection_name&gt;</em>/<em>&lt;connector_specific_resource&gt;</em></td><td>GET</td><td>Retrieve
 arbitrary connector-specific 
resource</td><td>N/A</td><td><em>&lt;response_data&gt;</em> <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>} <strong>OR</strong> 
{"service_interruption":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>clearhistory/<em>&lt;encoded_repository_connection_name&gt;</em></td><td>PUT</td><td>Clear
 history linked with repository 
connection</td><td>N/A</td><td><em>&lt;response_data&gt;</em> 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>} <strong>OR</strong> 
{"service_interruption":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>jobs</td><td>GET</td><td>List all job 
definitions</td><td>N/A</td><td>{"job":[<em>&lt;list_of_job_objects&gt;</em>]} 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>jobs</td><td>POST</td><td>Create a 
job</td><td>{"job":<em>&lt;job_object&gt;</em>}</td><td>{"job_id":<em>&lt;job_identifier&gt;</em>}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>jobs/<em>&lt;job_id&gt;</em></td><td>GET</td><td>Get a 
specific job 
definition</td><td>N/A</td><td>{"job":<em>&lt;job_object_&gt;</em>} 
<strong>OR</strong> { } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>jobs/<em>&lt;job_id&gt;</em></td><td>PUT</td><td>Save a 
job definition</td><td>{"job":<em>&lt;job_object&gt;</em>}</td><td>{ } 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>jobs/<em>&lt;job_id&gt;</em></td><td>DELETE</td><td>Delete 
a job definition</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>jobstatuses</td><td>GET</td><td>List all jobs and their 
status</td><td>maxcount=&lt;maximum_documents_to_count&gt;</td><td>{"jobstatus":[<em>&lt;list_of_job_status_objects&gt;</em>]}
 <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>jobstatuses/<em>&lt;job_id&gt;</em></td><td>GET</td><td>Get a specific 
job's 
status</td><td>maxcount=&lt;maximum_documents_to_count&gt;</td><td>{"jobstatus":<em>&lt;job_status_object&gt;</em>}
 <strong>OR</strong> { } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>} </td></tr>
+            
<tr><td>jobstatusesnocounts<em>&lt;job_id&gt;</em></td><td>GET</td><td>List all 
jobs and their status, returning '0' for all 
counts</td><td>N/A</td><td>{"jobstatus":[<em>&lt;list_of_job_status_objects&gt;</em>]}
 <strong>OR</strong> { } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>} </td></tr>
+            
<tr><td>jobstatusesnocounts/<em>&lt;job_id&gt;</em></td><td>GET</td><td>Get a 
specific job's status, returning '0' for all 
counts</td><td>N/A</td><td>{"jobstatus":<em>&lt;job_status_object&gt;</em>} 
<strong>OR</strong> { } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>} </td></tr>
+            <tr><td>start/<em>&lt;job_id&gt;</em></td><td>PUT</td><td>Start a 
specified job manually</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>startminimal/<em>&lt;job_id&gt;</em></td><td>PUT</td><td>Start a 
specified job manually, minimal run requested</td><td>N/A</td><td>{ } 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>abort/<em>&lt;job_id&gt;</em></td><td>PUT</td><td>Abort a 
specified job</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>restart/<em>&lt;job_id&gt;</em></td><td>PUT</td><td>Stop 
and start a specified job</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>restartminimal/<em>&lt;job_id&gt;</em></td><td>PUT</td><td>Stop and 
start a specified job, minimal run requested</td><td>N/A</td><td>{ } 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>pause/<em>&lt;job_id&gt;</em></td><td>PUT</td><td>Pause a 
specified job</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>resume/<em>&lt;job_id&gt;</em></td><td>PUT</td><td>Resume 
a specified job</td><td>N/A</td><td>{ } <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            <tr><td>reseed/<em>&lt;job_id&gt;</em></td><td>PUT</td><td>Reset 
incremental seeding for a specified job</td><td>N/A</td><td>{ } 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+
+            
<tr><td>repositoryconnectionhistory/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Get
 a history 
report</td><td><em>&lt;history_query_parameters&gt;</em></td><td>{"row":[{"column":[{"name":<em>&lt;col_name&gt;</em>,"value":<em>&lt;col_value&gt;</em>},
 ...]}, ...]} <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>repositoryconnectionquery/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Get
 a queue 
report</td><td><em>&lt;queue_query_parameters&gt;</em></td><td>{"row":[{"column":[{"name":<em>&lt;col_name&gt;</em>,"value":<em>&lt;col_value&gt;</em>},
 ...]}, ...]} <strong>OR</strong> 
{"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>repositoryconnectionactivities/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Get
 a list of legal activities for a 
connection</td><td>N/A</td><td>{"activity":[<em>&lt;activity_name&gt;</em>, 
...]} <strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+            
<tr><td>repositoryconnectionjobs/<em>&lt;encoded_connection_name&gt;</em></td><td>GET</td><td>Get
 a list of jobs for a 
connection</td><td>N/A</td><td>{"job":[<em>&lt;list_of_job_objects&gt;</em>]} 
<strong>OR</strong> {"error":<em>&lt;error_text&gt;</em>}</td></tr>
+
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>History query parameters</title>
+          <p></p>
+          <p>The history query parameters and their meanings are as 
follows:</p>
+          <table>
+            <tr><th>Parameter</th><th>Report 
type</th><th>Multivalued?</th><th>Meaning</th></tr>
+            <tr><td>report</td><td>All</td><td>No</td><td>The kind of history 
report desired; legal values are "simple", "maxactivity", "maxbandwidth", and 
"result"; defaults to "simple"</td></tr>
+            <tr><td>starttime</td><td>All</td><td>No</td><td>Starting time in 
ms since epoch; defaults to "0"</td></tr>
+            <tr><td>endtime</td><td>All</td><td>No</td><td>Ending time in ms 
since epoch; defaults to now</td></tr>
+            <tr><td>activity</td><td>All</td><td>Yes</td><td>Which activities 
you want to see</td></tr>
+            <tr><td>entitymatch</td><td>All</td><td>No</td><td>Regular 
expression matching entity identifier; defaults to ""</td></tr>
+            
<tr><td>entitymatch_insensitive</td><td>All</td><td>No</td><td>Case insensitive 
version of entitymatch</td></tr>
+            <tr><td>resultcodematch</td><td>All</td><td>No</td><td>Regular 
expression match result code; defaults to ""</td></tr>
+            
<tr><td>resultcodematch_insensitive</td><td>All</td><td>No</td><td>Case 
insensitive version of resultcodematch</td></tr>
+            <tr><td>sortcolumn</td><td>All</td><td>Yes</td><td>Result column 
to sort the result by</td></tr>
+            
<tr><td>sortcolumn_direction</td><td>All</td><td>Yes</td><td>Direction to sort 
the corresponding column ("ascending" or "descending")</td></tr>
+            <tr><td>startrow</td><td>All</td><td>No</td><td>Starting row in 
resultset to return; defaults to 0</td></tr>
+            <tr><td>rowcount</td><td>All</td><td>No</td><td>Maximum number of 
rows to return; defaults to 20</td></tr>
+            <tr><td>idbucket</td><td>maxactivity, maxbandwidth, 
result</td><td>No</td><td>Regular expression selecting which part of the entity 
identifier to use as an aggregation key; defaults to "()"</td></tr>
+            <tr><td>idbucket_insensitive</td><td>maxactivity, maxbandwidth, 
result</td><td>No</td><td>Case insensitive version of idbucket</td></tr>
+            <tr><td>resultcodebucket</td><td>result</td><td>No</td><td>Regular 
expression selecting which part of the result code to use as an aggregation 
key; defaults to "(.*)"</td></tr>
+            
<tr><td>resultcodebucket_insensitive</td><td>result</td><td>No</td><td>Case 
insensitive version of resultcodebucket</td></tr>
+            <tr><td>interval</td><td>maxactivity, 
maxbandwidth</td><td>No</td><td>Size of window in milliseconds for assessing 
rate; defaults to 300000</td></tr>
+          </table>
+          <p></p>
+          <p>Each report type has different return columns, as listed 
below:</p>
+          <p></p>
+          <table>
+            <tr><th>Report type</th><th>Return columns</th></tr>
+            <tr><td>simple</td><td>starttime, resultcode, resultdesc, 
identifier, activity, bytes, elapsedtime</td></tr>
+            <tr><td>maxactivity</td><td>starttime, endtime, activitycount, 
idbucket</td></tr>
+            <tr><td>maxbandwidth</td><td>starttime, endtime, bytecount, 
idbucket</td></tr>
+            <tr><td>result</td><td>idbucket, resultcodebucket, 
eventcount</td></tr>
+          </table>
+        </section>
+        <section>
+          <title>Queue query parameters</title>
+          <p></p>
+          <p>The queue query parameters and their meanings are as follows:</p>
+          <table>
+            <tr><th>Parameter</th><th>Report 
type</th><th>Multivalued?</th><th>Meaning</th></tr>
+            <tr><td>report</td><td>All</td><td>No</td><td>The kind of queue 
report desired; legal values are "document" or "status"; defaults to 
"document"</td></tr>
+            <tr><td>now</td><td>All</td><td>No</td><td>The time in 
milliseconds since epoch to perform the queue assessment relative to; defaults 
to current time</td></tr>
+            <tr><td>idmatch</td><td>All</td><td>No</td><td>Regular expression 
matching document identifier; defaults to ""</td></tr>
+            <tr><td>idmatch_insensitive</td><td>All</td><td>No</td><td>Case 
insensitive version of idmatch</td></tr>
+            <tr><td>statematch</td><td>All</td><td>Yes</td><td>State to match; 
valid values are "neverprocessed", "previouslyprocessed", "outofscope"</td></tr>
+            <tr><td>statusmatch</td><td>All</td><td>Yes</td><td>Status to 
match; valid values are "inactive", "processing", "expiring", "deleting", 
"readyforprocessing", "readyforexpiration", "waitingforprocessing", 
"waitingforexpiration", "waitingforever", and "hopcountexceeded"</td></tr>
+            <tr><td>sortcolumn</td><td>All</td><td>Yes</td><td>Result column 
to sort the result by</td></tr>
+            
<tr><td>sortcolumn_direction</td><td>All</td><td>Yes</td><td>Direction to sort 
the corresponding column ("ascending" or "descending")</td></tr>
+            <tr><td>startrow</td><td>All</td><td>No</td><td>Starting row in 
resultset to return; defaults to 0</td></tr>
+            <tr><td>rowcount</td><td>All</td><td>No</td><td>Maximum number of 
rows to return; defaults to 20</td></tr>
+            <tr><td>idbucket</td><td>status</td><td>No</td><td>Regular 
expression selecting which part of the document identifier to use as an 
aggregation key; defaults to "()"</td></tr>
+            
<tr><td>idbucket_insensitive</td><td>status</td><td>No</td><td>Case insensitive 
version of idbucket</td></tr>
+          </table>
+          <p></p>
+          <p>Each report type has different return columns, as listed 
below:</p>
+          <p></p>
+          <table>
+            <tr><th>Report type</th><th>Return columns</th></tr>
+            <tr><td>document</td><td>identifier, job, state, status, 
scheduled, action, retrycount, retrylimit</td></tr>
+            <tr><td>status</td><td>idbucket, inactive, processing, expiring, 
deleting, processready, expireready, processwaiting, expirewaiting, 
waitingforever, hopcountexceeded</td></tr>
+          </table>
+        </section>
+        <section>
+          <title>Authorization domain objects</title>
+          <p></p>
+          <p>The JSON fields an authorization domain object has are as 
follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"description"</td><td>The optional description of the 
authorization domain</td></tr>
+            <tr><td>"domain_name"</td><td>The internal name of the 
authorization domain, i.e. what is sent to the Authority Service</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Output connector objects</title>
+          <p></p>
+          <p>The JSON fields an output connector object has are as follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"description"</td><td>The optional description of the 
connector</td></tr>
+            <tr><td>"class_name"</td><td>The class name of the class 
implementing the connector</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Transformation connector objects</title>
+          <p></p>
+          <p>The JSON fields a transformation connector object has are as 
follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"description"</td><td>The optional description of the 
connector</td></tr>
+            <tr><td>"class_name"</td><td>The class name of the class 
implementing the connector</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Mapping connector objects</title>
+          <p></p>
+          <p>The JSON fields a mapping connector object has are as follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"description"</td><td>The optional description of the 
connector</td></tr>
+            <tr><td>"class_name"</td><td>The class name of the class 
implementing the connector</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Authority connector objects</title>
+          <p></p>
+          <p>The JSON fields an authority connector object has are as 
follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"description"</td><td>The optional description of the 
connector</td></tr>
+            <tr><td>"class_name"</td><td>The class name of the class 
implementing the connector</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Repository connector objects</title>
+          <p></p>
+          <p>The JSON fields a repository connector object has are as 
follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"description"</td><td>The optional description of the 
connector</td></tr>
+            <tr><td>"class_name"</td><td>The class name of the class 
implementing the connector</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Authority group objects</title>
+          <p></p>
+          <p>Authority group names, when they are part of a URL, should be 
encoded as follows:</p>
+          <p></p>
+          <ol>
+            <li>All instances of '.' should be replaced by '..'.</li>
+            <li>All instances of '/' should be replaced by '.+'.</li>
+            <li>The URL should be encoded using standard URL utf-8-based 
%-encoding.</li>
+          </ol>
+          <p></p>
+          <p>The JSON fields an authority group object has are as follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"name"</td><td>The unique name of the group</td></tr>
+            <tr><td>"description"</td><td>The description of the 
group</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Output connection objects</title>
+          <p></p>
+          <p>Output connection names, when they are part of a URL, should be 
encoded as follows:</p>
+          <p></p>
+          <ol>
+            <li>All instances of '.' should be replaced by '..'.</li>
+            <li>All instances of '/' should be replaced by '.+'.</li>
+            <li>The URL should be encoded using standard URL utf-8-based 
%-encoding.</li>
+          </ol>
+          <p></p>
+          <p>The JSON fields an output connection object has are as 
follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"name"</td><td>The unique name of the connection</td></tr>
+            <tr><td>"description"</td><td>The description of the 
connection</td></tr>
+            <tr><td>"class_name"</td><td>The java class name of the class 
implementing the connection</td></tr>
+            <tr><td>"max_connections"</td><td>The total number of outstanding 
connections allowed to exist at a time</td></tr>
+            <tr><td>"configuration"</td><td>The configuration object for the 
connection, which is specific to the connection class</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Transformation connection objects</title>
+          <p></p>
+          <p>Transformation connection names, when they are part of a URL, 
should be encoded as follows:</p>
+          <p></p>
+          <ol>
+            <li>All instances of '.' should be replaced by '..'.</li>
+            <li>All instances of '/' should be replaced by '.+'.</li>
+            <li>The URL should be encoded using standard URL utf-8-based 
%-encoding.</li>
+          </ol>
+          <p></p>
+          <p>The JSON fields an output connection object has are as 
follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"name"</td><td>The unique name of the connection</td></tr>
+            <tr><td>"description"</td><td>The description of the 
connection</td></tr>
+            <tr><td>"class_name"</td><td>The java class name of the class 
implementing the connection</td></tr>
+            <tr><td>"max_connections"</td><td>The total number of outstanding 
connections allowed to exist at a time</td></tr>
+            <tr><td>"configuration"</td><td>The configuration object for the 
connection, which is specific to the connection class</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Mapping connection objects</title>
+          <p></p>
+          <p>Mapping connection names, when they are part of a URL, should be 
encoded as follows:</p>
+          <p></p>
+          <ol>
+            <li>All instances of '.' should be replaced by '..'.</li>
+            <li>All instances of '/' should be replaced by '.+'.</li>
+            <li>The URL should be encoded using standard URL utf-8-based 
%-encoding.</li>
+          </ol>
+          <p></p>
+          <p>The JSON fields for a mapping connection object are as 
follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"name"</td><td>The unique name of the connection</td></tr>
+            <tr><td>"description"</td><td>The description of the 
connection</td></tr>
+            <tr><td>"class_name"</td><td>The java class name of the class 
implementing the connection</td></tr>
+            <tr><td>"max_connections"</td><td>The total number of outstanding 
connections allowed to exist at a time</td></tr>
+            <tr><td>"configuration"</td><td>The configuration object for the 
connection, which is specific to the connection class</td></tr>
+            <tr><td>"prerequisite"</td><td>The mapping connection 
prerequisite, if any</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Authority connection objects</title>
+          <p></p>
+          <p>Authority connection names, when they are part of a URL, should 
be encoded as follows:</p>
+          <p></p>
+          <ol>
+            <li>All instances of '.' should be replaced by '..'.</li>
+            <li>All instances of '/' should be replaced by '.+'.</li>
+            <li>The URL should be encoded using standard URL utf-8-based 
%-encoding.</li>
+          </ol>
+          <p></p>
+          <p>The JSON fields for an authority connection object are as 
follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"name"</td><td>The unique name of the connection</td></tr>
+            <tr><td>"description"</td><td>The description of the 
connection</td></tr>
+            <tr><td>"class_name"</td><td>The java class name of the class 
implementing the connection</td></tr>
+            <tr><td>"max_connections"</td><td>The total number of outstanding 
connections allowed to exist at a time</td></tr>
+            <tr><td>"configuration"</td><td>The configuration object for the 
connection, which is specific to the connection class</td></tr>
+            <tr><td>"prerequisite"</td><td>The mapping connection 
prerequisite, if any</td></tr>
+            <tr><td>"authdomain"</td><td>The authorization domain for the 
authority connection, if any</td></tr>
+            <tr><td>"authgroup"</td><td>The required authority group for the 
authority connection</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Repository connection objects</title>
+          <p></p>
+          <p>Repository connection names, when they are part of a URL, should 
be encoded as follows:</p>
+          <p></p>
+          <ol>
+            <li>All instances of '.' should be replaced by '..'.</li>
+            <li>All instances of '/' should be replaced by '.+'.</li>
+            <li>The URL should be encoded using standard URL utf-8-based 
%-encoding.</li>
+          </ol>
+          <p></p>
+          <p>The JSON fields for a repository connection object are as 
follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"name"</td><td>The unique name of the connection</td></tr>
+            <tr><td>"description"</td><td>The description of the 
connection</td></tr>
+            <tr><td>"class_name"</td><td>The java class name of the class 
implementing the connection</td></tr>
+            <tr><td>"max_connections"</td><td>The total number of outstanding 
connections allowed to exist at a time</td></tr>
+            <tr><td>"configuration"</td><td>The configuration object for the 
connection, which is specific to the connection class</td></tr>
+            <tr><td>"acl_authority"</td><td>The (optional) name of the 
authority group that will enforce security for this connection</td></tr>
+            <tr><td>"throttle"</td><td>An array of throttle objects, which 
control how quickly documents can be requested from this connection</td></tr>
+          </table>
+          <p></p>
+          <p>Each throttle object has the following fields:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"match"</td><td>The regular expression which is used to 
match a document's bins to determine if the throttle should be applied</td></tr>
+            <tr><td>"match_description"</td><td>Optional text describing the 
meaning of the throttle</td></tr>
+            <tr><td>"rate"</td><td>The maximum fetch rate to use if the 
throttle applies, in fetches per minute</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Job objects</title>
+          <p></p>
+          <p>The JSON fields for a job are is as follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"id"</td><td>The job's identifier, if present.  If not 
present, ManifoldCF will create one (and will also create the job when 
saved).</td></tr>
+            <tr><td>"description"</td><td>Text describing the job</td></tr>
+            <tr><td>"repository_connection"</td><td>The name of the repository 
connection to use with the job</td></tr>
+            <tr><td>"output_connection"</td><td>The name of the output 
connection to use with the job</td></tr>
+            <tr><td>"document_specification"</td><td>The document 
specification object for the job, whose format is repository-connection 
specific</td></tr>
+            <tr><td>"output_specification"</td><td>The output specification 
object for the job, whose format is output-connection specific</td></tr>
+            <tr><td>"start_mode"</td><td>The start mode for the job, which can 
be one of "schedule window start", "schedule window anytime", or 
"manual"</td></tr>
+            <tr><td>"run_mode"</td><td>The run mode for the job, which can be 
either "continuous" or "scan once"</td></tr>
+            <tr><td>"hopcount_mode"</td><td>The hopcount mode for the job, 
which can be either "accurate", "no delete", "never delete"</td></tr>
+            <tr><td>"priority"</td><td>The job's priority, typically 
"5"</td></tr>
+            <tr><td>"recrawl_interval"</td><td>The default time between 
recrawl of documents (if the job is "continuous"), in milliseconds, or 
"infinite" for infinity</td></tr>
+            <tr><td>"expiration_interval"</td><td>The time until a document 
expires (if the job is "continuous"), in milliseconds, or "infinite" for 
infinity</td></tr>
+            <tr><td>"reseed_interval"</td><td>The time between reseeding 
operations (if the job is "continuous"), in milliseconds, or "infinite" for 
infinity</td></tr>
+            <tr><td>"hopcount"</td><td>An array of hopcount objects, 
describing the link types and associated maximum hops permitted for the 
job</td></tr>
+            <tr><td>"schedule"</td><td>An array of schedule objects, 
describing when the job should be started and run</td></tr>
+            <tr><td>"forcedparam"</td><td>An array of forcedparam objects, 
describing what forced parameters should be set</td></tr>
+            <tr><td>"pipelinestage"</td><td>An array of pipelinestage objects, 
describing what the transformation pipeline is</td></tr>
+          </table>
+          <p></p>
+          <p>Each pipelinestage object has the following fields:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"stage_connectionname"</td><td>The connection name for the 
pipeline stage</td></tr>
+            <tr><td>"stage_description"</td><td>A description of the pipeline 
stage</td></tr>
+            <tr><td>"stage_specification"</td><td>The transformation 
specification for the pipeline stage</td></tr>
+          </table>
+          <p></p>
+          <p>Each forcedparam object has the following fields:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"paramname"</td><td>The name of the parameter</td></tr>
+            <tr><td>"paramvalue"</td><td>The value of the parameter</td></tr>
+          </table>
+          <p></p>
+          <p>Each hopcount object has the following fields:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"link_type"</td><td>The connection-type-dependent type of 
a link for which a hop count restriction is specified</td></tr>
+            <tr><td>"count"</td><td>The maximum number of hops allowed for the 
associated link type, starting at a seed</td></tr>
+          </table>
+          <p></p>
+          <p>Each schedule object has the following fields:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"timezone"</td><td>The optional time zone for the schedule 
object; if not present the default server time zone is used</td></tr>
+            <tr><td>"duration"</td><td>The optional length of the described 
time window, in milliseconds; if not present, duration is considered 
infinite</td></tr>
+            <tr><td>"dayofweek"</td><td>The optional day-of-the-week 
enumeration object</td></tr>
+            <tr><td>"monthofyear"</td><td>The optional month-of-the-year 
enumeration object</td></tr>
+            <tr><td>"dayofmonth"</td><td>The optional day-of-the-month 
enumeration object</td></tr>
+            <tr><td>"year"</td><td>The optional year enumeration 
object</td></tr>
+            <tr><td>"hourofday"</td><td>The optional hour-of-the-day 
enumeration object</td></tr>
+            <tr><td>"minutesofhour"</td><td>The optional minutes-of-the-hour 
enumeration object</td></tr>
+            <tr><td>"requestminimum"</td><td>Optional flag indicating whether 
the job run will be minimal or not ("true" means minimal)</td></tr>
+          </table>
+          <p></p>
+          <p>Each enumeration object describes an array of integers using the 
form:</p>
+          <p></p>
+          <p>{"value":[<em>&lt;integer_list&gt;</em>]}</p>
+          <p></p>
+          <p>Each integer is a zero-based index describing which entity is 
being specified.  For example, for "dayofweek", 0 corresponds to Sunday, etc., 
and thus "dayofweek":{"value":[0,6]} would describe Saturdays and Sundays.</p>
+          <p></p>
+        </section>
+        <section>
+          <title>Job status objects</title>
+          <p></p>
+          <p>The JSON fields of a job status object are as follows:</p>
+          <p></p>
+          <table>
+            <tr><th>Field</th><th>Meaning</th></tr>
+            <tr><td>"job_id"</td><td>The job identifier</td></tr>
+            <tr><td>"status"</td><td>The job status, having the possible 
values: "not yet run", "running", "paused", "done", "waiting", "stopping", 
"resuming", "starting up", "cleaning up", "error", "aborting", "restarting", 
"running no connector", and "terminating"</td></tr>
+            <tr><td>"error_text"</td><td>The error text, if the status is 
"error"</td></tr>
+            <tr><td>"start_time"</td><td>The job start time, in milliseconds 
since Jan 1, 1970</td></tr>
+            <tr><td>"end_time"</td><td>The job end time, in milliseconds since 
Jan 1, 1970</td></tr>
+            <tr><td>"documents_in_queue"</td><td>The total number of documents 
in the queue for the job</td></tr>
+            <tr><td>"documents_outstanding"</td><td>The number of documents 
for the job that are currently considered 'active'</td></tr>
+            <tr><td>"documents_processed"</td><td>The number of documents that 
in the queue for the job that have been processed at least once</td></tr>
+          </table>
+          <p></p>
+        </section>
+        <section>
+          <title>Connection-type-specific objects</title>
+          <p></p>
+          <p>As you may note when trying to use the above JSON API methods, 
you cannot get very far in defining connections or jobs without knowing the 
JSON format of a connection's configuration information, or a job's 
connection-specific document specification and output specification 
information.  The form of these objects is controlled by the Java 
implementation of the underlying connector, and is translated directly into 
JSON, so if you write your own connector you should be able to figure out what 
it will be in the API.  For connectors already part of ManifoldCF, it remains 
an ongoing task to document these connector-specific objects.  This task is not 
yet underway.</p>
+          <p></p>
+          <p>Luckily, it is pretty easy to learn a lot about the objects in 
question by simply creating connections and jobs in the ManifoldCF crawler UI, 
and then inspecting the resulting JSON objects through the API.  In this way, 
it should be possible to do a decent job of coding most API-based integrations. 
 The one place where difficulties will certainly occur will be if you try to 
completely replace the ManifoldCF crawler UI with one of your own.  This is 
because most connectors have methods that communicate with their respective 
back-ends in order to allow the user to select appropriate values.  For 
example, the path drill-down that is presented by the LiveLink connector 
requires that the connector interrogate the appropriate LiveLink repository in 
order to populate its path selection pull-downs.  There is, at this time, only 
one sanctioned way to accomplish the same job using the API, which is to use 
the appropriate "<em>connection_type</em>/execute/<em>type-specific_command
 </em>" command to perform the necessary functions.  Some set of useful 
functions has been coded for every appropriate connector, but the exact 
commands for every connector, and their JSON syntax, remains undocumented for 
now.</p>
+          <p></p>
+        </section>
+        <section>
+          <title>File system connector</title>
+          <p></p>
+          <p>The file system connector has no configuration information, and 
no connector-specific commands.  However, it does have document specification 
information.  The information looks something like this:</p>
+          <p></p>
+          
<p>{"startpoint":[{"_attribute_path":"c:\path_to_files","include":[{"_attribute_type":"file","_attribute_match":"*.txt"},{"_attribute_type":"file","_attribute_match":"*.doc"\,"_attribute_type":"directory","_attribute_match":"*"],"exclude":["*.mov"]]}</p>
+          <p></p>
+          <p>As you can see, multiple starting paths are possible, and the 
inclusion and exclusion rules also can be one or multiple.</p>
+          <p></p>
+          <p></p>
+        </section>
+      </section>
+      <section>
+        <title>Control via Commands</title>
+        <p></p>
+        <p>For script writers, there currently exist a number of ManifoldCF 
execution commands.  These commands are primarily rich in the area of 
definition of connections and jobs, controlling jobs, and running reports.  The 
following table lists the current suite.</p>
+        <p></p>
+        <table>
+          <tr><th>Command</th><th>What it does</th></tr>
+          
<tr><td>org.apache.manifoldcf.agents.DefineOutputConnection</td><td>Create a 
new output connection</td></tr>
+          
<tr><td>org.apache.manifoldcf.agents.DeleteOutputConnection</td><td>Delete an 
existing output connection</td></tr>
+          
<tr><td>org.apache.manifoldcf.agents.DefineTransformationConnection</td><td>Create
 a new transformation connection</td></tr>
+          
<tr><td>org.apache.manifoldcf.agents.DeleteTransformationConnection</td><td>Delete
 an existing transformation connection</td></tr>
+          
<tr><td>org.apache.manifoldcf.authorities.ChangeAuthSpec</td><td>Modify an 
authority's configuration information</td></tr>
+          <tr><td>org.apache.manifoldcf.authorities.CheckAll</td><td>Check all 
authorities to be sure they are functioning</td></tr>
+          
<tr><td>org.apache.manifoldcf.authorities.DefineAuthorityConnection</td><td>Create
 a new authority connection</td></tr>
+          
<tr><td>org.apache.manifoldcf.authorities.DeleteAuthorityConnection</td><td>Delete
 an existing authority connection</td></tr>
+          
<tr><td>org.apache.manifoldcf.authorities.DefineMappingConnection</td><td>Create
 a new mapping connection</td></tr>
+          
<tr><td>org.apache.manifoldcf.authorities.DeleteMappingConnection</td><td>Delete
 an existing mapping connection</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.AbortJob</td><td>Abort a 
running job</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.AddScheduledTime</td><td>Add a 
schedule record to a job</td></tr>
+          
<tr><td>org.apache.manifoldcf.crawler.ChangeJobDocSpec</td><td>Modify a job's 
specification information</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.DefineJob</td><td>Create a new 
job</td></tr>
+          
<tr><td>org.apache.manifoldcf.crawler.DefineRepositoryConnection</td><td>Create 
a new repository connection</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.DeleteJob</td><td>Delete an 
existing job</td></tr>
+          
<tr><td>org.apache.manifoldcf.crawler.DeleteRepositoryConnection</td><td>Delete 
an existing repository connection</td></tr>
+          
<tr><td>org.apache.manifoldcf.crawler.ExportConfiguration</td><td>Write the 
complete list of all connection definitions and job specifications to a 
file</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.FindJob</td><td>Locate a job 
identifier given a job's name</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.GetJobSchedule</td><td>Find a 
job's schedule given a job's identifier</td></tr>
+          
<tr><td>org.apache.manifoldcf.crawler.ImportConfiguration</td><td>Import 
configuration as written by a previous ExportConfiguration command</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.ListJobStatuses</td><td>List 
the status of all jobs</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.ListJobs</td><td>List the 
identifiers for all jobs</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.PauseJob</td><td>Given a job 
identifier, pause the specified job</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.RestartJob</td><td>Given a job 
identifier, restart the specified job</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.RunDocumentStatus</td><td>Run 
a document status report</td></tr>
+          
<tr><td>org.apache.manifoldcf.crawler.RunMaxActivityHistory</td><td>Run a 
maximum activity report</td></tr>
+          
<tr><td>org.apache.manifoldcf.crawler.RunMaxBandwidthHistory</td><td>Run a 
maximum bandwidth report</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.RunQueueStatus</td><td>Run a 
queue status report</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.RunResultHistory</td><td>Run a 
result history report</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.RunSimpleHistory</td><td>Run a 
simply history report</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.StartJob</td><td>Start a 
job</td></tr>
+          
<tr><td>org.apache.manifoldcf.crawler.WaitForJobDeleted</td><td>After a job has 
been deleted, wait until the delete has completed</td></tr>
+          
<tr><td>org.apache.manifoldcf.crawler.WaitForJobInactive</td><td>After a job 
has been started or aborted, wait until the job ceases all activity</td></tr>
+          <tr><td>org.apache.manifoldcf.crawler.WaitJobPaused</td><td>After a 
job has been paused, wait for the pause to take effect</td></tr>
+        </table>
+        <p></p>
+      </section>
+      <section>
+        <title>Control by direct code</title>
+        <p></p>
+        <p>Control by direct java code is quite a reasonable thing to do.  The 
sources of the above commands should give a pretty clear idea how to proceed, 
if that's what you
+          want to do.</p>
+        <p></p>
+        <p></p>
+      </section>
+      <section>
+        <title>Caveats</title>
+        <p></p>
+        <p>The above commands know nothing about the differences between 
connection types.  Instead, they deal with configuration and specification 
information in the
+          form of XML documents.  Normally, these XML documents are hidden 
from a system integrator, unless they happen to look into the database with a 
tool such as
+          psql.  But the API commands above often will require such XML 
documents to be included as part of the command execution.</p>
+        <p></p>
+        <p>This has one major consequence.  Any application that would 
manipulate connections and jobs directly cannot be connection-type independent 
- these
+          applications must know the proper form of XML to submit to the 
command.  So, it is not possible to use these command APIs to write one's own 
UI wrapper,
+          without sacrificing some of the repository independence that 
ManifoldCF by itself maintains.</p>
+      </section>
+    </section>
+  </body>
+
+</document>

svn commit: r1617058 [5/8] - in /manifoldcf/trunk: connectors/rss/connector/src/main/native2ascii/org/apache/manifoldcf/crawler/connectors/rss/ framework/ui-core/src/main/native2ascii/org/apache/manifoldcf/ui/i18n/ site/src/documentation/content/xdocs/...

Reply via email to