NUTCH-1595 Upgrade to Tika 1.4

git-svn-id: https://svn.apache.org/repos/asf/nutch/trunk@1499960 13f79535-47bb-0310-9956-ffa450edef68
sunmeng007 · Jul 5, 2013 · d3388ef · d3388ef
1 parent 4b14891
commit d3388ef
Show file tree

Hide file tree

Showing 5 changed files with 23 additions and 13 deletions.
diff --git a/CHANGES.txt b/CHANGES.txt
@@ -2,6 +2,8 @@ Nutch Change Log
 
 Nutch Development Trunk
 
+* NUTCH-1595 Upgrade to Tika 1.4 (jnioche, markus)
+
 * NUTCH-1598 ElasticSearchIndexer to read ImmutableSettings from config (markus)
 
 * NUTCH-1520 SegmentMerger looses records (markus)

diff --git a/ivy/ivy.xml b/ivy/ivy.xml
@@ -64,7 +64,7 @@
 			<exclude org="ant" name="ant" />
 		</dependency>
 
-		<dependency org="org.apache.tika" name="tika-core" rev="1.3" />
+		<dependency org="org.apache.tika" name="tika-core" rev="1.4" />
 		<dependency org="com.ibm.icu" name="icu4j" rev="4.0.1" />
 
 		<dependency org="org.mortbay.jetty" name="jetty-client"

diff --git a/src/plugin/parse-tika/howto_upgrade_tika.txt b/src/plugin/parse-tika/howto_upgrade_tika.txt
@@ -0,0 +1,8 @@
+1. Upgrade Tika depencency in trunk/ivy/ivy.xml
+
+2. Upgrade Tika dependency in src/plugin/parse-tika/ivy.xml
+
+3. Upgrade Tika's own dependencies in src/plugin/parse-tika/plugin.xml
+   To get the list of dependencies and their versions execute:
+   $ ant -f ./build-ivy.xml
+   $ ls lib/
diff --git a/src/plugin/parse-tika/ivy.xml b/src/plugin/parse-tika/ivy.xml
@@ -36,7 +36,7 @@
   </publications>
 
   <dependencies>
-    <dependency org="org.apache.tika" name="tika-parsers" rev="1.3" conf="*->default">
+    <dependency org="org.apache.tika" name="tika-parsers" rev="1.4" conf="*->default">
      <exclude org="org.apache.tika" name="tika-core" />
     </dependency>
   </dependencies>

diff --git a/src/plugin/parse-tika/plugin.xml b/src/plugin/parse-tika/plugin.xml
@@ -28,39 +28,39 @@
 
       <library name="apache-mime4j-core-0.7.2.jar"/>
       <library name="apache-mime4j-dom-0.7.2.jar"/>
-      <library name="asm-3.1.jar"/>
+      <library name="asm-4.1.jar"/>
       <library name="aspectjrt-1.6.11.jar"/>
       <library name="bcmail-jdk15-1.45.jar"/>
       <library name="bcprov-jdk15-1.45.jar"/>
       <library name="boilerpipe-1.1.0.jar"/>
       <library name="commons-codec-1.5.jar"/>
-      <library name="commons-compress-1.4.1.jar"/>
+      <library name="commons-compress-1.5.jar"/>
       <library name="commons-logging-1.1.1.jar"/>
       <library name="dom4j-1.6.1.jar"/>
-      <library name="fontbox-1.7.1.jar"/>
+      <library name="fontbox-1.8.1.jar"/>
       <library name="geronimo-stax-api_1.0_spec-1.0.1.jar"/>
       <library name="isoparser-1.0-RC-1.jar"/>
       <library name="jdom-1.0.jar"/>
-      <library name="jempbox-1.7.1.jar"/>
+      <library name="jempbox-1.8.1.jar"/>
       <library name="juniversalchardet-1.0.3.jar"/>
       <library name="metadata-extractor-2.6.2.jar"/>
       <library name="netcdf-4.2-min.jar"/>
-      <library name="pdfbox-1.7.1.jar"/>
-      <library name="poi-3.8.jar"/>
-      <library name="poi-ooxml-3.8.jar"/>
-      <library name="poi-ooxml-schemas-3.8.jar"/>
-      <library name="poi-scratchpad-3.8.jar"/>
+      <library name="pdfbox-1.8.1.jar"/>
+      <library name="poi-3.9.jar"/>
+      <library name="poi-ooxml-3.9.jar"/>
+      <library name="poi-ooxml-schemas-3.9.jar"/>
+      <library name="poi-scratchpad-3.9.jar"/>
       <library name="rome-0.9.jar"/>
       <library name="slf4j-api-1.5.6.jar"/>
       <library name="tagsoup-1.2.1.jar"/>
-      <library name="tika-parsers-1.3.jar"/>
+      <library name="tika-parsers-1.4.jar"/>
       <library name="vorbis-java-core-0.1.jar"/>
       <library name="vorbis-java-tika-0.1.jar"/>
       <library name="xercesImpl-2.8.1.jar"/>
       <library name="xml-apis-1.3.03.jar"/>
       <library name="xmlbeans-2.3.0.jar"/>
       <library name="xmpcore-5.1.2.jar"/>
-      <library name="xz-1.0.jar"/>
+      <library name="xz-1.2.jar"/>
    </runtime>
 
    <requires>