You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@manifoldcf.apache.org by kw...@apache.org on 2014/10/05 23:13:10 UTC

svn commit: r1629541 [1/3] - in /manifoldcf/trunk: build.xml connectors/tika/build.xml connectors/tika/pom.xml dist-license/LICENSE.txt lib-license/LICENSE.txt

Author: kwright
Date: Sun Oct  5 21:13:09 2014
New Revision: 1629541

URL: http://svn.apache.org/r1629541
Log:
Another fix for migration to Tika 1.6.  Remove netcdf jjar, since it's LGPL now and can't be redistributed, and audit all the subdependencies of Tika thoroughly.

Modified:
    manifoldcf/trunk/build.xml
    manifoldcf/trunk/connectors/tika/build.xml
    manifoldcf/trunk/connectors/tika/pom.xml
    manifoldcf/trunk/dist-license/LICENSE.txt
    manifoldcf/trunk/lib-license/LICENSE.txt

Modified: manifoldcf/trunk/build.xml
URL: http://svn.apache.org/viewvc/manifoldcf/trunk/build.xml?rev=1629541&r1=1629540&r2=1629541&view=diff
==============================================================================
--- manifoldcf/trunk/build.xml (original)
+++ manifoldcf/trunk/build.xml Sun Oct  5 21:13:09 2014
@@ -99,7 +99,33 @@
     <property name="mockito.version" value="1.9.5"/>
     <property name="wiremock.version" value="1.34"/>
     <property name="objenesis.version" value="2.1"/>
-    
+    <property name="tika.version" value="1.6"/>
+    <property name="tagsoup.version" value="1.2.1"/>
+    <property name="james.version" value="0.7.2"/>
+    <property name="vorbis.version" value="0.6"/>
+    <property name="metadata-extractor.version" value="2.6.2"/>
+    <property name="aspectjrt.version" value="1.8.0"/>
+    <property name="jhighlight.version" value="1.0"/>
+    <property name="xmlbeans.version" value="2.6.0"/>
+    <property name="bc.version" value="1.45"/>
+    <property name="tukaani.version" value="1.5"/>
+    <property name="pdfbox.version" value="1.8.6"/>
+    <property name="commons-compress.version" value="1.8.1"/>
+    <property name="juniversalchardet.version" value="1.0.3"/>
+    <property name="netcdf.version" value="4.2.20"/>
+    <property name="boilerpipe.version" value="1.1.0"/>
+    <property name="dom4j.version" value="1.6.1"/>
+    <property name="asm.version" value="4.1"/>
+    <property name="xmpcore.version" value="5.1.2"/>
+    <property name="jdom.version" value="1.0"/>
+    <property name="rome.version" value="1.0"/>
+    <property name="mp4parser.version" value="1.0.2"/>
+    <property name="jmatio.version" value="1.0"/>
+    <property name="java-libpst.version" value="0.8.1"/>
+    <property name="commons-httpclient.version" value="3.1"/>
+    <property name="jackson-databind.version" value="2.1.3"/>
+    <property name="jackson-annotations.version" value="2.1.2"/>
+
     <target name="downloaded-condition">
         <!-- Spot check a few of the dependent jars; no point including ALL of them here... -->
         <available file="lib/hsqldb-${hsqldb.version}.jar" property="hsqldb-found"/>
@@ -1586,201 +1612,257 @@ Use Apache Forrest version forrest-0.9-d
         </antcall>
     </target>
     
+    
     <target name="download-tika">
         <mkdir dir="lib"/>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/tika"/>
-            <param name="artifact-version" value="1.6"/>
+            <param name="artifact-version" value="${tika.version}"/>
             <param name="artifact-name" value="tika-core"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/tika"/>
-            <param name="artifact-version" value="1.6"/>
+            <param name="artifact-version" value="${tika.version}"/>
             <param name="artifact-name" value="tika-parsers"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/ccil/cowan/tagsoup"/>
-            <param name="artifact-version" value="1.2.1"/>
+            <param name="artifact-version" value="${tagsoup.version}"/>
             <param name="artifact-name" value="tagsoup"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/james"/>
             <param name="artifact-name" value="apache-mime4j-core"/>
-            <param name="artifact-version" value="0.7.2"/>
+            <param name="artifact-version" value="${james.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/james"/>
             <param name="artifact-name" value="apache-mime4j-dom"/>
-            <param name="artifact-version" value="0.7.2"/>
+            <param name="artifact-version" value="${james.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/gagravarr"/>
             <param name="artifact-name" value="vorbis-java-tika"/>
-            <param name="artifact-version" value="0.6"/>
+            <param name="artifact-version" value="${vorbis.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/poi"/>
             <param name="artifact-name" value="poi-scratchpad"/>
-            <param name="artifact-version" value="3.11-beta2"/>
+            <param name="artifact-version" value="${poi.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="com/drewnoakes"/>
             <param name="artifact-name" value="metadata-extractor"/>
-            <param name="artifact-version" value="2.6.2"/>
+            <param name="artifact-version" value="${metadata-extractor.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/aspectj"/>
             <param name="artifact-name" value="aspectjrt"/>
-            <param name="artifact-version" value="1.8.0"/>
+            <param name="artifact-version" value="${aspectjrt.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="com/uwyn"/>
             <param name="artifact-name" value="jhighlight"/>
-            <param name="artifact-version" value="1.0"/>
+            <param name="artifact-version" value="${jhighlight.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/xmlbeans"/>
             <param name="artifact-name" value="xmlbeans"/>
-            <param name="artifact-version" value="2.6.0"/>
+            <param name="artifact-version" value="${xmlbeans.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/bouncycastle"/>
             <param name="artifact-name" value="bcprov-jdk15"/>
-            <param name="artifact-version" value="1.45"/>
+            <param name="artifact-version" value="${bc.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/tukaani"/>
             <param name="artifact-name" value="xz"/>
-            <param name="artifact-version" value="1.5"/>
+            <param name="artifact-version" value="${tukaani.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/pdfbox"/>
             <param name="artifact-name" value="jempbox"/>
-            <param name="artifact-version" value="1.8.4"/>
+            <param name="artifact-version" value="${pdfbox.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/pdfbox"/>
             <param name="artifact-name" value="pdfbox"/>
-            <param name="artifact-version" value="1.8.6"/>
+            <param name="artifact-version" value="${pdfbox.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/pdfbox"/>
             <param name="artifact-name" value="fontbox"/>
-            <param name="artifact-version" value="1.8.6"/>
+            <param name="artifact-version" value="${pdfbox.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/commons"/>
             <param name="artifact-name" value="commons-compress"/>
-            <param name="artifact-version" value="1.8.1"/>
+            <param name="artifact-version" value="${commons-compress.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="com/googlecode/juniversalchardet"/>
             <param name="artifact-name" value="juniversalchardet"/>
-            <param name="artifact-version" value="1.0.3"/>
+            <param name="artifact-version" value="${juniversalchardet.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
-        <antcall target="download-via-maven"><param name="target" value="lib"/>
+        <!-- netcdf is a dependency of tika, but is lgpl, so we don't download it anymore
+        antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="edu/ucar"/>
             <param name="artifact-name" value="netcdf"/>
-            <param name="artifact-version" value="4.2.20"/>
+            <param name="artifact-version" value="${netcdf.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
+            <param name="project-path" value="commons-httpclient"/>
+            <param name="artifact-name" value="commons-httpclient"/>
+            <param name="artifact-version" value="${commons-httpclient.version}"/>
+            <param name="artifact-type" value="jar"/>
+        </antcall>
+        <antcall target="download-via-maven"><param name="target" value="lib"/>
+            <param name="project-path" value="edu/ucar"/>
+            <param name="artifact-name" value="unidataCommon"/>
+            <param name="artifact-version" value="${netcdf.version}"/>
+            <param name="artifact-type" value="jar"/>
+        </antcall -->
+        <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="de/l3s/boilerpipe"/>
             <param name="artifact-name" value="boilerpipe"/>
-            <param name="artifact-version" value="1.1.0"/>
+            <param name="artifact-version" value="${boilerpipe.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="dom4j"/>
             <param name="artifact-name" value="dom4j"/>
-            <param name="artifact-version" value="1.6.1"/>
+            <param name="artifact-version" value="${dom4j.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/ow2/asm"/>
             <param name="artifact-name" value="asm-debug-all"/>
-            <param name="artifact-version" value="4.1"/>
+            <param name="artifact-version" value="${asm.version}"/>
+            <param name="artifact-type" value="jar"/>
+        </antcall>
+        <antcall target="download-via-maven"><param name="target" value="lib"/>
+            <param name="project-path" value="org/ow2/asm"/>
+            <param name="artifact-name" value="asm-analysis"/>
+            <param name="artifact-version" value="${asm.version}"/>
+            <param name="artifact-type" value="jar"/>
+        </antcall>
+        <antcall target="download-via-maven"><param name="target" value="lib"/>
+            <param name="project-path" value="org/ow2/asm"/>
+            <param name="artifact-name" value="asm-commons"/>
+            <param name="artifact-version" value="${asm.version}"/>
+            <param name="artifact-type" value="jar"/>
+        </antcall>
+        <antcall target="download-via-maven"><param name="target" value="lib"/>
+            <param name="project-path" value="org/ow2/asm"/>
+            <param name="artifact-name" value="asm"/>
+            <param name="artifact-version" value="${asm.version}"/>
+            <param name="artifact-type" value="jar"/>
+        </antcall>
+        <antcall target="download-via-maven"><param name="target" value="lib"/>
+            <param name="project-path" value="org/ow2/asm"/>
+            <param name="artifact-name" value="asm-tree"/>
+            <param name="artifact-version" value="${asm.version}"/>
+            <param name="artifact-type" value="jar"/>
+        </antcall>
+        <antcall target="download-via-maven"><param name="target" value="lib"/>
+            <param name="project-path" value="org/ow2/asm"/>
+            <param name="artifact-name" value="asm-util"/>
+            <param name="artifact-version" value="${asm.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="com/adobe/xmp"/>
             <param name="artifact-name" value="xmpcore"/>
-            <param name="artifact-version" value="5.1.2"/>
+            <param name="artifact-version" value="${xmpcore.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/gagravarr"/>
             <param name="artifact-name" value="vorbis-java-core"/>
-            <param name="artifact-version" value="0.6"/>
+            <param name="artifact-version" value="${vorbis.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/poi"/>
             <param name="artifact-name" value="poi-ooxml"/>
-            <param name="artifact-version" value="3.11-beta2"/>
+            <param name="artifact-version" value="${poi.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/apache/poi"/>
             <param name="artifact-name" value="poi-ooxml-schemas"/>
-            <param name="artifact-version" value="3.11-beta2"/>
+            <param name="artifact-version" value="${poi.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="org/bouncycastle"/>
             <param name="artifact-name" value="bcmail-jdk15"/>
-            <param name="artifact-version" value="1.45"/>
+            <param name="artifact-version" value="${bc.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="jdom"/>
             <param name="artifact-name" value="jdom"/>
-            <param name="artifact-version" value="1.0"/>
+            <param name="artifact-version" value="${jdom.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="rome"/>
             <param name="artifact-name" value="rome"/>
-            <param name="artifact-version" value="1.0"/>
+            <param name="artifact-version" value="${rome.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="com/googlecode/mp4parser"/>
             <param name="artifact-name" value="isoparser"/>
-            <param name="artifact-version" value="1.0.2"/>
+            <param name="artifact-version" value="${mp4parser.version}"/>
+            <param name="artifact-type" value="jar"/>
+        </antcall>
+        <antcall target="download-via-maven"><param name="target" value="lib"/>
+            <param name="project-path" value="net/sourceforge/jmatio"/>
+            <param name="artifact-name" value="jmatio"/>
+            <param name="artifact-version" value="${jmatio.version}"/>
+            <param name="artifact-type" value="jar"/>
+        </antcall>
+        <antcall target="download-via-maven"><param name="target" value="lib"/>
+            <param name="project-path" value="com/pff"/>
+            <param name="artifact-name" value="java-libpst"/>
+            <param name="artifact-version" value="${java-libpst.version}"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
     </target>
-	
+    
     <target name="download-jackson">
         <mkdir dir="lib"/>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="com/fasterxml/jackson/core"/>
-            <param name="artifact-version" value="2.1.3"/>
+            <param name="artifact-version" value="${jackson-databind.version}"/>
             <param name="artifact-name" value="jackson-databind"/>
             <param name="artifact-type" value="jar"/>
         </antcall>
         <antcall target="download-via-maven"><param name="target" value="lib"/>
             <param name="project-path" value="com/fasterxml/jackson/core"/>
-            <param name="artifact-version" value="2.1.2"/>
+            <param name="artifact-version" value="${jackson-annotations.version}"/>
             <param name="artifact-name" value="jackson-annotations"/>
             <param name="artifact-type" value="jar"/>
         </antcall>

Modified: manifoldcf/trunk/connectors/tika/build.xml
URL: http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/tika/build.xml?rev=1629541&r1=1629540&r2=1629541&view=diff
==============================================================================
--- manifoldcf/trunk/connectors/tika/build.xml (original)
+++ manifoldcf/trunk/connectors/tika/build.xml Sun Oct  5 21:13:09 2014
@@ -41,9 +41,10 @@
             <include name="tika-parsers*.jar"/>
             <include name="tagsoup*.jar"/>
             <include name="poi*.jar"/>
-            <include name="vorbis-java-tika*.jar"/>
-            <include name="vorbis-java-core*.jar"/>
+            <include name="vorbis-java*.jar"/>
             <include name="netcdf*.jar"/>
+            <include name="unidataCommon*.jar"/>
+            <include name="commons-httpclient*.jar"/>
             <include name="apache-mime4j-core*.jar"/>
             <include name="apache-mime4j-dom*.jar"/>
             <include name="commons-compress*.jar"/>
@@ -60,7 +61,7 @@
             <include name="xmlbeans*.jar"/>
             <include name="dom4j*.jar"/>
             <include name="geronimo-stax-api_1.0_spec*.jar"/>
-            <include name="asm-debug-all*.jar"/>
+            <include name="asm*.jar"/>
             <include name="isoparser*.jar"/>
             <include name="aspectjrt*.jar"/>
             <include name="metadata-extractor*.jar"/>
@@ -73,6 +74,8 @@
             <include name="vorbis-java-core*.jar"/>
             <include name="juniversalchardet*.jar"/>
             <include name="jhighlight*.jar"/>
+            <include name="jmatio*.jar"/>
+            <include name="java-libpst*.jar"/>
         </fileset>
     </path>
 
@@ -88,9 +91,10 @@
                 <include name="tika-parsers*.jar"/>
                 <include name="tagsoup*.jar"/>
                 <include name="poi*.jar"/>
-                <include name="vorbis-java-tika*.jar"/>
-                <include name="vorbis-java-core*.jar"/>
+                <include name="vorbis-java*.jar"/>
                 <include name="netcdf*.jar"/>
+                <include name="unidataCommon*.jar"/>
+                <include name="commons-httpclient*.jar"/>
                 <include name="apache-mime4j-core*.jar"/>
                 <include name="apache-mime4j-dom*.jar"/>
                 <include name="commons-compress*.jar"/>
@@ -107,7 +111,7 @@
                 <include name="xmlbeans*.jar"/>
                 <include name="dom4j*.jar"/>
                 <include name="geronimo-stax-api_1.0_spec*.jar"/>
-                <include name="asm-debug-all*.jar"/>
+                <include name="asm*.jar"/>
                 <include name="isoparser*.jar"/>
                 <include name="aspectjrt*.jar"/>
                 <include name="metadata-extractor*.jar"/>
@@ -120,6 +124,8 @@
                 <include name="vorbis-java-core*.jar"/>
                 <include name="juniversalchardet*.jar"/>
                 <include name="jhighlight*.jar"/>
+                <include name="jmatio*.jar"/>
+                <include name="java-libpst*.jar"/>
             </fileset>
         </copy>
     </target>

Modified: manifoldcf/trunk/connectors/tika/pom.xml
URL: http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/tika/pom.xml?rev=1629541&r1=1629540&r2=1629541&view=diff
==============================================================================
--- manifoldcf/trunk/connectors/tika/pom.xml (original)
+++ manifoldcf/trunk/connectors/tika/pom.xml Sun Oct  5 21:13:09 2014
@@ -221,33 +221,6 @@
 	  <artifactId>tika-parsers</artifactId>
 	  <version>1.6</version>
     </dependency>
-    <!-- Override tika dependencies, to make sure we fix various
-      CVE's -->
-    <dependency>
-	  <groupId>org.apache.xmlbeans</groupId>
-	  <artifactId>xmlbeans</artifactId>
-	  <version>${xmlbeans.version}</version>
-    </dependency>
-    <dependency>
-	  <groupId>org.apache.poi</groupId>
-	  <artifactId>poi</artifactId>
-	  <version>${poi.version}</version>
-    </dependency>
-    <dependency>
-	  <groupId>org.apache.poi</groupId>
-	  <artifactId>poi-ooxml</artifactId>
-	  <version>${poi.version}</version>
-    </dependency>
-    <dependency>
-	  <groupId>org.apache.poi</groupId>
-	  <artifactId>poi-ooxml-schemas</artifactId>
-	  <version>${poi.version}</version>
-    </dependency>
-    <dependency>
-	  <groupId>org.apache.poi</groupId>
-	  <artifactId>poi-scratchpad</artifactId>
-	  <version>${poi.version}</version>
-    </dependency>
     
     <!-- Testing dependencies -->