Changeset 34206

Timestamp:

2020-06-18T19:22:34+12:00 (4 years ago)

Author:

ak19

Message:

UnknownConverterPlugin configured to use Tika for doc processing

Location:

main/trunk/model-sites-dev/opotiki/collect

Files:

• imagesco/etc/oai-inf.jdb (modified) ( previous)
• imagesco/etc/oai-inf.jdb.bak (modified) ( previous)
• textdemo/etc/collectionConfig.xml (modified) (1 diff)
• textdemo/etc/oai-inf.jdb (modified) ( previous)
• textdemo/etc/oai-inf.jdb.bak (modified) ( previous)
• waiatade/etc/collectionConfig.xml (modified) (2 diffs)
• waiatade/etc/fail.log (modified) (1 diff)
• waiatade/etc/oai-inf.jdb (modified) ( previous)
• waiatade/etc/oai-inf.jdb.bak (modified) ( previous)

main/trunk/model-sites-dev/opotiki/collect/textdemo/etc/collectionConfig.xml

@@ -107 +107 @@
             <plugin name="PDFv2Plugin">
                 <option name="-convert_to" value="paged_pretty_html"/>
+            </plugin>
+            <!-- Configuring an UnknownConverterPlugin for docx processing with Tika -->
+            <plugin name="UnknownConverterPlugin">
+              <option name="-exec_cmd" value="java -jar $GSDLHOME/ext/tika/tika-app-1.24.1.jar --html %%INPUT_FILE &gt; %%OUTPUT"/>
+              <option name="-convert_to" value="html"/>
+              <option name="-mime_type" value="application/vnd.openxmlformats-officedocument.wordprocessingml.document"/>
+              <option name="-srcicon" value="icondocx"/>
+              <option name="-process_extension" value="docx"/>
             </plugin>
             <plugin name="RTFPlugin"/>

main/trunk/model-sites-dev/opotiki/collect/waiatade/etc/collectionConfig.xml

@@ -14 +14 @@
         <displayItem assigned="true" lang="en" name="description">A Collection of Waiata.
 Songs (waiata) are sung solo, in unison or at the octave. 
-Types of song include lullabies (oriori), love songs (waitata aroha) and laments (waiata tangi). 
+Types of song include lullabies (oriori), love songs (waiata aroha) and laments (waiata tangi). 
 Traditionally all formal speeches are followed by a waiata sung by the speaker and their group of supporters. 
 Some of the smaller wind instruments are also sung into, and the sound of the poi (raupo ball swung on the end of a flax cord) provides a rhythmic accompaniment to waiata poi.</displayItem>
@@ -93 +93 @@
                 <option name="-convert_to" value="paged_pretty_html"/>
             </plugin>
+            <!-- Configuring an UnknownConverterPlugin for docx processing with Tika -->
+            <plugin name="UnknownConverterPlugin">
+              <option name="-exec_cmd" value="java -jar $GSDLHOME/ext/tika/tika-app-1.24.1.jar --html %%INPUT_FILE &gt; %%OUTPUT"/>
+              <option name="-convert_to" value="html"/>
+              <option name="-mime_type" value="application/vnd.openxmlformats-officedocument.wordprocessingml.document"/>
+              <option name="-srcicon" value="icondocx"/>
+              <option name="-process_extension" value="docx"/>
+            </plugin>           
             <plugin name="RTFPlugin"/>
             <plugin name="WordPlugin"/>

main/trunk/model-sites-dev/opotiki/collect/waiatade/etc/fail.log

@@ -1 @@
-Tera te po pango.docx: WordPlugin failed to convert to html
-06\Tera te po pango.docx: no plugin could process this file
+06/Tera te po pango.docx: no plugin could recognise this file