TIKA-4831: Add content-based detection and a parser for GeoGebra files (ggb, ggs, ggt)

CHANGES.txt

@@ -227,6 +227,21 @@ Release 4.1.0 - unreleased
      recursion/allocation; malformed files fall back to the legacy string dump
      (TIKA-4814).
 
+   * New GeoGebraParser for *.ggb/*.ggs/*.ggt: geogebra:* metadata, text and
+     the thumbnail as a THUMBNAIL embedded document, with content-based
+     detection. Previously typed application/zip with every entry as an
+     attachment. *.ggs and *.ggp are new mime types; *.ggp is glob-only
+     (TIKA-4831).
+
+   * RawTiffParser extracts the camera-generated JPEG previews embedded in
+     TIFF-based raw images (Nikon NEF/NRW, Sony ARW/SRF/SR2, Pentax PEF/PTX,
+     Adobe DNG and Canon CR2, including BigTIFF DNG containers) as thumbnail
+     embedded documents. image/x-raw-{nikon,sony,pentax,adobe} are now
+     sub-classes of image/tiff, so a named NEF/ARW/PEF/DNG that used to detect
+     as image/tiff (TiffParser, metadata only) now detects as image/x-raw-* and
+     emits thumbnail-N.jpg attachments in /rmeta and /unpack; CR2 keeps its
+     detection but also gains the attachments. Disable via
+     "raw-tiff-parser": {"extractPreviews": false} (TIKA-4824).
    * RawTiffParser extracts embedded JPEG previews from NEF/NRW, ARW/SRF/SR2,
      PEF/PTX, DNG and CR2 as thumbnail embedded documents. image/x-raw-* are
      now subtypes of image/tiff, so named raw files detect as image/x-raw-*.

tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml

@@ -1591,10 +1591,24 @@
     <glob pattern="*.txd"/>
   </mime-type>
   <mime-type type="application/vnd.geogebra.file">
+    <_comment>GeoGebra Worksheet</_comment>
     <glob pattern="*.ggb"/>
+    <sub-class-of type="application/zip"/>
+  </mime-type>
+  <mime-type type="application/vnd.geogebra.pinboard">
+    <_comment>GeoGebra Pinboard</_comment>
+    <glob pattern="*.ggp"/>
+    <sub-class-of type="application/json"/>
+  </mime-type>
+  <mime-type type="application/vnd.geogebra.slides">
+    <_comment>GeoGebra Notes/Slides</_comment>
+    <glob pattern="*.ggs"/>
+    <sub-class-of type="application/zip"/>
   </mime-type>
   <mime-type type="application/vnd.geogebra.tool">
+    <_comment>GeoGebra Tool</_comment>
     <glob pattern="*.ggt"/>
+    <sub-class-of type="application/zip"/>
   </mime-type>
   <mime-type type="application/vnd.geometry-explorer">
     <glob pattern="*.gex"/>

tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java

@@ -239,6 +239,8 @@ public void testHttpServerFileExtensions() {
         assertEquals("application/vnd.fuzzysheet", tika.detect("x.fzs"));
         assertEquals("application/vnd.genomatix.tuxedo", tika.detect("x.txd"));
         assertEquals("application/vnd.geogebra.file", tika.detect("x.ggb"));
+        assertEquals("application/vnd.geogebra.pinboard", tika.detect("x.ggp"));
+        assertEquals("application/vnd.geogebra.slides", tika.detect("x.ggs"));
         assertEquals("application/vnd.geogebra.tool", tika.detect("x.ggt"));
         assertEquals("application/vnd.geometry-explorer", tika.detect("x.gex"));
         assertEquals("application/vnd.geometry-explorer", tika.detect("x.gre"));

tika-metadata-schema/src/main/resources/org/apache/tika/metadata/metadata-key-fields.json

@@ -735,6 +735,12 @@
   {"class":"org.apache.tika.parser.gdal.GDALParser","field":"SIZE","key":"gdal:size"},
   {"class":"org.apache.tika.parser.gdal.GDALParser","field":"UPPER_LEFT","key":"gdal:upper-left"},
   {"class":"org.apache.tika.parser.gdal.GDALParser","field":"UPPER_RIGHT","key":"gdal:upper-right"},
+  {"class":"org.apache.tika.parser.geogebra.GeoGebraParser","field":"APP_NAME","key":"geogebra:app-name"},
+  {"class":"org.apache.tika.parser.geogebra.GeoGebraParser","field":"APP_VERSION","key":"geogebra:app-version"},
+  {"class":"org.apache.tika.parser.geogebra.GeoGebraParser","field":"DATE","key":"geogebra:date"},
+  {"class":"org.apache.tika.parser.geogebra.GeoGebraParser","field":"FORMAT_VERSION","key":"geogebra:format-version"},
+  {"class":"org.apache.tika.parser.geogebra.GeoGebraParser","field":"ID","key":"geogebra:id"},
+  {"class":"org.apache.tika.parser.geogebra.GeoGebraParser","field":"TOOL_NAME","key":"geogebra:toolName"},
   {"class":"org.apache.tika.parser.hdf.HDFParser","field":"FILE_TYPE_DESCRIPTION","key":"hdf:file-type-description"},
   {"class":"org.apache.tika.parser.iwork.KeynoteContentHandler","field":"PRESENTATION_HEIGHT","key":"keynote:slides-height"},
   {"class":"org.apache.tika.parser.iwork.KeynoteContentHandler","field":"PRESENTATION_WIDTH","key":"keynote:slides-width"},

tika-metadata-schema/src/main/resources/org/apache/tika/metadata/metadata-keys.json

@@ -192,6 +192,12 @@
   {"key":"geo:lat","namespace":"geo","valueType":"REAL","cardinality":"SIMPLE","module":"tika-core"},
   {"key":"geo:long","namespace":"geo","valueType":"REAL","cardinality":"SIMPLE","module":"tika-core"},
   {"key":"geo:timestamp","namespace":"geo","valueType":"DATE","cardinality":"SIMPLE","module":"tika-core"},
+  {"key":"geogebra:app-name","namespace":"geogebra","valueType":"TEXT","cardinality":"SIMPLE","module":"tika-parser-miscoffice-module"},
+  {"key":"geogebra:app-version","namespace":"geogebra","valueType":"TEXT","cardinality":"SIMPLE","module":"tika-parser-miscoffice-module"},
+  {"key":"geogebra:date","namespace":"geogebra","valueType":"TEXT","cardinality":"SIMPLE","module":"tika-parser-miscoffice-module"},
+  {"key":"geogebra:format-version","namespace":"geogebra","valueType":"TEXT","cardinality":"SIMPLE","module":"tika-parser-miscoffice-module"},
+  {"key":"geogebra:id","namespace":"geogebra","valueType":"TEXT","cardinality":"SIMPLE","module":"tika-parser-miscoffice-module"},
+  {"key":"geogebra:toolName","namespace":"geogebra","valueType":"TEXT","cardinality":"BAG","module":"tika-parser-miscoffice-module"},
   {"key":"geotopic:latitude","namespace":"geotopic","valueType":"TEXT","cardinality":"SIMPLE","module":""},
   {"key":"geotopic:longitude","namespace":"geotopic","valueType":"TEXT","cardinality":"SIMPLE","module":""},
   {"key":"geotopic:name","namespace":"geotopic","valueType":"TEXT","cardinality":"SIMPLE","module":""},

tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/java/org/apache/tika/detect/TestContainerAwareDetector.java

@@ -454,6 +454,12 @@ public void testDetectKMZ() throws Exception {
         assertTypeByData("testKMZ.kmz", "application/vnd.google-earth.kmz");
     }
 
+    @Test
+    public void testDetectGeoGebra() throws Exception {
+        assertTypeByData("testGeoGebra_classic.ggb", "application/vnd.geogebra.file");
+        assertTypeByData("testGeoGebra_notes.ggs", "application/vnd.geogebra.slides");
+    }
+
     @Test
     public void testDetectIPA() throws Exception {
         assertTypeByNameAndData("testIPA.ipa", "application/x-itunes-ipa");

tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/pom.xml

@@ -89,6 +89,11 @@
       <artifactId>tika-parser-xmp-commons</artifactId>
       <version>${project.version}</version>
     </dependency>
+    <!-- for the GeoGebra structure.json and inline text content -->
+    <dependency>
+      <groupId>com.fasterxml.jackson.core</groupId>
+      <artifactId>jackson-databind</artifactId>
+    </dependency>
   </dependencies>
 
   <build>