Upgrade tools (#386)

* upgrade tika, jhove, exiftool, and mediainfo * jhove 1.28 * MediaInfo 23.07
harvard-lts · Jul 18, 2023 · 6bd135e · 6bd135e
1 parent 4b94881
commit 6bd135e
Show file tree

Hide file tree

Showing 12 changed files with 40 additions and 35 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,10 @@
 ## Unreleased (TBD)
-- ?
+
+- Tool upgrades
+  - ExifTool 12.60
+  - Jhove 1.28.0
+  - MediaInfo 23.07
+  - Tika 2.8.0
 
 ## Version 1.6.0 (1/16/2023)
 

diff --git a/pom.xml b/pom.xml
@@ -41,11 +41,11 @@
         <embarc.version>0.2</embarc.version>
 
         <!-- Tool properties -->
-        <tika.version>2.6.0</tika.version>
+        <tika.version>2.8.0</tika.version>
         <tika.dir>lib/tika</tika.dir>
         <droid.version>6.5.2</droid.version>
         <droid.dir>lib/droid</droid.dir>
-        <jhove.version>1.26.1</jhove.version>
+        <jhove.version>1.28.0</jhove.version>
         <jhove.dir>lib/jhove</jhove.dir>
     </properties>
 

diff --git a/src/main/java/edu/harvard/hul/ois/fits/tools/tika/TikaTool.java b/src/main/java/edu/harvard/hul/ois/fits/tools/tika/TikaTool.java
@@ -201,7 +201,7 @@ private enum TikaProperty {
 
     private static final Namespace fitsNS = Namespace.getNamespace(Fits.XML_NAMESPACE);
     private static final String TOOL_NAME = "Tika";
-    private static final String TOOL_VERSION = "2.6.0"; // Hard-coded version till we can do better
+    private static final String TOOL_VERSION = "2.8.0"; // Hard-coded version till we can do better
 
     private static final MimeTypes mimeTypes = MimeTypes.getDefaultMimeTypes();
     private final Parser tikaParser;

diff --git a/testfiles/output/FITS-SAMPLE-26.mov-default_XmlUnitExpectedOutput.xml b/testfiles/output/FITS-SAMPLE-26.mov-default_XmlUnitExpectedOutput.xml
@@ -26,8 +26,8 @@
       <duration toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">3971</duration>
       <timecodeStart toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">01:58:41:27</timecodeStart>
       <bitRate toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">30341389</bitRate>
-      <dateCreated toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">UTC 2015-03-13 15:36:19</dateCreated>
-      <dateModified toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">UTC 2022-10-30 15:39:47</dateModified>
+      <dateCreated toolname="MediaInfo" toolversion="23.04" status="SINGLE_RESULT">2015-03-13 15:36:19 UTC</dateCreated>
+      <dateModified toolname="MediaInfo" toolversion="23.04" status="SINGLE_RESULT">2022-10-23 21:57:52 UTC</dateModified>
       <track type="video" id="1" toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">
         <videoDataEncoding>AVdv</videoDataEncoding>
         <codecId>AVdv</codecId>

diff --git a/testfiles/output/FITS-SAMPLE-26.mov_XmlUnitExpectedOutput.xml b/testfiles/output/FITS-SAMPLE-26.mov_XmlUnitExpectedOutput.xml
@@ -26,8 +26,8 @@
       <duration toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">3971</duration>
       <timecodeStart toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">01:58:41:27</timecodeStart>
       <bitRate toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">30341389</bitRate>
-      <dateCreated toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">UTC 2015-03-13 15:36:19</dateCreated>
-      <dateModified toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">UTC 2022-10-30 15:39:47</dateModified>
+      <dateCreated toolname="MediaInfo" toolversion="23.04" status="SINGLE_RESULT">2015-03-13 15:36:19 UTC</dateCreated>
+      <dateModified toolname="MediaInfo" toolversion="23.04" status="SINGLE_RESULT">2022-10-23 21:57:52 UTC</dateModified>
       <track type="video" id="1" toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">
         <videoDataEncoding>AVdv</videoDataEncoding>
         <codecId>AVdv</codecId>
@@ -152,7 +152,7 @@
               <ebucore:mimeType typeLabel="video/quicktime" />
               <ebucore:locator>/fits/testfiles/input/FITS-SAMPLE-26.mov</ebucore:locator>
               <ebucore:technicalAttributeString typeLabel="overallBitRate">30341389</ebucore:technicalAttributeString>
-              <ebucore:dateModified startTime="15:39:47Z" startDate="2022-10-30" />
+              <ebucore:dateModified startTime="21:57:52Z" startDate="2022-10-23" />
             </ebucore:format>
           </ebucore:coreMetadata>
         </ebucore:ebuCoreMain>

diff --git a/testfiles/output/FITS-SAMPLE-44_1_1_4_4_4_6_1_1_2_3_1.mp4-default_XmlUnitExpectedOutput.xml b/testfiles/output/FITS-SAMPLE-44_1_1_4_4_4_6_1_1_2_3_1.mp4-default_XmlUnitExpectedOutput.xml
@@ -24,8 +24,8 @@
       <formatProfile toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">Base Media / Version 2</formatProfile>
       <duration toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">4137</duration>
       <bitRate toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">17585272</bitRate>
-      <dateCreated toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">UTC 2015-03-13 19:21:21</dateCreated>
-      <dateModified toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">UTC 2022-10-30 15:39:47</dateModified>
+      <dateCreated toolname="MediaInfo" toolversion="23.04" status="SINGLE_RESULT">2015-03-13 19:21:21 UTC</dateCreated>
+      <dateModified toolname="MediaInfo" toolversion="23.04" status="SINGLE_RESULT">2022-10-23 21:57:52 UTC</dateModified>
       <track type="video" id="1" toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">
         <videoDataEncoding>avc1</videoDataEncoding>
         <codecId>avc1</codecId>

diff --git a/testfiles/output/FITS-SAMPLE-44_1_1_4_4_4_6_1_1_2_3_1.mp4-no-md5_XmlUnitExpectedOutput.xml b/testfiles/output/FITS-SAMPLE-44_1_1_4_4_4_6_1_1_2_3_1.mp4-no-md5_XmlUnitExpectedOutput.xml
@@ -23,8 +23,8 @@
       <formatProfile toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">Base Media / Version 2</formatProfile>
       <duration toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">4137</duration>
       <bitRate toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">17585272</bitRate>
-      <dateCreated toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">UTC 2015-03-13 19:21:21</dateCreated>
-      <dateModified toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">UTC 2023-01-10 13:43:06</dateModified>
+      <dateCreated toolname="MediaInfo" toolversion="23.04" status="SINGLE_RESULT">2015-03-13 19:21:21 UTC</dateCreated>
+      <dateModified toolname="MediaInfo" toolversion="23.04" status="SINGLE_RESULT">2022-10-23 21:57:52 UTC</dateModified>
       <track type="video" id="1" toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">
         <videoDataEncoding>avc1</videoDataEncoding>
         <codecId>avc1</codecId>

diff --git a/testfiles/output/ICFA.KC.BIA.1524-small.jpg_XmlUnitExpectedOutput.xml b/testfiles/output/ICFA.KC.BIA.1524-small.jpg_XmlUnitExpectedOutput.xml
@@ -40,7 +40,7 @@
       <colorSpace toolname="Exiftool" toolversion="12.50" status="CONFLICT">RGB</colorSpace>
       <iccProfileName toolname="Jhove" toolversion="1.26.1">Adobe RGB (1998)</iccProfileName>
       <YCbCrSubSampling toolname="Exiftool" toolversion="12.50" status="SINGLE_RESULT">1 1</YCbCrSubSampling>
-      <orientation toolname="Exiftool" toolversion="12.50" status="SINGLE_RESULT">normal*</orientation>
+      <orientation toolname="Jhove" toolversion="1.26.1">normal*</orientation>
       <samplingFrequencyUnit toolname="Jhove" toolversion="1.26.1">in.</samplingFrequencyUnit>
       <xSamplingFrequency toolname="Jhove" toolversion="1.26.1">350</xSamplingFrequency>
       <ySamplingFrequency toolname="Jhove" toolversion="1.26.1">350</ySamplingFrequency>

diff --git a/testfiles/output/JPEGTest_20170591--JPEGTest_20170591.jpeg_XmlUnitExpectedOutput.xml b/testfiles/output/JPEGTest_20170591--JPEGTest_20170591.jpeg_XmlUnitExpectedOutput.xml
@@ -35,7 +35,7 @@
       <iccProfileName toolname="Jhove" toolversion="1.26.1">sRGB IEC61966-2.1</iccProfileName>
       <YCbCrSubSampling toolname="Exiftool" toolversion="12.50" status="SINGLE_RESULT">1 1</YCbCrSubSampling>
       <YCbCrPositioning toolname="Exiftool" toolversion="12.50" status="SINGLE_RESULT">1</YCbCrPositioning>
-      <orientation toolname="Exiftool" toolversion="12.50" status="SINGLE_RESULT">normal*</orientation>
+      <orientation toolname="Jhove" toolversion="1.26.1">normal*</orientation>
       <samplingFrequencyUnit toolname="Jhove" toolversion="1.26.1">in.</samplingFrequencyUnit>
       <xSamplingFrequency toolname="Jhove" toolversion="1.26.1">72</xSamplingFrequency>
       <ySamplingFrequency toolname="Jhove" toolversion="1.26.1">72</ySamplingFrequency>

diff --git a/testfiles/output/aletrek-rle.mov_XmlUnitExpectedOutput.xml b/testfiles/output/aletrek-rle.mov_XmlUnitExpectedOutput.xml
@@ -23,8 +23,8 @@
       <format toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">QuickTime</format>
       <duration toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">3333</duration>
       <bitRate toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">567338</bitRate>
-      <dateCreated toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">UTC 2002-10-18 17:15:11</dateCreated>
-      <dateModified toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">UTC 2022-11-05 19:13:39</dateModified>
+      <dateCreated toolname="MediaInfo" toolversion="23.04" status="SINGLE_RESULT">2002-10-18 17:15:11 UTC</dateCreated>
+      <dateModified toolname="MediaInfo" toolversion="23.04" status="SINGLE_RESULT">2022-11-27 22:46:47 UTC</dateModified>
       <track type="video" id="1" toolname="MediaInfo" toolversion="22.09" status="SINGLE_RESULT">
         <videoDataEncoding>rle </videoDataEncoding>
         <codecId>rle </codecId>
@@ -87,7 +87,7 @@
               <ebucore:mimeType typeLabel="video/quicktime" />
               <ebucore:locator>/fits/testfiles/input/aletrek-rle.mov</ebucore:locator>
               <ebucore:technicalAttributeString typeLabel="overallBitRate">567338</ebucore:technicalAttributeString>
-              <ebucore:dateModified startTime="19:13:39Z" startDate="2022-11-05" />
+              <ebucore:dateModified startTime="22:46:47Z" startDate="2022-11-27" />
             </ebucore:format>
           </ebucore:coreMetadata>
         </ebucore:ebuCoreMain>

diff --git a/testfiles/output/gps.jpg_XmlUnitExpectedOutput.xml b/testfiles/output/gps.jpg_XmlUnitExpectedOutput.xml
@@ -36,7 +36,7 @@
       <colorSpace toolname="Jhove" toolversion="1.26.1" status="SINGLE_RESULT">YCbCr</colorSpace>
       <YCbCrSubSampling toolname="Exiftool" toolversion="12.50" status="SINGLE_RESULT">2 2</YCbCrSubSampling>
       <YCbCrPositioning toolname="Exiftool" toolversion="12.50" status="SINGLE_RESULT">2</YCbCrPositioning>
-      <orientation toolname="Exiftool" toolversion="12.50" status="SINGLE_RESULT">normal*</orientation>
+      <orientation toolname="Jhove" toolversion="1.26.1">normal*</orientation>
       <samplingFrequencyUnit toolname="Jhove" toolversion="1.26.1">in.</samplingFrequencyUnit>
       <xSamplingFrequency toolname="Exiftool" toolversion="12.50">72</xSamplingFrequency>
       <ySamplingFrequency toolname="Exiftool" toolversion="12.50">72</ySamplingFrequency>

diff --git a/tools.properties b/tools.properties
@@ -1,25 +1,25 @@
 # exiftool
 # When upgrading exiftool, be sure to select a *production release* version (https://www.exiftool.org/history.html).
 # None production releases are not available for download long-term.
-exiftool.version=12.50
-exiftool.unix.url=https://exiftool.org/Image-ExifTool-12.50.tar.gz
-exiftool.unix.md5=75dd9d375c1c4798a082dda79eaf6ba7
-exiftool.windows.url=https://exiftool.org/exiftool-12.50.zip
-exiftool.windows.md5=c5cc07cd015c9e029786894243ace2e9
+exiftool.version=12.60
+exiftool.unix.url=https://exiftool.org/Image-ExifTool-12.60.tar.gz
+exiftool.unix.md5=ab1b5d756aaa8188890afa5a16563f57
+exiftool.windows.url=https://exiftool.org/exiftool-12.60.zip
+exiftool.windows.md5=a020948fd8d1a8c891266bebee65792a
 
 # MediaInfo
 # https://mediaarea.net/en/MediaInfo/Download
-mediainfo.version=22.09
-mediainfo.linux.url=https://mediaarea.net/download/binary/libmediainfo0/22.09/libmediainfo0v5_22.09-1_amd64.xUbuntu_22.04.deb
-mediainfo.linux.md5=6a0929e0223008f6648f6596ac5730de
-mediainfo.linux.zen.url=https://mediaarea.net/download/binary/libzen0/0.4.39/libzen0v5_0.4.39-1_amd64.xUbuntu_22.04.deb
-mediainfo.linux.zen.md5=6cc1229b89370b3cc91b6d77e93c682e
-mediainfo.linux.source.url=https://mediaarea.net/download/binary/libmediainfo0/22.09/MediaInfo_DLL_22.09_GNU_FromSource.tar.gz
-mediainfo.linux.source.md5=632f1e258b9caca5bceb184c597fc243
-mediainfo.mac.url=https://mediaarea.net/download/binary/libmediainfo0/22.09/MediaInfo_DLL_22.09_Mac_x86_64+arm64.tar.bz2
-mediainfo.mac.md5=fb0722f85eb8c1cd97ffcd89af8b9232
-mediainfo.windows.url=https://mediaarea.net/download/binary/libmediainfo0/22.09/MediaInfo_DLL_22.09_Windows_x64_WithoutInstaller.zip
-mediainfo.windows.md5=cb62db87fb4d8ecd312a33130fcdf8b0
+mediainfo.version=23.07
+mediainfo.linux.url=https://mediaarea.net/download/binary/libmediainfo0/23.07/libmediainfo0v5_23.07-1_amd64.Ubuntu_23.04.deb
+mediainfo.linux.md5=1c37765affba25d2eba540e81f014ab8
+mediainfo.linux.zen.url=https://mediaarea.net/download/binary/libzen0/0.4.41/libzen0v5_0.4.41-1_amd64.Ubuntu_23.04.deb
+mediainfo.linux.zen.md5=79ec9ca86e939e70dcc6969cdc3072fe
+mediainfo.linux.source.url=https://mediaarea.net/download/binary/libmediainfo0/23.07/MediaInfo_DLL_23.07_GNU_FromSource.tar.gz
+mediainfo.linux.source.md5=29ca097a662768d1bb11262accc232ef
+mediainfo.mac.url=https://mediaarea.net/download/binary/libmediainfo0/23.07/MediaInfo_DLL_23.07_Mac_x86_64+arm64.tar.bz2
+mediainfo.mac.md5=62e5404ada8386135b61d89eb092162a
+mediainfo.windows.url=https://mediaarea.net/download/binary/libmediainfo0/23.07/MediaInfo_DLL_23.07_Windows_x64_WithoutInstaller.zip
+mediainfo.windows.md5=693718e588e2a323f4e7fe28b0477ca7
 
 # Windows file util
 # https://gnuwin32.sourceforge.net/packages/file.htm