Updating tika to 2.9.3 (#127353)

This commit is contained in:
Keith Massey 2025-04-25 08:43:26 -05:00 committed by GitHub
parent 6dfb824868
commit 3f736a7826
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 110 additions and 90 deletions

View file

@ -0,0 +1,5 @@
pr: 127353
summary: Updating tika to 2.9.3
area: Ingest Node
type: upgrade
issues: []

View file

@ -1261,6 +1261,11 @@
<sha256 value="f700de80ac270d0344fdea7468201d8b9c805e5c648331c3619f2ee067ccfc59" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="commons-codec" name="commons-codec" version="1.18.0">
<artifact name="commons-codec-1.18.0.jar">
<sha256 value="ba005f304cef92a3dede24a38ad5ac9b8afccf0d8f75839d6c1338634cf7f6e4" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="commons-codec" name="commons-codec" version="1.9">
<artifact name="commons-codec-1.9.jar">
<sha256 value="ad19d2601c3abf0b946b5c3a4113e226a8c1e3305e395b90013b78dd94a723ce" origin="Generated by Gradle"/>
@ -1306,6 +1311,11 @@
<sha256 value="4aa4ca48f3dfd30b78220b7881d8cb93eac4093ec94361b6befa9487998a550b" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="commons-io" name="commons-io" version="2.18.0">
<artifact name="commons-io-2.18.0.jar">
<sha256 value="f3ca0f8d63c40e23a56d54101c60d5edee136b42d84bfb85bc7963093109cf8b" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="commons-io" name="commons-io" version="2.2">
<artifact name="commons-io-2.2.jar">
<sha256 value="675f60bd11a82d481736591fe4054c66471fa5463d45616652fd71585792ba87" origin="Generated by Gradle"/>
@ -2058,6 +2068,11 @@
<sha256 value="27bb5d40f37c3bb7205b4a0540247df057715e9f6cbbd97d626ab8b50318bb04" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.commons" name="commons-compress" version="1.27.1">
<artifact name="commons-compress-1.27.1.jar">
<sha256 value="293d80f54b536b74095dcd7ea3cf0a29bbfc3402519281332495f4420d370d16" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.commons" name="commons-compress" version="1.4.1">
<artifact name="commons-compress-1.4.1.jar">
<sha256 value="28a00d80716f073d644b9da76e94b5e8ff94de8e9323f06f558fba653fcf5f86" origin="Generated by Gradle"/>
@ -2083,21 +2098,16 @@
<sha256 value="4ee380259c068d1dbe9e84ab52186f2acd65de067ec09beff731fca1697fdb16" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.commons" name="commons-lang3" version="3.12.0">
<artifact name="commons-lang3-3.12.0.jar">
<sha256 value="d919d904486c037f8d193412da0c92e22a9fa24230b9d67a57855c5c31c7e94e" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.commons" name="commons-lang3" version="3.13.0">
<artifact name="commons-lang3-3.13.0.jar">
<sha256 value="82f528cf718c7a3c2f30fc5bc784e3c6a0a10b17605dadb9e16c82ede11e6064" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.commons" name="commons-lang3" version="3.14.0">
<artifact name="commons-lang3-3.14.0.jar">
<sha256 value="7b96bf3ee68949abb5bc465559ac270e0551596fa34523fddf890ec418dde13c" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.commons" name="commons-lang3" version="3.17.0">
<artifact name="commons-lang3-3.17.0.jar">
<sha256 value="6ee731df5c8e5a2976a1ca023b6bb320ea8d3539fbe64c8a1d5cb765127c33b4" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.commons" name="commons-lang3" version="3.7">
<artifact name="commons-lang3-3.7.jar">
<sha256 value="6e8dc31e046508d9953c96534edf0c2e0bfe6f468966b5b842b3f87e43b6a847" origin="Generated by Gradle"/>
@ -2711,14 +2721,14 @@
<sha256 value="a121f4b14ec525e54e29b9f5db7b93f4a97e088774e81c7143b5198f67d81bec" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.james" name="apache-mime4j-core" version="0.8.11">
<artifact name="apache-mime4j-core-0.8.11.jar">
<sha256 value="62a7853523dff0c382065df82fa280c1bf59bcd9b329180d707b0f6f15ceb903" origin="Generated by Gradle"/>
<component group="org.apache.james" name="apache-mime4j-core" version="0.8.12">
<artifact name="apache-mime4j-core-0.8.12.jar">
<sha256 value="b2180c13b97ade21edb5f52581ade0a6f82b5084bb9ca5bdf83584deb6225a69" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.james" name="apache-mime4j-dom" version="0.8.11">
<artifact name="apache-mime4j-dom-0.8.11.jar">
<sha256 value="80b301f08e21a6de6d941bb98ef1361ad816c057b7aa61c95cf6249e90d87183" origin="Generated by Gradle"/>
<component group="org.apache.james" name="apache-mime4j-dom" version="0.8.12">
<artifact name="apache-mime4j-dom-0.8.12.jar">
<sha256 value="d8de21f9091a0109bdfe68d323f2a5ffb326922f8493f88b1203a04a69198940" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.kerby" name="kerb-admin" version="1.0.1">
@ -3181,9 +3191,9 @@
<sha256 value="39b2dfc8e84380bf7adab657d3d5e1625cb6592a885ebdb854ec5c6f7a3ec88d" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.pdfbox" name="fontbox" version="2.0.31">
<artifact name="fontbox-2.0.31.jar">
<sha256 value="0d36d14d3a43fd7a7d8d84d317ed8201b9d16fcba75b27e54f6f39775348c032" origin="Generated by Gradle"/>
<component group="org.apache.pdfbox" name="fontbox" version="2.0.33">
<artifact name="fontbox-2.0.33.jar">
<sha256 value="95e16863508697a2b4a3a8b8996919cd426b9b01696e10964e42523496854c5b" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.pdfbox" name="jempbox" version="1.8.17">
@ -3191,29 +3201,29 @@
<sha256 value="ded9c81038dd1bbcba18f07e1028d70c9ceaf0b48ac56cea8ab6ec2c255fc1b3" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.pdfbox" name="pdfbox" version="2.0.31">
<artifact name="pdfbox-2.0.31.jar">
<sha256 value="8a8d10b41961e69ffb8b7f6aa8936d34b96a8854aaf47a8cc081f4289120cef3" origin="Generated by Gradle"/>
<component group="org.apache.pdfbox" name="pdfbox" version="2.0.33">
<artifact name="pdfbox-2.0.33.jar">
<sha256 value="34e104a3526925419a3671f8eb3f38565890f0f0106c659f2f8e7ce87b46d490" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.poi" name="poi" version="5.2.5">
<artifact name="poi-5.2.5.jar">
<sha256 value="352e1b44a5777af2df3d7dc408cda9f75f932d0e0125fa1a7d336a13c0a663a7" origin="Generated by Gradle"/>
<component group="org.apache.poi" name="poi" version="5.4.0">
<artifact name="poi-5.4.0.jar">
<sha256 value="ace71e79873059e273036674560b50c3d6b945b7ca168b0d4962ad7650ae1eec" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.poi" name="poi-ooxml" version="5.2.5">
<artifact name="poi-ooxml-5.2.5.jar">
<sha256 value="c6ad01a10cefa1d2a9c1b552bd4293a3eca29b513353f1ec814041d38da9ec5b" origin="Generated by Gradle"/>
<component group="org.apache.poi" name="poi-ooxml" version="5.4.0">
<artifact name="poi-ooxml-5.4.0.jar">
<sha256 value="98693442ed7d44791de4a57962b6c820ae678e0eba9cf854681b62ff62c9611d" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.poi" name="poi-ooxml-lite" version="5.2.5">
<artifact name="poi-ooxml-lite-5.2.5.jar">
<sha256 value="6d4ce6736c422c52e47ffbfa08c784e1b8c188efb69583ac001a0ab16022d774" origin="Generated by Gradle"/>
<component group="org.apache.poi" name="poi-ooxml-lite" version="5.4.0">
<artifact name="poi-ooxml-lite-5.4.0.jar">
<sha256 value="bb5a8a6c833279ced51afb6042aa15ae5d5ca312ee682e570e23917b522b079e" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.poi" name="poi-scratchpad" version="5.2.5">
<artifact name="poi-scratchpad-5.2.5.jar">
<sha256 value="233b279830c8c68ce57b3202164d5bcee53850a770883c4674cfb8d3dd52fc56" origin="Generated by Gradle"/>
<component group="org.apache.poi" name="poi-scratchpad" version="5.4.0">
<artifact name="poi-scratchpad-5.4.0.jar">
<sha256 value="6665792cde201f5828e38e0d214aa67d817e34de3e7a5946e6a488c4534b4561" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.rat" name="apache-rat" version="0.11">
@ -3241,64 +3251,64 @@
<sha256 value="3902794d36d9b81da1b7e697f21ed04ccae276cc116eecc640a4cd0fff2691f2" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.tika" name="tika-core" version="2.9.2">
<artifact name="tika-core-2.9.2.jar">
<sha256 value="8c43f48ab8a784f2cda8a386d5f425060d57e3232dc6b49f9915029ac1f0b783" origin="Generated by Gradle"/>
<component group="org.apache.tika" name="tika-core" version="2.9.3">
<artifact name="tika-core-2.9.3.jar">
<sha256 value="ec1ce5791ed2c81867a45b183c87d6e2a9fe67f4920567b08fcae5a3edff0fee" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.tika" name="tika-langdetect-tika" version="2.9.2">
<artifact name="tika-langdetect-tika-2.9.2.jar">
<sha256 value="389d7d32e20d61ea985b5ffcdaef6531b4ecf09a98c04ee7152ef9332a1e5fa9" origin="Generated by Gradle"/>
<component group="org.apache.tika" name="tika-langdetect-tika" version="2.9.3">
<artifact name="tika-langdetect-tika-2.9.3.jar">
<sha256 value="5b5075b838c75bef02052d9bef2631cb83fa245418113135f2e6cfab0c81c2a5" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.tika" name="tika-parser-apple-module" version="2.9.2">
<artifact name="tika-parser-apple-module-2.9.2.jar">
<sha256 value="b6d594bf779055bacf5cef40380fddbda1bf08d4da1225428f559640cea83e0f" origin="Generated by Gradle"/>
<component group="org.apache.tika" name="tika-parser-apple-module" version="2.9.3">
<artifact name="tika-parser-apple-module-2.9.3.jar">
<sha256 value="798c334f71849fe1652bded5e518de59c485dbbf2dd2dede4bfcecf7a2ebd523" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.tika" name="tika-parser-html-module" version="2.9.2">
<artifact name="tika-parser-html-module-2.9.2.jar">
<sha256 value="bbaad920536b6bbd66e5ae80fd50d08681fa655fa226f84ccf88dc0a83cc5ab4" origin="Generated by Gradle"/>
<component group="org.apache.tika" name="tika-parser-html-module" version="2.9.3">
<artifact name="tika-parser-html-module-2.9.3.jar">
<sha256 value="6445ba6bc1dcc41301346099b47e3b88bb0a264a4f839206a5dc7a46bda78efa" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.tika" name="tika-parser-microsoft-module" version="2.9.2">
<artifact name="tika-parser-microsoft-module-2.9.2.jar">
<sha256 value="4ecc4a54049cb82ebb57dd7220243a50dd1fae9673f9cfd0751b12405d352f76" origin="Generated by Gradle"/>
<component group="org.apache.tika" name="tika-parser-microsoft-module" version="2.9.3">
<artifact name="tika-parser-microsoft-module-2.9.3.jar">
<sha256 value="1da265d127f372042a4de1032e9af14e0179e7edda4bc8e9f051c68ce25a98ea" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.tika" name="tika-parser-miscoffice-module" version="2.9.2">
<artifact name="tika-parser-miscoffice-module-2.9.2.jar">
<sha256 value="8847fba5aa0dda13fa7ed6e6ca9079ba94df6a73be990540361744c9e0ae6b74" origin="Generated by Gradle"/>
<component group="org.apache.tika" name="tika-parser-miscoffice-module" version="2.9.3">
<artifact name="tika-parser-miscoffice-module-2.9.3.jar">
<sha256 value="405a68372c64f1d83094555d7c5e3a88902c4166a3c5d0418e89fc23dba40727" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.tika" name="tika-parser-pdf-module" version="2.9.2">
<artifact name="tika-parser-pdf-module-2.9.2.jar">
<sha256 value="c436d561f9645c3a6814b62ad93c46864197bc726d43f1d055269f290c631230" origin="Generated by Gradle"/>
<component group="org.apache.tika" name="tika-parser-pdf-module" version="2.9.3">
<artifact name="tika-parser-pdf-module-2.9.3.jar">
<sha256 value="b72f736be311b88662680e46275034da65f4d5fb91e5b0178323b36261f1222f" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.tika" name="tika-parser-text-module" version="2.9.2">
<artifact name="tika-parser-text-module-2.9.2.jar">
<sha256 value="7c957b3ac019825a83553cfce9c59bbf1161734329a91a334044ed4dde60c41f" origin="Generated by Gradle"/>
<component group="org.apache.tika" name="tika-parser-text-module" version="2.9.3">
<artifact name="tika-parser-text-module-2.9.3.jar">
<sha256 value="ad50ef8150497b9a9bd655f19a619f9935d7c2f36986c1889bb85a3f024db4c2" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.tika" name="tika-parser-xml-module" version="2.9.2">
<artifact name="tika-parser-xml-module-2.9.2.jar">
<sha256 value="08112db5662be78fb6ef57485abeaab019df8fff4a559ae552ef205b6600a64e" origin="Generated by Gradle"/>
<component group="org.apache.tika" name="tika-parser-xml-module" version="2.9.3">
<artifact name="tika-parser-xml-module-2.9.3.jar">
<sha256 value="0b84ca2adb58b8f15c234f75722cf8c63c0d3611dc6d9040c7a5fbff5e2705de" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.tika" name="tika-parser-xmp-commons" version="2.9.2">
<artifact name="tika-parser-xmp-commons-2.9.2.jar">
<sha256 value="859f25e753b30b02f5a352505fcdaf7b39e1b9a46a64aa17bcf239725f579d66" origin="Generated by Gradle"/>
<component group="org.apache.tika" name="tika-parser-xmp-commons" version="2.9.3">
<artifact name="tika-parser-xmp-commons-2.9.3.jar">
<sha256 value="529dc45f7abb9dd7034f1f3c7a4a09c9147d8ef24619e96a74532e4f283a85a9" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.tika" name="tika-parser-zip-commons" version="2.9.2">
<artifact name="tika-parser-zip-commons-2.9.2.jar">
<sha256 value="2542778293f331358bb37e32e008831031c0b75d4d27d7b65416829d28ff91c0" origin="Generated by Gradle"/>
<component group="org.apache.tika" name="tika-parser-zip-commons" version="2.9.3">
<artifact name="tika-parser-zip-commons-2.9.3.jar">
<sha256 value="29167d467ae43893f4e0e1df072f8aa8011c85604df7ce039f50159818b47023" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.xmlbeans" name="xmlbeans" version="5.2.0">
<artifact name="xmlbeans-5.2.0.jar">
<sha256 value="5a344f323c049b7024edd39bbd58a38e77eb44218aad2794879e7f4ac3ca1de1" origin="Generated by Gradle"/>
<component group="org.apache.xmlbeans" name="xmlbeans" version="5.3.0">
<artifact name="xmlbeans-5.3.0.jar">
<sha256 value="6cc69da3b4d35b83c5e477cd4daba204e44109833e34af2b9a8a2c8788289917" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.yetus" name="audience-annotations" version="0.5.0">
@ -4554,9 +4564,9 @@
<sha256 value="a310bc79c3f4744e2b2e993702fcebaf3696fec0063643ffdc6b49a8fb03ef39" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.slf4j" name="jcl-over-slf4j" version="2.0.10">
<artifact name="jcl-over-slf4j-2.0.10.jar">
<sha256 value="5dc8cec38fdc9b70df4fae9779894c1487c782502a934eaa273c31237bb42d62" origin="Generated by Gradle"/>
<component group="org.slf4j" name="jcl-over-slf4j" version="2.0.16">
<artifact name="jcl-over-slf4j-2.0.16.jar">
<sha256 value="5744d62c5af556e839ab922c9fa3f737f0a5971e478ba68b2eb5256b2842ec78" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.slf4j" name="slf4j-api" version="1.7.10">
@ -4589,9 +4599,9 @@
<sha256 value="fe30825245d2336c859dc38d60c0fc5f3668dbf29cd586828d2b5667ec355b91" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.slf4j" name="slf4j-api" version="2.0.10">
<artifact name="slf4j-api-2.0.10.jar">
<sha256 value="b7ddb31a515debbddec8e9145e2cf7b197926f40e454376647724f92e6382043" origin="Generated by Gradle"/>
<component group="org.slf4j" name="slf4j-api" version="2.0.16">
<artifact name="slf4j-api-2.0.16.jar">
<sha256 value="a12578dde1ba00bd9b816d388a0b879928d00bab3c83c240f7013bf4196c579a" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.slf4j" name="slf4j-api" version="2.0.6">
@ -4609,9 +4619,9 @@
<sha256 value="4d41e01c40caf8a6c74add2b073055d8a4ce1c30e58154177b13f12d78abbe7b" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.slf4j" name="slf4j-nop" version="2.0.10">
<artifact name="slf4j-nop-2.0.10.jar">
<sha256 value="9e6d4b070aad63b6ba8d79f2fb0d93ad9a2b9fc8fb8946c324dfb4202dae0016" origin="Generated by Gradle"/>
<component group="org.slf4j" name="slf4j-nop" version="2.0.16">
<artifact name="slf4j-nop-2.0.16.jar">
<sha256 value="deca6c04ed35515a0a911fa44c0e836bee92c0c59d2e8fa9bab8ffbc464a9ba7" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.slf4j" name="slf4j-nop" version="2.0.6">
@ -4679,6 +4689,11 @@
<sha256 value="7eafdc8880da10286c2398fa42e3bf68c3e845c35ae7a6ae67f5cc1fa16c7405" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.tukaani" name="xz" version="1.10">
<artifact name="xz-1.10.jar">
<sha256 value="95c63c1a55b22dd6453890a419cc1a640f790bbf7d8ae82db1e30aefefb08888" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.tukaani" name="xz" version="1.8">
<artifact name="xz-1.8.jar">
<sha256 value="8c7964b36fe3f0cbe644b04fcbff84e491ce81917db2f5bfa0cba8e9548aff5d" origin="Generated by Gradle"/>

View file

@ -19,24 +19,24 @@ esplugin {
// when updating tika, please review it's parent pom : https://repo1.maven.org/maven2/org/apache/tika/tika-parent
// and manually update the transitive dependencies here
def versions = [
'tika' : '2.9.2',
'pdfbox': '2.0.31',
'poi' : '5.2.5',
'tika' : '2.9.3',
'pdfbox': '2.0.33',
'poi' : '5.4.0',
'sparsebitset' : '1.3', //poi dependency: https://repo1.maven.org/maven2/org/apache/poi/poi/
'mime4j': '0.8.11',
'commonsCodec': '1.16.1',
'slf4' : '2.0.10',
'xz' : '1.9',
'commonsIo' : '2.15.1',
'mime4j': '0.8.12',
'commonsCodec': '1.18.0',
'slf4' : '2.0.16',
'xz' : '1.10',
'commonsIo' : '2.18.0',
//intentionally using the elder "juniversalchardet:juniversalchardet" rather than the newer "com.github.albfernandez:juniversalchardet"
//since the "com.github.albfernandez" fork has some problems with Chinese.
'juniversalchardet' : '1.0.3',
'tagsoup' : '1.2.1',
'jempbox' : '1.8.17',
'xmlbeans' : '5.2.0', //poi-ooxml dependency: https://repo1.maven.org/maven2/org/apache/poi/poi-ooxml/
'xmlbeans' : '5.3.0', //poi-ooxml dependency: https://repo1.maven.org/maven2/org/apache/poi/poi-ooxml/
'commonsCollections4' : '4.4',
'commonsCompress' : '1.26.1',
'commonsLang3' :'3.14.0',
'commonsCompress' : '1.27.1',
'commonsLang3' :'3.17.0',
'commonsMath3' : '3.6.1'
]