)]}'
{
  "commit": "6d28ed1b72bf3dc34fb72894b8998819c0f662c2",
  "tree": "09d246aaf47d08d38bf2ceb2f9e6c5a9b1684951",
  "parents": [
    "a1459227d3b167a31d31d5a706f0a90256ede74b"
  ],
  "author": {
    "name": "Marc Kupietz",
    "email": "kupietz@ids-mannheim.de",
    "time": "Thu Jul 15 21:09:47 2021 +0200"
  },
  "committer": {
    "name": "Marc Kupietz",
    "email": "kupietz@ids-mannheim.de",
    "time": "Fri Jul 16 21:36:38 2021 +0200"
  },
  "message": "Separate apostrophe marked contractions and clitics for en and fr\n\nThe original working rule was overwritten with a rule for German \"omission\nwords\" like \"W\u0027schaft\", \"M\u0027gladbach\u0027, ... in:\n\nhttps://korap.ids-mannheim.de/gerrit/c/private/Ingestion/+/390/1/src/main/jflex/de/ids_mannheim/korap/tokenizer/KorAPTokenizerImpl.jflex\n\nFor German we stick to the standard of *not* separating clitics and\ncontractions, however the changes for English end French words will\nalso be applied in the de tokenizer except for \u0027s and \u0027n.\n\nThanks @Mai \u0026 Harald!\n\nResolves #22\n\nChange-Id: I5e0a81fd38709e49a734d16ad077265a1571c824\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "833e56246b1d71786caed7ce0bdfcb5ae04727cb",
      "old_mode": 33188,
      "old_path": "CHANGELOG.md",
      "new_id": "e5349d260173711da6b3174b35a0d205b4e0216d",
      "new_mode": 33188,
      "new_path": "CHANGELOG.md"
    },
    {
      "type": "modify",
      "old_id": "cfbe24eb45cc9e8613f19a64878047cb518b9376",
      "old_mode": 33188,
      "old_path": "src/main/jpc/jflex/de/ids_mannheim/korap/tokenizer/DerekoDfaTokenizer.jflex",
      "new_id": "5a3993292fa9d608c8d0b52d15a3265cecc58f13",
      "new_mode": 33188,
      "new_path": "src/main/jpc/jflex/de/ids_mannheim/korap/tokenizer/DerekoDfaTokenizer.jflex"
    },
    {
      "type": "modify",
      "old_id": "6a7404e7fa7e9dfe7bfbcb39e6d160934ef44f34",
      "old_mode": 33188,
      "old_path": "src/main/jpc/jflex/de/ids_mannheim/korap/tokenizer/language-specific_de.jflex-macro",
      "new_id": "b36026c7f9f9337334faef0b48c8a6932628660d",
      "new_mode": 33188,
      "new_path": "src/main/jpc/jflex/de/ids_mannheim/korap/tokenizer/language-specific_de.jflex-macro"
    },
    {
      "type": "modify",
      "old_id": "8bd5321f2d84e33509835d8e5f7039c52326af12",
      "old_mode": 33188,
      "old_path": "src/main/jpc/jflex/de/ids_mannheim/korap/tokenizer/language-specific_en.jflex-macro",
      "new_id": "fcfac6c9c1020af9a3ee7e44d906bb0e6871dd8f",
      "new_mode": 33188,
      "new_path": "src/main/jpc/jflex/de/ids_mannheim/korap/tokenizer/language-specific_en.jflex-macro"
    },
    {
      "type": "modify",
      "old_id": "58c133329157f088d5ec39589ccac4a19f0cd9b5",
      "old_mode": 33188,
      "old_path": "src/main/jpc/jflex/de/ids_mannheim/korap/tokenizer/language-specific_fr.jflex-macro",
      "new_id": "be9bd71c2f38266cf28e60fd3f6d8a22c6c4fbd6",
      "new_mode": 33188,
      "new_path": "src/main/jpc/jflex/de/ids_mannheim/korap/tokenizer/language-specific_fr.jflex-macro"
    },
    {
      "type": "modify",
      "old_id": "1629d213a535274897af5dbe555421eb5b0fa179",
      "old_mode": 33188,
      "old_path": "src/test/java/de/ids_mannheim/korap/tokenizer/IPCOffsetTests.java",
      "new_id": "b8f520f17952763222c7a253c8d9d38b68d8f489",
      "new_mode": 33188,
      "new_path": "src/test/java/de/ids_mannheim/korap/tokenizer/IPCOffsetTests.java"
    },
    {
      "type": "modify",
      "old_id": "5a434a4746085b7c4318fb0e43473ba1eb762f25",
      "old_mode": 33188,
      "old_path": "src/test/java/de/ids_mannheim/korap/tokenizer/TokenizerTest.java",
      "new_id": "87a95db4b7a93c3e5dd101afc5ad86f019d49ebe",
      "new_mode": 33188,
      "new_path": "src/test/java/de/ids_mannheim/korap/tokenizer/TokenizerTest.java"
    },
    {
      "type": "modify",
      "old_id": "3af06dcc8683d201ed7b8a489909394fa9c8af2b",
      "old_mode": 33188,
      "old_path": "src/test/resources/other_test_data/test.de.latin1.01.positions.txt",
      "new_id": "690fd75c8fedb52687e5a1222be8d591b87fb696",
      "new_mode": 33188,
      "new_path": "src/test/resources/other_test_data/test.de.latin1.01.positions.txt"
    },
    {
      "type": "modify",
      "old_id": "3841111ed07b6bb1fc6578ed22f6fa855edabe5e",
      "old_mode": 33188,
      "old_path": "src/test/resources/other_test_data/test.de.latin1.01.tokens.txt",
      "new_id": "f09b8df57812d81d421d61bd1ad931126f571bb0",
      "new_mode": 33188,
      "new_path": "src/test/resources/other_test_data/test.de.latin1.01.tokens.txt"
    },
    {
      "type": "modify",
      "old_id": "37e2f7bf19fcf2340b05ef1d84c2bfebef0736d8",
      "old_mode": 33188,
      "old_path": "src/test/resources/other_test_data/test.de.utf8.01.positions.txt",
      "new_id": "f0a84c8d5d580d249060c899d732cb7a3f95a4e1",
      "new_mode": 33188,
      "new_path": "src/test/resources/other_test_data/test.de.utf8.01.positions.txt"
    },
    {
      "type": "modify",
      "old_id": "60b82db67b9fe520c93f962ce086e4c05ba7bde9",
      "old_mode": 33188,
      "old_path": "src/test/resources/other_test_data/test.de.utf8.01.tokens.txt",
      "new_id": "b54e59675c7dba9cb3405693ca4071b07478a806",
      "new_mode": 33188,
      "new_path": "src/test/resources/other_test_data/test.de.utf8.01.tokens.txt"
    },
    {
      "type": "modify",
      "old_id": "2ce7d24cb51ebdea8367f807bc276a2c3477a370",
      "old_mode": 33188,
      "old_path": "src/test/resources/other_test_data/test.fr.utf8.01.positions.txt",
      "new_id": "07c22f1af076be09ee647ba3dabf6ebf5d9be78b",
      "new_mode": 33188,
      "new_path": "src/test/resources/other_test_data/test.fr.utf8.01.positions.txt"
    },
    {
      "type": "modify",
      "old_id": "0286db17789c47585becc7476f6f9939c397b0b1",
      "old_mode": 33188,
      "old_path": "src/test/resources/other_test_data/test.fr.utf8.01.tokens.txt",
      "new_id": "151604464bf7abf697b863115fe55b9519b1e357",
      "new_mode": 33188,
      "new_path": "src/test/resources/other_test_data/test.fr.utf8.01.tokens.txt"
    }
  ]
}