)]}'
{
  "log": [
    {
      "commit": "67eed1c2ffa2a4b61958071d61f4f84d9bd10861",
      "tree": "ae3a7c8042c9eaaf534909b99ad46d10bfde1e1f",
      "parents": [
        "8e197f3c8895ff5d66d903f17da7e915076c84c8"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Mon Sep 28 21:37:16 2020 +0200"
      },
      "committer": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Fri Oct 09 14:48:55 2020 +0200"
      },
      "message": "Build language specific tokenizers: de, en\n\nChange-Id: Iedad4d96aa702e173ed98d888685b4dd7b113cd5\n"
    },
    {
      "commit": "751868b9a6f8c65ae26bd212c746c91e80d00d7c",
      "tree": "efa93123637391ce7b6718a269495f9677717a64",
      "parents": [
        "b9f45e084ceca956b3378fe12d20d9d5b08edadc"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Fri Sep 25 17:59:38 2020 +0200"
      },
      "committer": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Mon Sep 28 09:04:10 2020 +0200"
      },
      "message": "Make tokenizer implementation exchangeable\n\nAllows for quite an easy adaptation and integration of other language\nspecializations and other tokenizers, also from the command line with\nnew -T option that allows to specify the tokenizer class name.\n\nTODO: add documentation to the KorapTokenizer interface\n\nChange-Id: Ib95793f47887a3b0829d68ebdbf8bc40815a0605\n"
    },
    {
      "commit": "b9f45e084ceca956b3378fe12d20d9d5b08edadc",
      "tree": "c600f3a8d842f7ee6607080840ea0701de57085c",
      "parents": [
        "c419d5b22c508a352f00fb11f23034a10bfbaf3d"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Thu Sep 17 20:03:59 2020 +0200"
      },
      "committer": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Fri Sep 18 19:13:17 2020 +0200"
      },
      "message": "Rename tokenizer class to KorAPDFATokenizer\n\nChange-Id: Icad8af7582689f599eda27258cc397e6155aeefe\n"
    },
    {
      "commit": "c419d5b22c508a352f00fb11f23034a10bfbaf3d",
      "tree": "83eb21aa0d47920a7c1fcd225601249c1dc4108c",
      "parents": [
        "de949deb083c43f4e0fed3713617aed768c000aa"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Thu Sep 17 15:21:26 2020 +0200"
      },
      "committer": {
        "name": "Akron",
        "email": "nils@diewald-online.de",
        "time": "Fri Sep 18 17:44:06 2020 +0200"
      },
      "message": "Add new command line options using picocli and sanitize code\n\nUsage: koraptokenizer [-hnpsV] [--force] [-ktt] [--[no-]tokens]\n                      [-o\u003d\u003coutput_fillename\u003e] [\u003cinputFiles\u003e...]\nTokenizes (and sentence splits) text input.\n      [\u003cinputFiles\u003e...]   input files\n      --force             Force overwrite (default: false)\n  -h, --help              Show this help message and exit.\n      -ktt                Deprecated. For internal use only. (default: false)\n  -n, --normalize         Normalize tokens (default: false)\n      --[no-]tokens       Print tokens (default: true)\n  -o, --output-file\u003d\u003coutput_fillename\u003e\n                          Output file (default: -)\n  -p, --positions         Print token start and end positions as character\n                            offsets (default: false)\n  -s, --sentence-boundaries\n                          Print sentence boundary positions (default: false)\n  -V, --version           Print version information and exit.\n\nChange-Id: Ib92678c832a2d95799a8f503c3e86dd4da2b4d73\n"
    },
    {
      "commit": "783e2a27b3e9612cff8348e841c6a484c0d761f9",
      "tree": "e2605d396fbfad73b94a2e0c085e509a2360ca4a",
      "parents": [
        "571c194376e9bfc928da5a4eb765e59eceae096d"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Fri Sep 11 23:34:27 2020 +0200"
      },
      "committer": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Mon Sep 14 09:40:25 2020 +0200"
      },
      "message": "Ignore quoted email names like \"John Doe\"@xx.com\n\nThey are rare and are now delivering too many false positives due to Twitter handles, like:\n\n Pluto.\"  Eris-Entdecker Mike Brown, der im Kurznachrichtendienst Twitter unter \"@plutokiller\n\n A different prioritization does not seem necessary either.\n\nChange-Id: I75e328f027f917ab1db246da80201e30604472db\n"
    },
    {
      "commit": "571c194376e9bfc928da5a4eb765e59eceae096d",
      "tree": "ec8d984c8b3b5b1b045315b4591d2954e639133a",
      "parents": [
        "6afd12177bab60924a76c214cacb03029e244c11"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Tue Sep 08 18:39:57 2020 +0200"
      },
      "committer": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Wed Sep 09 08:32:37 2020 +0200"
      },
      "message": "Empty text (\u003cEOT\u003e\u003cEOT\u003e) -\u003e empty output line\n\nEmpty texts, i. e. \u003cEOT\u003e\u003cEOF\u003e will result in empty output lines. At the end of a file however one additional \u003cEOT\u003e will not produce an empty outpu line.\n\nChange-Id: Ib989f91f7172441e6b6d8689dfc118f07d91e1c2\n"
    },
    {
      "commit": "6afd12177bab60924a76c214cacb03029e244c11",
      "tree": "d605c7640a1100490e5c02169921217fb8585b23",
      "parents": [
        "793f85dffdd621f671962eb6e080887d5355a802"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Tue Sep 08 14:29:11 2020 +0200"
      },
      "committer": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Tue Sep 08 17:51:46 2020 +0200"
      },
      "message": "Use standard EOT/EOF character x04 instead of magic escape \\n\\x03\\n\n\nChange-Id: I06b4eb09064c08b5708a612666b7d807785ae580\n"
    },
    {
      "commit": "b2666fc5a425f68797079e32c0e3cb6d25d056d7",
      "tree": "bb2764a228d392c2127d92fee69188d1e0e1a2bb",
      "parents": [
        "07d97146420a0909c9d2c21ab21c95069b3a98b1"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Mon Sep 07 18:03:46 2020 +0200"
      },
      "committer": {
        "name": "Akron",
        "email": "nils@diewald-online.de",
        "time": "Tue Sep 08 17:25:08 2020 +0200"
      },
      "message": "Implement sentence splitter\n\nChange-Id: I80969a8ac68193dd2a3dd82c1f606807193c39c8\n"
    },
    {
      "commit": "81925096b645bf17cf688d1311bce002b5a9418f",
      "tree": "72e8930b1290ff3567cd9987d7e425d9b5e4c580",
      "parents": [
        "478632eb7e133969531f3b401576564783183707"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Mon Sep 07 15:16:51 2020 +0200"
      },
      "committer": {
        "name": "Marc K",
        "email": "morckx@gmail.com",
        "time": "Mon Sep 07 15:25:28 2020 +0200"
      },
      "message": "Use original Span class and implement Tokenizer interface from OpenNLP\n\nUsing maven assembly plugin to include the required classes into a jar\nfor binary distribution.\n\nThis makes it possible to use KorAPTokenizerImpl as tokenizer in OpenNLP\napplications.\n\nChange-Id: I627dcdd046334db1b1ae9dd60cf7104fd3a3c518\n"
    },
    {
      "commit": "478632eb7e133969531f3b401576564783183707",
      "tree": "750d4b79b2f2b1e4e36794a8d593ebc3cb68b0be",
      "parents": [
        "fe84dd00e4116df5fc7b3bfd026249fe5a8ece5b"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Sat Sep 05 21:52:54 2020 +0200"
      },
      "committer": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Mon Sep 07 10:59:10 2020 +0200"
      },
      "message": "Clean up code\n\nChange-Id: Icc8d4b091b4f61401d7f4194188b568dd30d627f\n"
    },
    {
      "commit": "3367773b65d4629b0cdc994d134129b00f0f9a63",
      "tree": "86588a5c60e52c837aa8e16090089bbb7da95abe",
      "parents": [],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Fri Sep 04 22:07:39 2020 +0200"
      },
      "committer": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Sat Sep 05 22:07:36 2020 +0200"
      },
      "message": "Initial import from private/Ingestion\n\nChange-Id: I96f428c440ef301384de6d7ef2e348df7d729816\n"
    }
  ]
}
