)]}' { "log": [ { "commit": "104c94b34d577adb1e51979ef9c12619f58382fb", "tree": "1a9c2501101c3c1383f29da77af667e235232f77", "parents": [ "b028de453ff7bc84e558bdf05c331803b1cdb0a8" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Thu Feb 02 19:53:53 2023 +0100" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Sun Feb 05 11:16:06 2023 +0100" }, "message": "Add option -Z to exclude empty texts\n\nChange-Id: I1f2594ce839351205ce43b5047b349af7ba019bb\n" }, { "commit": "f5d4d75543681f23046fb0e7034b24a815cd8ab3", "tree": "b0148326458fb6aa516f9d6fe45cf072dccdc5f3", "parents": [ "95e3f4f6beaf45dfc9f1264cfc42d5b97a21b975" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Mon Jan 23 17:11:06 2023 +0100" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Mon Jan 23 17:29:36 2023 +0100" }, "message": "Fix empty cardinal tokens and lemmas in FilterKeys\n\nFor example:\n\n1000 1143\n\nwas after filtering:\n\n\t1143\n\nDisadvantage (and funny result) of implicit typing in Groovy.\n\nChange-Id: I328cd3babb7de472a6e2ff2914f7559a954c4c8e\n" }, { "commit": "545bb919879b8d4a130eb1040efa5443e18a63fe", "tree": "d2e6a1f1b2b54fc6cf7e02f7c47bc2f7f6ba67bc", "parents": [ "575ab1cfa7b5ed38f8e50881ef06398100c5183c" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Thu Dec 08 08:05:59 2022 +0100" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Thu Dec 08 10:25:28 2022 +0100" }, "message": "Extend isPunctuation unit test\n\nChange-Id: I670a7679e774e23aa914230bf2b72df2a3bd839e\n" }, { "commit": "a4f6cf9ea44b1a6fce6e59e6530e1ecf8658ba9f", "tree": "8e59bdcd3dfae181c200c685d98ecc17243144ba", "parents": [ "464b1c88414ef715b5f9f50c0e3b6a6c32db5ce2" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Wed Dec 07 17:28:29 2022 +0100" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Wed Dec 07 17:30:42 2022 +0100" }, "message": "Add exclude punctuation option\n\nChange-Id: Ie90a59f77a92b8007af92411bcbaf00a8c910722\n" }, { "commit": "47bd7434f76b70233505bd4ffefde34d64b35980", "tree": "cbbec21c9e2b3c21a0f5a47ea112d4c5b74411a9", "parents": [ "869bfb99e954d6a478422f31cfc0804f536b3f2f" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Mon Nov 07 13:34:12 2022 +0100" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Mon Nov 07 13:34:12 2022 +0100" }, "message": "Drop failing stderr test\n\nChange-Id: I32d0e26debe582b76edf54c3c4d3b544b1ecb961\n" }, { "commit": "869bfb99e954d6a478422f31cfc0804f536b3f2f", "tree": "2b6ae092e47356262eadfcbe02d4ab340aa84c8d", "parents": [ "e582d9c091fc886a1a01d7c7c19a75acd47c1987" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Sun Nov 06 20:38:40 2022 +0100" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Mon Nov 07 13:33:32 2022 +0100" }, "message": "Incorporate pseudonymization scripts into maven project\n\nAnd set minimum java version to 17\n\nChange-Id: Ieb8c9c0cd64214111cb7ef11775ea0272f46054c\n" }, { "commit": "37197a8f03987ce026804962647365479c98c45b", "tree": "0a03608bace58f834d59e14b3125f589ce5ea339", "parents": [ "be2995930dd9fa80b969f766095285ca27c2bd36" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Sun Sep 26 14:42:43 2021 +0200" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Sun Sep 26 14:53:08 2021 +0200" }, "message": "Fix bug in simple test\n\nWhich resulted in always pass\n\nChange-Id: I672fa850bbd908cdfa9978e08d9febdcd684d6a9\n" }, { "commit": "be2995930dd9fa80b969f766095285ca27c2bd36", "tree": "837ce161b1aeb1ee8178227cea93eac78d707d15", "parents": [ "e4adb6901cf99cc3295905fb64e8c906b3893f6a" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Sun Sep 26 11:57:39 2021 +0200" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Sun Sep 26 14:53:08 2021 +0200" }, "message": "Test simple text also without padding\n\nChange-Id: I1b720659b38aabc613ef06b81b259a18c6eab142\n" }, { "commit": "a691041dec4308c43716a77451bd6fb917f60945", "tree": "01ecef067465a1e2dc90e311d1a066b39f0c6663", "parents": [ "ead2a6fcbb23c8860648199c2d62c41908eaf15b" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Thu Sep 23 23:15:20 2021 +0200" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Fri Sep 24 16:26:02 2021 +0200" }, "message": "Add --pad option to optionally add padding symbols at text edges\n\n1 ich ich PPER PPER _ _ _ _ 1\n 2 bin sein VAFIN VAFIN _ _ _ _ 1.000000\n 3 alex alex NE NE _ _ _ _ 0.565630\n 4 . . $. $. _ _ _ _ 1.000000\n\n # text_id \u003d TST_TST.00001\n 1 alex alex NE NE _ _ _ _ 0.565630\n 2 bin sein VAFIN VAFIN _ _ _ _ 1.000000\n 3 ich ich PPER PPER _ _ _ _ 1\n 4 . . $. $. _ _ _ _ 1.000000\n\n # text_id \u003d TST_TST.00002\n 1 ich ich PPER PPER _ _ _ _ 1\n 2 heiße heißen VAFIN VAFIN _ _ _ _ 1.000000\n 3 alex alex NE NE _ _ _ _ 0.565630\n 4 . . $. $. _ _ _ _ 1.000000\n\n----\u003e\n\n. «END» «END» 3\n«END» «END» «END» 3\n«START» «START» «START» 3\n«START» «START» ich 2\nalex . «END» 2\n«START» «START» alex 1\n«START» alex bin 1\n«START» ich bin 1\n«START» ich heiße 1\nalex bin ich 1\nbin alex . 1\nbin ich . 1\nheiße alex . 1\nich . «END» 1\nich bin alex 1\nich heiße alex 1\n\nChange-Id: Ib4826400da657787940805c616a0000ac089120d\n" }, { "commit": "ead2a6fcbb23c8860648199c2d62c41908eaf15b", "tree": "42c2be0399d17b232cb44f3794c06d51af719387", "parents": [ "03f9dc05a9527cf9851ec294d3fda92976fb505d" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Thu Sep 23 23:13:41 2021 +0200" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Thu Sep 23 23:13:41 2021 +0200" }, "message": "Improve null handling in tests\n\nChange-Id: Ia01359e4b273b1fc9f9835d5d9c10057af051f2e\n" }, { "commit": "1b717be23ed24c717c510a8ea59e42450b261337", "tree": "cf61fceea236ac78a4db5b118ba751b664ccd140", "parents": [ "f14c0967e4a4e909944b42c5c01073bd4ba06c77" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Wed Sep 15 16:36:11 2021 +0200" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Wed Sep 15 16:46:46 2021 +0200" }, "message": "Auto detect xz compression for input and output\n\nNote that the compression is much slower than with gz, because\nthe xz compressor cannot yet run multi-threaded. However, xz compression\nis typically much better.\n\nChange-Id: Ia8bc7f6238f3c6367fd78ab45d37d2485090ef6f\n" }, { "commit": "53623e04349fa06a8951eda046c4170ca6657566", "tree": "e8784c743cec9f5d35c8d04f52d0d50e2b0e1f35", "parents": [ "bc8bd3d86fb7bc465fc6e4241a9d86b267823958" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Wed Apr 07 19:07:20 2021 +0200" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Wed Apr 07 19:07:20 2021 +0200" }, "message": "Add --downcase/-d option to convert all token characters to lower case\n\nChange-Id: I236cf61369faead4b9e4d955b7190b25f88d4a46\n" }, { "commit": "c78b5a5131a3faaa8f9400147b3f2c1e39a5669c", "tree": "4492bbe4de7aba5035296fd1ac2f7505e0d14b6e", "parents": [ "aca0a8dd422a5697bed66be33b51f4dd4f564214" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Mon Oct 05 09:40:30 2020 +0200" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Mon Oct 05 09:40:50 2020 +0200" }, "message": "totalNGrams: unescape all XML entities (\u0026, \u003c, \u003e, \")\n" }, { "commit": "aaf46f13ed75919fdba2ebb506d2e614256142a1", "tree": "dd7e5bf2e2d70f7223d0df85fcf674fca5fc636d", "parents": [ "cf6ec7d69ed7a82a2763a10f83951aa5643733a4" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Wed Jul 29 18:00:57 2020 +0200" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Wed Jul 29 18:00:57 2020 +0200" }, "message": "totalngrams: fix main class name\n" }, { "commit": "3db37c55019ebc33c4483438c8f320aa8844c190", "tree": "3fe2bc144ac9aee35c4087f37e837a2e250f6951", "parents": [ "b66b832cd05c71077c3b2494728d4383d4b6e486" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Wed Jul 29 17:21:21 2020 +0200" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Wed Jul 29 17:21:21 2020 +0200" }, "message": "totalngrams: add unit test for almost the whole pipeline\n" }, { "commit": "2ea60bd1571777050fe386dc0b15abff909808f0", "tree": "8e03839c46fdfc0d3f3bc86b6368727683cf51c6", "parents": [ "8780be5e975a6c29ed6b8e057972559b9ea5ce7d" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Tue Jul 28 09:24:43 2020 +0200" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Tue Jul 28 09:24:43 2020 +0200" }, "message": "Use cryptogrphic Blake2b hash as determisitic fold random source\n\nThe original standard hash code function was in effect partially\ndependent on the order of the texts.\n" }, { "commit": "6638bb2d153d5b460b9e17ffc020e67283a8b877", "tree": "2d427ee9d3441cf67f704653916c78dd2352bb25", "parents": [ "9c63b57bf420e50494aada8066a081610bcfb54c" ], "author": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Mon Jul 27 12:27:59 2020 +0200" }, "committer": { "name": "Marc Kupietz", "email": "kupietz@ids-mannheim.de", "time": "Mon Jul 27 15:53:37 2020 +0200" }, "message": "totalngrams: start adding unit tests\n" } ] }