)]}'
{
  "log": [
    {
      "commit": "2d421910c2bebe7239c0bd011631ba3a55d62008",
      "tree": "b8cced9b969285d1db4dc91cbdd6e7ce594132fd",
      "parents": [
        "800d9b7b9cc945dd7d4083bf775be1bbf0cbe49c"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Wed Jun 10 07:25:33 2026 +0200"
      },
      "committer": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Wed Jun 10 07:25:33 2026 +0200"
      },
      "message": "Fix worker-pool streaming deadlock on large corpora\n\nAnnotate and flush per document instead of buffering 20000 sentences with\nno flush. parse_spacy_pipe.py now treats korapxmltool\u0027s \u0027# eot\u0027/\u0027# eof\u0027\nlines as document delimiters (rather than swallowing them as CoNLL-U\ncomments), emits the matching marker after each document, and flushes\nstdout. This lets korapxmltool\u0027s AnnotationWorkerPool deliver each result\nand release its bounded in-flight buffer slot.\n\nPreviously nothing was emitted until the process exited at stdin EOF, so\nthe in-flight buffer filled and the producer blocked in\nbufferedTaskPermits.acquire while the parser blocked reading stdin for a\nfull chunk - a deadlock with idle CPU and zero progress that only appeared\non corpora with many small documents (small ones fit inside the buffer).\n\nInputs without protocol markers (a CoNLL-U file piped in directly) are\nstill read in SPACY_CHUNK_SIZE-bounded blocks and now stream their output.\n\nVerified end-to-end with \u0027korapxmltool -P spacy\u0027 on zca24.zip: progress\nstreams 0-\u003e95 to completion, morpho/dependency output is correct, and no\nmarkers leak into the annotations.\n\nCo-Authored-By: Claude Opus 4.8 \u003cnoreply@anthropic.com\u003e\nChange-Id: I07d18c54e6e3238758b2c4a885ceabd428ec3f82\n"
    },
    {
      "commit": "9baa27a69f78d35f55b51fd41f84458147213ae3",
      "tree": "70769b1dc8fa1e791a9e8b24cd9d466d1d04a93d",
      "parents": [
        "68a1813d2c4472d9e9372b16e9e10d5be85f2c60"
      ],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Sat Nov 29 15:32:16 2025 +0100"
      },
      "committer": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Sat Nov 29 15:32:16 2025 +0100"
      },
      "message": "Shrink docker size by avoiding chown\n\nChange-Id: I778c3993a37deef1d2eaa3d2b401d796ce8662f7\n"
    },
    {
      "commit": "8604485f28d54fef4e34fde53f0bd08161901722",
      "tree": "47796f9dd1e45a9b88a2dc493fa16a1c6b8b273e",
      "parents": [],
      "author": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Sat Nov 29 10:19:03 2025 +0100"
      },
      "committer": {
        "name": "Marc Kupietz",
        "email": "kupietz@ids-mannheim.de",
        "time": "Sat Nov 29 10:21:33 2025 +0100"
      },
      "message": "Initial import\n\nChange-Id: I6315233ee1bfbdf7cc985cb336d0df7a10274189\n"
    }
  ]
}