)]}'
{
  "log": [
    {
      "commit": "e74785d85a4ecee829e1e405444d6a1b24b8bc9c",
      "tree": "75ac6593de596194f0502c62e0d97405101f290f",
      "parents": [
        "ba5e59c775e8fc2b615fd76d95f7c57a72935864"
      ],
      "author": {
        "name": "hsiang-c",
        "email": "137842490+hsiang-c@users.noreply.github.com",
        "time": "Tue Mar 03 22:49:07 2026 -0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Mar 04 08:49:07 2026 +0200"
      },
      "message": "Added AES-256 encrypted parquet generated from parquet-java (#102)\n\n* Added AES-256 encrypted parquet from modified parquet-java\n\n* Match schema and values\n\n* Match INT96 values\n\n* Note on AES256 test data\n\n* Binary in ByteOrder.LITTLE_ENDIAN\n\n* Fix byte order\n\n* Updated notes"
    },
    {
      "commit": "ba5e59c775e8fc2b615fd76d95f7c57a72935864",
      "tree": "d5a79c4e767646a083a0f11bee4c5ed27e77a71e",
      "parents": [
        "92d45b0752487a4b55fb7f1581c8126ee3e73b0d"
      ],
      "author": {
        "name": "fenfeng9",
        "email": "36840213+fenfeng9@users.noreply.github.com",
        "time": "Wed Feb 25 22:08:06 2026 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Feb 25 15:08:06 2026 +0100"
      },
      "message": "Add encrypted bloom filter test file (#103)\n\n"
    },
    {
      "commit": "92d45b0752487a4b55fb7f1581c8126ee3e73b0d",
      "tree": "85757c451292c89c892e74bb794cdabe37550d56",
      "parents": [
        "a3d96a65e11e2bbca7d22a894e8313ede90a33a3"
      ],
      "author": {
        "name": "Xu Bai",
        "email": "tocreationbai@gmail.com",
        "time": "Thu Nov 27 00:39:02 2025 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Nov 26 11:39:02 2025 -0500"
      },
      "message": "Correct typo in variant generation for primitive_int64 (#98)\n\n"
    },
    {
      "commit": "a3d96a65e11e2bbca7d22a894e8313ede90a33a3",
      "tree": "32fda3f6278ef38268ab1f4e99c5847f31127880",
      "parents": [
        "5cbfc43d488c9c8404a1a7088cca400ae095b831"
      ],
      "author": {
        "name": "Aihua Xu",
        "email": "aihuaxu@gmail.com",
        "time": "Wed Aug 20 22:38:15 2025 -0700"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Aug 21 13:38:15 2025 +0800"
      },
      "message": "Add shredded Variant reader cases with variant logical type (#91)\n\n* Add shredded variant reader test cases.\n* Add parquet_file for error cases.\n* Add variant logical type. Update decimal values. Add invalid test case notes.\n\n---------\n\nCo-authored-by: Ryan Blue \u003cblue@apache.org\u003e"
    },
    {
      "commit": "5cbfc43d488c9c8404a1a7088cca400ae095b831",
      "tree": "0e82f41b2c4031bb75c7fb364a36fb1083df030c",
      "parents": [
        "4cf674fc589309ba8651ad676f3fb557582d9cab"
      ],
      "author": {
        "name": "Congxian Qiu",
        "email": "qcx978132955@gmail.com",
        "time": "Thu Aug 14 14:19:11 2025 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Aug 14 14:19:11 2025 +0800"
      },
      "message": "Add Primitive time/timestamp_nanos/timestampntz_nanos/uuid test file (#92)\n\n* add primitive_time\n\n* update data_dictionary and regen script\n\n* add timestamp_nanos(tz\u0026ntz) and uuid binary artifacts\n\n* fix typo\n\n* update the primitive data order in data_dictionary.json\n\n* update readme"
    },
    {
      "commit": "4cf674fc589309ba8651ad676f3fb557582d9cab",
      "tree": "6c7546c7ed9788ff76fab23d8c67d18a808748f9",
      "parents": [
        "84d525a8731cec345852fb4ea2e7c581fbf2ef29"
      ],
      "author": {
        "name": "Raúl Cumplido",
        "email": "raulcumplido@gmail.com",
        "time": "Tue Jul 08 16:44:15 2025 +0200"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Tue Jul 08 22:44:15 2025 +0800"
      },
      "message": "Add binary truncated min/max statistics with is_{max/min}_value_exact\u003dfalse (#88)\n\n"
    },
    {
      "commit": "84d525a8731cec345852fb4ea2e7c581fbf2ef29",
      "tree": "9fe68700ae5638a553d86dc6b4e03a006fdf2b33",
      "parents": [
        "e7b28dd520fb3c9f0908daa84c0ef20d83c73794"
      ],
      "author": {
        "name": "Andrew Lamb",
        "email": "andrew@nerdnetworks.org",
        "time": "Mon Jun 09 03:17:43 2025 -0400"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Mon Jun 09 15:17:43 2025 +0800"
      },
      "message": "Correct `primitive_null.value` (#86)\n\n"
    },
    {
      "commit": "e7b28dd520fb3c9f0908daa84c0ef20d83c73794",
      "tree": "1575eb99f7e1edca0a5e6599c3265e990d2af3f3",
      "parents": [
        "107b36603e051aee26bd93e04b871034f6c756c0"
      ],
      "author": {
        "name": "Andrew Lamb",
        "email": "andrew@nerdnetworks.org",
        "time": "Fri May 23 08:02:17 2025 -0400"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Fri May 23 20:02:17 2025 +0800"
      },
      "message": "Add primitive_null metadata for example Variant values (#84)\n\n* Add primitive_null metadata\n\n* Update variant/README.md\n\nCo-authored-by: Fokko Driesprong \u003cfokko@apache.org\u003e\n\n* Update variant/README.md\n\n---------\n\nCo-authored-by: Fokko Driesprong \u003cfokko@apache.org\u003e"
    },
    {
      "commit": "107b36603e051aee26bd93e04b871034f6c756c0",
      "tree": "29749da087234cf6e9e2d6ed1df229cbaf7e6385",
      "parents": [
        "2dc8bf140ed6e28652fc347211c7d661714c7f95"
      ],
      "author": {
        "name": "Andrew Lamb",
        "email": "andrew@nerdnetworks.org",
        "time": "Wed May 21 23:14:56 2025 -0400"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu May 22 11:14:56 2025 +0800"
      },
      "message": "Fix Variant int64 variant example (#85)\n\n"
    },
    {
      "commit": "2dc8bf140ed6e28652fc347211c7d661714c7f95",
      "tree": "eba8577537604f7218c58dd78d23d91c3cbd7b32",
      "parents": [
        "d1f14a06f800238b127b51fef6fa6b9feb15ab0b"
      ],
      "author": {
        "name": "Andrew Lamb",
        "email": "andrew@nerdnetworks.org",
        "time": "Sat May 03 02:42:57 2025 -0400"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Fri May 02 23:42:57 2025 -0700"
      },
      "message": "Add example binary variant data and regeneration scripts (#76)\n\nAdds raw binary encodings for variant types along with script that was used to generate them and a JSON map documenting values in the files.\n\nCo-authored-by: Russell Spitzer \u003crussell.spitzer@GMAIL.COM\u003e\n\n---------\n\nCo-authored-by: Russell Spitzer \u003crussell.spitzer@GMAIL.COM\u003e"
    },
    {
      "commit": "d1f14a06f800238b127b51fef6fa6b9feb15ab0b",
      "tree": "8578e533763363db0821a231b8e2c52048a15126",
      "parents": [
        "e845e41789ec8d3aa6317e6464cdbbca987bf91d"
      ],
      "author": {
        "name": "Dewey Dunnington",
        "email": "dewey@wherobots.com",
        "time": "Wed Apr 30 13:25:51 2025 -0500"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Apr 30 11:25:51 2025 -0700"
      },
      "message": "Example files for GEOMETRY and GEOGRAPHY logical type (#70)\n\n* add some files\n\n* slightly better crs representations for projjson\n\n* maybe actually fix\n\n* remove redundant files\n\n* rewrite with crs keys that are less likely to collide\n\n* remove previous files\n\n* simpler example file\n\n* fix WKB in file for emtpy multiX types\n\n* add crs files\n\n* add nan case\n\n* rewrite geospatial.parquet with new empty/all null logic\n\n* update Shapely stats calculator for new files"
    },
    {
      "commit": "e845e41789ec8d3aa6317e6464cdbbca987bf91d",
      "tree": "fd1aebbf6e7eb691336aac1b6184fbc7674c98d6",
      "parents": [
        "6e851ddd768d6af741c7b15dc594874399fc3cff"
      ],
      "author": {
        "name": "Enrico Minack",
        "email": "github@enrico.minack.dev",
        "time": "Thu Apr 17 03:24:35 2025 +0200"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Apr 17 09:24:35 2025 +0800"
      },
      "message": "Add test file with empty DataPage v2 (#74)\n\n"
    },
    {
      "commit": "6e851ddd768d6af741c7b15dc594874399fc3cff",
      "tree": "0f7ae19310dfecba36295a261eb0a7641259f8de",
      "parents": [
        "18d17540097fca7c40be3d42c167e6bfad90763c"
      ],
      "author": {
        "name": "Matt Butrovich",
        "email": "mbutrovich@users.noreply.github.com",
        "time": "Thu Apr 03 10:35:07 2025 -0400"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Apr 03 22:35:07 2025 +0800"
      },
      "message": "Add int96 from Apache Spark (#73)\n\n"
    },
    {
      "commit": "18d17540097fca7c40be3d42c167e6bfad90763c",
      "tree": "841db0ea3846716e910817b485c9df4c7e696499",
      "parents": [
        "39b91cf853062d92f0d20581d37b20dabe70a6a0"
      ],
      "author": {
        "name": "Dewey Dunnington",
        "email": "dewey@dunnington.ca",
        "time": "Wed Mar 26 07:36:41 2025 -0500"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Mar 26 20:36:41 2025 +0800"
      },
      "message": "Add test file with unknown logical type (#72)\n\n"
    },
    {
      "commit": "39b91cf853062d92f0d20581d37b20dabe70a6a0",
      "tree": "6a7aaa92ed2fc381f23512af24304872e0a7a2d7",
      "parents": [
        "f4d7ed772a62a95111db50fbcad2460833e8c882"
      ],
      "author": {
        "name": "mwish",
        "email": "maplewish117@gmail.com",
        "time": "Wed Mar 05 10:39:41 2025 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Mar 05 10:39:41 2025 +0800"
      },
      "message": "Add DataPageV2 with zero-sized compression (#71)\n\n* Add DataPageV2 with zero-sized compression\n\n* Update data/README.md\n\nCo-authored-by: Antoine Pitrou \u003cpitrou@free.fr\u003e\n\n---------\n\nCo-authored-by: Antoine Pitrou \u003cpitrou@free.fr\u003e"
    },
    {
      "commit": "f4d7ed772a62a95111db50fbcad2460833e8c882",
      "tree": "1f8a76662bad72bd78a59355088f1a9205ef3cf0",
      "parents": [
        "c7cf1374cf284c0c73024cd1437becea75558bf8"
      ],
      "author": {
        "name": "Adam Reeve",
        "email": "adreeve@gmail.com",
        "time": "Tue Jan 14 00:43:53 2025 +1300"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Mon Jan 13 19:43:53 2025 +0800"
      },
      "message": "GH-45185: Add bad_data file with invalid repetition levels (#67)\n\n* Add example file with bad repetition levels\r\n\r\n* Simplify and improve test file\r\n\r\n* Reduce row count\r\n* Use int32 values\r\n* Disable dictionary encoding and statistics\r\n* Use correct list structure with logical type annotation"
    },
    {
      "commit": "c7cf1374cf284c0c73024cd1437becea75558bf8",
      "tree": "9be3bc45772a3b6ce496154138f03fe716658633",
      "parents": [
        "4439a223a315cf874746d3b5da25e6a6b2a2b16e"
      ],
      "author": {
        "name": "Adam Reeve",
        "email": "adreeve@gmail.com",
        "time": "Fri Jan 03 15:44:56 2025 +1300"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Fri Jan 03 10:44:56 2025 +0800"
      },
      "message": "Update encryption test files to correct invalid repetition levels (#65)\n\n"
    },
    {
      "commit": "4439a223a315cf874746d3b5da25e6a6b2a2b16e",
      "tree": "30d21641c576ed4425117cbcc091652dc8410414",
      "parents": [
        "2af9e9ad1c034436043867a96169fc65a91cf000"
      ],
      "author": {
        "name": "Ed Seidl",
        "email": "etseidl@users.noreply.github.com",
        "time": "Fri Nov 22 10:21:26 2024 -0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Sat Nov 23 02:21:26 2024 +0800"
      },
      "message": "Add map_no_value.parquet (#63)\n\n* add map_no_value.parquet\r\n\r\n* fix wording\r\n\r\n* add map with all null values, provide code to generate\r\n\r\n* reduce file overhead\r\n\r\n* close code block properly"
    },
    {
      "commit": "2af9e9ad1c034436043867a96169fc65a91cf000",
      "tree": "84e36b7383f59ccf3a58c6b0ac5f50b0c84ded3e",
      "parents": [
        "2fa03fc70787d5764cc03d85ed8d7b6c93683cad"
      ],
      "author": {
        "name": "zuyu",
        "email": "zuyu@users.noreply.github.com",
        "time": "Thu Nov 21 17:21:43 2024 -0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Fri Nov 22 09:21:43 2024 +0800"
      },
      "message": "Remove x permissions in parquet files (#64)\n\n"
    },
    {
      "commit": "2fa03fc70787d5764cc03d85ed8d7b6c93683cad",
      "tree": "ca8284a961916853f1a69805c448a34d85d453e9",
      "parents": [
        "550368ca77b97231efead39251a96bd6f8f08c6e"
      ],
      "author": {
        "name": "Louis FRULEUX",
        "email": "louis.fruleux1@gmail.com",
        "time": "Wed Nov 13 15:22:29 2024 +0100"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Nov 13 22:22:29 2024 +0800"
      },
      "message": "Update test data name to reflect actual file name (#62)\n\n"
    },
    {
      "commit": "550368ca77b97231efead39251a96bd6f8f08c6e",
      "tree": "9e39598f1f20f87b13802e7d04ec7265c3d02091",
      "parents": [
        "a7f1d288e693dbb08e3199851c4eb2140ff8dff2"
      ],
      "author": {
        "name": "Ze\u0027ev Maor",
        "email": "zeevm@users.noreply.github.com",
        "time": "Thu Oct 31 16:32:17 2024 +0200"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Oct 31 22:32:17 2024 +0800"
      },
      "message": "Add repeated_primitive_no_list.parquet (#61)\n\n"
    },
    {
      "commit": "a7f1d288e693dbb08e3199851c4eb2140ff8dff2",
      "tree": "2918a97201566637d8dc40717c86931a8847f77f",
      "parents": [
        "50af3d8ce206990d81014b1862e5ce7380dc3e08"
      ],
      "author": {
        "name": "Gang Wu",
        "email": "ustcwg@gmail.com",
        "time": "Thu Oct 24 12:48:00 2024 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Oct 24 12:48:00 2024 +0800"
      },
      "message": "Add file with nesting two-level list structure (#60)\n\n* Add file with nesting two-level list structure\r\n\r\n* add description to md"
    },
    {
      "commit": "50af3d8ce206990d81014b1862e5ce7380dc3e08",
      "tree": "86d3b1133703df900d0a26f8b99f7c45473070ec",
      "parents": [
        "cb7a9674142c137367bf75a01b79c6e214a73199"
      ],
      "author": {
        "name": "Anthony De Bortoli",
        "email": "anthony.debortoli@protonmail.com",
        "time": "Fri Aug 23 19:31:53 2024 +0200"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Sat Aug 24 01:31:53 2024 +0800"
      },
      "message": "Add test data for RLE with bit_width \u003d\u003d 0 (#57)\n\n* Add test data for crash in go file reader\r\n\r\n* Rename test data filename\r\n\r\n* add description\r\n\r\n---------\r\n\r\nCo-authored-by: mwish \u003cmaplewish117@gmail.com\u003e"
    },
    {
      "commit": "cb7a9674142c137367bf75a01b79c6e214a73199",
      "tree": "d547a49cc72c15ee5b191eb74a6c5da995d2709e",
      "parents": [
        "89ec47ee5fae5a8d865ca3321b4f9a3b209a53c2"
      ],
      "author": {
        "name": "Jinpeng",
        "email": "zjpzlz@163.com",
        "time": "Thu Aug 15 03:00:42 2024 -0700"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Aug 15 18:00:42 2024 +0800"
      },
      "message": "adding some bad parquet files (#58)\n\n* adding some bad parquet files\r\n\r\n* move to bad-data\r\n\r\n* fmt?\r\n\r\n---------\r\n\r\nCo-authored-by: jp0317 \u003czjpzlz@gmail.com\u003e\r\nCo-authored-by: mwish \u003cmaplewish117@gmail.com\u003e"
    },
    {
      "commit": "89ec47ee5fae5a8d865ca3321b4f9a3b209a53c2",
      "tree": "7a4493d97a632046d11bea563ec5d954085ec94a",
      "parents": [
        "45b737f49dc2bc707292983d8865263dd7e19f54"
      ],
      "author": {
        "name": "Even Rouault",
        "email": "even.rouault@spatialys.com",
        "time": "Thu Aug 15 10:42:19 2024 +0200"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Aug 15 16:42:19 2024 +0800"
      },
      "message": "Add corrupted files in bad_data (#48)\n\n* Add arrow_issue_41321.parquet\r\n\r\n* Add arrow_issue_41317.parquet\r\n\r\n* resolve comment\r\n\r\n---------\r\n\r\nCo-authored-by: mwish \u003cmaplewish117@gmail.com\u003e"
    },
    {
      "commit": "45b737f49dc2bc707292983d8865263dd7e19f54",
      "tree": "b4092b4c94a36e576fcc67c7f70e1bb8fc3a5ece",
      "parents": [
        "9b48ff4f94dc5e89592d46a119884dbb88100884"
      ],
      "author": {
        "name": "mwish",
        "email": "maplewish117@gmail.com",
        "time": "Wed Aug 14 00:56:36 2024 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Aug 14 00:56:36 2024 +0800"
      },
      "message": "Add test file with sorting columns (#56)\n\n* Add file with sorting columns\r\n\r\n* change to 2 row-groups\r\n\r\n* Update data/README.md\r\n\r\nCo-authored-by: Gang Wu \u003custcwg@gmail.com\u003e\r\n\r\n---------\r\n\r\nCo-authored-by: Gang Wu \u003custcwg@gmail.com\u003e"
    },
    {
      "commit": "9b48ff4f94dc5e89592d46a119884dbb88100884",
      "tree": "d2b31e26e2af5837b05cdd44475ca15bb6418e36",
      "parents": [
        "1bf4bd39df2135d132451c281754268f03dc1c0e"
      ],
      "author": {
        "name": "Chungmin Lee",
        "email": "cmlee650@gmail.com",
        "time": "Sun Jul 21 00:43:59 2024 -0700"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Sun Jul 21 15:43:59 2024 +0800"
      },
      "message": "Add a Parquet file with column chunk key-value metadata (#49)\n\n* Add a Parquet file with column chunk key-value metadata\r\n\r\nThis file has a single row group with 0 row and 1 column. The column\r\nchunk has key-value metadata, with a key \"foo\" mapped to a value \"bar\".\r\n\r\nCreated with this code:\r\n\r\n```c++\r\nPARQUET_ASSIGN_OR_THROW(\r\n    auto sink, arrow::io::FileOutputStream::Open(\r\n                   \"column-chunk-key-value-metadata.parquet\"));\r\nparquet::ParquetFileWriter::Open(\r\n    sink, std::static_pointer_cast\u003cparquet::schema::GroupNode\u003e(\r\n              parquet::schema::GroupNode::Make(\r\n                  \"schema\", parquet::Repetition::REQUIRED,\r\n                  {parquet::schema::PrimitiveNode::Make(\r\n                      \"column1\", parquet::Repetition::OPTIONAL,\r\n                      parquet::Type::INT32)})))\r\n    -\u003eAppendRowGroup()\r\n    -\u003eNextColumn()\r\n    -\u003ekey_value_metadata()\r\n    .Append(\"foo\", \"bar\");\r\n```\r\n\r\n* Rename to match the prevalent style\r\n\r\n* Make it 2 columns\r\n\r\n* Update data/README.md\r\n\r\n* Add a KeyValue entry without Value\r\n\r\n* Update data/README.md\r\n\r\nCo-authored-by: mwish \u003cmaplewish117@gmail.com\u003e\r\n\r\n* Update README.md\r\n\r\n* Update README.md\r\n\r\n---------\r\n\r\nCo-authored-by: mwish \u003cmaplewish117@gmail.com\u003e"
    },
    {
      "commit": "1bf4bd39df2135d132451c281754268f03dc1c0e",
      "tree": "5fee89ed84560fe91dd23ae3248fbe796f1fe62b",
      "parents": [
        "1ba34478f535c89382263c42c675a9af4f57f2dd"
      ],
      "author": {
        "name": "Gang Wu",
        "email": "ustcwg@gmail.com",
        "time": "Fri Jun 21 10:06:21 2024 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Fri Jun 21 10:06:21 2024 +0800"
      },
      "message": "Add .asf.yaml to enable Github issues and redirect notifications (#50)\n\n"
    },
    {
      "commit": "1ba34478f535c89382263c42c675a9af4f57f2dd",
      "tree": "cc568aed9744159cc2bf6b0065c8c5f518ec77a9",
      "parents": [
        "74278bc4a1122d74945969e6dec405abd1533ec3"
      ],
      "author": {
        "name": "Pieter Raubenheimer",
        "email": "pieter@wavana.com",
        "time": "Tue Apr 16 15:30:45 2024 +0100"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Tue Apr 16 16:30:45 2024 +0200"
      },
      "message": "File containing a Map schema without explicitly required key (#47)\n\n"
    },
    {
      "commit": "74278bc4a1122d74945969e6dec405abd1533ec3",
      "tree": "8681091bbade825ce036d5adf4732bf7e7983362",
      "parents": [
        "4cb3cff24c965fb329cdae763eabce47395a68a0"
      ],
      "author": {
        "name": "Antoine Pitrou",
        "email": "antoine@python.org",
        "time": "Mon Mar 18 11:42:46 2024 +0100"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Mon Mar 18 11:42:46 2024 +0100"
      },
      "message": "PARQUET-2414: Add test file for additional BYTE_STREAM_SPLIT types (#46)\n\nAdd a new data file that allows exercising BYTE_STREAM_SPLIT for all supported types:\r\nFLOAT, DOUBLE, INT32, INT64, FIXED_LEN_BYTE_ARRAY (the latter with several widths and logical types).\r\n\r\nFor each type, two columns are provided with the same values: one PLAIN-encoded, the other BYTE_STREAM_SPLIT-encoded.\r\n"
    },
    {
      "commit": "4cb3cff24c965fb329cdae763eabce47395a68a0",
      "tree": "565ef60dd3d2742452678a663944a52ef1b06b5e",
      "parents": [
        "d69d979223e883faef9dc6fe3cf573087243c28a"
      ],
      "author": {
        "name": "Martin",
        "email": "m.w.loncaric0@gmail.com",
        "time": "Tue Jan 09 09:26:11 2024 -0500"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Tue Jan 09 15:26:11 2024 +0100"
      },
      "message": "Add BYTE_STREAM_SPLIT data file (#45)\n\n\r\n---------\r\n\r\nCo-authored-by: Antoine Pitrou \u003cpitrou@free.fr\u003e"
    },
    {
      "commit": "d69d979223e883faef9dc6fe3cf573087243c28a",
      "tree": "4a75722650ab28ef9978f44c22bfc03b6a154f5a",
      "parents": [
        "da467dac2f095b979af37bcf40fa0d1dee5ff652"
      ],
      "author": {
        "name": "mwish",
        "email": "maplewish117@gmail.com",
        "time": "Fri Nov 24 00:41:57 2023 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Nov 23 17:41:57 2023 +0100"
      },
      "message": "Add bloom-filter with length (#43)\n\n\r\n\r\n---------\r\n\r\nCo-authored-by: Gang Wu \u003custcwg@gmail.com\u003e\r\nCo-authored-by: Antoine Pitrou \u003cpitrou@free.fr\u003e"
    },
    {
      "commit": "da467dac2f095b979af37bcf40fa0d1dee5ff652",
      "tree": "2c253f3e8eff0e42a32e3bf5999ed560ac96c5ad",
      "parents": [
        "89b685a64c3117b3023d8684af1f41400841db71",
        "ee03e10e7749f2909ecfa574dbb8c212995d92fa"
      ],
      "author": {
        "name": "Gang Wu",
        "email": "ustcwg@gmail.com",
        "time": "Wed Nov 22 09:17:20 2023 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Nov 22 09:17:20 2023 +0800"
      },
      "message": "Regenerate Float16 files without compression (#42)\n\n"
    },
    {
      "commit": "ee03e10e7749f2909ecfa574dbb8c212995d92fa",
      "tree": "2c253f3e8eff0e42a32e3bf5999ed560ac96c5ad",
      "parents": [
        "89b685a64c3117b3023d8684af1f41400841db71"
      ],
      "author": {
        "name": "benibus",
        "email": "bpharks@gmx.com",
        "time": "Tue Nov 21 15:20:39 2023 -0500"
      },
      "committer": {
        "name": "benibus",
        "email": "bpharks@gmx.com",
        "time": "Tue Nov 21 15:20:39 2023 -0500"
      },
      "message": "Regenerate without compression\n"
    },
    {
      "commit": "89b685a64c3117b3023d8684af1f41400841db71",
      "tree": "4a8ddc4012bce26d2890725da9c226c7729fefa7",
      "parents": [
        "506afff9b6957ffe10d08470d467867d43e1bb91"
      ],
      "author": {
        "name": "Atheel Massalha",
        "email": "147729443+amassalha@users.noreply.github.com",
        "time": "Wed Nov 15 12:17:46 2023 +0200"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Nov 15 11:17:46 2023 +0100"
      },
      "message": "PARQUET-2369: Add new test file concatenated_gzip_members.parquet (#41)\n\n* Add new test file concatenated_gzip_members.parquet\r\n\r\n* Update README.md"
    },
    {
      "commit": "506afff9b6957ffe10d08470d467867d43e1bb91",
      "tree": "00d827e4846e6ed86c1a697fb602291effe0bc3e",
      "parents": [
        "e45cd23f784aab3d6bf0701f8f4e621469ed3be7"
      ],
      "author": {
        "name": "Ben Harkins",
        "email": "60872452+benibus@users.noreply.github.com",
        "time": "Thu Nov 09 11:54:37 2023 -0500"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Nov 09 17:54:37 2023 +0100"
      },
      "message": "PARQUET-758: Add files with Float16 column (#40)\n\n\r\n---------\r\n\r\nCo-authored-by: Antoine Pitrou \u003cpitrou@free.fr\u003e"
    },
    {
      "commit": "e45cd23f784aab3d6bf0701f8f4e621469ed3be7",
      "tree": "c72b415f22c25fad386676fcf8c1e9b83ff774e4",
      "parents": [
        "d79a0101d90dfa3bbb10337626f57a3e8c4b5363"
      ],
      "author": {
        "name": "Gang Wu",
        "email": "ustcwg@gmail.com",
        "time": "Tue Sep 26 00:06:41 2023 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Mon Sep 25 18:06:41 2023 +0200"
      },
      "message": "Replace encrypted files with page index enabled (#39)\n\n---------\r\n\r\nCo-authored-by: Antoine Pitrou \u003cantoine@python.org\u003e"
    },
    {
      "commit": "d79a0101d90dfa3bbb10337626f57a3e8c4b5363",
      "tree": "c8369c0ed6bc7c1b655e2e5b5b8963c0dc22b7c7",
      "parents": [
        "b2e7cc755159196e3a068c8594f7acbaecfdaaac"
      ],
      "author": {
        "name": "Arthur Passos",
        "email": "arthur.ti@outlook.com",
        "time": "Wed Jun 21 14:01:14 2023 -0300"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Jun 21 19:01:14 2023 +0200"
      },
      "message": "Add large_string_map data file (#38)\n\n* add chunked_string_map data file\r\n\r\n* use BROTLI compression for greater space saving\r\n\r\n* add description\r\n\r\n* correct arrow type name\r\n\r\n* rename file as suggested by reviewers\r\n\r\n* update readme as suggested\r\n\r\n* rename in docs as well\r\n\r\n* Make wording more precise, remove Arrow vocabulary\r\n\r\n* Add description of how the file was generated\r\n\r\n* Add link to paragraph\r\n\r\n---------\r\n\r\nCo-authored-by: Antoine Pitrou \u003cpitrou@free.fr\u003e"
    },
    {
      "commit": "b2e7cc755159196e3a068c8594f7acbaecfdaaac",
      "tree": "8fe358fd93a03a0de6c7b044989abaf751efb8e5",
      "parents": [
        "4aec91f0c26c39a5946db50f615d06b954810032"
      ],
      "author": {
        "name": "mwish",
        "email": "maplewish117@gmail.com",
        "time": "Thu Feb 23 01:06:25 2023 +0800"
      },
      "committer": {
        "name": "Gang Wu",
        "email": "ustcwg@gmail.com",
        "time": "Mon Mar 06 19:29:32 2023 +0800"
      },
      "message": "Add test files for dictionary page crc\n"
    },
    {
      "commit": "4aec91f0c26c39a5946db50f615d06b954810032",
      "tree": "a342cc71d3ec9001a841617e2252a839d1fd2ea6",
      "parents": [
        "33b4e23376c28e489c6a08b9207829b29e4bffb8",
        "be74fc0873381110e8a1f69f321cee81bd3f2f60"
      ],
      "author": {
        "name": "ggershinsky",
        "email": "ggershinsky@users.noreply.github.com",
        "time": "Sat Feb 18 09:16:14 2023 +0200"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Sat Feb 18 09:16:14 2023 +0200"
      },
      "message": "Merge pull request #36 from adamreeve/java_external_key_material\n\nGH-25986: Add file encrypted using parquet-mr with external key material"
    },
    {
      "commit": "be74fc0873381110e8a1f69f321cee81bd3f2f60",
      "tree": "a342cc71d3ec9001a841617e2252a839d1fd2ea6",
      "parents": [
        "33b4e23376c28e489c6a08b9207829b29e4bffb8"
      ],
      "author": {
        "name": "Adam Reeve",
        "email": "adreeve@gmail.com",
        "time": "Tue Feb 14 16:35:10 2023 +1300"
      },
      "committer": {
        "name": "Adam Reeve",
        "email": "adreeve@gmail.com",
        "time": "Tue Feb 14 17:33:41 2023 +1300"
      },
      "message": "Add test file encrypted with external key material\n"
    },
    {
      "commit": "33b4e23376c28e489c6a08b9207829b29e4bffb8",
      "tree": "fe22b586610f55435958c25518a968bcc82dcfa7",
      "parents": [
        "e2d244ab9a84d382e3a50f55db41f362e450428b"
      ],
      "author": {
        "name": "Will Jones",
        "email": "willjones127@gmail.com",
        "time": "Mon Jan 30 02:21:59 2023 -0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Mon Jan 30 11:21:59 2023 +0100"
      },
      "message": "Add file with NaN in statistics (#35)\n\n* add file with NaN in statistics\r\n\r\n* copy down relevant rules into readme\r\n\r\n* add more explination"
    },
    {
      "commit": "e2d244ab9a84d382e3a50f55db41f362e450428b",
      "tree": "0f33444c09741c1e810729d1b54f8ab3dcb5f1e3",
      "parents": [
        "5b82793ef7196f7b3583e85669ced211cd8b5ff2"
      ],
      "author": {
        "name": "mwish",
        "email": "maplewish117@gmail.com",
        "time": "Thu Jan 26 00:39:16 2023 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Jan 25 17:39:16 2023 +0100"
      },
      "message": "GH-15164: Add new bloom filter example for current spec (#34)\n\nCo-authored-by: Antoine Pitrou \u003cpitrou@free.fr\u003e"
    },
    {
      "commit": "5b82793ef7196f7b3583e85669ced211cd8b5ff2",
      "tree": "3cd2c1b1a374a546056dba46c845c83174503996",
      "parents": [
        "8a3d3fd5ff7691ee07ca9802df66290a3106e4b7"
      ],
      "author": {
        "name": "mwish",
        "email": "1506118561@qq.com",
        "time": "Wed Jan 11 23:23:51 2023 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Jan 11 16:23:51 2023 +0100"
      },
      "message": "Add parquet file with rowgroup having larger than INT16_MAX pages (#33)\n\n"
    },
    {
      "commit": "8a3d3fd5ff7691ee07ca9802df66290a3106e4b7",
      "tree": "dbe9f8ce88d2d6683258de8b7bba45d14cc47ec1",
      "parents": [
        "de7570a865af017add78432e4c045912c213ae24"
      ],
      "author": {
        "name": "Gang Wu",
        "email": "ustcwg@gmail.com",
        "time": "Tue Dec 13 20:18:06 2022 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Tue Dec 13 13:18:06 2022 +0100"
      },
      "message": "ARROW-18420: Add fint32_with_null_pages.parquet for page index test (#32)\n\n"
    },
    {
      "commit": "de7570a865af017add78432e4c045912c213ae24",
      "tree": "cc1e52edc5f7dfb2293d6094c2b1b44dac21446d",
      "parents": [
        "3510fa8d34ba577f36f399d4642f9e1ccdf18b30"
      ],
      "author": {
        "name": "Gang Wu",
        "email": "ustcwg@gmail.com",
        "time": "Fri Dec 09 00:44:17 2022 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Dec 08 17:44:17 2022 +0100"
      },
      "message": "ARROW-18420: Add fixed_length_byte_array.parquet for page index test (#31)\n\n"
    },
    {
      "commit": "3510fa8d34ba577f36f399d4642f9e1ccdf18b30",
      "tree": "caf777c63de8d69385d07722a84837191a3802fc",
      "parents": [
        "e13af117de7c4f0a4d9908ae3827b3ab119868f3"
      ],
      "author": {
        "name": "mwish",
        "email": "1506118561@qq.com",
        "time": "Mon Dec 05 23:20:57 2022 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Mon Dec 05 16:20:57 2022 +0100"
      },
      "message": "ARROW-17904: [Parquet] Add data files with checksums on datapage v1 (#29)\n\n"
    },
    {
      "commit": "e13af117de7c4f0a4d9908ae3827b3ab119868f3",
      "tree": "3f8b822541006040324278cac42506ae02e85980",
      "parents": [
        "19fcd4d5e8a6bc66a8ba7c37b05eb3e698e73c2b"
      ],
      "author": {
        "name": "Nishanth Thimmegowda",
        "email": "nishanth.thimmegowda@snowflake.com",
        "time": "Thu Sep 29 00:50:24 2022 -0700"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Sep 29 09:50:24 2022 +0200"
      },
      "message": "PARQUET-2187: Update rle_boolean_encoding file with more rows\n\nThe previous file with RLE encoding with boolean type had only 7 rows, which did not use `rle-run` part of the encoded data\r\n\r\nRLE encoding has a combination of` \u003cbit-packed-run\u003e` and ` \u003crle-run\u003e` . [RLE encoding ](https://parquet.apache.org/docs/file-format/data-pages/encodings/#a-namerlearun-length-encoding--bit-packing-hybrid-rle--3)\r\n\r\n`run :\u003d \u003cbit-packed-run\u003e | \u003crle-run\u003e`\r\n\r\nReplacing with a new file with more data (68 rows) , produced by the following statement. This ensures we will have coverage for both `bit-packed` decoding and `rle-run` decoding\r\n\r\nCreate with Athena. \r\n\r\ninsert into  boolean_datatype_athena VALUES (true), (false), (null), (true), (true), (false), (false), (true) ,  (true), (true), (false), (false), (true),\r\n (true), (false), (null), (true), (true), (false), (false), (true) , (true), (false), (null), (true), (true), (false), (false), (true) ,  (true), (true), (false), (false) , (false), (false), (true) , (true), (false), (null), (true), (true), (false), (false), (true) ,  (true), (true), (false), (false), (null), (true), (true), (false), (false), (true) ,  (true), (true) ,(false), (true) , (true), (false), (null), (true), (true), (false), (false), (true) ,  (true), (true)  ;"
    },
    {
      "commit": "19fcd4d5e8a6bc66a8ba7c37b05eb3e698e73c2b",
      "tree": "52f9bc9a7087e0e9490c993ef96c27627dd179c7",
      "parents": [
        "a11fc8f148f8a7a89d9281cc0da3eb9d56095fbf"
      ],
      "author": {
        "name": "Muthunagappan Muthuraman",
        "email": "m.muthuraman@snowflake.com",
        "time": "Tue Sep 27 14:13:17 2022 +0530"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Tue Sep 27 10:43:17 2022 +0200"
      },
      "message": "Fix CRC checksum on data_length_byte_array.parquet\n\nFollowup to PR #24"
    },
    {
      "commit": "a11fc8f148f8a7a89d9281cc0da3eb9d56095fbf",
      "tree": "98a16fd14d09cc45fc14748ec017686b5430792d",
      "parents": [
        "aafd3fc9df431c2625a514fb46626e5614f1d199"
      ],
      "author": {
        "name": "Nishanth Thimmegowda",
        "email": "nishanth.thimmegowda@snowflake.com",
        "time": "Wed Sep 14 05:38:26 2022 -0700"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Sep 14 14:38:26 2022 +0200"
      },
      "message": " PARQUET-2187: Add RLE encoding with boolean columns parquet file (#26)\n\n"
    },
    {
      "commit": "aafd3fc9df431c2625a514fb46626e5614f1d199",
      "tree": "71e6c2ec5328d87eea91d863513e452d6836a066",
      "parents": [
        "b76cde43bad62ebf531ae3736d7a59cf645d3a6f"
      ],
      "author": {
        "name": "Yang Jiang",
        "email": "jiangyang381@163.com",
        "time": "Mon Jul 04 22:32:23 2022 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Mon Jul 04 10:32:23 2022 -0400"
      },
      "message": "add test file for page index filter. (#25)\n\n* add test file for page index filter.\r\n\r\n* add link"
    },
    {
      "commit": "b76cde43bad62ebf531ae3736d7a59cf645d3a6f",
      "tree": "33fb6502106486b59629165b18e63b26ab8b89a6",
      "parents": [
        "7175a471339704c7645af0fe66c68305e2e6759c"
      ],
      "author": {
        "name": "Muthunagappan Muthuraman",
        "email": "m.muthuraman@snowflake.com",
        "time": "Wed Jun 22 08:45:10 2022 -0700"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Jun 22 10:45:10 2022 -0500"
      },
      "message": "Test file for DELTA_LENGTH_BYTE_ARRAY decoding (#24)\n\n* Test file for DELTA_LENGTH_BYTE_ARRAY decoding\r\n\r\n* Update README"
    },
    {
      "commit": "7175a471339704c7645af0fe66c68305e2e6759c",
      "tree": "10e4f4c93fc805a868e79a0b37e2e73c5a269862",
      "parents": [
        "3edb72ae36305b24bf45dde4af41c92e54be85cf"
      ],
      "author": {
        "name": "Navin",
        "email": "navin@novemberkilo.com",
        "time": "Tue Mar 22 03:52:20 2022 +1100"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Mon Mar 21 17:52:20 2022 +0100"
      },
      "message": "Add empty file with list data (#23)\n\n* Adds emptylist.\r\n\r\n* Add description of null_list.wq"
    },
    {
      "commit": "3edb72ae36305b24bf45dde4af41c92e54be85cf",
      "tree": "70e1db88b1faf88381923738f03095356d6cd9ff",
      "parents": [
        "acd375eb86a81cd856476fca0f52ba6036a067ff"
      ],
      "author": {
        "name": "Shani Solomon",
        "email": "84128749+shanisolomon@users.noreply.github.com",
        "time": "Tue Feb 15 17:34:14 2022 +0200"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Tue Feb 15 16:34:14 2022 +0100"
      },
      "message": "Add parquet file with optional metadata (#22)\n\nCo-authored-by: Shani Solomon \u003c84128749+shaniso-microsoft@users.noreply.github.com\u003e"
    },
    {
      "commit": "acd375eb86a81cd856476fca0f52ba6036a067ff",
      "tree": "da014c39d4aa6f3cda58f2ea03739fdfecb06426",
      "parents": [
        "d4d485956a643c693b5549e1a62d52ca61c170f1"
      ],
      "author": {
        "name": "Shan Huang",
        "email": "85105837+shanhuuang@users.noreply.github.com",
        "time": "Fri Dec 31 01:53:02 2021 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Thu Dec 30 18:53:02 2021 +0100"
      },
      "message": "ARROW-15184: Add delta-encoded Parquet files with and without nulls (#21)\n\n"
    },
    {
      "commit": "d4d485956a643c693b5549e1a62d52ca61c170f1",
      "tree": "66c786a26deffc6cbcf3b562aacd272214e2af10",
      "parents": [
        "600d437de0e8b0e9927c87e76f844a1b385b02e8"
      ],
      "author": {
        "name": "Shan Huang",
        "email": "85105837+shanhuuang@users.noreply.github.com",
        "time": "Wed Sep 08 21:40:58 2021 +0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Sep 08 15:40:58 2021 +0200"
      },
      "message": "PARQUET-492: Add file of DELTA_BYTE_ARRAY encoding. (#20)\n\n* PARQUET-492: Add file of DELTA_BYTE_ARRAY encoding.\r\n\r\n* Make the file smaller. Each column has 1000 rows."
    },
    {
      "commit": "600d437de0e8b0e9927c87e76f844a1b385b02e8",
      "tree": "96ad26cdff311db229210e14e560d033a69c156d",
      "parents": [
        "ec600191d31a4c567c0c96bb0b2ae6449412460d"
      ],
      "author": {
        "name": "Antoine Pitrou",
        "email": "antoine@python.org",
        "time": "Thu Aug 19 12:39:00 2021 +0200"
      },
      "committer": {
        "name": "Antoine Pitrou",
        "email": "pitrou@free.fr",
        "time": "Thu Aug 19 12:42:34 2021 +0200"
      },
      "message": "Include some comments about the data\n"
    },
    {
      "commit": "ec600191d31a4c567c0c96bb0b2ae6449412460d",
      "tree": "ff336df3317f8368a9900e81e14fbb1d0685896f",
      "parents": [
        "897975e44b0cc4d10206fe3998650ed109e5ef7e"
      ],
      "author": {
        "name": "shanhuuang",
        "email": "shanhuuang@gmail.com",
        "time": "Thu Aug 19 13:57:47 2021 +0800"
      },
      "committer": {
        "name": "Antoine Pitrou",
        "email": "pitrou@free.fr",
        "time": "Thu Aug 19 12:42:34 2021 +0200"
      },
      "message": "Generate new files with 200 rows of data.\n"
    },
    {
      "commit": "897975e44b0cc4d10206fe3998650ed109e5ef7e",
      "tree": "f64da85228b0677a6cf01aab91accb29f2f49aa6",
      "parents": [
        "ddd898958803cb89b7156c6350584d1cda0fe8de"
      ],
      "author": {
        "name": "pincheng.hs",
        "email": "pincheng.hs@alibaba-inc.com",
        "time": "Wed Jun 30 20:05:52 2021 +0800"
      },
      "committer": {
        "name": "Antoine Pitrou",
        "email": "pitrou@free.fr",
        "time": "Thu Aug 19 12:42:34 2021 +0200"
      },
      "message": "ARROW-13206: Add file of DELTA_BINARY_PACKED encoding\n\ndelta_binary_packed.parquet is generated with parquet-mr version 1.10.0\nThe file contents are in delta_binary_packed_expect.csv\n"
    },
    {
      "commit": "ddd898958803cb89b7156c6350584d1cda0fe8de",
      "tree": "3b77c9a42120611504e7bdbb42cb8a4f4afbc43a",
      "parents": [
        "8e7badc6a3817a02e06d17b5d8ab6b6dc356e890"
      ],
      "author": {
        "name": "Antoine Pitrou",
        "email": "antoine@python.org",
        "time": "Tue Mar 23 16:29:57 2021 +0100"
      },
      "committer": {
        "name": "Antoine Pitrou",
        "email": "pitrou@free.fr",
        "time": "Thu Apr 22 17:04:15 2021 +0200"
      },
      "message": "PARQUET-1998: Add LZ_RAW compressed files\n\nThe files were generated with Parquet C++.\n\n* `lz4_raw_compressed.parquet` contains the same data as `hadoop_lz4_compressed.parquet`.\n* `lz4_raw_compressed_larger.parquet` contains the same data as `hadoop_lz4_compressed_larger.parquet`.\n\nHere are the file contents for `lz4_raw_compressed.parquet`:\n```\nFile Name: parquet-testing/data/lz4_raw_compressed.parquet\nVersion: 1.0\nCreated By: parquet-cpp version 1.5.1-SNAPSHOT\nTotal rows: 4\nNumber of RowGroups: 1\nNumber of Real Columns: 3\nNumber of Columns: 3\nNumber of Selected Columns: 3\nColumn 0: c0 (INT64)\nColumn 1: c1 (BYTE_ARRAY)\nColumn 2: v11 (DOUBLE)\n--- Row Group: 0 ---\n--- Total Bytes: 251 ---\n--- Total Compressed Bytes: 238 ---\n--- Rows: 4 ---\nColumn 0\n  Values: 4, Null Values: 0, Distinct Values: 0\n  Max: 1593604801, Min: 1593604800\n  Compression: LZ4_RAW, Encodings: PLAIN RLE\n  Uncompressed Size: 93, Compressed Size: 85\nColumn 1\n  Values: 4, Null Values: 0, Distinct Values: 0\n  Max: def, Min: abc\n  Compression: LZ4_RAW, Encodings: PLAIN RLE\n  Uncompressed Size: 59, Compressed Size: 58\nColumn 2\n  Values: 4, Null Values: 0, Distinct Values: 0\n  Max: 42.125, Min: 7.7\n  Compression: LZ4_RAW, Encodings: PLAIN RLE\n  Uncompressed Size: 99, Compressed Size: 95\n--- Values ---\nc0                            |c1                            |v11                           |\n1593604800                    |abc                           |42.000000                     |\n1593604800                    |def                           |7.700000                      |\n1593604801                    |abc                           |42.125000                     |\n1593604801                    |def                           |7.700000                      |\n```\n\nHere are the partial file contents for `lz4_raw_compressed_larger.parquet`:\n```\nFile Name: parquet-testing/data/lz4_raw_compressed_larger.parquet\nVersion: 1.0\nCreated By: parquet-cpp version 1.5.1-SNAPSHOT\nTotal rows: 10000\nNumber of RowGroups: 1\nNumber of Real Columns: 1\nNumber of Columns: 1\nNumber of Selected Columns: 1\nColumn 0: a (BYTE_ARRAY/UTF8)\n--- Row Group: 0 ---\n--- Total Bytes: 400103 ---\n--- Total Compressed Bytes: 380480 ---\n--- Rows: 10000 ---\nColumn 0\n  Values: 10000, Null Values: 0, Distinct Values: 0\n  Max: ffffe6a0-e0c0-4e65-a9d4-f7f4c176aea2, Min: 00087de7-10df-4979-94cf-79279f9745ce\n  Compression: LZ4_RAW, Encodings: PLAIN RLE\n  Uncompressed Size: 400103, Compressed Size: 380480\n--- Values ---\na                             |\nc7ce6bef-d5b0-4863-b199-8ea8c7fb117b|\ne8fb9197-cb9f-4118-b67f-fbfa65f61843|\n885136e1-0aa1-4fdb-8847-63d87b07c205|\nce7b2019-8ebe-4906-a74d-0afa2409e5df|\na9ee2527-821b-4b71-a926-03f73c3fc8b7|\n[...]\n```\n"
    },
    {
      "commit": "8e7badc6a3817a02e06d17b5d8ab6b6dc356e890",
      "tree": "6f2e1e351ad4ca7fc665063fd3560a2e23fbed61",
      "parents": [
        "e31fe1a02c9e9f271e4bfb8002d403c52f1ef8eb"
      ],
      "author": {
        "name": "Max Burke",
        "email": "maxburke@gmail.com",
        "time": "Sun Feb 07 15:58:23 2021 -0800"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Sun Feb 07 17:58:23 2021 -0600"
      },
      "message": "ARROW-11452: Add file for testing ARROW-11452 (#17)\n\n* Add file for testing ARROW-11452\r\n\r\n* rename structs file, and add description\r\n\r\nCo-authored-by: Neville Dipale \u003cnevilledips@gmail.com\u003e"
    },
    {
      "commit": "e31fe1a02c9e9f271e4bfb8002d403c52f1ef8eb",
      "tree": "be0a5a0e1eeba0806bcae08414142f4f463d5d05",
      "parents": [
        "d914f9d289488c7db1759d7a88a4a1b8f062c7dd"
      ],
      "author": {
        "name": "Antoine Pitrou",
        "email": "antoine@python.org",
        "time": "Mon Jan 18 14:07:14 2021 +0100"
      },
      "committer": {
        "name": "Antoine Pitrou",
        "email": "pitrou@free.fr",
        "time": "Mon Jan 18 14:08:54 2021 +0100"
      },
      "message": "ARROW-9177: Add Hadoop-produced LZ4-compressed file with several frames\n\nIt seems than when the decompressed size exceeds 128 kiB, Hadoop compresses the data in several concatenated \"frames\".\n\nData in this file:\n```\nVersion: 1.0\nCreated By: parquet-mr version 1.11.1 (build 765bd5cd7fdef2af1cecd0755000694b992bfadd)\nTotal rows: 10000\nNumber of RowGroups: 1\nNumber of Real Columns: 1\nNumber of Columns: 1\nNumber of Selected Columns: 1\nColumn 0: a (BYTE_ARRAY/UTF8)\n--- Row Group: 0 ---\n--- Total Bytes: 400029 ---\n--- Rows: 10000 ---\nColumn 0\n  Values: 10000, Null Values: 0, Distinct Values: 0\n  Max: ffffe6a0-e0c0-4e65-a9d4-f7f4c176aea2, Min: 00087de7-10df-4979-94cf-79279f9745ce\n  Compression: LZ4_HADOOP, Encodings: BIT_PACKED PLAIN\n  Uncompressed Size: 400029, Compressed Size: 358351\n--- Values ---\na                             |\n[ ... ]\n```\n"
    },
    {
      "commit": "d914f9d289488c7db1759d7a88a4a1b8f062c7dd",
      "tree": "7c173fcb4c769b21e79a3e776be2b5ce399dab49",
      "parents": [
        "60deed44bb750dd584c7307690b450400e916cb6"
      ],
      "author": {
        "name": "Antoine Pitrou",
        "email": "antoine@python.org",
        "time": "Tue Sep 22 16:44:12 2020 +0200"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Tue Sep 22 09:44:12 2020 -0500"
      },
      "message": "PARQUET-1878: Fix legacy LZ4-compressed file (#14)\n\nA Snappy-compressed file was mistakingly uploaded.\r\nReplace it with a \"raw\" LZ4-compressed file (generated by Arrow 0.17.0).\r\nThis is the LZ4 block format without the custom Hadoop header.\r\n\r\n```\r\nVersion: 1.0\r\nCreated By: parquet-cpp version 1.5.1-SNAPSHOT\r\nTotal rows: 4\r\nNumber of RowGroups: 1\r\nNumber of Real Columns: 3\r\nNumber of Columns: 3\r\nNumber of Selected Columns: 3\r\nColumn 0: c0 (INT64)\r\nColumn 1: c1 (BYTE_ARRAY)\r\nColumn 2: v11 (DOUBLE)\r\n--- Row Group: 0 ---\r\n--- Total Bytes: 281 ---\r\n--- Rows: 4 ---\r\nColumn 0\r\n  Values: 4, Null Values: 0, Distinct Values: 0\r\n  Max: 1593604801, Min: 1593604800\r\n  Compression: LZ4_RAW, Encodings: PLAIN_DICTIONARY PLAIN RLE\r\n  Uncompressed Size: 100, Compressed Size: 103\r\nColumn 1\r\n  Values: 4, Null Values: 0, Distinct Values: 0\r\n  Max: def, Min: abc\r\n  Compression: LZ4_RAW, Encodings: PLAIN_DICTIONARY PLAIN RLE\r\n  Uncompressed Size: 68, Compressed Size: 70\r\nColumn 2\r\n  Values: 4, Null Values: 0, Distinct Values: 0\r\n  Max: 42.125, Min: 7.7\r\n  Compression: LZ4_RAW, Encodings: PLAIN_DICTIONARY PLAIN RLE\r\n  Uncompressed Size: 109, Compressed Size: 108\r\n--- Values ---\r\nc0                            |c1                            |v11                           |\r\n1593604800                    |abc                           |42.000000                     |\r\n1593604800                    |def                           |7.700000                      |\r\n1593604801                    |abc                           |42.125000                     |\r\n1593604801                    |def                           |7.700000                      |\r\n```"
    },
    {
      "commit": "60deed44bb750dd584c7307690b450400e916cb6",
      "tree": "f1e9c6628bd24bf3c13feede2825e97cc01cda1f",
      "parents": [
        "40379b3c58298fd22589dec7e41748375b5a8e82",
        "25c8ce4ca16d58c1f3206c0c56e7009f60d9dd0d"
      ],
      "author": {
        "name": "Wes McKinney",
        "email": "wesm@users.noreply.github.com",
        "time": "Wed Aug 05 14:09:04 2020 -0500"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Wed Aug 05 14:09:04 2020 -0500"
      },
      "message": "PARQUET-1878: [C++] lz4 codec is not compatible with Hadoop Lz4Codec (#13)\n\nThis patch adds two parquet files used for testing in https://github.com/apache/arrow/pull/7789\r\n\r\nFile contents (same for both files):\r\n```\r\n$ parquet-tools dump hadoop_snappy_348283e35cc107e1a1f6b1bb00e397fe576bf4bad16ec3216799aa52a7552357.parquet\r\nrow group 0\r\n--------------------------------------------------------------------------------\r\nc0:   INT64 SNAPPY DO:0 FPO:4 SZ:97/93/0.96 VC:4 ENC:PLAIN_DICTIONARY,BIT_PACKED [more]...\r\nc1:   BINARY SNAPPY DO:0 FPO:101 SZ:65/61/0.94 VC:4 ENC:PLAIN_DICTIONA [more]...\r\nv11:  DOUBLE SNAPPY DO:0 FPO:166 SZ:110/108/0.98 VC:4 ENC:RLE,PLAIN_DI [more]...\r\n    c0 TV\u003d4 RL\u003d0 DL\u003d0 DS:  2 DE:PLAIN_DICTIONARY\r\n    ----------------------------------------------------------------------------\r\n    page 0:                 DLE:BIT_PACKED RLE:BIT_PACKED VLE:PLAIN_DICTIONARY [more]... VC:4\r\n    c1 TV\u003d4 RL\u003d0 DL\u003d0 DS:  2 DE:PLAIN_DICTIONARY\r\n    ----------------------------------------------------------------------------\r\n    page 0:                 DLE:BIT_PACKED RLE:BIT_PACKED VLE:PLAIN_DICTIONARY [more]... VC:4\r\n    v11 TV\u003d4 RL\u003d0 DL\u003d1 DS: 3 DE:PLAIN_DICTIONARY\r\n    ----------------------------------------------------------------------------\r\n    page 0:                 DLE:RLE RLE:BIT_PACKED VLE:PLAIN_DICTIONARY [more]... VC:4\r\nINT64 c0\r\n--------------------------------------------------------------------------------\r\n*** row group 1 of 1, values 1 to 4 ***\r\nvalue 1: R:0 D:0 V:1593604800\r\nvalue 2: R:0 D:0 V:1593604800\r\nvalue 3: R:0 D:0 V:1593604801\r\nvalue 4: R:0 D:0 V:1593604801\r\nBINARY c1\r\n--------------------------------------------------------------------------------\r\n*** row group 1 of 1, values 1 to 4 ***\r\nvalue 1: R:0 D:0 V:0x616263\r\nvalue 2: R:0 D:0 V:0x646566\r\nvalue 3: R:0 D:0 V:0x616263\r\nvalue 4: R:0 D:0 V:0x646566\r\nDOUBLE v11\r\n--------------------------------------------------------------------------------\r\n*** row group 1 of 1, values 1 to 4 ***\r\nvalue 1: R:0 D:1 V:42.0\r\nvalue 2: R:0 D:1 V:7.7\r\nvalue 3: R:0 D:1 V:42.125\r\nvalue 4: R:0 D:1 V:7.7\r\n```"
    },
    {
      "commit": "25c8ce4ca16d58c1f3206c0c56e7009f60d9dd0d",
      "tree": "f1e9c6628bd24bf3c13feede2825e97cc01cda1f",
      "parents": [
        "1e8480a770141f3391172580bda1e47a9025ee00"
      ],
      "author": {
        "name": "Patrick Pai",
        "email": "patrick.m.pai@gmail.com",
        "time": "Mon Jul 20 10:30:07 2020 -0500"
      },
      "committer": {
        "name": "Patrick Pai",
        "email": "patrick.m.pai@gmail.com",
        "time": "Mon Jul 20 10:30:07 2020 -0500"
      },
      "message": "add non_hadoop_lz4_compressed.parquet\n"
    },
    {
      "commit": "1e8480a770141f3391172580bda1e47a9025ee00",
      "tree": "6cfa24155211f68b73dd5ce3a4b777d0cf10d92e",
      "parents": [
        "40379b3c58298fd22589dec7e41748375b5a8e82"
      ],
      "author": {
        "name": "Patrick Pai",
        "email": "patrick.m.pai@gmail.com",
        "time": "Thu Jul 16 13:36:40 2020 -0500"
      },
      "committer": {
        "name": "Patrick Pai",
        "email": "patrick.m.pai@gmail.com",
        "time": "Thu Jul 16 15:11:04 2020 -0500"
      },
      "message": "Add hadoop_lz4_compressed.parquet\n"
    },
    {
      "commit": "40379b3c58298fd22589dec7e41748375b5a8e82",
      "tree": "bd78955f204ee6c951f9507e6e974840d5afe351",
      "parents": [
        "bcd9ebcf9204a346df47204fe21b85c8d0498816",
        "98f8510ea180fa17d3d78e40e12d5240c771e0e2"
      ],
      "author": {
        "name": "Fokko Driesprong",
        "email": "fokko@apache.org",
        "time": "Tue May 05 11:43:21 2020 +0200"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Tue May 05 11:43:21 2020 +0200"
      },
      "message": "Merge pull request #11 from urbanlogiq/list_columns\n\nARROW-7842 add tiny parquet with int and utf8 list columns"
    },
    {
      "commit": "bcd9ebcf9204a346df47204fe21b85c8d0498816",
      "tree": "d3684623512ab6ee4faee96c72ba005d7e3e8823",
      "parents": [
        "46c9e977f58f6c5ef1b81f782f3746b3656e5a8c"
      ],
      "author": {
        "name": "andersonm-ibm",
        "email": "63074550+andersonm-ibm@users.noreply.github.com",
        "time": "Mon Apr 06 23:55:45 2020 +0300"
      },
      "committer": {
        "name": "GitHub",
        "email": "noreply@github.com",
        "time": "Mon Apr 06 15:55:45 2020 -0500"
      },
      "message": "PARQUET-1834: Add Apache 2.0 license to README.md files in apache/parquet-testing (#12)\n\n"
    },
    {
      "commit": "98f8510ea180fa17d3d78e40e12d5240c771e0e2",
      "tree": "36f78a1e5ef829d0fc15ac3e8aae1bd8b8b998f7",
      "parents": [
        "46c9e977f58f6c5ef1b81f782f3746b3656e5a8c"
      ],
      "author": {
        "name": "Morgan Cassels",
        "email": "morgan@urbanlogiq.com",
        "time": "Mon Mar 30 16:35:52 2020 -0700"
      },
      "committer": {
        "name": "Morgan Cassels",
        "email": "morgan@urbanlogiq.com",
        "time": "Mon Mar 30 16:35:52 2020 -0700"
      },
      "message": "add tiny parquet with int and utf8 list columns\n"
    },
    {
      "commit": "46c9e977f58f6c5ef1b81f782f3746b3656e5a8c",
      "tree": "6d71dff22fe80af6d289cd322c07a0159962458e",
      "parents": [
        "a277dc4e55ded3e3ea27dab1e4faf98c112442df"
      ],
      "author": {
        "name": "Ádám Lippai",
        "email": "adam@rigo.sk",
        "time": "Thu Sep 26 21:08:53 2019 +0200"
      },
      "committer": {
        "name": "Wes McKinney",
        "email": "wesm@users.noreply.github.com",
        "time": "Thu Sep 26 14:08:53 2019 -0500"
      },
      "message": "ARROW-6687: Add .parquet file with single np.nan value (#9)\n\n"
    },
    {
      "commit": "a277dc4e55ded3e3ea27dab1e4faf98c112442df",
      "tree": "0ad5dd3b36096509035fa4e854dc4518fabb88d3",
      "parents": [
        "2fc3ade4ccbf17271194df0b1549bc6733204314"
      ],
      "author": {
        "name": "revit1976",
        "email": "51282986+revit1976@users.noreply.github.com",
        "time": "Thu Jul 18 19:28:41 2019 +0300"
      },
      "committer": {
        "name": "Wes McKinney",
        "email": "wesm@users.noreply.github.com",
        "time": "Thu Jul 18 11:28:41 2019 -0500"
      },
      "message": "PARQUET-1621: [C++] Add encrypted parquet files to apache parquet-testing repository (#7)\n\n* Add encrypted parquet files to apache parquet-testing repository\r\n\r\n* Update README.md\r\n\r\nAdd encryption keys and explanation to data/README.md\r\n\r\n* Update README.md\r\n\r\nAdditional fixes to encrypted files section.\r\n"
    },
    {
      "commit": "2fc3ade4ccbf17271194df0b1549bc6733204314",
      "tree": "5698901f9127f0c59c4232f20500dac38ac7ae2b",
      "parents": [
        "8991d0b58d5a59925c87dd2a0bdb59a5a4a16bd4"
      ],
      "author": {
        "name": "shyam",
        "email": "shyam@dremio.com",
        "time": "Tue May 21 16:39:03 2019 +0530"
      },
      "committer": {
        "name": "shyam",
        "email": "shyam@dremio.com",
        "time": "Tue May 21 16:39:03 2019 +0530"
      },
      "message": "ARROW-5322 : Parquet files with dictionary page offset as 0 is not readable\n\npyarrow needs to handle dictionary page offset \u003d 0 as a special case to be compatible with java parquet reader.\nAdding a parquet file read by java reader and not by parquet reader.\n"
    },
    {
      "commit": "8991d0b58d5a59925c87dd2a0bdb59a5a4a16bd4",
      "tree": "57227b4d5460b56b743c098833217f00aa7e0f62",
      "parents": [
        "bb7b6abbb3fbeff845646364a4286142127be04c"
      ],
      "author": {
        "name": "Wes McKinney",
        "email": "wesm+git@apache.org",
        "time": "Tue Jan 29 16:25:35 2019 -0600"
      },
      "committer": {
        "name": "Wes McKinney",
        "email": "wesm+git@apache.org",
        "time": "Tue Jan 29 16:25:35 2019 -0600"
      },
      "message": "Add LICENSE.txt (Apache 2.0)\n"
    },
    {
      "commit": "bb7b6abbb3fbeff845646364a4286142127be04c",
      "tree": "6645d2d6ba88828c6e7f65c6d8284b0f3943c68e",
      "parents": [
        "8eb0213c491752c9bbb1b884fcbb21deb548e464"
      ],
      "author": {
        "name": "Ildar Musin",
        "email": "zildermann@gmail.com",
        "time": "Tue Jan 22 11:53:50 2019 +0100"
      },
      "committer": {
        "name": "Ildar Musin",
        "email": "zildermann@gmail.com",
        "time": "Tue Jan 22 11:53:50 2019 +0100"
      },
      "message": "Data file for binary min-max statistics test\n"
    },
    {
      "commit": "8eb0213c491752c9bbb1b884fcbb21deb548e464",
      "tree": "c2ee9a7b56299dd1b81f83496a4b6ef605e97d79",
      "parents": [
        "92a8e6c2efdce1925c605d6313994db2c94478fb"
      ],
      "author": {
        "name": "Wes McKinney",
        "email": "wesm+git@apache.org",
        "time": "Mon Dec 24 16:01:58 2018 -0600"
      },
      "committer": {
        "name": "Wes McKinney",
        "email": "wesm+git@apache.org",
        "time": "Mon Dec 24 16:01:58 2018 -0600"
      },
      "message": "Add bad_data/ directory\n"
    },
    {
      "commit": "92a8e6c2efdce1925c605d6313994db2c94478fb",
      "tree": "37f0486a3af3f52521dc7102e42c5fa131cf1d89",
      "parents": [
        "46ae2605c2de306f5740587107dcf333a527f2d1"
      ],
      "author": {
        "name": "Chao Sun",
        "email": "sunchao@apache.org",
        "time": "Sun Dec 02 11:13:20 2018 -0800"
      },
      "committer": {
        "name": "Wes McKinney",
        "email": "wesm@users.noreply.github.com",
        "time": "Sun Dec 02 13:13:20 2018 -0600"
      },
      "message": "Add additional data files used for testing Rust library (#2)\n\n"
    },
    {
      "commit": "46ae2605c2de306f5740587107dcf333a527f2d1",
      "tree": "962f848ebd842e77e3bc33836579eb0e9f96d0f6",
      "parents": [
        "48a657ca05eb308539f3f00c698e8bb5185d9b38"
      ],
      "author": {
        "name": "thaining",
        "email": "thaining@xcalar.com",
        "time": "Fri Sep 28 02:51:59 2018 -0700"
      },
      "committer": {
        "name": "Wes McKinney",
        "email": "wesm@users.noreply.github.com",
        "time": "Fri Sep 28 11:51:59 2018 +0200"
      },
      "message": "PARQUET-1160: [C++] Implement BYTE_ARRAY-backed Decimal reads (#1)\n\nThis change adds a data file with BYTE_ARRAY-backed decimals for unit testing."
    },
    {
      "commit": "48a657ca05eb308539f3f00c698e8bb5185d9b38",
      "tree": "301acbd3ac4f897b3c537c27338b5eba3690ccc1",
      "parents": [
        "9e22cb52331d8c526600b8c19c4e8c33397d4b63"
      ],
      "author": {
        "name": "Wes McKinney",
        "email": "wesm+git@apache.org",
        "time": "Mon Sep 03 14:08:28 2018 -0400"
      },
      "committer": {
        "name": "Wes McKinney",
        "email": "wesm+git@apache.org",
        "time": "Mon Sep 03 14:08:28 2018 -0400"
      },
      "message": "Add test data files from parquet-cpp\n"
    },
    {
      "commit": "9e22cb52331d8c526600b8c19c4e8c33397d4b63",
      "tree": "f1c9baee721db6be62d1e4fac1400114bc4b89d4",
      "parents": [],
      "author": {
        "name": "Wes McKinney",
        "email": "wesm+git@apache.org",
        "time": "Mon Sep 03 14:07:15 2018 -0400"
      },
      "committer": {
        "name": "Wes McKinney",
        "email": "wesm+git@apache.org",
        "time": "Mon Sep 03 14:07:15 2018 -0400"
      },
      "message": "Initial commit\n"
    }
  ]
}