mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-31 14:34:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update test cases for office formats

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-02-17 11:36:02 +01:00
parent a80d350b38
commit ed6631b60f
5 changed files with 52 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

90
poetry.lock generated
View File

@ -894,7 +894,7 @@ chunking = ["semchunk (>=2.2.0,<3.0.0)", "transformers (>=4.34.0,<5.0.0)"]
type = "git"
url = "https://github.com/DS4SD/docling-core.git"
reference = "dt_cleanup"
resolved_reference = "9502052fbbc9e313cb2597b9c0b3d4d46d11a16f"
resolved_reference = "3667caf9faeae5b3e79772aacc4d63eb54a1438d"
[[package]]
name = "docling-ibm-models"
@ -6094,51 +6094,57 @@ test = ["array-api-strict", "asv", "gmpy2", "hypothesis (>=6.30)", "mpmath", "po
[[package]]
name = "scipy"
version = "1.15.1"
version = "1.15.2"
description = "Fundamental algorithms for scientific computing in Python"
optional = false
python-versions = ">=3.10"
files = [
{file = "scipy-1.15.1-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:c64ded12dcab08afff9e805a67ff4480f5e69993310e093434b10e85dc9d43e1"},
{file = "scipy-1.15.1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:5b190b935e7db569960b48840e5bef71dc513314cc4e79a1b7d14664f57fd4ff"},
{file = "scipy-1.15.1-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:4b17d4220df99bacb63065c76b0d1126d82bbf00167d1730019d2a30d6ae01ea"},
{file = "scipy-1.15.1-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:63b9b6cd0333d0eb1a49de6f834e8aeaefe438df8f6372352084535ad095219e"},
{file = "scipy-1.15.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9f151e9fb60fbf8e52426132f473221a49362091ce7a5e72f8aa41f8e0da4f25"},
{file = "scipy-1.15.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:21e10b1dd56ce92fba3e786007322542361984f8463c6d37f6f25935a5a6ef52"},
{file = "scipy-1.15.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:5dff14e75cdbcf07cdaa1c7707db6017d130f0af9ac41f6ce443a93318d6c6e0"},
{file = "scipy-1.15.1-cp310-cp310-win_amd64.whl", hash = "sha256:f82fcf4e5b377f819542fbc8541f7b5fbcf1c0017d0df0bc22c781bf60abc4d8"},
{file = "scipy-1.15.1-cp311-cp311-macosx_10_13_x86_64.whl", hash = "sha256:5bd8d27d44e2c13d0c1124e6a556454f52cd3f704742985f6b09e75e163d20d2"},
{file = "scipy-1.15.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:be3deeb32844c27599347faa077b359584ba96664c5c79d71a354b80a0ad0ce0"},
{file = "scipy-1.15.1-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:5eb0ca35d4b08e95da99a9f9c400dc9f6c21c424298a0ba876fdc69c7afacedf"},
{file = "scipy-1.15.1-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:74bb864ff7640dea310a1377d8567dc2cb7599c26a79ca852fc184cc851954ac"},
{file = "scipy-1.15.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:667f950bf8b7c3a23b4199db24cb9bf7512e27e86d0e3813f015b74ec2c6e3df"},
{file = "scipy-1.15.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:395be70220d1189756068b3173853029a013d8c8dd5fd3d1361d505b2aa58fa7"},
{file = "scipy-1.15.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:ce3a000cd28b4430426db2ca44d96636f701ed12e2b3ca1f2b1dd7abdd84b39a"},
{file = "scipy-1.15.1-cp311-cp311-win_amd64.whl", hash = "sha256:3fe1d95944f9cf6ba77aa28b82dd6bb2a5b52f2026beb39ecf05304b8392864b"},
{file = "scipy-1.15.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:c09aa9d90f3500ea4c9b393ee96f96b0ccb27f2f350d09a47f533293c78ea776"},
{file = "scipy-1.15.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:0ac102ce99934b162914b1e4a6b94ca7da0f4058b6d6fd65b0cef330c0f3346f"},
{file = "scipy-1.15.1-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:09c52320c42d7f5c7748b69e9f0389266fd4f82cf34c38485c14ee976cb8cb04"},
{file = "scipy-1.15.1-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:cdde8414154054763b42b74fe8ce89d7f3d17a7ac5dd77204f0e142cdc9239e9"},
{file = "scipy-1.15.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4c9d8fc81d6a3b6844235e6fd175ee1d4c060163905a2becce8e74cb0d7554ce"},
{file = "scipy-1.15.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0fb57b30f0017d4afa5fe5f5b150b8f807618819287c21cbe51130de7ccdaed2"},
{file = "scipy-1.15.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:491d57fe89927fa1aafbe260f4cfa5ffa20ab9f1435025045a5315006a91b8f5"},
{file = "scipy-1.15.1-cp312-cp312-win_amd64.whl", hash = "sha256:900f3fa3db87257510f011c292a5779eb627043dd89731b9c461cd16ef76ab3d"},
{file = "scipy-1.15.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:100193bb72fbff37dbd0bf14322314fc7cbe08b7ff3137f11a34d06dc0ee6b85"},
{file = "scipy-1.15.1-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:2114a08daec64980e4b4cbdf5bee90935af66d750146b1d2feb0d3ac30613692"},
{file = "scipy-1.15.1-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:6b3e71893c6687fc5e29208d518900c24ea372a862854c9888368c0b267387ab"},
{file = "scipy-1.15.1-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:837299eec3d19b7e042923448d17d95a86e43941104d33f00da7e31a0f715d3c"},
{file = "scipy-1.15.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:82add84e8a9fb12af5c2c1a3a3f1cb51849d27a580cb9e6bd66226195142be6e"},
{file = "scipy-1.15.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:070d10654f0cb6abd295bc96c12656f948e623ec5f9a4eab0ddb1466c000716e"},
{file = "scipy-1.15.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:55cc79ce4085c702ac31e49b1e69b27ef41111f22beafb9b49fea67142b696c4"},
{file = "scipy-1.15.1-cp313-cp313-win_amd64.whl", hash = "sha256:c352c1b6d7cac452534517e022f8f7b8d139cd9f27e6fbd9f3cbd0bfd39f5bef"},
{file = "scipy-1.15.1-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:0458839c9f873062db69a03de9a9765ae2e694352c76a16be44f93ea45c28d2b"},
{file = "scipy-1.15.1-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:af0b61c1de46d0565b4b39c6417373304c1d4f5220004058bdad3061c9fa8a95"},
{file = "scipy-1.15.1-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:71ba9a76c2390eca6e359be81a3e879614af3a71dfdabb96d1d7ab33da6f2364"},
{file = "scipy-1.15.1-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:14eaa373c89eaf553be73c3affb11ec6c37493b7eaaf31cf9ac5dffae700c2e0"},
{file = "scipy-1.15.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f735bc41bd1c792c96bc426dece66c8723283695f02df61dcc4d0a707a42fc54"},
{file = "scipy-1.15.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:2722a021a7929d21168830790202a75dbb20b468a8133c74a2c0230c72626b6c"},
{file = "scipy-1.15.1-cp313-cp313t-win_amd64.whl", hash = "sha256:bc7136626261ac1ed988dca56cfc4ab5180f75e0ee52e58f1e6aa74b5f3eacd5"},
{file = "scipy-1.15.1.tar.gz", hash = "sha256:033a75ddad1463970c96a88063a1df87ccfddd526437136b6ee81ff0312ebdf6"},
{file = "scipy-1.15.2-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:a2ec871edaa863e8213ea5df811cd600734f6400b4af272e1c011e69401218e9"},
{file = "scipy-1.15.2-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:6f223753c6ea76983af380787611ae1291e3ceb23917393079dcc746ba60cfb5"},
{file = "scipy-1.15.2-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:ecf797d2d798cf7c838c6d98321061eb3e72a74710e6c40540f0e8087e3b499e"},
{file = "scipy-1.15.2-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:9b18aa747da280664642997e65aab1dd19d0c3d17068a04b3fe34e2559196cb9"},
{file = "scipy-1.15.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:87994da02e73549dfecaed9e09a4f9d58a045a053865679aeb8d6d43747d4df3"},
{file = "scipy-1.15.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:69ea6e56d00977f355c0f84eba69877b6df084516c602d93a33812aa04d90a3d"},
{file = "scipy-1.15.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:888307125ea0c4466287191e5606a2c910963405ce9671448ff9c81c53f85f58"},
{file = "scipy-1.15.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:9412f5e408b397ff5641080ed1e798623dbe1ec0d78e72c9eca8992976fa65aa"},
{file = "scipy-1.15.2-cp310-cp310-win_amd64.whl", hash = "sha256:b5e025e903b4f166ea03b109bb241355b9c42c279ea694d8864d033727205e65"},
{file = "scipy-1.15.2-cp311-cp311-macosx_10_13_x86_64.whl", hash = "sha256:92233b2df6938147be6fa8824b8136f29a18f016ecde986666be5f4d686a91a4"},
{file = "scipy-1.15.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:62ca1ff3eb513e09ed17a5736929429189adf16d2d740f44e53270cc800ecff1"},
{file = "scipy-1.15.2-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:4c6676490ad76d1c2894d77f976144b41bd1a4052107902238047fb6a473e971"},
{file = "scipy-1.15.2-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:a8bf5cb4a25046ac61d38f8d3c3426ec11ebc350246a4642f2f315fe95bda655"},
{file = "scipy-1.15.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6a8e34cf4c188b6dd004654f88586d78f95639e48a25dfae9c5e34a6dc34547e"},
{file = "scipy-1.15.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:28a0d2c2075946346e4408b211240764759e0fabaeb08d871639b5f3b1aca8a0"},
{file = "scipy-1.15.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:42dabaaa798e987c425ed76062794e93a243be8f0f20fff6e7a89f4d61cb3d40"},
{file = "scipy-1.15.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:6f5e296ec63c5da6ba6fa0343ea73fd51b8b3e1a300b0a8cae3ed4b1122c7462"},
{file = "scipy-1.15.2-cp311-cp311-win_amd64.whl", hash = "sha256:597a0c7008b21c035831c39927406c6181bcf8f60a73f36219b69d010aa04737"},
{file = "scipy-1.15.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:c4697a10da8f8765bb7c83e24a470da5797e37041edfd77fd95ba3811a47c4fd"},
{file = "scipy-1.15.2-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:869269b767d5ee7ea6991ed7e22b3ca1f22de73ab9a49c44bad338b725603301"},
{file = "scipy-1.15.2-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:bad78d580270a4d32470563ea86c6590b465cb98f83d760ff5b0990cb5518a93"},
{file = "scipy-1.15.2-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:b09ae80010f52efddb15551025f9016c910296cf70adbf03ce2a8704f3a5ad20"},
{file = "scipy-1.15.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5a6fd6eac1ce74a9f77a7fc724080d507c5812d61e72bd5e4c489b042455865e"},
{file = "scipy-1.15.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2b871df1fe1a3ba85d90e22742b93584f8d2b8e6124f8372ab15c71b73e428b8"},
{file = "scipy-1.15.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:03205d57a28e18dfd39f0377d5002725bf1f19a46f444108c29bdb246b6c8a11"},
{file = "scipy-1.15.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:601881dfb761311045b03114c5fe718a12634e5608c3b403737ae463c9885d53"},
{file = "scipy-1.15.2-cp312-cp312-win_amd64.whl", hash = "sha256:e7c68b6a43259ba0aab737237876e5c2c549a031ddb7abc28c7b47f22e202ded"},
{file = "scipy-1.15.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:01edfac9f0798ad6b46d9c4c9ca0e0ad23dbf0b1eb70e96adb9fa7f525eff0bf"},
{file = "scipy-1.15.2-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:08b57a9336b8e79b305a143c3655cc5bdbe6d5ece3378578888d2afbb51c4e37"},
{file = "scipy-1.15.2-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:54c462098484e7466362a9f1672d20888f724911a74c22ae35b61f9c5919183d"},
{file = "scipy-1.15.2-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:cf72ff559a53a6a6d77bd8eefd12a17995ffa44ad86c77a5df96f533d4e6c6bb"},
{file = "scipy-1.15.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9de9d1416b3d9e7df9923ab23cd2fe714244af10b763975bea9e4f2e81cebd27"},
{file = "scipy-1.15.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fb530e4794fc8ea76a4a21ccb67dea33e5e0e60f07fc38a49e821e1eae3b71a0"},
{file = "scipy-1.15.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:5ea7ed46d437fc52350b028b1d44e002646e28f3e8ddc714011aaf87330f2f32"},
{file = "scipy-1.15.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:11e7ad32cf184b74380f43d3c0a706f49358b904fa7d5345f16ddf993609184d"},
{file = "scipy-1.15.2-cp313-cp313-win_amd64.whl", hash = "sha256:a5080a79dfb9b78b768cebf3c9dcbc7b665c5875793569f48bf0e2b1d7f68f6f"},
{file = "scipy-1.15.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:447ce30cee6a9d5d1379087c9e474628dab3db4a67484be1b7dc3196bfb2fac9"},
{file = "scipy-1.15.2-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:c90ebe8aaa4397eaefa8455a8182b164a6cc1d59ad53f79943f266d99f68687f"},
{file = "scipy-1.15.2-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:def751dd08243934c884a3221156d63e15234a3155cf25978b0a668409d45eb6"},
{file = "scipy-1.15.2-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:302093e7dfb120e55515936cb55618ee0b895f8bcaf18ff81eca086c17bd80af"},
{file = "scipy-1.15.2-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7cd5b77413e1855351cdde594eca99c1f4a588c2d63711388b6a1f1c01f62274"},
{file = "scipy-1.15.2-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d0194c37037707b2afa7a2f2a924cf7bac3dc292d51b6a925e5fcb89bc5c776"},
{file = "scipy-1.15.2-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:bae43364d600fdc3ac327db99659dcb79e6e7ecd279a75fe1266669d9a652828"},
{file = "scipy-1.15.2-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:f031846580d9acccd0044efd1a90e6f4df3a6e12b4b6bd694a7bc03a89892b28"},
{file = "scipy-1.15.2-cp313-cp313t-win_amd64.whl", hash = "sha256:fe8a9eb875d430d81755472c5ba75e84acc980e4a8f6204d402849234d3017db"},
{file = "scipy-1.15.2.tar.gz", hash = "sha256:cd58a314d92838f7e6f755c8a2167ead4f27e1fd5c1251fd54289569ef3495ec"},
]
[package.dependencies]

2
tests/data/groundtruth/docling_v2/powerpoint_with_image.pptx.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/test-01.xlsx.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/test_emf_docx.docx.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/word_sample.docx.json
View File

File diff suppressed because one or more lines are too long