install: pdfplumber v0.11.4

pyproject.toml

@@ -27,6 +27,7 @@ dependencies = [
     "mkdocs-glightbox>=0.4.0",
     "mkdocs-jupyter>=0.25.0",
     "jupyter>=1.1.1",
+    "pdfplumber>=0.11.4",
 ]
 
 [project.optional-dependencies]
@@ -34,6 +35,7 @@ core = [
     "Byaldi>=0.0.5",
     "firerequests>=0.0.7",
     "pdf2image>=1.17.0",
+    "pdfplumber>=0.11.4",
     "python-dotenv>=1.0.1",
     "pymupdf4llm>=0.0.17",
     "torch>=2.4.1",

uv.lock

@@ -549,6 +549,39 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e6/75/49e5bfe642f71f272236b5b2d2691cf915a7283cc0ceda56357b61daa538/comm-0.2.2-py3-none-any.whl", hash = "sha256:e6fb86cb70ff661ee8c9c14e7d36d6de3b4066f1441be4063df9c5009f0a64d3", size = 7180 },
 ]
 
+[[package]]
+name = "cryptography"
+version = "43.0.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "cffi", marker = "platform_python_implementation != 'PyPy'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/de/ba/0664727028b37e249e73879348cc46d45c5c1a2a2e81e8166462953c5755/cryptography-43.0.1.tar.gz", hash = "sha256:203e92a75716d8cfb491dc47c79e17d0d9207ccffcbcb35f598fbe463ae3444d", size = 686927 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/58/28/b92c98a04ba762f8cdeb54eba5c4c84e63cac037a7c5e70117d337b15ad6/cryptography-43.0.1-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:8385d98f6a3bf8bb2d65a73e17ed87a3ba84f6991c155691c51112075f9ffc5d", size = 6223222 },
+    { url = "https://files.pythonhosted.org/packages/33/13/1193774705783ba364121aa2a60132fa31a668b8ababd5edfa1662354ccd/cryptography-43.0.1-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:27e613d7077ac613e399270253259d9d53872aaf657471473ebfc9a52935c062", size = 3794751 },
+    { url = "https://files.pythonhosted.org/packages/5e/4b/39bb3c4c8cfb3e94e736b8d8859ce5c81536e91a1033b1d26770c4249000/cryptography-43.0.1-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:68aaecc4178e90719e95298515979814bda0cbada1256a4485414860bd7ab962", size = 3981827 },
+    { url = "https://files.pythonhosted.org/packages/ce/dc/1471d4d56608e1013237af334b8a4c35d53895694fbb73882d1c4fd3f55e/cryptography-43.0.1-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:de41fd81a41e53267cb020bb3a7212861da53a7d39f863585d13ea11049cf277", size = 3780034 },
+    { url = "https://files.pythonhosted.org/packages/ad/43/7a9920135b0d5437cc2f8f529fa757431eb6a7736ddfadfdee1cc5890800/cryptography-43.0.1-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:f98bf604c82c416bc829e490c700ca1553eafdf2912a91e23a79d97d9801372a", size = 3993407 },
+    { url = "https://files.pythonhosted.org/packages/cc/42/9ab8467af6c0b76f3d9b8f01d1cf25b9c9f3f2151f4acfab888d21c55a72/cryptography-43.0.1-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:61ec41068b7b74268fa86e3e9e12b9f0c21fcf65434571dbb13d954bceb08042", size = 3886457 },
+    { url = "https://files.pythonhosted.org/packages/a4/65/430509e31700286ec02868a2457d2111d03ccefc20349d24e58d171ae0a7/cryptography-43.0.1-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:014f58110f53237ace6a408b5beb6c427b64e084eb451ef25a28308270086494", size = 4081499 },
+    { url = "https://files.pythonhosted.org/packages/bb/18/a04b6467e6e09df8c73b91dcee8878f4a438a43a3603dc3cd6f8003b92d8/cryptography-43.0.1-cp37-abi3-win32.whl", hash = "sha256:2bd51274dcd59f09dd952afb696bf9c61a7a49dfc764c04dd33ef7a6b502a1e2", size = 2616504 },
+    { url = "https://files.pythonhosted.org/packages/cc/73/0eacbdc437202edcbdc07f3576ed8fb8b0ab79d27bf2c5d822d758a72faa/cryptography-43.0.1-cp37-abi3-win_amd64.whl", hash = "sha256:666ae11966643886c2987b3b721899d250855718d6d9ce41b521252a17985f4d", size = 3067456 },
+    { url = "https://files.pythonhosted.org/packages/8a/b6/bc54b371f02cffd35ff8dc6baba88304d7cf8e83632566b4b42e00383e03/cryptography-43.0.1-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:ac119bb76b9faa00f48128b7f5679e1d8d437365c5d26f1c2c3f0da4ce1b553d", size = 6225263 },
+    { url = "https://files.pythonhosted.org/packages/00/0e/8217e348a1fa417ec4c78cd3cdf24154f5e76fd7597343a35bd403650dfd/cryptography-43.0.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1bbcce1a551e262dfbafb6e6252f1ae36a248e615ca44ba302df077a846a8806", size = 3794368 },
+    { url = "https://files.pythonhosted.org/packages/3d/ed/38b6be7254d8f7251fde8054af597ee8afa14f911da67a9410a45f602fc3/cryptography-43.0.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:58d4e9129985185a06d849aa6df265bdd5a74ca6e1b736a77959b498e0505b85", size = 3981750 },
+    { url = "https://files.pythonhosted.org/packages/64/f3/b7946c3887cf7436f002f4cbb1e6aec77b8d299b86be48eeadfefb937c4b/cryptography-43.0.1-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:d03a475165f3134f773d1388aeb19c2d25ba88b6a9733c5c590b9ff7bbfa2e0c", size = 3778925 },
+    { url = "https://files.pythonhosted.org/packages/ac/7e/ebda4dd4ae098a0990753efbb4b50954f1d03003846b943ea85070782da7/cryptography-43.0.1-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:511f4273808ab590912a93ddb4e3914dfd8a388fed883361b02dea3791f292e1", size = 3993152 },
+    { url = "https://files.pythonhosted.org/packages/43/f6/feebbd78a3e341e3913846a3bb2c29d0b09b1b3af1573c6baabc2533e147/cryptography-43.0.1-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:80eda8b3e173f0f247f711eef62be51b599b5d425c429b5d4ca6a05e9e856baa", size = 3886392 },
+    { url = "https://files.pythonhosted.org/packages/bd/4c/ab0b9407d5247576290b4fd8abd06b7f51bd414f04eef0f2800675512d61/cryptography-43.0.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:38926c50cff6f533f8a2dae3d7f19541432610d114a70808f0926d5aaa7121e4", size = 4082606 },
+    { url = "https://files.pythonhosted.org/packages/05/36/e532a671998d6fcfdb9122da16434347a58a6bae9465e527e450e0bc60a5/cryptography-43.0.1-cp39-abi3-win32.whl", hash = "sha256:a575913fb06e05e6b4b814d7f7468c2c660e8bb16d8d5a1faf9b33ccc569dd47", size = 2617948 },
+    { url = "https://files.pythonhosted.org/packages/b3/c6/c09cee6968add5ff868525c3815e5dccc0e3c6e89eec58dc9135d3c40e88/cryptography-43.0.1-cp39-abi3-win_amd64.whl", hash = "sha256:d75601ad10b059ec832e78823b348bfa1a59f6b8d545db3a24fd44362a1564cb", size = 3070445 },
+    { url = "https://files.pythonhosted.org/packages/18/23/4175dcd935e1649865e1af7bd0b827cc9d9769a586dcc84f7cbe96839086/cryptography-43.0.1-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ea25acb556320250756e53f9e20a4177515f012c9eaea17eb7587a8c4d8ae034", size = 3152694 },
+    { url = "https://files.pythonhosted.org/packages/ea/45/967da50269954b993d4484bf85026c7377bd551651ebdabba94905972556/cryptography-43.0.1-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c1332724be35d23a854994ff0b66530119500b6053d0bd3363265f7e5e77288d", size = 3713077 },
+    { url = "https://files.pythonhosted.org/packages/df/e6/ccd29a1f9a6b71294e1e9f530c4d779d5dd37c8bb736c05d5fb6d98a971b/cryptography-43.0.1-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:fba1007b3ef89946dbbb515aeeb41e30203b004f0b4b00e5e16078b518563289", size = 3915597 },
+    { url = "https://files.pythonhosted.org/packages/a2/80/fb7d668f1be5e4443b7ac191f68390be24f7c2ebd36011741f62c7645eb2/cryptography-43.0.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:5b43d1ea6b378b54a1dc99dd8a2b5be47658fe9a7ce0a58ff0b55f4b43ef2b84", size = 2989208 },
+]
+
 [[package]]
 name = "csscompressor"
 version = "0.9.5"
@@ -1504,6 +1537,7 @@ dependencies = [
     { name = "mkdocstrings" },
     { name = "mkdocstrings-python" },
     { name = "pdf2image" },
+    { name = "pdfplumber" },
     { name = "pip" },
     { name = "pymupdf4llm" },
     { name = "pypdf2" },
@@ -1520,6 +1554,7 @@ core = [
     { name = "byaldi" },
     { name = "firerequests" },
     { name = "pdf2image" },
+    { name = "pdfplumber" },
     { name = "pymupdf4llm" },
     { name = "python-dotenv" },
     { name = "torch" },
@@ -1571,6 +1606,8 @@ requires-dist = [
     { name = "mkdocstrings-python", marker = "extra == 'docs'", specifier = ">=1.11.1" },
     { name = "pdf2image", specifier = ">=1.17.0" },
     { name = "pdf2image", marker = "extra == 'core'", specifier = ">=1.17.0" },
+    { name = "pdfplumber", specifier = ">=0.11.4" },
+    { name = "pdfplumber", marker = "extra == 'core'", specifier = ">=0.11.4" },
     { name = "pip", specifier = ">=24.2" },
     { name = "pymupdf4llm", specifier = ">=0.0.17" },
     { name = "pymupdf4llm", marker = "extra == 'core'", specifier = ">=0.0.17" },
@@ -2337,6 +2374,33 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/62/33/61766ae033518957f877ab246f87ca30a85b778ebaad65b7f74fa7e52988/pdf2image-1.17.0-py3-none-any.whl", hash = "sha256:ecdd58d7afb810dffe21ef2b1bbc057ef434dabbac6c33778a38a3f7744a27e2", size = 11618 },
 ]
 
+[[package]]
+name = "pdfminer-six"
+version = "20231228"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "charset-normalizer" },
+    { name = "cryptography" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/31/b1/a43e3bd872ded4deea4f8efc7aff1703fca8c5455d0c06e20506a06a44ff/pdfminer.six-20231228.tar.gz", hash = "sha256:6004da3ad1a7a4d45930cb950393df89b068e73be365a6ff64a838d37bcb08c4", size = 7362505 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/eb/9c/e46fe7502b32d7db6af6e36a9105abb93301fa1ec475b5ddcba8b35ae23a/pdfminer.six-20231228-py3-none-any.whl", hash = "sha256:e8d3c3310e6fbc1fe414090123ab01351634b4ecb021232206c4c9a8ca3e3b8f", size = 5614515 },
+]
+
+[[package]]
+name = "pdfplumber"
+version = "0.11.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pdfminer-six" },
+    { name = "pillow" },
+    { name = "pypdfium2" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ca/f0/457bda3629dfa5b01c645519fe30230e1739751f6645e23fca2dabf6c2e5/pdfplumber-0.11.4.tar.gz", hash = "sha256:147b55cde2351fcb9523b46b09cc771eea3602faecfb60d463c6bf951694fbe8", size = 113305 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d0/87/415cb472981a8d2e36beeeadf074ebb686cc2bfe8d18de973232da291bd5/pdfplumber-0.11.4-py3-none-any.whl", hash = "sha256:6150f0678c7aaba974ac09839c17475d6c0c4d126b5f92cb85154885f31c6d73", size = 59182 },
+]
+
 [[package]]
 name = "peft"
 version = "0.11.1"
@@ -2777,6 +2841,26 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/8e/5e/c86a5643653825d3c913719e788e41386bee415c2b87b4f955432f2de6b2/pypdf2-3.0.1-py3-none-any.whl", hash = "sha256:d16e4205cfee272fbdc0568b68d82be796540b1537508cef59388f839c191928", size = 232572 },
 ]
 
+[[package]]
+name = "pypdfium2"
+version = "4.30.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a1/14/838b3ba247a0ba92e4df5d23f2bea9478edcfd72b78a39d6ca36ccd84ad2/pypdfium2-4.30.0.tar.gz", hash = "sha256:48b5b7e5566665bc1015b9d69c1ebabe21f6aee468b509531c3c8318eeee2e16", size = 140239 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c7/9a/c8ff5cc352c1b60b0b97642ae734f51edbab6e28b45b4fcdfe5306ee3c83/pypdfium2-4.30.0-py3-none-macosx_10_13_x86_64.whl", hash = "sha256:b33ceded0b6ff5b2b93bc1fe0ad4b71aa6b7e7bd5875f1ca0cdfb6ba6ac01aab", size = 2837254 },
+    { url = "https://files.pythonhosted.org/packages/21/8b/27d4d5409f3c76b985f4ee4afe147b606594411e15ac4dc1c3363c9a9810/pypdfium2-4.30.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:4e55689f4b06e2d2406203e771f78789bd4f190731b5d57383d05cf611d829de", size = 2707624 },
+    { url = "https://files.pythonhosted.org/packages/11/63/28a73ca17c24b41a205d658e177d68e198d7dde65a8c99c821d231b6ee3d/pypdfium2-4.30.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4e6e50f5ce7f65a40a33d7c9edc39f23140c57e37144c2d6d9e9262a2a854854", size = 2793126 },
+    { url = "https://files.pythonhosted.org/packages/d1/96/53b3ebf0955edbd02ac6da16a818ecc65c939e98fdeb4e0958362bd385c8/pypdfium2-4.30.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3d0dd3ecaffd0b6dbda3da663220e705cb563918249bda26058c6036752ba3a2", size = 2591077 },
+    { url = "https://files.pythonhosted.org/packages/ec/ee/0394e56e7cab8b5b21f744d988400948ef71a9a892cbeb0b200d324ab2c7/pypdfium2-4.30.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cc3bf29b0db8c76cdfaac1ec1cde8edf211a7de7390fbf8934ad2aa9b4d6dfad", size = 2864431 },
+    { url = "https://files.pythonhosted.org/packages/65/cd/3f1edf20a0ef4a212a5e20a5900e64942c5a374473671ac0780eaa08ea80/pypdfium2-4.30.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f1f78d2189e0ddf9ac2b7a9b9bd4f0c66f54d1389ff6c17e9fd9dc034d06eb3f", size = 2812008 },
+    { url = "https://files.pythonhosted.org/packages/c8/91/2d517db61845698f41a2a974de90762e50faeb529201c6b3574935969045/pypdfium2-4.30.0-py3-none-musllinux_1_1_aarch64.whl", hash = "sha256:5eda3641a2da7a7a0b2f4dbd71d706401a656fea521b6b6faa0675b15d31a163", size = 6181543 },
+    { url = "https://files.pythonhosted.org/packages/ba/c4/ed1315143a7a84b2c7616569dfb472473968d628f17c231c39e29ae9d780/pypdfium2-4.30.0-py3-none-musllinux_1_1_i686.whl", hash = "sha256:0dfa61421b5eb68e1188b0b2231e7ba35735aef2d867d86e48ee6cab6975195e", size = 6175911 },
+    { url = "https://files.pythonhosted.org/packages/7a/c4/9e62d03f414e0e3051c56d5943c3bf42aa9608ede4e19dc96438364e9e03/pypdfium2-4.30.0-py3-none-musllinux_1_1_x86_64.whl", hash = "sha256:f33bd79e7a09d5f7acca3b0b69ff6c8a488869a7fab48fdf400fec6e20b9c8be", size = 6267430 },
+    { url = "https://files.pythonhosted.org/packages/90/47/eda4904f715fb98561e34012826e883816945934a851745570521ec89520/pypdfium2-4.30.0-py3-none-win32.whl", hash = "sha256:ee2410f15d576d976c2ab2558c93d392a25fb9f6635e8dd0a8a3a5241b275e0e", size = 2775951 },
+    { url = "https://files.pythonhosted.org/packages/25/bd/56d9ec6b9f0fc4e0d95288759f3179f0fcd34b1a1526b75673d2f6d5196f/pypdfium2-4.30.0-py3-none-win_amd64.whl", hash = "sha256:90dbb2ac07be53219f56be09961eb95cf2473f834d01a42d901d13ccfad64b4c", size = 2892098 },
+    { url = "https://files.pythonhosted.org/packages/be/7a/097801205b991bc3115e8af1edb850d30aeaf0118520b016354cf5ccd3f6/pypdfium2-4.30.0-py3-none-win_arm64.whl", hash = "sha256:119b2969a6d6b1e8d55e99caaf05290294f2d0fe49c12a3f17102d01c441bd29", size = 2752118 },
+]
+
 [[package]]
 name = "pytest"
 version = "8.3.3"