Add test for stripping OCR

README.md

@@ -5,7 +5,7 @@ Marker converts PDFs to markdown, JSON, and HTML quickly and accurately.
 - Supports a wide range of documents
 - Supports all languages
 - Removes headers/footers/other artifacts
-- Formats tables and code blocks
+- Formats tables, forms, and code blocks
 - Extracts and saves images along with the markdown
 - Converts equations to latex
 - Easily extensible with your own formatting and logic
@@ -19,6 +19,7 @@ Marker is a pipeline of deep learning models:
 - Extract text, OCR if necessary (heuristics, [surya](https://github.com/VikParuchuri/surya))
 - Detect page layout and find reading order ([surya](https://github.com/VikParuchuri/surya))
 - Clean and format each block (heuristics, [texify](https://github.com/VikParuchuri/texify). [tabled](https://github.com/VikParuchuri/tabled))
+- Optionally use an LLM to improve quality
 - Combine blocks and postprocess complete text
 
 It only uses models where necessary, which improves speed and accuracy.
@@ -66,6 +67,8 @@ PDF is a tricky format, so marker will not always work perfectly.  Here are some
 - Forms are not converted optimally
 - Very complex layouts, with nested tables and forms, may not work
 
+Note: Passing the `--use_llm` flag will mostly solve all of these issues.
+
 # Installation
 
 You'll need python 3.10+ and PyTorch.  You may need to install the CPU version of torch first if you're not using a Mac or a GPU machine.  See [here](https://pytorch.org/get-started/locally/) for more details.
@@ -105,6 +108,7 @@ Options:
 - `--disable_image_extraction`: Don't extract images from the PDF.  If you also specify `--use_llm`, then images will be replaced with a description.
 - `--page_range TEXT`: Specify which pages to process. Accepts comma-separated page numbers and ranges. Example: `--page_range "0,5-10,20"` will process pages 0, 5 through 10, and page 20.
 - `--force_ocr`: Force OCR processing on the entire document, even for pages that might contain extractable text.
+- `--strip_existing_ocr`: Remove all existing OCR text in the document and re-OCR with surya.
 - `--debug`: Enable debug mode for additional logging and diagnostic information.
 - `--processors TEXT`: Override the default processors by providing their full module paths, separated by commas. Example: `--processors "module1.processor1,module2.processor2"`
 - `--config_json PATH`: Path to a JSON configuration file containing additional settings.

marker_app.py

@@ -114,7 +114,9 @@ page_range = st.sidebar.text_input("Page range to parse, comma separated like 0,
 output_format = st.sidebar.selectbox("Output format", ["markdown", "json", "html"], index=0)
 run_marker = st.sidebar.button("Run Marker")
 
+use_llm = st.sidebar.checkbox("Use LLM", help="Use LLM for higher quality processing", value=False)
 force_ocr = st.sidebar.checkbox("Force OCR", help="Force OCR on all pages", value=False)
+strip_existing_ocr = st.sidebar.checkbox("Strip existing OCR", help="Strip existing OCR text from the PDF and re-OCR.", value=False)
 debug = st.sidebar.checkbox("Debug", help="Show debug information", value=False)
 
 if not run_marker:
@@ -131,6 +133,8 @@ with tempfile.NamedTemporaryFile(suffix=".pdf", mode="wb+") as temp_pdf:
         "force_ocr": force_ocr,
         "debug": debug,
         "output_dir": settings.DEBUG_DATA_FOLDER if debug else None,
+        "use_llm": use_llm,
+        "strip_existing_ocr": strip_existing_ocr
     }
     config_parser = ConfigParser(cli_options)
     rendered = convert_pdf(

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.5 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -373,6 +373,7 @@ files = [
 ]
 
 [package.dependencies]
+tinycss2 = {version = ">=1.1.0,<1.5", optional = true, markers = "extra == \"css\""}
 webencodings = "*"
 
 [package.extras]
@@ -1008,13 +1009,13 @@ wcwidth = "*"
 
 [[package]]
 name = "gitdb"
-version = "4.0.11"
+version = "4.0.12"
 description = "Git Object Database"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "gitdb-4.0.11-py3-none-any.whl", hash = "sha256:81a3407ddd2ee8df444cbacea00e2d038e40150acfa3001696fe0dcf1d3adfa4"},
-    {file = "gitdb-4.0.11.tar.gz", hash = "sha256:bf5421126136d6d0af55bc1e7c1af1c397a34f5b7bd79e776cd3e89785c2b04b"},
+    {file = "gitdb-4.0.12-py3-none-any.whl", hash = "sha256:67073e15955400952c6565cc3e707c554a4eea2e428946f7a4c162fab9bd9bcf"},
+    {file = "gitdb-4.0.12.tar.gz", hash = "sha256:5ef71f855d191a3326fcfbc0d5da835f26b13fbcba60c32c21091c349ffdb571"},
 ]
 
 [package.dependencies]
@@ -1022,20 +1023,20 @@ smmap = ">=3.0.1,<6"
 
 [[package]]
 name = "gitpython"
-version = "3.1.43"
+version = "3.1.44"
 description = "GitPython is a Python library used to interact with Git repositories"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "GitPython-3.1.43-py3-none-any.whl", hash = "sha256:eec7ec56b92aad751f9912a73404bc02ba212a23adb2c7098ee668417051a1ff"},
-    {file = "GitPython-3.1.43.tar.gz", hash = "sha256:35f314a9f878467f5453cc1fee295c3e18e52f1b99f10f6cf5b1682e968a9e7c"},
+    {file = "GitPython-3.1.44-py3-none-any.whl", hash = "sha256:9e0e10cda9bed1ee64bc9a6de50e7e38a9c9943241cd7f585f6df3ed28011110"},
+    {file = "gitpython-3.1.44.tar.gz", hash = "sha256:c87e30b26253bf5418b01b0660f818967f3c503193838337fe5e573331249269"},
 ]
 
 [package.dependencies]
 gitdb = ">=4.0.1,<5"
 
 [package.extras]
-doc = ["sphinx (==4.3.2)", "sphinx-autodoc-typehints", "sphinx-rtd-theme", "sphinxcontrib-applehelp (>=1.0.2,<=1.0.4)", "sphinxcontrib-devhelp (==1.0.2)", "sphinxcontrib-htmlhelp (>=2.0.0,<=2.0.1)", "sphinxcontrib-qthelp (==1.0.3)", "sphinxcontrib-serializinghtml (==1.1.5)"]
+doc = ["sphinx (>=7.1.2,<7.2)", "sphinx-autodoc-typehints", "sphinx_rtd_theme"]
 test = ["coverage[toml]", "ddt (>=1.1.1,!=1.4.3)", "mock", "mypy", "pre-commit", "pytest (>=7.3.1)", "pytest-cov", "pytest-instafail", "pytest-mock", "pytest-sugar", "typing-extensions"]
 
 [[package]]
@@ -2237,18 +2238,18 @@ test = ["flaky", "ipykernel (>=6.19.3)", "ipython", "ipywidgets", "nbconvert (>=
 
 [[package]]
 name = "nbconvert"
-version = "7.16.4"
+version = "7.16.5"
 description = "Converting Jupyter Notebooks (.ipynb files) to other formats.  Output formats include asciidoc, html, latex, markdown, pdf, py, rst, script.  nbconvert can be used both as a Python library (`import nbconvert`) or as a command line tool (invoked as `jupyter nbconvert ...`)."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "nbconvert-7.16.4-py3-none-any.whl", hash = "sha256:05873c620fe520b6322bf8a5ad562692343fe3452abda5765c7a34b7d1aa3eb3"},
-    {file = "nbconvert-7.16.4.tar.gz", hash = "sha256:86ca91ba266b0a448dc96fa6c5b9d98affabde2867b363258703536807f9f7f4"},
+    {file = "nbconvert-7.16.5-py3-none-any.whl", hash = "sha256:e12eac052d6fd03040af4166c563d76e7aeead2e9aadf5356db552a1784bd547"},
+    {file = "nbconvert-7.16.5.tar.gz", hash = "sha256:c83467bb5777fdfaac5ebbb8e864f300b277f68692ecc04d6dab72f2d8442344"},
 ]
 
 [package.dependencies]
 beautifulsoup4 = "*"
-bleach = "!=5.0.0"
+bleach = {version = "!=5.0.0", extras = ["css"]}
 defusedxml = "*"
 jinja2 = ">=3.0"
 jupyter-core = ">=4.7"
@@ -2260,7 +2261,6 @@ nbformat = ">=5.7"
 packaging = "*"
 pandocfilters = ">=1.4.1"
 pygments = ">=2.4.1"
-tinycss2 = "*"
 traitlets = ">=5.1"
 
 [package.extras]
@@ -3066,8 +3066,6 @@ files = [
     {file = "psutil-6.1.1-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:8df0178ba8a9e5bc84fed9cfa61d54601b371fbec5c8eebad27575f1e105c0d4"},
     {file = "psutil-6.1.1-cp27-cp27mu-manylinux2010_i686.whl", hash = "sha256:1924e659d6c19c647e763e78670a05dbb7feaf44a0e9c94bf9e14dfc6ba50468"},
     {file = "psutil-6.1.1-cp27-cp27mu-manylinux2010_x86_64.whl", hash = "sha256:018aeae2af92d943fdf1da6b58665124897cfc94faa2ca92098838f83e1b1bca"},
-    {file = "psutil-6.1.1-cp27-none-win32.whl", hash = "sha256:6d4281f5bbca041e2292be3380ec56a9413b790579b8e593b1784499d0005dac"},
-    {file = "psutil-6.1.1-cp27-none-win_amd64.whl", hash = "sha256:c777eb75bb33c47377c9af68f30e9f11bc78e0f07fbf907be4a5d70b2fe5f030"},
     {file = "psutil-6.1.1-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:fc0ed7fe2231a444fc219b9c42d0376e0a9a1a72f16c5cfa0f68d19f1a0663e8"},
     {file = "psutil-6.1.1-cp36-abi3-macosx_11_0_arm64.whl", hash = "sha256:0bdd4eab935276290ad3cb718e9809412895ca6b5b334f5a9111ee6d9aff9377"},
     {file = "psutil-6.1.1-cp36-abi3-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b6e06c20c05fe95a3d7302d74e7097756d4ba1247975ad6905441ae1b5b66003"},
@@ -3333,13 +3331,13 @@ typing-extensions = ">=4.6.0,<4.7.0 || >4.7.0"
 
 [[package]]
 name = "pydantic-settings"
-version = "2.7.0"
+version = "2.7.1"
 description = "Settings management using Pydantic"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pydantic_settings-2.7.0-py3-none-any.whl", hash = "sha256:e00c05d5fa6cbbb227c84bd7487c5c1065084119b750df7c8c1a554aed236eb5"},
-    {file = "pydantic_settings-2.7.0.tar.gz", hash = "sha256:ac4bfd4a36831a48dbf8b2d9325425b549a0a6f18cea118436d728eb4f1c4d66"},
+    {file = "pydantic_settings-2.7.1-py3-none-any.whl", hash = "sha256:590be9e6e24d06db33a4262829edef682500ef008565a969c73d39d5f8bfb3fd"},
+    {file = "pydantic_settings-2.7.1.tar.gz", hash = "sha256:10c9caad35e64bfb3c2fbf70a078c0e25cc92499782e5200747f942a065dec93"},
 ]
 
 [package.dependencies]
@@ -3386,13 +3384,13 @@ windows-terminal = ["colorama (>=0.4.6)"]
 
 [[package]]
 name = "pyparsing"
-version = "3.2.0"
+version = "3.2.1"
 description = "pyparsing module - Classes and methods to define and execute parsing grammars"
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "pyparsing-3.2.0-py3-none-any.whl", hash = "sha256:93d9577b88da0bbea8cc8334ee8b918ed014968fd2ec383e868fb8afb1ccef84"},
-    {file = "pyparsing-3.2.0.tar.gz", hash = "sha256:cbf74e27246d595d9a74b186b810f6fbb86726dbf3b9532efb343f6d7294fe9c"},
+    {file = "pyparsing-3.2.1-py3-none-any.whl", hash = "sha256:506ff4f4386c4cec0590ec19e6302d3aedb992fdc02c761e90416f158dacf8e1"},
+    {file = "pyparsing-3.2.1.tar.gz", hash = "sha256:61980854fd66de3a90028d679a954d5f2623e83144b5afe5ee86f43d762e5f0a"},
 ]
 
 [package.extras]
@@ -4159,121 +4157,26 @@ pyasn1 = ">=0.1.3"
 
 [[package]]
 name = "safetensors"
-version = "0.4.5"
+version = "0.5.0"
 description = ""
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "safetensors-0.4.5-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:a63eaccd22243c67e4f2b1c3e258b257effc4acd78f3b9d397edc8cf8f1298a7"},
-    {file = "safetensors-0.4.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:23fc9b4ec7b602915cbb4ec1a7c1ad96d2743c322f20ab709e2c35d1b66dad27"},
-    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6885016f34bef80ea1085b7e99b3c1f92cb1be78a49839203060f67b40aee761"},
-    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:133620f443450429322f238fda74d512c4008621227fccf2f8cf4a76206fea7c"},
-    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4fb3e0609ec12d2a77e882f07cced530b8262027f64b75d399f1504ffec0ba56"},
-    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d0f1dd769f064adc33831f5e97ad07babbd728427f98e3e1db6902e369122737"},
-    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c6d156bdb26732feada84f9388a9f135528c1ef5b05fae153da365ad4319c4c5"},
-    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:9e347d77e2c77eb7624400ccd09bed69d35c0332f417ce8c048d404a096c593b"},
-    {file = "safetensors-0.4.5-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9f556eea3aec1d3d955403159fe2123ddd68e880f83954ee9b4a3f2e15e716b6"},
-    {file = "safetensors-0.4.5-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:9483f42be3b6bc8ff77dd67302de8ae411c4db39f7224dec66b0eb95822e4163"},
-    {file = "safetensors-0.4.5-cp310-none-win32.whl", hash = "sha256:7389129c03fadd1ccc37fd1ebbc773f2b031483b04700923c3511d2a939252cc"},
-    {file = "safetensors-0.4.5-cp310-none-win_amd64.whl", hash = "sha256:e98ef5524f8b6620c8cdef97220c0b6a5c1cef69852fcd2f174bb96c2bb316b1"},
-    {file = "safetensors-0.4.5-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:21f848d7aebd5954f92538552d6d75f7c1b4500f51664078b5b49720d180e47c"},
-    {file = "safetensors-0.4.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:bb07000b19d41e35eecef9a454f31a8b4718a185293f0d0b1c4b61d6e4487971"},
-    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:09dedf7c2fda934ee68143202acff6e9e8eb0ddeeb4cfc24182bef999efa9f42"},
-    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:59b77e4b7a708988d84f26de3ebead61ef1659c73dcbc9946c18f3b1786d2688"},
-    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5d3bc83e14d67adc2e9387e511097f254bd1b43c3020440e708858c684cbac68"},
-    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:39371fc551c1072976073ab258c3119395294cf49cdc1f8476794627de3130df"},
-    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a6c19feda32b931cae0acd42748a670bdf56bee6476a046af20181ad3fee4090"},
-    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:a659467495de201e2f282063808a41170448c78bada1e62707b07a27b05e6943"},
-    {file = "safetensors-0.4.5-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:bad5e4b2476949bcd638a89f71b6916fa9a5cae5c1ae7eede337aca2100435c0"},
-    {file = "safetensors-0.4.5-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:a3a315a6d0054bc6889a17f5668a73f94f7fe55121ff59e0a199e3519c08565f"},
-    {file = "safetensors-0.4.5-cp311-none-win32.whl", hash = "sha256:a01e232e6d3d5cf8b1667bc3b657a77bdab73f0743c26c1d3c5dd7ce86bd3a92"},
-    {file = "safetensors-0.4.5-cp311-none-win_amd64.whl", hash = "sha256:cbd39cae1ad3e3ef6f63a6f07296b080c951f24cec60188378e43d3713000c04"},
-    {file = "safetensors-0.4.5-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:473300314e026bd1043cef391bb16a8689453363381561b8a3e443870937cc1e"},
-    {file = "safetensors-0.4.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:801183a0f76dc647f51a2d9141ad341f9665602a7899a693207a82fb102cc53e"},
-    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1524b54246e422ad6fb6aea1ac71edeeb77666efa67230e1faf6999df9b2e27f"},
-    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:b3139098e3e8b2ad7afbca96d30ad29157b50c90861084e69fcb80dec7430461"},
-    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:65573dc35be9059770808e276b017256fa30058802c29e1038eb1c00028502ea"},
-    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fd33da8e9407559f8779c82a0448e2133737f922d71f884da27184549416bfed"},
-    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3685ce7ed036f916316b567152482b7e959dc754fcc4a8342333d222e05f407c"},
-    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:dde2bf390d25f67908278d6f5d59e46211ef98e44108727084d4637ee70ab4f1"},
-    {file = "safetensors-0.4.5-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:7469d70d3de970b1698d47c11ebbf296a308702cbaae7fcb993944751cf985f4"},
-    {file = "safetensors-0.4.5-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:3a6ba28118636a130ccbb968bc33d4684c48678695dba2590169d5ab03a45646"},
-    {file = "safetensors-0.4.5-cp312-none-win32.whl", hash = "sha256:c859c7ed90b0047f58ee27751c8e56951452ed36a67afee1b0a87847d065eec6"},
-    {file = "safetensors-0.4.5-cp312-none-win_amd64.whl", hash = "sha256:b5a8810ad6a6f933fff6c276eae92c1da217b39b4d8b1bc1c0b8af2d270dc532"},
-    {file = "safetensors-0.4.5-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:25e5f8e2e92a74f05b4ca55686234c32aac19927903792b30ee6d7bd5653d54e"},
-    {file = "safetensors-0.4.5-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:81efb124b58af39fcd684254c645e35692fea81c51627259cdf6d67ff4458916"},
-    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:585f1703a518b437f5103aa9cf70e9bd437cb78eea9c51024329e4fb8a3e3679"},
-    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4b99fbf72e3faf0b2f5f16e5e3458b93b7d0a83984fe8d5364c60aa169f2da89"},
-    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b17b299ca9966ca983ecda1c0791a3f07f9ca6ab5ded8ef3d283fff45f6bcd5f"},
-    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:76ded72f69209c9780fdb23ea89e56d35c54ae6abcdec67ccb22af8e696e449a"},
-    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2783956926303dcfeb1de91a4d1204cd4089ab441e622e7caee0642281109db3"},
-    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d94581aab8c6b204def4d7320f07534d6ee34cd4855688004a4354e63b639a35"},
-    {file = "safetensors-0.4.5-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:67e1e7cb8678bb1b37ac48ec0df04faf689e2f4e9e81e566b5c63d9f23748523"},
-    {file = "safetensors-0.4.5-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:dbd280b07e6054ea68b0cb4b16ad9703e7d63cd6890f577cb98acc5354780142"},
-    {file = "safetensors-0.4.5-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:77d9b228da8374c7262046a36c1f656ba32a93df6cc51cd4453af932011e77f1"},
-    {file = "safetensors-0.4.5-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:500cac01d50b301ab7bb192353317035011c5ceeef0fca652f9f43c000bb7f8d"},
-    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:75331c0c746f03158ded32465b7d0b0e24c5a22121743662a2393439c43a45cf"},
-    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:670e95fe34e0d591d0529e5e59fd9d3d72bc77b1444fcaa14dccda4f36b5a38b"},
-    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:098923e2574ff237c517d6e840acada8e5b311cb1fa226019105ed82e9c3b62f"},
-    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:13ca0902d2648775089fa6a0c8fc9e6390c5f8ee576517d33f9261656f851e3f"},
-    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5f0032bedc869c56f8d26259fe39cd21c5199cd57f2228d817a0e23e8370af25"},
-    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f4b15f51b4f8f2a512341d9ce3475cacc19c5fdfc5db1f0e19449e75f95c7dc8"},
-    {file = "safetensors-0.4.5-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:f6594d130d0ad933d885c6a7b75c5183cb0e8450f799b80a39eae2b8508955eb"},
-    {file = "safetensors-0.4.5-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:60c828a27e852ded2c85fc0f87bf1ec20e464c5cd4d56ff0e0711855cc2e17f8"},
-    {file = "safetensors-0.4.5-cp37-none-win32.whl", hash = "sha256:6d3de65718b86c3eeaa8b73a9c3d123f9307a96bbd7be9698e21e76a56443af5"},
-    {file = "safetensors-0.4.5-cp37-none-win_amd64.whl", hash = "sha256:5a2d68a523a4cefd791156a4174189a4114cf0bf9c50ceb89f261600f3b2b81a"},
-    {file = "safetensors-0.4.5-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:e7a97058f96340850da0601a3309f3d29d6191b0702b2da201e54c6e3e44ccf0"},
-    {file = "safetensors-0.4.5-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:63bfd425e25f5c733f572e2246e08a1c38bd6f2e027d3f7c87e2e43f228d1345"},
-    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f3664ac565d0e809b0b929dae7ccd74e4d3273cd0c6d1220c6430035befb678e"},
-    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:313514b0b9b73ff4ddfb4edd71860696dbe3c1c9dc4d5cc13dbd74da283d2cbf"},
-    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:31fa33ee326f750a2f2134a6174773c281d9a266ccd000bd4686d8021f1f3dac"},
-    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:09566792588d77b68abe53754c9f1308fadd35c9f87be939e22c623eaacbed6b"},
-    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:309aaec9b66cbf07ad3a2e5cb8a03205663324fea024ba391594423d0f00d9fe"},
-    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:53946c5813b8f9e26103c5efff4a931cc45d874f45229edd68557ffb35ffb9f8"},
-    {file = "safetensors-0.4.5-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:868f9df9e99ad1e7f38c52194063a982bc88fedc7d05096f4f8160403aaf4bd6"},
-    {file = "safetensors-0.4.5-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:9cc9449bd0b0bc538bd5e268221f0c5590bc5c14c1934a6ae359d44410dc68c4"},
-    {file = "safetensors-0.4.5-cp38-none-win32.whl", hash = "sha256:83c4f13a9e687335c3928f615cd63a37e3f8ef072a3f2a0599fa09f863fb06a2"},
-    {file = "safetensors-0.4.5-cp38-none-win_amd64.whl", hash = "sha256:b98d40a2ffa560653f6274e15b27b3544e8e3713a44627ce268f419f35c49478"},
-    {file = "safetensors-0.4.5-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:cf727bb1281d66699bef5683b04d98c894a2803442c490a8d45cd365abfbdeb2"},
-    {file = "safetensors-0.4.5-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:96f1d038c827cdc552d97e71f522e1049fef0542be575421f7684756a748e457"},
-    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:139fbee92570ecea774e6344fee908907db79646d00b12c535f66bc78bd5ea2c"},
-    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:c36302c1c69eebb383775a89645a32b9d266878fab619819ce660309d6176c9b"},
-    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d641f5b8149ea98deb5ffcf604d764aad1de38a8285f86771ce1abf8e74c4891"},
-    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b4db6a61d968de73722b858038c616a1bebd4a86abe2688e46ca0cc2d17558f2"},
-    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b75a616e02f21b6f1d5785b20cecbab5e2bd3f6358a90e8925b813d557666ec1"},
-    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:788ee7d04cc0e0e7f944c52ff05f52a4415b312f5efd2ee66389fb7685ee030c"},
-    {file = "safetensors-0.4.5-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:87bc42bd04fd9ca31396d3ca0433db0be1411b6b53ac5a32b7845a85d01ffc2e"},
-    {file = "safetensors-0.4.5-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4037676c86365a721a8c9510323a51861d703b399b78a6b4486a54a65a975fca"},
-    {file = "safetensors-0.4.5-cp39-none-win32.whl", hash = "sha256:1500418454529d0ed5c1564bda376c4ddff43f30fce9517d9bee7bcce5a8ef50"},
-    {file = "safetensors-0.4.5-cp39-none-win_amd64.whl", hash = "sha256:9d1a94b9d793ed8fe35ab6d5cea28d540a46559bafc6aae98f30ee0867000cab"},
-    {file = "safetensors-0.4.5-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:fdadf66b5a22ceb645d5435a0be7a0292ce59648ca1d46b352f13cff3ea80410"},
-    {file = "safetensors-0.4.5-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:d42ffd4c2259f31832cb17ff866c111684c87bd930892a1ba53fed28370c918c"},
-    {file = "safetensors-0.4.5-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dd8a1f6d2063a92cd04145c7fd9e31a1c7d85fbec20113a14b487563fdbc0597"},
-    {file = "safetensors-0.4.5-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:951d2fcf1817f4fb0ef0b48f6696688a4e852a95922a042b3f96aaa67eedc920"},
-    {file = "safetensors-0.4.5-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:6ac85d9a8c1af0e3132371d9f2d134695a06a96993c2e2f0bbe25debb9e3f67a"},
-    {file = "safetensors-0.4.5-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:e3cec4a29eb7fe8da0b1c7988bc3828183080439dd559f720414450de076fcab"},
-    {file = "safetensors-0.4.5-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:21742b391b859e67b26c0b2ac37f52c9c0944a879a25ad2f9f9f3cd61e7fda8f"},
-    {file = "safetensors-0.4.5-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:c7db3006a4915151ce1913652e907cdede299b974641a83fbc092102ac41b644"},
-    {file = "safetensors-0.4.5-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f68bf99ea970960a237f416ea394e266e0361895753df06e3e06e6ea7907d98b"},
-    {file = "safetensors-0.4.5-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8158938cf3324172df024da511839d373c40fbfaa83e9abf467174b2910d7b4c"},
-    {file = "safetensors-0.4.5-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:540ce6c4bf6b58cb0fd93fa5f143bc0ee341c93bb4f9287ccd92cf898cc1b0dd"},
-    {file = "safetensors-0.4.5-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:bfeaa1a699c6b9ed514bd15e6a91e74738b71125a9292159e3d6b7f0a53d2cde"},
-    {file = "safetensors-0.4.5-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:01c8f00da537af711979e1b42a69a8ec9e1d7112f208e0e9b8a35d2c381085ef"},
-    {file = "safetensors-0.4.5-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:a0dd565f83b30f2ca79b5d35748d0d99dd4b3454f80e03dfb41f0038e3bdf180"},
-    {file = "safetensors-0.4.5-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:023b6e5facda76989f4cba95a861b7e656b87e225f61811065d5c501f78cdb3f"},
-    {file = "safetensors-0.4.5-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9633b663393d5796f0b60249549371e392b75a0b955c07e9c6f8708a87fc841f"},
-    {file = "safetensors-0.4.5-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78dd8adfb48716233c45f676d6e48534d34b4bceb50162c13d1f0bdf6f78590a"},
-    {file = "safetensors-0.4.5-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:8e8deb16c4321d61ae72533b8451ec4a9af8656d1c61ff81aa49f966406e4b68"},
-    {file = "safetensors-0.4.5-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:52452fa5999dc50c4decaf0c53aa28371f7f1e0fe5c2dd9129059fbe1e1599c7"},
-    {file = "safetensors-0.4.5-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:d5f23198821e227cfc52d50fa989813513db381255c6d100927b012f0cfec63d"},
-    {file = "safetensors-0.4.5-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:f4beb84b6073b1247a773141a6331117e35d07134b3bb0383003f39971d414bb"},
-    {file = "safetensors-0.4.5-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:68814d599d25ed2fdd045ed54d370d1d03cf35e02dce56de44c651f828fb9b7b"},
-    {file = "safetensors-0.4.5-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f0b6453c54c57c1781292c46593f8a37254b8b99004c68d6c3ce229688931a22"},
-    {file = "safetensors-0.4.5-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:adaa9c6dead67e2dd90d634f89131e43162012479d86e25618e821a03d1eb1dc"},
-    {file = "safetensors-0.4.5-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:73e7d408e9012cd17511b382b43547850969c7979efc2bc353f317abaf23c84c"},
-    {file = "safetensors-0.4.5-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:775409ce0fcc58b10773fdb4221ed1eb007de10fe7adbdf8f5e8a56096b6f0bc"},
-    {file = "safetensors-0.4.5-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:834001bed193e4440c4a3950a31059523ee5090605c907c66808664c932b549c"},
-    {file = "safetensors-0.4.5.tar.gz", hash = "sha256:d73de19682deabb02524b3d5d1f8b3aaba94c72f1bbfc7911b9b9d5d391c0310"},
+    {file = "safetensors-0.5.0-cp38-abi3-macosx_10_12_x86_64.whl", hash = "sha256:c683b9b485bee43422ba2855f72777c37647190281e03da4c8d2a69fa5336558"},
+    {file = "safetensors-0.5.0-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:6106aa835deb7263f7014f74c05842ab828d6c11d789f2e7e98f26b1a305e72d"},
+    {file = "safetensors-0.5.0-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a1349611f74f55c5ee1c1c144c536a2743c38f7d8bf60b9fc8267e0efc0591a2"},
+    {file = "safetensors-0.5.0-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:56d936028ac799e18644b08a91fd98b4b62ae3dcd0440b1cfcb56535785589f1"},
+    {file = "safetensors-0.5.0-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a2f26afada2233576ffea6b80042c2c0a8105c164254af56168ec14299ad3122"},
+    {file = "safetensors-0.5.0-cp38-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:20067e7a5e63f0cbc88457b2a1161e70ff73af4cc3a24bce90309430cd6f6e7e"},
+    {file = "safetensors-0.5.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:649d6a4aa34d5174ae87289068ccc2fec2a1a998ecf83425aa5a42c3eff69bcf"},
+    {file = "safetensors-0.5.0-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:debff88f41d569a3e93a955469f83864e432af35bb34b16f65a9ddf378daa3ae"},
+    {file = "safetensors-0.5.0-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:bdf6a3e366ea8ba1a0538db6099229e95811194432c684ea28ea7ae28763b8dc"},
+    {file = "safetensors-0.5.0-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:0371afd84c200a80eb7103bf715108b0c3846132fb82453ae018609a15551580"},
+    {file = "safetensors-0.5.0-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:5ec7fc8c3d2f32ebf1c7011bc886b362e53ee0a1ec6d828c39d531fed8b325d6"},
+    {file = "safetensors-0.5.0-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:53715e4ea0ef23c08f004baae0f609a7773de7d4148727760417c6760cfd6b76"},
+    {file = "safetensors-0.5.0-cp38-abi3-win32.whl", hash = "sha256:b85565bc2f0456961a788d2f11d9d892eec46603db0e4923aa9512c2355aa727"},
+    {file = "safetensors-0.5.0-cp38-abi3-win_amd64.whl", hash = "sha256:f451941f8aa11e7be5c3fa450e264609a2b1e65fa38ae590a74e55a94d646b76"},
+    {file = "safetensors-0.5.0.tar.gz", hash = "sha256:c47b34c549fa1e0c655c4644da31332c61332c732c47c8dd9399347e9aac69d1"},
 ]
 
 [package.extras]
@@ -4283,7 +4186,7 @@ jax = ["flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "safetensors[num
 mlx = ["mlx (>=0.0.9)"]
 numpy = ["numpy (>=1.21.6)"]
 paddlepaddle = ["paddlepaddle (>=2.4.1)", "safetensors[numpy]"]
-pinned-tf = ["safetensors[numpy]", "tensorflow (==2.11.0)"]
+pinned-tf = ["safetensors[numpy]", "tensorflow (==2.18.0)"]
 quality = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "isort (>=5.5.4)"]
 tensorflow = ["safetensors[numpy]", "tensorflow (>=2.11.0)"]
 testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "hypothesis (>=6.70.2)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "safetensors[numpy]", "setuptools-rust (>=1.5.2)"]
@@ -4442,13 +4345,13 @@ files = [
 
 [[package]]
 name = "smmap"
-version = "5.0.1"
+version = "5.0.2"
 description = "A pure Python implementation of a sliding window memory map manager"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "smmap-5.0.1-py3-none-any.whl", hash = "sha256:e6d8668fa5f93e706934a62d7b4db19c8d9eb8cf2adbb75ef1b675aa332b69da"},
-    {file = "smmap-5.0.1.tar.gz", hash = "sha256:dceeb6c0028fdb6734471eb07c0cd2aae706ccaecab45965ee83f11c8d3b1f62"},
+    {file = "smmap-5.0.2-py3-none-any.whl", hash = "sha256:b30115f0def7d7531d22a0fb6502488d879e75b260a9db4d0819cfb25403af5e"},
+    {file = "smmap-5.0.2.tar.gz", hash = "sha256:26ea65a03958fa0c8a1c7e8c7a58fdc77221b8910f6be2131affade476898ad5"},
 ]
 
 [[package]]
@@ -4546,24 +4449,24 @@ snowflake = ["snowflake-connector-python (>=2.8.0)", "snowflake-snowpark-python[
 
 [[package]]
 name = "surya-ocr"
-version = "0.8.2"
+version = "0.8.3"
 description = "OCR, layout, reading order, and table recognition in 90+ languages"
 optional = false
 python-versions = "<4.0,>=3.10"
 files = [
-    {file = "surya_ocr-0.8.2-py3-none-any.whl", hash = "sha256:9536d79eef23341ec9aa8caadca2938fbcfd9ec00e1bb0a571f36aee98be1137"},
-    {file = "surya_ocr-0.8.2.tar.gz", hash = "sha256:eae8ce47e1873d42a0e35d58205dc7378dc813021b68881854e446d3e4a3a95e"},
+    {file = "surya_ocr-0.8.3-py3-none-any.whl", hash = "sha256:b2a0e07de8741d2f1b68a1b9f33b6864779648619607ee09dcbeabc31ee79289"},
+    {file = "surya_ocr-0.8.3.tar.gz", hash = "sha256:13d9ab7d5d971f16e37bffe48767b80df6999cccd3c7eb7c154f33f440ac02e3"},
 ]
 
 [package.dependencies]
 filetype = ">=1.2.0,<2.0.0"
 ftfy = ">=6.1.3,<7.0.0"
 opencv-python = ">=4.9.0.80,<5.0.0.0"
-pdftext = ">=0.4.0,<0.5.0"
+pdftext = ">=0.4.1,<0.5.0"
 pillow = ">=10.2.0,<11.0.0"
 pydantic = ">=2.5.3,<3.0.0"
 pydantic-settings = ">=2.1.0,<3.0.0"
-pypdfium2 = ">=4.25.0,<5.0.0"
+pypdfium2 = "4.30.0"
 python-dotenv = ">=1.0.0,<2.0.0"
 tabulate = ">=0.9.0,<0.10.0"
 torch = ">=2.4.1,<3.0.0"
@@ -5417,4 +5320,4 @@ propcache = ">=0.2.0"
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "1690ddbd87582f785efd2b1755bf688b72afb04586a421e0c0284236b2113cf8"
+content-hash = "f10872bc2f59616bf1093839e7065c82f7d78a88d8db91fa3c05c2ec5f857e7f"

pyproject.toml

@@ -33,7 +33,7 @@ tabulate = "^0.9.0"
 ftfy = "^6.1.1"
 texify = "^0.2.1"
 rapidfuzz = "^3.8.1"
-surya-ocr = "~0.8.2"
+surya-ocr = "~0.8.3"
 regex = "^2024.4.28"
 pdftext = "~0.4.1"
 tabled-pdf = "~0.2.0"

tests/builders/test_strip_existing_ocr.py

@@ -0,0 +1,16 @@
+import pytest
+
+from marker.builders.document import DocumentBuilder
+from marker.builders.layout import LayoutBuilder
+from marker.schema import BlockTypes
+
+@pytest.mark.config({"page_range": [0], "strip_existing_ocr": True})
+@pytest.mark.filename("handwritten.pdf")
+def test_strip_ocr(pdf_provider):
+    # Ensure that the OCR text isn't extracted
+    assert len(pdf_provider.page_lines) == 0
+
+@pytest.mark.config({"page_range": [0]})
+@pytest.mark.filename("handwritten.pdf")
+def test_keep_ocr(pdf_provider):
+    assert len(pdf_provider.page_lines) == 1