docling-parse 1.3.0__tar.gz

docling_parse-1.3.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) [year] [fullname]
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

docling_parse-1.3.0/PKG-INFO

@@ -0,0 +1,208 @@
+Metadata-Version: 2.1
+Name: docling-parse
+Version: 1.3.0
+Summary: Simple package to extract text with coordinates from programmatic PDFs
+Home-page: https://github.com/DS4SD/docling-parse
+License: MIT
+Keywords: docling,pdf,parser
+Author: Peter Staar
+Author-email: taa@zurich.ibm.com
+Maintainer: Peter Staar
+Maintainer-email: taa@zurich.ibm.com
+Requires-Python: >=3.9,<4.0
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: C++
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: tabulate (>=0.9.0,<1.0.0)
+Project-URL: Repository, https://github.com/DS4SD/docling-parse
+Description-Content-Type: text/markdown
+
+# Docling Parse
+
+[![PyPI version](https://img.shields.io/pypi/v/docling-parse)](https://pypi.org/project/docling-parse/)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling-parse)](https://pypi.org/project/docling-parse/)
+[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
+[![Pybind11](https://img.shields.io/badge/build-pybind11-blue)](https://github.com/pybind/pybind11/)
+[![Platforms](https://img.shields.io/badge/platform-macos%20|%20linux%20|%20windows-blue)](https://github.com/DS4SD/docling-parse/)
+[![License MIT](https://img.shields.io/github/license/DS4SD/docling-parse)](https://opensource.org/licenses/MIT)
+
+Simple package to extract text with coordinates from programmatic PDFs.
+This package is part of the [Docling](https://github.com/DS4SD/docling) conversion.
+
+
+## Quick start
+
+Install the package from Pypi
+
+```sh
+pip install docling-parse
+```
+
+Convert a PDF
+
+```python
+from docling_parse.docling_parse import pdf_parser
+
+# Do this only once to load fonts (avoid initialising it many times)
+parser = pdf_parser()
+
+# parser.set_loglevel(1) # 1=error, 2=warning, 3=success, 4=info
+
+doc_file = "my-doc.pdf" # filename
+doc_key = f"key={pdf_doc}" # unique document key (eg hash, UUID, etc)
+
+# Load the document from file using filename doc_file. This only loads
+# the QPDF document, but no extracted data
+success = parser.load_document(doc_key, doc_file)
+
+# Open the file in binary mode and read its contents
+# with open(pdf_doc, "rb") as file:
+#      file_content = file.read()
+
+# Create a BytesIO object and write the file contents to it
+# bytes_io = io.BytesIO(file_content)
+# success = parser.load_document_from_bytesio(doc_key, bytes_io)
+
+# Parse the entire document in one go, easier, but could require
+# a lot (more) memory as parsing page-by-page
+# json_doc = parser.parse_pdf_from_key(doc_key)	
+
+# Get number of pages
+num_pages = parser.number_of_pages(doc_key)
+
+# Parse page by page to minimize memory footprint
+for page in range(0, num_pages):
+
+    # Internal memory for page is auto-deleted after this call.
+    # No need to unload a specifc page 
+    json_doc = parser.parse_pdf_from_key_on_page(doc_key, page)
+
+    if "pages" not in json_doc:  # page could not get parsed
+       continue
+
+    # parsed page is the first one!				  
+    json_page = json_doc["pages"][0] 
+    
+    page_dimensions = [json_page["dimensions"]["width"], json_page["dimensions"]["height"]]
+
+    # find text cells
+    cells=[]
+    for cell_id,cell in enumerate(json_page["cells"]):
+    	cells.append([page,
+	              cell_id,
+		      cell["content"]["rnormalized"], # text
+	              cell["box"]["device"][0], # x0 (lower left x)
+		      cell["box"]["device"][1], # y0 (lower left y)
+		      cell["box"]["device"][2], # x1 (upper right x)
+		      cell["box"]["device"][3], # y1 (upper right y)	
+		      ])
+
+    # find bitmap images
+    images=[]
+    for image_id,image in enumerate(json_page["images"]):
+    	images.append([page,
+	               image_id,
+	               image["box"][0], # x0 (lower left x)
+		       image["box"][1], # y0 (lower left y)
+		       image["box"][2], # x1 (upper right x)
+		       image["box"][3], # y1 (upper right y)
+		       ])
+
+    # find paths
+    paths=[]
+    for path_id,path in enumerate(json_page["paths"]):
+    	paths.append([page,
+	              path_id,
+	              path["x-values"], # array of x values
+	              path["y-values"], # array of y values
+		      ])
+
+# Unload the (QPDF) document and buffers
+parser.unload_document(doc_key)
+
+# Unloads everything at once
+# parser.unload_documents()
+```
+
+Use the CLI
+
+```sh
+$ docling-parse -h
+usage: docling-parse [-h] -p PDF
+
+Process a PDF file.
+
+options:
+  -h, --help         show this help message and exit
+  -p PDF, --pdf PDF  Path to the PDF file
+```
+
+## Development
+
+### CXX
+
+To build the parse, simply run the following command in the root folder,
+
+```sh
+rm -rf build; cmake -B ./build; cd build; make
+```
+
+You can run the parser from your build folder with
+
+```sh
+./parse.exe <input-file> <optional-logging:true>
+```
+
+If you dont have an input file, then a template input file will be printed on the terminal.
+
+
+### Python
+
+To build the package, simply run (make sure [poetry](https://python-poetry.org/) is [installed](https://python-poetry.org/docs/#installing-with-the-official-installer)),
+
+```
+poetry build
+```
+
+To test the package, run,
+
+```
+poetry run pytest ./tests/test_parse.py
+```
+
+
+## Contributing
+
+Please read [Contributing to Docling Parse](https://github.com/DS4SD/docling-parse/blob/main/CONTRIBUTING.md) for details.
+
+
+## References
+
+If you use Docling in your projects, please consider citing the following:
+
+```bib
+@software{Docling,
+author = {Deep Search Team},
+month = {7},
+title = {{Docling}},
+url = {https://github.com/DS4SD/docling},
+version = {main},
+year = {2024}
+}
+```
+
+## License
+
+The Docling Parse codebase is under MIT license.
+For individual model usage, please refer to the model licenses found in the original packages.
+

docling_parse-1.3.0/README.md

@@ -0,0 +1,178 @@
+# Docling Parse
+
+[![PyPI version](https://img.shields.io/pypi/v/docling-parse)](https://pypi.org/project/docling-parse/)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling-parse)](https://pypi.org/project/docling-parse/)
+[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
+[![Pybind11](https://img.shields.io/badge/build-pybind11-blue)](https://github.com/pybind/pybind11/)
+[![Platforms](https://img.shields.io/badge/platform-macos%20|%20linux%20|%20windows-blue)](https://github.com/DS4SD/docling-parse/)
+[![License MIT](https://img.shields.io/github/license/DS4SD/docling-parse)](https://opensource.org/licenses/MIT)
+
+Simple package to extract text with coordinates from programmatic PDFs.
+This package is part of the [Docling](https://github.com/DS4SD/docling) conversion.
+
+
+## Quick start
+
+Install the package from Pypi
+
+```sh
+pip install docling-parse
+```
+
+Convert a PDF
+
+```python
+from docling_parse.docling_parse import pdf_parser
+
+# Do this only once to load fonts (avoid initialising it many times)
+parser = pdf_parser()
+
+# parser.set_loglevel(1) # 1=error, 2=warning, 3=success, 4=info
+
+doc_file = "my-doc.pdf" # filename
+doc_key = f"key={pdf_doc}" # unique document key (eg hash, UUID, etc)
+
+# Load the document from file using filename doc_file. This only loads
+# the QPDF document, but no extracted data
+success = parser.load_document(doc_key, doc_file)
+
+# Open the file in binary mode and read its contents
+# with open(pdf_doc, "rb") as file:
+#      file_content = file.read()
+
+# Create a BytesIO object and write the file contents to it
+# bytes_io = io.BytesIO(file_content)
+# success = parser.load_document_from_bytesio(doc_key, bytes_io)
+
+# Parse the entire document in one go, easier, but could require
+# a lot (more) memory as parsing page-by-page
+# json_doc = parser.parse_pdf_from_key(doc_key)	
+
+# Get number of pages
+num_pages = parser.number_of_pages(doc_key)
+
+# Parse page by page to minimize memory footprint
+for page in range(0, num_pages):
+
+    # Internal memory for page is auto-deleted after this call.
+    # No need to unload a specifc page 
+    json_doc = parser.parse_pdf_from_key_on_page(doc_key, page)
+
+    if "pages" not in json_doc:  # page could not get parsed
+       continue
+
+    # parsed page is the first one!				  
+    json_page = json_doc["pages"][0] 
+    
+    page_dimensions = [json_page["dimensions"]["width"], json_page["dimensions"]["height"]]
+
+    # find text cells
+    cells=[]
+    for cell_id,cell in enumerate(json_page["cells"]):
+    	cells.append([page,
+	              cell_id,
+		      cell["content"]["rnormalized"], # text
+	              cell["box"]["device"][0], # x0 (lower left x)
+		      cell["box"]["device"][1], # y0 (lower left y)
+		      cell["box"]["device"][2], # x1 (upper right x)
+		      cell["box"]["device"][3], # y1 (upper right y)	
+		      ])
+
+    # find bitmap images
+    images=[]
+    for image_id,image in enumerate(json_page["images"]):
+    	images.append([page,
+	               image_id,
+	               image["box"][0], # x0 (lower left x)
+		       image["box"][1], # y0 (lower left y)
+		       image["box"][2], # x1 (upper right x)
+		       image["box"][3], # y1 (upper right y)
+		       ])
+
+    # find paths
+    paths=[]
+    for path_id,path in enumerate(json_page["paths"]):
+    	paths.append([page,
+	              path_id,
+	              path["x-values"], # array of x values
+	              path["y-values"], # array of y values
+		      ])
+
+# Unload the (QPDF) document and buffers
+parser.unload_document(doc_key)
+
+# Unloads everything at once
+# parser.unload_documents()
+```
+
+Use the CLI
+
+```sh
+$ docling-parse -h
+usage: docling-parse [-h] -p PDF
+
+Process a PDF file.
+
+options:
+  -h, --help         show this help message and exit
+  -p PDF, --pdf PDF  Path to the PDF file
+```
+
+## Development
+
+### CXX
+
+To build the parse, simply run the following command in the root folder,
+
+```sh
+rm -rf build; cmake -B ./build; cd build; make
+```
+
+You can run the parser from your build folder with
+
+```sh
+./parse.exe <input-file> <optional-logging:true>
+```
+
+If you dont have an input file, then a template input file will be printed on the terminal.
+
+
+### Python
+
+To build the package, simply run (make sure [poetry](https://python-poetry.org/) is [installed](https://python-poetry.org/docs/#installing-with-the-official-installer)),
+
+```
+poetry build
+```
+
+To test the package, run,
+
+```
+poetry run pytest ./tests/test_parse.py
+```
+
+
+## Contributing
+
+Please read [Contributing to Docling Parse](https://github.com/DS4SD/docling-parse/blob/main/CONTRIBUTING.md) for details.
+
+
+## References
+
+If you use Docling in your projects, please consider citing the following:
+
+```bib
+@software{Docling,
+author = {Deep Search Team},
+month = {7},
+title = {{Docling}},
+url = {https://github.com/DS4SD/docling},
+version = {main},
+year = {2024}
+}
+```
+
+## License
+
+The Docling Parse codebase is under MIT license.
+For individual model usage, please refer to the model licenses found in the original packages.

docling_parse-1.3.0/build.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python
+
+import os
+
+import sys
+
+import subprocess
+
+ROOT_DIR = os.path.abspath("./")
+BUILD_DIR = os.path.join(ROOT_DIR, "build")
+
+
+def run(cmd, cwd="./"):
+
+    print(f"\nlaunch: {cmd}")
+
+    parts = cmd.split(" ")
+    message = subprocess.run(parts, cwd=cwd)
+
+    if "returncode=0" in str(message):
+        print(f" -> SUCCESS")
+        return True
+
+    print(f" -> ERROR with message: '{message}'\n")
+    return False
+
+
+def build_local(num_threads: int):
+
+    if not os.path.exists(BUILD_DIR):
+        print("python executable: ", sys.executable)
+
+        cmd = f"cmake -B {BUILD_DIR} -DPYTHON_EXECUTABLE={sys.executable}"
+        success = run(cmd, cwd=ROOT_DIR)
+        if not success:
+            raise RuntimeError("Error building.")
+    else:
+        print(f"build directory detected: {BUILD_DIR}")
+
+    cmd = f"cmake --build {BUILD_DIR} --target install"
+    if num_threads > 1:
+        cmd += f" -j {num_threads}"
+    success = run(cmd, cwd=ROOT_DIR)
+    if not success:
+        raise RuntimeError("Error building.")
+
+
+if "__main__" == __name__:
+    num_threads = int(os.getenv("BUILD_THREADS", "4"))
+    build_local(num_threads=num_threads)

docling_parse-1.3.0/docling_parse/eval.py

@@ -0,0 +1,104 @@
+import argparse
+import glob
+import io
+import os
+
+from tabulate import tabulate
+
+# from docling_parse.docling_parse import pdf_parser
+import docling_parse
+from docling_parse import pdf_parser
+
+
+def main():
+    # Create the argument parser
+    parser = argparse.ArgumentParser(description="Process a PDF file.")
+
+    # Add an argument for the path to the PDF file
+    parser.add_argument(
+        "-l",
+        "--log-level",
+        type=int,
+        required=False,
+        default=2,
+        help="log-level 1,2,3,4",
+    )
+
+    # Add an argument for the path to the PDF file
+    parser.add_argument(
+        "-d",
+        "--pdfdir",
+        type=str,
+        help="Path to the directory with PDF files",
+        required=True,
+    )
+
+    # Add an argument for the path to the PDF file
+    parser.add_argument(
+        "-m",
+        "--max-docs",
+        type=int,
+        required=False,
+        default=None,
+        help="max number of documents to run on",
+    )
+
+    # Parse the command-line arguments
+    args = parser.parse_args()
+    print(f"The provided PDF path is: {args.pdfdir}")
+
+    # Check if the provided path is valid
+    if not os.path.exists(args.pdfdir):
+        print(f"Error: The directory {args.pdfdir} does not exist.")
+        return
+
+    # Print the path to the PDF file (or add your processing logic here)
+
+    parser = docling_parse.pdf_parser()
+    parser.set_loglevel(args.log_level)
+
+    overview = []
+
+    doc_files = sorted(glob.glob(os.path.join(args.pdfdir, "*.pdf")))
+    if args.max_docs != None:
+        doc_files = doc_files[0 : args.max_docs]
+
+    for doc_id, doc_file in enumerate(doc_files):
+        print(doc_file)
+
+        doc_key = f"key={doc_file}"  # unique document key (eg hash, UUID, etc)
+
+        # Load the document
+        success = parser.load_document(doc_key, doc_file)
+        # parser.set_loglevel(args.log_level)
+
+        # Get number of pages
+        num_pages = parser.number_of_pages(doc_key)
+        print("#-pages: ", num_pages)
+
+        failed = False
+
+        try:
+            # Parse page by page to minimize memory footprint
+            for page in range(0, num_pages):
+                json_doc = parser.parse_pdf_from_key_on_page(doc_key, page)
+
+                if "pages" not in json_doc:  # page could not get parsed
+                    print(f"ERROR: page {page} is not parsed ... ")
+                    failed = True
+                else:
+                    print(f"SUCCESS: page {page} is parsed ... ")
+        except Exception as e:
+            print(f"ERROR: page {page} is not parsed: {e}")
+            failed = True
+
+        # Unload the document
+        parser.unload_document(doc_key)
+
+        overview.append([doc_file, (not failed), num_pages])
+
+    print(tabulate(overview, headers=["filename", "success", "#-pages"]))
+
+
+if __name__ == "__main__":
+    main()

docling_parse-1.3.0/docling_parse/pdf_resources/cmap-resources/Adobe-CNS1-7/CMap/Adobe-CNS1-0

@@ -0,0 +1,134 @@
+%!PS-Adobe-3.0 Resource-CMap
+%%DocumentNeededResources: ProcSet (CIDInit)
+%%IncludeResource: ProcSet (CIDInit)
+%%BeginResource: CMap (Identity)
+%%Title: (Identity Adobe CNS1 0)
+%%Version: 10.006
+%%Copyright: -----------------------------------------------------------
+%%Copyright: Copyright 1990-2019 Adobe. All rights reserved.
+%%Copyright:
+%%Copyright: Redistribution and use in source and binary forms, with or
+%%Copyright: without modification, are permitted provided that the
+%%Copyright: following conditions are met:
+%%Copyright:
+%%Copyright: Redistributions of source code must retain the above
+%%Copyright: copyright notice, this list of conditions and the following
+%%Copyright: disclaimer.
+%%Copyright:
+%%Copyright: Redistributions in binary form must reproduce the above
+%%Copyright: copyright notice, this list of conditions and the following
+%%Copyright: disclaimer in the documentation and/or other materials
+%%Copyright: provided with the distribution. 
+%%Copyright:
+%%Copyright: Neither the name of Adobe nor the names of its contributors
+%%Copyright: may be used to endorse or promote products derived from
+%%Copyright: this software without specific prior written permission.
+%%Copyright:
+%%Copyright: THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+%%Copyright: CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+%%Copyright: INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+%%Copyright: MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+%%Copyright: DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR
+%%Copyright: CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+%%Copyright: SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+%%Copyright: NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+%%Copyright: LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+%%Copyright: HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+%%Copyright: CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+%%Copyright: OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+%%Copyright: SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+%%Copyright: -----------------------------------------------------------
+%%EndComments
+
+/CIDInit /ProcSet findresource begin
+
+12 dict begin
+
+begincmap
+
+/CIDSystemInfo 3 dict dup begin
+  /Registry (Adobe) def
+  /Ordering (CNS1) def
+  /Supplement 0 def
+end def
+
+/CMapName /Adobe-CNS1-0 def
+/CMapVersion 10.006 def
+/CMapType 1 def
+
+/UIDOffset 960 def
+/XUID [1 10 25394] def
+
+/WMode 0 def
+
+/CIDCount 14099 def
+
+1 begincodespacerange
+  <0000> <37FF>
+endcodespacerange
+
+56 begincidrange
+<0000> <00ff>     0
+<0100> <01ff>   256
+<0200> <02ff>   512
+<0300> <03ff>   768
+<0400> <04ff>  1024
+<0500> <05ff>  1280
+<0600> <06ff>  1536
+<0700> <07ff>  1792
+<0800> <08ff>  2048
+<0900> <09ff>  2304
+<0a00> <0aff>  2560
+<0b00> <0bff>  2816
+<0c00> <0cff>  3072
+<0d00> <0dff>  3328
+<0e00> <0eff>  3584
+<0f00> <0fff>  3840
+<1000> <10ff>  4096
+<1100> <11ff>  4352
+<1200> <12ff>  4608
+<1300> <13ff>  4864
+<1400> <14ff>  5120
+<1500> <15ff>  5376
+<1600> <16ff>  5632
+<1700> <17ff>  5888
+<1800> <18ff>  6144
+<1900> <19ff>  6400
+<1a00> <1aff>  6656
+<1b00> <1bff>  6912
+<1c00> <1cff>  7168
+<1d00> <1dff>  7424
+<1e00> <1eff>  7680
+<1f00> <1fff>  7936
+<2000> <20ff>  8192
+<2100> <21ff>  8448
+<2200> <22ff>  8704
+<2300> <23ff>  8960
+<2400> <24ff>  9216
+<2500> <25ff>  9472
+<2600> <26ff>  9728
+<2700> <27ff>  9984
+<2800> <28ff> 10240
+<2900> <29ff> 10496
+<2a00> <2aff> 10752
+<2b00> <2bff> 11008
+<2c00> <2cff> 11264
+<2d00> <2dff> 11520
+<2e00> <2eff> 11776
+<2f00> <2fff> 12032
+<3000> <30ff> 12288
+<3100> <31ff> 12544
+<3200> <32ff> 12800
+<3300> <33ff> 13056
+<3400> <34ff> 13312
+<3500> <35ff> 13568
+<3600> <36ff> 13824
+<3700> <3712> 14080
+endcidrange
+endcmap
+CMapName currentdict /CMap defineresource pop
+end
+end
+
+%%EndResource
+%%EOF