fix: add requirements.txt, fix empty debug dir

.gitignore

@@ -0,0 +1,467 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python,linux,macos,windows,vim,emacs,visualstudiocode,pycharm
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,linux,macos,windows,vim,emacs,visualstudiocode,pycharm
+
+activate*
+activate/*
+.env
+
+### Emacs ###
+# -*- mode: gitignore; -*-
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+auto-save-list
+tramp
+.\#*
+
+# Org-mode
+.org-id-locations
+*_archive
+
+# flymake-mode
+*_flymake.*
+
+# eshell files
+/eshell/history
+/eshell/lastdir
+
+# elpa packages
+/elpa/
+
+# reftex files
+*.rel
+
+# AUCTeX auto folder
+/auto/
+
+# cask packages
+.cask/
+dist/
+
+# Flycheck
+flycheck_*.el
+
+# server auth directory
+/server/
+
+# projectiles files
+.projectile
+
+# directory configuration
+.dir-locals.el
+
+# network security
+/network-security.data
+
+### Linux ###
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### PyCharm ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+### PyCharm Patch ###
+# Comment Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-215987721
+
+# *.iml
+# modules.xml
+# .idea/misc.xml
+# *.ipr
+
+# Sonarlint plugin
+# https://plugins.jetbrains.com/plugin/7973-sonarlint
+.idea/**/sonarlint/
+
+# SonarQube Plugin
+# https://plugins.jetbrains.com/plugin/7238-sonarqube-community-plugin
+.idea/**/sonarIssues.xml
+
+# Markdown Navigator plugin
+# https://plugins.jetbrains.com/plugin/7896-markdown-navigator-enhanced
+.idea/**/markdown-navigator.xml
+.idea/**/markdown-navigator-enh.xml
+.idea/**/markdown-navigator/
+
+# Cache file creation bug
+# See https://youtrack.jetbrains.com/issue/JBR-2257
+.idea/$CACHE_FILE$
+
+# CodeStream plugin
+# https://plugins.jetbrains.com/plugin/12206-codestream
+.idea/codestream.xml
+
+# Azure Toolkit for IntelliJ plugin
+# https://plugins.jetbrains.com/plugin/8053-azure-toolkit-for-intellij
+.idea/**/azureSettings.xml
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### Vim ###
+# Swap
+[._]*.s[a-v][a-z]
+!*.svg # comment out if you don't need vector files
+[._]*.sw[a-p]
+[._]s[a-rt-v][a-z]
+[._]ss[a-gi-z]
+[._]sw[a-p]
+
+# Session
+Session.vim
+Sessionx.vim
+
+# Temporary
+.netrwhist
+# Auto-generated tag files
+tags
+# Persistent undo
+[._]*.un~
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# PDF files
+*.pdf
+
+# End of https://www.toptal.com/developers/gitignore/api/python,linux,macos,windows,vim,emacs,visualstudiocode,pycharm
+*.py[coid]
+
+logs/
+.gitsecret/keys/random_seed
+!*.secret
+.envrc
+.env
+
+S.gpg-agent*
+.vscode/settings.json
+examples/example1/assets
+storage/*

app.py

@@ -53,7 +53,7 @@ def convert_document(path, method, enabled=True):
 
 def show_tabs(selected_methods):
     visible_tabs = []
-    for method in supported_methods:
+    for method in SUPPORTED_METHODS:
         visible_tabs.append(gr.update(visible=method in selected_methods))
 
     return visible_tabs
@@ -66,14 +66,14 @@ latex_delimiters = [
 
 # startup test (also for loading models the first time)
 start_startup = time.time()
-test_pdf_path = "/home/tadashi/MinerU/examples/complex_layout.pdf"
-supported_methods = ["Docling", "Marker", "Unstructured", "MinerU", "PyMuPDF"]
+WARMUP_PDF_PATH = "/home/tadashi/MinerU/examples/complex_layout.pdf"
+SUPPORTED_METHODS = ["Docling", "Marker", "Unstructured", "MinerU", "PyMuPDF"]
 
-# print("Warm-up sequence")
-# for method in supported_methods:
-#     for _ in range(1):
-#         convert_document(test_pdf_path, method)
-# print("Start up time", time.time() - start_startup, "seconds")
+print("Warm-up sequence")
+for method in SUPPORTED_METHODS:
+    for _ in range(1):
+        convert_document(WARMUP_PDF_PATH, method)
+print("Start up time", time.time() - start_startup, "seconds")
 
 with gr.Blocks(
     theme=gr.themes.Ocean(),
@@ -84,7 +84,7 @@ with gr.Blocks(
     output_components = []
     output_tabs = []
     visualization_sub_tabs = []
-    first_method = supported_methods[0]
+    first_method = SUPPORTED_METHODS[0]
 
     with gr.Row():
         with gr.Column(variant="panel", scale=5):
@@ -99,7 +99,7 @@ with gr.Blocks(
         with gr.Column(variant="panel", scale=5):
             with gr.Row():
                 methods = gr.Dropdown(
-                    supported_methods,
+                    SUPPORTED_METHODS,
                     label="Conversion methods",
                     value=first_method,
                     multiselect=True,
@@ -125,7 +125,7 @@ with gr.Blocks(
 
         with gr.Column(variant="panel", scale=5):
             with gr.Tabs():
-                for method in supported_methods:
+                for method in SUPPORTED_METHODS:
                     with gr.Tab(method, visible=False) as output_tab:
                         with gr.Tabs():
                             with gr.Tab("Markdown rendering"):
@@ -162,17 +162,17 @@ with gr.Blocks(
         inputs=[methods],
         outputs=output_tabs,
     )
-    for idx, method in enumerate(supported_methods):
+    for idx, method in enumerate(SUPPORTED_METHODS):
 
         def progress_message(selected_methods, method=method):
             selected_methods_indices = [
                 idx
-                for idx, current_method in enumerate(supported_methods)
+                for idx, current_method in enumerate(SUPPORTED_METHODS)
                 if current_method in selected_methods
             ]
             try:
                 current_method_idx = selected_methods_indices.index(
-                    supported_methods.index(method)
+                    SUPPORTED_METHODS.index(method)
                 )
                 msg = (
                     f"Processing ({current_method_idx + 1} / "

backends/docling.py

@@ -42,8 +42,11 @@ def convert_docling(path: str, file_name: str):
     result = docling_converter.convert(path)
     text = result.document.export_to_markdown(image_mode=ImageRefMode.EMBEDDED)
     debug_image_dir = DOCLING_DEBUG_PATH / f"debug_{file_name}"
-    debug_image_paths = [
-        path for path in debug_image_dir.iterdir() if path.suffix == ".png"
-    ]
+    if debug_image_dir.exists():
+        debug_image_paths = [
+            path for path in debug_image_dir.iterdir() if path.suffix == ".png"
+        ]
+    else:
+        debug_image_paths = []
 
     return text, debug_image_paths

backends/marker.py

@@ -53,8 +53,11 @@ def convert_marker(path: str, file_name: str):
     text, _, images = text_from_rendered(rendered)
     text = markdown_insert_images(text, images)
     debug_image_dir = Path(rendered.metadata.get("debug_data_path"))
-    debug_image_paths = [
-        path for path in debug_image_dir.iterdir() if "pdf_page" in path.stem
-    ]
+    if debug_image_dir.exists():
+        debug_image_paths = [
+            path for path in debug_image_dir.iterdir() if "pdf_page" in path.stem
+        ]
+    else:
+        debug_image_paths = []
 
     return text, debug_image_paths

backends/mineru.py

@@ -72,11 +72,13 @@ def convert_mineru(path: str, file_name: str):
     text = replace_image_with_base64(text, local_md_dir)
 
     debug_pdf = str(local_md_dir / (file_name + "_layout.pdf"))
-    doc = pymupdf.open(debug_pdf)  # open document
-    for page in doc:  # iterate through the pages
-        pix = page.get_pixmap()  # render page to an image
-        page_debug_path = str(output_path / ("page-%i.png" % page.number))
-        debug_image_paths.append(page_debug_path)
-        pix.save(page_debug_path)  # store image as a PNG
+
+    if Path(debug_pdf).exists():
+        doc = pymupdf.open(debug_pdf)  # open document
+        for page in doc:  # iterate through the pages
+            pix = page.get_pixmap()  # render page to an image
+            page_debug_path = str(output_path / ("page-%i.png" % page.number))
+            debug_image_paths.append(page_debug_path)
+            pix.save(page_debug_path)  # store image as a PNG
 
     return text, debug_image_paths

backends/unstructured.py

@@ -66,8 +66,11 @@ def convert_unstructured(path: str, file_name: str):
     )
     text = convert_elements_to_markdown(elements)
     debug_image_dir = UNSTRUCTURED_DEBUG_PATH / "analysis" / file_name / "bboxes"
-    debug_image_paths = [
-        path for path in debug_image_dir.iterdir() if "od_model" in path.stem
-    ]
+    if debug_image_dir.exists():
+        debug_image_paths = [
+            path for path in debug_image_dir.iterdir() if "od_model" in path.stem
+        ]
+    else:
+        debug_image_paths = []
 
     return text, debug_image_paths

requirements.txt

@@ -0,0 +1,20 @@
+torch>=2.2.2,<=2.3.1
+torchvision>=0.17.2,<=0.18.1
+paddlepaddle-gpu @ https://paddle-whl.bj.bcebos.com/stable/cu118/paddlepaddle-gpu/paddlepaddle_gpu-3.0.0b1-cp310-cp310-linux_x86_64.whl
+detectron2 @ https://wheels-1251341229.cos.ap-shanghai.myqcloud.com/assets/whl/detectron2/detectron2-0.6-cp310-cp310-linux_x86_64.whl
+paddleocr==2.7.3
+rapid-table>=1.0.3,<2.0.0
+rapidocr-paddle
+rapidocr-onnxruntime
+gradio-pdf>=0.0.21
+git+https://github.com/opendatalab/MinerU.git@dev
+git+https://github.com/VikParuchuri/marker
+docling
+PyMuPDF>=1.24.9,<1.24.14
+pymupdf4llm
+unstructured[pdf]
+ultralytics>=8.3.48
+unimernet==0.2.3
+transformers<5.0.0,>=4.45.2
+struct-eqtable==0.3.2
+openai

utils.py

@@ -1,3 +1,4 @@
+import functools
 import re
 from pathlib import Path
 from shutil import copy2
@@ -12,6 +13,7 @@ def remove_images_from_markdown(markdown_text):
     return markdown_text
 
 
+@functools.lru_cache(maxsize=None)
 def trim_pages(pdf_path, output_path, trim_pages=5):
     doc = pymupdf.open(pdf_path)
     parent_dir_name = Path(pdf_path).parent.name