chore: Remove PDF parsing code and dependencies (Unstructured-IO#75)

Remove PDF parsing code and dependencies.

.github/workflows/ci.yml

@@ -25,8 +25,11 @@ jobs:
         path: |
           .venv
           nltk_data
-        key: ${{ runner.os }}-${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements/*.txt') }}
-
+        key: unstructured-${{ runner.os }}-${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements/*.txt') }}
+    - name: Set up Python ${{ env.PYTHON_VERSION }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ env.PYTHON_VERSION }}
     - name: Setup virtual environment (no cache hit)
       if: steps.virtualenv-cache.outputs.cache-hit != 'true'
       run: |
@@ -43,9 +46,13 @@ jobs:
       id: virtualenv-cache
       with:
         path: .venv
-        key: ${{ runner.os }}-${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements/*.txt') }}
+        key: unstructured-${{ runner.os }}-${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements/*.txt') }}
     # NOTE(robinson) - This is a fallback in case the lint job does not find the cache.
     # We can take this out when we implement the fix in CORE-99
+    - name: Set up Python ${{ env.PYTHON_VERSION }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ env.PYTHON_VERSION }}
     - name: Setup virtual environment (no cache hit)
       if: steps.virtualenv-cache.outputs.cache-hit != 'true'
       run: |
@@ -77,7 +84,7 @@ jobs:
         path: |
           .venv
           nltk_data
-        key: ${{ runner.os }}-${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements/*.txt') }}
+        key: unstructured-${{ runner.os }}-${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements/*.txt') }}
     # NOTE(robinson) - This is a fallback in case the lint job does not find the cache.
     # We can take this out when we implement the fix in CORE-99
     - name: Setup virtual environment (no cache hit)

CHANGELOG.md

@@ -1,4 +1,8 @@
-## 0.2.6-dev1
+## 0.3.0-dev1
+
+* Removing the local PDF parsing code and any dependencies and tests.
+
+## 0.2.6
 
 * Small change to how _read is placed within the inheritance structure since it doesn't really apply to pdf
 * Add partitioning brick for calling the document image analysis API

Makefile

@@ -17,10 +17,10 @@ install-base: install-base-pip-packages install-nltk-models
 
 ## install:                 installs all test, dev, and experimental requirements
 .PHONY: install
-install: install-base-pip-packages install-dev install-detectron2 install-nltk-models install-test
+install: install-base-pip-packages install-dev install-nltk-models install-test
 
 .PHONY: install-ci
-install-ci: install-base-pip-packages install-pdf install-test install-nltk-models install-huggingface
+install-ci: install-base-pip-packages install-test install-nltk-models install-huggingface
 
 .PHONY: install-base-pip-packages
 install-base-pip-packages:
@@ -32,18 +32,6 @@ install-huggingface:
 	python3 -m pip install pip==${PIP_VERSION}
 	pip install -r requirements/huggingface.txt
 
-.PHONY: install-pdf
-install-pdf:
-	python3 -m pip install pip==${PIP_VERSION}
-	pip install -r requirements/pdf.txt
-	@echo "\n\n========================================================================"
-	@echo " WARNING: PDF parsing capabilities in unstructured is still experimental"
-	@echo "========================================================================\n\n"
-
-.PHONY: install-detectron2
-install-detectron2: install-pdf
-	pip install "detectron2@git+https://github.com/facebookresearch/detectron2.git@v0.6#egg=detectron2"
-
 .PHONE: install-nltk-models
 install-nltk-models:
 	python -c "import nltk; nltk.download('punkt')"
@@ -67,12 +55,9 @@ pip-compile:
 	pip-compile -o requirements/base.txt
 	# Extra requirements for huggingface staging functions
 	pip-compile --extra huggingface -o requirements/huggingface.txt
-	# Extra requirements for parsing PDF files
-	pip-compile --extra pdf -o requirements/pdf.txt
 	# NOTE(robinson) - We want the dependencies for detectron2 in the requirements.txt, but not
 	# the detectron2 repo itself. If detectron2 is in the requirements.txt file, an order of
 	# operations issue related to the torch library causes the install to fail
-	sed 's/^detectron2 @/# detectron2 @/g' requirements/pdf.txt
 	pip-compile requirements/dev.in
 	pip-compile requirements/test.in
 	pip-compile requirements/build.in

README.md

@@ -88,17 +88,16 @@ titles and narrative text.
 
 ### PDF Parsing
 
-You can use the following workflow to parse PDF documents. Note, PDF parsing is currently
-expiremental and will be refined in the coming months.
+You can use the following workflow to parse PDF documents.
 
 ```python
-from unstructured.documents.pdf import PDFDocument
+from unstructured.nlp.partition import partition_pdf
 
-doc = PDFDocument.from_file("example-docs/layout-parser-paper.pdf")
+elements = partition_pdf("example-docs/layout-parser-paper.pdf")
 print(doc)
 ```
 
-At this point, `print(doc)` will print out a string representation of the PDF file. The
+At this point, `print(elements)` will print out a string representation of the PDF file. The
 first page of output looks like the following:
 
 ```

docs/requirements.txt

@@ -8,7 +8,7 @@ alabaster==0.7.12
     # via sphinx
 babel==2.10.3
     # via sphinx
-certifi==2022.9.14
+certifi==2022.9.24
     # via requests
 charset-normalizer==2.1.1
     # via requests
@@ -38,11 +38,11 @@ requests==2.28.1
     # via sphinx
 snowballstemmer==2.2.0
     # via sphinx
-sphinx==5.2.3
+sphinx==5.3.0
     # via
     #   -r requirements/build.in
     #   sphinx-rtd-theme
-sphinx-rtd-theme==1.0.0
+sphinx-rtd-theme==1.1.1
     # via -r requirements/build.in
 sphinxcontrib-applehelp==1.0.2
     # via sphinx
@@ -58,5 +58,5 @@ sphinxcontrib-serializinghtml==1.1.5
     # via sphinx
 urllib3==1.26.12
     # via requests
-zipp==3.9.0
+zipp==3.10.0
     # via importlib-metadata

docs/source/installing.rst

@@ -3,8 +3,7 @@ Installation
 
 You can install the library by cloning the repo and running ``make install`` from the
 root directory. Developers can run ``make install-local`` to install the dev and test
-requirements alongside the base requirements. Specific parsing capabilities may require
-extra dependencies, as documented below. If you want a minimal installation without any
+requirements alongside the base requirements. If you want a minimal installation without any
 parser specific dependencies, run ``make install-base``.
 
 Logging
@@ -37,23 +36,6 @@ that with:
 		$ brew install libxml2
 		$ brew install libxslt
 
-================
-PDF Dependencies
-================
-
-Currently, PDF parsing capabilities rely on the
-`Detectron2 <https://github.com/facebookresearch/detectron2>`_ object detection model. The
-``make install-local`` command installs all of the dependencies for Detectron2. If you
-need to parse PDFs and Detectron2 is not already installed, you can install it with
-``make install-detectron2``.
-
-Also ensure that you have ``poppler`` installed on your system. On a Mac, you can run:
-
-.. code:: console
-
-		$ brew install poppler
-
-
 ========================
 Huggingface Dependencies
 ========================

requirements/build.txt

@@ -20,6 +20,8 @@ idna==3.4
     # via requests
 imagesize==1.4.1
     # via sphinx
+importlib-metadata==5.0.0
+    # via sphinx
 jinja2==3.1.2
     # via sphinx
 markupsafe==2.1.1
@@ -38,10 +40,10 @@ snowballstemmer==2.2.0
     # via sphinx
 sphinx==5.3.0
     # via
-    #   -r build.in
+    #   -r requirements/build.in
     #   sphinx-rtd-theme
 sphinx-rtd-theme==1.1.1
-    # via -r build.in
+    # via -r requirements/build.in
 sphinxcontrib-applehelp==1.0.2
     # via sphinx
 sphinxcontrib-devhelp==1.0.2
@@ -56,3 +58,5 @@ sphinxcontrib-serializinghtml==1.1.5
     # via sphinx
 urllib3==1.26.12
     # via requests
+zipp==3.10.0
+    # via importlib-metadata

requirements/dev.txt

@@ -4,6 +4,10 @@
 #
 #    pip-compile requirements/dev.in
 #
+appnope==0.1.3
+    # via
+    #   ipykernel
+    #   ipython
 argon2-cffi==21.3.0
     # via notebook
 argon2-cffi-bindings==21.2.0
@@ -36,6 +40,10 @@ executing==1.0.0
     # via stack-data
 fastjsonschema==2.16.2
     # via nbformat
+importlib-metadata==5.0.0
+    # via nbconvert
+importlib-resources==5.10.0
+    # via jsonschema
 ipykernel==6.15.3
     # via
     #   ipywidgets
@@ -45,7 +53,7 @@ ipykernel==6.15.3
     #   qtconsole
 ipython==8.6.0
     # via
-    #   -r dev.in
+    #   -r requirements/dev.in
     #   ipykernel
     #   ipywidgets
     #   jupyter-console
@@ -64,7 +72,7 @@ jinja2==3.1.2
 jsonschema==4.16.0
     # via nbformat
 jupyter==1.0.0
-    # via -r dev.in
+    # via -r requirements/dev.in
 jupyter-client==7.3.5
     # via
     #   ipykernel
@@ -133,7 +141,9 @@ pexpect==4.8.0
 pickleshare==0.7.5
     # via ipython
 pip-tools==6.10.0
-    # via -r dev.in
+    # via -r requirements/dev.in
+pkgutil-resolve-name==1.3.10
+    # via jsonschema
 prometheus-client==0.14.1
     # via notebook
 prompt-toolkit==3.0.31
@@ -187,6 +197,10 @@ terminado==0.15.0
     # via notebook
 tinycss2==1.1.1
     # via nbconvert
+tomli==2.0.1
+    # via
+    #   build
+    #   pep517
 tornado==6.2
     # via
     #   ipykernel
@@ -216,6 +230,10 @@ wheel==0.37.1
     # via pip-tools
 widgetsnbextension==4.0.3
     # via ipywidgets
+zipp==3.10.0
+    # via
+    #   importlib-metadata
+    #   importlib-resources
 
 # The following packages are considered to be unsafe in a requirements file:
 # pip