feat: better image support

CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.2.13-dev0
+
+* Change OCR logic to be aware of PDF image elements
+
 ## 0.2.12
 
 * Fix for processing RGBA images

requirements/base.txt

@@ -12,7 +12,7 @@ certifi==2022.12.7
     # via requests
 cffi==1.15.1
     # via cryptography
-charset-normalizer==3.0.1
+charset-normalizer==3.1.0
     # via
     #   pdfminer-six
     #   requests
@@ -22,25 +22,26 @@ coloredlogs==15.0.1
     # via onnxruntime
 contourpy==1.0.7
     # via matplotlib
-cryptography==39.0.1
+cryptography==39.0.2
     # via pdfminer-six
 cycler==0.11.0
     # via matplotlib
 effdet==0.3.0
     # via layoutparser
-fastapi==0.92.0
+fastapi==0.95.0
     # via unstructured-inference (setup.py)
-filelock==3.9.0
+filelock==3.10.0
     # via
     #   huggingface-hub
+    #   torch
     #   transformers
-flatbuffers==23.1.21
+flatbuffers==23.3.3
     # via onnxruntime
-fonttools==4.38.0
+fonttools==4.39.2
     # via matplotlib
 h11==0.14.0
     # via uvicorn
-huggingface-hub==0.12.1
+huggingface-hub==0.13.3
     # via
     #   timm
     #   transformers
@@ -55,14 +56,20 @@ importlib-resources==5.12.0
     # via matplotlib
 iopath==0.1.10
     # via layoutparser
+jinja2==3.1.2
+    # via torch
 kiwisolver==1.4.4
     # via matplotlib
 layoutparser[layoutmodels,tesseract]==0.3.4
     # via unstructured-inference (setup.py)
-matplotlib==3.7.0
+markupsafe==2.1.2
+    # via jinja2
+matplotlib==3.7.1
     # via pycocotools
-mpmath==1.2.1
+mpmath==1.3.0
     # via sympy
+networkx==3.0
+    # via torch
 numpy==1.24.2
     # via
     #   contourpy
@@ -92,7 +99,7 @@ packaging==23.0
     #   transformers
 pandas==1.5.3
     # via layoutparser
-pdf2image==1.16.2
+pdf2image==1.16.3
     # via layoutparser
 pdfminer-six==20221105
     # via pdfplumber
@@ -108,13 +115,13 @@ pillow==9.4.0
     #   torchvision
 portalocker==2.7.0
     # via iopath
-protobuf==4.22.0
+protobuf==4.22.1
     # via onnxruntime
 pycocotools==2.0.6
     # via effdet
 pycparser==2.21
     # via cffi
-pydantic==1.10.5
+pydantic==1.10.6
     # via fastapi
 pyparsing==3.0.9
     # via matplotlib
@@ -142,39 +149,39 @@ requests==2.28.2
     #   huggingface-hub
     #   torchvision
     #   transformers
-scipy==1.10.0
+scipy==1.10.1
     # via layoutparser
 six==1.16.0
-    # via
-    #   python-dateutil
-    #   python-multipart
+    # via python-dateutil
 sniffio==1.3.0
     # via anyio
-starlette==0.25.0
+starlette==0.26.1
     # via fastapi
 sympy==1.11.1
-    # via onnxruntime
+    # via
+    #   onnxruntime
+    #   torch
 timm==0.6.12
     # via effdet
 tokenizers==0.13.2
     # via transformers
-torch==1.13.1
+torch==2.0.0
     # via
     #   effdet
     #   layoutparser
     #   timm
     #   torchvision
-torchvision==0.14.1
+torchvision==0.15.1
     # via
     #   effdet
     #   layoutparser
     #   timm
-tqdm==4.64.1
+tqdm==4.65.0
     # via
     #   huggingface-hub
     #   iopath
     #   transformers
-transformers==4.26.1
+transformers==4.27.2
     # via unstructured-inference (setup.py)
 typing-extensions==4.5.0
     # via
@@ -183,12 +190,11 @@ typing-extensions==4.5.0
     #   pydantic
     #   starlette
     #   torch
-    #   torchvision
-urllib3==1.26.14
+urllib3==1.26.15
     # via requests
-uvicorn==0.20.0
+uvicorn==0.21.1
     # via unstructured-inference (setup.py)
 wand==0.6.11
     # via pdfplumber
-zipp==3.14.0
+zipp==3.15.0
     # via importlib-resources

requirements/dev.txt

@@ -21,7 +21,7 @@ attrs==22.2.0
     # via jsonschema
 backcall==0.2.0
     # via ipython
-beautifulsoup4==4.11.2
+beautifulsoup4==4.12.0
     # via nbconvert
 bleach==6.0.0
     # via nbconvert
@@ -41,17 +41,22 @@ defusedxml==0.7.1
     # via nbconvert
 executing==1.2.0
     # via stack-data
-fastjsonschema==2.16.2
+fastjsonschema==2.16.3
     # via nbformat
 fqdn==1.5.1
     # via jsonschema
 idna==3.4
     # via
     #   anyio
     #   jsonschema
-ipykernel==6.21.2
+importlib-metadata==6.1.0
+    # via
+    #   jupyter-client
+    #   nbconvert
+importlib-resources==5.12.0
+    # via jsonschema
+ipykernel==6.22.0
     # via
-    #   ipywidgets
     #   jupyter
     #   jupyter-console
     #   nbclassic
@@ -68,7 +73,7 @@ ipython-genutils==0.2.0
     #   nbclassic
     #   notebook
     #   qtconsole
-ipywidgets==8.0.4
+ipywidgets==8.0.5
     # via jupyter
 isoduration==20.11.0
     # via jsonschema
@@ -87,8 +92,8 @@ jsonschema[format-nongpl]==4.17.3
     #   jupyter-events
     #   nbformat
 jupyter==1.0.0
-    # via -r dev.in
-jupyter-client==8.0.3
+    # via -r requirements/dev.in
+jupyter-client==8.1.0
     # via
     #   ipykernel
     #   jupyter-console
@@ -97,9 +102,9 @@ jupyter-client==8.0.3
     #   nbclient
     #   notebook
     #   qtconsole
-jupyter-console==6.5.1
+jupyter-console==6.6.3
     # via jupyter
-jupyter-core==5.2.0
+jupyter-core==5.3.0
     # via
     #   ipykernel
     #   jupyter-client
@@ -113,15 +118,15 @@ jupyter-core==5.2.0
     #   qtconsole
 jupyter-events==0.6.3
     # via jupyter-server
-jupyter-server==2.3.0
+jupyter-server==2.5.0
     # via
     #   nbclassic
     #   notebook-shim
 jupyter-server-terminals==0.4.4
     # via jupyter-server
 jupyterlab-pygments==0.2.2
     # via nbconvert
-jupyterlab-widgets==3.0.5
+jupyterlab-widgets==3.0.6
     # via ipywidgets
 markupsafe==2.1.2
     # via
@@ -133,17 +138,17 @@ matplotlib-inline==0.1.6
     #   ipython
 mistune==2.0.5
     # via nbconvert
-nbclassic==0.5.1
+nbclassic==0.5.3
     # via notebook
 nbclient==0.7.2
     # via nbconvert
-nbconvert==7.2.9
+nbconvert==7.2.10
     # via
     #   jupyter
     #   jupyter-server
     #   nbclassic
     #   notebook
-nbformat==5.7.3
+nbformat==5.8.0
     # via
     #   jupyter-server
     #   nbclassic
@@ -155,7 +160,7 @@ nest-asyncio==1.5.6
     #   ipykernel
     #   nbclassic
     #   notebook
-notebook==6.5.2
+notebook==6.5.3
     # via jupyter
 notebook-shim==0.2.2
     # via nbclassic
@@ -165,6 +170,7 @@ packaging==23.0
     #   ipykernel
     #   jupyter-server
     #   nbconvert
+    #   qtconsole
     #   qtpy
 pandocfilters==1.5.0
     # via nbconvert
@@ -174,16 +180,18 @@ pexpect==4.8.0
     # via ipython
 pickleshare==0.7.5
     # via ipython
-pip-tools==6.12.2
-    # via -r dev.in
-platformdirs==3.0.0
+pip-tools==6.12.3
+    # via -r requirements/dev.in
+pkgutil-resolve-name==1.3.10
+    # via jsonschema
+platformdirs==3.1.1
     # via jupyter-core
 prometheus-client==0.16.0
     # via
     #   jupyter-server
     #   nbclassic
     #   notebook
-prompt-toolkit==3.0.36
+prompt-toolkit==3.0.38
     # via
     #   ipython
     #   jupyter-console
@@ -211,11 +219,11 @@ python-dateutil==2.8.2
     # via
     #   arrow
     #   jupyter-client
-python-json-logger==2.0.6
+python-json-logger==2.0.7
     # via jupyter-events
 pyyaml==6.0
     # via jupyter-events
-pyzmq==25.0.0
+pyzmq==25.0.2
     # via
     #   ipykernel
     #   jupyter-client
@@ -224,7 +232,7 @@ pyzmq==25.0.0
     #   nbclassic
     #   notebook
     #   qtconsole
-qtconsole==5.4.0
+qtconsole==5.4.1
     # via jupyter
 qtpy==2.3.0
     # via qtconsole
@@ -299,10 +307,14 @@ webencodings==0.5.1
     #   tinycss2
 websocket-client==1.5.1
     # via jupyter-server
-wheel==0.38.4
+wheel==0.40.0
     # via pip-tools
-widgetsnbextension==4.0.5
+widgetsnbextension==4.0.6
     # via ipywidgets
+zipp==3.15.0
+    # via
+    #   importlib-metadata
+    #   importlib-resources
 
 # The following packages are considered to be unsafe in a requirements file:
 # pip

requirements/test.in

@@ -8,6 +8,7 @@ click>=8.1
 # starlette even though it's required for TestClient
 httpx
 flake8
+flake8-docstrings
 mypy
 pytest-cov
 pdf2image>=1.16.2