build(deps): remove ebooklib (#1878)

* **Removed `ebooklib` as a dependency** `ebooklib` is licensed under
AGPL3, which is incompatible with the Apache 2.0 license. Thus it is
being removed.

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.10.27-dev0
+## 0.10.27
 
 ### Enhancements
 
@@ -8,6 +8,7 @@
 
 ### Fixes
 
+* **Removed `ebooklib` as a dependency** `ebooklib` is licensed under AGPL3, which is incompatible with the Apache 2.0 license. Thus it is being removed.
 * **Caching fixes in ingest pipeline** Previously, steps like the source node were not leveraging parameters such as `re_download` to dictate if files should be forced to redownload rather than use what might already exist locally.
 
 ## 0.10.26

requirements/base.txt

@@ -14,7 +14,7 @@ certifi==2023.7.22
     #   requests
 chardet==5.2.0
     # via -r requirements/base.in
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via requests
 click==8.1.7
     # via nltk

requirements/build.txt

@@ -6,7 +6,7 @@
 #
 alabaster==0.7.13
     # via sphinx
-babel==2.13.0
+babel==2.13.1
     # via sphinx
 beautifulsoup4==4.12.2
     # via
@@ -18,7 +18,7 @@ certifi==2023.7.22
     #   -c requirements/constraints.in
     #   -r requirements/build.in
     #   requests
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/base.txt
     #   requests
@@ -90,7 +90,7 @@ sphinx-basic-ng==1.0.0b2
     # via furo
 sphinx-rtd-theme==1.2.2
     # via -r requirements/build.in
-sphinx-tabs==3.4.1
+sphinx-tabs==3.4.4
     # via -r requirements/build.in
 sphinxcontrib-applehelp==1.0.4
     # via

requirements/constraints.in

@@ -52,3 +52,4 @@ opencv-python==4.8.0.76
 opencv-contrib-python==4.8.0.76
 onnxruntime==1.15.1
 platformdirs==3.10.0
+pillow<=10.0.1

requirements/dev.txt

@@ -18,15 +18,15 @@ argon2-cffi-bindings==21.2.0
     # via argon2-cffi
 arrow==1.3.0
     # via isoduration
-asttokens==2.4.0
+asttokens==2.4.1
     # via stack-data
 async-lru==2.0.4
     # via jupyterlab
 attrs==23.1.0
     # via
     #   jsonschema
     #   referencing
-babel==2.13.0
+babel==2.13.1
     # via jupyterlab-server
 backcall==0.2.0
     # via ipython
@@ -48,7 +48,7 @@ cffi==1.16.0
     # via argon2-cffi-bindings
 cfgv==3.4.0
     # via pre-commit
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/base.txt
     #   -c requirements/test.txt
@@ -104,7 +104,7 @@ importlib-resources==6.1.0
     #   jsonschema
     #   jsonschema-specifications
     #   jupyterlab
-ipykernel==6.25.2
+ipykernel==6.26.0
     # via
     #   jupyter
     #   jupyter-console
@@ -144,7 +144,7 @@ jsonschema-specifications==2023.7.1
     # via jsonschema
 jupyter==1.0.0
     # via -r requirements/dev.in
-jupyter-client==8.4.0
+jupyter-client==8.5.0
     # via
     #   ipykernel
     #   jupyter-console
@@ -169,7 +169,7 @@ jupyter-events==0.8.0
     # via jupyter-server
 jupyter-lsp==2.2.0
     # via jupyterlab
-jupyter-server==2.8.0
+jupyter-server==2.9.1
     # via
     #   jupyter-lsp
     #   jupyterlab
@@ -300,7 +300,7 @@ pyzmq==25.1.1
     #   qtconsole
 qtconsole==5.4.4
     # via jupyter
-qtpy==2.4.0
+qtpy==2.4.1
     # via qtconsole
 referencing==0.30.2
     # via
@@ -363,7 +363,7 @@ tornado==6.3.3
     #   jupyterlab
     #   notebook
     #   terminado
-traitlets==5.11.2
+traitlets==5.12.0
     # via
     #   comm
     #   ipykernel
@@ -396,7 +396,7 @@ urllib3==1.26.18
     #   -c requirements/constraints.in
     #   -c requirements/test.txt
     #   requests
-virtualenv==20.24.5
+virtualenv==20.24.6
     # via pre-commit
 wcwidth==0.2.8
     # via prompt-toolkit

requirements/embed-huggingface.txt

@@ -23,7 +23,7 @@ certifi==2023.7.22
     #   -c requirements/base.txt
     #   -c requirements/constraints.in
     #   requests
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/base.txt
     #   aiohttp
@@ -76,9 +76,9 @@ jsonpatch==1.33
     # via langchain
 jsonpointer==2.4
     # via jsonpatch
-langchain==0.0.320
+langchain==0.0.323
     # via -r requirements/embed-huggingface.in
-langsmith==0.0.49
+langsmith==0.0.52
     # via langchain
 markupsafe==2.1.3
     # via jinja2
@@ -118,8 +118,10 @@ packaging==23.2
     #   huggingface-hub
     #   marshmallow
     #   transformers
-pillow==10.1.0
-    # via torchvision
+pillow==10.0.1
+    # via
+    #   -c requirements/constraints.in
+    #   torchvision
 pydantic==1.10.13
     # via
     #   -c requirements/constraints.in
@@ -147,7 +149,7 @@ safetensors==0.3.2
     # via
     #   -c requirements/constraints.in
     #   transformers
-scikit-learn==1.3.1
+scikit-learn==1.3.2
     # via sentence-transformers
 scipy==1.10.1
     # via

requirements/extra-epub.in

@@ -1,4 +1,4 @@
 -c constraints.in
 -c base.txt
 
-ebooklib
+pypandoc

requirements/extra-epub.txt

@@ -4,13 +4,5 @@
 #
 #    pip-compile --constraint=requirements/constraints.in requirements/extra-epub.in
 #
-ebooklib==0.18
+pypandoc==1.12
     # via -r requirements/extra-epub.in
-lxml==4.9.3
-    # via
-    #   -c requirements/base.txt
-    #   ebooklib
-six==1.16.0
-    # via
-    #   -c requirements/base.txt
-    #   ebooklib

requirements/extra-paddleocr.txt

@@ -6,20 +6,20 @@
 #
 attrdict==2.0.1
     # via unstructured-paddleocr
-babel==2.13.0
+babel==2.13.1
     # via flask-babel
 bce-python-sdk==0.8.92
     # via visualdl
 blinker==1.6.3
     # via flask
-cachetools==5.3.1
+cachetools==5.3.2
     # via premailer
 certifi==2023.7.22
     # via
     #   -c requirements/base.txt
     #   -c requirements/constraints.in
     #   requests
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/base.txt
     #   requests
@@ -53,7 +53,7 @@ idna==3.4
     # via
     #   -c requirements/base.txt
     #   requests
-imageio==2.31.5
+imageio==2.31.6
     # via
     #   imgaug
     #   scikit-image
@@ -134,8 +134,9 @@ pandas==2.0.3
     #   visualdl
 pdf2image==1.16.3
     # via unstructured-paddleocr
-pillow==10.1.0
+pillow==10.0.1
     # via
+    #   -c requirements/constraints.in
     #   imageio
     #   imgaug
     #   matplotlib
@@ -220,7 +221,7 @@ urllib3==1.26.18
     #   requests
 visualdl==2.5.3
     # via unstructured-paddleocr
-werkzeug==3.0.0
+werkzeug==3.0.1
     # via flask
 zipp==3.17.0
     # via

requirements/extra-pdf-image.txt

@@ -13,7 +13,7 @@ certifi==2023.7.22
     #   requests
 cffi==1.16.0
     # via cryptography
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/base.txt
     #   pdfminer-six
@@ -22,7 +22,7 @@ coloredlogs==15.0.1
     # via onnxruntime
 contourpy==1.1.1
     # via matplotlib
-cryptography==41.0.4
+cryptography==41.0.5
     # via pdfminer-six
 cycler==0.12.1
     # via matplotlib
@@ -125,10 +125,11 @@ pdfminer-six==20221105
     # via
     #   -r requirements/extra-pdf-image.in
     #   pdfplumber
-pdfplumber==0.10.2
+pdfplumber==0.10.3
     # via layoutparser
-pillow==10.1.0
+pillow==10.0.1
     # via
+    #   -c requirements/constraints.in
     #   layoutparser
     #   matplotlib
     #   pdf2image

requirements/extra-pptx.txt

@@ -6,8 +6,10 @@
 #
 lxml==4.9.3
     # via python-pptx
-pillow==10.1.0
-    # via python-pptx
+pillow==10.0.1
+    # via
+    #   -c requirements/constraints.in
+    #   python-pptx
 python-pptx==0.6.21
     # via -r requirements/extra-pptx.in
 xlsxwriter==3.1.9

requirements/huggingface.txt

@@ -9,7 +9,7 @@ certifi==2023.7.22
     #   -c requirements/base.txt
     #   -c requirements/constraints.in
     #   requests
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/base.txt
     #   requests

requirements/ingest/airtable.txt

@@ -10,7 +10,7 @@ certifi==2023.7.22
     #   -c requirements/ingest/../base.txt
     #   -c requirements/ingest/../constraints.in
     #   requests
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/ingest/../base.txt
     #   requests

requirements/ingest/azure-cognitive-search.txt

@@ -19,7 +19,7 @@ certifi==2023.7.22
     #   -c requirements/ingest/../constraints.in
     #   msrest
     #   requests
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/ingest/../base.txt
     #   requests

requirements/ingest/azure.txt

@@ -35,12 +35,12 @@ cffi==1.16.0
     # via
     #   azure-datalake-store
     #   cryptography
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/ingest/../base.txt
     #   aiohttp
     #   requests
-cryptography==41.0.4
+cryptography==41.0.5
     # via
     #   azure-identity
     #   azure-storage-blob

requirements/ingest/bedrock.txt

@@ -36,7 +36,7 @@ certifi==2023.7.22
     #   -c requirements/ingest/../base.txt
     #   -c requirements/ingest/../constraints.in
     #   requests
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/ingest/../base.txt
     #   aiohttp
@@ -65,9 +65,9 @@ jsonpatch==1.33
     # via langchain
 jsonpointer==2.4
     # via jsonpatch
-langchain==0.0.321
+langchain==0.0.323
     # via -r requirements/ingest/bedrock.in
-langsmith==0.0.49
+langsmith==0.0.52
     # via langchain
 marshmallow==3.20.1
     # via

requirements/ingest/box.txt

@@ -18,11 +18,11 @@ certifi==2023.7.22
     #   requests
 cffi==1.16.0
     # via cryptography
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/ingest/../base.txt
     #   requests
-cryptography==41.0.4
+cryptography==41.0.5
     # via boxsdk
 fsspec==2023.9.1
     # via

requirements/ingest/confluence.txt

@@ -12,7 +12,7 @@ certifi==2023.7.22
     #   -c requirements/ingest/../base.txt
     #   -c requirements/ingest/../constraints.in
     #   requests
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/ingest/../base.txt
     #   requests

requirements/ingest/discord.txt

@@ -12,7 +12,7 @@ async-timeout==4.0.3
     # via aiohttp
 attrs==23.1.0
     # via aiohttp
-charset-normalizer==3.3.0
+charset-normalizer==3.3.1
     # via
     #   -c requirements/ingest/../base.txt
     #   aiohttp