chore: update python-docx version dependency (#2952)

**Summary**
`unstructured` will use table features added in the most recent version
of `python-docx`.

Also update the `lxml` version constraint because `lxml>4.9.2` will not
install on Apple Silicon
(#1707).

`python-docx` requires `lxml` although other file formats require it as
well.

Author: scanny

CHANGELOG.md

@@ -1,6 +1,7 @@
-## 0.13.7-dev0
+## 0.13.7-dev1
 
 ### Enhancements
+
 * **Remove `page_number` metadata fields** for HTML partition until we have a better strategy to decide page counting.
 
 ### Features

docs/requirements.txt

@@ -52,7 +52,7 @@ mdit-py-plugins==0.4.0
     # via myst-parser
 mdurl==0.1.2
     # via markdown-it-py
-myst-parser==3.0.0
+myst-parser==3.0.1
     # via -r ./build.in
 packaging==23.2
     # via

requirements/base.txt

@@ -21,7 +21,7 @@ charset-normalizer==3.3.2
     #   unstructured-client
 click==8.1.7
     # via nltk
-dataclasses-json==0.6.4
+dataclasses-json==0.6.5
     # via -r ./base.in
 dataclasses-json-speakeasy==0.5.11
     # via unstructured-client
@@ -39,10 +39,8 @@ jsonpath-python==1.0.6
     # via unstructured-client
 langdetect==1.0.9
     # via -r ./base.in
-lxml==4.9.4
-    # via
-    #   -c ././deps/constraints.txt
-    #   -r ./base.in
+lxml==5.2.1
+    # via -r ./base.in
 marshmallow==3.21.1
     # via
     #   dataclasses-json
@@ -63,13 +61,13 @@ packaging==23.2
     #   unstructured-client
 python-dateutil==2.9.0.post0
     # via unstructured-client
-python-iso639==2024.2.7
+python-iso639==2024.4.27
     # via -r ./base.in
 python-magic==0.4.27
     # via -r ./base.in
 rapidfuzz==3.8.1
     # via -r ./base.in
-regex==2024.4.16
+regex==2024.4.28
     # via nltk
 requests==2.31.0
     # via

requirements/build.txt

@@ -52,7 +52,7 @@ mdit-py-plugins==0.4.0
     # via myst-parser
 mdurl==0.1.2
     # via markdown-it-py
-myst-parser==3.0.0
+myst-parser==3.0.1
     # via -r ./build.in
 packaging==23.2
     # via

requirements/deps/constraints.txt

@@ -38,6 +38,10 @@ opencv-python==4.8.0.76
 opencv-contrib-python==4.8.0.76
 platformdirs==3.10.0
 
+# Note(scanny): partition_docx() uses table features added in python-docx v1.1.2. Added here since
+# multiple formats have a python-docx dependency (docx, odt)
+python-docx>=1.1.2
+
 # TODO: Constraint due to langchain, remove when that gets updated:
 packaging<24.0
 
@@ -48,8 +52,5 @@ urllib3<1.27
 # TODO: Constriant due to aiobotocore, remove when that gets updates:
 botocore<1.34.52
 
-# TODO: constraint due to current release of pikepdf (v8.14.0), remove once next version releases since fix is on main
-lxml<5
-
 # NOTE(jennings): pinned due to later versions not supporting api_key_auth in UnstructuredClient
 unstructured-client<=0.18.0

requirements/dev.txt

@@ -81,7 +81,7 @@ executing==2.0.1
     # via stack-data
 fastjsonschema==2.19.1
     # via nbformat
-filelock==3.13.4
+filelock==3.14.0
     # via virtualenv
 fqdn==1.5.1
     # via jsonschema
@@ -138,7 +138,7 @@ json5==0.9.25
     # via jupyterlab-server
 jsonpointer==2.4
     # via jsonschema
-jsonschema[format-nongpl]==4.21.1
+jsonschema[format-nongpl]==4.22.0
     # via
     #   jupyter-events
     #   jupyterlab-server
@@ -203,7 +203,7 @@ mistune==3.0.2
     # via nbconvert
 nbclient==0.10.0
     # via nbconvert
-nbconvert==7.16.3
+nbconvert==7.16.4
     # via
     #   jupyter
     #   jupyter-server
@@ -277,7 +277,7 @@ pygments==2.17.2
     #   jupyter-console
     #   nbconvert
     #   qtconsole
-pyproject-hooks==1.0.0
+pyproject-hooks==1.1.0
     # via
     #   build
     #   pip-tools
@@ -294,7 +294,7 @@ pyyaml==6.0.1
     #   -c ./test.txt
     #   jupyter-events
     #   pre-commit
-pyzmq==26.0.2
+pyzmq==26.0.3
     # via
     #   ipykernel
     #   jupyter-client
@@ -305,7 +305,7 @@ qtconsole==5.5.1
     # via jupyter
 qtpy==2.4.1
     # via qtconsole
-referencing==0.35.0
+referencing==0.35.1
     # via
     #   jsonschema
     #   jsonschema-specifications
@@ -359,7 +359,6 @@ tomli==2.0.1
     #   build
     #   jupyterlab
     #   pip-tools
-    #   pyproject-hooks
 tornado==6.4
     # via
     #   ipykernel
@@ -401,7 +400,7 @@ urllib3==1.26.18
     #   -c ./base.txt
     #   -c ./test.txt
     #   requests
-virtualenv==20.26.0
+virtualenv==20.26.1
     # via pre-commit
 wcwidth==0.2.13
     # via prompt-toolkit

requirements/extra-docx.txt

@@ -4,13 +4,14 @@
 #
 #    pip-compile ./extra-docx.in
 #
-lxml==4.9.4
+lxml==5.2.1
     # via
-    #   -c ././deps/constraints.txt
     #   -c ./base.txt
     #   python-docx
-python-docx==1.1.0
-    # via -r ./extra-docx.in
+python-docx==1.1.2
+    # via
+    #   -c ././deps/constraints.txt
+    #   -r ./extra-docx.in
 typing-extensions==4.11.0
     # via
     #   -c ./base.txt

requirements/extra-odt.txt

@@ -4,15 +4,16 @@
 #
 #    pip-compile ./extra-odt.in
 #
-lxml==4.9.4
+lxml==5.2.1
     # via
-    #   -c ././deps/constraints.txt
     #   -c ./base.txt
     #   python-docx
 pypandoc==1.13
     # via -r ./extra-odt.in
-python-docx==1.1.0
-    # via -r ./extra-odt.in
+python-docx==1.1.2
+    # via
+    #   -c ././deps/constraints.txt
+    #   -r ./extra-odt.in
 typing-extensions==4.11.0
     # via
     #   -c ./base.txt

requirements/extra-paddleocr.txt

@@ -10,7 +10,7 @@ babel==2.14.0
     # via flask-babel
 bce-python-sdk==0.9.7
     # via visualdl
-blinker==1.8.0
+blinker==1.8.1
     # via flask
 cachetools==5.3.3
     # via premailer
@@ -77,9 +77,8 @@ lazy-loader==0.4
     # via scikit-image
 lmdb==1.4.1
     # via unstructured-paddleocr
-lxml==4.9.4
+lxml==5.2.1
     # via
-    #   -c ././deps/constraints.txt
     #   -c ./base.txt
     #   premailer
     #   unstructured-paddleocr

requirements/extra-pdf-image.txt

@@ -32,7 +32,7 @@ deprecated==1.2.14
     # via pikepdf
 effdet==0.4.1
     # via layoutparser
-filelock==3.13.4
+filelock==3.14.0
     # via
     #   huggingface-hub
     #   torch
@@ -45,8 +45,10 @@ fsspec==2024.3.1
     # via
     #   huggingface-hub
     #   torch
-google-api-core[grpc]==2.18.0
-    # via google-cloud-vision
+google-api-core[grpc]==2.19.0
+    # via
+    #   google-api-core
+    #   google-cloud-vision
 google-auth==2.29.0
     # via
     #   google-api-core
@@ -57,7 +59,7 @@ googleapis-common-protos==1.63.0
     # via
     #   google-api-core
     #   grpcio-status
-grpcio==1.62.2
+grpcio==1.63.0
     # via
     #   google-api-core
     #   grpcio-status
@@ -85,9 +87,8 @@ kiwisolver==1.4.5
     # via matplotlib
 layoutparser[layoutmodels,tesseract]==0.3.4
     # via unstructured-inference
-lxml==4.9.4
+lxml==5.2.1
     # via
-    #   -c ././deps/constraints.txt
     #   -c ./base.txt
     #   pikepdf
 markupsafe==2.1.5
@@ -223,7 +224,7 @@ rapidfuzz==3.8.1
     # via
     #   -c ./base.txt
     #   unstructured-inference
-regex==2024.4.16
+regex==2024.4.28
     # via
     #   -c ./base.txt
     #   transformers