Merge branch 'main' into pprados/fix_password

Author: pprados

CHANGELOG.md

@@ -1,15 +1,15 @@
-## 0.16.12-dev5
+## 0.16.12
 
 ### Enhancements
 
 - **Prepare auto-partitioning for pluggable partitioners**. Move toward a uniform partitioner call signature so a custom or override partitioner can be registered without code changes.
-- **Add NDJSON file type support**
+- **Add NDJSON file type support.**
 
 ### Features
 
 ### Fixes
 
-- Base image has been updated, trigger new workflows
+- **Base image has been updated.**
 - **Upgrade ruff to latest.** Previously the ruff version was pinned to <0.5. Remove that pin and fix the handful of lint items that resulted.
 - **CSV with asserted XLS content-type is correctly identified as CSV.** Resolves a bug where a CSV file with an asserted content-type of `application/vnd.ms-excel` was incorrectly identified as an XLS file.
 - **Improve element-type mapping for Chinese text.** Fixes bug where Chinese text would produce large numbers of false-positive `Title` elements.

CONTRIBUTING.md

@@ -115,7 +115,7 @@ The Unstructured Team
 | Section | Description |
 |-|-|
 | [Company Website](https://unstructured.io) | Unstructured.io product and company info |
-| [Documentation](https://unstructured-io.github.io/unstructured) | Full API documentation |
+| [Documentation](https://docs.unstructured.io/) | Full API documentation |
 | [Working with Pull Requests](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/about-pull-requests) | About pull requests |
 | [Code of Conduct](https://www.contributor-covenant.org/version/1/4/code-of-conduct/) | Contributor Covenant Code Of Conduct |
 | [Conventional Commits](https://www.freecodecamp.org/news/how-to-write-better-git-commit-messages/) | How to write better git commit messages |

requirements/base.txt

@@ -20,11 +20,11 @@ cffi==1.17.1
     # via cryptography
 chardet==5.2.0
     # via -r ./base.in
-charset-normalizer==3.4.0
+charset-normalizer==3.4.1
     # via
     #   requests
     #   unstructured-client
-click==8.1.7
+click==8.1.8
     # via
     #   nltk
     #   python-oxmsg
@@ -64,7 +64,7 @@ langdetect==1.0.9
     # via -r ./base.in
 lxml==5.3.0
     # via -r ./base.in
-marshmallow==3.23.1
+marshmallow==3.23.2
     # via
     #   dataclasses-json
     #   unstructured-client
@@ -88,7 +88,7 @@ packaging==24.2
     # via
     #   marshmallow
     #   unstructured-client
-psutil==6.1.0
+psutil==6.1.1
     # via -r ./base.in
 pycparser==2.22
     # via cffi

requirements/dev.txt

@@ -8,7 +8,7 @@ build==1.2.2.post1
     # via pip-tools
 cfgv==3.4.0
     # via pre-commit
-click==8.1.7
+click==8.1.8
     # via
     #   -c ./base.txt
     #   -c ./test.txt
@@ -17,7 +17,7 @@ distlib==0.3.9
     # via virtualenv
 filelock==3.16.1
     # via virtualenv
-identify==2.6.3
+identify==2.6.4
     # via pre-commit
 importlib-metadata==8.5.0
     # via
@@ -51,7 +51,7 @@ tomli==2.2.1
     #   -c ./test.txt
     #   build
     #   pip-tools
-virtualenv==20.28.0
+virtualenv==20.28.1
     # via pre-commit
 wheel==0.45.1
     # via pip-tools

requirements/extra-paddleocr.txt

@@ -16,7 +16,7 @@ certifi==2024.12.14
     #   httpcore
     #   httpx
     #   requests
-charset-normalizer==3.4.0
+charset-normalizer==3.4.1
     # via
     #   -c ./base.txt
     #   requests
@@ -58,7 +58,7 @@ imageio==2.36.1
     #   scikit-image
 imgaug==0.4.0
     # via unstructured-paddleocr
-importlib-resources==6.4.5
+importlib-resources==6.5.1
     # via matplotlib
 kiwisolver==1.4.7
     # via matplotlib
@@ -104,7 +104,7 @@ paddlepaddle==3.0.0b1
     # via -r ./extra-paddleocr.in
 pdf2image==1.17.0
     # via unstructured-paddleocr
-pillow==11.0.0
+pillow==11.1.0
     # via
     #   imageio
     #   imgaug
@@ -119,7 +119,7 @@ protobuf==4.25.5
     #   paddlepaddle
 pyclipper==1.3.0.post6
     # via unstructured-paddleocr
-pyparsing==3.2.0
+pyparsing==3.2.1
     # via matplotlib
 python-dateutil==2.9.0.post0
     # via

requirements/extra-pdf-image.txt

@@ -16,7 +16,7 @@ cffi==1.17.1
     # via
     #   -c ./base.txt
     #   cryptography
-charset-normalizer==3.4.0
+charset-normalizer==3.4.1
     # via
     #   -c ./base.txt
     #   pdfminer-six
@@ -40,11 +40,11 @@ filelock==3.16.1
     #   huggingface-hub
     #   torch
     #   transformers
-flatbuffers==24.3.25
+flatbuffers==24.12.23
     # via onnxruntime
 fonttools==4.55.3
     # via matplotlib
-fsspec==2024.10.0
+fsspec==2024.12.0
     # via
     #   huggingface-hub
     #   torch
@@ -79,11 +79,11 @@ idna==3.10
     # via
     #   -c ./base.txt
     #   requests
-importlib-resources==6.4.5
+importlib-resources==6.5.1
     # via matplotlib
 iopath==0.1.10
     # via layoutparser
-jinja2==3.1.4
+jinja2==3.1.5
     # via torch
 kiwisolver==1.4.7
     # via matplotlib
@@ -149,13 +149,13 @@ pdfminer-six==20231228
     # via
     #   -r ./extra-pdf-image.in
     #   pdfplumber
-pdfplumber==0.11.4
+pdfplumber==0.11.5
     # via layoutparser
 pi-heif==0.21.0
     # via -r ./extra-pdf-image.in
-pikepdf==9.4.2
+pikepdf==9.5.0
     # via -r ./extra-pdf-image.in
-pillow==11.0.0
+pillow==11.1.0
     # via
     #   layoutparser
     #   matplotlib
@@ -165,7 +165,7 @@ pillow==11.0.0
     #   pikepdf
     #   torchvision
     #   unstructured-pytesseract
-portalocker==3.0.0
+portalocker==3.1.1
     # via iopath
 proto-plus==1.25.0
     # via
@@ -193,13 +193,13 @@ pycparser==2.22
     # via
     #   -c ./base.txt
     #   cffi
-pyparsing==3.2.0
+pyparsing==3.2.1
     # via matplotlib
 pypdf==5.1.0
     # via
     #   -c ./base.txt
     #   -r ./extra-pdf-image.in
-pypdfium2==4.30.0
+pypdfium2==4.30.1
     # via pdfplumber
 python-dateutil==2.9.0.post0
     # via
@@ -233,7 +233,7 @@ requests==2.32.3
     #   transformers
 rsa==4.9
     # via google-auth
-safetensors==0.4.5
+safetensors==0.5.0
     # via
     #   timm
     #   transformers

requirements/extra-pptx.txt

@@ -6,7 +6,7 @@
 #
 lxml==5.3.0
     # via python-pptx
-pillow==11.0.0
+pillow==11.1.0
     # via python-pptx
 python-pptx==1.0.2
     # via -r ./extra-pptx.in

requirements/huggingface.txt

@@ -8,11 +8,11 @@ certifi==2024.12.14
     # via
     #   -c ./base.txt
     #   requests
-charset-normalizer==3.4.0
+charset-normalizer==3.4.1
     # via
     #   -c ./base.txt
     #   requests
-click==8.1.7
+click==8.1.8
     # via
     #   -c ./base.txt
     #   sacremoses
@@ -21,7 +21,7 @@ filelock==3.16.1
     #   huggingface-hub
     #   torch
     #   transformers
-fsspec==2024.10.0
+fsspec==2024.12.0
     # via
     #   huggingface-hub
     #   torch
@@ -33,7 +33,7 @@ idna==3.10
     # via
     #   -c ./base.txt
     #   requests
-jinja2==3.1.4
+jinja2==3.1.5
     # via torch
 joblib==1.4.2
     # via
@@ -74,7 +74,7 @@ requests==2.32.3
     #   transformers
 sacremoses==0.1.1
     # via -r ./huggingface.in
-safetensors==0.4.5
+safetensors==0.5.0
     # via transformers
 sentencepiece==0.2.0
     # via -r ./huggingface.in

requirements/test.txt

@@ -12,7 +12,7 @@ anyio==4.7.0
     #   httpx
 appdirs==1.4.4
     # via label-studio-sdk
-argcomplete==3.5.2
+argcomplete==3.5.3
     # via datamodel-code-generator
 attrs==24.3.0
     # via
@@ -30,16 +30,16 @@ certifi==2024.12.14
     #   httpcore
     #   httpx
     #   requests
-charset-normalizer==3.4.0
+charset-normalizer==3.4.1
     # via
     #   -c ./base.txt
     #   requests
-click==8.1.7
+click==8.1.8
     # via
     #   -c ./base.txt
     #   black
     #   nltk
-coverage[toml]==7.6.9
+coverage[toml]==7.6.10
     # via
     #   -r ./test.in
     #   pytest-cov
@@ -98,7 +98,7 @@ iniconfig==2.0.0
     # via pytest
 isort==5.13.2
     # via datamodel-code-generator
-jinja2==3.1.4
+jinja2==3.1.5
     # via datamodel-code-generator
 joblib==1.4.2
     # via
@@ -126,7 +126,7 @@ mccabe==0.7.0
     # via flake8
 multidict==6.1.0
     # via yarl
-mypy==1.13.0
+mypy==1.14.1
     # via -r ./test.in
 mypy-extensions==1.0.0
     # via
@@ -152,7 +152,7 @@ pandas==2.2.3
     # via label-studio-sdk
 pathspec==0.12.1
     # via black
-pillow==11.0.0
+pillow==11.1.0
     # via label-studio-sdk
 platformdirs==4.3.6
     # via black
@@ -164,13 +164,13 @@ pycodestyle==2.12.1
     # via
     #   flake8
     #   flake8-print
-pydantic[email]==2.10.3
+pydantic[email]==2.10.4
     # via
     #   -r ./test.in
     #   datamodel-code-generator
     #   jsf
     #   label-studio-sdk
-pydantic-core==2.27.1
+pydantic-core==2.27.2
     # via pydantic
 pyflakes==3.2.0
     # via
@@ -218,7 +218,7 @@ rpds-py==0.22.3
     #   referencing
 rstr==3.2.2
     # via jsf
-ruff==0.8.3
+ruff==0.8.5
     # via -r ./test.in
 semantic-version==2.10.0
     # via liccheck
@@ -279,7 +279,7 @@ urllib3==1.26.20
     #   -c ./base.txt
     #   requests
     #   vcrpy
-vcrpy==6.0.2
+vcrpy==7.0.0
     # via -r ./test.in
 wrapt==1.17.0
     # via

test_unstructured_ingest/expected-structured-output/outlook/21be155fb0c95885.eml.json

@@ -26,7 +26,7 @@
         },
         "date_created": "1689435368.0",
         "date_modified": "1689435537.0",
-        "filesize_bytes": 9189
+        "filesize_bytes": 9179
       }
     }
   }