Merge branch 'main' into feat/using-nltk-assets-from-docker-image

CHANGELOG.md

@@ -3,11 +3,13 @@
 ### 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**
 
 ### Features
 
 ### Fixes
 
+- Base image has been updated, trigger new workflows
 - **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.

Dockerfile

@@ -10,9 +10,11 @@ COPY test_unstructured test_unstructured
 COPY example-docs example-docs
 
 RUN chown -R notebook-user:notebook-user /app && \
-    apk add font-ubuntu git && \
-    fc-cache -fv && \
-    if [ ! -e /usr/bin/python3 ]; then ln -s /usr/bin/python3.11 /usr/bin/python3; fi
+  apk add font-ubuntu git && \
+  fc-cache -fv && \
+  if [ "$(readlink -f /usr/bin/python3)" != "/usr/bin/python3.11" ]; then \
+        ln -sf /usr/bin/python3.11 /usr/bin/python3; \
+  fi
 
 USER notebook-user
 

example-docs/simple.ndjson

@@ -0,0 +1,8 @@
+{"element_id": "a06d2d9e65212d4aa955c3ab32950ffa", "metadata": {"category_depth": 0, "file_directory": "unstructured/example-docs", "filename": "simple.docx", "filetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "languages": ["eng"], "last_modified": "2024-07-06T16:44:51"}, "text": "These are a few of my favorite things:", "type": "Title"}
+{"element_id": "b334c93e9b1cbca3b6f6d78ce8bc2484", "metadata": {"category_depth": 0, "file_directory": "unstructured/example-docs", "filename": "simple.docx", "filetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "languages": ["eng"], "last_modified": "2024-07-06T16:44:51", "parent_id": "a06d2d9e65212d4aa955c3ab32950ffa"}, "text": "Parrots", "type": "ListItem"}
+{"element_id": "76469ecb9f1459943c8d8cca1a550b5a", "metadata": {"category_depth": 0, "file_directory": "unstructured/example-docs", "filename": "simple.docx", "filetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "languages": ["eng"], "last_modified": "2024-07-06T16:44:51", "parent_id": "a06d2d9e65212d4aa955c3ab32950ffa"}, "text": "Hockey", "type": "ListItem"}
+{"element_id": "261fac731945a138415adc2dd4434b17", "metadata": {"category_depth": 0, "file_directory": "unstructured/example-docs", "filename": "simple.docx", "filetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "languages": ["eng"], "last_modified": "2024-07-06T16:44:51"}, "text": "Analysis", "type": "Title"}
+{"element_id": "95f392d32c5271bfdb30eaef45921e59", "metadata": {"category_depth": 0, "file_directory": "unstructured/example-docs", "filename": "simple.docx", "filetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "languages": ["eng"], "last_modified": "2024-07-06T16:44:51", "parent_id": "261fac731945a138415adc2dd4434b17"}, "text": "This is my first thought. This is my second thought.", "type": "NarrativeText"}
+{"element_id": "0de25bd6f0d74bc4f909f2678f385736", "metadata": {"category_depth": 0, "file_directory": "unstructured/example-docs", "filename": "simple.docx", "filetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "languages": ["eng"], "last_modified": "2024-07-06T16:44:51", "parent_id": "261fac731945a138415adc2dd4434b17"}, "text": "This is my third thought.", "type": "NarrativeText"}
+{"element_id": "f296a3bc8a901f19199fda1da92829b6", "metadata": {"category_depth": 0, "file_directory": "unstructured/example-docs", "filename": "simple.docx", "filetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "languages": ["eng"], "last_modified": "2024-07-06T16:44:51", "parent_id": "261fac731945a138415adc2dd4434b17"}, "text": "2023", "type": "UncategorizedText"}
+{"element_id": "78c62edbc674fdca0f6a0e3ffb459f86", "metadata": {"category_depth": 0, "file_directory": "unstructured/example-docs", "filename": "simple.docx", "filetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "languages": ["eng"], "last_modified": "2024-07-06T16:44:51"}, "text": "DOYLESTOWN, PA 18901", "type": "Address"}

requirements/base.in

@@ -22,3 +22,4 @@ tqdm
 psutil
 python-oxmsg
 html5lib
+ndjson

requirements/base.txt

@@ -4,13 +4,13 @@
 #
 #    pip-compile ./base.in
 #
-anyio==4.6.2.post1
+anyio==4.7.0
     # via httpx
 backoff==2.2.1
     # via -r ./base.in
 beautifulsoup4==4.12.3
     # via -r ./base.in
-certifi==2024.8.30
+certifi==2024.12.14
     # via
     #   httpcore
     #   httpx
@@ -28,13 +28,13 @@ click==8.1.7
     # via
     #   nltk
     #   python-oxmsg
-cryptography==43.0.3
+cryptography==44.0.0
     # via unstructured-client
 dataclasses-json==0.6.7
     # via
     #   -r ./base.in
     #   unstructured-client
-deepdiff==8.0.1
+deepdiff==8.1.1
     # via unstructured-client
 emoji==2.14.0
     # via -r ./base.in
@@ -46,9 +46,9 @@ h11==0.14.0
     # via httpcore
 html5lib==1.1
     # via -r ./base.in
-httpcore==1.0.6
+httpcore==1.0.7
     # via httpx
-httpx==0.27.2
+httpx==0.28.1
     # via unstructured-client
 idna==3.10
     # via
@@ -64,14 +64,16 @@ langdetect==1.0.9
     # via -r ./base.in
 lxml==5.3.0
     # via -r ./base.in
-marshmallow==3.23.0
+marshmallow==3.23.1
     # via
     #   dataclasses-json
     #   unstructured-client
 mypy-extensions==1.0.0
     # via
     #   typing-inspect
     #   unstructured-client
+ndjson==0.3.1
+    # via -r ./base.in
 nest-asyncio==1.6.0
     # via unstructured-client
 nltk==3.9.1
@@ -80,17 +82,17 @@ numpy==1.26.4
     # via -r ./base.in
 olefile==0.47
     # via python-oxmsg
-orderly-set==5.2.2
+orderly-set==5.2.3
     # via deepdiff
-packaging==24.1
+packaging==24.2
     # via
     #   marshmallow
     #   unstructured-client
 psutil==6.1.0
     # via -r ./base.in
 pycparser==2.22
     # via cffi
-pypdf==5.0.1
+pypdf==5.1.0
     # via unstructured-client
 python-dateutil==2.9.0.post0
     # via unstructured-client
@@ -100,9 +102,9 @@ python-magic==0.4.27
     # via -r ./base.in
 python-oxmsg==0.0.1
     # via -r ./base.in
-rapidfuzz==3.10.1
+rapidfuzz==3.11.0
     # via -r ./base.in
-regex==2024.9.11
+regex==2024.11.6
     # via nltk
 requests==2.32.3
     # via
@@ -111,19 +113,17 @@ requests==2.32.3
     #   unstructured-client
 requests-toolbelt==1.0.0
     # via unstructured-client
-six==1.16.0
+six==1.17.0
     # via
     #   html5lib
     #   langdetect
     #   python-dateutil
     #   unstructured-client
 sniffio==1.3.1
-    # via
-    #   anyio
-    #   httpx
+    # via anyio
 soupsieve==2.6
     # via beautifulsoup4
-tqdm==4.66.5
+tqdm==4.67.1
     # via
     #   -r ./base.in
     #   nltk
@@ -150,5 +150,5 @@ urllib3==1.26.20
     #   unstructured-client
 webencodings==0.5.1
     # via html5lib
-wrapt==1.16.0
+wrapt==1.17.0
     # via -r ./base.in

requirements/dev.txt

@@ -17,15 +17,15 @@ distlib==0.3.9
     # via virtualenv
 filelock==3.16.1
     # via virtualenv
-identify==2.6.1
+identify==2.6.3
     # via pre-commit
 importlib-metadata==8.5.0
     # via
     #   -c ././deps/constraints.txt
     #   build
 nodeenv==1.9.1
     # via pre-commit
-packaging==24.1
+packaging==24.2
     # via
     #   -c ./base.txt
     #   -c ./test.txt
@@ -46,16 +46,16 @@ pyyaml==6.0.2
     # via
     #   -c ./test.txt
     #   pre-commit
-tomli==2.0.2
+tomli==2.2.1
     # via
     #   -c ./test.txt
     #   build
     #   pip-tools
-virtualenv==20.27.0
+virtualenv==20.28.0
     # via pre-commit
-wheel==0.44.0
+wheel==0.45.1
     # via pip-tools
-zipp==3.20.2
+zipp==3.21.0
     # via importlib-metadata
 
 # The following packages are considered to be unsafe in a requirements file:

requirements/extra-csv.txt

@@ -16,7 +16,7 @@ python-dateutil==2.9.0.post0
     #   pandas
 pytz==2024.2
     # via pandas
-six==1.16.0
+six==1.17.0
     # via
     #   -c ./base.txt
     #   python-dateutil

requirements/extra-markdown.txt

@@ -10,5 +10,5 @@ importlib-metadata==8.5.0
     #   markdown
 markdown==3.7
     # via -r ./extra-markdown.in
-zipp==3.20.2
+zipp==3.21.0
     # via importlib-metadata

requirements/extra-paddleocr.txt

@@ -4,13 +4,13 @@
 #
 #    pip-compile ./extra-paddleocr.in
 #
-anyio==4.6.2.post1
+anyio==4.7.0
     # via
     #   -c ./base.txt
     #   httpx
 astor==0.8.1
     # via paddlepaddle
-certifi==2024.8.30
+certifi==2024.12.14
     # via
     #   -c ./base.txt
     #   httpcore
@@ -32,17 +32,17 @@ exceptiongroup==1.2.2
     # via
     #   -c ./base.txt
     #   anyio
-fonttools==4.54.1
+fonttools==4.55.3
     # via matplotlib
 h11==0.14.0
     # via
     #   -c ./base.txt
     #   httpcore
-httpcore==1.0.6
+httpcore==1.0.7
     # via
     #   -c ./base.txt
     #   httpx
-httpx==0.27.2
+httpx==0.28.1
     # via
     #   -c ./base.txt
     #   paddlepaddle
@@ -52,7 +52,7 @@ idna==3.10
     #   anyio
     #   httpx
     #   requests
-imageio==2.36.0
+imageio==2.36.1
     # via
     #   imgaug
     #   scikit-image
@@ -64,7 +64,7 @@ kiwisolver==1.4.7
     # via matplotlib
 lazy-loader==0.4
     # via scikit-image
-matplotlib==3.9.2
+matplotlib==3.9.4
     # via imgaug
 networkx==3.2.1
     # via
@@ -94,7 +94,7 @@ opencv-python==4.10.0.84
     #   unstructured-paddleocr
 opt-einsum==3.3.0
     # via paddlepaddle
-packaging==24.1
+packaging==24.2
     # via
     #   -c ./base.txt
     #   lazy-loader
@@ -127,7 +127,7 @@ python-dateutil==2.9.0.post0
     #   matplotlib
 pyyaml==6.0.2
     # via unstructured-paddleocr
-rapidfuzz==3.10.1
+rapidfuzz==3.11.0
     # via
     #   -c ./base.txt
     #   unstructured-paddleocr
@@ -147,7 +147,7 @@ shapely==2.0.6
     # via
     #   imgaug
     #   unstructured-paddleocr
-six==1.16.0
+six==1.17.0
     # via
     #   -c ./base.txt
     #   imgaug
@@ -156,10 +156,9 @@ sniffio==1.3.1
     # via
     #   -c ./base.txt
     #   anyio
-    #   httpx
 tifffile==2024.8.30
     # via scikit-image
-tqdm==4.66.5
+tqdm==4.67.1
     # via
     #   -c ./base.txt
     #   unstructured-paddleocr
@@ -175,5 +174,5 @@ urllib3==1.26.20
     #   -c ././deps/constraints.txt
     #   -c ./base.txt
     #   requests
-zipp==3.20.2
+zipp==3.21.0
     # via importlib-resources