From db07cf48616bface38e89b20819daf0136db85ec Mon Sep 17 00:00:00 2001 From: tbs17 Date: Tue, 21 Jan 2025 11:18:17 -0500 Subject: [PATCH 1/2] include pdfminer in base.in --- requirements/base.in | 3 ++- requirements/base.txt | 13 +++++-------- requirements/dev.txt | 6 +++--- 3 files changed, 10 insertions(+), 12 deletions(-) diff --git a/requirements/base.in b/requirements/base.in index a4ad49a2..a7781de8 100644 --- a/requirements/base.in +++ b/requirements/base.in @@ -13,4 +13,5 @@ transformers>=4.25.1 rapidfuzz pandas scipy -pdfplumber \ No newline at end of file +pypdfium2 +pdfminer-six==20240706 \ No newline at end of file diff --git a/requirements/base.txt b/requirements/base.txt index 6dd8d064..f0a9a6b3 100644 --- a/requirements/base.txt +++ b/requirements/base.txt @@ -27,7 +27,7 @@ filelock==3.16.1 # transformers flatbuffers==24.12.23 # via onnxruntime -fonttools==4.55.3 +fonttools==4.55.4 # via matplotlib fsspec==2024.12.0 # via @@ -83,14 +83,11 @@ packaging==24.2 # transformers pandas==2.2.3 # via -r requirements/base.in -pdfminer-six==20231228 - # via pdfplumber -pdfplumber==0.11.5 +pdfminer-six==20240706 # via -r requirements/base.in pillow==11.1.0 # via # matplotlib - # pdfplumber # torchvision protobuf==5.29.3 # via @@ -101,7 +98,7 @@ pycparser==2.22 pyparsing==3.2.1 # via matplotlib pypdfium2==4.30.1 - # via pdfplumber + # via -r requirements/base.in python-dateutil==2.9.0.post0 # via # matplotlib @@ -135,7 +132,7 @@ sympy==1.13.1 # via # onnxruntime # torch -timm==1.0.13 +timm==1.0.14 # via -r requirements/base.in tokenizers==0.21.0 # via transformers @@ -150,7 +147,7 @@ tqdm==4.67.1 # via # huggingface-hub # transformers -transformers==4.48.0 +transformers==4.48.1 # via -r requirements/base.in typing-extensions==4.12.2 # via diff --git a/requirements/dev.txt b/requirements/dev.txt index b4ea4117..ed449e59 100644 --- a/requirements/dev.txt +++ b/requirements/dev.txt @@ -80,7 +80,7 @@ executing==2.1.0 # via stack-data fastjsonschema==2.21.1 # via nbformat -fonttools==4.55.3 +fonttools==4.55.4 # via # -c requirements/base.txt # matplotlib @@ -106,7 +106,7 @@ idna==3.10 # httpx # jsonschema # requests -importlib-metadata==8.5.0 +importlib-metadata==8.6.1 # via # build # jupyter-client @@ -273,7 +273,7 @@ platformdirs==4.3.6 # jupyter-core prometheus-client==0.21.1 # via jupyter-server -prompt-toolkit==3.0.48 +prompt-toolkit==3.0.50 # via # ipython # jupyter-console From 03f2d6f338cc1816c10795dd7ac86c476cf92e2f Mon Sep 17 00:00:00 2001 From: tbs17 Date: Tue, 21 Jan 2025 11:21:23 -0500 Subject: [PATCH 2/2] update changelog and version --- CHANGELOG.md | 4 ++++ unstructured_inference/__version__.py | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 6a83327c..101c5db5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,7 @@ +## 0.8.5 + +* fix: remove `pdfplumber` but include `pdfminer-six==20240706` to update `pdfminer` + ## 0.8.4 * feat: add `text_as_html` and `table_as_cells` to `LayoutElements` class as new attributes diff --git a/unstructured_inference/__version__.py b/unstructured_inference/__version__.py index 37769adf..9641792f 100644 --- a/unstructured_inference/__version__.py +++ b/unstructured_inference/__version__.py @@ -1 +1 @@ -__version__ = "0.8.4" # pragma: no cover +__version__ = "0.8.5" # pragma: no cover