huangfu/DronePlanning
2
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

修改为东南天坐标系

Browse Source
This commit is contained in:
huangfu
2026-01-20 09:49:52 +08:00
parent 9538757047
commit 333fad40ac
7201 changed files with 1030888 additions and 85410 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
backend_service/venv/lib/python3.13/site-packages/unstructured-0.18.27.dist-info/INSTALLER Normal file
View File

@@ -0,0 +1 @@
pip

419
backend_service/venv/lib/python3.13/site-packages/unstructured-0.18.27.dist-info/METADATA Normal file
View File

@@ -0,0 +1,419 @@
Metadata-Version: 2.4
Name: unstructured
Version: 0.18.27
Summary: A library that prepares raw documents for downstream ML tasks.
Home-page: https://github.com/Unstructured-IO/unstructured
Author: Unstructured Technologies
Author-email: devops@unstructuredai.io
License: Apache-2.0
Keywords: NLP PDF HTML CV XML parsing preprocessing
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10.0
Description-Content-Type: text/markdown
License-File: LICENSE.md
Requires-Dist: charset-normalizer
Requires-Dist: filetype
Requires-Dist: python-magic
Requires-Dist: lxml
Requires-Dist: nltk
Requires-Dist: requests
Requires-Dist: beautifulsoup4
Requires-Dist: emoji
Requires-Dist: dataclasses-json
Requires-Dist: python-iso639
Requires-Dist: langdetect
Requires-Dist: numpy
Requires-Dist: rapidfuzz
Requires-Dist: backoff
Requires-Dist: typing-extensions
Requires-Dist: unstructured-client
Requires-Dist: wrapt
Requires-Dist: tqdm
Requires-Dist: psutil
Requires-Dist: python-oxmsg
Requires-Dist: html5lib
Provides-Extra: all-docs
Requires-Dist: markdown; extra == "all-docs"
Requires-Dist: openpyxl; extra == "all-docs"
Requires-Dist: python-pptx>=1.0.1; extra == "all-docs"
Requires-Dist: python-docx>=1.1.2; extra == "all-docs"
Requires-Dist: pypdf; extra == "all-docs"
Requires-Dist: onnx>=1.17.0; extra == "all-docs"
Requires-Dist: google-cloud-vision; extra == "all-docs"
Requires-Dist: pi_heif; extra == "all-docs"
Requires-Dist: pdf2image; extra == "all-docs"
Requires-Dist: effdet; extra == "all-docs"
Requires-Dist: networkx; extra == "all-docs"
Requires-Dist: pdfminer.six; extra == "all-docs"
Requires-Dist: xlrd; extra == "all-docs"
Requires-Dist: onnxruntime>=1.19.0; extra == "all-docs"
Requires-Dist: unstructured.pytesseract>=0.3.12; extra == "all-docs"
Requires-Dist: pandas; extra == "all-docs"
Requires-Dist: pikepdf; extra == "all-docs"
Requires-Dist: unstructured-inference>=1.1.1; extra == "all-docs"
Requires-Dist: msoffcrypto-tool; extra == "all-docs"
Requires-Dist: pypandoc; extra == "all-docs"
Provides-Extra: csv
Requires-Dist: pandas; extra == "csv"
Provides-Extra: doc
Requires-Dist: python-docx>=1.1.2; extra == "doc"
Provides-Extra: docx
Requires-Dist: python-docx>=1.1.2; extra == "docx"
Provides-Extra: epub
Requires-Dist: pypandoc; extra == "epub"
Provides-Extra: image
Requires-Dist: onnx>=1.17.0; extra == "image"
Requires-Dist: onnxruntime>=1.19.0; extra == "image"
Requires-Dist: pdf2image; extra == "image"
Requires-Dist: pdfminer.six; extra == "image"
Requires-Dist: pikepdf; extra == "image"
Requires-Dist: pi_heif; extra == "image"
Requires-Dist: pypdf; extra == "image"
Requires-Dist: google-cloud-vision; extra == "image"
Requires-Dist: effdet; extra == "image"
Requires-Dist: unstructured-inference>=1.1.1; extra == "image"
Requires-Dist: unstructured.pytesseract>=0.3.12; extra == "image"
Provides-Extra: md
Requires-Dist: markdown; extra == "md"
Provides-Extra: odt
Requires-Dist: python-docx>=1.1.2; extra == "odt"
Requires-Dist: pypandoc; extra == "odt"
Provides-Extra: org
Requires-Dist: pypandoc; extra == "org"
Provides-Extra: pdf
Requires-Dist: onnx>=1.17.0; extra == "pdf"
Requires-Dist: onnxruntime>=1.19.0; extra == "pdf"
Requires-Dist: pdf2image; extra == "pdf"
Requires-Dist: pdfminer.six; extra == "pdf"
Requires-Dist: pikepdf; extra == "pdf"
Requires-Dist: pi_heif; extra == "pdf"
Requires-Dist: pypdf; extra == "pdf"
Requires-Dist: google-cloud-vision; extra == "pdf"
Requires-Dist: effdet; extra == "pdf"
Requires-Dist: unstructured-inference>=1.1.1; extra == "pdf"
Requires-Dist: unstructured.pytesseract>=0.3.12; extra == "pdf"
Provides-Extra: ppt
Requires-Dist: python-pptx>=1.0.1; extra == "ppt"
Provides-Extra: pptx
Requires-Dist: python-pptx>=1.0.1; extra == "pptx"
Provides-Extra: rtf
Requires-Dist: pypandoc; extra == "rtf"
Provides-Extra: rst
Requires-Dist: pypandoc; extra == "rst"
Provides-Extra: tsv
Requires-Dist: pandas; extra == "tsv"
Provides-Extra: xlsx
Requires-Dist: openpyxl; extra == "xlsx"
Requires-Dist: pandas; extra == "xlsx"
Requires-Dist: xlrd; extra == "xlsx"
Requires-Dist: networkx; extra == "xlsx"
Requires-Dist: msoffcrypto-tool; extra == "xlsx"
Provides-Extra: huggingface
Requires-Dist: langdetect; extra == "huggingface"
Requires-Dist: sacremoses; extra == "huggingface"
Requires-Dist: sentencepiece; extra == "huggingface"
Requires-Dist: torch; extra == "huggingface"
Requires-Dist: transformers; extra == "huggingface"
Provides-Extra: local-inference
Requires-Dist: markdown; extra == "local-inference"
Requires-Dist: openpyxl; extra == "local-inference"
Requires-Dist: python-pptx>=1.0.1; extra == "local-inference"
Requires-Dist: python-docx>=1.1.2; extra == "local-inference"
Requires-Dist: pypdf; extra == "local-inference"
Requires-Dist: onnx>=1.17.0; extra == "local-inference"
Requires-Dist: google-cloud-vision; extra == "local-inference"
Requires-Dist: pi_heif; extra == "local-inference"
Requires-Dist: pdf2image; extra == "local-inference"
Requires-Dist: effdet; extra == "local-inference"
Requires-Dist: networkx; extra == "local-inference"
Requires-Dist: pdfminer.six; extra == "local-inference"
Requires-Dist: xlrd; extra == "local-inference"
Requires-Dist: onnxruntime>=1.19.0; extra == "local-inference"
Requires-Dist: unstructured.pytesseract>=0.3.12; extra == "local-inference"
Requires-Dist: pandas; extra == "local-inference"
Requires-Dist: pikepdf; extra == "local-inference"
Requires-Dist: unstructured-inference>=1.1.1; extra == "local-inference"
Requires-Dist: msoffcrypto-tool; extra == "local-inference"
Requires-Dist: pypandoc; extra == "local-inference"
Provides-Extra: paddleocr
Requires-Dist: paddlepaddle>=3.0.0b1; extra == "paddleocr"
Requires-Dist: unstructured.paddleocr==2.10.0; extra == "paddleocr"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: license-file
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary
<h3 align="center">
<img
src="https://raw.githubusercontent.com/Unstructured-IO/unstructured/main/img/unstructured_logo.png"
height="200"
>
</h3>
<div align="center">
<a href="https://github.com/Unstructured-IO/unstructured/blob/main/LICENSE.md">![https://pypi.python.org/pypi/unstructured/](https://img.shields.io/pypi/l/unstructured.svg)</a>
<a href="https://pypi.python.org/pypi/unstructured/">![https://pypi.python.org/pypi/unstructured/](https://img.shields.io/pypi/pyversions/unstructured.svg)</a>
<a href="https://GitHub.com/unstructured-io/unstructured/graphs/contributors">![https://GitHub.com/unstructured-io/unstructured.js/graphs/contributors](https://img.shields.io/github/contributors/unstructured-io/unstructured)</a>
<a href="https://github.com/Unstructured-IO/unstructured/blob/main/CODE_OF_CONDUCT.md">![code_of_conduct.md](https://img.shields.io/badge/Contributor%20Covenant-2.1-4baaaa.svg) </a>
<a href="https://GitHub.com/unstructured-io/unstructured/releases">![https://GitHub.com/unstructured-io/unstructured.js/releases](https://img.shields.io/github/release/unstructured-io/unstructured)</a>
<a href="https://pypi.python.org/pypi/unstructured/">![https://github.com/Naereen/badges/](https://badgen.net/badge/Open%20Source%20%3F/Yes%21/blue?icon=github)</a>
[![Downloads](https://static.pepy.tech/badge/unstructured)](https://pepy.tech/project/unstructured)
[![Downloads](https://static.pepy.tech/badge/unstructured/month)](https://pepy.tech/project/unstructured)
<a
href="https://www.phorm.ai/query?projectId=34efc517-2201-4376-af43-40c4b9da3dc5">
<img src="https://img.shields.io/badge/Phorm-Ask_AI-%23F2777A.svg?&logo=data:image/svg+xml;base64,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" />
</a>
</div>
<div>
<p align="center">
<a
href="https://short.unstructured.io/pzw05l7">
<img src="https://img.shields.io/badge/JOIN US ON SLACK-4A154B?style=for-the-badge&logo=slack&logoColor=white" />
</a>
<a href="https://www.linkedin.com/company/unstructuredio/">
<img src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" />
</a>
</div>
<h2 align="center">
<p>Open-Source Pre-Processing Tools for Unstructured Data</p>
</h2>
The `unstructured` library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and [many more](https://docs.unstructured.io/open-source/core-functionality/partitioning). The use cases of `unstructured` revolve around streamlining and optimizing the data processing workflow for LLMs. `unstructured` modular functions and connectors form a cohesive system that simplifies data ingestion and pre-processing, making it adaptable to different platforms and efficient in transforming unstructured data into structured outputs.
## Try the Unstructured Platform Product
Ready to move your data processing pipeline to production, and take advantage of advanced features? Check out [Unstructured Platform](https://unstructured.io/enterprise). In addition to better processing performance, take advantage of chunking, embedding, and image and table enrichment generation, all from a low code UI or an API. [Request a demo](https://unstructured.io/contact) from our sales team to learn more about how to get started.
## :eight_pointed_black_star: Quick Start
There are several ways to use the `unstructured` library:
* [Run the library in a container](https://github.com/Unstructured-IO/unstructured#run-the-library-in-a-container) or
* Install the library
1. [Install from PyPI](https://github.com/Unstructured-IO/unstructured#installing-the-library)
2. [Install for local development](https://github.com/Unstructured-IO/unstructured#installation-instructions-for-local-development)
* For installation with `conda` on Windows system, please refer to the [documentation](https://unstructured-io.github.io/unstructured/installing.html#installation-with-conda-on-windows)
### Run the library in a container
The following instructions are intended to help you get up and running using Docker to interact with `unstructured`.
See [here](https://docs.docker.com/get-docker/) if you don't already have docker installed on your machine.
NOTE: we build multi-platform images to support both x86_64 and Apple silicon hardware. `docker pull` should download the corresponding image for your architecture, but you can specify with `--platform` (e.g. `--platform linux/amd64`) if needed.
We build Docker images for all pushes to `main`. We tag each image with the corresponding short commit hash (e.g. `fbc7a69`) and the application version (e.g. `0.5.5-dev1`). We also tag the most recent image with `latest`. To leverage this, `docker pull` from our image repository.
```bash
docker pull downloads.unstructured.io/unstructured-io/unstructured:latest
```
Once pulled, you can create a container from this image and shell to it.
```bash
# create the container
docker run -dt --name unstructured downloads.unstructured.io/unstructured-io/unstructured:latest
# this will drop you into a bash shell where the Docker image is running
docker exec -it unstructured bash
```
You can also build your own Docker image. Note that the base image is `wolfi-base`, which is
updated regularly. If you are building the image locally, it is possible `docker-build` could
fail due to upstream changes in `wolfi-base`.
If you only plan on parsing one type of data you can speed up building the image by commenting out some
of the packages/requirements necessary for other data types. See Dockerfile to know which lines are necessary
for your use case.
```bash
make docker-build
# this will drop you into a bash shell where the Docker image is running
make docker-start-bash
```
Once in the running container, you can try things directly in Python interpreter's interactive mode.
```bash
# this will drop you into a python console so you can run the below partition functions
python3
>>> from unstructured.partition.pdf import partition_pdf
>>> elements = partition_pdf(filename="example-docs/layout-parser-paper-fast.pdf")
>>> from unstructured.partition.text import partition_text
>>> elements = partition_text(filename="example-docs/fake-text.txt")
```
### Installing the library
Use the following instructions to get up and running with `unstructured` and test your
installation.
- Install the Python SDK to support all document types with `pip install "unstructured[all-docs]"`
- For plain text files, HTML, XML, JSON and Emails that do not require any extra dependencies, you can run `pip install unstructured`
- To process other doc types, you can install the extras required for those documents, such as `pip install "unstructured[docx,pptx]"`
- Install the following system dependencies if they are not already available on your system.
Depending on what document types you're parsing, you may not need all of these.
- `libmagic-dev` (filetype detection)
- `poppler-utils` (images and PDFs)
- `tesseract-ocr` (images and PDFs, install `tesseract-lang` for additional language support)
- `libreoffice` (MS Office docs)
- `pandoc` (EPUBs, RTFs and Open Office docs). Please note that to handle RTF files, you need version `2.14.2` or newer. Running either `make install-pandoc` or `./scripts/install-pandoc.sh` will install the correct version for you.
- For suggestions on how to install on the Windows and to learn about dependencies for other features, see the
installation documentation [here](https://unstructured-io.github.io/unstructured/installing.html).
At this point, you should be able to run the following code:
```python
from unstructured.partition.auto import partition
elements = partition(filename="example-docs/eml/fake-email.eml")
print("\n\n".join([str(el) for el in elements]))
```
### Installation Instructions for Local Development
The following instructions are intended to help you get up and running with `unstructured`
locally if you are planning to contribute to the project.
* Using `pyenv` to manage virtualenv's is recommended but not necessary
* Mac install instructions. See [here](https://github.com/Unstructured-IO/community#mac--homebrew) for more detailed instructions.
* `brew install pyenv-virtualenv`
* `pyenv install 3.10`
* Linux instructions are available [here](https://github.com/Unstructured-IO/community#linux).
* Create a virtualenv to work in and activate it, e.g. for one named `unstructured`:
`pyenv virtualenv 3.10 unstructured` <br />
`pyenv activate unstructured`
* Run `make install`
* Optional:
* To install models and dependencies for processing images and PDFs locally, run `make install-local-inference`.
* For processing image files, `tesseract` is required. See [here](https://tesseract-ocr.github.io/tessdoc/Installation.html) for installation instructions.
* For processing PDF files, `tesseract` and `poppler` are required. The [pdf2image docs](https://pdf2image.readthedocs.io/en/latest/installation.html) have instructions on installing `poppler` across various platforms.
Additionally, if you're planning to contribute to `unstructured`, we provide you an optional `pre-commit` configuration
file to ensure your code matches the formatting and linting standards used in `unstructured`.
If you'd prefer not to have code changes auto-tidied before every commit, you can use `make check` to see
whether any linting or formatting changes should be applied, and `make tidy` to apply them.
If using the optional `pre-commit`, you'll just need to install the hooks with `pre-commit install` since the
`pre-commit` package is installed as part of `make install` mentioned above. Finally, if you decided to use `pre-commit`
you can also uninstall the hooks with `pre-commit uninstall`.
In addition to develop in your local OS we also provide a helper to use docker providing a development environment:
```bash
make docker-start-dev
```
This starts a docker container with your local repo mounted to `/mnt/local_unstructured`. This docker image allows you to develop without worrying about your OS's compatibility with the repo and its dependencies.
## :clap: Quick Tour
### Documentation
For more comprehensive documentation, visit https://docs.unstructured.io . You can also learn
more about our other products on the documentation page, including our SaaS API.
Here are a few pages from the [Open Source documentation page](https://docs.unstructured.io/open-source/introduction/overview)
that are helpful for new users to review:
- [Quick Start](https://docs.unstructured.io/open-source/introduction/quick-start)
- [Using the `unstructured` open source package](https://docs.unstructured.io/open-source/core-functionality/overview)
- [Connectors](https://docs.unstructured.io/open-source/ingest/overview)
- [Concepts](https://docs.unstructured.io/open-source/concepts/document-elements)
- [Integrations](https://docs.unstructured.io/open-source/integrations)
### PDF Document Parsing Example
The following examples show how to get started with the `unstructured` library. The easiest way to parse a document in unstructured is to use the `partition` function. If you use `partition` function, `unstructured` will detect the file type and route it to the appropriate file-specific partitioning function. If you are using the `partition` function, you may need to install additional dependencies per doc type.
For example, to install docx dependencies you need to run `pip install "unstructured[docx]"`.
See our [installation guide](https://docs.unstructured.io/open-source/installation/full-installation) for more details.
```python
from unstructured.partition.auto import partition
elements = partition("example-docs/layout-parser-paper.pdf")
```
Run `print("\n\n".join([str(el) for el in elements]))` to get a string representation of the
output, which looks like:
```
LayoutParser : A Unified Toolkit for Deep Learning Based Document Image Analysis
Zejiang Shen 1 ( (cid:0) ), Ruochen Zhang 2 , Melissa Dell 3 , Benjamin Charles Germain Lee 4 , Jacob Carlson 3 , and
Weining Li 5
Abstract. Recent advances in document image analysis (DIA) have been primarily driven by the application of neural
networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation.
However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy
reuse of important innovations by a wide audience. Though there have been ongoing efforts to improve reusability and
simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none
of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA
is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper
introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applications.
The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models
for layout detection, character recognition, and many other document processing tasks. To promote extensibility,
LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digitization
pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in
real-word use cases. The library is publicly available at https://layout-parser.github.io
Keywords: Document Image Analysis · Deep Learning · Layout Analysis · Character Recognition · Open Source library ·
Toolkit.
Introduction
Deep Learning(DL)-based approaches are the state-of-the-art for a wide range of document image analysis (DIA) tasks
including document image classification [11,
```
See the [partitioning](https://docs.unstructured.io/open-source/core-functionality/partitioning)
section in our documentation for a full list of options and instructions on how to use
file-specific partitioning functions.
## :guardsman: Security Policy
See our [security policy](https://github.com/Unstructured-IO/unstructured/security/policy) for
information on how to report security vulnerabilities.
## :bug: Reporting Bugs
Encountered a bug? Please create a new [GitHub issue](https://github.com/Unstructured-IO/unstructured/issues/new/choose) and use our bug report template to describe the problem. To help us diagnose the issue, use the `python scripts/collect_env.py` command to gather your system's environment information and include it in your report. Your assistance helps us continuously improve our software - thank you!
## :books: Learn more
| Section | Description |
|-|-|
| [Company Website](https://unstructured.io) | Unstructured.io product and company info |
| [Documentation](https://docs.unstructured.io/) | Full API documentation |
| [Batch Processing](https://github.com/Unstructured-IO/unstructured-ingest) | Ingesting batches of documents through Unstructured |
## :chart_with_upwards_trend: Analytics
This library includes a very lightweight analytics "ping" when the library is loaded, however you can opt out of this data collection by setting the environment variable `DO_NOT_TRACK=true` before executing any `unstructured` code. To learn more about how we collect and use this data, please read our [Privacy Policy](https://unstructured.io/privacy-policy).

477
backend_service/venv/lib/python3.13/site-packages/unstructured-0.18.27.dist-info/RECORD Normal file
View File

@@ -0,0 +1,477 @@
test_unstructured/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/__pycache__/test_utils.cpython-313.pyc,,
test_unstructured/__pycache__/unit_utils.cpython-313.pyc,,
test_unstructured/chunking/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/chunking/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/chunking/__pycache__/test_base.cpython-313.pyc,,
test_unstructured/chunking/__pycache__/test_basic.cpython-313.pyc,,
test_unstructured/chunking/__pycache__/test_dispatch.cpython-313.pyc,,
test_unstructured/chunking/__pycache__/test_html_output.cpython-313.pyc,,
test_unstructured/chunking/__pycache__/test_title.cpython-313.pyc,,
test_unstructured/chunking/test_base.py,sha256=cLCbSX2Dr-ckG774tAaxurZ0peiV0xfbRn7IeISsyis,74047
test_unstructured/chunking/test_basic.py,sha256=x1l8Rnl4tnG1_VjwdJn-LTCZbGXGPyzF3pXGNZuntfQ,8309
test_unstructured/chunking/test_dispatch.py,sha256=xHD5BTim8aTLmi7PH65mKvXmrJslAf6xYd-sKgd1fSo,3255
test_unstructured/chunking/test_html_output.py,sha256=uJ7jdvuZYTstgE5xrQ-BF1QfFvowJbOJjwO66LAjRu8,3253
test_unstructured/chunking/test_title.py,sha256=o4OHl_KoFnGznLJ1cssB5C1YcBnDsFoFVpM3h4wWM9A,19446
test_unstructured/cleaners/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/cleaners/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/cleaners/__pycache__/test_core.cpython-313.pyc,,
test_unstructured/cleaners/__pycache__/test_extract.cpython-313.pyc,,
test_unstructured/cleaners/__pycache__/test_translate.cpython-313.pyc,,
test_unstructured/cleaners/test_core.py,sha256=3FVidZQD-qK9lCsiKftkARghqCAYcelHbBD0BnLve8k,10357
test_unstructured/cleaners/test_extract.py,sha256=A5g85ipVESZkD_4TA0s7WOujddlA3sqsHnSFQlzMrus,4679
test_unstructured/cleaners/test_translate.py,sha256=TWRfa05gpqffjIShfkU2wEG24wBYfg4TOjaJJP_04qA,2074
test_unstructured/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/common/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/common/__pycache__/test_html_table.cpython-313.pyc,,
test_unstructured/common/test_html_table.py,sha256=fUcK9yFK_ArNBeDrfxKft8GAfsU9bqp3WEEdxdKTLPM,7579
test_unstructured/documents/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/documents/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/documents/__pycache__/test_coordinates.cpython-313.pyc,,
test_unstructured/documents/__pycache__/test_elements.cpython-313.pyc,,
test_unstructured/documents/__pycache__/test_mappings.cpython-313.pyc,,
test_unstructured/documents/__pycache__/test_ontology_to_unstructured_parsing.cpython-313.pyc,,
test_unstructured/documents/test_coordinates.py,sha256=8kIj45xu8SSf6vt3LRxoraMpY2yjiVcPsXYFPkpz2hU,2795
test_unstructured/documents/test_elements.py,sha256=4fkmdTjaLrAtzuEKFQwrV53dAcfKrASJjbS_yoQYDMQ,28660
test_unstructured/documents/test_mappings.py,sha256=9-LYAJQuJ7jEALqEJoBu3Jso80oVarsvQG4XoRiZZD4,1877
test_unstructured/documents/test_ontology_to_unstructured_parsing.py,sha256=GPnwlWWl7C9SG_hClSn4UykTPSzGSy3bJxHXSZKV1FY,12207
test_unstructured/embed/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/embed/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/embed/__pycache__/test_mixedbreadai.cpython-313.pyc,,
test_unstructured/embed/__pycache__/test_octoai.cpython-313.pyc,,
test_unstructured/embed/__pycache__/test_openai.cpython-313.pyc,,
test_unstructured/embed/__pycache__/test_vertexai.cpython-313.pyc,,
test_unstructured/embed/__pycache__/test_voyageai.cpython-313.pyc,,
test_unstructured/embed/test_mixedbreadai.py,sha256=3XzkygDeKXUAWiVEXKSdBi5ue8ilXqxZs9WxSgx9kek,1357
test_unstructured/embed/test_octoai.py,sha256=ok4ZO_80zuQpI16mASLTlregGCiFwpJOWnsafNn4U80,861
test_unstructured/embed/test_openai.py,sha256=1vsK1DuJu1krdes1uOBpzdFlnrHc5WbQ8CzzsJFh6H0,861
test_unstructured/embed/test_vertexai.py,sha256=uZ5aCGZgJjlx_SD1jKozukt7dWXm_hNXyiUuK2gPku0,876
test_unstructured/embed/test_voyageai.py,sha256=rCVbkKekcmigUDPOIuCosZG8qPwJZifsKaLJ1BmEjww,9324
test_unstructured/file_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/file_utils/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/file_utils/__pycache__/test_encoding.cpython-313.pyc,,
test_unstructured/file_utils/__pycache__/test_file_conversion.cpython-313.pyc,,
test_unstructured/file_utils/__pycache__/test_filetype.cpython-313.pyc,,
test_unstructured/file_utils/__pycache__/test_model.cpython-313.pyc,,
test_unstructured/file_utils/test_encoding.py,sha256=5o6OS5RpDNbzZgka6GCLhbsAyw-TdURAFxBl9sugbsE,2871
test_unstructured/file_utils/test_file_conversion.py,sha256=dtZ0Q4uMk46rbO25ofVQrDKwJCi8N8QmMH6jJidXSL4,1942
test_unstructured/file_utils/test_filetype.py,sha256=ZCc3z5yQlsj7V-chw8YauTKeSlro_qoWEE0MRilg3bE,40399
test_unstructured/file_utils/test_model.py,sha256=wfE8wD04wyKz2bDqtqMdNVmBL0TQOSAmsNWLHAq5SSY,8957
test_unstructured/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/metrics/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/metrics/__pycache__/test_element_type.cpython-313.pyc,,
test_unstructured/metrics/__pycache__/test_evaluate.cpython-313.pyc,,
test_unstructured/metrics/__pycache__/test_table_alignment.cpython-313.pyc,,
test_unstructured/metrics/__pycache__/test_table_detection_metrics.cpython-313.pyc,,
test_unstructured/metrics/__pycache__/test_table_formats.cpython-313.pyc,,
test_unstructured/metrics/__pycache__/test_table_structure.cpython-313.pyc,,
test_unstructured/metrics/__pycache__/test_text_extraction.cpython-313.pyc,,
test_unstructured/metrics/__pycache__/test_utils.cpython-313.pyc,,
test_unstructured/metrics/test_element_type.py,sha256=Yd7Tzxw29nlCqCjzL7LvRh7m9AfWuE9PO8I3u93pD8s,3388
test_unstructured/metrics/test_evaluate.py,sha256=hE2fEW23Mwfg-63r3zDZ7J2xnUFrZHPEYTxsmkYe07k,24604
test_unstructured/metrics/test_table_alignment.py,sha256=li4P_NLr5OaWCDR2adGadi_iycc_uzi0U5W5SbwVCAA,554
test_unstructured/metrics/test_table_detection_metrics.py,sha256=j4F9UdrRuSqp144P-Bxt03sANjQ3ovlalEIc8QYzopc,1555
test_unstructured/metrics/test_table_formats.py,sha256=esS-Ri8FQ9_nRCs0HVHrR2bkYevT3H_zML0p_BbmLn8,1357
test_unstructured/metrics/test_table_structure.py,sha256=9iMPU-HJ3ZwTZ2e7MljVkI0HAHqLKCFFNmkef1E4VKA,19704
test_unstructured/metrics/test_text_extraction.py,sha256=baLWgeXw4mwxCYM9aKbDEcu13foKL83M82_gILGSVM0,27042
test_unstructured/metrics/test_utils.py,sha256=PxMmFRjoHbJ2W-8YDBjJamLQb5a9n8JtQM6nsSmWdgU,925
test_unstructured/nlp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/nlp/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/nlp/__pycache__/mock_nltk.cpython-313.pyc,,
test_unstructured/nlp/__pycache__/test_partition.cpython-313.pyc,,
test_unstructured/nlp/__pycache__/test_tokenize.cpython-313.pyc,,
test_unstructured/nlp/mock_nltk.py,sha256=PsoZesQcrTP4Gxkx6_1CAI8TuYgVrLF2bDPP-i_nR6A,566
test_unstructured/nlp/test_partition.py,sha256=qz883Zaw3nFKv2fDVMng2TsY9FxY7ujvkYw3_RDTsUM,15
test_unstructured/nlp/test_tokenize.py,sha256=Mw9Ec128mFNyVXIsF6nP-MBoZDBKtbDckCY2VKDVFfE,2134
test_unstructured/partition/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/partition/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/partition/__pycache__/conftest.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_api.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_auto.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_constants.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_csv.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_doc.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_docx.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_email.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_epub.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_json.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_md.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_msg.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_ndjson.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_odt.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_org.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_ppt.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_pptx.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_rst.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_rtf.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_strategies.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_text.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_text_type.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_tsv.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_xlsx.cpython-313.pyc,,
test_unstructured/partition/__pycache__/test_xml.cpython-313.pyc,,
test_unstructured/partition/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/partition/common/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/partition/common/__pycache__/test_common.cpython-313.pyc,,
test_unstructured/partition/common/__pycache__/test_lang.cpython-313.pyc,,
test_unstructured/partition/common/__pycache__/test_metadata.cpython-313.pyc,,
test_unstructured/partition/common/test_common.py,sha256=3DIOGqXjX721ZYH1y9l1Q5CKhP-Tw5L0FxUrxqC6dxs,14318
test_unstructured/partition/common/test_lang.py,sha256=Mw_GPafrlQRo-64vkZSj7t1l7fi5dhBeV0zx43WjZxY,8981
test_unstructured/partition/common/test_metadata.py,sha256=uc0BLbw7wUlWiqj45XTKhYCNrkJeL0UsYoM98a-puDs,20448
test_unstructured/partition/conftest.py,sha256=eYZeMvCxxTqmNYghD5XewLToWKNHAmWLYKGj4uiMjt0,652
test_unstructured/partition/html/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/partition/html/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/partition/html/__pycache__/test_convert.cpython-313.pyc,,
test_unstructured/partition/html/__pycache__/test_html_to_ontology_parsing.cpython-313.pyc,,
test_unstructured/partition/html/__pycache__/test_html_to_unstructured_and_back_parsing.cpython-313.pyc,,
test_unstructured/partition/html/__pycache__/test_html_utils.cpython-313.pyc,,
test_unstructured/partition/html/__pycache__/test_parser.cpython-313.pyc,,
test_unstructured/partition/html/__pycache__/test_partition.cpython-313.pyc,,
test_unstructured/partition/html/__pycache__/test_partition_v2.cpython-313.pyc,,
test_unstructured/partition/html/__pycache__/test_unstructured_elements_to_ontology_parsing.cpython-313.pyc,,
test_unstructured/partition/html/test_convert.py,sha256=bN9cc6MqrJgpWuBToAmUMc8uOEBZvp-QkYOa2Y7PFm0,18123
test_unstructured/partition/html/test_html_to_ontology_parsing.py,sha256=FE9JH0F0TbouLU1qwuBkkLfb9wfIRGyXUaAPmoxWFuw,19935
test_unstructured/partition/html/test_html_to_unstructured_and_back_parsing.py,sha256=g2D7ngX24a2OZnfvxDVQZ5RdYACo4wiaxE_xMtlg6UU,15339
test_unstructured/partition/html/test_html_utils.py,sha256=ltlllMtcDlY4QFhhttue_eZgOafFYuIayYJ8gc_0nac,1069
test_unstructured/partition/html/test_parser.py,sha256=M99jj7Nw-EWDxwQ5aAz-Fwf4x3lnRdwYHZPIFwgwkTc,56536
test_unstructured/partition/html/test_partition.py,sha256=fRM4HIYIL-OsJyESpp_fnWn_j83Gwd9qY9M__5VMe4A,52492
test_unstructured/partition/html/test_partition_v2.py,sha256=zrqG11K3oXH6vsahLgAUq9G-zSn5FNYWZ6sNbpljD0w,2097
test_unstructured/partition/html/test_unstructured_elements_to_ontology_parsing.py,sha256=MvMxu-T9JfW-oZqLFUYbUMzoTNQiCd0Mx33Os65b81A,4903
test_unstructured/partition/pdf_image/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/partition/pdf_image/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/partition/pdf_image/__pycache__/conftest.cpython-313.pyc,,
test_unstructured/partition/pdf_image/__pycache__/test_analysis.cpython-313.pyc,,
test_unstructured/partition/pdf_image/__pycache__/test_image.cpython-313.pyc,,
test_unstructured/partition/pdf_image/__pycache__/test_inference_utils.cpython-313.pyc,,
test_unstructured/partition/pdf_image/__pycache__/test_merge_elements.cpython-313.pyc,,
test_unstructured/partition/pdf_image/__pycache__/test_ocr.cpython-313.pyc,,
test_unstructured/partition/pdf_image/__pycache__/test_pdf.cpython-313.pyc,,
test_unstructured/partition/pdf_image/__pycache__/test_pdf_image_utils.cpython-313.pyc,,
test_unstructured/partition/pdf_image/__pycache__/test_pdfminer_processing.cpython-313.pyc,,
test_unstructured/partition/pdf_image/__pycache__/test_pdfminer_utils.cpython-313.pyc,,
test_unstructured/partition/pdf_image/conftest.py,sha256=ejimRq_95Bb3Hfm6Yjyzu5tudx7ieidQ1gFXSUEpSMI,2293
test_unstructured/partition/pdf_image/test_analysis.py,sha256=T-NZKcfZLYM-pTZfUeWlYHfXTKjnv7b3_v5Fnslg3V0,5147
test_unstructured/partition/pdf_image/test_image.py,sha256=b2tLY240c2Z8r2ykl8K9tLQgAr1lTFIhCcLFmpmRpcY,23368
test_unstructured/partition/pdf_image/test_inference_utils.py,sha256=gDtk6QhNQAb6RWMglq-E1Nc7bLNr0T_Ia0icSY4mnmA,5924
test_unstructured/partition/pdf_image/test_merge_elements.py,sha256=-rBdRK1sHd0XVj32bplzqu7wPURoLiC1AF9Ynwq4nPQ,1973
test_unstructured/partition/pdf_image/test_ocr.py,sha256=iRFjByiypkCaFffli-23HmqzsltrLQPL7afx3A-MezQ,21539
test_unstructured/partition/pdf_image/test_pdf.py,sha256=D485nIa72EmoDSZq_obLX7P7KV8pBLECIekAdq0JPiY,57775
test_unstructured/partition/pdf_image/test_pdf_image_utils.py,sha256=c6gyxdeYGAwDLIr-5UIohaZy2Tuqctd-c6JZVemykuM,14102
test_unstructured/partition/pdf_image/test_pdfminer_processing.py,sha256=m1cfG51FnP3OHT392J_9-WqQr0VepuxDUnGAJ121nBA,12634
test_unstructured/partition/pdf_image/test_pdfminer_utils.py,sha256=vkedoo8pYVaEJrj_TKJHxDbyfUVkkFPfoiR4HjQJnt8,1104
test_unstructured/partition/test_api.py,sha256=ZKxZuPyf9XYYrYCU4S9olRuFYSl7lKXdi5TtNF45iAU,24218
test_unstructured/partition/test_auto.py,sha256=ljS8hBc_I0pJklXvIDaMVmGdP5oBbx6P-5ixsR7bHUc,51089
test_unstructured/partition/test_constants.py,sha256=iNYSaQMNH23A8hfhD7_gC6kJE4NwiOt76jaS1mLj-Ak,3852
test_unstructured/partition/test_csv.py,sha256=OcKyCuZMYNCr7TgSsEb0HpL_ry49CsCNeYDTYx2yRZU,12557
test_unstructured/partition/test_doc.py,sha256=SrrvLG77eR210TtOPX0u-2lppvkFBDs0RNAAP57_rck,9934
test_unstructured/partition/test_docx.py,sha256=0pHy4D-U4hJ1swk23P6FVE7VyBHGX4QDUyqCfD5gqx4,48962
test_unstructured/partition/test_email.py,sha256=yQA2s6ef4Vs_kq-eM92fyxcWK27uDD0cl1vzeVJDxkA,25443
test_unstructured/partition/test_epub.py,sha256=uAummMB0pz-OwR6QbCGBl66HbDCH9oAmyomzhQuLL0w,6505
test_unstructured/partition/test_json.py,sha256=Lk6ghCXif4sYoeClc8D61rMbMT4EgLdpmASthwb1eTc,11288
test_unstructured/partition/test_md.py,sha256=ULIKpVVI58ZBZNpKRKnBmS1FDeLSWv9s9oEZiAceA78,10507
test_unstructured/partition/test_msg.py,sha256=mqqDzf4OB0wy-XivJcjzp0i0M64bhiYthI3fBkjIFmA,22058
test_unstructured/partition/test_ndjson.py,sha256=hMr6FnjVI1fu_a6WeBF83tw66faZ6X9IJaij-E6M-aQ,11163
test_unstructured/partition/test_odt.py,sha256=oHMon5QMPRO2oSvz9OtfRlQl3zmi4Ab14GfjteoZ2DU,7751
test_unstructured/partition/test_org.py,sha256=yhe76gkM3xBsd97AoV-NOECAl2Si0Wk0obVa-G6mDBI,5765
test_unstructured/partition/test_ppt.py,sha256=AszuiZi3HESwZaE1PTGYgEQd5DUi4VI_KbHJqvV3Ig4,6917
test_unstructured/partition/test_pptx.py,sha256=iHIcUmbu-gSFBOVFAFOTYQyUiQJWtAsJ8YSgdGSh800,30211
test_unstructured/partition/test_rst.py,sha256=fg1YcPeaZkgl2v7z1qq729yvK4RJjccfc24vP9gy9ec,5122
test_unstructured/partition/test_rtf.py,sha256=f9Nw6Tj7lnzF0DB3H7E6l0njOgrO9uGjpCO3zYmsy9Y,4591
test_unstructured/partition/test_strategies.py,sha256=uNmDKQwOWgXGqKh0kX63XI_444CuC7nowAWOiv0j7Sw,4344
test_unstructured/partition/test_text.py,sha256=f_VODf0KXD_KcPzfOdzEFyLVBzMm61YpU0YqCmq4gbY,14834
test_unstructured/partition/test_text_type.py,sha256=Q_cdaDlzlEgw2FZ0dm9LSGQOJohFPR7_U4DD9K3Xv5A,12603
test_unstructured/partition/test_tsv.py,sha256=h_3WZ9IpqsAPMRPGKQCaPnL7q_XxdklyUNkCV6JnueY,5995
test_unstructured/partition/test_xlsx.py,sha256=VKdoJRbAS-YrET2hBGT5SOW8qhY0dkIBTOAD2dVwymc,24121
test_unstructured/partition/test_xml.py,sha256=Udvqw3Zn_tpzTZ_B3ImHeckkhqbXPLB04IS4fw0HbB8,8745
test_unstructured/partition/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/partition/utils/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/partition/utils/__pycache__/test_config.cpython-313.pyc,,
test_unstructured/partition/utils/__pycache__/test_sorting.cpython-313.pyc,,
test_unstructured/partition/utils/__pycache__/test_xycut.cpython-313.pyc,,
test_unstructured/partition/utils/test_config.py,sha256=-L866HOHHfWN6rF85FxkETfbfpGOEcg23DbmcAX2Mes,2001
test_unstructured/partition/utils/test_sorting.py,sha256=-ViuWVKUNjJkobee1fcf_7kVViXuVnf0TYdapPnrv4E,5132
test_unstructured/partition/utils/test_xycut.py,sha256=I-VaPlTnxuPp8G0FC8iqUYGm0Z9UxtQ9ddtZh7q5HYo,6211
test_unstructured/staging/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
test_unstructured/staging/__pycache__/__init__.cpython-313.pyc,,
test_unstructured/staging/__pycache__/test_base.cpython-313.pyc,,
test_unstructured/staging/__pycache__/test_baseplate.cpython-313.pyc,,
test_unstructured/staging/__pycache__/test_datasaur.cpython-313.pyc,,
test_unstructured/staging/__pycache__/test_huggingface.cpython-313.pyc,,
test_unstructured/staging/__pycache__/test_label_box.cpython-313.pyc,,
test_unstructured/staging/__pycache__/test_label_studio.cpython-313.pyc,,
test_unstructured/staging/__pycache__/test_prodigy.cpython-313.pyc,,
test_unstructured/staging/__pycache__/test_weaviate.cpython-313.pyc,,
test_unstructured/staging/test_base.py,sha256=kiSmNfWXtSoaj_r6rk97fE4W9R9JBUwb8d_vsu0751A,24704
test_unstructured/staging/test_baseplate.py,sha256=ACJ_OtLK_64e3xn3hS1jYZYApxaenETclphCzGyAFTc,2800
test_unstructured/staging/test_datasaur.py,sha256=jxn8jopADs1J7jRL-teWWtL0fD17wma0PAaAqoeDCkU,2176
test_unstructured/staging/test_huggingface.py,sha256=00MvpucyTEBFJebAVPxGlfOX4T3zl1esphH4W6JL-s8,2356
test_unstructured/staging/test_label_box.py,sha256=Pjbe5cPBWX2tlFk1YX1U29ujX-8slDYehQLd_1VC7K4,4335
test_unstructured/staging/test_label_studio.py,sha256=cH6oWhHHPGNAOBfH72T1xFGLQU-IakONZSskzDwlUts,10107
test_unstructured/staging/test_prodigy.py,sha256=MTFItzYNSnLNZ-ekMoNlGsfT4v9Hh8rFNFNwhtMvU-k,4020
test_unstructured/staging/test_weaviate.py,sha256=Mb0t_GrIzPjuTzYD3xdWMCu_PMCX0AfdRwn36hI6sdw,2214
test_unstructured/test_utils.py,sha256=v7ytk5UJccQ7OvaIOq8E6ioGSStcfG4HrPQD27xAQIU,10997
test_unstructured/unit_utils.py,sha256=ou0MBP2MStAx_ob-QGsuE5_JoDp_u6MUZoTEWFG7OAQ,8492
unstructured-0.18.27.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
unstructured-0.18.27.dist-info/METADATA,sha256=QlXqcOmSsWvw86hMA_i0VlGqnO1SZ7hU1GmQcABAEDY,25018
unstructured-0.18.27.dist-info/RECORD,,
unstructured-0.18.27.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured-0.18.27.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
unstructured-0.18.27.dist-info/licenses/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
unstructured-0.18.27.dist-info/top_level.txt,sha256=IVbYkzQJXExO4_PhBGUf5dc7OZZ75t9XYrjKn3KvodA,31
unstructured/__init__.py,sha256=SvwSYurR6AKi7Zp-JY0ZnR9D1QkIqtHM4FEdCgdAolM,77
unstructured/__pycache__/__init__.cpython-313.pyc,,
unstructured/__pycache__/__version__.cpython-313.pyc,,
unstructured/__pycache__/errors.cpython-313.pyc,,
unstructured/__pycache__/logger.cpython-313.pyc,,
unstructured/__pycache__/utils.cpython-313.pyc,,
unstructured/__version__.py,sha256=lelBG9J03KC3bE-uBTDR9rwZiF_HzLw9pM5W1SBXjyQ,44
unstructured/chunking/__init__.py,sha256=jvlh7MH_R3-v_5-ynDXcksd68w3ZejZcBbv5iJhLpOg,590
unstructured/chunking/__pycache__/__init__.cpython-313.pyc,,
unstructured/chunking/__pycache__/base.cpython-313.pyc,,
unstructured/chunking/__pycache__/basic.cpython-313.pyc,,
unstructured/chunking/__pycache__/dispatch.cpython-313.pyc,,
unstructured/chunking/__pycache__/title.cpython-313.pyc,,
unstructured/chunking/base.py,sha256=ehRDS7fvrgQs1PqnDblzrBECGFgf6Uu265m4FgBtXH4,57844
unstructured/chunking/basic.py,sha256=nIl41mrfV8pAxOEehwI20bKc-dwwNpBfRf8VWpKlw08,4249
unstructured/chunking/dispatch.py,sha256=hvZyn_K1vWFB2qIe6ndelDTr6YE7ZTUQSjidwzQmaew,5189
unstructured/chunking/title.py,sha256=UqB7-unPo49SeZVKG_rKeWJiESrREubv3Da3EE0yi6c,7594
unstructured/cleaners/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/cleaners/__pycache__/__init__.cpython-313.pyc,,
unstructured/cleaners/__pycache__/core.cpython-313.pyc,,
unstructured/cleaners/__pycache__/extract.cpython-313.pyc,,
unstructured/cleaners/__pycache__/translate.cpython-313.pyc,,
unstructured/cleaners/core.py,sha256=rbiTgt0ynMNPZHxaJuQSa4FpJsV0i8gOAiMHbkegkQs,14805
unstructured/cleaners/extract.py,sha256=BbBYANbWz1BSYWaip2kAQ6GN86nVVr6HiyO5FRqjEHc,4339
unstructured/cleaners/translate.py,sha256=iyA3fSUtNAUnqiD-qP4RoqujNGaw9y07Mo9vztZkTJU,3288
unstructured/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/common/__pycache__/__init__.cpython-313.pyc,,
unstructured/common/__pycache__/html_table.cpython-313.pyc,,
unstructured/common/html_table.py,sha256=dTZAsVksgQlOopxwnppCqivwBqM0BLDKOervnSc0o0U,5824
unstructured/documents/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/documents/__pycache__/__init__.cpython-313.pyc,,
unstructured/documents/__pycache__/coordinates.cpython-313.pyc,,
unstructured/documents/__pycache__/elements.cpython-313.pyc,,
unstructured/documents/__pycache__/mappings.cpython-313.pyc,,
unstructured/documents/__pycache__/ontology.cpython-313.pyc,,
unstructured/documents/coordinates.py,sha256=LoHrK13Py3TkQL__Vobug0KmF1MYwMAXP81AFinuPJw,3937
unstructured/documents/elements.py,sha256=4VFycRPIpVkDipdZqfO7bnKcB4axK8YOsiX-CNZDgho,38900
unstructured/documents/mappings.py,sha256=23AAZIIuZcX1V07dHGdcZNfz9wkm8TWhwYvpGpZal4A,7097
unstructured/documents/ontology.py,sha256=1YKYNy9Cq3UpnC376tca69uYXBWp4PRXwkB_MXLEsKk,25065
unstructured/embed/__init__.py,sha256=lqw55OZ3ibMbwPxdBcjPwbOPEDfjUguakuj7xN4bDdc,1046
unstructured/embed/__pycache__/__init__.cpython-313.pyc,,
unstructured/embed/__pycache__/bedrock.cpython-313.pyc,,
unstructured/embed/__pycache__/huggingface.cpython-313.pyc,,
unstructured/embed/__pycache__/interfaces.cpython-313.pyc,,
unstructured/embed/__pycache__/mixedbreadai.cpython-313.pyc,,
unstructured/embed/__pycache__/octoai.cpython-313.pyc,,
unstructured/embed/__pycache__/openai.cpython-313.pyc,,
unstructured/embed/__pycache__/vertexai.cpython-313.pyc,,
unstructured/embed/__pycache__/voyageai.cpython-313.pyc,,
unstructured/embed/bedrock.py,sha256=p8Pgm8PEYq_Z2c1f-D-LidtAyzxJ7uFzsWY52WcO-gM,2602
unstructured/embed/huggingface.py,sha256=GYTuTUwaZbfu6WFc5Nu3xLDXZxDdGXeZuPEfUIxe0C8,2465
unstructured/embed/interfaces.py,sha256=I5TDdbVC3x_yXXfBqSp1VOtVRBrLXwKbf4SgfTVhl2w,979
unstructured/embed/mixedbreadai.py,sha256=T2vibcjwIZExe64ko_zbY1t1izwuV6XvxkybLyHxbCU,5471
unstructured/embed/octoai.py,sha256=aFlgLhrTw-nrP_2gINO3AilJDDNiqCXObjtufjl0Yyw,2376
unstructured/embed/openai.py,sha256=cx_wBCENyBuQVJMG43xSTSXLSXm6_YH4YljeEWNSEI0,2284
unstructured/embed/vertexai.py,sha256=0PSdFuW_-5bR4UXrvzYBER7awTBqZtW8BVIBmaTXlW0,2821
unstructured/embed/voyageai.py,sha256=_SQtxjxlv1Hgy8uP4viZbJcIa7E2AYu0oK8v7699bFE,7686
unstructured/errors.py,sha256=SJ5q6qYbVXtHN622mZL9TC1EhrbQnEijxjEFy_xY1xg,597
unstructured/file_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/file_utils/__pycache__/__init__.cpython-313.pyc,,
unstructured/file_utils/__pycache__/encoding.cpython-313.pyc,,
unstructured/file_utils/__pycache__/file_conversion.cpython-313.pyc,,
unstructured/file_utils/__pycache__/filetype.cpython-313.pyc,,
unstructured/file_utils/__pycache__/google_filetype.cpython-313.pyc,,
unstructured/file_utils/__pycache__/model.cpython-313.pyc,,
unstructured/file_utils/__pycache__/ndjson.cpython-313.pyc,,
unstructured/file_utils/encoding.py,sha256=8kKud_BS21_gVB9nVMpx0PHN5f3CKRupR89lTtzpluY,5280
unstructured/file_utils/file_conversion.py,sha256=WcLLSxexstSkX7PNbbwjCbm9cIOkG1AJmDE8NAv44nk,3072
unstructured/file_utils/filetype.py,sha256=NGc7g3Q0NuvD3OJF2C1hPJdkoHfRnD-3lDQkzy3NXCE,30606
unstructured/file_utils/google_filetype.py,sha256=YVspEkiiBrRUSGVeVbsavvLvTmizdy2e6TsjigXTSRU,468
unstructured/file_utils/model.py,sha256=Oqx_9Zq81zbyMBCmalJ4fNzWvYIbdG6Q_miNjOQR6mU,17292
unstructured/file_utils/ndjson.py,sha256=LezsF5LzmSPgTAE4PgGm0_DcPlgMDvPxRn2HONJm_yw,1974
unstructured/logger.py,sha256=aD9qsYFQBbyPSiuTfosXphv1k5EGcRnX7dAGB6sgb-g,686
unstructured/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/metrics/__pycache__/__init__.cpython-313.pyc,,
unstructured/metrics/__pycache__/element_type.cpython-313.pyc,,
unstructured/metrics/__pycache__/evaluate.cpython-313.pyc,,
unstructured/metrics/__pycache__/object_detection.cpython-313.pyc,,
unstructured/metrics/__pycache__/table_structure.cpython-313.pyc,,
unstructured/metrics/__pycache__/text_extraction.cpython-313.pyc,,
unstructured/metrics/__pycache__/utils.cpython-313.pyc,,
unstructured/metrics/element_type.py,sha256=OQuuB5Z6Xej2acJFowhTKSEJN0glyx69OCkYKocy8yg,3666
unstructured/metrics/evaluate.py,sha256=GxMbTvgtyA-751kJy5bh3iHUKRo4Abc2u7rFZbO2slM,33710
unstructured/metrics/object_detection.py,sha256=t988hG16em75Rh0OXqo-3pLoEOPjmnVVt-3yYbOtUAE,31067
unstructured/metrics/table/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/metrics/table/__pycache__/__init__.cpython-313.pyc,,
unstructured/metrics/table/__pycache__/table_alignment.cpython-313.pyc,,
unstructured/metrics/table/__pycache__/table_eval.cpython-313.pyc,,
unstructured/metrics/table/__pycache__/table_extraction.cpython-313.pyc,,
unstructured/metrics/table/__pycache__/table_formats.cpython-313.pyc,,
unstructured/metrics/table/table_alignment.py,sha256=tyUG9XedxVppQydISoYfzlWlBsLHTB8yU38yko6nkts,7734
unstructured/metrics/table/table_eval.py,sha256=VUVzyaDn04OdJ_PhPJNNLDE8S6gkOFYboIZ8rxTYnrY,12479
unstructured/metrics/table/table_extraction.py,sha256=Qs9k8CLJJoAL5IMmiO-QLmpaL6QjoBFTNsj32mWb5Zo,9723
unstructured/metrics/table/table_formats.py,sha256=Jqrb-26zRtUVvwOyXw-CWLyV6vKrgFHVpZKD7TFzFjk,1383
unstructured/metrics/table_structure.py,sha256=uyWihfHyESx7aTr2A0YYqr7e5JkqEDVfrsSyI_pHcp8,1859
unstructured/metrics/text_extraction.py,sha256=QfHRfHPpyHkHt915GXCjLxy0PhlZrAjkoCgFVvz8utE,10068
unstructured/metrics/utils.py,sha256=TF_o-kZQ4NhZXn1JpC0l9a_ijE2SdzrpfTLn62UxW5A,8117
unstructured/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/models/__pycache__/__init__.cpython-313.pyc,,
unstructured/nlp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/nlp/__pycache__/__init__.cpython-313.pyc,,
unstructured/nlp/__pycache__/english_words.cpython-313.pyc,,
unstructured/nlp/__pycache__/partition.cpython-313.pyc,,
unstructured/nlp/__pycache__/patterns.cpython-313.pyc,,
unstructured/nlp/__pycache__/tokenize.cpython-313.pyc,,
unstructured/nlp/english-words.txt,sha256=8fpk2f3iMm87qMppZMFAt1eWJcqOMALtt1YHE-fm7bY,4472047
unstructured/nlp/english_words.py,sha256=Ng2ozKrwF0Pw-qblYtBxxFOW9hT0eVL5uLqEgf0BHsw,701
unstructured/nlp/partition.py,sha256=8bTfn7O4Plk6FJ3-TmuTnxgjdZDnvExSGQpRYrddNJE,210
unstructured/nlp/patterns.py,sha256=Qtfdxyk3ieApTc9bWSZeFButZcnDdHvRjysC5SBxYeE,5664
unstructured/nlp/tokenize.py,sha256=trL-de2-peFs2kt6JcQQYRoAozEyy2xDOlpART9FU2U,2805
unstructured/partition/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/partition/__pycache__/__init__.cpython-313.pyc,,
unstructured/partition/__pycache__/api.cpython-313.pyc,,
unstructured/partition/__pycache__/auto.cpython-313.pyc,,
unstructured/partition/__pycache__/csv.cpython-313.pyc,,
unstructured/partition/__pycache__/doc.cpython-313.pyc,,
unstructured/partition/__pycache__/docx.cpython-313.pyc,,
unstructured/partition/__pycache__/email.cpython-313.pyc,,
unstructured/partition/__pycache__/epub.cpython-313.pyc,,
unstructured/partition/__pycache__/image.cpython-313.pyc,,
unstructured/partition/__pycache__/json.cpython-313.pyc,,
unstructured/partition/__pycache__/md.cpython-313.pyc,,
unstructured/partition/__pycache__/model_init.cpython-313.pyc,,
unstructured/partition/__pycache__/msg.cpython-313.pyc,,
unstructured/partition/__pycache__/ndjson.cpython-313.pyc,,
unstructured/partition/__pycache__/odt.cpython-313.pyc,,
unstructured/partition/__pycache__/org.cpython-313.pyc,,
unstructured/partition/__pycache__/pdf.cpython-313.pyc,,
unstructured/partition/__pycache__/ppt.cpython-313.pyc,,
unstructured/partition/__pycache__/pptx.cpython-313.pyc,,
unstructured/partition/__pycache__/rst.cpython-313.pyc,,
unstructured/partition/__pycache__/rtf.cpython-313.pyc,,
unstructured/partition/__pycache__/strategies.cpython-313.pyc,,
unstructured/partition/__pycache__/text.cpython-313.pyc,,
unstructured/partition/__pycache__/text_type.cpython-313.pyc,,
unstructured/partition/__pycache__/tsv.cpython-313.pyc,,
unstructured/partition/__pycache__/xlsx.cpython-313.pyc,,
unstructured/partition/__pycache__/xml.cpython-313.pyc,,
unstructured/partition/api.py,sha256=wrXj2iUuVgWIBI94416gYbTdRHAxcAYMypjW_gpM9I8,13773
unstructured/partition/auto.py,sha256=D3Gyzw7tiumuCyNCcOq150jNfrKiQeocs1KMpbxfQpM,17564
unstructured/partition/common/__init__.py,sha256=s6_gBQedBRh0pGtrLb8qdlPdONTrq08GBWxFaGY4qpo,276
unstructured/partition/common/__pycache__/__init__.cpython-313.pyc,,
unstructured/partition/common/__pycache__/common.cpython-313.pyc,,
unstructured/partition/common/__pycache__/lang.cpython-313.pyc,,
unstructured/partition/common/__pycache__/metadata.cpython-313.pyc,,
unstructured/partition/common/common.py,sha256=h-qczp5tIG_yBgDHsvpgaKgM-URfV-f2zhTtoPFzmtU,15710
unstructured/partition/common/lang.py,sha256=KxSUvyPH6qCmt_oRDyBtBGKTFQnYyVVZYzUh26_-mcU,17276
unstructured/partition/common/metadata.py,sha256=uz_EIhBCXbOVtb3WsfIMbl4_20tD3Oumv1CfhWviAIw,11424
unstructured/partition/csv.py,sha256=FTTz20Dh-87u4dzfaycpS2kTzmKGr2gEJjASmZMmQlo,6259
unstructured/partition/doc.py,sha256=ltrI9GISr4JNxktgVRpfMpyH55r1XK801P2g52EgRBA,4584
unstructured/partition/docx.py,sha256=JEgfV-bAuIpq1F4XwcGrt8GrtUfcV2zzMgMHrSmQ3o8,45431
unstructured/partition/email.py,sha256=ol212it9RziyT-H3gbiZHwsmJCvQSi80q3dCVuGE7KU,16991
unstructured/partition/epub.py,sha256=45bz_h5OfuOHgwM87eLG440tP3KhCOrPLXVtxbYdfjQ,2231
unstructured/partition/html/__init__.py,sha256=uFCKUengmT1m-Q_GkkZogEhv3MF7_rA9ahM0EF0S5dY,95
unstructured/partition/html/__pycache__/__init__.cpython-313.pyc,,
unstructured/partition/html/__pycache__/convert.cpython-313.pyc,,
unstructured/partition/html/__pycache__/html_utils.cpython-313.pyc,,
unstructured/partition/html/__pycache__/parser.cpython-313.pyc,,
unstructured/partition/html/__pycache__/partition.cpython-313.pyc,,
unstructured/partition/html/__pycache__/transformations.cpython-313.pyc,,
unstructured/partition/html/convert.py,sha256=7zOnwN--NWtRecDiU1sQiXc0TOWZEHBMudvo5arP6AQ,11148
unstructured/partition/html/html_utils.py,sha256=AZm8KaPu5DCzuXZFqy3IVeTIk0lZ0-LJL8fSaT0DFRU,1064
unstructured/partition/html/parser.py,sha256=gh4nIbbaB34rgigzashoh37CFNBjqu38wBF_CE7kfbM,41326
unstructured/partition/html/partition.py,sha256=ijJxeN_nmcNeYwr0wqYEZrQVu9qQHshVqBtTEEIdF1I,10880
unstructured/partition/html/transformations.py,sha256=ZFuJ410r1hiZx3MmWmavvDNa1Rg4wM_8N5c8nHSpeI0,17559
unstructured/partition/image.py,sha256=YAbHdw8-d0tH0I7T1JkdVD_EBL7b0wkwYfbxTmPCdl0,5831
unstructured/partition/json.py,sha256=IehL7ciIdlMrV6VsBSBXYTuBBtTrq5Gp1ChS1W9ISKc,3101
unstructured/partition/md.py,sha256=NqGUQLkHiR36EkZU7r0D9UZRMlxqLEcCXr-2DM7aYng,2583
unstructured/partition/model_init.py,sha256=HdbUAn2jyMuJQG_s_vJT7polwh3epUx-H6SILETEhhA,586
unstructured/partition/msg.py,sha256=eWk5R5nEqywH3E4jrL-6o_w6n43nMIetoaUc8XKlZ7w,12144
unstructured/partition/ndjson.py,sha256=r4YLOQL37VNEvMAJhKK_sd9GdE-slAUrMPNsJF79tvU,3184
unstructured/partition/odt.py,sha256=PXZNY60Mu75Tqti393tivvP-n7R8mqNhINZMCpI0p_0,4560
unstructured/partition/org.py,sha256=8qQuG7QhWr49cgkTLlx23aKOQenyCO0KyiZqkmNPU9k,1615
unstructured/partition/pdf.py,sha256=66ahL74nxWqQs4_XmWg9oDMylt1js37Iv9_OpcsN0zc,49752
unstructured/partition/pdf_image/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/partition/pdf_image/__pycache__/__init__.cpython-313.pyc,,
unstructured/partition/pdf_image/__pycache__/form_extraction.cpython-313.pyc,,
unstructured/partition/pdf_image/__pycache__/inference_utils.cpython-313.pyc,,
unstructured/partition/pdf_image/__pycache__/ocr.cpython-313.pyc,,
unstructured/partition/pdf_image/__pycache__/pdf_image_utils.cpython-313.pyc,,
unstructured/partition/pdf_image/__pycache__/pdfminer_processing.cpython-313.pyc,,
unstructured/partition/pdf_image/__pycache__/pdfminer_utils.cpython-313.pyc,,
unstructured/partition/pdf_image/__pycache__/pypdf_utils.cpython-313.pyc,,
unstructured/partition/pdf_image/analysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/partition/pdf_image/analysis/__pycache__/__init__.cpython-313.pyc,,
unstructured/partition/pdf_image/analysis/__pycache__/bbox_visualisation.cpython-313.pyc,,
unstructured/partition/pdf_image/analysis/__pycache__/layout_dump.cpython-313.pyc,,
unstructured/partition/pdf_image/analysis/__pycache__/processor.cpython-313.pyc,,
unstructured/partition/pdf_image/analysis/__pycache__/tools.cpython-313.pyc,,
unstructured/partition/pdf_image/analysis/bbox_visualisation.py,sha256=kgjAY7bBdVgTmYoOFV_9tpYdc4pV8otWnxtVEQ4b6Nc,24714
unstructured/partition/pdf_image/analysis/layout_dump.py,sha256=tA0y6e8RpLTQnE3z0FXsFdbTs9jpDDTdF_dFWO-yktA,6775
unstructured/partition/pdf_image/analysis/processor.py,sha256=sipHTC66UaB8NlVihEcnSm-b2cqmFedyEsM2rt6QjY4,433
unstructured/partition/pdf_image/analysis/tools.py,sha256=2Ue4pDdsiz7CXi1A-AQzxkpPQImqJE8Ag0YBR4WWmO4,7236
unstructured/partition/pdf_image/form_extraction.py,sha256=8yDrbMZEZbt6AaKuZvLl3YiRzp2rgiu3QN2a55CJlIo,369
unstructured/partition/pdf_image/inference_utils.py,sha256=wFAPfNL4OvhU35zZ6A94wPIej13SjcnbhfX4slbaAAU,3316
unstructured/partition/pdf_image/ocr.py,sha256=CwW-VlplcRxaSkjygLj8Lg5rBFDb6-GVBujBo2W5IG4,20128
unstructured/partition/pdf_image/pdf_image_utils.py,sha256=gFwcxdIdZWqLqPIFSO2JP_2Md93NXEHuP7XrUfLL9bQ,16068
unstructured/partition/pdf_image/pdfminer_processing.py,sha256=NMG5ldwEWI02azqzFt0ZtXTi8hxIKV_7s5ROFhSjtF8,47067
unstructured/partition/pdf_image/pdfminer_utils.py,sha256=PNWEA3cEZqEEFm9L3nOGumYobuQUuW0XLHWQHRiODjQ,5002
unstructured/partition/pdf_image/pypdf_utils.py,sha256=tE14XrOLRRNbhFwfdUXD9kLrD9BbSX3ipr7ggiB3AeU,409
unstructured/partition/ppt.py,sha256=YFj60k9OukrUlezMFzRHzmF7q9XYPRb8z2HcLAwqg-0,2659
unstructured/partition/pptx.py,sha256=pJZGMjaZf2TriA7V7yYytt4s9r8iFDfTslCA_EKlcQw,21616
unstructured/partition/rst.py,sha256=F96LxPOLvEAuKng5RN3xjBVozdv7vM_XROjheksuN6c,1637
unstructured/partition/rtf.py,sha256=NdrMLnFkEwmG1eSrsEv1XAfr1AhoNr6g1gobMoqqDAo,1637
unstructured/partition/strategies.py,sha256=rvSaAxzJqFxnmAkQPwMQI42d4vv0Iz7tqoDD2wz9y5s,4303
unstructured/partition/text.py,sha256=m1-BsxShkuy3W9BSz8v4_xzfASWUbovCMD_R5MSGqso,6867
unstructured/partition/text_type.py,sha256=pCP5kXyHQKAMBPpKrW6HlLqd2NbhBxN3xCh409OyCsU,11858
unstructured/partition/tsv.py,sha256=Ye6OYCW-IrvlEwiEtlf-q_Yf_1H7_jOlhxT4DHg6uwk,2050
unstructured/partition/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/partition/utils/__pycache__/__init__.cpython-313.pyc,,
unstructured/partition/utils/__pycache__/config.cpython-313.pyc,,
unstructured/partition/utils/__pycache__/constants.cpython-313.pyc,,
unstructured/partition/utils/__pycache__/sorting.cpython-313.pyc,,
unstructured/partition/utils/__pycache__/xycut.cpython-313.pyc,,
unstructured/partition/utils/config.py,sha256=zS8aEFgCvMUvCwtR87ir3N390lhraTLYUWwEnE6P6PQ,9637
unstructured/partition/utils/constants.py,sha256=L-B0ZSMLyBtaj-AI5clyr8yOybtT2fHV2EQifnp_0e8,5666
unstructured/partition/utils/ocr_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/partition/utils/ocr_models/__pycache__/__init__.cpython-313.pyc,,
unstructured/partition/utils/ocr_models/__pycache__/google_vision_ocr.cpython-313.pyc,,
unstructured/partition/utils/ocr_models/__pycache__/ocr_interface.cpython-313.pyc,,
unstructured/partition/utils/ocr_models/__pycache__/paddle_ocr.cpython-313.pyc,,
unstructured/partition/utils/ocr_models/__pycache__/tesseract_ocr.cpython-313.pyc,,
unstructured/partition/utils/ocr_models/google_vision_ocr.py,sha256=Cm149mCppQjhZEMZcS26ySJxbPOk--MiMOF3ZhIF8Uk,4840
unstructured/partition/utils/ocr_models/ocr_interface.py,sha256=uu5srL2QYmQq4uMSLtn1kcmQQ6yxakgPn1x5HJjMA0c,3493
unstructured/partition/utils/ocr_models/paddle_ocr.py,sha256=_pRDod1RpRwGuqn8r-DpbTVDMoTePkSKcIvH-DJfLoU,5769
unstructured/partition/utils/ocr_models/tesseract_ocr.py,sha256=7rgXtRuSNd-wPODIkiy74PmJSdRofi9zMvIySPNr40I,9958
unstructured/partition/utils/sorting.py,sha256=sNWply9T2zYE3S4CplIiHTLltB96n9z3vxNZencjbbs,8607
unstructured/partition/utils/xycut.py,sha256=K_4PaKNc7Vs3iL-PQ9FaP-r3gU2WahulOpaRYpP3rq0,10202
unstructured/partition/xlsx.py,sha256=1E0A0Ukf6j6LnsQQXOLg2RRUIcV2ng5sJxrNaI_5Kqg,17792
unstructured/partition/xml.py,sha256=32BIGMfU3cFtFkEv8s-2MCsKSGC8JvBUUg2RrbBBDmI,4416
unstructured/patches/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/patches/__pycache__/__init__.cpython-313.pyc,,
unstructured/patches/__pycache__/pdfminer.cpython-313.pyc,,
unstructured/patches/pdfminer.py,sha256=5JhA0ogzH4PplbEulN25XqwClsKldDCtfOcUplNvObk,2145
unstructured/py.typed,sha256=z3PGyU9Bs9Gq1-s8CjEJ8Y4Aev2MwVgsaVDwglLkTZw,118
unstructured/staging/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
unstructured/staging/__pycache__/__init__.cpython-313.pyc,,
unstructured/staging/__pycache__/argilla.cpython-313.pyc,,
unstructured/staging/__pycache__/base.cpython-313.pyc,,
unstructured/staging/__pycache__/baseplate.cpython-313.pyc,,
unstructured/staging/__pycache__/datasaur.cpython-313.pyc,,
unstructured/staging/__pycache__/huggingface.cpython-313.pyc,,
unstructured/staging/__pycache__/label_box.cpython-313.pyc,,
unstructured/staging/__pycache__/label_studio.cpython-313.pyc,,
unstructured/staging/__pycache__/prodigy.cpython-313.pyc,,
unstructured/staging/__pycache__/weaviate.cpython-313.pyc,,
unstructured/staging/argilla.py,sha256=DcG9QNYLTP8nN124OUcBB1lisFxQ-ruD4e_zJXEY97M,2292
unstructured/staging/base.py,sha256=yxlkG02GSDHp587zjgrPdERr-nlIaK7X9H_W5D8uV_4,21702
unstructured/staging/baseplate.py,sha256=sTQ7umr6PlzjxrRwB2XDlFJGVUY1rv4VZ4z1UQ7q59g,1755
unstructured/staging/datasaur.py,sha256=7kG_XjY5YA0w1aPxR-PUSAllXNXKZdMop02Uu41wHc4,1417
unstructured/staging/huggingface.py,sha256=Nsej3wBydQDVvGNGPmsRZbeYOaMea8kRF949EY-kNxA,3838
unstructured/staging/label_box.py,sha256=uOaPT-3FtP_TkOSIjM2pUCZBxK8YgiDEwPblc1I8sSA,3855
unstructured/staging/label_studio.py,sha256=Ri7JfASfKfIgwdGaEF_tsBAVywfrr6_ReFZBjCnBLNA,5355
unstructured/staging/prodigy.py,sha256=wPMwatJ2lWr2_0qvlkv3MV55mkovHPz-ItUY0WcKxqw,3130
unstructured/staging/weaviate.py,sha256=hsl9OQ8Nwsx5GNrPI_-PQpNUX7lDCKBD0xImTMzKuHs,2607
unstructured/utils.py,sha256=UK2n1VHayr2ctlTiic0iEhXvrbveb2LHszapGXwot30,27965

0
backend_service/venv/lib/python3.13/site-packages/unstructured-0.18.27.dist-info/REQUESTED Normal file
View File

5
backend_service/venv/lib/python3.13/site-packages/unstructured-0.18.27.dist-info/WHEEL Normal file
View File

@@ -0,0 +1,5 @@
Wheel-Version: 1.0
Generator: setuptools (79.0.1)
Root-Is-Purelib: true
Tag: py3-none-any

201
backend_service/venv/lib/python3.13/site-packages/unstructured-0.18.27.dist-info/licenses/LICENSE.md Normal file
View File

@@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2022 Unstructured Technologies, Inc
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

2
backend_service/venv/lib/python3.13/site-packages/unstructured-0.18.27.dist-info/top_level.txt Normal file
View File

@@ -0,0 +1,2 @@
test_unstructured
unstructured