Compare commits
No commits in common. "master" and "v0.5.0" have entirely different histories.
|
|
@ -1,2 +1,2 @@
|
|||
[run]
|
||||
branch = True
|
||||
branch = True
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
root = true
|
||||
|
||||
[*]
|
||||
end_of_line = lf
|
||||
insert_final_newline = true
|
||||
|
||||
[*.py]
|
||||
charset = utf-8
|
||||
indent_style = space
|
||||
indent_size = 4
|
||||
|
|
@ -1 +0,0 @@
|
|||
open_collective: camelot
|
||||
|
|
@ -1,57 +0,0 @@
|
|||
---
|
||||
name: Bug report
|
||||
about: Please follow this template to submit bug reports.
|
||||
title: ''
|
||||
labels: bug
|
||||
assignees: ''
|
||||
|
||||
---
|
||||
|
||||
<!-- Please read the filing issues section of the contributor's guide first: https://camelot-py.readthedocs.io/en/master/dev/contributing.html -->
|
||||
|
||||
**Describe the bug**
|
||||
|
||||
<!-- A clear and concise description of what the bug is. -->
|
||||
|
||||
**Steps to reproduce the bug**
|
||||
|
||||
<!-- Steps used to install `camelot`:
|
||||
1. Add step here (you can add more steps too) -->
|
||||
|
||||
<!-- Steps to be used to reproduce behavior:
|
||||
1. Add step here (you can add more steps too) -->
|
||||
|
||||
**Expected behavior**
|
||||
|
||||
<!-- A clear and concise description of what you expected to happen. -->
|
||||
|
||||
**Code**
|
||||
|
||||
<!-- Add the Camelot code snippet that you used. -->
|
||||
|
||||
```
|
||||
import camelot
|
||||
|
||||
# add your code here
|
||||
```
|
||||
|
||||
**PDF**
|
||||
|
||||
<!-- Add the PDF file that you want to extract tables from. -->
|
||||
|
||||
**Screenshots**
|
||||
|
||||
<!-- If applicable, add screenshots to help explain your problem. -->
|
||||
|
||||
**Environment**
|
||||
|
||||
- OS: [e.g. macOS]
|
||||
- Python version:
|
||||
- Numpy version:
|
||||
- OpenCV version:
|
||||
- Ghostscript version:
|
||||
- Camelot version:
|
||||
|
||||
**Additional context**
|
||||
|
||||
<!-- Add any other context about the problem here. -->
|
||||
|
|
@ -1,44 +0,0 @@
|
|||
name: tests
|
||||
|
||||
on: [pull_request]
|
||||
|
||||
jobs:
|
||||
test:
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: [3.6, 3.7, 3.8]
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v2
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
- name: Install camelot with dependencies
|
||||
run: |
|
||||
make install
|
||||
- name: Test with pytest
|
||||
run: |
|
||||
make test
|
||||
|
||||
test_latest:
|
||||
name: Test on ${{ matrix.os }} with Python 3.9
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
matrix:
|
||||
os: [ubuntu-latest, macos-latest, windows-latest]
|
||||
python-version: [3.9]
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v2
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
- name: Install camelot with dependencies
|
||||
run: |
|
||||
make install
|
||||
- name: Test with pytest
|
||||
run: |
|
||||
make test
|
||||
|
|
@ -1,4 +1,3 @@
|
|||
fontconfig/
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*.so
|
||||
|
|
@ -13,8 +12,5 @@ coverage.xml
|
|||
.pytest_cache/
|
||||
_build/
|
||||
|
||||
.venv/
|
||||
htmlcov/
|
||||
|
||||
# vscode
|
||||
.vscode
|
||||
.vscode
|
||||
|
|
@ -1,27 +0,0 @@
|
|||
# .readthedocs.yml
|
||||
# Read the Docs configuration file
|
||||
# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
|
||||
|
||||
# Required
|
||||
version: 2
|
||||
|
||||
# Build documentation in the docs/ directory with Sphinx
|
||||
sphinx:
|
||||
configuration: docs/conf.py
|
||||
|
||||
# Build documentation with MkDocs
|
||||
#mkdocs:
|
||||
# configuration: mkdocs.yml
|
||||
|
||||
# Optionally build your docs in additional formats such as PDF
|
||||
formats:
|
||||
- pdf
|
||||
|
||||
# Optionally set the version of Python and requirements required to build your docs
|
||||
python:
|
||||
version: 3.8
|
||||
install:
|
||||
- method: pip
|
||||
path: .
|
||||
extra_requirements:
|
||||
- dev
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
sudo: true
|
||||
language: python
|
||||
cache: pip
|
||||
addons:
|
||||
apt:
|
||||
update: true
|
||||
install:
|
||||
- make install
|
||||
jobs:
|
||||
include:
|
||||
- stage: test
|
||||
script:
|
||||
- make test
|
||||
python: '2.7'
|
||||
- stage: test
|
||||
script:
|
||||
- make test
|
||||
python: '3.5'
|
||||
- stage: test
|
||||
script:
|
||||
- make test
|
||||
python: '3.6'
|
||||
- stage: test
|
||||
script:
|
||||
- make test
|
||||
python: '3.7'
|
||||
dist: xenial
|
||||
- stage: coverage
|
||||
python: '3.6'
|
||||
script:
|
||||
- make test
|
||||
- codecov --verbose
|
||||
|
|
@ -16,14 +16,14 @@ As the [Requests Code Of Conduct](http://docs.python-requests.org/en/master/dev/
|
|||
|
||||
## Your first contribution
|
||||
|
||||
A great way to start contributing to Camelot is to pick an issue tagged with the [help wanted](https://github.com/camelot-dev/camelot/labels/help%20wanted) tag or the [good first issue](https://github.com/camelot-dev/camelot/labels/good%20first%20issue) tag. If you're unable to find a good first issue, feel free to contact the maintainer.
|
||||
A great way to start contributing to Camelot is to pick an issue tagged with the [help wanted](https://github.com/socialcopsdev/camelot/labels/help%20wanted) tag or the [good first issue](https://github.com/socialcopsdev/camelot/labels/good%20first%20issue) tag. If you're unable to find a good first issue, feel free to contact the maintainer.
|
||||
|
||||
## Setting up a development environment
|
||||
|
||||
To install the dependencies needed for development, you can use pip:
|
||||
|
||||
<pre>
|
||||
$ pip install "camelot-py[dev]"
|
||||
$ pip install camelot-py[dev]
|
||||
</pre>
|
||||
|
||||
Alternatively, you can clone the project repository, and install using pip:
|
||||
|
|
@ -36,7 +36,7 @@ $ pip install ".[dev]"
|
|||
|
||||
### Submit a pull request
|
||||
|
||||
The preferred workflow for contributing to Camelot is to fork the [project repository](https://github.com/camelot-dev/camelot) on GitHub, clone, develop on a branch and then finally submit a pull request. Here are the steps:
|
||||
The preferred workflow for contributing to Camelot is to fork the [project repository](https://github.com/socialcopsdev/camelot) on GitHub, clone, develop on a branch and then finally submit a pull request. Here are the steps:
|
||||
|
||||
1. Fork the project repository. Click on the ‘Fork’ button near the top of the page. This creates a copy of the code under your account on the GitHub.
|
||||
|
||||
|
|
@ -106,7 +106,7 @@ The function docstrings are written using the [numpydoc](https://numpydoc.readth
|
|||
|
||||
## Filing Issues
|
||||
|
||||
We use [GitHub issues](https://github.com/camelot-dev/camelot/issues) to keep track of all issues and pull requests. Before opening an issue (which asks a question or reports a bug), please use GitHub search to look for existing issues (both open and closed) that may be similar.
|
||||
We use [GitHub issues](https://github.com/socialcopsdev/camelot/issues) to keep track of all issues and pull requests. Before opening an issue (which asks a question or reports a bug), please use GitHub search to look for existing issues (both open and closed) that may be similar.
|
||||
|
||||
### Questions
|
||||
|
||||
|
|
|
|||
135
HISTORY.md
135
HISTORY.md
|
|
@ -4,141 +4,6 @@ Release History
|
|||
master
|
||||
------
|
||||
|
||||
0.10.1 (2021-07-11)
|
||||
------------------
|
||||
|
||||
- Change extra requirements from `cv` to `base`. You can use `pip install "camelot-py[base]"` to install everything required to run camelot.
|
||||
|
||||
0.10.0 (2021-07-11)
|
||||
------------------
|
||||
|
||||
**Improvements**
|
||||
|
||||
- Add support for multiple image conversion backends. [#198](https://github.com/camelot-dev/camelot/pull/198) and [#253](https://github.com/camelot-dev/camelot/pull/253) by Vinayak Mehta.
|
||||
- Add markdown export format. [#222](https://github.com/camelot-dev/camelot/pull/222/) by [Lucas Cimon](https://github.com/Lucas-C).
|
||||
|
||||
**Documentation**
|
||||
|
||||
- Add faq section. [#216](https://github.com/camelot-dev/camelot/pull/216) by [Stefano Fiorucci](https://github.com/anakin87).
|
||||
|
||||
0.9.0 (2021-06-15)
|
||||
------------------
|
||||
|
||||
**Bugfixes**
|
||||
|
||||
- Fix use of resolution argument to generate image with ghostscript. [#231](https://github.com/camelot-dev/camelot/pull/231) by [Tiago Samaha Cordeiro](https://github.com/tiagosamaha).
|
||||
- [#15](https://github.com/camelot-dev/camelot/issues/15) Fix duplicate strings being assigned to the same cell. [#206](https://github.com/camelot-dev/camelot/pull/206) by [Eduardo Gonzalez Lopez de Murillas](https://github.com/edugonza).
|
||||
- Save plot when filename is specified. [#121](https://github.com/camelot-dev/camelot/pull/121) by [Jens Diemer](https://github.com/jedie).
|
||||
- Close file streams explicitly. [#202](https://github.com/camelot-dev/camelot/pull/202) by [Martin Abente Lahaye](https://github.com/tchx84).
|
||||
- Use correct re.sub signature. [#186](https://github.com/camelot-dev/camelot/pull/186) by [pevisscher](https://github.com/pevisscher).
|
||||
- [#183](https://github.com/camelot-dev/camelot/issues/183) Fix UnicodeEncodeError when using Stream flavor by adding encoding kwarg to `to_html`. [#188](https://github.com/camelot-dev/camelot/pull/188) by [Stefano Fiorucci](https://github.com/anakin87).
|
||||
- [#179](https://github.com/camelot-dev/camelot/issues/179) Fix `max() arg is an empty sequence` error on PDFs with blank pages. [#189](https://github.com/camelot-dev/camelot/pull/189) by Vinayak Mehta.
|
||||
|
||||
**Improvements**
|
||||
|
||||
- Add `line_overlap` and `boxes_flow` to `LAParams`. [#219](https://github.com/camelot-dev/camelot/pull/219) by [Arnie97](https://github.com/Arnie97).
|
||||
- [Add bug report template.](https://github.com/camelot-dev/camelot/commit/0a3944e54d133b701edfe9c7546ff11289301ba8)
|
||||
- Move from [Travis to GitHub Actions](https://github.com/camelot-dev/camelot/pull/241).
|
||||
- Update `.readthedocs.yml` and [remove requirements.txt](https://github.com/camelot-dev/camelot/commit/7ab5db39d07baa4063f975e9e00f6073340e04c1#diff-cde814ef2f549dc093f5b8fc533b7e8f47e7b32a8081e0760e57d5c25a1139d9)
|
||||
|
||||
**Documentation**
|
||||
|
||||
- [#193](https://github.com/camelot-dev/camelot/issues/193) Add better checks to confirm proper installation of ghostscript. [#196](https://github.com/camelot-dev/camelot/pull/196) by [jimhall](https://github.com/jimhall).
|
||||
- Update `advanced.rst` plotting examples. [#119](https://github.com/camelot-dev/camelot/pull/119) by [Jens Diemer](https://github.com/jedie).
|
||||
|
||||
0.8.2 (2020-07-27)
|
||||
------------------
|
||||
|
||||
* Revert the changes in `0.8.1`.
|
||||
|
||||
0.8.1 (2020-07-21)
|
||||
------------------
|
||||
|
||||
**Bugfixes**
|
||||
|
||||
* [#169](https://github.com/camelot-dev/camelot/issues/169) Fix import error caused by `pdfminer.six==20200720`. [#171](https://github.com/camelot-dev/camelot/pull/171) by Vinayak Mehta.
|
||||
|
||||
0.8.0 (2020-05-24)
|
||||
------------------
|
||||
|
||||
**Improvements**
|
||||
|
||||
* Drop Python 2 support!
|
||||
* Remove Python 2.7 and 3.5 support.
|
||||
* Replace all instances of `.format` with f-strings.
|
||||
* Remove all `__future__` imports.
|
||||
* Fix HTTP 403 forbidden exception in read_pdf(url) and remove Python 2 urllib support.
|
||||
* Fix test data.
|
||||
|
||||
**Bugfixes**
|
||||
|
||||
* Fix library discovery on Windows. [#32](https://github.com/camelot-dev/camelot/pull/32) by [KOLANICH](https://github.com/KOLANICH).
|
||||
* Fix calling convention of callback functions. [#34](https://github.com/camelot-dev/camelot/pull/34) by [KOLANICH](https://github.com/KOLANICH).
|
||||
|
||||
0.7.3 (2019-07-07)
|
||||
------------------
|
||||
|
||||
**Improvements**
|
||||
|
||||
* Camelot now follows the Black code style! [#1](https://github.com/camelot-dev/camelot/pull/1) and [#3](https://github.com/camelot-dev/camelot/pull/3).
|
||||
|
||||
**Bugfixes**
|
||||
|
||||
* Fix Click.HelpFormatter monkey-patch. [#5](https://github.com/camelot-dev/camelot/pull/5) by [Dimiter Naydenov](https://github.com/dimitern).
|
||||
* Fix strip_text argument getting ignored. [#4](https://github.com/camelot-dev/camelot/pull/4) by [Dimiter Naydenov](https://github.com/dimitern).
|
||||
* [#25](https://github.com/camelot-dev/camelot/issues/25) edge_tol skipped in read_pdf. [#26](https://github.com/camelot-dev/camelot/pull/26) by Vinayak Mehta.
|
||||
* Fix pytest deprecation warning. [#2](https://github.com/camelot-dev/camelot/pull/2) by Vinayak Mehta.
|
||||
* [#293](https://github.com/socialcopsdev/camelot/issues/293) Split text ignores all text to the right of last cut. [#294](https://github.com/socialcopsdev/camelot/pull/294) by Vinayak Mehta.
|
||||
* [#277](https://github.com/socialcopsdev/camelot/issues/277) Sort TableList by order of tables in PDF. [#283](https://github.com/socialcopsdev/camelot/pull/283) by [Sym Roe](https://github.com/symroe).
|
||||
* [#312](https://github.com/socialcopsdev/camelot/issues/312) `table_regions` throws `ValueError` when `flavor='stream'`. [#332](https://github.com/socialcopsdev/camelot/pull/332) by Vinayak Mehta.
|
||||
|
||||
0.7.2 (2019-01-10)
|
||||
------------------
|
||||
|
||||
**Bugfixes**
|
||||
|
||||
* [#245](https://github.com/socialcopsdev/camelot/issues/245) Fix AttributeError for encrypted files. [#251](https://github.com/socialcopsdev/camelot/pull/251) by Yatin Taluja.
|
||||
|
||||
|
||||
0.7.1 (2019-01-06)
|
||||
------------------
|
||||
|
||||
**Bugfixes**
|
||||
|
||||
* Move ghostscript import to inside the function so Anaconda builds don't fail.
|
||||
|
||||
0.7.0 (2019-01-05)
|
||||
------------------
|
||||
|
||||
**Improvements**
|
||||
|
||||
* [#240](https://github.com/socialcopsdev/camelot/issues/209) Add support to analyze only certain page regions to look for tables. [#243](https://github.com/socialcopsdev/camelot/pull/243) by Vinayak Mehta.
|
||||
* You can use `table_regions` in `read_pdf()` to specify approximate page regions which may contain tables.
|
||||
* Kwarg `line_size_scaling` is now called `line_scale`.
|
||||
* [#212](https://github.com/socialcopsdev/camelot/issues/212) Add support to export as sqlite database. [#244](https://github.com/socialcopsdev/camelot/pull/244) by Vinayak Mehta.
|
||||
* [#239](https://github.com/socialcopsdev/camelot/issues/239) Raise warning if PDF is image-based. [#240](https://github.com/socialcopsdev/camelot/pull/240) by Vinayak Mehta.
|
||||
|
||||
**Documentation**
|
||||
|
||||
* Remove mention of old mesh kwarg from docs. [#241](https://github.com/socialcopsdev/camelot/pull/241) by [fte10kso](https://github.com/fte10kso).
|
||||
|
||||
**Note**: The python wrapper to Ghostscript's C API is now vendorized under the `ext` module. This was done due to unavailability of the [ghostscript](https://pypi.org/project/ghostscript/) package on Anaconda. The code should be removed after we submit a recipe for it to conda-forge. With this release, the user doesn't need to ensure that the Ghostscript executable is available on the PATH variable.
|
||||
|
||||
0.6.0 (2018-12-24)
|
||||
------------------
|
||||
|
||||
**Improvements**
|
||||
|
||||
* [#91](https://github.com/socialcopsdev/camelot/issues/91) Add support to read from url. [#236](https://github.com/socialcopsdev/camelot/pull/236) by Vinayak Mehta.
|
||||
* [#229](https://github.com/socialcopsdev/camelot/issues/229), [#230](https://github.com/socialcopsdev/camelot/issues/230) and [#233](https://github.com/socialcopsdev/camelot/issues/233) New configuration parameters. [#234](https://github.com/socialcopsdev/camelot/pull/234) by Vinayak Mehta.
|
||||
* `strip_text`: To define characters that should be stripped from each string.
|
||||
* `edge_tol`: Tolerance parameter for extending textedges vertically.
|
||||
* `resolution`: Resolution used for PDF to PNG conversion.
|
||||
* Check out the [advanced docs](https://camelot-py.readthedocs.io/en/master/user/advanced.html#strip-characters-from-text) for usage details.
|
||||
* [#170](https://github.com/socialcopsdev/camelot/issues/170) Add option to pass pdfminer layout kwargs. [#232](https://github.com/socialcopsdev/camelot/pull/232) by Vinayak Mehta.
|
||||
* Keyword arguments for [pdfminer.layout.LAParams](https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33) can now be passed using `layout_kwargs` in `read_pdf()`.
|
||||
* The `margins` keyword argument in `read_pdf()` is now deprecated.
|
||||
|
||||
0.5.0 (2018-12-13)
|
||||
------------------
|
||||
|
||||
|
|
|
|||
3
LICENSE
3
LICENSE
|
|
@ -1,7 +1,6 @@
|
|||
MIT License
|
||||
|
||||
Copyright (c) 2019-2021 Camelot Developers
|
||||
Copyright (c) 2018-2019 Peeply Private Ltd (Singapore)
|
||||
Copyright (c) 2018 Peeply Private Ltd (Singapore)
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
|
|
|
|||
78
README.md
78
README.md
|
|
@ -1,28 +1,27 @@
|
|||
<p align="center">
|
||||
<img src="https://raw.githubusercontent.com/camelot-dev/camelot/master/docs/_static/camelot.png" width="200">
|
||||
<img src="https://raw.githubusercontent.com/socialcopsdev/camelot/master/docs/_static/camelot.png" width="200">
|
||||
</p>
|
||||
|
||||
# Camelot: PDF Table Extraction for Humans
|
||||
|
||||
[](https://github.com/camelot-dev/camelot/actions/workflows/tests.yml) [](https://camelot-py.readthedocs.io/en/master/)
|
||||
[](https://codecov.io/github/camelot-dev/camelot?branch=master)
|
||||
[](https://travis-ci.org/socialcopsdev/camelot) [](https://camelot-py.readthedocs.io/en/master/)
|
||||
[](https://codecov.io/github/socialcopsdev/camelot?branch=master)
|
||||
[](https://pypi.org/project/camelot-py/) [](https://pypi.org/project/camelot-py/) [](https://pypi.org/project/camelot-py/) [](https://gitter.im/camelot-dev/Lobby)
|
||||
[](https://github.com/ambv/black)
|
||||
|
||||
**Camelot** is a Python library that can help you extract tables from PDFs!
|
||||
**Camelot** is a Python library that makes it easy for *anyone* to extract tables from PDF files!
|
||||
|
||||
**Note:** You can also check out [Excalibur](https://github.com/camelot-dev/excalibur), the web interface to Camelot!
|
||||
**Note:** You can also check out [Excalibur](https://github.com/camelot-dev/excalibur), which is a web interface for Camelot!
|
||||
|
||||
---
|
||||
|
||||
**Here's how you can extract tables from PDFs.** You can check out the PDF used in this example [here](https://github.com/camelot-dev/camelot/blob/master/docs/_static/pdf/foo.pdf).
|
||||
**Here's how you can extract tables from PDF files.** Check out the PDF used in this example [here](https://github.com/socialcopsdev/camelot/blob/master/docs/_static/pdf/foo.pdf).
|
||||
|
||||
<pre>
|
||||
>>> import camelot
|
||||
>>> tables = camelot.read_pdf('foo.pdf')
|
||||
>>> tables
|
||||
<TableList n=1>
|
||||
>>> tables.export('foo.csv', f='csv', compress=True) # json, excel, html, markdown, sqlite
|
||||
>>> tables.export('foo.csv', f='csv', compress=True) # json, excel, html
|
||||
>>> tables[0]
|
||||
<Table shape=(7, 7)>
|
||||
>>> tables[0].parsing_report
|
||||
|
|
@ -32,7 +31,7 @@
|
|||
'order': 1,
|
||||
'page': 1
|
||||
}
|
||||
>>> tables[0].to_csv('foo.csv') # to_json, to_excel, to_html, to_markdown, to_sqlite
|
||||
>>> tables[0].to_csv('foo.csv') # to_json, to_excel, to_html
|
||||
>>> tables[0].df # get a pandas DataFrame!
|
||||
</pre>
|
||||
|
||||
|
|
@ -45,29 +44,24 @@
|
|||
| 2032_2 | 0.17 | 57.8 | 21.7% | 0.3% | 2.7% | 1.2% |
|
||||
| 4171_1 | 0.07 | 173.9 | 58.1% | 1.6% | 2.1% | 0.5% |
|
||||
|
||||
Camelot also comes packaged with a [command-line interface](https://camelot-py.readthedocs.io/en/master/user/cli.html)!
|
||||
There's a [command-line interface](https://camelot-py.readthedocs.io/en/master/user/cli.html) too!
|
||||
|
||||
**Note:** Camelot only works with text-based PDFs and not scanned documents. (As Tabula [explains](https://github.com/tabulapdf/tabula#why-tabula), "If you can click and drag to select text in your table in a PDF viewer, then your PDF is text-based".)
|
||||
|
||||
You can check out some frequently asked questions [here](https://camelot-py.readthedocs.io/en/master/user/faq.html).
|
||||
|
||||
## Why Camelot?
|
||||
|
||||
- **Configurability**: Camelot gives you control over the table extraction process with [tweakable settings](https://camelot-py.readthedocs.io/en/master/user/advanced.html).
|
||||
- **Metrics**: You can discard bad tables based on metrics like accuracy and whitespace, without having to manually look at each table.
|
||||
- **Output**: Each table is extracted into a **pandas DataFrame**, which seamlessly integrates into [ETL and data analysis workflows](https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873). You can also export tables to multiple formats, which include CSV, JSON, Excel, HTML, Markdown, and Sqlite.
|
||||
- **You are in control.**: Unlike other libraries and tools which either give a nice output or fail miserably (with no in-between), Camelot gives you the power to tweak table extraction. (This is important since everything in the real world, including PDF table extraction, is fuzzy.)
|
||||
- *Bad* tables can be discarded based on **metrics** like accuracy and whitespace, without ever having to manually look at each table.
|
||||
- Each table is a **pandas DataFrame**, which seamlessly integrates into [ETL and data analysis workflows](https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873).
|
||||
- **Export** to multiple formats, including JSON, Excel and HTML.
|
||||
|
||||
See [comparison with similar libraries and tools](https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools).
|
||||
|
||||
## Support the development
|
||||
|
||||
If Camelot has helped you, please consider supporting its development with a one-time or monthly donation [on OpenCollective](https://opencollective.com/camelot).
|
||||
See [comparison with other PDF table extraction libraries and tools](https://github.com/socialcopsdev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools).
|
||||
|
||||
## Installation
|
||||
|
||||
### Using conda
|
||||
|
||||
The easiest way to install Camelot is with [conda](https://conda.io/docs/), which is a package manager and environment management system for the [Anaconda](http://docs.continuum.io/anaconda/) distribution.
|
||||
The easiest way to install Camelot is to install it with [conda](https://conda.io/docs/), which is a package manager and environment management system for the [Anaconda](http://docs.continuum.io/anaconda/) distribution.
|
||||
|
||||
<pre>
|
||||
$ conda install -c conda-forge camelot-py
|
||||
|
|
@ -75,10 +69,10 @@ $ conda install -c conda-forge camelot-py
|
|||
|
||||
### Using pip
|
||||
|
||||
After [installing the dependencies](https://camelot-py.readthedocs.io/en/master/user/install-deps.html) ([tk](https://packages.ubuntu.com/bionic/python/python-tk) and [ghostscript](https://www.ghostscript.com/)), you can also just use pip to install Camelot:
|
||||
After [installing the dependencies](https://camelot-py.readthedocs.io/en/master/user/install-deps.html) ([tk](https://packages.ubuntu.com/trusty/python-tk) and [ghostscript](https://www.ghostscript.com/)), you can simply use pip to install Camelot:
|
||||
|
||||
<pre>
|
||||
$ pip install "camelot-py[base]"
|
||||
$ pip install camelot-py[cv]
|
||||
</pre>
|
||||
|
||||
### From the source code
|
||||
|
|
@ -86,32 +80,52 @@ $ pip install "camelot-py[base]"
|
|||
After [installing the dependencies](https://camelot-py.readthedocs.io/en/master/user/install.html#using-pip), clone the repo using:
|
||||
|
||||
<pre>
|
||||
$ git clone https://www.github.com/camelot-dev/camelot
|
||||
$ git clone https://www.github.com/socialcopsdev/camelot
|
||||
</pre>
|
||||
|
||||
and install Camelot using pip:
|
||||
|
||||
<pre>
|
||||
$ cd camelot
|
||||
$ pip install ".[base]"
|
||||
$ pip install ".[cv]"
|
||||
</pre>
|
||||
|
||||
## Documentation
|
||||
|
||||
The documentation is available at [http://camelot-py.readthedocs.io/](http://camelot-py.readthedocs.io/).
|
||||
Great documentation is available at [http://camelot-py.readthedocs.io/](http://camelot-py.readthedocs.io/).
|
||||
|
||||
## Wrappers
|
||||
## Development
|
||||
|
||||
- [camelot-php](https://github.com/randomstate/camelot-php) provides a [PHP](https://www.php.net/) wrapper on Camelot.
|
||||
The [Contributor's Guide](https://camelot-py.readthedocs.io/en/master/dev/contributing.html) has detailed information about contributing code, documentation, tests and more. We've included some basic information in this README.
|
||||
|
||||
## Contributing
|
||||
### Source code
|
||||
|
||||
The [Contributor's Guide](https://camelot-py.readthedocs.io/en/master/dev/contributing.html) has detailed information about contributing issues, documentation, code, and tests.
|
||||
You can check the latest sources with:
|
||||
|
||||
<pre>
|
||||
$ git clone https://www.github.com/socialcopsdev/camelot
|
||||
</pre>
|
||||
|
||||
### Setting up a development environment
|
||||
|
||||
You can install the development dependencies easily, using pip:
|
||||
|
||||
<pre>
|
||||
$ pip install camelot-py[dev]
|
||||
</pre>
|
||||
|
||||
### Testing
|
||||
|
||||
After installation, you can run tests using:
|
||||
|
||||
<pre>
|
||||
$ python setup.py test
|
||||
</pre>
|
||||
|
||||
## Versioning
|
||||
|
||||
Camelot uses [Semantic Versioning](https://semver.org/). For the available versions, see the tags on this repository. For the changelog, you can check out [HISTORY.md](https://github.com/camelot-dev/camelot/blob/master/HISTORY.md).
|
||||
Camelot uses [Semantic Versioning](https://semver.org/). For the available versions, see the tags on this repository. For the changelog, you can check out [HISTORY.md](https://github.com/socialcopsdev/camelot/blob/master/HISTORY.md).
|
||||
|
||||
## License
|
||||
|
||||
This project is licensed under the MIT License, see the [LICENSE](https://github.com/camelot-dev/camelot/blob/master/LICENSE) file for details.
|
||||
This project is licensed under the MIT License, see the [LICENSE](https://github.com/socialcopsdev/camelot/blob/master/LICENSE) file for details.
|
||||
|
|
|
|||
|
|
@ -2,16 +2,26 @@
|
|||
|
||||
import logging
|
||||
|
||||
from click import HelpFormatter
|
||||
|
||||
from .__version__ import __version__
|
||||
from .io import read_pdf
|
||||
from .plotting import PlotMethods
|
||||
|
||||
|
||||
# set up logging
|
||||
logger = logging.getLogger("camelot")
|
||||
def _write_usage(self, prog, args='', prefix='Usage: '):
|
||||
return self._write_usage('camelot', args, prefix=prefix)
|
||||
|
||||
format_string = "%(asctime)s - %(levelname)s - %(message)s"
|
||||
formatter = logging.Formatter(format_string, datefmt="%Y-%m-%dT%H:%M:%S")
|
||||
|
||||
# monkey patch click.HelpFormatter
|
||||
HelpFormatter._write_usage = HelpFormatter.write_usage
|
||||
HelpFormatter.write_usage = _write_usage
|
||||
|
||||
# set up logging
|
||||
logger = logging.getLogger('camelot')
|
||||
|
||||
format_string = '%(asctime)s - %(levelname)s - %(message)s'
|
||||
formatter = logging.Formatter(format_string, datefmt='%Y-%m-%dT%H:%M:%S')
|
||||
handler = logging.StreamHandler()
|
||||
handler.setFormatter(formatter)
|
||||
|
||||
|
|
|
|||
|
|
@ -1,7 +1,9 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
from __future__ import absolute_import
|
||||
|
||||
__all__ = ("main",)
|
||||
|
||||
__all__ = ('main',)
|
||||
|
||||
|
||||
def main():
|
||||
|
|
|
|||
|
|
@ -1,23 +1,23 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
VERSION = (0, 10, 1)
|
||||
PRERELEASE = None # alpha, beta or rc
|
||||
VERSION = (0, 5, 0)
|
||||
PRERELEASE = None # alpha, beta or rc
|
||||
REVISION = None
|
||||
|
||||
|
||||
def generate_version(version, prerelease=None, revision=None):
|
||||
version_parts = [".".join(map(str, version))]
|
||||
version_parts = ['.'.join(map(str, version))]
|
||||
if prerelease is not None:
|
||||
version_parts.append(f"-{prerelease}")
|
||||
version_parts.append('-{}'.format(prerelease))
|
||||
if revision is not None:
|
||||
version_parts.append(f".{revision}")
|
||||
return "".join(version_parts)
|
||||
version_parts.append('.{}'.format(revision))
|
||||
return ''.join(version_parts)
|
||||
|
||||
|
||||
__title__ = "camelot-py"
|
||||
__description__ = "PDF Table Extraction for Humans."
|
||||
__url__ = "http://camelot-py.readthedocs.io/"
|
||||
__title__ = 'camelot-py'
|
||||
__description__ = 'PDF Table Extraction for Humans.'
|
||||
__url__ = 'http://camelot-py.readthedocs.io/'
|
||||
__version__ = generate_version(VERSION, prerelease=PRERELEASE, revision=REVISION)
|
||||
__author__ = "Vinayak Mehta"
|
||||
__author_email__ = "vmehta94@gmail.com"
|
||||
__license__ = "MIT License"
|
||||
__author__ = 'Vinayak Mehta'
|
||||
__author_email__ = 'vmehta94@gmail.com'
|
||||
__license__ = 'MIT License'
|
||||
|
|
|
|||
|
|
@ -1,3 +0,0 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
from .image_conversion import ImageConversionBackend
|
||||
|
|
@ -1,47 +0,0 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import sys
|
||||
import ctypes
|
||||
from ctypes.util import find_library
|
||||
|
||||
|
||||
def installed_posix():
|
||||
library = find_library("gs")
|
||||
return library is not None
|
||||
|
||||
|
||||
def installed_windows():
|
||||
library = find_library(
|
||||
"".join(("gsdll", str(ctypes.sizeof(ctypes.c_voidp) * 8), ".dll"))
|
||||
)
|
||||
return library is not None
|
||||
|
||||
|
||||
class GhostscriptBackend(object):
|
||||
def installed(self):
|
||||
if sys.platform in ["linux", "darwin"]:
|
||||
return installed_posix()
|
||||
elif sys.platform == "win32":
|
||||
return installed_windows()
|
||||
else:
|
||||
return installed_posix()
|
||||
|
||||
def convert(self, pdf_path, png_path, resolution=300):
|
||||
if not self.installed():
|
||||
raise OSError(
|
||||
"Ghostscript is not installed. You can install it using the instructions"
|
||||
" here: https://camelot-py.readthedocs.io/en/master/user/install-deps.html"
|
||||
)
|
||||
|
||||
import ghostscript
|
||||
|
||||
gs_command = [
|
||||
"gs",
|
||||
"-q",
|
||||
"-sDEVICE=png16m",
|
||||
"-o",
|
||||
png_path,
|
||||
f"-r{resolution}",
|
||||
pdf_path,
|
||||
]
|
||||
ghostscript.Ghostscript(*gs_command)
|
||||
|
|
@ -1,40 +0,0 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
from .poppler_backend import PopplerBackend
|
||||
from .ghostscript_backend import GhostscriptBackend
|
||||
|
||||
BACKENDS = {"poppler": PopplerBackend, "ghostscript": GhostscriptBackend}
|
||||
|
||||
|
||||
class ImageConversionBackend(object):
|
||||
def __init__(self, backend="poppler", use_fallback=True):
|
||||
if backend not in BACKENDS.keys():
|
||||
raise ValueError(f"Image conversion backend '{backend}' not supported")
|
||||
|
||||
self.backend = backend
|
||||
self.use_fallback = use_fallback
|
||||
self.fallbacks = list(filter(lambda x: x != backend, BACKENDS.keys()))
|
||||
|
||||
def convert(self, pdf_path, png_path):
|
||||
try:
|
||||
converter = BACKENDS[self.backend]()
|
||||
converter.convert(pdf_path, png_path)
|
||||
except Exception as e:
|
||||
import sys
|
||||
|
||||
if self.use_fallback:
|
||||
for fallback in self.fallbacks:
|
||||
try:
|
||||
converter = BACKENDS[fallback]()
|
||||
converter.convert(pdf_path, png_path)
|
||||
except Exception as e:
|
||||
raise type(e)(
|
||||
str(e) + f" with image conversion backend '{fallback}'"
|
||||
).with_traceback(sys.exc_info()[2])
|
||||
continue
|
||||
else:
|
||||
break
|
||||
else:
|
||||
raise type(e)(
|
||||
str(e) + f" with image conversion backend '{self.backend}'"
|
||||
).with_traceback(sys.exc_info()[2])
|
||||
|
|
@ -1,22 +0,0 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import shutil
|
||||
import subprocess
|
||||
|
||||
|
||||
class PopplerBackend(object):
|
||||
def convert(self, pdf_path, png_path):
|
||||
pdftopng_executable = shutil.which("pdftopng")
|
||||
if pdftopng_executable is None:
|
||||
raise OSError(
|
||||
"pdftopng is not installed. You can install it using the 'pip install pdftopng' command."
|
||||
)
|
||||
|
||||
pdftopng_command = [pdftopng_executable, pdf_path, png_path]
|
||||
|
||||
try:
|
||||
subprocess.check_output(
|
||||
" ".join(pdftopng_command), stderr=subprocess.STDOUT, shell=True
|
||||
)
|
||||
except subprocess.CalledProcessError as e:
|
||||
raise ValueError(e.output)
|
||||
327
camelot/cli.py
327
camelot/cli.py
|
|
@ -3,7 +3,6 @@
|
|||
import logging
|
||||
|
||||
import click
|
||||
|
||||
try:
|
||||
import matplotlib.pyplot as plt
|
||||
except ImportError:
|
||||
|
|
@ -14,7 +13,7 @@ else:
|
|||
from . import __version__, read_pdf, plot
|
||||
|
||||
|
||||
logger = logging.getLogger("camelot")
|
||||
logger = logging.getLogger('camelot')
|
||||
logger.setLevel(logging.INFO)
|
||||
|
||||
|
||||
|
|
@ -29,49 +28,23 @@ class Config(object):
|
|||
pass_config = click.make_pass_decorator(Config)
|
||||
|
||||
|
||||
@click.group(name="camelot")
|
||||
@click.group()
|
||||
@click.version_option(version=__version__)
|
||||
@click.option("-q", "--quiet", is_flag=False, help="Suppress logs and warnings.")
|
||||
@click.option(
|
||||
"-p",
|
||||
"--pages",
|
||||
default="1",
|
||||
help="Comma-separated page numbers." " Example: 1,3,4 or 1,4-end or all.",
|
||||
)
|
||||
@click.option("-pw", "--password", help="Password for decryption.")
|
||||
@click.option("-o", "--output", help="Output file path.")
|
||||
@click.option(
|
||||
"-f",
|
||||
"--format",
|
||||
type=click.Choice(["csv", "excel", "html", "json", "markdown", "sqlite"]),
|
||||
help="Output file format.",
|
||||
)
|
||||
@click.option("-z", "--zip", is_flag=True, help="Create ZIP archive.")
|
||||
@click.option(
|
||||
"-split",
|
||||
"--split_text",
|
||||
is_flag=True,
|
||||
help="Split text that spans across multiple cells.",
|
||||
)
|
||||
@click.option(
|
||||
"-flag",
|
||||
"--flag_size",
|
||||
is_flag=True,
|
||||
help="Flag text based on" " font size. Useful to detect super/subscripts.",
|
||||
)
|
||||
@click.option(
|
||||
"-strip",
|
||||
"--strip_text",
|
||||
help="Characters that should be stripped from a string before"
|
||||
" assigning it to a cell.",
|
||||
)
|
||||
@click.option(
|
||||
"-M",
|
||||
"--margins",
|
||||
nargs=3,
|
||||
default=(1.0, 0.5, 0.1),
|
||||
help="PDFMiner char_margin, line_margin and word_margin.",
|
||||
)
|
||||
@click.option('-q', '--quiet', is_flag=False, help='Suppress logs and warnings.')
|
||||
@click.option('-p', '--pages', default='1', help='Comma-separated page numbers.'
|
||||
' Example: 1,3,4 or 1,4-end.')
|
||||
@click.option('-pw', '--password', help='Password for decryption.')
|
||||
@click.option('-o', '--output', help='Output file path.')
|
||||
@click.option('-f', '--format',
|
||||
type=click.Choice(['csv', 'json', 'excel', 'html']),
|
||||
help='Output file format.')
|
||||
@click.option('-z', '--zip', is_flag=True, help='Create ZIP archive.')
|
||||
@click.option('-split', '--split_text', is_flag=True,
|
||||
help='Split text that spans across multiple cells.')
|
||||
@click.option('-flag', '--flag_size', is_flag=True, help='Flag text based on'
|
||||
' font size. Useful to detect super/subscripts.')
|
||||
@click.option('-M', '--margins', nargs=3, default=(1.0, 0.5, 0.1),
|
||||
help='PDFMiner char_margin, line_margin and word_margin.')
|
||||
@click.pass_context
|
||||
def cli(ctx, *args, **kwargs):
|
||||
"""Camelot: PDF Table Extraction for Humans"""
|
||||
|
|
@ -80,131 +53,72 @@ def cli(ctx, *args, **kwargs):
|
|||
ctx.obj.set_config(key, value)
|
||||
|
||||
|
||||
@cli.command("lattice")
|
||||
@click.option(
|
||||
"-R",
|
||||
"--table_regions",
|
||||
default=[],
|
||||
multiple=True,
|
||||
help="Page regions to analyze. Example: x1,y1,x2,y2"
|
||||
" where x1, y1 -> left-top and x2, y2 -> right-bottom.",
|
||||
)
|
||||
@click.option(
|
||||
"-T",
|
||||
"--table_areas",
|
||||
default=[],
|
||||
multiple=True,
|
||||
help="Table areas to process. Example: x1,y1,x2,y2"
|
||||
" where x1, y1 -> left-top and x2, y2 -> right-bottom.",
|
||||
)
|
||||
@click.option(
|
||||
"-back", "--process_background", is_flag=True, help="Process background lines."
|
||||
)
|
||||
@click.option(
|
||||
"-scale",
|
||||
"--line_scale",
|
||||
default=15,
|
||||
help="Line size scaling factor. The larger the value,"
|
||||
" the smaller the detected lines.",
|
||||
)
|
||||
@click.option(
|
||||
"-copy",
|
||||
"--copy_text",
|
||||
default=[],
|
||||
type=click.Choice(["h", "v"]),
|
||||
multiple=True,
|
||||
help="Direction in which text in a spanning cell" " will be copied over.",
|
||||
)
|
||||
@click.option(
|
||||
"-shift",
|
||||
"--shift_text",
|
||||
default=["l", "t"],
|
||||
type=click.Choice(["", "l", "r", "t", "b"]),
|
||||
multiple=True,
|
||||
help="Direction in which text in a spanning cell will flow.",
|
||||
)
|
||||
@click.option(
|
||||
"-l",
|
||||
"--line_tol",
|
||||
default=2,
|
||||
help="Tolerance parameter used to merge close vertical" " and horizontal lines.",
|
||||
)
|
||||
@click.option(
|
||||
"-j",
|
||||
"--joint_tol",
|
||||
default=2,
|
||||
help="Tolerance parameter used to decide whether"
|
||||
" the detected lines and points lie close to each other.",
|
||||
)
|
||||
@click.option(
|
||||
"-block",
|
||||
"--threshold_blocksize",
|
||||
default=15,
|
||||
help="For adaptive thresholding, size of a pixel"
|
||||
" neighborhood that is used to calculate a threshold value for"
|
||||
" the pixel. Example: 3, 5, 7, and so on.",
|
||||
)
|
||||
@click.option(
|
||||
"-const",
|
||||
"--threshold_constant",
|
||||
default=-2,
|
||||
help="For adaptive thresholding, constant subtracted"
|
||||
" from the mean or weighted mean. Normally, it is positive but"
|
||||
" may be zero or negative as well.",
|
||||
)
|
||||
@click.option(
|
||||
"-I",
|
||||
"--iterations",
|
||||
default=0,
|
||||
help="Number of times for erosion/dilation will be applied.",
|
||||
)
|
||||
@click.option(
|
||||
"-res",
|
||||
"--resolution",
|
||||
default=300,
|
||||
help="Resolution used for PDF to PNG conversion.",
|
||||
)
|
||||
@click.option(
|
||||
"-plot",
|
||||
"--plot_type",
|
||||
type=click.Choice(["text", "grid", "contour", "joint", "line"]),
|
||||
help="Plot elements found on PDF page for visual debugging.",
|
||||
)
|
||||
@click.argument("filepath", type=click.Path(exists=True))
|
||||
@cli.command('lattice')
|
||||
@click.option('-T', '--table_areas', default=[], multiple=True,
|
||||
help='Table areas to process. Example: x1,y1,x2,y2'
|
||||
' where x1, y1 -> left-top and x2, y2 -> right-bottom.')
|
||||
@click.option('-back', '--process_background', is_flag=True,
|
||||
help='Process background lines.')
|
||||
@click.option('-scale', '--line_size_scaling', default=15,
|
||||
help='Line size scaling factor. The larger the value,'
|
||||
' the smaller the detected lines.')
|
||||
@click.option('-copy', '--copy_text', default=[], type=click.Choice(['h', 'v']),
|
||||
multiple=True, help='Direction in which text in a spanning cell'
|
||||
' will be copied over.')
|
||||
@click.option('-shift', '--shift_text', default=['l', 't'],
|
||||
type=click.Choice(['', 'l', 'r', 't', 'b']), multiple=True,
|
||||
help='Direction in which text in a spanning cell will flow.')
|
||||
@click.option('-l', '--line_close_tol', default=2,
|
||||
help='Tolerance parameter used to merge close vertical'
|
||||
' and horizontal lines.')
|
||||
@click.option('-j', '--joint_close_tol', default=2,
|
||||
help='Tolerance parameter used to decide whether'
|
||||
' the detected lines and points lie close to each other.')
|
||||
@click.option('-block', '--threshold_blocksize', default=15,
|
||||
help='For adaptive thresholding, size of a pixel'
|
||||
' neighborhood that is used to calculate a threshold value for'
|
||||
' the pixel. Example: 3, 5, 7, and so on.')
|
||||
@click.option('-const', '--threshold_constant', default=-2,
|
||||
help='For adaptive thresholding, constant subtracted'
|
||||
' from the mean or weighted mean. Normally, it is positive but'
|
||||
' may be zero or negative as well.')
|
||||
@click.option('-I', '--iterations', default=0,
|
||||
help='Number of times for erosion/dilation will be applied.')
|
||||
@click.option('-plot', '--plot_type',
|
||||
type=click.Choice(['text', 'grid', 'contour', 'joint', 'line']),
|
||||
help='Plot elements found on PDF page for visual debugging.')
|
||||
@click.argument('filepath', type=click.Path(exists=True))
|
||||
@pass_config
|
||||
def lattice(c, *args, **kwargs):
|
||||
"""Use lines between text to parse the table."""
|
||||
conf = c.config
|
||||
pages = conf.pop("pages")
|
||||
output = conf.pop("output")
|
||||
f = conf.pop("format")
|
||||
compress = conf.pop("zip")
|
||||
quiet = conf.pop("quiet")
|
||||
plot_type = kwargs.pop("plot_type")
|
||||
filepath = kwargs.pop("filepath")
|
||||
pages = conf.pop('pages')
|
||||
output = conf.pop('output')
|
||||
f = conf.pop('format')
|
||||
compress = conf.pop('zip')
|
||||
quiet = conf.pop('quiet')
|
||||
plot_type = kwargs.pop('plot_type')
|
||||
filepath = kwargs.pop('filepath')
|
||||
kwargs.update(conf)
|
||||
|
||||
table_regions = list(kwargs["table_regions"])
|
||||
kwargs["table_regions"] = None if not table_regions else table_regions
|
||||
table_areas = list(kwargs["table_areas"])
|
||||
kwargs["table_areas"] = None if not table_areas else table_areas
|
||||
copy_text = list(kwargs["copy_text"])
|
||||
kwargs["copy_text"] = None if not copy_text else copy_text
|
||||
kwargs["shift_text"] = list(kwargs["shift_text"])
|
||||
table_areas = list(kwargs['table_areas'])
|
||||
kwargs['table_areas'] = None if not table_areas else table_areas
|
||||
copy_text = list(kwargs['copy_text'])
|
||||
kwargs['copy_text'] = None if not copy_text else copy_text
|
||||
kwargs['shift_text'] = list(kwargs['shift_text'])
|
||||
|
||||
if plot_type is not None:
|
||||
if not _HAS_MPL:
|
||||
raise ImportError("matplotlib is required for plotting.")
|
||||
raise ImportError('matplotlib is required for plotting.')
|
||||
else:
|
||||
if output is None:
|
||||
raise click.UsageError("Please specify output file path using --output")
|
||||
raise click.UsageError('Please specify output file path using --output')
|
||||
if f is None:
|
||||
raise click.UsageError("Please specify output file format using --format")
|
||||
raise click.UsageError('Please specify output file format using --format')
|
||||
|
||||
tables = read_pdf(
|
||||
filepath, pages=pages, flavor="lattice", suppress_stdout=quiet, **kwargs
|
||||
)
|
||||
click.echo(f"Found {tables.n} tables")
|
||||
tables = read_pdf(filepath, pages=pages, flavor='lattice',
|
||||
suppress_stdout=quiet, **kwargs)
|
||||
click.echo('Found {} tables'.format(tables.n))
|
||||
if plot_type is not None:
|
||||
for table in tables:
|
||||
plot(table, kind=plot_type)
|
||||
|
|
@ -213,89 +127,50 @@ def lattice(c, *args, **kwargs):
|
|||
tables.export(output, f=f, compress=compress)
|
||||
|
||||
|
||||
@cli.command("stream")
|
||||
@click.option(
|
||||
"-R",
|
||||
"--table_regions",
|
||||
default=[],
|
||||
multiple=True,
|
||||
help="Page regions to analyze. Example: x1,y1,x2,y2"
|
||||
" where x1, y1 -> left-top and x2, y2 -> right-bottom.",
|
||||
)
|
||||
@click.option(
|
||||
"-T",
|
||||
"--table_areas",
|
||||
default=[],
|
||||
multiple=True,
|
||||
help="Table areas to process. Example: x1,y1,x2,y2"
|
||||
" where x1, y1 -> left-top and x2, y2 -> right-bottom.",
|
||||
)
|
||||
@click.option(
|
||||
"-C",
|
||||
"--columns",
|
||||
default=[],
|
||||
multiple=True,
|
||||
help="X coordinates of column separators.",
|
||||
)
|
||||
@click.option(
|
||||
"-e",
|
||||
"--edge_tol",
|
||||
default=50,
|
||||
help="Tolerance parameter" " for extending textedges vertically.",
|
||||
)
|
||||
@click.option(
|
||||
"-r",
|
||||
"--row_tol",
|
||||
default=2,
|
||||
help="Tolerance parameter" " used to combine text vertically, to generate rows.",
|
||||
)
|
||||
@click.option(
|
||||
"-c",
|
||||
"--column_tol",
|
||||
default=0,
|
||||
help="Tolerance parameter"
|
||||
" used to combine text horizontally, to generate columns.",
|
||||
)
|
||||
@click.option(
|
||||
"-plot",
|
||||
"--plot_type",
|
||||
type=click.Choice(["text", "grid", "contour", "textedge"]),
|
||||
help="Plot elements found on PDF page for visual debugging.",
|
||||
)
|
||||
@click.argument("filepath", type=click.Path(exists=True))
|
||||
@cli.command('stream')
|
||||
@click.option('-T', '--table_areas', default=[], multiple=True,
|
||||
help='Table areas to process. Example: x1,y1,x2,y2'
|
||||
' where x1, y1 -> left-top and x2, y2 -> right-bottom.')
|
||||
@click.option('-C', '--columns', default=[], multiple=True,
|
||||
help='X coordinates of column separators.')
|
||||
@click.option('-r', '--row_close_tol', default=2, help='Tolerance parameter'
|
||||
' used to combine text vertically, to generate rows.')
|
||||
@click.option('-c', '--col_close_tol', default=0, help='Tolerance parameter'
|
||||
' used to combine text horizontally, to generate columns.')
|
||||
@click.option('-plot', '--plot_type',
|
||||
type=click.Choice(['text', 'grid', 'contour', 'textedge']),
|
||||
help='Plot elements found on PDF page for visual debugging.')
|
||||
@click.argument('filepath', type=click.Path(exists=True))
|
||||
@pass_config
|
||||
def stream(c, *args, **kwargs):
|
||||
"""Use spaces between text to parse the table."""
|
||||
conf = c.config
|
||||
pages = conf.pop("pages")
|
||||
output = conf.pop("output")
|
||||
f = conf.pop("format")
|
||||
compress = conf.pop("zip")
|
||||
quiet = conf.pop("quiet")
|
||||
plot_type = kwargs.pop("plot_type")
|
||||
filepath = kwargs.pop("filepath")
|
||||
pages = conf.pop('pages')
|
||||
output = conf.pop('output')
|
||||
f = conf.pop('format')
|
||||
compress = conf.pop('zip')
|
||||
quiet = conf.pop('quiet')
|
||||
plot_type = kwargs.pop('plot_type')
|
||||
filepath = kwargs.pop('filepath')
|
||||
kwargs.update(conf)
|
||||
|
||||
table_regions = list(kwargs["table_regions"])
|
||||
kwargs["table_regions"] = None if not table_regions else table_regions
|
||||
table_areas = list(kwargs["table_areas"])
|
||||
kwargs["table_areas"] = None if not table_areas else table_areas
|
||||
columns = list(kwargs["columns"])
|
||||
kwargs["columns"] = None if not columns else columns
|
||||
table_areas = list(kwargs['table_areas'])
|
||||
kwargs['table_areas'] = None if not table_areas else table_areas
|
||||
columns = list(kwargs['columns'])
|
||||
kwargs['columns'] = None if not columns else columns
|
||||
|
||||
if plot_type is not None:
|
||||
if not _HAS_MPL:
|
||||
raise ImportError("matplotlib is required for plotting.")
|
||||
raise ImportError('matplotlib is required for plotting.')
|
||||
else:
|
||||
if output is None:
|
||||
raise click.UsageError("Please specify output file path using --output")
|
||||
raise click.UsageError('Please specify output file path using --output')
|
||||
if f is None:
|
||||
raise click.UsageError("Please specify output file format using --format")
|
||||
raise click.UsageError('Please specify output file format using --format')
|
||||
|
||||
tables = read_pdf(
|
||||
filepath, pages=pages, flavor="stream", suppress_stdout=quiet, **kwargs
|
||||
)
|
||||
click.echo(f"Found {tables.n} tables")
|
||||
tables = read_pdf(filepath, pages=pages, flavor='stream',
|
||||
suppress_stdout=quiet, **kwargs)
|
||||
click.echo('Found {} tables'.format(tables.n))
|
||||
if plot_type is not None:
|
||||
for table in tables:
|
||||
plot(table, kind=plot_type)
|
||||
|
|
|
|||
267
camelot/core.py
267
camelot/core.py
|
|
@ -1,7 +1,6 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import os
|
||||
import sqlite3
|
||||
import zipfile
|
||||
import tempfile
|
||||
from itertools import chain
|
||||
|
|
@ -14,6 +13,8 @@ import pandas as pd
|
|||
# minimum number of vertical textline intersections for a textedge
|
||||
# to be considered valid
|
||||
TEXTEDGE_REQUIRED_ELEMENTS = 4
|
||||
# y coordinate tolerance for extending textedge
|
||||
TEXTEDGE_EXTEND_TOLERANCE = 50
|
||||
# padding added to table area on the left, right and bottom
|
||||
TABLE_AREA_PADDING = 10
|
||||
|
||||
|
|
@ -42,8 +43,7 @@ class TextEdge(object):
|
|||
TEXTEDGE_REQUIRED_ELEMENTS horizontal text rows.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, x, y0, y1, align="left"):
|
||||
def __init__(self, x, y0, y1, align='left'):
|
||||
self.x = x
|
||||
self.y0 = y0
|
||||
self.y1 = y1
|
||||
|
|
@ -52,18 +52,14 @@ class TextEdge(object):
|
|||
self.is_valid = False
|
||||
|
||||
def __repr__(self):
|
||||
x = round(self.x, 2)
|
||||
y0 = round(self.y0, 2)
|
||||
y1 = round(self.y1, 2)
|
||||
return (
|
||||
f"<TextEdge x={x} y0={y0} y1={y1} align={self.align} valid={self.is_valid}>"
|
||||
)
|
||||
return '<TextEdge x={} y0={} y1={} align={} valid={}>'.format(
|
||||
round(self.x, 2), round(self.y0, 2), round(self.y1, 2), self.align, self.is_valid)
|
||||
|
||||
def update_coords(self, x, y0, edge_tol=50):
|
||||
def update_coords(self, x, y0):
|
||||
"""Updates the text edge's x and bottom y coordinates and sets
|
||||
the is_valid attribute.
|
||||
"""
|
||||
if np.isclose(self.y0, y0, atol=edge_tol):
|
||||
if np.isclose(self.y0, y0, atol=TEXTEDGE_EXTEND_TOLERANCE):
|
||||
self.x = (self.intersections * self.x + x) / float(self.intersections + 1)
|
||||
self.y0 = y0
|
||||
self.intersections += 1
|
||||
|
|
@ -78,10 +74,8 @@ class TextEdges(object):
|
|||
the PDF page. The dict has three keys based on the alignments,
|
||||
and each key's value is a list of camelot.core.TextEdge objects.
|
||||
"""
|
||||
|
||||
def __init__(self, edge_tol=50):
|
||||
self.edge_tol = edge_tol
|
||||
self._textedges = {"left": [], "right": [], "middle": []}
|
||||
def __init__(self):
|
||||
self._textedges = {'left': [], 'right': [], 'middle': []}
|
||||
|
||||
@staticmethod
|
||||
def get_x_coord(textline, align):
|
||||
|
|
@ -91,7 +85,7 @@ class TextEdges(object):
|
|||
x_left = textline.x0
|
||||
x_right = textline.x1
|
||||
x_middle = x_left + (x_right - x_left) / 2.0
|
||||
x_coord = {"left": x_left, "middle": x_middle, "right": x_right}
|
||||
x_coord = {'left': x_left, 'middle': x_middle, 'right': x_right}
|
||||
return x_coord[align]
|
||||
|
||||
def find(self, x_coord, align):
|
||||
|
|
@ -104,7 +98,8 @@ class TextEdges(object):
|
|||
return None
|
||||
|
||||
def add(self, textline, align):
|
||||
"""Adds a new text edge to the current dict."""
|
||||
"""Adds a new text edge to the current dict.
|
||||
"""
|
||||
x = self.get_x_coord(textline, align)
|
||||
y0 = textline.y0
|
||||
y1 = textline.y1
|
||||
|
|
@ -112,23 +107,22 @@ class TextEdges(object):
|
|||
self._textedges[align].append(te)
|
||||
|
||||
def update(self, textline):
|
||||
"""Updates an existing text edge in the current dict."""
|
||||
for align in ["left", "right", "middle"]:
|
||||
"""Updates an existing text edge in the current dict.
|
||||
"""
|
||||
for align in ['left', 'right', 'middle']:
|
||||
x_coord = self.get_x_coord(textline, align)
|
||||
idx = self.find(x_coord, align)
|
||||
if idx is None:
|
||||
self.add(textline, align)
|
||||
else:
|
||||
self._textedges[align][idx].update_coords(
|
||||
x_coord, textline.y0, edge_tol=self.edge_tol
|
||||
)
|
||||
self._textedges[align][idx].update_coords(x_coord, textline.y0)
|
||||
|
||||
def generate(self, textlines):
|
||||
"""Generates the text edges dict based on horizontal text
|
||||
rows.
|
||||
"""
|
||||
for tl in textlines:
|
||||
if len(tl.get_text().strip()) > 1: # TODO: hacky
|
||||
if len(tl.get_text().strip()) > 1: # TODO: hacky
|
||||
self.update(tl)
|
||||
|
||||
def get_relevant(self):
|
||||
|
|
@ -137,15 +131,9 @@ class TextEdges(object):
|
|||
the most.
|
||||
"""
|
||||
intersections_sum = {
|
||||
"left": sum(
|
||||
te.intersections for te in self._textedges["left"] if te.is_valid
|
||||
),
|
||||
"right": sum(
|
||||
te.intersections for te in self._textedges["right"] if te.is_valid
|
||||
),
|
||||
"middle": sum(
|
||||
te.intersections for te in self._textedges["middle"] if te.is_valid
|
||||
),
|
||||
'left': sum(te.intersections for te in self._textedges['left'] if te.is_valid),
|
||||
'right': sum(te.intersections for te in self._textedges['right'] if te.is_valid),
|
||||
'middle': sum(te.intersections for te in self._textedges['middle'] if te.is_valid)
|
||||
}
|
||||
|
||||
# TODO: naive
|
||||
|
|
@ -158,7 +146,6 @@ class TextEdges(object):
|
|||
"""Returns a dict of interesting table areas on the PDF page
|
||||
calculated using relevant text edges.
|
||||
"""
|
||||
|
||||
def pad(area, average_row_height):
|
||||
x0 = area[0] - TABLE_AREA_PADDING
|
||||
y0 = area[1] - TABLE_AREA_PADDING
|
||||
|
|
@ -187,11 +174,7 @@ class TextEdges(object):
|
|||
else:
|
||||
table_areas.pop(found)
|
||||
updated_area = (
|
||||
found[0],
|
||||
min(te.y0, found[1]),
|
||||
max(found[2], te.x),
|
||||
max(found[3], te.y1),
|
||||
)
|
||||
found[0], min(te.y0, found[1]), max(found[2], te.x), max(found[3], te.y1))
|
||||
table_areas[updated_area] = None
|
||||
|
||||
# extend table areas based on textlines that overlap
|
||||
|
|
@ -212,11 +195,7 @@ class TextEdges(object):
|
|||
if found is not None:
|
||||
table_areas.pop(found)
|
||||
updated_area = (
|
||||
min(tl.x0, found[0]),
|
||||
min(tl.y0, found[1]),
|
||||
max(found[2], tl.x1),
|
||||
max(found[3], tl.y1),
|
||||
)
|
||||
min(tl.x0, found[0]), min(tl.y0, found[1]), max(found[2], tl.x1), max(found[3], tl.y1))
|
||||
table_areas[updated_area] = None
|
||||
average_textline_height = sum_textline_height / float(len(textlines))
|
||||
|
||||
|
|
@ -285,14 +264,11 @@ class Cell(object):
|
|||
self.bottom = False
|
||||
self.hspan = False
|
||||
self.vspan = False
|
||||
self._text = ""
|
||||
self._text = ''
|
||||
|
||||
def __repr__(self):
|
||||
x1 = round(self.x1)
|
||||
y1 = round(self.y1)
|
||||
x2 = round(self.x2)
|
||||
y2 = round(self.y2)
|
||||
return f"<Cell x1={x1} y1={y1} x2={x2} y2={y2}>"
|
||||
return '<Cell x1={} y1={} x2={} y2={}>'.format(
|
||||
round(self.x1, 2), round(self.y1, 2), round(self.x2, 2), round(self.y2, 2))
|
||||
|
||||
@property
|
||||
def text(self):
|
||||
|
|
@ -300,11 +276,12 @@ class Cell(object):
|
|||
|
||||
@text.setter
|
||||
def text(self, t):
|
||||
self._text = "".join([self._text, t])
|
||||
self._text = ''.join([self._text, t])
|
||||
|
||||
@property
|
||||
def bound(self):
|
||||
"""The number of sides on which the cell is bounded."""
|
||||
"""The number of sides on which the cell is bounded.
|
||||
"""
|
||||
return self.top + self.bottom + self.left + self.right
|
||||
|
||||
|
||||
|
|
@ -336,11 +313,11 @@ class Table(object):
|
|||
PDF page number.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, cols, rows):
|
||||
self.cols = cols
|
||||
self.rows = rows
|
||||
self.cells = [[Cell(c[0], r[1], c[1], r[0]) for c in cols] for r in rows]
|
||||
self.cells = [[Cell(c[0], r[1], c[1], r[0])
|
||||
for c in cols] for r in rows]
|
||||
self.df = None
|
||||
self.shape = (0, 0)
|
||||
self.accuracy = 0
|
||||
|
|
@ -349,18 +326,12 @@ class Table(object):
|
|||
self.page = None
|
||||
|
||||
def __repr__(self):
|
||||
return f"<{self.__class__.__name__} shape={self.shape}>"
|
||||
|
||||
def __lt__(self, other):
|
||||
if self.page == other.page:
|
||||
if self.order < other.order:
|
||||
return True
|
||||
if self.page < other.page:
|
||||
return True
|
||||
return '<{} shape={}>'.format(self.__class__.__name__, self.shape)
|
||||
|
||||
@property
|
||||
def data(self):
|
||||
"""Returns two-dimensional list of strings in table."""
|
||||
"""Returns two-dimensional list of strings in table.
|
||||
"""
|
||||
d = []
|
||||
for row in self.cells:
|
||||
d.append([cell.text.strip() for cell in row])
|
||||
|
|
@ -373,21 +344,22 @@ class Table(object):
|
|||
"""
|
||||
# pretty?
|
||||
report = {
|
||||
"accuracy": round(self.accuracy, 2),
|
||||
"whitespace": round(self.whitespace, 2),
|
||||
"order": self.order,
|
||||
"page": self.page,
|
||||
'accuracy': round(self.accuracy, 2),
|
||||
'whitespace': round(self.whitespace, 2),
|
||||
'order': self.order,
|
||||
'page': self.page
|
||||
}
|
||||
return report
|
||||
|
||||
def set_all_edges(self):
|
||||
"""Sets all table edges to True."""
|
||||
"""Sets all table edges to True.
|
||||
"""
|
||||
for row in self.cells:
|
||||
for cell in row:
|
||||
cell.left = cell.right = cell.top = cell.bottom = True
|
||||
return self
|
||||
|
||||
def set_edges(self, vertical, horizontal, joint_tol=2):
|
||||
def set_edges(self, vertical, horizontal, joint_close_tol=2):
|
||||
"""Sets a cell's edges to True depending on whether the cell's
|
||||
coordinates overlap with the line's coordinates within a
|
||||
tolerance.
|
||||
|
|
@ -403,21 +375,12 @@ class Table(object):
|
|||
for v in vertical:
|
||||
# find closest x coord
|
||||
# iterate over y coords and find closest start and end points
|
||||
i = [
|
||||
i
|
||||
for i, t in enumerate(self.cols)
|
||||
if np.isclose(v[0], t[0], atol=joint_tol)
|
||||
]
|
||||
j = [
|
||||
j
|
||||
for j, t in enumerate(self.rows)
|
||||
if np.isclose(v[3], t[0], atol=joint_tol)
|
||||
]
|
||||
k = [
|
||||
k
|
||||
for k, t in enumerate(self.rows)
|
||||
if np.isclose(v[1], t[0], atol=joint_tol)
|
||||
]
|
||||
i = [i for i, t in enumerate(self.cols)
|
||||
if np.isclose(v[0], t[0], atol=joint_close_tol)]
|
||||
j = [j for j, t in enumerate(self.rows)
|
||||
if np.isclose(v[3], t[0], atol=joint_close_tol)]
|
||||
k = [k for k, t in enumerate(self.rows)
|
||||
if np.isclose(v[1], t[0], atol=joint_close_tol)]
|
||||
if not j:
|
||||
continue
|
||||
J = j[0]
|
||||
|
|
@ -463,21 +426,12 @@ class Table(object):
|
|||
for h in horizontal:
|
||||
# find closest y coord
|
||||
# iterate over x coords and find closest start and end points
|
||||
i = [
|
||||
i
|
||||
for i, t in enumerate(self.rows)
|
||||
if np.isclose(h[1], t[0], atol=joint_tol)
|
||||
]
|
||||
j = [
|
||||
j
|
||||
for j, t in enumerate(self.cols)
|
||||
if np.isclose(h[0], t[0], atol=joint_tol)
|
||||
]
|
||||
k = [
|
||||
k
|
||||
for k, t in enumerate(self.cols)
|
||||
if np.isclose(h[2], t[0], atol=joint_tol)
|
||||
]
|
||||
i = [i for i, t in enumerate(self.rows)
|
||||
if np.isclose(h[1], t[0], atol=joint_close_tol)]
|
||||
j = [j for j, t in enumerate(self.cols)
|
||||
if np.isclose(h[0], t[0], atol=joint_close_tol)]
|
||||
k = [k for k, t in enumerate(self.cols)
|
||||
if np.isclose(h[2], t[0], atol=joint_close_tol)]
|
||||
if not j:
|
||||
continue
|
||||
J = j[0]
|
||||
|
|
@ -523,7 +477,8 @@ class Table(object):
|
|||
return self
|
||||
|
||||
def set_border(self):
|
||||
"""Sets table border edges to True."""
|
||||
"""Sets table border edges to True.
|
||||
"""
|
||||
for r in range(len(self.rows)):
|
||||
self.cells[r][0].left = True
|
||||
self.cells[r][len(self.cols) - 1].right = True
|
||||
|
|
@ -574,7 +529,12 @@ class Table(object):
|
|||
Output filepath.
|
||||
|
||||
"""
|
||||
kw = {"encoding": "utf-8", "index": False, "header": False, "quoting": 1}
|
||||
kw = {
|
||||
'encoding': 'utf-8',
|
||||
'index': False,
|
||||
'header': False,
|
||||
'quoting': 1
|
||||
}
|
||||
kw.update(kwargs)
|
||||
self.df.to_csv(path, **kw)
|
||||
|
||||
|
|
@ -589,10 +549,12 @@ class Table(object):
|
|||
Output filepath.
|
||||
|
||||
"""
|
||||
kw = {"orient": "records"}
|
||||
kw = {
|
||||
'orient': 'records'
|
||||
}
|
||||
kw.update(kwargs)
|
||||
json_string = self.df.to_json(**kw)
|
||||
with open(path, "w") as f:
|
||||
with open(path, 'w') as f:
|
||||
f.write(json_string)
|
||||
|
||||
def to_excel(self, path, **kwargs):
|
||||
|
|
@ -607,8 +569,8 @@ class Table(object):
|
|||
|
||||
"""
|
||||
kw = {
|
||||
"sheet_name": f"page-{self.page}-table-{self.order}",
|
||||
"encoding": "utf-8",
|
||||
'sheet_name': 'page-{}-table-{}'.format(self.page, self.order),
|
||||
'encoding': 'utf-8'
|
||||
}
|
||||
kw.update(kwargs)
|
||||
writer = pd.ExcelWriter(path)
|
||||
|
|
@ -627,43 +589,9 @@ class Table(object):
|
|||
|
||||
"""
|
||||
html_string = self.df.to_html(**kwargs)
|
||||
with open(path, "w", encoding="utf-8") as f:
|
||||
with open(path, 'w') as f:
|
||||
f.write(html_string)
|
||||
|
||||
def to_markdown(self, path, **kwargs):
|
||||
"""Writes Table to a Markdown file.
|
||||
|
||||
For kwargs, check :meth:`pandas.DataFrame.to_markdown`.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
path : str
|
||||
Output filepath.
|
||||
|
||||
"""
|
||||
md_string = self.df.to_markdown(**kwargs)
|
||||
with open(path, "w", encoding="utf-8") as f:
|
||||
f.write(md_string)
|
||||
|
||||
def to_sqlite(self, path, **kwargs):
|
||||
"""Writes Table to sqlite database.
|
||||
|
||||
For kwargs, check :meth:`pandas.DataFrame.to_sql`.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
path : str
|
||||
Output filepath.
|
||||
|
||||
"""
|
||||
kw = {"if_exists": "replace", "index": False}
|
||||
kw.update(kwargs)
|
||||
conn = sqlite3.connect(path)
|
||||
table_name = f"page-{self.page}-table-{self.order}"
|
||||
self.df.to_sql(table_name, conn, **kw)
|
||||
conn.commit()
|
||||
conn.close()
|
||||
|
||||
|
||||
class TableList(object):
|
||||
"""Defines a list of camelot.core.Table objects. Each table can
|
||||
|
|
@ -675,12 +603,12 @@ class TableList(object):
|
|||
Number of tables in the list.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, tables):
|
||||
self._tables = tables
|
||||
|
||||
def __repr__(self):
|
||||
return f"<{self.__class__.__name__} n={self.n}>"
|
||||
return '<{} n={}>'.format(
|
||||
self.__class__.__name__, self.n)
|
||||
|
||||
def __len__(self):
|
||||
return len(self._tables)
|
||||
|
|
@ -690,35 +618,37 @@ class TableList(object):
|
|||
|
||||
@staticmethod
|
||||
def _format_func(table, f):
|
||||
return getattr(table, f"to_{f}")
|
||||
return getattr(table, 'to_{}'.format(f))
|
||||
|
||||
@property
|
||||
def n(self):
|
||||
return len(self)
|
||||
|
||||
def _write_file(self, f=None, **kwargs):
|
||||
dirname = kwargs.get("dirname")
|
||||
root = kwargs.get("root")
|
||||
ext = kwargs.get("ext")
|
||||
dirname = kwargs.get('dirname')
|
||||
root = kwargs.get('root')
|
||||
ext = kwargs.get('ext')
|
||||
for table in self._tables:
|
||||
filename = f"{root}-page-{table.page}-table-{table.order}{ext}"
|
||||
filename = os.path.join('{}-page-{}-table-{}{}'.format(
|
||||
root, table.page, table.order, ext))
|
||||
filepath = os.path.join(dirname, filename)
|
||||
to_format = self._format_func(table, f)
|
||||
to_format(filepath)
|
||||
|
||||
def _compress_dir(self, **kwargs):
|
||||
path = kwargs.get("path")
|
||||
dirname = kwargs.get("dirname")
|
||||
root = kwargs.get("root")
|
||||
ext = kwargs.get("ext")
|
||||
zipname = os.path.join(os.path.dirname(path), root) + ".zip"
|
||||
with zipfile.ZipFile(zipname, "w", allowZip64=True) as z:
|
||||
path = kwargs.get('path')
|
||||
dirname = kwargs.get('dirname')
|
||||
root = kwargs.get('root')
|
||||
ext = kwargs.get('ext')
|
||||
zipname = os.path.join(os.path.dirname(path), root) + '.zip'
|
||||
with zipfile.ZipFile(zipname, 'w', allowZip64=True) as z:
|
||||
for table in self._tables:
|
||||
filename = f"{root}-page-{table.page}-table-{table.order}{ext}"
|
||||
filename = os.path.join('{}-page-{}-table-{}{}'.format(
|
||||
root, table.page, table.order, ext))
|
||||
filepath = os.path.join(dirname, filename)
|
||||
z.write(filepath, os.path.basename(filepath))
|
||||
|
||||
def export(self, path, f="csv", compress=False):
|
||||
def export(self, path, f='csv', compress=False):
|
||||
"""Exports the list of tables to specified file format.
|
||||
|
||||
Parameters
|
||||
|
|
@ -726,7 +656,7 @@ class TableList(object):
|
|||
path : str
|
||||
Output filepath.
|
||||
f : str
|
||||
File format. Can be csv, excel, html, json, markdown or sqlite.
|
||||
File format. Can be csv, json, excel and html.
|
||||
compress : bool
|
||||
Whether or not to add files to a ZIP archive.
|
||||
|
||||
|
|
@ -737,28 +667,25 @@ class TableList(object):
|
|||
if compress:
|
||||
dirname = tempfile.mkdtemp()
|
||||
|
||||
kwargs = {"path": path, "dirname": dirname, "root": root, "ext": ext}
|
||||
kwargs = {
|
||||
'path': path,
|
||||
'dirname': dirname,
|
||||
'root': root,
|
||||
'ext': ext
|
||||
}
|
||||
|
||||
if f in ["csv", "html", "json", "markdown"]:
|
||||
if f in ['csv', 'json', 'html']:
|
||||
self._write_file(f=f, **kwargs)
|
||||
if compress:
|
||||
self._compress_dir(**kwargs)
|
||||
elif f == "excel":
|
||||
elif f == 'excel':
|
||||
filepath = os.path.join(dirname, basename)
|
||||
writer = pd.ExcelWriter(filepath)
|
||||
for table in self._tables:
|
||||
sheet_name = f"page-{table.page}-table-{table.order}"
|
||||
table.df.to_excel(writer, sheet_name=sheet_name, encoding="utf-8")
|
||||
sheet_name = 'page-{}-table-{}'.format(table.page, table.order)
|
||||
table.df.to_excel(writer, sheet_name=sheet_name, encoding='utf-8')
|
||||
writer.save()
|
||||
if compress:
|
||||
zipname = os.path.join(os.path.dirname(path), root) + ".zip"
|
||||
with zipfile.ZipFile(zipname, "w", allowZip64=True) as z:
|
||||
z.write(filepath, os.path.basename(filepath))
|
||||
elif f == "sqlite":
|
||||
filepath = os.path.join(dirname, basename)
|
||||
for table in self._tables:
|
||||
table.to_sqlite(filepath)
|
||||
if compress:
|
||||
zipname = os.path.join(os.path.dirname(path), root) + ".zip"
|
||||
with zipfile.ZipFile(zipname, "w", allowZip64=True) as z:
|
||||
zipname = os.path.join(os.path.dirname(path), root) + '.zip'
|
||||
with zipfile.ZipFile(zipname, 'w', allowZip64=True) as z:
|
||||
z.write(filepath, os.path.basename(filepath))
|
||||
|
|
|
|||
|
|
@ -7,14 +7,8 @@ from PyPDF2 import PdfFileReader, PdfFileWriter
|
|||
|
||||
from .core import TableList
|
||||
from .parsers import Stream, Lattice
|
||||
from .utils import (
|
||||
TemporaryDirectory,
|
||||
get_page_layout,
|
||||
get_text_objects,
|
||||
get_rotation,
|
||||
is_url,
|
||||
download_url,
|
||||
)
|
||||
from .utils import (TemporaryDirectory, get_page_layout, get_text_objects,
|
||||
get_rotation)
|
||||
|
||||
|
||||
class PDFHandler(object):
|
||||
|
|
@ -24,41 +18,37 @@ class PDFHandler(object):
|
|||
|
||||
Parameters
|
||||
----------
|
||||
filepath : str
|
||||
Filepath or URL of the PDF file.
|
||||
filename : str
|
||||
Path to PDF file.
|
||||
pages : str, optional (default: '1')
|
||||
Comma-separated page numbers.
|
||||
Example: '1,3,4' or '1,4-end' or 'all'.
|
||||
Example: '1,3,4' or '1,4-end'.
|
||||
password : str, optional (default: None)
|
||||
Password for decryption.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, filepath, pages="1", password=None):
|
||||
if is_url(filepath):
|
||||
filepath = download_url(filepath)
|
||||
self.filepath = filepath
|
||||
# if not filepath.lower().endswith(".pdf"):
|
||||
# raise NotImplementedError("File format not supported")
|
||||
|
||||
def __init__(self, filename, pages='1', password=None):
|
||||
self.filename = filename
|
||||
if not filename.lower().endswith('.pdf'):
|
||||
raise NotImplementedError("File format not supported")
|
||||
self.pages = self._get_pages(self.filename, pages)
|
||||
if password is None:
|
||||
self.password = ""
|
||||
self.password = ''
|
||||
else:
|
||||
self.password = password
|
||||
if sys.version_info[0] < 3:
|
||||
self.password = self.password.encode("ascii")
|
||||
self.pages = self._get_pages(pages)
|
||||
self.password = self.password.encode('ascii')
|
||||
|
||||
def _get_pages(self, pages):
|
||||
def _get_pages(self, filename, pages):
|
||||
"""Converts pages string to list of ints.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
filepath : str
|
||||
Filepath or URL of the PDF file.
|
||||
filename : str
|
||||
Path to PDF file.
|
||||
pages : str, optional (default: '1')
|
||||
Comma-separated page numbers.
|
||||
Example: '1,3,4' or '1,4-end' or 'all'.
|
||||
Example: 1,3,4 or 1,4-end.
|
||||
|
||||
Returns
|
||||
-------
|
||||
|
|
@ -67,84 +57,75 @@ class PDFHandler(object):
|
|||
|
||||
"""
|
||||
page_numbers = []
|
||||
|
||||
if pages == "1":
|
||||
page_numbers.append({"start": 1, "end": 1})
|
||||
if pages == '1':
|
||||
page_numbers.append({'start': 1, 'end': 1})
|
||||
else:
|
||||
with open(self.filepath, "rb") as f:
|
||||
infile = PdfFileReader(f, strict=False)
|
||||
|
||||
if infile.isEncrypted:
|
||||
infile.decrypt(self.password)
|
||||
|
||||
if pages == "all":
|
||||
page_numbers.append({"start": 1, "end": infile.getNumPages()})
|
||||
else:
|
||||
for r in pages.split(","):
|
||||
if "-" in r:
|
||||
a, b = r.split("-")
|
||||
if b == "end":
|
||||
b = infile.getNumPages()
|
||||
page_numbers.append({"start": int(a), "end": int(b)})
|
||||
else:
|
||||
page_numbers.append({"start": int(r), "end": int(r)})
|
||||
|
||||
infile = PdfFileReader(open(filename, 'rb'), strict=False)
|
||||
if infile.isEncrypted:
|
||||
infile.decrypt(self.password)
|
||||
if pages == 'all':
|
||||
page_numbers.append({'start': 1, 'end': infile.getNumPages()})
|
||||
else:
|
||||
for r in pages.split(','):
|
||||
if '-' in r:
|
||||
a, b = r.split('-')
|
||||
if b == 'end':
|
||||
b = infile.getNumPages()
|
||||
page_numbers.append({'start': int(a), 'end': int(b)})
|
||||
else:
|
||||
page_numbers.append({'start': int(r), 'end': int(r)})
|
||||
P = []
|
||||
for p in page_numbers:
|
||||
P.extend(range(p["start"], p["end"] + 1))
|
||||
P.extend(range(p['start'], p['end'] + 1))
|
||||
return sorted(set(P))
|
||||
|
||||
def _save_page(self, filepath, page, temp):
|
||||
def _save_page(self, filename, page, temp):
|
||||
"""Saves specified page from PDF into a temporary directory.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
filepath : str
|
||||
Filepath or URL of the PDF file.
|
||||
filename : str
|
||||
Path to PDF file.
|
||||
page : int
|
||||
Page number.
|
||||
temp : str
|
||||
Tmp directory.
|
||||
|
||||
"""
|
||||
with open(filepath, "rb") as fileobj:
|
||||
with open(filename, 'rb') as fileobj:
|
||||
infile = PdfFileReader(fileobj, strict=False)
|
||||
if infile.isEncrypted:
|
||||
infile.decrypt(self.password)
|
||||
fpath = os.path.join(temp, f"page-{page}.pdf")
|
||||
fpath = os.path.join(temp, 'page-{0}.pdf'.format(page))
|
||||
froot, fext = os.path.splitext(fpath)
|
||||
p = infile.getPage(page - 1)
|
||||
outfile = PdfFileWriter()
|
||||
outfile.addPage(p)
|
||||
with open(fpath, "wb") as f:
|
||||
with open(fpath, 'wb') as f:
|
||||
outfile.write(f)
|
||||
layout, dim = get_page_layout(fpath)
|
||||
# fix rotated PDF
|
||||
chars = get_text_objects(layout, ltype="char")
|
||||
horizontal_text = get_text_objects(layout, ltype="horizontal_text")
|
||||
vertical_text = get_text_objects(layout, ltype="vertical_text")
|
||||
rotation = get_rotation(chars, horizontal_text, vertical_text)
|
||||
if rotation != "":
|
||||
fpath_new = "".join([froot.replace("page", "p"), "_rotated", fext])
|
||||
lttextlh = get_text_objects(layout, ltype="lh")
|
||||
lttextlv = get_text_objects(layout, ltype="lv")
|
||||
ltchar = get_text_objects(layout, ltype="char")
|
||||
rotation = get_rotation(lttextlh, lttextlv, ltchar)
|
||||
if rotation != '':
|
||||
fpath_new = ''.join([froot.replace('page', 'p'), '_rotated', fext])
|
||||
os.rename(fpath, fpath_new)
|
||||
instream = open(fpath_new, "rb")
|
||||
infile = PdfFileReader(instream, strict=False)
|
||||
infile = PdfFileReader(open(fpath_new, 'rb'), strict=False)
|
||||
if infile.isEncrypted:
|
||||
infile.decrypt(self.password)
|
||||
outfile = PdfFileWriter()
|
||||
p = infile.getPage(0)
|
||||
if rotation == "anticlockwise":
|
||||
if rotation == 'anticlockwise':
|
||||
p.rotateClockwise(90)
|
||||
elif rotation == "clockwise":
|
||||
elif rotation == 'clockwise':
|
||||
p.rotateCounterClockwise(90)
|
||||
outfile.addPage(p)
|
||||
with open(fpath, "wb") as f:
|
||||
with open(fpath, 'wb') as f:
|
||||
outfile.write(f)
|
||||
instream.close()
|
||||
|
||||
def parse(
|
||||
self, flavor="lattice", suppress_stdout=False, layout_kwargs={}, **kwargs
|
||||
):
|
||||
def parse(self, flavor='lattice', suppress_stdout=False, **kwargs):
|
||||
"""Extracts tables by calling parser.get_tables on all single
|
||||
page PDFs.
|
||||
|
||||
|
|
@ -155,8 +136,6 @@ class PDFHandler(object):
|
|||
Lattice is used by default.
|
||||
suppress_stdout : str (default: False)
|
||||
Suppress logs and warnings.
|
||||
layout_kwargs : dict, optional (default: {})
|
||||
A dict of `pdfminer.layout.LAParams <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ kwargs.
|
||||
kwargs : dict
|
||||
See camelot.read_pdf kwargs.
|
||||
|
||||
|
|
@ -169,12 +148,11 @@ class PDFHandler(object):
|
|||
tables = []
|
||||
with TemporaryDirectory() as tempdir:
|
||||
for p in self.pages:
|
||||
self._save_page(self.filepath, p, tempdir)
|
||||
pages = [os.path.join(tempdir, f"page-{p}.pdf") for p in self.pages]
|
||||
parser = Lattice(**kwargs) if flavor == "lattice" else Stream(**kwargs)
|
||||
self._save_page(self.filename, p, tempdir)
|
||||
pages = [os.path.join(tempdir, 'page-{0}.pdf'.format(p))
|
||||
for p in self.pages]
|
||||
parser = Lattice(**kwargs) if flavor == 'lattice' else Stream(**kwargs)
|
||||
for p in pages:
|
||||
t = parser.extract_tables(
|
||||
p, suppress_stdout=suppress_stdout, layout_kwargs=layout_kwargs
|
||||
)
|
||||
t = parser.extract_tables(p, suppress_stdout=suppress_stdout)
|
||||
tables.extend(t)
|
||||
return TableList(sorted(tables))
|
||||
return TableList(tables)
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
from __future__ import division
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
|
|
@ -37,23 +39,16 @@ def adaptive_threshold(imagename, process_background=False, blocksize=15, c=-2):
|
|||
|
||||
if process_background:
|
||||
threshold = cv2.adaptiveThreshold(
|
||||
gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, blocksize, c
|
||||
)
|
||||
gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
|
||||
cv2.THRESH_BINARY, blocksize, c)
|
||||
else:
|
||||
threshold = cv2.adaptiveThreshold(
|
||||
np.invert(gray),
|
||||
255,
|
||||
cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
|
||||
cv2.THRESH_BINARY,
|
||||
blocksize,
|
||||
c,
|
||||
)
|
||||
np.invert(gray), 255,
|
||||
cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, blocksize, c)
|
||||
return img, threshold
|
||||
|
||||
|
||||
def find_lines(
|
||||
threshold, regions=None, direction="horizontal", line_scale=15, iterations=0
|
||||
):
|
||||
def find_lines(threshold, direction='horizontal', line_size_scaling=15, iterations=0):
|
||||
"""Finds horizontal and vertical lines by applying morphological
|
||||
transformations on an image.
|
||||
|
||||
|
|
@ -61,13 +56,9 @@ def find_lines(
|
|||
----------
|
||||
threshold : object
|
||||
numpy.ndarray representing the thresholded image.
|
||||
regions : list, optional (default: None)
|
||||
List of page regions that may contain tables of the form x1,y1,x2,y2
|
||||
where (x1, y1) -> left-top and (x2, y2) -> right-bottom
|
||||
in image coordinate space.
|
||||
direction : string, optional (default: 'horizontal')
|
||||
Specifies whether to find vertical or horizontal lines.
|
||||
line_scale : int, optional (default: 15)
|
||||
line_size_scaling : int, optional (default: 15)
|
||||
Factor by which the page dimensions will be divided to get
|
||||
smallest length of lines that should be detected.
|
||||
|
||||
|
|
@ -91,21 +82,15 @@ def find_lines(
|
|||
"""
|
||||
lines = []
|
||||
|
||||
if direction == "vertical":
|
||||
size = threshold.shape[0] // line_scale
|
||||
if direction == 'vertical':
|
||||
size = threshold.shape[0] // line_size_scaling
|
||||
el = cv2.getStructuringElement(cv2.MORPH_RECT, (1, size))
|
||||
elif direction == "horizontal":
|
||||
size = threshold.shape[1] // line_scale
|
||||
elif direction == 'horizontal':
|
||||
size = threshold.shape[1] // line_size_scaling
|
||||
el = cv2.getStructuringElement(cv2.MORPH_RECT, (size, 1))
|
||||
elif direction is None:
|
||||
raise ValueError("Specify direction as either 'vertical' or 'horizontal'")
|
||||
|
||||
if regions is not None:
|
||||
region_mask = np.zeros(threshold.shape)
|
||||
for region in regions:
|
||||
x, y, w, h = region
|
||||
region_mask[y : y + h, x : x + w] = 1
|
||||
threshold = np.multiply(threshold, region_mask)
|
||||
raise ValueError("Specify direction as either 'vertical' or"
|
||||
" 'horizontal'")
|
||||
|
||||
threshold = cv2.erode(threshold, el)
|
||||
threshold = cv2.dilate(threshold, el)
|
||||
|
|
@ -113,27 +98,25 @@ def find_lines(
|
|||
|
||||
try:
|
||||
_, contours, _ = cv2.findContours(
|
||||
threshold.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
|
||||
)
|
||||
threshold, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
||||
except ValueError:
|
||||
# for opencv backward compatibility
|
||||
contours, _ = cv2.findContours(
|
||||
threshold.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
|
||||
)
|
||||
threshold, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
||||
|
||||
for c in contours:
|
||||
x, y, w, h = cv2.boundingRect(c)
|
||||
x1, x2 = x, x + w
|
||||
y1, y2 = y, y + h
|
||||
if direction == "vertical":
|
||||
if direction == 'vertical':
|
||||
lines.append(((x1 + x2) // 2, y2, (x1 + x2) // 2, y1))
|
||||
elif direction == "horizontal":
|
||||
elif direction == 'horizontal':
|
||||
lines.append((x1, (y1 + y2) // 2, x2, (y1 + y2) // 2))
|
||||
|
||||
return dmask, lines
|
||||
|
||||
|
||||
def find_contours(vertical, horizontal):
|
||||
def find_table_contours(vertical, horizontal):
|
||||
"""Finds table boundaries using OpenCV's findContours.
|
||||
|
||||
Parameters
|
||||
|
|
@ -155,14 +138,11 @@ def find_contours(vertical, horizontal):
|
|||
|
||||
try:
|
||||
__, contours, __ = cv2.findContours(
|
||||
mask.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
|
||||
)
|
||||
mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
||||
except ValueError:
|
||||
# for opencv backward compatibility
|
||||
contours, __ = cv2.findContours(
|
||||
mask.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
|
||||
)
|
||||
# sort in reverse based on contour area and use first 10 contours
|
||||
mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
||||
contours = sorted(contours, key=cv2.contourArea, reverse=True)[:10]
|
||||
|
||||
cont = []
|
||||
|
|
@ -173,7 +153,7 @@ def find_contours(vertical, horizontal):
|
|||
return cont
|
||||
|
||||
|
||||
def find_joints(contours, vertical, horizontal):
|
||||
def find_table_joints(contours, vertical, horizontal):
|
||||
"""Finds joints/intersections present inside each table boundary.
|
||||
|
||||
Parameters
|
||||
|
|
@ -196,20 +176,18 @@ def find_joints(contours, vertical, horizontal):
|
|||
and (x2, y2) -> rt in image coordinate space.
|
||||
|
||||
"""
|
||||
joints = np.multiply(vertical, horizontal)
|
||||
joints = np.bitwise_and(vertical, horizontal)
|
||||
tables = {}
|
||||
for c in contours:
|
||||
x, y, w, h = c
|
||||
roi = joints[y : y + h, x : x + w]
|
||||
try:
|
||||
__, jc, __ = cv2.findContours(
|
||||
roi.astype(np.uint8), cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE
|
||||
)
|
||||
roi, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
|
||||
except ValueError:
|
||||
# for opencv backward compatibility
|
||||
jc, __ = cv2.findContours(
|
||||
roi.astype(np.uint8), cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE
|
||||
)
|
||||
roi, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
|
||||
if len(jc) <= 4: # remove contours with less than 4 joints
|
||||
continue
|
||||
joint_coords = []
|
||||
|
|
|
|||
|
|
@ -1,20 +1,12 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import warnings
|
||||
|
||||
from .handlers import PDFHandler
|
||||
from .utils import validate_input, remove_extra
|
||||
|
||||
|
||||
def read_pdf(
|
||||
filepath,
|
||||
pages="1",
|
||||
password=None,
|
||||
flavor="lattice",
|
||||
suppress_stdout=False,
|
||||
layout_kwargs={},
|
||||
**kwargs
|
||||
):
|
||||
def read_pdf(filepath, pages='1', password=None, flavor='lattice',
|
||||
suppress_stdout=False, **kwargs):
|
||||
"""Read PDF and return extracted tables.
|
||||
|
||||
Note: kwargs annotated with ^ can only be used with flavor='stream'
|
||||
|
|
@ -23,10 +15,10 @@ def read_pdf(
|
|||
Parameters
|
||||
----------
|
||||
filepath : str
|
||||
Filepath or URL of the PDF file.
|
||||
Path to PDF file.
|
||||
pages : str, optional (default: '1')
|
||||
Comma-separated page numbers.
|
||||
Example: '1,3,4' or '1,4-end' or 'all'.
|
||||
Example: '1,3,4' or '1,4-end'.
|
||||
password : str, optional (default: None)
|
||||
Password for decryption.
|
||||
flavor : str (default: 'lattice')
|
||||
|
|
@ -34,8 +26,6 @@ def read_pdf(
|
|||
Lattice is used by default.
|
||||
suppress_stdout : bool, optional (default: True)
|
||||
Print all logs and warnings.
|
||||
layout_kwargs : dict, optional (default: {})
|
||||
A dict of `pdfminer.layout.LAParams <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ kwargs.
|
||||
table_areas : list, optional (default: None)
|
||||
List of table area strings of the form x1,y1,x2,y2
|
||||
where (x1, y1) -> left-top and (x2, y2) -> right-bottom
|
||||
|
|
@ -48,18 +38,15 @@ def read_pdf(
|
|||
flag_size : bool, optional (default: False)
|
||||
Flag text based on font size. Useful to detect
|
||||
super/subscripts. Adds <s></s> around flagged text.
|
||||
strip_text : str, optional (default: '')
|
||||
Characters that should be stripped from a string before
|
||||
assigning it to a cell.
|
||||
row_tol^ : int, optional (default: 2)
|
||||
row_close_tol^ : int, optional (default: 2)
|
||||
Tolerance parameter used to combine text vertically,
|
||||
to generate rows.
|
||||
column_tol^ : int, optional (default: 0)
|
||||
col_close_tol^ : int, optional (default: 0)
|
||||
Tolerance parameter used to combine text horizontally,
|
||||
to generate columns.
|
||||
process_background* : bool, optional (default: False)
|
||||
Process background lines.
|
||||
line_scale* : int, optional (default: 15)
|
||||
line_size_scaling* : int, optional (default: 15)
|
||||
Line size scaling factor. The larger the value the smaller
|
||||
the detected lines. Making it very large will lead to text
|
||||
being detected as lines.
|
||||
|
|
@ -70,10 +57,10 @@ def read_pdf(
|
|||
shift_text* : list, optional (default: ['l', 't'])
|
||||
{'l', 'r', 't', 'b'}
|
||||
Direction in which text in a spanning cell will flow.
|
||||
line_tol* : int, optional (default: 2)
|
||||
line_close_tol* : int, optional (default: 2)
|
||||
Tolerance parameter used to merge close vertical and horizontal
|
||||
lines.
|
||||
joint_tol* : int, optional (default: 2)
|
||||
joint_close_tol* : int, optional (default: 2)
|
||||
Tolerance parameter used to decide whether the detected lines
|
||||
and points lie close to each other.
|
||||
threshold_blocksize* : int, optional (default: 15)
|
||||
|
|
@ -90,18 +77,19 @@ def read_pdf(
|
|||
Number of times for erosion/dilation is applied.
|
||||
|
||||
For more information, refer `OpenCV's dilate <https://docs.opencv.org/2.4/modules/imgproc/doc/filtering.html#dilate>`_.
|
||||
resolution* : int, optional (default: 300)
|
||||
Resolution used for PDF to PNG conversion.
|
||||
margins : tuple
|
||||
PDFMiner char_margin, line_margin and word_margin.
|
||||
|
||||
For more information, refer `PDFMiner docs <https://euske.github.io/pdfminer/>`_.
|
||||
|
||||
Returns
|
||||
-------
|
||||
tables : camelot.core.TableList
|
||||
|
||||
"""
|
||||
if flavor not in ["lattice", "stream"]:
|
||||
raise NotImplementedError(
|
||||
"Unknown flavor specified." " Use either 'lattice' or 'stream'"
|
||||
)
|
||||
if flavor not in ['lattice', 'stream']:
|
||||
raise NotImplementedError("Unknown flavor specified."
|
||||
" Use either 'lattice' or 'stream'")
|
||||
|
||||
with warnings.catch_warnings():
|
||||
if suppress_stdout:
|
||||
|
|
@ -110,10 +98,5 @@ def read_pdf(
|
|||
validate_input(kwargs, flavor=flavor)
|
||||
p = PDFHandler(filepath, pages=pages, password=password)
|
||||
kwargs = remove_extra(kwargs, flavor=flavor)
|
||||
tables = p.parse(
|
||||
flavor=flavor,
|
||||
suppress_stdout=suppress_stdout,
|
||||
layout_kwargs=layout_kwargs,
|
||||
**kwargs
|
||||
)
|
||||
tables = p.parse(flavor=flavor, suppress_stdout=suppress_stdout, **kwargs)
|
||||
return tables
|
||||
|
|
|
|||
|
|
@ -6,15 +6,16 @@ from ..utils import get_page_layout, get_text_objects
|
|||
|
||||
|
||||
class BaseParser(object):
|
||||
"""Defines a base parser."""
|
||||
|
||||
def _generate_layout(self, filename, layout_kwargs):
|
||||
"""Defines a base parser.
|
||||
"""
|
||||
def _generate_layout(self, filename):
|
||||
self.filename = filename
|
||||
self.layout_kwargs = layout_kwargs
|
||||
self.layout, self.dimensions = get_page_layout(filename, **layout_kwargs)
|
||||
self.images = get_text_objects(self.layout, ltype="image")
|
||||
self.horizontal_text = get_text_objects(self.layout, ltype="horizontal_text")
|
||||
self.vertical_text = get_text_objects(self.layout, ltype="vertical_text")
|
||||
self.layout, self.dimensions = get_page_layout(
|
||||
self.filename,
|
||||
char_margin=self.char_margin,
|
||||
line_margin=self.line_margin,
|
||||
word_margin=self.word_margin)
|
||||
self.horizontal_text = get_text_objects(self.layout, ltype="lh")
|
||||
self.vertical_text = get_text_objects(self.layout, ltype="lv")
|
||||
self.pdf_width, self.pdf_height = self.dimensions
|
||||
self.rootname, __ = os.path.splitext(self.filename)
|
||||
self.imagename = "".join([self.rootname, ".png"])
|
||||
|
|
|
|||
|
|
@ -1,37 +1,25 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
from __future__ import division
|
||||
import os
|
||||
import sys
|
||||
import copy
|
||||
import locale
|
||||
import logging
|
||||
import warnings
|
||||
import subprocess
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
from .base import BaseParser
|
||||
from ..core import Table
|
||||
from ..utils import (
|
||||
scale_image,
|
||||
scale_pdf,
|
||||
segments_in_bbox,
|
||||
text_in_bbox,
|
||||
merge_close_lines,
|
||||
get_table_index,
|
||||
compute_accuracy,
|
||||
compute_whitespace,
|
||||
)
|
||||
from ..image_processing import (
|
||||
adaptive_threshold,
|
||||
find_lines,
|
||||
find_contours,
|
||||
find_joints,
|
||||
)
|
||||
from ..backends.image_conversion import BACKENDS
|
||||
from ..utils import (scale_image, scale_pdf, segments_in_bbox, text_in_bbox,
|
||||
merge_close_lines, get_table_index, compute_accuracy,
|
||||
compute_whitespace)
|
||||
from ..image_processing import (adaptive_threshold, find_lines,
|
||||
find_table_contours, find_table_joints)
|
||||
|
||||
|
||||
logger = logging.getLogger("camelot")
|
||||
logger = logging.getLogger('camelot')
|
||||
|
||||
|
||||
class Lattice(BaseParser):
|
||||
|
|
@ -40,17 +28,13 @@ class Lattice(BaseParser):
|
|||
|
||||
Parameters
|
||||
----------
|
||||
table_regions : list, optional (default: None)
|
||||
List of page regions that may contain tables of the form x1,y1,x2,y2
|
||||
where (x1, y1) -> left-top and (x2, y2) -> right-bottom
|
||||
in PDF coordinate space.
|
||||
table_areas : list, optional (default: None)
|
||||
List of table area strings of the form x1,y1,x2,y2
|
||||
where (x1, y1) -> left-top and (x2, y2) -> right-bottom
|
||||
in PDF coordinate space.
|
||||
process_background : bool, optional (default: False)
|
||||
Process background lines.
|
||||
line_scale : int, optional (default: 15)
|
||||
line_size_scaling : int, optional (default: 15)
|
||||
Line size scaling factor. The larger the value the smaller
|
||||
the detected lines. Making it very large will lead to text
|
||||
being detected as lines.
|
||||
|
|
@ -66,13 +50,10 @@ class Lattice(BaseParser):
|
|||
flag_size : bool, optional (default: False)
|
||||
Flag text based on font size. Useful to detect
|
||||
super/subscripts. Adds <s></s> around flagged text.
|
||||
strip_text : str, optional (default: '')
|
||||
Characters that should be stripped from a string before
|
||||
assigning it to a cell.
|
||||
line_tol : int, optional (default: 2)
|
||||
line_close_tol : int, optional (default: 2)
|
||||
Tolerance parameter used to merge close vertical and horizontal
|
||||
lines.
|
||||
joint_tol : int, optional (default: 2)
|
||||
joint_close_tol : int, optional (default: 2)
|
||||
Tolerance parameter used to decide whether the detected lines
|
||||
and points lie close to each other.
|
||||
threshold_blocksize : int, optional (default: 15)
|
||||
|
|
@ -89,77 +70,30 @@ class Lattice(BaseParser):
|
|||
Number of times for erosion/dilation is applied.
|
||||
|
||||
For more information, refer `OpenCV's dilate <https://docs.opencv.org/2.4/modules/imgproc/doc/filtering.html#dilate>`_.
|
||||
resolution : int, optional (default: 300)
|
||||
Resolution used for PDF to PNG conversion.
|
||||
margins : tuple
|
||||
PDFMiner char_margin, line_margin and word_margin.
|
||||
|
||||
For more information, refer `PDFMiner docs <https://euske.github.io/pdfminer/>`_.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
table_regions=None,
|
||||
table_areas=None,
|
||||
process_background=False,
|
||||
line_scale=15,
|
||||
copy_text=None,
|
||||
shift_text=["l", "t"],
|
||||
split_text=False,
|
||||
flag_size=False,
|
||||
strip_text="",
|
||||
line_tol=2,
|
||||
joint_tol=2,
|
||||
threshold_blocksize=15,
|
||||
threshold_constant=-2,
|
||||
iterations=0,
|
||||
resolution=300,
|
||||
backend="ghostscript",
|
||||
**kwargs,
|
||||
):
|
||||
self.table_regions = table_regions
|
||||
def __init__(self, table_areas=None, process_background=False,
|
||||
line_size_scaling=15, copy_text=None, shift_text=['l', 't'],
|
||||
split_text=False, flag_size=False, line_close_tol=2,
|
||||
joint_close_tol=2, threshold_blocksize=15, threshold_constant=-2,
|
||||
iterations=0, margins=(1.0, 0.5, 0.1), **kwargs):
|
||||
self.table_areas = table_areas
|
||||
self.process_background = process_background
|
||||
self.line_scale = line_scale
|
||||
self.line_size_scaling = line_size_scaling
|
||||
self.copy_text = copy_text
|
||||
self.shift_text = shift_text
|
||||
self.split_text = split_text
|
||||
self.flag_size = flag_size
|
||||
self.strip_text = strip_text
|
||||
self.line_tol = line_tol
|
||||
self.joint_tol = joint_tol
|
||||
self.line_close_tol = line_close_tol
|
||||
self.joint_close_tol = joint_close_tol
|
||||
self.threshold_blocksize = threshold_blocksize
|
||||
self.threshold_constant = threshold_constant
|
||||
self.iterations = iterations
|
||||
self.resolution = resolution
|
||||
self.backend = Lattice._get_backend(backend)
|
||||
|
||||
@staticmethod
|
||||
def _get_backend(backend):
|
||||
def implements_convert():
|
||||
methods = [
|
||||
method for method in dir(backend) if method.startswith("__") is False
|
||||
]
|
||||
return "convert" in methods
|
||||
|
||||
if isinstance(backend, str):
|
||||
if backend not in BACKENDS.keys():
|
||||
raise NotImplementedError(
|
||||
f"Unknown backend '{backend}' specified. Please use either 'poppler' or 'ghostscript'."
|
||||
)
|
||||
|
||||
if backend == "ghostscript":
|
||||
warnings.warn(
|
||||
"'ghostscript' will be replaced by 'poppler' as the default image conversion"
|
||||
" backend in v0.12.0. You can try out 'poppler' with backend='poppler'.",
|
||||
DeprecationWarning,
|
||||
)
|
||||
|
||||
return BACKENDS[backend]()
|
||||
else:
|
||||
if not implements_convert():
|
||||
raise NotImplementedError(
|
||||
f"'{backend}' must implement a 'convert' method"
|
||||
)
|
||||
|
||||
return backend
|
||||
self.char_margin, self.line_margin, self.word_margin = margins
|
||||
|
||||
@staticmethod
|
||||
def _reduce_index(t, idx, shift_text):
|
||||
|
|
@ -187,19 +121,19 @@ class Lattice(BaseParser):
|
|||
indices = []
|
||||
for r_idx, c_idx, text in idx:
|
||||
for d in shift_text:
|
||||
if d == "l":
|
||||
if d == 'l':
|
||||
if t.cells[r_idx][c_idx].hspan:
|
||||
while not t.cells[r_idx][c_idx].left:
|
||||
c_idx -= 1
|
||||
if d == "r":
|
||||
if d == 'r':
|
||||
if t.cells[r_idx][c_idx].hspan:
|
||||
while not t.cells[r_idx][c_idx].right:
|
||||
c_idx += 1
|
||||
if d == "t":
|
||||
if d == 't':
|
||||
if t.cells[r_idx][c_idx].vspan:
|
||||
while not t.cells[r_idx][c_idx].top:
|
||||
r_idx -= 1
|
||||
if d == "b":
|
||||
if d == 'b':
|
||||
if t.cells[r_idx][c_idx].vspan:
|
||||
while not t.cells[r_idx][c_idx].bottom:
|
||||
r_idx += 1
|
||||
|
|
@ -228,37 +162,72 @@ class Lattice(BaseParser):
|
|||
if f == "h":
|
||||
for i in range(len(t.cells)):
|
||||
for j in range(len(t.cells[i])):
|
||||
if t.cells[i][j].text.strip() == "":
|
||||
if t.cells[i][j].text.strip() == '':
|
||||
if t.cells[i][j].hspan and not t.cells[i][j].left:
|
||||
t.cells[i][j].text = t.cells[i][j - 1].text
|
||||
elif f == "v":
|
||||
for i in range(len(t.cells)):
|
||||
for j in range(len(t.cells[i])):
|
||||
if t.cells[i][j].text.strip() == "":
|
||||
if t.cells[i][j].text.strip() == '':
|
||||
if t.cells[i][j].vspan and not t.cells[i][j].top:
|
||||
t.cells[i][j].text = t.cells[i - 1][j].text
|
||||
return t
|
||||
|
||||
def _generate_table_bbox(self):
|
||||
def scale_areas(areas):
|
||||
scaled_areas = []
|
||||
for area in areas:
|
||||
x1, y1, x2, y2 = area.split(",")
|
||||
x1 = float(x1)
|
||||
y1 = float(y1)
|
||||
x2 = float(x2)
|
||||
y2 = float(y2)
|
||||
x1, y1, x2, y2 = scale_pdf((x1, y1, x2, y2), image_scalers)
|
||||
scaled_areas.append((x1, y1, abs(x2 - x1), abs(y2 - y1)))
|
||||
return scaled_areas
|
||||
def _generate_image(self):
|
||||
# TODO: get rid of ghostscript #96
|
||||
def get_executable():
|
||||
import platform
|
||||
from distutils.spawn import find_executable
|
||||
|
||||
self.image, self.threshold = adaptive_threshold(
|
||||
class GhostscriptNotFound(Exception): pass
|
||||
|
||||
gs = None
|
||||
system = platform.system().lower()
|
||||
try:
|
||||
if system == 'windows':
|
||||
if find_executable('gswin32c.exe'):
|
||||
gs = 'gswin32c.exe'
|
||||
elif find_executable('gswin64c.exe'):
|
||||
gs = 'gswin64c.exe'
|
||||
else:
|
||||
raise ValueError
|
||||
else:
|
||||
if find_executable('gs'):
|
||||
gs = 'gs'
|
||||
elif find_executable('gsc'):
|
||||
gs = 'gsc'
|
||||
else:
|
||||
raise ValueError
|
||||
if 'ghostscript' not in subprocess.check_output(
|
||||
[gs, '-version']).decode('utf-8').lower():
|
||||
raise ValueError
|
||||
except ValueError:
|
||||
raise GhostscriptNotFound(
|
||||
'Please make sure that Ghostscript is installed'
|
||||
' and available on the PATH environment variable')
|
||||
|
||||
return gs
|
||||
|
||||
self.imagename = ''.join([self.rootname, '.png'])
|
||||
gs_call = [
|
||||
'-q',
|
||||
'-sDEVICE=png16m',
|
||||
'-o',
|
||||
self.imagename,
|
||||
process_background=self.process_background,
|
||||
blocksize=self.threshold_blocksize,
|
||||
c=self.threshold_constant,
|
||||
)
|
||||
'-r600',
|
||||
self.filename
|
||||
]
|
||||
gs = get_executable()
|
||||
gs_call.insert(0, gs)
|
||||
|
||||
subprocess.call(
|
||||
gs_call, stdout=open(os.devnull, 'w'),
|
||||
stderr=subprocess.STDOUT)
|
||||
|
||||
def _generate_table_bbox(self):
|
||||
self.image, self.threshold = adaptive_threshold(
|
||||
self.imagename, process_background=self.process_background,
|
||||
blocksize=self.threshold_blocksize, c=self.threshold_constant)
|
||||
image_width = self.image.shape[1]
|
||||
image_height = self.image.shape[0]
|
||||
image_width_scaler = image_width / float(self.pdf_width)
|
||||
|
|
@ -268,62 +237,43 @@ class Lattice(BaseParser):
|
|||
image_scalers = (image_width_scaler, image_height_scaler, self.pdf_height)
|
||||
pdf_scalers = (pdf_width_scaler, pdf_height_scaler, image_height)
|
||||
|
||||
if self.table_areas is None:
|
||||
regions = None
|
||||
if self.table_regions is not None:
|
||||
regions = scale_areas(self.table_regions)
|
||||
vertical_mask, vertical_segments = find_lines(
|
||||
self.threshold, direction='vertical',
|
||||
line_size_scaling=self.line_size_scaling, iterations=self.iterations)
|
||||
horizontal_mask, horizontal_segments = find_lines(
|
||||
self.threshold, direction='horizontal',
|
||||
line_size_scaling=self.line_size_scaling, iterations=self.iterations)
|
||||
|
||||
vertical_mask, vertical_segments = find_lines(
|
||||
self.threshold,
|
||||
regions=regions,
|
||||
direction="vertical",
|
||||
line_scale=self.line_scale,
|
||||
iterations=self.iterations,
|
||||
)
|
||||
horizontal_mask, horizontal_segments = find_lines(
|
||||
self.threshold,
|
||||
regions=regions,
|
||||
direction="horizontal",
|
||||
line_scale=self.line_scale,
|
||||
iterations=self.iterations,
|
||||
)
|
||||
|
||||
contours = find_contours(vertical_mask, horizontal_mask)
|
||||
table_bbox = find_joints(contours, vertical_mask, horizontal_mask)
|
||||
if self.table_areas is not None:
|
||||
areas = []
|
||||
for area in self.table_areas:
|
||||
x1, y1, x2, y2 = area.split(",")
|
||||
x1 = float(x1)
|
||||
y1 = float(y1)
|
||||
x2 = float(x2)
|
||||
y2 = float(y2)
|
||||
x1, y1, x2, y2 = scale_pdf((x1, y1, x2, y2), image_scalers)
|
||||
areas.append((x1, y1, abs(x2 - x1), abs(y2 - y1)))
|
||||
table_bbox = find_table_joints(areas, vertical_mask, horizontal_mask)
|
||||
else:
|
||||
vertical_mask, vertical_segments = find_lines(
|
||||
self.threshold,
|
||||
direction="vertical",
|
||||
line_scale=self.line_scale,
|
||||
iterations=self.iterations,
|
||||
)
|
||||
horizontal_mask, horizontal_segments = find_lines(
|
||||
self.threshold,
|
||||
direction="horizontal",
|
||||
line_scale=self.line_scale,
|
||||
iterations=self.iterations,
|
||||
)
|
||||
|
||||
areas = scale_areas(self.table_areas)
|
||||
table_bbox = find_joints(areas, vertical_mask, horizontal_mask)
|
||||
contours = find_table_contours(vertical_mask, horizontal_mask)
|
||||
table_bbox = find_table_joints(contours, vertical_mask, horizontal_mask)
|
||||
|
||||
self.table_bbox_unscaled = copy.deepcopy(table_bbox)
|
||||
|
||||
self.table_bbox, self.vertical_segments, self.horizontal_segments = scale_image(
|
||||
table_bbox, vertical_segments, horizontal_segments, pdf_scalers
|
||||
)
|
||||
table_bbox, vertical_segments, horizontal_segments, pdf_scalers)
|
||||
|
||||
def _generate_columns_and_rows(self, table_idx, tk):
|
||||
# select elements which lie within table_bbox
|
||||
t_bbox = {}
|
||||
v_s, h_s = segments_in_bbox(
|
||||
tk, self.vertical_segments, self.horizontal_segments
|
||||
)
|
||||
t_bbox["horizontal"] = text_in_bbox(tk, self.horizontal_text)
|
||||
t_bbox["vertical"] = text_in_bbox(tk, self.vertical_text)
|
||||
tk, self.vertical_segments, self.horizontal_segments)
|
||||
t_bbox['horizontal'] = text_in_bbox(tk, self.horizontal_text)
|
||||
t_bbox['vertical'] = text_in_bbox(tk, self.vertical_text)
|
||||
|
||||
t_bbox["horizontal"].sort(key=lambda x: (-x.y0, x.x0))
|
||||
t_bbox["vertical"].sort(key=lambda x: (x.x0, -x.y0))
|
||||
t_bbox['horizontal'].sort(key=lambda x: (-x.y0, x.x0))
|
||||
t_bbox['vertical'].sort(key=lambda x: (x.x0, -x.y0))
|
||||
|
||||
self.t_bbox = t_bbox
|
||||
|
||||
|
|
@ -332,23 +282,27 @@ class Lattice(BaseParser):
|
|||
cols.extend([tk[0], tk[2]])
|
||||
rows.extend([tk[1], tk[3]])
|
||||
# sort horizontal and vertical segments
|
||||
cols = merge_close_lines(sorted(cols), line_tol=self.line_tol)
|
||||
rows = merge_close_lines(sorted(rows, reverse=True), line_tol=self.line_tol)
|
||||
cols = merge_close_lines(
|
||||
sorted(cols), line_close_tol=self.line_close_tol)
|
||||
rows = merge_close_lines(
|
||||
sorted(rows, reverse=True), line_close_tol=self.line_close_tol)
|
||||
# make grid using x and y coord of shortlisted rows and cols
|
||||
cols = [(cols[i], cols[i + 1]) for i in range(0, len(cols) - 1)]
|
||||
rows = [(rows[i], rows[i + 1]) for i in range(0, len(rows) - 1)]
|
||||
cols = [(cols[i], cols[i + 1])
|
||||
for i in range(0, len(cols) - 1)]
|
||||
rows = [(rows[i], rows[i + 1])
|
||||
for i in range(0, len(rows) - 1)]
|
||||
|
||||
return cols, rows, v_s, h_s
|
||||
|
||||
def _generate_table(self, table_idx, cols, rows, **kwargs):
|
||||
v_s = kwargs.get("v_s")
|
||||
h_s = kwargs.get("h_s")
|
||||
v_s = kwargs.get('v_s')
|
||||
h_s = kwargs.get('h_s')
|
||||
if v_s is None or h_s is None:
|
||||
raise ValueError("No segments found on {}".format(self.rootname))
|
||||
raise ValueError('No segments found on {}'.format(self.rootname))
|
||||
|
||||
table = Table(cols, rows)
|
||||
# set table edges to True using ver+hor lines
|
||||
table = table.set_edges(v_s, h_s, joint_tol=self.joint_tol)
|
||||
table = table.set_edges(v_s, h_s, joint_close_tol=self.joint_close_tol)
|
||||
# set table border edges to True
|
||||
table = table.set_border()
|
||||
# set spanning cells to True
|
||||
|
|
@ -357,21 +311,14 @@ class Lattice(BaseParser):
|
|||
pos_errors = []
|
||||
# TODO: have a single list in place of two directional ones?
|
||||
# sorted on x-coordinate based on reading order i.e. LTR or RTL
|
||||
for direction in ["vertical", "horizontal"]:
|
||||
for direction in ['vertical', 'horizontal']:
|
||||
for t in self.t_bbox[direction]:
|
||||
indices, error = get_table_index(
|
||||
table,
|
||||
t,
|
||||
direction,
|
||||
split_text=self.split_text,
|
||||
flag_size=self.flag_size,
|
||||
strip_text=self.strip_text,
|
||||
)
|
||||
table, t, direction, split_text=self.split_text,
|
||||
flag_size=self.flag_size)
|
||||
if indices[:2] != (-1, -1):
|
||||
pos_errors.append(error)
|
||||
indices = Lattice._reduce_index(
|
||||
table, indices, shift_text=self.shift_text
|
||||
)
|
||||
indices = Lattice._reduce_index(table, indices, shift_text=self.shift_text)
|
||||
for r_idx, c_idx, text in indices:
|
||||
table.cells[r_idx][c_idx].text = text
|
||||
accuracy = compute_accuracy([[100, pos_errors]])
|
||||
|
|
@ -384,11 +331,11 @@ class Lattice(BaseParser):
|
|||
table.shape = table.df.shape
|
||||
|
||||
whitespace = compute_whitespace(data)
|
||||
table.flavor = "lattice"
|
||||
table.flavor = 'lattice'
|
||||
table.accuracy = accuracy
|
||||
table.whitespace = whitespace
|
||||
table.order = table_idx + 1
|
||||
table.page = int(os.path.basename(self.rootname).replace("page-", ""))
|
||||
table.page = int(os.path.basename(self.rootname).replace('page-', ''))
|
||||
|
||||
# for plotting
|
||||
_text = []
|
||||
|
|
@ -401,32 +348,23 @@ class Lattice(BaseParser):
|
|||
|
||||
return table
|
||||
|
||||
def extract_tables(self, filename, suppress_stdout=False, layout_kwargs={}):
|
||||
self._generate_layout(filename, layout_kwargs)
|
||||
def extract_tables(self, filename, suppress_stdout=False):
|
||||
self._generate_layout(filename)
|
||||
if not suppress_stdout:
|
||||
logger.info("Processing {}".format(os.path.basename(self.rootname)))
|
||||
logger.info('Processing {}'.format(os.path.basename(self.rootname)))
|
||||
|
||||
if not self.horizontal_text:
|
||||
if self.images:
|
||||
warnings.warn(
|
||||
"{} is image-based, camelot only works on"
|
||||
" text-based pages.".format(os.path.basename(self.rootname))
|
||||
)
|
||||
else:
|
||||
warnings.warn(
|
||||
"No tables found on {}".format(os.path.basename(self.rootname))
|
||||
)
|
||||
warnings.warn("No tables found on {}".format(
|
||||
os.path.basename(self.rootname)))
|
||||
return []
|
||||
|
||||
self.backend.convert(self.filename, self.imagename)
|
||||
|
||||
self._generate_image()
|
||||
self._generate_table_bbox()
|
||||
|
||||
_tables = []
|
||||
# sort tables based on y-coord
|
||||
for table_idx, tk in enumerate(
|
||||
sorted(self.table_bbox.keys(), key=lambda x: x[1], reverse=True)
|
||||
):
|
||||
for table_idx, tk in enumerate(sorted(
|
||||
self.table_bbox.keys(), key=lambda x: x[1], reverse=True)):
|
||||
cols, rows, v_s, h_s = self._generate_columns_and_rows(table_idx, tk)
|
||||
table = self._generate_table(table_idx, cols, rows, v_s=v_s, h_s=h_s)
|
||||
table._bbox = tk
|
||||
|
|
|
|||
|
|
@ -1,5 +1,6 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
from __future__ import division
|
||||
import os
|
||||
import logging
|
||||
import warnings
|
||||
|
|
@ -9,10 +10,11 @@ import pandas as pd
|
|||
|
||||
from .base import BaseParser
|
||||
from ..core import TextEdges, Table
|
||||
from ..utils import text_in_bbox, get_table_index, compute_accuracy, compute_whitespace
|
||||
from ..utils import (text_in_bbox, get_table_index, compute_accuracy,
|
||||
compute_whitespace)
|
||||
|
||||
|
||||
logger = logging.getLogger("camelot")
|
||||
logger = logging.getLogger('camelot')
|
||||
|
||||
|
||||
class Stream(BaseParser):
|
||||
|
|
@ -24,10 +26,6 @@ class Stream(BaseParser):
|
|||
|
||||
Parameters
|
||||
----------
|
||||
table_regions : list, optional (default: None)
|
||||
List of page regions that may contain tables of the form x1,y1,x2,y2
|
||||
where (x1, y1) -> left-top and (x2, y2) -> right-bottom
|
||||
in PDF coordinate space.
|
||||
table_areas : list, optional (default: None)
|
||||
List of table area strings of the form x1,y1,x2,y2
|
||||
where (x1, y1) -> left-top and (x2, y2) -> right-bottom
|
||||
|
|
@ -40,43 +38,29 @@ class Stream(BaseParser):
|
|||
flag_size : bool, optional (default: False)
|
||||
Flag text based on font size. Useful to detect
|
||||
super/subscripts. Adds <s></s> around flagged text.
|
||||
strip_text : str, optional (default: '')
|
||||
Characters that should be stripped from a string before
|
||||
assigning it to a cell.
|
||||
edge_tol : int, optional (default: 50)
|
||||
Tolerance parameter for extending textedges vertically.
|
||||
row_tol : int, optional (default: 2)
|
||||
row_close_tol : int, optional (default: 2)
|
||||
Tolerance parameter used to combine text vertically,
|
||||
to generate rows.
|
||||
column_tol : int, optional (default: 0)
|
||||
col_close_tol : int, optional (default: 0)
|
||||
Tolerance parameter used to combine text horizontally,
|
||||
to generate columns.
|
||||
margins : tuple, optional (default: (1.0, 0.5, 0.1))
|
||||
PDFMiner char_margin, line_margin and word_margin.
|
||||
|
||||
For more information, refer `PDFMiner docs <https://euske.github.io/pdfminer/>`_.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
table_regions=None,
|
||||
table_areas=None,
|
||||
columns=None,
|
||||
split_text=False,
|
||||
flag_size=False,
|
||||
strip_text="",
|
||||
edge_tol=50,
|
||||
row_tol=2,
|
||||
column_tol=0,
|
||||
**kwargs,
|
||||
):
|
||||
self.table_regions = table_regions
|
||||
def __init__(self, table_areas=None, columns=None, split_text=False,
|
||||
flag_size=False, row_close_tol=2, col_close_tol=0,
|
||||
margins=(1.0, 0.5, 0.1), **kwargs):
|
||||
self.table_areas = table_areas
|
||||
self.columns = columns
|
||||
self._validate_columns()
|
||||
self.split_text = split_text
|
||||
self.flag_size = flag_size
|
||||
self.strip_text = strip_text
|
||||
self.edge_tol = edge_tol
|
||||
self.row_tol = row_tol
|
||||
self.column_tol = column_tol
|
||||
self.row_close_tol = row_close_tol
|
||||
self.col_close_tol = col_close_tol
|
||||
self.char_margin, self.line_margin, self.word_margin = margins
|
||||
|
||||
@staticmethod
|
||||
def _text_bbox(t_bbox):
|
||||
|
|
@ -102,7 +86,7 @@ class Stream(BaseParser):
|
|||
return text_bbox
|
||||
|
||||
@staticmethod
|
||||
def _group_rows(text, row_tol=2):
|
||||
def _group_rows(text, row_close_tol=2):
|
||||
"""Groups PDFMiner text objects into rows vertically
|
||||
within a tolerance.
|
||||
|
||||
|
|
@ -110,7 +94,7 @@ class Stream(BaseParser):
|
|||
----------
|
||||
text : list
|
||||
List of PDFMiner text objects.
|
||||
row_tol : int, optional (default: 2)
|
||||
row_close_tol : int, optional (default: 2)
|
||||
|
||||
Returns
|
||||
-------
|
||||
|
|
@ -121,25 +105,22 @@ class Stream(BaseParser):
|
|||
row_y = 0
|
||||
rows = []
|
||||
temp = []
|
||||
|
||||
for t in text:
|
||||
# is checking for upright necessary?
|
||||
# if t.get_text().strip() and all([obj.upright for obj in t._objs if
|
||||
# type(obj) is LTChar]):
|
||||
if t.get_text().strip():
|
||||
if not np.isclose(row_y, t.y0, atol=row_tol):
|
||||
if not np.isclose(row_y, t.y0, atol=row_close_tol):
|
||||
rows.append(sorted(temp, key=lambda t: t.x0))
|
||||
temp = []
|
||||
row_y = t.y0
|
||||
temp.append(t)
|
||||
|
||||
rows.append(sorted(temp, key=lambda t: t.x0))
|
||||
if len(rows) > 1:
|
||||
__ = rows.pop(0) # TODO: hacky
|
||||
__ = rows.pop(0) # TODO: hacky
|
||||
return rows
|
||||
|
||||
@staticmethod
|
||||
def _merge_columns(l, column_tol=0):
|
||||
def _merge_columns(l, col_close_tol=0):
|
||||
"""Merges column boundaries horizontally if they overlap
|
||||
or lie within a tolerance.
|
||||
|
||||
|
|
@ -147,7 +128,7 @@ class Stream(BaseParser):
|
|||
----------
|
||||
l : list
|
||||
List of column x-coordinate tuples.
|
||||
column_tol : int, optional (default: 0)
|
||||
col_close_tol : int, optional (default: 0)
|
||||
|
||||
Returns
|
||||
-------
|
||||
|
|
@ -161,18 +142,17 @@ class Stream(BaseParser):
|
|||
merged.append(higher)
|
||||
else:
|
||||
lower = merged[-1]
|
||||
if column_tol >= 0:
|
||||
if higher[0] <= lower[1] or np.isclose(
|
||||
higher[0], lower[1], atol=column_tol
|
||||
):
|
||||
if col_close_tol >= 0:
|
||||
if (higher[0] <= lower[1] or
|
||||
np.isclose(higher[0], lower[1], atol=col_close_tol)):
|
||||
upper_bound = max(lower[1], higher[1])
|
||||
lower_bound = min(lower[0], higher[0])
|
||||
merged[-1] = (lower_bound, upper_bound)
|
||||
else:
|
||||
merged.append(higher)
|
||||
elif column_tol < 0:
|
||||
elif col_close_tol < 0:
|
||||
if higher[0] <= lower[1]:
|
||||
if np.isclose(higher[0], lower[1], atol=abs(column_tol)):
|
||||
if np.isclose(higher[0], lower[1], atol=abs(col_close_tol)):
|
||||
merged.append(higher)
|
||||
else:
|
||||
upper_bound = max(lower[1], higher[1])
|
||||
|
|
@ -199,18 +179,17 @@ class Stream(BaseParser):
|
|||
List of continuous row y-coordinate tuples.
|
||||
|
||||
"""
|
||||
row_mids = [
|
||||
sum([(t.y0 + t.y1) / 2 for t in r]) / len(r) if len(r) > 0 else 0
|
||||
for r in rows_grouped
|
||||
]
|
||||
row_mids = [sum([(t.y0 + t.y1) / 2 for t in r]) / len(r)
|
||||
if len(r) > 0 else 0 for r in rows_grouped]
|
||||
rows = [(row_mids[i] + row_mids[i - 1]) / 2 for i in range(1, len(row_mids))]
|
||||
rows.insert(0, text_y_max)
|
||||
rows.append(text_y_min)
|
||||
rows = [(rows[i], rows[i + 1]) for i in range(0, len(rows) - 1)]
|
||||
rows = [(rows[i], rows[i + 1])
|
||||
for i in range(0, len(rows) - 1)]
|
||||
return rows
|
||||
|
||||
@staticmethod
|
||||
def _add_columns(cols, text, row_tol):
|
||||
def _add_columns(cols, text, row_close_tol):
|
||||
"""Adds columns to existing list by taking into account
|
||||
the text that lies outside the current column x-coordinates.
|
||||
|
||||
|
|
@ -229,11 +208,10 @@ class Stream(BaseParser):
|
|||
|
||||
"""
|
||||
if text:
|
||||
text = Stream._group_rows(text, row_tol=row_tol)
|
||||
text = Stream._group_rows(text, row_close_tol=row_close_tol)
|
||||
elements = [len(r) for r in text]
|
||||
new_cols = [
|
||||
(t.x0, t.x1) for r in text if len(r) == max(elements) for t in r
|
||||
]
|
||||
new_cols = [(t.x0, t.x1)
|
||||
for r in text if len(r) == max(elements) for t in r]
|
||||
cols.extend(Stream._merge_columns(sorted(new_cols)))
|
||||
return cols
|
||||
|
||||
|
|
@ -258,13 +236,15 @@ class Stream(BaseParser):
|
|||
cols = [(cols[i][0] + cols[i - 1][1]) / 2 for i in range(1, len(cols))]
|
||||
cols.insert(0, text_x_min)
|
||||
cols.append(text_x_max)
|
||||
cols = [(cols[i], cols[i + 1]) for i in range(0, len(cols) - 1)]
|
||||
cols = [(cols[i], cols[i + 1])
|
||||
for i in range(0, len(cols) - 1)]
|
||||
return cols
|
||||
|
||||
def _validate_columns(self):
|
||||
if self.table_areas is not None and self.columns is not None:
|
||||
if len(self.table_areas) != len(self.columns):
|
||||
raise ValueError("Length of table_areas and columns" " should be equal")
|
||||
raise ValueError("Length of table_areas and columns"
|
||||
" should be equal")
|
||||
|
||||
def _nurminen_table_detection(self, textlines):
|
||||
"""A general implementation of the table detection algorithm
|
||||
|
|
@ -274,10 +254,11 @@ class Stream(BaseParser):
|
|||
Assumes that tables are situated relatively far apart
|
||||
vertically.
|
||||
"""
|
||||
|
||||
# TODO: add support for arabic text #141
|
||||
# sort textlines in reading order
|
||||
textlines.sort(key=lambda x: (-x.y0, x.x0))
|
||||
textedges = TextEdges(edge_tol=self.edge_tol)
|
||||
textedges = TextEdges()
|
||||
# generate left, middle and right textedges
|
||||
textedges.generate(textlines)
|
||||
# select relevant edges
|
||||
|
|
@ -293,22 +274,7 @@ class Stream(BaseParser):
|
|||
|
||||
def _generate_table_bbox(self):
|
||||
self.textedges = []
|
||||
if self.table_areas is None:
|
||||
hor_text = self.horizontal_text
|
||||
if self.table_regions is not None:
|
||||
# filter horizontal text
|
||||
hor_text = []
|
||||
for region in self.table_regions:
|
||||
x1, y1, x2, y2 = region.split(",")
|
||||
x1 = float(x1)
|
||||
y1 = float(y1)
|
||||
x2 = float(x2)
|
||||
y2 = float(y2)
|
||||
region_text = text_in_bbox((x1, y2, x2, y1), self.horizontal_text)
|
||||
hor_text.extend(region_text)
|
||||
# find tables based on nurminen's detection algorithm
|
||||
table_bbox = self._nurminen_table_detection(hor_text)
|
||||
else:
|
||||
if self.table_areas is not None:
|
||||
table_bbox = {}
|
||||
for area in self.table_areas:
|
||||
x1, y1, x2, y2 = area.split(",")
|
||||
|
|
@ -317,21 +283,24 @@ class Stream(BaseParser):
|
|||
x2 = float(x2)
|
||||
y2 = float(y2)
|
||||
table_bbox[(x1, y2, x2, y1)] = None
|
||||
else:
|
||||
# find tables based on nurminen's detection algorithm
|
||||
table_bbox = self._nurminen_table_detection(self.horizontal_text)
|
||||
self.table_bbox = table_bbox
|
||||
|
||||
def _generate_columns_and_rows(self, table_idx, tk):
|
||||
# select elements which lie within table_bbox
|
||||
t_bbox = {}
|
||||
t_bbox["horizontal"] = text_in_bbox(tk, self.horizontal_text)
|
||||
t_bbox["vertical"] = text_in_bbox(tk, self.vertical_text)
|
||||
t_bbox['horizontal'] = text_in_bbox(tk, self.horizontal_text)
|
||||
t_bbox['vertical'] = text_in_bbox(tk, self.vertical_text)
|
||||
|
||||
t_bbox["horizontal"].sort(key=lambda x: (-x.y0, x.x0))
|
||||
t_bbox["vertical"].sort(key=lambda x: (x.x0, -x.y0))
|
||||
t_bbox['horizontal'].sort(key=lambda x: (-x.y0, x.x0))
|
||||
t_bbox['vertical'].sort(key=lambda x: (x.x0, -x.y0))
|
||||
|
||||
self.t_bbox = t_bbox
|
||||
|
||||
text_x_min, text_y_min, text_x_max, text_y_max = self._text_bbox(self.t_bbox)
|
||||
rows_grouped = self._group_rows(self.t_bbox["horizontal"], row_tol=self.row_tol)
|
||||
rows_grouped = self._group_rows(self.t_bbox['horizontal'], row_close_tol=self.row_close_tol)
|
||||
rows = self._join_rows(rows_grouped, text_y_max, text_y_min)
|
||||
elements = [len(r) for r in rows_grouped]
|
||||
|
||||
|
|
@ -340,7 +309,7 @@ class Stream(BaseParser):
|
|||
# take (0, pdf_width) by default
|
||||
# similar to else condition
|
||||
# len can't be 1
|
||||
cols = self.columns[table_idx].split(",")
|
||||
cols = self.columns[table_idx].split(',')
|
||||
cols = [float(c) for c in cols]
|
||||
cols.insert(0, text_x_min)
|
||||
cols.append(text_x_max)
|
||||
|
|
@ -348,46 +317,34 @@ class Stream(BaseParser):
|
|||
else:
|
||||
# calculate mode of the list of number of elements in
|
||||
# each row to guess the number of columns
|
||||
if not len(elements):
|
||||
cols = [(text_x_min, text_x_max)]
|
||||
else:
|
||||
ncols = max(set(elements), key=elements.count)
|
||||
if ncols == 1:
|
||||
# if mode is 1, the page usually contains not tables
|
||||
# but there can be cases where the list can be skewed,
|
||||
# try to remove all 1s from list in this case and
|
||||
# see if the list contains elements, if yes, then use
|
||||
# the mode after removing 1s
|
||||
elements = list(filter(lambda x: x != 1, elements))
|
||||
if len(elements):
|
||||
ncols = max(set(elements), key=elements.count)
|
||||
else:
|
||||
warnings.warn(f"No tables found in table area {table_idx + 1}")
|
||||
cols = [
|
||||
(t.x0, t.x1) for r in rows_grouped if len(r) == ncols for t in r
|
||||
]
|
||||
cols = self._merge_columns(sorted(cols), column_tol=self.column_tol)
|
||||
inner_text = []
|
||||
for i in range(1, len(cols)):
|
||||
left = cols[i - 1][1]
|
||||
right = cols[i][0]
|
||||
inner_text.extend(
|
||||
[
|
||||
t
|
||||
for direction in self.t_bbox
|
||||
ncols = max(set(elements), key=elements.count)
|
||||
if ncols == 1:
|
||||
# if mode is 1, the page usually contains not tables
|
||||
# but there can be cases where the list can be skewed,
|
||||
# try to remove all 1s from list in this case and
|
||||
# see if the list contains elements, if yes, then use
|
||||
# the mode after removing 1s
|
||||
elements = list(filter(lambda x: x != 1, elements))
|
||||
if len(elements):
|
||||
ncols = max(set(elements), key=elements.count)
|
||||
else:
|
||||
warnings.warn("No tables found in table area {}".format(
|
||||
table_idx + 1))
|
||||
cols = [(t.x0, t.x1) for r in rows_grouped if len(r) == ncols for t in r]
|
||||
cols = self._merge_columns(sorted(cols), col_close_tol=self.col_close_tol)
|
||||
inner_text = []
|
||||
for i in range(1, len(cols)):
|
||||
left = cols[i - 1][1]
|
||||
right = cols[i][0]
|
||||
inner_text.extend([t for direction in self.t_bbox
|
||||
for t in self.t_bbox[direction]
|
||||
if t.x0 > left and t.x1 < right])
|
||||
outer_text = [t for direction in self.t_bbox
|
||||
for t in self.t_bbox[direction]
|
||||
if t.x0 > left and t.x1 < right
|
||||
]
|
||||
)
|
||||
outer_text = [
|
||||
t
|
||||
for direction in self.t_bbox
|
||||
for t in self.t_bbox[direction]
|
||||
if t.x0 > cols[-1][1] or t.x1 < cols[0][0]
|
||||
]
|
||||
inner_text.extend(outer_text)
|
||||
cols = self._add_columns(cols, inner_text, self.row_tol)
|
||||
cols = self._join_columns(cols, text_x_min, text_x_max)
|
||||
if t.x0 > cols[-1][1] or t.x1 < cols[0][0]]
|
||||
inner_text.extend(outer_text)
|
||||
cols = self._add_columns(cols, inner_text, self.row_close_tol)
|
||||
cols = self._join_columns(cols, text_x_min, text_x_max)
|
||||
|
||||
return cols, rows
|
||||
|
||||
|
|
@ -398,16 +355,11 @@ class Stream(BaseParser):
|
|||
pos_errors = []
|
||||
# TODO: have a single list in place of two directional ones?
|
||||
# sorted on x-coordinate based on reading order i.e. LTR or RTL
|
||||
for direction in ["vertical", "horizontal"]:
|
||||
for direction in ['vertical', 'horizontal']:
|
||||
for t in self.t_bbox[direction]:
|
||||
indices, error = get_table_index(
|
||||
table,
|
||||
t,
|
||||
direction,
|
||||
split_text=self.split_text,
|
||||
flag_size=self.flag_size,
|
||||
strip_text=self.strip_text,
|
||||
)
|
||||
table, t, direction, split_text=self.split_text,
|
||||
flag_size=self.flag_size)
|
||||
if indices[:2] != (-1, -1):
|
||||
pos_errors.append(error)
|
||||
for r_idx, c_idx, text in indices:
|
||||
|
|
@ -419,11 +371,11 @@ class Stream(BaseParser):
|
|||
table.shape = table.df.shape
|
||||
|
||||
whitespace = compute_whitespace(data)
|
||||
table.flavor = "stream"
|
||||
table.flavor = 'stream'
|
||||
table.accuracy = accuracy
|
||||
table.whitespace = whitespace
|
||||
table.order = table_idx + 1
|
||||
table.page = int(os.path.basename(self.rootname).replace("page-", ""))
|
||||
table.page = int(os.path.basename(self.rootname).replace('page-', ''))
|
||||
|
||||
# for plotting
|
||||
_text = []
|
||||
|
|
@ -436,30 +388,22 @@ class Stream(BaseParser):
|
|||
|
||||
return table
|
||||
|
||||
def extract_tables(self, filename, suppress_stdout=False, layout_kwargs={}):
|
||||
self._generate_layout(filename, layout_kwargs)
|
||||
base_filename = os.path.basename(self.rootname)
|
||||
|
||||
def extract_tables(self, filename, suppress_stdout=False):
|
||||
self._generate_layout(filename)
|
||||
if not suppress_stdout:
|
||||
logger.info(f"Processing {base_filename}")
|
||||
logger.info('Processing {}'.format(os.path.basename(self.rootname)))
|
||||
|
||||
if not self.horizontal_text:
|
||||
if self.images:
|
||||
warnings.warn(
|
||||
f"{base_filename} is image-based, camelot only works on"
|
||||
" text-based pages."
|
||||
)
|
||||
else:
|
||||
warnings.warn(f"No tables found on {base_filename}")
|
||||
warnings.warn("No tables found on {}".format(
|
||||
os.path.basename(self.rootname)))
|
||||
return []
|
||||
|
||||
self._generate_table_bbox()
|
||||
|
||||
_tables = []
|
||||
# sort tables based on y-coord
|
||||
for table_idx, tk in enumerate(
|
||||
sorted(self.table_bbox.keys(), key=lambda x: x[1], reverse=True)
|
||||
):
|
||||
for table_idx, tk in enumerate(sorted(
|
||||
self.table_bbox.keys(), key=lambda x: x[1], reverse=True)):
|
||||
cols, rows = self._generate_columns_and_rows(table_idx, tk)
|
||||
table = self._generate_table(table_idx, cols, rows)
|
||||
table._bbox = tk
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ else:
|
|||
|
||||
|
||||
class PlotMethods(object):
|
||||
def __call__(self, table, kind="text", filename=None):
|
||||
def __call__(self, table, kind='text', filename=None):
|
||||
"""Plot elements found on PDF page based on kind
|
||||
specified, useful for debugging and playing with different
|
||||
parameters to get the best output.
|
||||
|
|
@ -31,21 +31,17 @@ class PlotMethods(object):
|
|||
|
||||
"""
|
||||
if not _HAS_MPL:
|
||||
raise ImportError("matplotlib is required for plotting.")
|
||||
raise ImportError('matplotlib is required for plotting.')
|
||||
|
||||
if table.flavor == "lattice" and kind in ["textedge"]:
|
||||
raise NotImplementedError(f"Lattice flavor does not support kind='{kind}'")
|
||||
elif table.flavor == "stream" and kind in ["joint", "line"]:
|
||||
raise NotImplementedError(f"Stream flavor does not support kind='{kind}'")
|
||||
if table.flavor == 'lattice' and kind in ['textedge']:
|
||||
raise NotImplementedError("Lattice flavor does not support kind='{}'".format(
|
||||
kind))
|
||||
elif table.flavor == 'stream' and kind in ['joint', 'line']:
|
||||
raise NotImplementedError("Stream flavor does not support kind='{}'".format(
|
||||
kind))
|
||||
|
||||
plot_method = getattr(self, kind)
|
||||
fig = plot_method(table)
|
||||
|
||||
if filename is not None:
|
||||
fig.savefig(filename)
|
||||
return None
|
||||
|
||||
return fig
|
||||
return plot_method(table)
|
||||
|
||||
def text(self, table):
|
||||
"""Generates a plot for all text elements present
|
||||
|
|
@ -61,12 +57,18 @@ class PlotMethods(object):
|
|||
|
||||
"""
|
||||
fig = plt.figure()
|
||||
ax = fig.add_subplot(111, aspect="equal")
|
||||
ax = fig.add_subplot(111, aspect='equal')
|
||||
xs, ys = [], []
|
||||
for t in table._text:
|
||||
xs.extend([t[0], t[2]])
|
||||
ys.extend([t[1], t[3]])
|
||||
ax.add_patch(patches.Rectangle((t[0], t[1]), t[2] - t[0], t[3] - t[1]))
|
||||
ax.add_patch(
|
||||
patches.Rectangle(
|
||||
(t[0], t[1]),
|
||||
t[2] - t[0],
|
||||
t[3] - t[1]
|
||||
)
|
||||
)
|
||||
ax.set_xlim(min(xs) - 10, max(xs) + 10)
|
||||
ax.set_ylim(min(ys) - 10, max(ys) + 10)
|
||||
return fig
|
||||
|
|
@ -85,17 +87,21 @@ class PlotMethods(object):
|
|||
|
||||
"""
|
||||
fig = plt.figure()
|
||||
ax = fig.add_subplot(111, aspect="equal")
|
||||
ax = fig.add_subplot(111, aspect='equal')
|
||||
for row in table.cells:
|
||||
for cell in row:
|
||||
if cell.left:
|
||||
ax.plot([cell.lb[0], cell.lt[0]], [cell.lb[1], cell.lt[1]])
|
||||
ax.plot([cell.lb[0], cell.lt[0]],
|
||||
[cell.lb[1], cell.lt[1]])
|
||||
if cell.right:
|
||||
ax.plot([cell.rb[0], cell.rt[0]], [cell.rb[1], cell.rt[1]])
|
||||
ax.plot([cell.rb[0], cell.rt[0]],
|
||||
[cell.rb[1], cell.rt[1]])
|
||||
if cell.top:
|
||||
ax.plot([cell.lt[0], cell.rt[0]], [cell.lt[1], cell.rt[1]])
|
||||
ax.plot([cell.lt[0], cell.rt[0]],
|
||||
[cell.lt[1], cell.rt[1]])
|
||||
if cell.bottom:
|
||||
ax.plot([cell.lb[0], cell.rb[0]], [cell.lb[1], cell.rb[1]])
|
||||
ax.plot([cell.lb[0], cell.rb[0]],
|
||||
[cell.lb[1], cell.rb[1]])
|
||||
return fig
|
||||
|
||||
def contour(self, table):
|
||||
|
|
@ -118,7 +124,7 @@ class PlotMethods(object):
|
|||
img, table_bbox = (None, {table._bbox: None})
|
||||
_FOR_LATTICE = False
|
||||
fig = plt.figure()
|
||||
ax = fig.add_subplot(111, aspect="equal")
|
||||
ax = fig.add_subplot(111, aspect='equal')
|
||||
|
||||
xs, ys = [], []
|
||||
if not _FOR_LATTICE:
|
||||
|
|
@ -127,14 +133,21 @@ class PlotMethods(object):
|
|||
ys.extend([t[1], t[3]])
|
||||
ax.add_patch(
|
||||
patches.Rectangle(
|
||||
(t[0], t[1]), t[2] - t[0], t[3] - t[1], color="blue"
|
||||
(t[0], t[1]),
|
||||
t[2] - t[0],
|
||||
t[3] - t[1],
|
||||
color='blue'
|
||||
)
|
||||
)
|
||||
|
||||
for t in table_bbox.keys():
|
||||
ax.add_patch(
|
||||
patches.Rectangle(
|
||||
(t[0], t[1]), t[2] - t[0], t[3] - t[1], fill=False, color="red"
|
||||
(t[0], t[1]),
|
||||
t[2] - t[0],
|
||||
t[3] - t[1],
|
||||
fill=False,
|
||||
color='red'
|
||||
)
|
||||
)
|
||||
if not _FOR_LATTICE:
|
||||
|
|
@ -160,19 +173,25 @@ class PlotMethods(object):
|
|||
|
||||
"""
|
||||
fig = plt.figure()
|
||||
ax = fig.add_subplot(111, aspect="equal")
|
||||
ax = fig.add_subplot(111, aspect='equal')
|
||||
xs, ys = [], []
|
||||
for t in table._text:
|
||||
xs.extend([t[0], t[2]])
|
||||
ys.extend([t[1], t[3]])
|
||||
ax.add_patch(
|
||||
patches.Rectangle((t[0], t[1]), t[2] - t[0], t[3] - t[1], color="blue")
|
||||
patches.Rectangle(
|
||||
(t[0], t[1]),
|
||||
t[2] - t[0],
|
||||
t[3] - t[1],
|
||||
color='blue'
|
||||
)
|
||||
)
|
||||
ax.set_xlim(min(xs) - 10, max(xs) + 10)
|
||||
ax.set_ylim(min(ys) - 10, max(ys) + 10)
|
||||
|
||||
for te in table._textedges:
|
||||
ax.plot([te.x, te.x], [te.y0, te.y1])
|
||||
ax.plot([te.x, te.x],
|
||||
[te.y0, te.y1])
|
||||
|
||||
return fig
|
||||
|
||||
|
|
@ -191,14 +210,14 @@ class PlotMethods(object):
|
|||
"""
|
||||
img, table_bbox = table._image
|
||||
fig = plt.figure()
|
||||
ax = fig.add_subplot(111, aspect="equal")
|
||||
ax = fig.add_subplot(111, aspect='equal')
|
||||
x_coord = []
|
||||
y_coord = []
|
||||
for k in table_bbox.keys():
|
||||
for coord in table_bbox[k]:
|
||||
x_coord.append(coord[0])
|
||||
y_coord.append(coord[1])
|
||||
ax.plot(x_coord, y_coord, "ro")
|
||||
ax.plot(x_coord, y_coord, 'ro')
|
||||
ax.imshow(img)
|
||||
return fig
|
||||
|
||||
|
|
@ -216,7 +235,7 @@ class PlotMethods(object):
|
|||
|
||||
"""
|
||||
fig = plt.figure()
|
||||
ax = fig.add_subplot(111, aspect="equal")
|
||||
ax = fig.add_subplot(111, aspect='equal')
|
||||
vertical, horizontal = table._segments
|
||||
for v in vertical:
|
||||
ax.plot([v[0], v[2]], [v[1], v[3]])
|
||||
|
|
|
|||
501
camelot/utils.py
501
camelot/utils.py
|
|
@ -1,16 +1,12 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import os
|
||||
import re
|
||||
import random
|
||||
from __future__ import division
|
||||
import shutil
|
||||
import string
|
||||
import tempfile
|
||||
import warnings
|
||||
from itertools import groupby
|
||||
from operator import itemgetter
|
||||
|
||||
import numpy as np
|
||||
|
||||
from pdfminer.pdfparser import PDFParser
|
||||
from pdfminer.pdfdocument import PDFDocument
|
||||
from pdfminer.pdfpage import PDFPage
|
||||
|
|
@ -18,112 +14,43 @@ from pdfminer.pdfpage import PDFTextExtractionNotAllowed
|
|||
from pdfminer.pdfinterp import PDFResourceManager
|
||||
from pdfminer.pdfinterp import PDFPageInterpreter
|
||||
from pdfminer.converter import PDFPageAggregator
|
||||
from pdfminer.layout import (
|
||||
LAParams,
|
||||
LTAnno,
|
||||
LTChar,
|
||||
LTTextLineHorizontal,
|
||||
LTTextLineVertical,
|
||||
LTImage,
|
||||
)
|
||||
|
||||
from urllib.request import Request, urlopen
|
||||
from urllib.parse import urlparse as parse_url
|
||||
from urllib.parse import uses_relative, uses_netloc, uses_params
|
||||
from pdfminer.layout import (LAParams, LTAnno, LTChar, LTTextLineHorizontal,
|
||||
LTTextLineVertical)
|
||||
|
||||
|
||||
_VALID_URLS = set(uses_relative + uses_netloc + uses_params)
|
||||
_VALID_URLS.discard("")
|
||||
|
||||
|
||||
# https://github.com/pandas-dev/pandas/blob/master/pandas/io/common.py
|
||||
def is_url(url):
|
||||
"""Check to see if a URL has a valid protocol.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
url : str or unicode
|
||||
|
||||
Returns
|
||||
-------
|
||||
isurl : bool
|
||||
If url has a valid protocol return True otherwise False.
|
||||
|
||||
"""
|
||||
try:
|
||||
return parse_url(url).scheme in _VALID_URLS
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
def random_string(length):
|
||||
ret = ""
|
||||
while length:
|
||||
ret += random.choice(
|
||||
string.digits + string.ascii_lowercase + string.ascii_uppercase
|
||||
)
|
||||
length -= 1
|
||||
return ret
|
||||
|
||||
|
||||
def download_url(url):
|
||||
"""Download file from specified URL.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
url : str or unicode
|
||||
|
||||
Returns
|
||||
-------
|
||||
filepath : str or unicode
|
||||
Temporary filepath.
|
||||
|
||||
"""
|
||||
filename = f"{random_string(6)}.pdf"
|
||||
with tempfile.NamedTemporaryFile("wb", delete=False) as f:
|
||||
headers = {"User-Agent": "Mozilla/5.0"}
|
||||
request = Request(url, None, headers)
|
||||
obj = urlopen(request)
|
||||
content_type = obj.info().get_content_type()
|
||||
if content_type != "application/pdf":
|
||||
raise NotImplementedError("File format not supported")
|
||||
f.write(obj.read())
|
||||
filepath = os.path.join(os.path.dirname(f.name), filename)
|
||||
shutil.move(f.name, filepath)
|
||||
return filepath
|
||||
|
||||
|
||||
stream_kwargs = ["columns", "edge_tol", "row_tol", "column_tol"]
|
||||
stream_kwargs = [
|
||||
'columns',
|
||||
'row_close_tol',
|
||||
'col_close_tol'
|
||||
]
|
||||
lattice_kwargs = [
|
||||
"process_background",
|
||||
"line_scale",
|
||||
"copy_text",
|
||||
"shift_text",
|
||||
"line_tol",
|
||||
"joint_tol",
|
||||
"threshold_blocksize",
|
||||
"threshold_constant",
|
||||
"iterations",
|
||||
"resolution",
|
||||
'process_background',
|
||||
'line_size_scaling',
|
||||
'copy_text',
|
||||
'shift_text',
|
||||
'line_close_tol',
|
||||
'joint_close_tol',
|
||||
'threshold_blocksize',
|
||||
'threshold_constant',
|
||||
'iterations'
|
||||
]
|
||||
|
||||
|
||||
def validate_input(kwargs, flavor="lattice"):
|
||||
def validate_input(kwargs, flavor='lattice'):
|
||||
def check_intersection(parser_kwargs, input_kwargs):
|
||||
isec = set(parser_kwargs).intersection(set(input_kwargs.keys()))
|
||||
if isec:
|
||||
raise ValueError(
|
||||
f"{','.join(sorted(isec))} cannot be used with flavor='{flavor}'"
|
||||
)
|
||||
raise ValueError("{} cannot be used with flavor='{}'".format(
|
||||
",".join(sorted(isec)), flavor))
|
||||
|
||||
if flavor == "lattice":
|
||||
if flavor == 'lattice':
|
||||
check_intersection(stream_kwargs, kwargs)
|
||||
else:
|
||||
check_intersection(lattice_kwargs, kwargs)
|
||||
|
||||
|
||||
def remove_extra(kwargs, flavor="lattice"):
|
||||
if flavor == "lattice":
|
||||
def remove_extra(kwargs, flavor='lattice'):
|
||||
if flavor == 'lattice':
|
||||
for key in kwargs.keys():
|
||||
if key in stream_kwargs:
|
||||
kwargs.pop(key)
|
||||
|
|
@ -253,33 +180,29 @@ def scale_image(tables, v_segments, h_segments, factors):
|
|||
v_segments_new = []
|
||||
for v in v_segments:
|
||||
x1, x2 = scale(v[0], scaling_factor_x), scale(v[2], scaling_factor_x)
|
||||
y1, y2 = (
|
||||
scale(abs(translate(-img_y, v[1])), scaling_factor_y),
|
||||
scale(abs(translate(-img_y, v[3])), scaling_factor_y),
|
||||
)
|
||||
y1, y2 = scale(abs(translate(-img_y, v[1])), scaling_factor_y), scale(
|
||||
abs(translate(-img_y, v[3])), scaling_factor_y)
|
||||
v_segments_new.append((x1, y1, x2, y2))
|
||||
|
||||
h_segments_new = []
|
||||
for h in h_segments:
|
||||
x1, x2 = scale(h[0], scaling_factor_x), scale(h[2], scaling_factor_x)
|
||||
y1, y2 = (
|
||||
scale(abs(translate(-img_y, h[1])), scaling_factor_y),
|
||||
scale(abs(translate(-img_y, h[3])), scaling_factor_y),
|
||||
)
|
||||
y1, y2 = scale(abs(translate(-img_y, h[1])), scaling_factor_y), scale(
|
||||
abs(translate(-img_y, h[3])), scaling_factor_y)
|
||||
h_segments_new.append((x1, y1, x2, y2))
|
||||
|
||||
return tables_new, v_segments_new, h_segments_new
|
||||
|
||||
|
||||
def get_rotation(chars, horizontal_text, vertical_text):
|
||||
def get_rotation(lttextlh, lttextlv, ltchar):
|
||||
"""Detects if text in table is rotated or not using the current
|
||||
transformation matrix (CTM) and returns its orientation.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
horizontal_text : list
|
||||
lttextlh : list
|
||||
List of PDFMiner LTTextLineHorizontal objects.
|
||||
vertical_text : list
|
||||
lttextlv : list
|
||||
List of PDFMiner LTTextLineVertical objects.
|
||||
ltchar : list
|
||||
List of PDFMiner LTChar objects.
|
||||
|
|
@ -292,13 +215,13 @@ def get_rotation(chars, horizontal_text, vertical_text):
|
|||
rotated 90 degree clockwise.
|
||||
|
||||
"""
|
||||
rotation = ""
|
||||
hlen = len([t for t in horizontal_text if t.get_text().strip()])
|
||||
vlen = len([t for t in vertical_text if t.get_text().strip()])
|
||||
rotation = ''
|
||||
hlen = len([t for t in lttextlh if t.get_text().strip()])
|
||||
vlen = len([t for t in lttextlv if t.get_text().strip()])
|
||||
if hlen < vlen:
|
||||
clockwise = sum(t.matrix[1] < 0 and t.matrix[2] > 0 for t in chars)
|
||||
anticlockwise = sum(t.matrix[1] > 0 and t.matrix[2] < 0 for t in chars)
|
||||
rotation = "anticlockwise" if clockwise < anticlockwise else "clockwise"
|
||||
clockwise = sum(t.matrix[1] < 0 and t.matrix[2] > 0 for t in ltchar)
|
||||
anticlockwise = sum(t.matrix[1] > 0 and t.matrix[2] < 0 for t in ltchar)
|
||||
rotation = 'anticlockwise' if clockwise < anticlockwise else 'clockwise'
|
||||
return rotation
|
||||
|
||||
|
||||
|
|
@ -326,16 +249,10 @@ def segments_in_bbox(bbox, v_segments, h_segments):
|
|||
"""
|
||||
lb = (bbox[0], bbox[1])
|
||||
rt = (bbox[2], bbox[3])
|
||||
v_s = [
|
||||
v
|
||||
for v in v_segments
|
||||
if v[1] > lb[1] - 2 and v[3] < rt[1] + 2 and lb[0] - 2 <= v[0] <= rt[0] + 2
|
||||
]
|
||||
h_s = [
|
||||
h
|
||||
for h in h_segments
|
||||
if h[0] > lb[0] - 2 and h[2] < rt[0] + 2 and lb[1] - 2 <= h[1] <= rt[1] + 2
|
||||
]
|
||||
v_s = [v for v in v_segments if v[1] > lb[1] - 2 and
|
||||
v[3] < rt[1] + 2 and lb[0] - 2 <= v[0] <= rt[0] + 2]
|
||||
h_s = [h for h in h_segments if h[0] > lb[0] - 2 and
|
||||
h[2] < rt[0] + 2 and lb[1] - 2 <= h[1] <= rt[1] + 2]
|
||||
return v_s, h_s
|
||||
|
||||
|
||||
|
|
@ -346,125 +263,32 @@ def text_in_bbox(bbox, text):
|
|||
----------
|
||||
bbox : tuple
|
||||
Tuple (x1, y1, x2, y2) representing a bounding box where
|
||||
(x1, y1) -> lb and (x2, y2) -> rt in the PDF coordinate
|
||||
(x1, y1) -> lb and (x2, y2) -> rt in PDFMiner coordinate
|
||||
space.
|
||||
text : List of PDFMiner text objects.
|
||||
|
||||
Returns
|
||||
-------
|
||||
t_bbox : list
|
||||
List of PDFMiner text objects that lie inside table, discarding the overlapping ones
|
||||
List of PDFMiner text objects that lie inside table.
|
||||
|
||||
"""
|
||||
lb = (bbox[0], bbox[1])
|
||||
rt = (bbox[2], bbox[3])
|
||||
t_bbox = [
|
||||
t
|
||||
for t in text
|
||||
if lb[0] - 2 <= (t.x0 + t.x1) / 2.0 <= rt[0] + 2
|
||||
and lb[1] - 2 <= (t.y0 + t.y1) / 2.0 <= rt[1] + 2
|
||||
]
|
||||
|
||||
# Avoid duplicate text by discarding overlapping boxes
|
||||
rest = {t for t in t_bbox}
|
||||
for ba in t_bbox:
|
||||
for bb in rest.copy():
|
||||
if ba == bb:
|
||||
continue
|
||||
if bbox_intersect(ba, bb):
|
||||
# if the intersection is larger than 80% of ba's size, we keep the longest
|
||||
if (bbox_intersection_area(ba, bb) / bbox_area(ba)) > 0.8:
|
||||
if bbox_longer(bb, ba):
|
||||
rest.discard(ba)
|
||||
unique_boxes = list(rest)
|
||||
|
||||
return unique_boxes
|
||||
t_bbox = [t for t in text if lb[0] - 2 <= (t.x0 + t.x1) / 2.0
|
||||
<= rt[0] + 2 and lb[1] - 2 <= (t.y0 + t.y1) / 2.0
|
||||
<= rt[1] + 2]
|
||||
return t_bbox
|
||||
|
||||
|
||||
def bbox_intersection_area(ba, bb) -> float:
|
||||
"""Returns area of the intersection of the bounding boxes of two PDFMiner objects.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
ba : PDFMiner text object
|
||||
bb : PDFMiner text object
|
||||
|
||||
Returns
|
||||
-------
|
||||
intersection_area : float
|
||||
Area of the intersection of the bounding boxes of both objects
|
||||
|
||||
"""
|
||||
x_left = max(ba.x0, bb.x0)
|
||||
y_top = min(ba.y1, bb.y1)
|
||||
x_right = min(ba.x1, bb.x1)
|
||||
y_bottom = max(ba.y0, bb.y0)
|
||||
|
||||
if x_right < x_left or y_bottom > y_top:
|
||||
return 0.0
|
||||
|
||||
intersection_area = (x_right - x_left) * (y_top - y_bottom)
|
||||
return intersection_area
|
||||
|
||||
|
||||
def bbox_area(bb) -> float:
|
||||
"""Returns area of the bounding box of a PDFMiner object.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
bb : PDFMiner text object
|
||||
|
||||
Returns
|
||||
-------
|
||||
area : float
|
||||
Area of the bounding box of the object
|
||||
|
||||
"""
|
||||
return (bb.x1 - bb.x0) * (bb.y1 - bb.y0)
|
||||
|
||||
|
||||
def bbox_intersect(ba, bb) -> bool:
|
||||
"""Returns True if the bounding boxes of two PDFMiner objects intersect.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
ba : PDFMiner text object
|
||||
bb : PDFMiner text object
|
||||
|
||||
Returns
|
||||
-------
|
||||
overlaps : bool
|
||||
True if the bounding boxes intersect
|
||||
|
||||
"""
|
||||
return ba.x1 >= bb.x0 and bb.x1 >= ba.x0 and ba.y1 >= bb.y0 and bb.y1 >= ba.y0
|
||||
|
||||
|
||||
def bbox_longer(ba, bb) -> bool:
|
||||
"""Returns True if the bounding box of the first PDFMiner object is longer or equal to the second.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
ba : PDFMiner text object
|
||||
bb : PDFMiner text object
|
||||
|
||||
Returns
|
||||
-------
|
||||
longer : bool
|
||||
True if the bounding box of the first object is longer or equal
|
||||
|
||||
"""
|
||||
return (ba.x1 - ba.x0) >= (bb.x1 - bb.x0)
|
||||
|
||||
|
||||
def merge_close_lines(ar, line_tol=2):
|
||||
def merge_close_lines(ar, line_close_tol=2):
|
||||
"""Merges lines which are within a tolerance by calculating a
|
||||
moving mean, based on their x or y axis projections.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
ar : list
|
||||
line_tol : int, optional (default: 2)
|
||||
line_close_tol : int, optional (default: 2)
|
||||
|
||||
Returns
|
||||
-------
|
||||
|
|
@ -477,7 +301,7 @@ def merge_close_lines(ar, line_tol=2):
|
|||
ret.append(a)
|
||||
else:
|
||||
temp = ret[-1]
|
||||
if np.isclose(temp, a, atol=line_tol):
|
||||
if np.isclose(temp, a, atol=line_close_tol):
|
||||
temp = (temp + a) / 2.0
|
||||
ret[-1] = temp
|
||||
else:
|
||||
|
|
@ -485,33 +309,7 @@ def merge_close_lines(ar, line_tol=2):
|
|||
return ret
|
||||
|
||||
|
||||
def text_strip(text, strip=""):
|
||||
"""Strips any characters in `strip` that are present in `text`.
|
||||
Parameters
|
||||
----------
|
||||
text : str
|
||||
Text to process and strip.
|
||||
strip : str, optional (default: '')
|
||||
Characters that should be stripped from `text`.
|
||||
Returns
|
||||
-------
|
||||
stripped : str
|
||||
"""
|
||||
if not strip:
|
||||
return text
|
||||
|
||||
stripped = re.sub(
|
||||
fr"[{''.join(map(re.escape, strip))}]", "", text, flags=re.UNICODE
|
||||
)
|
||||
return stripped
|
||||
|
||||
|
||||
# TODO: combine the following functions into a TextProcessor class which
|
||||
# applies corresponding transformations sequentially
|
||||
# (inspired from sklearn.pipeline.Pipeline)
|
||||
|
||||
|
||||
def flag_font_size(textline, direction, strip_text=""):
|
||||
def flag_font_size(textline, direction):
|
||||
"""Flags super/subscripts in text by enclosing them with <s></s>.
|
||||
May give false positives.
|
||||
|
||||
|
|
@ -521,27 +319,16 @@ def flag_font_size(textline, direction, strip_text=""):
|
|||
List of PDFMiner LTChar objects.
|
||||
direction : string
|
||||
Direction of the PDFMiner LTTextLine object.
|
||||
strip_text : str, optional (default: '')
|
||||
Characters that should be stripped from a string before
|
||||
assigning it to a cell.
|
||||
|
||||
Returns
|
||||
-------
|
||||
fstring : string
|
||||
|
||||
"""
|
||||
if direction == "horizontal":
|
||||
d = [
|
||||
(t.get_text(), np.round(t.height, decimals=6))
|
||||
for t in textline
|
||||
if not isinstance(t, LTAnno)
|
||||
]
|
||||
elif direction == "vertical":
|
||||
d = [
|
||||
(t.get_text(), np.round(t.width, decimals=6))
|
||||
for t in textline
|
||||
if not isinstance(t, LTAnno)
|
||||
]
|
||||
if direction == 'horizontal':
|
||||
d = [(t.get_text(), np.round(t.height, decimals=6)) for t in textline if not isinstance(t, LTAnno)]
|
||||
elif direction == 'vertical':
|
||||
d = [(t.get_text(), np.round(t.width, decimals=6)) for t in textline if not isinstance(t, LTAnno)]
|
||||
l = [np.round(size, decimals=6) for text, size in d]
|
||||
if len(set(l)) > 1:
|
||||
flist = []
|
||||
|
|
@ -549,21 +336,21 @@ def flag_font_size(textline, direction, strip_text=""):
|
|||
for key, chars in groupby(d, itemgetter(1)):
|
||||
if key == min_size:
|
||||
fchars = [t[0] for t in chars]
|
||||
if "".join(fchars).strip():
|
||||
fchars.insert(0, "<s>")
|
||||
fchars.append("</s>")
|
||||
flist.append("".join(fchars))
|
||||
if ''.join(fchars).strip():
|
||||
fchars.insert(0, '<s>')
|
||||
fchars.append('</s>')
|
||||
flist.append(''.join(fchars))
|
||||
else:
|
||||
fchars = [t[0] for t in chars]
|
||||
if "".join(fchars).strip():
|
||||
flist.append("".join(fchars))
|
||||
fstring = "".join(flist)
|
||||
if ''.join(fchars).strip():
|
||||
flist.append(''.join(fchars))
|
||||
fstring = ''.join(flist)
|
||||
else:
|
||||
fstring = "".join([t.get_text() for t in textline])
|
||||
return text_strip(fstring, strip_text)
|
||||
fstring = ''.join([t.get_text() for t in textline])
|
||||
return fstring
|
||||
|
||||
|
||||
def split_textline(table, textline, direction, flag_size=False, strip_text=""):
|
||||
def split_textline(table, textline, direction, flag_size=False):
|
||||
"""Splits PDFMiner LTTextLine into substrings if it spans across
|
||||
multiple rows/columns.
|
||||
|
||||
|
|
@ -578,9 +365,6 @@ def split_textline(table, textline, direction, flag_size=False, strip_text=""):
|
|||
Whether or not to highlight a substring using <s></s>
|
||||
if its size is different from rest of the string. (Useful for
|
||||
super and subscripts.)
|
||||
strip_text : str, optional (default: '')
|
||||
Characters that should be stripped from a string before
|
||||
assigning it to a cell.
|
||||
|
||||
Returns
|
||||
-------
|
||||
|
|
@ -593,70 +377,38 @@ def split_textline(table, textline, direction, flag_size=False, strip_text=""):
|
|||
cut_text = []
|
||||
bbox = textline.bbox
|
||||
try:
|
||||
if direction == "horizontal" and not textline.is_empty():
|
||||
x_overlap = [
|
||||
i
|
||||
for i, x in enumerate(table.cols)
|
||||
if x[0] <= bbox[2] and bbox[0] <= x[1]
|
||||
]
|
||||
r_idx = [
|
||||
j
|
||||
for j, r in enumerate(table.rows)
|
||||
if r[1] <= (bbox[1] + bbox[3]) / 2 <= r[0]
|
||||
]
|
||||
if direction == 'horizontal' and not textline.is_empty():
|
||||
x_overlap = [i for i, x in enumerate(table.cols) if x[0] <= bbox[2] and bbox[0] <= x[1]]
|
||||
r_idx = [j for j, r in enumerate(table.rows) if r[1] <= (bbox[1] + bbox[3]) / 2 <= r[0]]
|
||||
r = r_idx[0]
|
||||
x_cuts = [
|
||||
(c, table.cells[r][c].x2) for c in x_overlap if table.cells[r][c].right
|
||||
]
|
||||
x_cuts = [(c, table.cells[r][c].x2) for c in x_overlap if table.cells[r][c].right]
|
||||
if not x_cuts:
|
||||
x_cuts = [(x_overlap[0], table.cells[r][-1].x2)]
|
||||
for obj in textline._objs:
|
||||
row = table.rows[r]
|
||||
for cut in x_cuts:
|
||||
if isinstance(obj, LTChar):
|
||||
if (
|
||||
row[1] <= (obj.y0 + obj.y1) / 2 <= row[0]
|
||||
and (obj.x0 + obj.x1) / 2 <= cut[1]
|
||||
):
|
||||
if (row[1] <= (obj.y0 + obj.y1) / 2 <= row[0] and
|
||||
(obj.x0 + obj.x1) / 2 <= cut[1]):
|
||||
cut_text.append((r, cut[0], obj))
|
||||
break
|
||||
else:
|
||||
# TODO: add test
|
||||
if cut == x_cuts[-1]:
|
||||
cut_text.append((r, cut[0] + 1, obj))
|
||||
elif isinstance(obj, LTAnno):
|
||||
cut_text.append((r, cut[0], obj))
|
||||
elif direction == "vertical" and not textline.is_empty():
|
||||
y_overlap = [
|
||||
j
|
||||
for j, y in enumerate(table.rows)
|
||||
if y[1] <= bbox[3] and bbox[1] <= y[0]
|
||||
]
|
||||
c_idx = [
|
||||
i
|
||||
for i, c in enumerate(table.cols)
|
||||
if c[0] <= (bbox[0] + bbox[2]) / 2 <= c[1]
|
||||
]
|
||||
elif direction == 'vertical' and not textline.is_empty():
|
||||
y_overlap = [j for j, y in enumerate(table.rows) if y[1] <= bbox[3] and bbox[1] <= y[0]]
|
||||
c_idx = [i for i, c in enumerate(table.cols) if c[0] <= (bbox[0] + bbox[2]) / 2 <= c[1]]
|
||||
c = c_idx[0]
|
||||
y_cuts = [
|
||||
(r, table.cells[r][c].y1) for r in y_overlap if table.cells[r][c].bottom
|
||||
]
|
||||
y_cuts = [(r, table.cells[r][c].y1) for r in y_overlap if table.cells[r][c].bottom]
|
||||
if not y_cuts:
|
||||
y_cuts = [(y_overlap[0], table.cells[-1][c].y1)]
|
||||
for obj in textline._objs:
|
||||
col = table.cols[c]
|
||||
for cut in y_cuts:
|
||||
if isinstance(obj, LTChar):
|
||||
if (
|
||||
col[0] <= (obj.x0 + obj.x1) / 2 <= col[1]
|
||||
and (obj.y0 + obj.y1) / 2 >= cut[1]
|
||||
):
|
||||
if (col[0] <= (obj.x0 + obj.x1) / 2 <= col[1] and
|
||||
(obj.y0 + obj.y1) / 2 >= cut[1]):
|
||||
cut_text.append((cut[0], c, obj))
|
||||
break
|
||||
else:
|
||||
# TODO: add test
|
||||
if cut == y_cuts[-1]:
|
||||
cut_text.append((cut[0] - 1, c, obj))
|
||||
elif isinstance(obj, LTAnno):
|
||||
cut_text.append((cut[0], c, obj))
|
||||
except IndexError:
|
||||
|
|
@ -664,26 +416,14 @@ def split_textline(table, textline, direction, flag_size=False, strip_text=""):
|
|||
grouped_chars = []
|
||||
for key, chars in groupby(cut_text, itemgetter(0, 1)):
|
||||
if flag_size:
|
||||
grouped_chars.append(
|
||||
(
|
||||
key[0],
|
||||
key[1],
|
||||
flag_font_size(
|
||||
[t[2] for t in chars], direction, strip_text=strip_text
|
||||
),
|
||||
)
|
||||
)
|
||||
grouped_chars.append((key[0], key[1], flag_font_size([t[2] for t in chars], direction)))
|
||||
else:
|
||||
gchars = [t[2].get_text() for t in chars]
|
||||
grouped_chars.append(
|
||||
(key[0], key[1], text_strip("".join(gchars), strip_text))
|
||||
)
|
||||
grouped_chars.append((key[0], key[1], ''.join(gchars)))
|
||||
return grouped_chars
|
||||
|
||||
|
||||
def get_table_index(
|
||||
table, t, direction, split_text=False, flag_size=False, strip_text=""
|
||||
):
|
||||
def get_table_index(table, t, direction, split_text=False, flag_size=False):
|
||||
"""Gets indices of the table cell where given text object lies by
|
||||
comparing their y and x-coordinates.
|
||||
|
||||
|
|
@ -701,9 +441,6 @@ def get_table_index(
|
|||
Whether or not to highlight a substring using <s></s>
|
||||
if its size is different from rest of the string. (Useful for
|
||||
super and subscripts)
|
||||
strip_text : str, optional (default: '')
|
||||
Characters that should be stripped from a string before
|
||||
assigning it to a cell.
|
||||
|
||||
Returns
|
||||
-------
|
||||
|
|
@ -722,9 +459,8 @@ def get_table_index(
|
|||
"""
|
||||
r_idx, c_idx = [-1] * 2
|
||||
for r in range(len(table.rows)):
|
||||
if (t.y0 + t.y1) / 2.0 < table.rows[r][0] and (t.y0 + t.y1) / 2.0 > table.rows[
|
||||
r
|
||||
][1]:
|
||||
if ((t.y0 + t.y1) / 2.0 < table.rows[r][0] and
|
||||
(t.y0 + t.y1) / 2.0 > table.rows[r][1]):
|
||||
lt_col_overlap = []
|
||||
for c in table.cols:
|
||||
if c[0] <= t.x1 and c[1] >= t.x0:
|
||||
|
|
@ -734,12 +470,11 @@ def get_table_index(
|
|||
else:
|
||||
lt_col_overlap.append(-1)
|
||||
if len(list(filter(lambda x: x != -1, lt_col_overlap))) == 0:
|
||||
text = t.get_text().strip("\n")
|
||||
text = t.get_text().strip('\n')
|
||||
text_range = (t.x0, t.x1)
|
||||
col_range = (table.cols[0][0], table.cols[-1][1])
|
||||
warnings.warn(
|
||||
f"{text} {text_range} does not lie in column range {col_range}"
|
||||
)
|
||||
warnings.warn("{} {} does not lie in column range {}".format(
|
||||
text, text_range, col_range))
|
||||
r_idx = r
|
||||
c_idx = lt_col_overlap.index(max(lt_col_overlap))
|
||||
break
|
||||
|
|
@ -760,26 +495,12 @@ def get_table_index(
|
|||
error = ((X * (y0_offset + y1_offset)) + (Y * (x0_offset + x1_offset))) / charea
|
||||
|
||||
if split_text:
|
||||
return (
|
||||
split_textline(
|
||||
table, t, direction, flag_size=flag_size, strip_text=strip_text
|
||||
),
|
||||
error,
|
||||
)
|
||||
return split_textline(table, t, direction, flag_size=flag_size), error
|
||||
else:
|
||||
if flag_size:
|
||||
return (
|
||||
[
|
||||
(
|
||||
r_idx,
|
||||
c_idx,
|
||||
flag_font_size(t._objs, direction, strip_text=strip_text),
|
||||
)
|
||||
],
|
||||
error,
|
||||
)
|
||||
return [(r_idx, c_idx, flag_font_size(t._objs, direction))], error
|
||||
else:
|
||||
return [(r_idx, c_idx, text_strip(t.get_text(), strip_text))], error
|
||||
return [(r_idx, c_idx, t.get_text())], error
|
||||
|
||||
|
||||
def compute_accuracy(error_weights):
|
||||
|
|
@ -830,35 +551,25 @@ def compute_whitespace(d):
|
|||
r_nempty_cells, c_nempty_cells = [], []
|
||||
for i in d:
|
||||
for j in i:
|
||||
if j.strip() == "":
|
||||
if j.strip() == '':
|
||||
whitespace += 1
|
||||
whitespace = 100 * (whitespace / float(len(d) * len(d[0])))
|
||||
return whitespace
|
||||
|
||||
|
||||
def get_page_layout(
|
||||
filename,
|
||||
line_overlap=0.5,
|
||||
char_margin=1.0,
|
||||
line_margin=0.5,
|
||||
word_margin=0.1,
|
||||
boxes_flow=0.5,
|
||||
detect_vertical=True,
|
||||
all_texts=True,
|
||||
):
|
||||
def get_page_layout(filename, char_margin=1.0, line_margin=0.5, word_margin=0.1,
|
||||
detect_vertical=True, all_texts=True):
|
||||
"""Returns a PDFMiner LTPage object and page dimension of a single
|
||||
page pdf. To get the definitions of kwargs, see
|
||||
https://pdfminersix.rtfd.io/en/latest/reference/composable.html.
|
||||
page pdf. See https://euske.github.io/pdfminer/ to get definitions
|
||||
of kwargs.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
filename : string
|
||||
Path to pdf file.
|
||||
line_overlap : float
|
||||
char_margin : float
|
||||
line_margin : float
|
||||
word_margin : float
|
||||
boxes_flow : float
|
||||
detect_vertical : bool
|
||||
all_texts : bool
|
||||
|
||||
|
|
@ -870,22 +581,16 @@ def get_page_layout(
|
|||
Dimension of pdf page in the form (width, height).
|
||||
|
||||
"""
|
||||
with open(filename, "rb") as f:
|
||||
with open(filename, 'rb') as f:
|
||||
parser = PDFParser(f)
|
||||
document = PDFDocument(parser)
|
||||
if not document.is_extractable:
|
||||
raise PDFTextExtractionNotAllowed(
|
||||
f"Text extraction is not allowed: {filename}"
|
||||
)
|
||||
laparams = LAParams(
|
||||
line_overlap=line_overlap,
|
||||
char_margin=char_margin,
|
||||
line_margin=line_margin,
|
||||
word_margin=word_margin,
|
||||
boxes_flow=boxes_flow,
|
||||
detect_vertical=detect_vertical,
|
||||
all_texts=all_texts,
|
||||
)
|
||||
raise PDFTextExtractionNotAllowed
|
||||
laparams = LAParams(char_margin=char_margin,
|
||||
line_margin=line_margin,
|
||||
word_margin=word_margin,
|
||||
detect_vertical=detect_vertical,
|
||||
all_texts=all_texts)
|
||||
rsrcmgr = PDFResourceManager()
|
||||
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
|
||||
interpreter = PDFPageInterpreter(rsrcmgr, device)
|
||||
|
|
@ -919,11 +624,9 @@ def get_text_objects(layout, ltype="char", t=None):
|
|||
"""
|
||||
if ltype == "char":
|
||||
LTObject = LTChar
|
||||
elif ltype == "image":
|
||||
LTObject = LTImage
|
||||
elif ltype == "horizontal_text":
|
||||
elif ltype == "lh":
|
||||
LTObject = LTTextLineHorizontal
|
||||
elif ltype == "vertical_text":
|
||||
elif ltype == "lv":
|
||||
LTObject = LTTextLineVertical
|
||||
if t is None:
|
||||
t = []
|
||||
|
|
|
|||
|
|
@ -1,4 +0,0 @@
|
|||
"Età dell’Assicuratoall’epoca del decesso","Misura % dimaggiorazione"
|
||||
"18-75","1,00%"
|
||||
"76-80","0,50%"
|
||||
"81 in poi","0,10%"
|
||||
|
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 20 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 20 KiB |
|
|
@ -4,13 +4,13 @@
|
|||
</a>
|
||||
</p>
|
||||
<p>
|
||||
<iframe src="https://ghbtns.com/github-btn.html?user=camelot-dev&repo=camelot&type=watch&count=true&size=large"
|
||||
<iframe src="https://ghbtns.com/github-btn.html?user=socialcopsdev&repo=camelot&type=watch&count=true&size=large"
|
||||
allowtransparency="true" frameborder="0" scrolling="0" width="200px" height="35px"></iframe>
|
||||
</p>
|
||||
|
||||
<h3>Useful Links</h3>
|
||||
<ul>
|
||||
<li><a href="https://github.com/camelot-dev/camelot">Camelot @ GitHub</a></li>
|
||||
<li><a href="https://github.com/socialcopsdev/camelot">Camelot @ GitHub</a></li>
|
||||
<li><a href="https://pypi.org/project/camelot-py/">Camelot @ PyPI</a></li>
|
||||
<li><a href="https://github.com/camelot-dev/camelot/issues">Issue Tracker</a></li>
|
||||
</ul>
|
||||
<li><a href="https://github.com/socialcopsdev/camelot/issues">Issue Tracker</a></li>
|
||||
</ul>
|
||||
|
|
@ -4,6 +4,6 @@
|
|||
</a>
|
||||
</p>
|
||||
<p>
|
||||
<iframe src="https://ghbtns.com/github-btn.html?user=camelot-dev&repo=camelot&type=watch&count=true&size=large"
|
||||
<iframe src="https://ghbtns.com/github-btn.html?user=socialcopsdev&repo=camelot&type=watch&count=true&size=large"
|
||||
allowtransparency="true" frameborder="0" scrolling="0" width="200px" height="35px"></iframe>
|
||||
</p>
|
||||
</p>
|
||||
|
|
@ -1,19 +1,7 @@
|
|||
# flasky pygments style based on tango style
|
||||
from pygments.style import Style
|
||||
from pygments.token import (
|
||||
Keyword,
|
||||
Name,
|
||||
Comment,
|
||||
String,
|
||||
Error,
|
||||
Number,
|
||||
Operator,
|
||||
Generic,
|
||||
Whitespace,
|
||||
Punctuation,
|
||||
Other,
|
||||
Literal,
|
||||
)
|
||||
from pygments.token import Keyword, Name, Comment, String, Error, \
|
||||
Number, Operator, Generic, Whitespace, Punctuation, Other, Literal
|
||||
|
||||
|
||||
class FlaskyStyle(Style):
|
||||
|
|
@ -23,67 +11,76 @@ class FlaskyStyle(Style):
|
|||
styles = {
|
||||
# No corresponding class for the following:
|
||||
# Text: "", # class: ''
|
||||
Whitespace: "underline #f8f8f8", # class: 'w'
|
||||
Error: "#a40000 border:#ef2929", # class: 'err'
|
||||
Other: "#000000", # class 'x'
|
||||
Comment: "italic #8f5902", # class: 'c'
|
||||
Comment.Preproc: "noitalic", # class: 'cp'
|
||||
Keyword: "bold #004461", # class: 'k'
|
||||
Keyword.Constant: "bold #004461", # class: 'kc'
|
||||
Keyword.Declaration: "bold #004461", # class: 'kd'
|
||||
Keyword.Namespace: "bold #004461", # class: 'kn'
|
||||
Keyword.Pseudo: "bold #004461", # class: 'kp'
|
||||
Keyword.Reserved: "bold #004461", # class: 'kr'
|
||||
Keyword.Type: "bold #004461", # class: 'kt'
|
||||
Operator: "#582800", # class: 'o'
|
||||
Operator.Word: "bold #004461", # class: 'ow' - like keywords
|
||||
Punctuation: "bold #000000", # class: 'p'
|
||||
Whitespace: "underline #f8f8f8", # class: 'w'
|
||||
Error: "#a40000 border:#ef2929", # class: 'err'
|
||||
Other: "#000000", # class 'x'
|
||||
|
||||
Comment: "italic #8f5902", # class: 'c'
|
||||
Comment.Preproc: "noitalic", # class: 'cp'
|
||||
|
||||
Keyword: "bold #004461", # class: 'k'
|
||||
Keyword.Constant: "bold #004461", # class: 'kc'
|
||||
Keyword.Declaration: "bold #004461", # class: 'kd'
|
||||
Keyword.Namespace: "bold #004461", # class: 'kn'
|
||||
Keyword.Pseudo: "bold #004461", # class: 'kp'
|
||||
Keyword.Reserved: "bold #004461", # class: 'kr'
|
||||
Keyword.Type: "bold #004461", # class: 'kt'
|
||||
|
||||
Operator: "#582800", # class: 'o'
|
||||
Operator.Word: "bold #004461", # class: 'ow' - like keywords
|
||||
|
||||
Punctuation: "bold #000000", # class: 'p'
|
||||
|
||||
# because special names such as Name.Class, Name.Function, etc.
|
||||
# are not recognized as such later in the parsing, we choose them
|
||||
# to look the same as ordinary variables.
|
||||
Name: "#000000", # class: 'n'
|
||||
Name.Attribute: "#c4a000", # class: 'na' - to be revised
|
||||
Name.Builtin: "#004461", # class: 'nb'
|
||||
Name.Builtin.Pseudo: "#3465a4", # class: 'bp'
|
||||
Name.Class: "#000000", # class: 'nc' - to be revised
|
||||
Name.Constant: "#000000", # class: 'no' - to be revised
|
||||
Name.Decorator: "#888", # class: 'nd' - to be revised
|
||||
Name.Entity: "#ce5c00", # class: 'ni'
|
||||
Name.Exception: "bold #cc0000", # class: 'ne'
|
||||
Name.Function: "#000000", # class: 'nf'
|
||||
Name.Property: "#000000", # class: 'py'
|
||||
Name.Label: "#f57900", # class: 'nl'
|
||||
Name.Namespace: "#000000", # class: 'nn' - to be revised
|
||||
Name.Other: "#000000", # class: 'nx'
|
||||
Name.Tag: "bold #004461", # class: 'nt' - like a keyword
|
||||
Name.Variable: "#000000", # class: 'nv' - to be revised
|
||||
Name.Variable.Class: "#000000", # class: 'vc' - to be revised
|
||||
Name.Variable.Global: "#000000", # class: 'vg' - to be revised
|
||||
Name.Variable.Instance: "#000000", # class: 'vi' - to be revised
|
||||
Number: "#990000", # class: 'm'
|
||||
Literal: "#000000", # class: 'l'
|
||||
Literal.Date: "#000000", # class: 'ld'
|
||||
String: "#4e9a06", # class: 's'
|
||||
String.Backtick: "#4e9a06", # class: 'sb'
|
||||
String.Char: "#4e9a06", # class: 'sc'
|
||||
String.Doc: "italic #8f5902", # class: 'sd' - like a comment
|
||||
String.Double: "#4e9a06", # class: 's2'
|
||||
String.Escape: "#4e9a06", # class: 'se'
|
||||
String.Heredoc: "#4e9a06", # class: 'sh'
|
||||
String.Interpol: "#4e9a06", # class: 'si'
|
||||
String.Other: "#4e9a06", # class: 'sx'
|
||||
String.Regex: "#4e9a06", # class: 'sr'
|
||||
String.Single: "#4e9a06", # class: 's1'
|
||||
String.Symbol: "#4e9a06", # class: 'ss'
|
||||
Generic: "#000000", # class: 'g'
|
||||
Generic.Deleted: "#a40000", # class: 'gd'
|
||||
Generic.Emph: "italic #000000", # class: 'ge'
|
||||
Generic.Error: "#ef2929", # class: 'gr'
|
||||
Generic.Heading: "bold #000080", # class: 'gh'
|
||||
Generic.Inserted: "#00A000", # class: 'gi'
|
||||
Generic.Output: "#888", # class: 'go'
|
||||
Generic.Prompt: "#745334", # class: 'gp'
|
||||
Generic.Strong: "bold #000000", # class: 'gs'
|
||||
Generic.Subheading: "bold #800080", # class: 'gu'
|
||||
Generic.Traceback: "bold #a40000", # class: 'gt'
|
||||
Name: "#000000", # class: 'n'
|
||||
Name.Attribute: "#c4a000", # class: 'na' - to be revised
|
||||
Name.Builtin: "#004461", # class: 'nb'
|
||||
Name.Builtin.Pseudo: "#3465a4", # class: 'bp'
|
||||
Name.Class: "#000000", # class: 'nc' - to be revised
|
||||
Name.Constant: "#000000", # class: 'no' - to be revised
|
||||
Name.Decorator: "#888", # class: 'nd' - to be revised
|
||||
Name.Entity: "#ce5c00", # class: 'ni'
|
||||
Name.Exception: "bold #cc0000", # class: 'ne'
|
||||
Name.Function: "#000000", # class: 'nf'
|
||||
Name.Property: "#000000", # class: 'py'
|
||||
Name.Label: "#f57900", # class: 'nl'
|
||||
Name.Namespace: "#000000", # class: 'nn' - to be revised
|
||||
Name.Other: "#000000", # class: 'nx'
|
||||
Name.Tag: "bold #004461", # class: 'nt' - like a keyword
|
||||
Name.Variable: "#000000", # class: 'nv' - to be revised
|
||||
Name.Variable.Class: "#000000", # class: 'vc' - to be revised
|
||||
Name.Variable.Global: "#000000", # class: 'vg' - to be revised
|
||||
Name.Variable.Instance: "#000000", # class: 'vi' - to be revised
|
||||
|
||||
Number: "#990000", # class: 'm'
|
||||
|
||||
Literal: "#000000", # class: 'l'
|
||||
Literal.Date: "#000000", # class: 'ld'
|
||||
|
||||
String: "#4e9a06", # class: 's'
|
||||
String.Backtick: "#4e9a06", # class: 'sb'
|
||||
String.Char: "#4e9a06", # class: 'sc'
|
||||
String.Doc: "italic #8f5902", # class: 'sd' - like a comment
|
||||
String.Double: "#4e9a06", # class: 's2'
|
||||
String.Escape: "#4e9a06", # class: 'se'
|
||||
String.Heredoc: "#4e9a06", # class: 'sh'
|
||||
String.Interpol: "#4e9a06", # class: 'si'
|
||||
String.Other: "#4e9a06", # class: 'sx'
|
||||
String.Regex: "#4e9a06", # class: 'sr'
|
||||
String.Single: "#4e9a06", # class: 's1'
|
||||
String.Symbol: "#4e9a06", # class: 'ss'
|
||||
|
||||
Generic: "#000000", # class: 'g'
|
||||
Generic.Deleted: "#a40000", # class: 'gd'
|
||||
Generic.Emph: "italic #000000", # class: 'ge'
|
||||
Generic.Error: "#ef2929", # class: 'gr'
|
||||
Generic.Heading: "bold #000080", # class: 'gh'
|
||||
Generic.Inserted: "#00A000", # class: 'gi'
|
||||
Generic.Output: "#888", # class: 'go'
|
||||
Generic.Prompt: "#745334", # class: 'gp'
|
||||
Generic.Strong: "bold #000000", # class: 'gs'
|
||||
Generic.Subheading: "bold #800080", # class: 'gu'
|
||||
Generic.Traceback: "bold #a40000", # class: 'gt'
|
||||
}
|
||||
|
|
|
|||
120
docs/conf.py
120
docs/conf.py
|
|
@ -22,8 +22,8 @@ import sys
|
|||
# sys.path.insert(0, os.path.abspath('..'))
|
||||
|
||||
# Insert Camelot's path into the system.
|
||||
sys.path.insert(0, os.path.abspath(".."))
|
||||
sys.path.insert(0, os.path.abspath("_themes"))
|
||||
sys.path.insert(0, os.path.abspath('..'))
|
||||
sys.path.insert(0, os.path.abspath('_themes'))
|
||||
|
||||
import camelot
|
||||
|
||||
|
|
@ -38,33 +38,33 @@ import camelot
|
|||
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
|
||||
# ones.
|
||||
extensions = [
|
||||
"sphinx.ext.autodoc",
|
||||
"sphinx.ext.napoleon",
|
||||
"sphinx.ext.intersphinx",
|
||||
"sphinx.ext.todo",
|
||||
"sphinx.ext.viewcode",
|
||||
'sphinx.ext.autodoc',
|
||||
'sphinx.ext.napoleon',
|
||||
'sphinx.ext.intersphinx',
|
||||
'sphinx.ext.todo',
|
||||
'sphinx.ext.viewcode',
|
||||
]
|
||||
|
||||
# Add any paths that contain templates here, relative to this directory.
|
||||
templates_path = ["_templates"]
|
||||
templates_path = ['_templates']
|
||||
|
||||
# The suffix(es) of source filenames.
|
||||
# You can specify multiple suffix as a list of string:
|
||||
#
|
||||
# source_suffix = ['.rst', '.md']
|
||||
source_suffix = ".rst"
|
||||
source_suffix = '.rst'
|
||||
|
||||
# The encoding of source files.
|
||||
#
|
||||
# source_encoding = 'utf-8-sig'
|
||||
|
||||
# The master toctree document.
|
||||
master_doc = "index"
|
||||
master_doc = 'index'
|
||||
|
||||
# General information about the project.
|
||||
project = u"Camelot"
|
||||
copyright = u"2021, Camelot Developers"
|
||||
author = u"Vinayak Mehta"
|
||||
project = u'Camelot'
|
||||
copyright = u'2018, <a href="https://socialcops.com" target="_blank">SocialCops</a>'
|
||||
author = u'Vinayak Mehta'
|
||||
|
||||
# The version info for the project you're documenting, acts as replacement for
|
||||
# |version| and |release|, also used in various other places throughout the
|
||||
|
|
@ -94,7 +94,7 @@ language = None
|
|||
# List of patterns, relative to source directory, that match files and
|
||||
# directories to ignore when looking for source files.
|
||||
# This patterns also effect to html_static_path and html_extra_path
|
||||
exclude_patterns = ["_build"]
|
||||
exclude_patterns = ['_build']
|
||||
|
||||
# The reST default role (used for this markup: `text`) to use for all
|
||||
# documents.
|
||||
|
|
@ -114,7 +114,7 @@ add_module_names = True
|
|||
# show_authors = False
|
||||
|
||||
# The name of the Pygments (syntax highlighting) style to use.
|
||||
pygments_style = "flask_theme_support.FlaskyStyle"
|
||||
pygments_style = 'flask_theme_support.FlaskyStyle'
|
||||
|
||||
# A list of ignored prefixes for module index sorting.
|
||||
# modindex_common_prefix = []
|
||||
|
|
@ -130,18 +130,18 @@ todo_include_todos = True
|
|||
|
||||
# The theme to use for HTML and HTML Help pages. See the documentation for
|
||||
# a list of builtin themes.
|
||||
html_theme = "alabaster"
|
||||
html_theme = 'alabaster'
|
||||
|
||||
# Theme options are theme-specific and customize the look and feel of a theme
|
||||
# further. For a list of options available for each theme, see the
|
||||
# documentation.
|
||||
html_theme_options = {
|
||||
"show_powered_by": False,
|
||||
"github_user": "camelot-dev",
|
||||
"github_repo": "camelot",
|
||||
"github_banner": True,
|
||||
"show_related": False,
|
||||
"note_bg": "#FFF59C",
|
||||
'show_powered_by': False,
|
||||
'github_user': 'socialcopsdev',
|
||||
'github_repo': 'camelot',
|
||||
'github_banner': True,
|
||||
'show_related': False,
|
||||
'note_bg': '#FFF59C'
|
||||
}
|
||||
|
||||
# Add any paths that contain custom themes here, relative to this directory.
|
||||
|
|
@ -164,12 +164,12 @@ html_theme_options = {
|
|||
# The name of an image file (relative to this directory) to use as a favicon of
|
||||
# the docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
|
||||
# pixels large.
|
||||
html_favicon = "_static/favicon.ico"
|
||||
html_favicon = '_static/favicon.ico'
|
||||
|
||||
# Add any paths that contain custom static files (such as style sheets) here,
|
||||
# relative to this directory. They are copied after the builtin static files,
|
||||
# so a file named "default.css" will overwrite the builtin "default.css".
|
||||
html_static_path = ["_static"]
|
||||
html_static_path = ['_static']
|
||||
|
||||
# Add any extra paths that contain custom files (such as robots.txt or
|
||||
# .htaccess) here, relative to this directory. These files are copied
|
||||
|
|
@ -189,21 +189,10 @@ html_use_smartypants = True
|
|||
|
||||
# Custom sidebar templates, maps document names to template names.
|
||||
html_sidebars = {
|
||||
"index": [
|
||||
"sidebarintro.html",
|
||||
"relations.html",
|
||||
"sourcelink.html",
|
||||
"searchbox.html",
|
||||
"hacks.html",
|
||||
],
|
||||
"**": [
|
||||
"sidebarlogo.html",
|
||||
"localtoc.html",
|
||||
"relations.html",
|
||||
"sourcelink.html",
|
||||
"searchbox.html",
|
||||
"hacks.html",
|
||||
],
|
||||
'index': ['sidebarintro.html', 'relations.html', 'sourcelink.html',
|
||||
'searchbox.html', 'hacks.html'],
|
||||
'**': ['sidebarlogo.html', 'localtoc.html', 'relations.html',
|
||||
'sourcelink.html', 'searchbox.html', 'hacks.html']
|
||||
}
|
||||
|
||||
# Additional templates that should be rendered to pages, maps page names to
|
||||
|
|
@ -260,30 +249,34 @@ html_show_copyright = True
|
|||
# html_search_scorer = 'scorer.js'
|
||||
|
||||
# Output file base name for HTML help builder.
|
||||
htmlhelp_basename = "Camelotdoc"
|
||||
htmlhelp_basename = 'Camelotdoc'
|
||||
|
||||
# -- Options for LaTeX output ---------------------------------------------
|
||||
|
||||
latex_elements = {
|
||||
# The paper size ('letterpaper' or 'a4paper').
|
||||
#
|
||||
# 'papersize': 'letterpaper',
|
||||
# The font size ('10pt', '11pt' or '12pt').
|
||||
#
|
||||
# 'pointsize': '10pt',
|
||||
# Additional stuff for the LaTeX preamble.
|
||||
#
|
||||
# 'preamble': '',
|
||||
# Latex figure (float) alignment
|
||||
#
|
||||
# 'figure_align': 'htbp',
|
||||
# The paper size ('letterpaper' or 'a4paper').
|
||||
#
|
||||
# 'papersize': 'letterpaper',
|
||||
|
||||
# The font size ('10pt', '11pt' or '12pt').
|
||||
#
|
||||
# 'pointsize': '10pt',
|
||||
|
||||
# Additional stuff for the LaTeX preamble.
|
||||
#
|
||||
# 'preamble': '',
|
||||
|
||||
# Latex figure (float) alignment
|
||||
#
|
||||
# 'figure_align': 'htbp',
|
||||
}
|
||||
|
||||
# Grouping the document tree into LaTeX files. List of tuples
|
||||
# (source start file, target name, title,
|
||||
# author, documentclass [howto, manual, or own class]).
|
||||
latex_documents = [
|
||||
(master_doc, "Camelot.tex", u"Camelot Documentation", u"Vinayak Mehta", "manual"),
|
||||
(master_doc, 'Camelot.tex', u'Camelot Documentation',
|
||||
u'Vinayak Mehta', 'manual'),
|
||||
]
|
||||
|
||||
# The name of an image file (relative to this directory) to place at the top of
|
||||
|
|
@ -323,7 +316,10 @@ latex_documents = [
|
|||
|
||||
# One entry per manual page. List of tuples
|
||||
# (source start file, name, description, authors, manual section).
|
||||
man_pages = [(master_doc, "Camelot", u"Camelot Documentation", [author], 1)]
|
||||
man_pages = [
|
||||
(master_doc, 'Camelot', u'Camelot Documentation',
|
||||
[author], 1)
|
||||
]
|
||||
|
||||
# If true, show URL addresses after external links.
|
||||
#
|
||||
|
|
@ -336,15 +332,9 @@ man_pages = [(master_doc, "Camelot", u"Camelot Documentation", [author], 1)]
|
|||
# (source start file, target name, title, author,
|
||||
# dir menu entry, description, category)
|
||||
texinfo_documents = [
|
||||
(
|
||||
master_doc,
|
||||
"Camelot",
|
||||
u"Camelot Documentation",
|
||||
author,
|
||||
"Camelot",
|
||||
"One line description of project.",
|
||||
"Miscellaneous",
|
||||
),
|
||||
(master_doc, 'Camelot', u'Camelot Documentation',
|
||||
author, 'Camelot', 'One line description of project.',
|
||||
'Miscellaneous'),
|
||||
]
|
||||
|
||||
# Documents to append as an appendix to all manuals.
|
||||
|
|
@ -366,6 +356,6 @@ texinfo_documents = [
|
|||
|
||||
# Example configuration for intersphinx: refer to the Python standard library.
|
||||
intersphinx_mapping = {
|
||||
"https://docs.python.org/2": None,
|
||||
"http://pandas.pydata.org/pandas-docs/stable": None,
|
||||
'https://docs.python.org/2': None,
|
||||
'http://pandas.pydata.org/pandas-docs/stable': None
|
||||
}
|
||||
|
|
|
|||
|
|
@ -29,15 +29,15 @@ Your first contribution
|
|||
|
||||
A great way to start contributing to Camelot is to pick an issue tagged with the `help wanted`_ or the `good first issue`_ tags. If you're unable to find a good first issue, feel free to contact the maintainer.
|
||||
|
||||
.. _help wanted: https://github.com/camelot-dev/camelot/labels/help%20wanted
|
||||
.. _good first issue: https://github.com/camelot-dev/camelot/labels/good%20first%20issue
|
||||
.. _help wanted: https://github.com/socialcopsdev/camelot/labels/help%20wanted
|
||||
.. _good first issue: https://github.com/socialcopsdev/camelot/labels/good%20first%20issue
|
||||
|
||||
Setting up a development environment
|
||||
------------------------------------
|
||||
|
||||
To install the dependencies needed for development, you can use pip::
|
||||
|
||||
$ pip install "camelot-py[dev]"
|
||||
$ pip install camelot-py[dev]
|
||||
|
||||
Alternatively, you can clone the project repository, and install using pip::
|
||||
|
||||
|
|
@ -51,7 +51,7 @@ Submit a pull request
|
|||
|
||||
The preferred workflow for contributing to Camelot is to fork the `project repository`_ on GitHub, clone, develop on a branch and then finally submit a pull request. Here are the steps:
|
||||
|
||||
.. _project repository: https://github.com/camelot-dev/camelot
|
||||
.. _project repository: https://github.com/socialcopsdev/camelot
|
||||
|
||||
1. Fork the project repository. Click on the ‘Fork’ button near the top of the page. This creates a copy of the code under your account on the GitHub.
|
||||
|
||||
|
|
@ -134,7 +134,7 @@ Filing Issues
|
|||
|
||||
We use `GitHub issues`_ to keep track of all issues and pull requests. Before opening an issue (which asks a question or reports a bug), please use GitHub search to look for existing issues (both open and closed) that may be similar.
|
||||
|
||||
.. _GitHub issues: https://github.com/camelot-dev/camelot/issues
|
||||
.. _GitHub issues: https://github.com/socialcopsdev/camelot/issues
|
||||
|
||||
Questions
|
||||
^^^^^^^^^
|
||||
|
|
|
|||
|
|
@ -8,15 +8,15 @@ Camelot: PDF Table Extraction for Humans
|
|||
|
||||
Release v\ |version|. (:ref:`Installation <install>`)
|
||||
|
||||
.. image:: https://travis-ci.org/camelot-dev/camelot.svg?branch=master
|
||||
:target: https://travis-ci.org/camelot-dev/camelot
|
||||
.. image:: https://travis-ci.org/socialcopsdev/camelot.svg?branch=master
|
||||
:target: https://travis-ci.org/socialcopsdev/camelot
|
||||
|
||||
.. image:: https://readthedocs.org/projects/camelot-py/badge/?version=master
|
||||
:target: https://camelot-py.readthedocs.io/en/master/
|
||||
:alt: Documentation Status
|
||||
|
||||
.. image:: https://codecov.io/github/camelot-dev/camelot/badge.svg?branch=master&service=github
|
||||
:target: https://codecov.io/github/camelot-dev/camelot?branch=master
|
||||
.. image:: https://codecov.io/github/socialcopsdev/camelot/badge.svg?branch=master&service=github
|
||||
:target: https://codecov.io/github/socialcopsdev/camelot?branch=master
|
||||
|
||||
.. image:: https://img.shields.io/pypi/v/camelot-py.svg
|
||||
:target: https://pypi.org/project/camelot-py/
|
||||
|
|
@ -30,21 +30,15 @@ Release v\ |version|. (:ref:`Installation <install>`)
|
|||
.. image:: https://badges.gitter.im/camelot-dev/Lobby.png
|
||||
:target: https://gitter.im/camelot-dev/Lobby
|
||||
|
||||
.. image:: https://img.shields.io/badge/code%20style-black-000000.svg
|
||||
:target: https://github.com/ambv/black
|
||||
**Camelot** is a Python library that makes it easy for *anyone* to extract tables from PDF files!
|
||||
|
||||
.. image:: https://img.shields.io/badge/continous%20quality-deepsource-lightgrey
|
||||
:target: https://deepsource.io/gh/camelot-dev/camelot/?ref=repository-badge
|
||||
|
||||
**Camelot** is a Python library that can help you extract tables from PDFs!
|
||||
|
||||
.. note:: You can also check out `Excalibur`_, the web interface to Camelot!
|
||||
.. note:: You can also check out `Excalibur`_, which is a web interface for Camelot!
|
||||
|
||||
.. _Excalibur: https://github.com/camelot-dev/excalibur
|
||||
|
||||
----
|
||||
|
||||
**Here's how you can extract tables from PDFs.** You can check out the PDF used in this example `here`_.
|
||||
**Here's how you can extract tables from PDF files.** Check out the PDF used in this example `here`_.
|
||||
|
||||
.. _here: _static/pdf/foo.pdf
|
||||
|
||||
|
|
@ -54,7 +48,7 @@ Release v\ |version|. (:ref:`Installation <install>`)
|
|||
>>> tables = camelot.read_pdf('foo.pdf')
|
||||
>>> tables
|
||||
<TableList n=1>
|
||||
>>> tables.export('foo.csv', f='csv', compress=True) # json, excel, html, markdown, sqlite
|
||||
>>> tables.export('foo.csv', f='csv', compress=True) # json, excel, html
|
||||
>>> tables[0]
|
||||
<Table shape=(7, 7)>
|
||||
>>> tables[0].parsing_report
|
||||
|
|
@ -64,44 +58,35 @@ Release v\ |version|. (:ref:`Installation <install>`)
|
|||
'order': 1,
|
||||
'page': 1
|
||||
}
|
||||
>>> tables[0].to_csv('foo.csv') # to_json, to_excel, to_html, to_markdown, to_sqlite
|
||||
>>> tables[0].to_csv('foo.csv') # to_json, to_excel, to_html
|
||||
>>> tables[0].df # get a pandas DataFrame!
|
||||
|
||||
.. csv-table::
|
||||
:file: _static/csv/foo.csv
|
||||
|
||||
Camelot also comes packaged with a :ref:`command-line interface <cli>`!
|
||||
There's a :ref:`command-line interface <cli>` too!
|
||||
|
||||
.. note:: Camelot only works with text-based PDFs and not scanned documents. (As Tabula `explains`_, "If you can click and drag to select text in your table in a PDF viewer, then your PDF is text-based".)
|
||||
|
||||
You can check out some frequently asked questions :ref:`here <faq>`.
|
||||
|
||||
.. _explains: https://github.com/tabulapdf/tabula#why-tabula
|
||||
|
||||
Why Camelot?
|
||||
------------
|
||||
|
||||
- **Configurability**: Camelot gives you control over the table extraction process with :ref:`tweakable settings <advanced>`.
|
||||
- **Metrics**: You can discard bad tables based on metrics like accuracy and whitespace, without having to manually look at each table.
|
||||
- **Output**: Each table is extracted into a **pandas DataFrame**, which seamlessly integrates into `ETL and data analysis workflows`_. You can also export tables to multiple formats, which include CSV, JSON, Excel, HTML, Markdown, and Sqlite.
|
||||
- **You are in control.** Unlike other libraries and tools which either give a nice output or fail miserably (with no in-between), Camelot gives you the power to tweak table extraction. (This is important since everything in the real world, including PDF table extraction, is fuzzy.)
|
||||
- *Bad* tables can be discarded based on **metrics** like accuracy and whitespace, without ever having to manually look at each table.
|
||||
- Each table is a **pandas DataFrame**, which seamlessly integrates into `ETL and data analysis workflows`_.
|
||||
- **Export** to multiple formats, including JSON, Excel and HTML.
|
||||
|
||||
See `comparison with other PDF table extraction libraries and tools`_.
|
||||
|
||||
.. _ETL and data analysis workflows: https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873
|
||||
|
||||
See `comparison with similar libraries and tools`_.
|
||||
|
||||
.. _comparison with similar libraries and tools: https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools
|
||||
|
||||
Support the development
|
||||
-----------------------
|
||||
|
||||
If Camelot has helped you, please consider supporting its development with a one-time or monthly donation `on OpenCollective`_!
|
||||
|
||||
.. _on OpenCollective: https://opencollective.com/camelot
|
||||
.. _comparison with other PDF table extraction libraries and tools: https://github.com/socialcopsdev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools
|
||||
|
||||
The User Guide
|
||||
--------------
|
||||
|
||||
This part of the documentation begins with some background information about why Camelot was created, takes you through some implementation details, and then focuses on step-by-step instructions for getting the most out of Camelot.
|
||||
This part of the documentation begins with some background information about why Camelot was created, takes a small dip into the implementation details and then focuses on step-by-step instructions for getting the most out of Camelot.
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
|
|
@ -112,13 +97,13 @@ This part of the documentation begins with some background information about why
|
|||
user/how-it-works
|
||||
user/quickstart
|
||||
user/advanced
|
||||
user/faq
|
||||
user/cli
|
||||
|
||||
The API Documentation/Guide
|
||||
---------------------------
|
||||
|
||||
If you are looking for information on a specific function, class, or method, this part of the documentation is for you.
|
||||
If you are looking for information on a specific function, class, or method,
|
||||
this part of the documentation is for you.
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
|
|
@ -128,7 +113,8 @@ If you are looking for information on a specific function, class, or method, thi
|
|||
The Contributor Guide
|
||||
---------------------
|
||||
|
||||
If you want to contribute to the project, this part of the documentation is for you.
|
||||
If you want to contribute to the project, this part of the documentation is for
|
||||
you.
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
|
|
|
|||
|
|
@ -24,12 +24,6 @@ To process background lines, you can pass ``process_background=True``.
|
|||
>>> tables = camelot.read_pdf('background_lines.pdf', process_background=True)
|
||||
>>> tables[1].df
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot lattice -back background_lines.pdf
|
||||
|
||||
.. csv-table::
|
||||
:file: ../_static/csv/background_lines.csv
|
||||
|
||||
|
|
@ -66,13 +60,8 @@ Let's plot all the text present on the table's PDF page.
|
|||
|
||||
::
|
||||
|
||||
>>> camelot.plot(tables[0], kind='text').show()
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot lattice -plot text foo.pdf
|
||||
>>> camelot.plot(tables[0], kind='text')
|
||||
>>> plt.show()
|
||||
|
||||
.. figure:: ../_static/png/plot_text.png
|
||||
:height: 674
|
||||
|
|
@ -92,13 +81,8 @@ Let's plot the table (to see if it was detected correctly or not). This plot typ
|
|||
|
||||
::
|
||||
|
||||
>>> camelot.plot(tables[0], kind='grid').show()
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot lattice -plot grid foo.pdf
|
||||
>>> camelot.plot(tables[0], kind='grid')
|
||||
>>> plt.show()
|
||||
|
||||
.. figure:: ../_static/png/plot_table.png
|
||||
:height: 674
|
||||
|
|
@ -116,13 +100,8 @@ Now, let's plot all table boundaries present on the table's PDF page.
|
|||
|
||||
::
|
||||
|
||||
>>> camelot.plot(tables[0], kind='contour').show()
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot lattice -plot contour foo.pdf
|
||||
>>> camelot.plot(tables[0], kind='contour')
|
||||
>>> plt.show()
|
||||
|
||||
.. figure:: ../_static/png/plot_contour.png
|
||||
:height: 674
|
||||
|
|
@ -138,13 +117,8 @@ Cool, let's plot all line segments present on the table's PDF page.
|
|||
|
||||
::
|
||||
|
||||
>>> camelot.plot(tables[0], kind='line').show()
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot lattice -plot line foo.pdf
|
||||
>>> camelot.plot(tables[0], kind='line')
|
||||
>>> plt.show()
|
||||
|
||||
.. figure:: ../_static/png/plot_line.png
|
||||
:height: 674
|
||||
|
|
@ -160,13 +134,8 @@ Finally, let's plot all line intersections present on the table's PDF page.
|
|||
|
||||
::
|
||||
|
||||
>>> camelot.plot(tables[0], kind='joint').show()
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot lattice -plot joint foo.pdf
|
||||
>>> camelot.plot(tables[0], kind='joint')
|
||||
>>> plt.show()
|
||||
|
||||
.. figure:: ../_static/png/plot_joint.png
|
||||
:height: 674
|
||||
|
|
@ -182,13 +151,8 @@ You can also visualize the textedges found on a page by specifying ``kind='texte
|
|||
|
||||
::
|
||||
|
||||
>>> camelot.plot(tables[0], kind='textedge').show()
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot stream -plot textedge foo.pdf
|
||||
>>> camelot.plot(tables[0], kind='textedge')
|
||||
>>> plt.show()
|
||||
|
||||
.. figure:: ../_static/png/plot_textedge.png
|
||||
:height: 674
|
||||
|
|
@ -200,47 +164,20 @@ You can also visualize the textedges found on a page by specifying ``kind='texte
|
|||
Specify table areas
|
||||
-------------------
|
||||
|
||||
In cases such as `these <../_static/pdf/table_areas.pdf>`__, it can be useful to specify exact table boundaries. You can plot the text on this page and note the top left and bottom right coordinates of the table.
|
||||
In cases such as `these <../_static/pdf/table_areas.pdf>`__, it can be useful to specify table boundaries. You can plot the text on this page and note the top left and bottom right coordinates of the table.
|
||||
|
||||
Table areas that you want Camelot to analyze can be passed as a list of comma-separated strings to :meth:`read_pdf() <camelot.read_pdf>`, using the ``table_areas`` keyword argument.
|
||||
|
||||
.. _for now: https://github.com/socialcopsdev/camelot/issues/102
|
||||
|
||||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('table_areas.pdf', flavor='stream', table_areas=['316,499,566,337'])
|
||||
>>> tables[0].df
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot stream -T 316,499,566,337 table_areas.pdf
|
||||
|
||||
.. csv-table::
|
||||
:file: ../_static/csv/table_areas.csv
|
||||
|
||||
.. note:: ``table_areas`` accepts strings of the form x1,y1,x2,y2 where (x1, y1) -> top-left and (x2, y2) -> bottom-right in PDF coordinate space. In PDF coordinate space, the bottom-left corner of the page is the origin, with coordinates (0, 0).
|
||||
|
||||
Specify table regions
|
||||
---------------------
|
||||
|
||||
However there may be cases like `[1] <../_static/pdf/table_regions.pdf>`__ and `[2] <https://github.com/camelot-dev/camelot/blob/master/tests/files/tableception.pdf>`__, where the table might not lie at the exact coordinates every time but in an approximate region.
|
||||
|
||||
You can use the ``table_regions`` keyword argument to :meth:`read_pdf() <camelot.read_pdf>` to solve for such cases. When ``table_regions`` is specified, Camelot will only analyze the specified regions to look for tables.
|
||||
|
||||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('table_regions.pdf', table_regions=['170,370,560,270'])
|
||||
>>> tables[0].df
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot lattice -R 170,370,560,270 table_regions.pdf
|
||||
|
||||
.. csv-table::
|
||||
:file: ../_static/csv/table_regions.csv
|
||||
|
||||
Specify column separators
|
||||
-------------------------
|
||||
|
||||
|
|
@ -259,12 +196,6 @@ Let's get back to the *x* coordinates we got from plotting the text that exists
|
|||
>>> tables = camelot.read_pdf('column_separators.pdf', flavor='stream', columns=['72,95,209,327,442,529,566,606,683'])
|
||||
>>> tables[0].df
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot stream -C 72,95,209,327,442,529,566,606,683 column_separators.pdf
|
||||
|
||||
.. csv-table::
|
||||
|
||||
"...","...","...","...","...","...","...","...","...","..."
|
||||
|
|
@ -284,12 +215,6 @@ To deal with cases like the output from the previous section, you can pass ``spl
|
|||
>>> tables = camelot.read_pdf('column_separators.pdf', flavor='stream', columns=['72,95,209,327,442,529,566,606,683'], split_text=True)
|
||||
>>> tables[0].df
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot -split stream -C 72,95,209,327,442,529,566,606,683 column_separators.pdf
|
||||
|
||||
.. csv-table::
|
||||
|
||||
"...","...","...","...","...","...","...","...","...","..."
|
||||
|
|
@ -310,19 +235,13 @@ In this case, the text that `other tools`_ return, will be ``24.912``. This is r
|
|||
|
||||
You can solve this by passing ``flag_size=True``, which will enclose the superscripts and subscripts with ``<s></s>``, based on font size, as shown below.
|
||||
|
||||
.. _other tools: https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools
|
||||
.. _other tools: https://github.com/socialcopsdev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools
|
||||
|
||||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('superscript.pdf', flavor='stream', flag_size=True)
|
||||
>>> tables[0].df
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot -flag stream superscript.pdf
|
||||
|
||||
.. csv-table::
|
||||
|
||||
"...","...","...","...","...","...","...","...","...","...","..."
|
||||
|
|
@ -331,85 +250,10 @@ You can solve this by passing ``flag_size=True``, which will enclose the supersc
|
|||
"Madhya Pradesh","27.13","23.57","-","-","3.56","0.38","-","1.86","-","1.28"
|
||||
"...","...","...","...","...","...","...","...","...","...","..."
|
||||
|
||||
Strip characters from text
|
||||
--------------------------
|
||||
Control how text is grouped into rows
|
||||
-------------------------------------
|
||||
|
||||
You can strip unwanted characters like spaces, dots and newlines from a string using the ``strip_text`` keyword argument. Take a look at `this PDF <https://github.com/camelot-dev/camelot/blob/master/tests/files/tabula/12s0324.pdf>`_ as an example, the text at the start of each row contains a lot of unwanted spaces, dots and newlines.
|
||||
|
||||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('12s0324.pdf', flavor='stream', strip_text=' .\n')
|
||||
>>> tables[0].df
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot -strip ' .\n' stream 12s0324.pdf
|
||||
|
||||
.. csv-table::
|
||||
|
||||
"...","...","...","...","...","...","...","...","...","..."
|
||||
"Forcible rape","17.5","2.6","14.9","17.2","2.5","14.7","–","–","–"
|
||||
"Robbery","102.1","25.5","76.6","90.0","22.9","67.1","12.1","2.5","9.5"
|
||||
"Aggravated assault","338.4","40.1","298.3","264.0","30.2","233.8","74.4","9.9","64.5"
|
||||
"Property crime","1,396 .4","338 .7","1,057 .7","875 .9","210 .8","665 .1","608 .2","127 .9","392 .6"
|
||||
"Burglary","240.9","60.3","180.6","205.0","53.4","151.7","35.9","6.9","29.0"
|
||||
"...","...","...","...","...","...","...","...","...","..."
|
||||
|
||||
Improve guessed table areas
|
||||
---------------------------
|
||||
|
||||
While using :ref:`Stream <stream>`, automatic table detection can fail for PDFs like `this one <https://github.com/camelot-dev/camelot/blob/master/tests/files/edge_tol.pdf>`_. That's because the text is relatively far apart vertically, which can lead to shorter textedges being calculated.
|
||||
|
||||
.. note:: To know more about how textedges are calculated to guess table areas, you can see pages 20, 35 and 40 of `Anssi Nurminen's master's thesis <http://dspace.cc.tut.fi/dpub/bitstream/handle/123456789/21520/Nurminen.pdf?sequence=3>`_.
|
||||
|
||||
Let's see the table area that is detected by default.
|
||||
|
||||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('edge_tol.pdf', flavor='stream')
|
||||
>>> camelot.plot(tables[0], kind='contour').show()
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot stream -plot contour edge.pdf
|
||||
|
||||
.. figure:: ../_static/png/edge_tol_1.png
|
||||
:height: 674
|
||||
:width: 1366
|
||||
:scale: 50%
|
||||
:alt: Table area with default edge_tol
|
||||
:align: left
|
||||
|
||||
To improve the detected area, you can increase the ``edge_tol`` (default: 50) value to counter the effect of text being placed relatively far apart vertically. Larger ``edge_tol`` will lead to longer textedges being detected, leading to an improved guess of the table area. Let's use a value of 500.
|
||||
|
||||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('edge_tol.pdf', flavor='stream', edge_tol=500)
|
||||
>>> camelot.plot(tables[0], kind='contour').show()
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot stream -e 500 -plot contour edge.pdf
|
||||
|
||||
.. figure:: ../_static/png/edge_tol_2.png
|
||||
:height: 674
|
||||
:width: 1366
|
||||
:scale: 50%
|
||||
:alt: Table area with default edge_tol
|
||||
:align: left
|
||||
|
||||
As you can see, the guessed table area has improved!
|
||||
|
||||
Improve guessed table rows
|
||||
--------------------------
|
||||
|
||||
You can pass ``row_tol=<+int>`` to group the rows closer together, as shown below.
|
||||
You can pass ``row_close_tol=<+int>`` to group the rows closer together, as shown below.
|
||||
|
||||
::
|
||||
|
||||
|
|
@ -427,15 +271,9 @@ You can pass ``row_tol=<+int>`` to group the rows closer together, as shown belo
|
|||
|
||||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('group_rows.pdf', flavor='stream', row_tol=10)
|
||||
>>> tables = camelot.read_pdf('group_rows.pdf', flavor='stream', row_close_tol=10)
|
||||
>>> tables[0].df
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot stream -r 10 group_rows.pdf
|
||||
|
||||
.. csv-table::
|
||||
|
||||
"Clave","Nombre Entidad","Clave","","Nombre Municipio","Clave","Nombre Localidad"
|
||||
|
|
@ -447,11 +285,11 @@ You can pass ``row_tol=<+int>`` to group the rows closer together, as shown belo
|
|||
Detect short lines
|
||||
------------------
|
||||
|
||||
There might be cases while using :ref:`Lattice <lattice>` when smaller lines don't get detected. The size of the smallest line that gets detected is calculated by dividing the PDF page's dimensions with a scaling factor called ``line_scale``. By default, its value is 15.
|
||||
There might be cases while using :ref:`Lattice <lattice>` when smaller lines don't get detected. The size of the smallest line that gets detected is calculated by dividing the PDF page's dimensions with a scaling factor called ``line_size_scaling``. By default, its value is 15.
|
||||
|
||||
As you can guess, the larger the ``line_scale``, the smaller the size of lines getting detected.
|
||||
As you can guess, the larger the ``line_size_scaling``, the smaller the size of lines getting detected.
|
||||
|
||||
.. warning:: Making ``line_scale`` very large (>150) will lead to text getting detected as lines.
|
||||
.. warning:: Making ``line_size_scaling`` very large (>150) will lead to text getting detected as lines.
|
||||
|
||||
Here's a `PDF <../_static/pdf/short_lines.pdf>`__ where small lines separating the the headers don't get detected with the default value of 15.
|
||||
|
||||
|
|
@ -464,24 +302,20 @@ Let's plot the table for this PDF.
|
|||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('short_lines.pdf')
|
||||
>>> camelot.plot(tables[0], kind='grid').show()
|
||||
>>> camelot.plot(tables[0], kind='grid')
|
||||
>>> plt.show()
|
||||
|
||||
.. figure:: ../_static/png/short_lines_1.png
|
||||
:alt: A plot of the PDF table with short lines
|
||||
:align: left
|
||||
|
||||
Clearly, the smaller lines separating the headers, couldn't be detected. Let's try with ``line_scale=40``, and plot the table again.
|
||||
Clearly, the smaller lines separating the headers, couldn't be detected. Let's try with ``line_size_scaling=40``, and plot the table again.
|
||||
|
||||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('short_lines.pdf', line_scale=40)
|
||||
>>> camelot.plot(tables[0], kind='grid').show()
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot lattice -scale 40 -plot grid short_lines.pdf
|
||||
>>> tables = camelot.read_pdf('short_lines.pdf', line_size_scaling=40)
|
||||
>>> camelot.plot(tables[0], kind='grid')
|
||||
>>> plt.show()
|
||||
|
||||
.. figure:: ../_static/png/short_lines_2.png
|
||||
:alt: An improved plot of the PDF table with short lines
|
||||
|
|
@ -522,7 +356,7 @@ We'll use the `PDF <../_static/pdf/short_lines.pdf>`__ from the previous example
|
|||
|
||||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('short_lines.pdf', line_scale=40, shift_text=[''])
|
||||
>>> tables = camelot.read_pdf('short_lines.pdf', line_size_scaling=40, shift_text=[''])
|
||||
>>> tables[0].df
|
||||
|
||||
.. csv-table::
|
||||
|
|
@ -543,15 +377,9 @@ No surprises there — it did remain in place (observe the strings "2400" and "A
|
|||
|
||||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('short_lines.pdf', line_scale=40, shift_text=['r', 'b'])
|
||||
>>> tables = camelot.read_pdf('short_lines.pdf', line_size_scaling=40, shift_text=['r', 'b'])
|
||||
>>> tables[0].df
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot lattice -scale 40 -shift r -shift b short_lines.pdf
|
||||
|
||||
.. csv-table::
|
||||
|
||||
"Investigations","No. ofHHs","Age/Sex/Physiological Group","Preva-lence","C.I*","RelativePrecision","Sample sizeper State"
|
||||
|
|
@ -597,12 +425,6 @@ We don't need anything else. Now, let's pass ``copy_text=['v']`` to copy text in
|
|||
>>> tables = camelot.read_pdf('copy_text.pdf', copy_text=['v'])
|
||||
>>> tables[0].df
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot lattice -copy v copy_text.pdf
|
||||
|
||||
.. csv-table::
|
||||
|
||||
"Sl. No.","Name of State/UT","Name of District","Disease/ Illness","No. of Cases","No. of Deaths","Date of start of outbreak","Date of reporting","Current Status","..."
|
||||
|
|
@ -612,37 +434,3 @@ We don't need anything else. Now, let's pass ``copy_text=['v']`` to copy text in
|
|||
"4","West Bengal","West Medinipur","iv. Acute Diarrhoeal Disease","145","0","04/01/14","05/01/14","Under control","..."
|
||||
"4","West Bengal","Birbhum","v. Food Poisoning","199","0","31/12/13","31/12/13","Under control","..."
|
||||
"4","West Bengal","Howrah","vi. Viral Hepatitis A &E","85","0","26/12/13","27/12/13","Under surveillance","..."
|
||||
|
||||
Tweak layout generation
|
||||
-----------------------
|
||||
|
||||
Camelot is built on top of PDFMiner's functionality of grouping characters on a page into words and sentences. In some cases (such as `#170 <https://github.com/camelot-dev/camelot/issues/170>`_ and `#215 <https://github.com/camelot-dev/camelot/issues/215>`_), PDFMiner can group characters that should belong to the same sentence into separate sentences.
|
||||
|
||||
To deal with such cases, you can tweak PDFMiner's `LAParams kwargs <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ to improve layout generation, by passing the keyword arguments as a dict using ``layout_kwargs`` in :meth:`read_pdf() <camelot.read_pdf>`. To know more about the parameters you can tweak, you can check out `PDFMiner docs <https://pdfminersix.rtfd.io/en/latest/reference/composable.html>`_.
|
||||
|
||||
::
|
||||
|
||||
>>> tables = camelot.read_pdf('foo.pdf', layout_kwargs={'detect_vertical': False})
|
||||
|
||||
.. _image-conversion-backend:
|
||||
|
||||
Use alternate image conversion backends
|
||||
---------------------------------------
|
||||
|
||||
When using the :ref:`Lattice <lattice>` flavor, Camelot uses ``ghostscript`` to convert PDF pages to images for line recognition. If you face installation issues with ``ghostscript``, you can use an alternate image conversion backend called ``poppler``. You can specify which image conversion backend you want to use with::
|
||||
|
||||
>>> tables = camelot.read_pdf(filename, backend="ghostscript") # default
|
||||
>>> tables = camelot.read_pdf(filename, backend="poppler")
|
||||
|
||||
.. note:: ``ghostscript`` will be replaced by ``poppler`` as the default image conversion backend in ``v0.12.0``.
|
||||
|
||||
If you face issues with both ``ghostscript`` and ``poppler``, you can supply your own image conversion backend::
|
||||
|
||||
>>> class ConversionBackend(object):
|
||||
>>> def convert(pdf_path, png_path):
|
||||
>>> # read pdf page from pdf_path
|
||||
>>> # convert pdf page to image
|
||||
>>> # write image to png_path
|
||||
>>> pass
|
||||
>>>
|
||||
>>> tables = camelot.read_pdf(filename, backend=ConversionBackend())
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@ You can print the help for the interface by typing ``camelot --help`` in your fa
|
|||
|
||||
Options:
|
||||
--version Show the version and exit.
|
||||
-q, --quiet TEXT Suppress logs and warnings.
|
||||
-v, --verbose Verbose.
|
||||
-p, --pages TEXT Comma-separated page numbers. Example: 1,3,4
|
||||
or 1,4-end.
|
||||
-pw, --password TEXT Password for decryption.
|
||||
|
|
@ -26,8 +26,6 @@ You can print the help for the interface by typing ``camelot --help`` in your fa
|
|||
-split, --split_text Split text that spans across multiple cells.
|
||||
-flag, --flag_size Flag text based on font size. Useful to
|
||||
detect super/subscripts.
|
||||
-strip, --strip_text Characters that should be stripped from a
|
||||
string before assigning it to a cell.
|
||||
-M, --margins <FLOAT FLOAT FLOAT>...
|
||||
PDFMiner char_margin, line_margin and
|
||||
word_margin.
|
||||
|
|
|
|||
|
|
@ -1,70 +0,0 @@
|
|||
.. _faq:
|
||||
|
||||
Frequently Asked Questions
|
||||
==========================
|
||||
|
||||
This part of the documentation answers some common questions. To add questions, please open an issue `here <https://github.com/camelot-dev/camelot/issues/new>`_.
|
||||
|
||||
Does Camelot work with image-based PDFs?
|
||||
----------------------------------------
|
||||
|
||||
**No**, Camelot only works with text-based PDFs and not scanned documents. (As Tabula `explains <https://github.com/tabulapdf/tabula#why-tabula>`_, "If you can click and drag to select text in your table in a PDF viewer, then your PDF is text-based".)
|
||||
|
||||
How to reduce memory usage for long PDFs?
|
||||
-----------------------------------------
|
||||
|
||||
During table extraction from long PDF documents, RAM usage can grow significantly.
|
||||
|
||||
A simple workaround is to divide the extraction into chunks, and save extracted data to disk at the end of every chunk.
|
||||
|
||||
For more details, check out this code snippet from `@anakin87 <https://github.com/anakin87>`_:
|
||||
|
||||
::
|
||||
|
||||
import camelot
|
||||
|
||||
|
||||
def chunks(l, n):
|
||||
"""Yield successive n-sized chunks from l."""
|
||||
for i in range(0, len(l), n):
|
||||
yield l[i : i + n]
|
||||
|
||||
|
||||
def extract_tables(filepath, pages, chunks=50, export_path=".", params={}):
|
||||
"""
|
||||
Divide the extraction work into n chunks. At the end of every chunk,
|
||||
save data on disk and free RAM.
|
||||
|
||||
filepath : str
|
||||
Filepath or URL of the PDF file.
|
||||
pages : str, optional (default: '1')
|
||||
Comma-separated page numbers.
|
||||
Example: '1,3,4' or '1,4-end' or 'all'.
|
||||
"""
|
||||
|
||||
# get list of pages from camelot.handlers.PDFHandler
|
||||
handler = camelot.handlers.PDFHandler(filepath)
|
||||
page_list = handler._get_pages(filepath, pages=pages)
|
||||
|
||||
# chunk pages list
|
||||
page_chunks = list(chunks(page_list, chunks))
|
||||
|
||||
# extraction and export
|
||||
for chunk in page_chunks:
|
||||
pages_string = str(chunk).replace("[", "").replace("]", "")
|
||||
tables = camelot.read_pdf(filepath, pages=pages_string, **params)
|
||||
tables.export(f"{export_path}/tables.csv")
|
||||
|
||||
How can I supply my own image conversion backend to Lattice?
|
||||
------------------------------------------------------------
|
||||
|
||||
When using the :ref:`Lattice <lattice>` flavor, you can supply your own :ref:`image conversion backend <image-conversion-backend>` by creating a class with a ``convert`` method as follows::
|
||||
|
||||
>>> class ConversionBackend(object):
|
||||
>>> def convert(pdf_path, png_path):
|
||||
>>> # read pdf page from pdf_path
|
||||
>>> # convert pdf page to image
|
||||
>>> # write image to png_path
|
||||
>>> pass
|
||||
>>>
|
||||
>>> tables = camelot.read_pdf(filename, backend=ConversionBackend())
|
||||
|
|
@ -16,11 +16,11 @@ Stream can be used to parse tables that have whitespaces between cells to simula
|
|||
|
||||
1. Words on the PDF page are grouped into text rows based on their *y* axis overlaps.
|
||||
|
||||
2. Textedges are calculated and then used to guess interesting table areas on the PDF page. You can read `Anssi Nurminen's master's thesis <https://pdfs.semanticscholar.org/a9b1/67a86fb189bfcd366c3839f33f0404db9c10.pdf>`_ to know more about this table detection technique. [See pages 20, 35 and 40]
|
||||
2. Textedges are calculated and then used to guess interesting table areas on the PDF page. You can read `Anssi Nurminen's master's thesis <http://dspace.cc.tut.fi/dpub/bitstream/handle/123456789/21520/Nurminen.pdf?sequence=3>`_ to know more about this table detection technique. [See pages 20, 35 and 40]
|
||||
|
||||
3. The number of columns inside each table area are then guessed. This is done by calculating the mode of number of words in each text row. Based on this mode, words in each text row are chosen to calculate a list of column *x* ranges.
|
||||
|
||||
4. Words that lie inside/outside the current column *x* ranges are then used to extend the current list of columns.
|
||||
4. Words that lie inside/outside the current column *x* ranges are then used to extend extend the current list of columns.
|
||||
|
||||
5. Finally, a table is formed using the text rows' *y* ranges and column *x* ranges and words found on the page are assigned to the table's cells based on their *x* and *y* coordinates.
|
||||
|
||||
|
|
|
|||
|
|
@ -3,60 +3,74 @@
|
|||
Installation of dependencies
|
||||
============================
|
||||
|
||||
The dependencies `Ghostscript <https://www.ghostscript.com>`_ and `Tkinter <https://wiki.python.org/moin/TkInter>`_ can be installed using your system's package manager or by running their installer.
|
||||
The dependencies `Tkinter`_ and `ghostscript`_ can be installed using your system's package manager. You can run one of the following, based on your OS.
|
||||
|
||||
.. _Tkinter: https://wiki.python.org/moin/TkInter
|
||||
.. _ghostscript: https://www.ghostscript.com
|
||||
|
||||
OS-specific instructions
|
||||
------------------------
|
||||
|
||||
Ubuntu
|
||||
^^^^^^
|
||||
For Ubuntu
|
||||
^^^^^^^^^^
|
||||
::
|
||||
|
||||
$ apt install ghostscript python3-tk
|
||||
$ apt install python-tk ghostscript
|
||||
|
||||
MacOS
|
||||
^^^^^
|
||||
Or for Python 3::
|
||||
|
||||
$ apt install python3-tk ghostscript
|
||||
|
||||
For macOS
|
||||
^^^^^^^^^
|
||||
::
|
||||
|
||||
$ brew install ghostscript tcl-tk
|
||||
$ brew install tcl-tk ghostscript
|
||||
|
||||
Windows
|
||||
^^^^^^^
|
||||
For Windows
|
||||
^^^^^^^^^^^
|
||||
|
||||
For Ghostscript, you can get the installer at their `downloads page <https://www.ghostscript.com/download/gsdnld.html>`_. And for Tkinter, you can download the `ActiveTcl Community Edition <https://www.activestate.com/activetcl/downloads>`_ from ActiveState.
|
||||
For Tkinter, you can download the `ActiveTcl Community Edition`_ from ActiveState. For ghostscript, you can get the installer at the `ghostscript downloads page`_.
|
||||
|
||||
Checks to see if dependencies are installed correctly
|
||||
-----------------------------------------------------
|
||||
After installing ghostscript, you'll need to reboot your system to make sure that the ghostscript executable's path is in the windows PATH environment variable. In case you don't want to reboot, you can manually add the ghostscript executable's path to the PATH variable, `as shown here`_.
|
||||
|
||||
You can run the following checks to see if the dependencies were installed correctly.
|
||||
.. _ActiveTcl Community Edition: https://www.activestate.com/activetcl/downloads
|
||||
.. _ghostscript downloads page: https://www.ghostscript.com/download/gsdnld.html
|
||||
.. _as shown here: https://java.com/en/download/help/path.xml
|
||||
|
||||
For Ghostscript
|
||||
^^^^^^^^^^^^^^^
|
||||
Checks to see if dependencies were installed correctly
|
||||
------------------------------------------------------
|
||||
|
||||
Open the Python REPL and run the following:
|
||||
|
||||
For Ubuntu/MacOS::
|
||||
|
||||
>>> from ctypes.util import find_library
|
||||
>>> find_library("gs")
|
||||
"libgs.so.9"
|
||||
|
||||
For Windows::
|
||||
|
||||
>>> import ctypes
|
||||
>>> from ctypes.util import find_library
|
||||
>>> find_library("".join(("gsdll", str(ctypes.sizeof(ctypes.c_voidp) * 8), ".dll")))
|
||||
<name-of-ghostscript-library-on-windows>
|
||||
|
||||
**Check:** The output of the ``find_library`` function should not be empty.
|
||||
|
||||
If the output is empty, then it's possible that the Ghostscript library is not available one of the ``LD_LIBRARY_PATH``/``DYLD_LIBRARY_PATH``/``PATH`` variables depending on your operating system. In this case, you may have to modify one of those path variables.
|
||||
You can do the following checks to see if the dependencies were installed correctly.
|
||||
|
||||
For Tkinter
|
||||
^^^^^^^^^^^
|
||||
|
||||
Launch Python and then import Tkinter::
|
||||
Launch Python, and then at the prompt, type::
|
||||
|
||||
>>> import Tkinter
|
||||
|
||||
Or in Python 3::
|
||||
|
||||
>>> import tkinter
|
||||
|
||||
**Check:** Importing ``tkinter`` should not raise an import error.
|
||||
If you have Tkinter, Python will not print an error message, and if not, you will see an ``ImportError``.
|
||||
|
||||
For ghostscript
|
||||
^^^^^^^^^^^^^^^
|
||||
|
||||
Run the following to check the ghostscript version.
|
||||
|
||||
For Ubuntu/macOS::
|
||||
|
||||
$ gs -version
|
||||
|
||||
For Windows::
|
||||
|
||||
C:\> gswin64c.exe -version
|
||||
|
||||
Or for Windows 32-bit::
|
||||
|
||||
C:\> gswin32c.exe -version
|
||||
|
||||
If you have ghostscript, you should see the ghostscript version and copyright information.
|
||||
|
|
|
|||
|
|
@ -5,36 +5,43 @@ Installation of Camelot
|
|||
|
||||
This part of the documentation covers the steps to install Camelot.
|
||||
|
||||
After :ref:`installing the dependencies <install_deps>`, which include `Ghostscript <https://www.ghostscript.com>`_ and `Tkinter <https://wiki.python.org/moin/TkInter>`_, you can use one of the following methods to install Camelot:
|
||||
Using conda
|
||||
-----------
|
||||
|
||||
.. warning:: The ``lattice`` flavor will fail to run if Ghostscript is not installed. You may run into errors as shown in `issue #193 <https://github.com/camelot-dev/camelot/issues/193>`_.
|
||||
|
||||
pip
|
||||
---
|
||||
|
||||
To install Camelot from PyPI using ``pip``, please include the extra ``cv`` requirement as shown::
|
||||
|
||||
$ pip install "camelot-py[base]"
|
||||
|
||||
conda
|
||||
-----
|
||||
|
||||
`conda`_ is a package manager and environment management system for the `Anaconda <https://anaconda.org>`_ distribution. It can be used to install Camelot from the ``conda-forge`` channel::
|
||||
The easiest way to install Camelot is to install it with `conda`_, which is a package manager and environment management system for the `Anaconda`_ distribution.
|
||||
::
|
||||
|
||||
$ conda install -c conda-forge camelot-py
|
||||
|
||||
.. note:: Camelot is available for Python 2.7, 3.5 and 3.6 on Linux, macOS and Windows. For Windows, you will need to install ghostscript which you can get from their `downloads page`_.
|
||||
|
||||
.. _conda: https://conda.io/docs/
|
||||
.. _Anaconda: http://docs.continuum.io/anaconda/
|
||||
.. _downloads page: https://www.ghostscript.com/download/gsdnld.html
|
||||
.. _conda-forge: https://conda-forge.org/
|
||||
|
||||
Using pip
|
||||
---------
|
||||
|
||||
After :ref:`installing the dependencies <install_deps>`, which include `Tkinter`_ and `ghostscript`_, you can simply use pip to install Camelot::
|
||||
|
||||
$ pip install camelot-py[cv]
|
||||
|
||||
.. _Tkinter: https://wiki.python.org/moin/TkInter
|
||||
.. _ghostscript: https://www.ghostscript.com
|
||||
|
||||
From the source code
|
||||
--------------------
|
||||
|
||||
After :ref:`installing the dependencies <install_deps>`, you can install Camelot from source by:
|
||||
After :ref:`installing the dependencies <install_deps>`, you can install from the source by:
|
||||
|
||||
1. Cloning the GitHub repository.
|
||||
::
|
||||
|
||||
$ git clone https://www.github.com/camelot-dev/camelot
|
||||
$ git clone https://www.github.com/socialcopsdev/camelot
|
||||
|
||||
2. And then simply using pip again.
|
||||
2. Then simply using pip again.
|
||||
::
|
||||
|
||||
$ cd camelot
|
||||
$ pip install ".[base]"
|
||||
$ pip install ".[cv]"
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ Here is a `comparison`_ of Camelot's output with outputs from other open-source
|
|||
.. _pdf-table-extract: https://github.com/ashima/pdf-table-extract
|
||||
.. _PDFTables: https://pdftables.com/
|
||||
.. _Smallpdf: https://smallpdf.com
|
||||
.. _comparison: https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools
|
||||
.. _comparison: https://github.com/socialcopsdev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools
|
||||
|
||||
What's in a name?
|
||||
-----------------
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@ Begin by importing the Camelot module::
|
|||
|
||||
>>> import camelot
|
||||
|
||||
Now, let's try to read a PDF. (You can check out the PDF used in this example `here`_.) Since the PDF has a table with clearly demarcated lines, we will use the :ref:`Lattice <lattice>` method here.
|
||||
Now, let's try to read a PDF. (You can check out the PDF used in this example `here`_.) Since the PDF has a table with clearly demarcated lines, we will use the :ref:`Lattice <lattice>` method here. To do that, we will set the ``mesh`` keyword argument to ``True``.
|
||||
|
||||
.. note:: :ref:`Lattice <lattice>` is used by default. You can use :ref:`Stream <stream>` with ``flavor='stream'``.
|
||||
|
||||
|
|
@ -56,7 +56,7 @@ Woah! The accuracy is top-notch and there is less whitespace, which means the ta
|
|||
.. csv-table::
|
||||
:file: ../_static/csv/foo.csv
|
||||
|
||||
Looks good! You can now export the table as a CSV file using its :meth:`to_csv() <camelot.core.Table.to_csv>` method. Alternatively you can use :meth:`to_json() <camelot.core.Table.to_json>`, :meth:`to_excel() <camelot.core.Table.to_excel>` :meth:`to_html() <camelot.core.Table.to_html>` :meth:`to_markdown() <camelot.core.Table.to_markdown>` or :meth:`to_sqlite() <camelot.core.Table.to_sqlite>` methods to export the table as JSON, Excel, HTML files or a sqlite database respectively.
|
||||
Looks good! You can now export the table as a CSV file using its :meth:`to_csv() <camelot.core.Table.to_csv>` method. Alternatively you can use :meth:`to_json() <camelot.core.Table.to_json>`, :meth:`to_excel() <camelot.core.Table.to_excel>` or :meth:`to_html() <camelot.core.Table.to_html>` methods to export the table as JSON, Excel and HTML files respectively.
|
||||
|
||||
::
|
||||
|
||||
|
|
@ -70,13 +70,7 @@ You can also export all tables at once, using the :class:`tables <camelot.core.T
|
|||
|
||||
>>> tables.export('foo.csv', f='csv')
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot --format csv --output foo.csv lattice foo.pdf
|
||||
|
||||
This will export all tables as CSV files at the path specified. Alternatively, you can use ``f='json'``, ``f='excel'``, ``f='html'``, ``f='markdown'`` or ``f='sqlite'``.
|
||||
This will export all tables as CSV files at the path specified. Alternatively, you can use ``f='json'``, ``f='excel'`` or ``f='html'``.
|
||||
|
||||
.. note:: The :meth:`export() <camelot.core.TableList.export>` method exports files with a ``page-*-table-*`` suffix. In the example above, the single table in the list will be exported to ``foo-page-1-table-1.csv``. If the list contains multiple tables, multiple CSV files will be created. To avoid filling up your path with multiple files, you can use ``compress=True``, which will create a single ZIP file at your path with all the CSV files.
|
||||
|
||||
|
|
@ -91,12 +85,6 @@ By default, Camelot only uses the first page of the PDF to extract tables. To sp
|
|||
|
||||
>>> camelot.read_pdf('your.pdf', pages='1,2,3')
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot --pages 1,2,3 lattice your.pdf
|
||||
|
||||
The ``pages`` keyword argument accepts pages as comma-separated string of page numbers. You can also specify page ranges — for example, ``pages=1,4-10,20-30`` or ``pages=1,4-10,20-end``.
|
||||
|
||||
Reading encrypted PDFs
|
||||
|
|
@ -110,12 +98,6 @@ To extract tables from encrypted PDF files you must provide a password when call
|
|||
>>> tables
|
||||
<TableList n=1>
|
||||
|
||||
.. tip::
|
||||
Here's how you can do the same with the :ref:`command-line interface <cli>`.
|
||||
::
|
||||
|
||||
$ camelot --password userpass lattice foo.pdf
|
||||
|
||||
Currently Camelot only supports PDFs encrypted with ASCII passwords and algorithm `code 1 or 2`_. An exception is thrown if the PDF cannot be read. This may be due to no password being provided, an incorrect password, or an unsupported encryption algorithm.
|
||||
|
||||
Further encryption support may be added in future, however in the meantime if your PDF files are using unsupported encryption algorithms you are advised to remove encryption before calling :meth:`read_pdf() <camelot.read_pdf>`. This can been successfully achieved with third-party tools such as `QPDF`_.
|
||||
|
|
|
|||
|
|
@ -0,0 +1,8 @@
|
|||
click>=6.7
|
||||
matplotlib>=2.2.3
|
||||
numpy>=1.13.3
|
||||
opencv-python>=3.4.2.17
|
||||
openpyxl>=2.5.8
|
||||
pandas>=0.23.4
|
||||
pdfminer.six>=20170720
|
||||
PyPDF2>=1.26.0
|
||||
106
setup.py
106
setup.py
|
|
@ -6,78 +6,76 @@ from setuptools import find_packages
|
|||
|
||||
here = os.path.abspath(os.path.dirname(__file__))
|
||||
about = {}
|
||||
with open(os.path.join(here, "camelot", "__version__.py"), "r") as f:
|
||||
with open(os.path.join(here, 'camelot', '__version__.py'), 'r') as f:
|
||||
exec(f.read(), about)
|
||||
|
||||
with open("README.md", "r") as f:
|
||||
with open('README.md', 'r') as f:
|
||||
readme = f.read()
|
||||
|
||||
|
||||
requires = [
|
||||
"chardet>=3.0.4",
|
||||
"click>=6.7",
|
||||
"numpy>=1.13.3",
|
||||
"openpyxl>=2.5.8",
|
||||
"pandas>=0.23.4",
|
||||
"pdfminer.six>=20200726",
|
||||
"PyPDF2>=1.26.0",
|
||||
"tabulate>=0.8.9",
|
||||
'chardet>=3.0.4',
|
||||
'click>=6.7',
|
||||
'numpy>=1.13.3',
|
||||
'openpyxl>=2.5.8',
|
||||
'pandas>=0.23.4',
|
||||
'pdfminer.six>=20170720',
|
||||
'PyPDF2>=1.26.0'
|
||||
]
|
||||
|
||||
base_requires = ["ghostscript>=0.7", "opencv-python>=3.4.2.17", "pdftopng>=0.2.3"]
|
||||
cv_requires = [
|
||||
'opencv-python>=3.4.2.17'
|
||||
]
|
||||
|
||||
plot_requires = [
|
||||
"matplotlib>=2.2.3",
|
||||
'matplotlib>=2.2.3',
|
||||
]
|
||||
|
||||
dev_requires = [
|
||||
"codecov>=2.0.15",
|
||||
"pytest>=5.4.3",
|
||||
"pytest-cov>=2.10.0",
|
||||
"pytest-mpl>=0.11",
|
||||
"pytest-runner>=5.2",
|
||||
"Sphinx>=3.1.2",
|
||||
"sphinx-autobuild>=2021.3.14",
|
||||
'codecov>=2.0.15',
|
||||
'pytest>=3.8.0',
|
||||
'pytest-cov>=2.6.0',
|
||||
'pytest-mpl>=0.10',
|
||||
'pytest-runner>=4.2',
|
||||
'Sphinx>=1.7.9'
|
||||
]
|
||||
|
||||
all_requires = base_requires + plot_requires
|
||||
all_requires = cv_requires + plot_requires
|
||||
dev_requires = dev_requires + all_requires
|
||||
|
||||
|
||||
def setup_package():
|
||||
metadata = dict(
|
||||
name=about["__title__"],
|
||||
version=about["__version__"],
|
||||
description=about["__description__"],
|
||||
long_description=readme,
|
||||
long_description_content_type="text/markdown",
|
||||
url=about["__url__"],
|
||||
author=about["__author__"],
|
||||
author_email=about["__author_email__"],
|
||||
license=about["__license__"],
|
||||
packages=find_packages(exclude=("tests",)),
|
||||
install_requires=requires,
|
||||
extras_require={
|
||||
"all": all_requires,
|
||||
"base": base_requires,
|
||||
"cv": base_requires, # deprecate
|
||||
"dev": dev_requires,
|
||||
"plot": plot_requires,
|
||||
},
|
||||
entry_points={
|
||||
"console_scripts": [
|
||||
"camelot = camelot.cli:cli",
|
||||
],
|
||||
},
|
||||
classifiers=[
|
||||
# Trove classifiers
|
||||
# Full list: https://pypi.python.org/pypi?%3Aaction=list_classifiers
|
||||
"License :: OSI Approved :: MIT License",
|
||||
"Programming Language :: Python :: 3.6",
|
||||
"Programming Language :: Python :: 3.7",
|
||||
"Programming Language :: Python :: 3.8",
|
||||
],
|
||||
)
|
||||
metadata = dict(name=about['__title__'],
|
||||
version=about['__version__'],
|
||||
description=about['__description__'],
|
||||
long_description=readme,
|
||||
long_description_content_type="text/markdown",
|
||||
url=about['__url__'],
|
||||
author=about['__author__'],
|
||||
author_email=about['__author_email__'],
|
||||
license=about['__license__'],
|
||||
packages=find_packages(exclude=('tests',)),
|
||||
install_requires=requires,
|
||||
extras_require={
|
||||
'all': all_requires,
|
||||
'cv': cv_requires,
|
||||
'dev': dev_requires,
|
||||
'plot': plot_requires
|
||||
},
|
||||
entry_points={
|
||||
'console_scripts': [
|
||||
'camelot = camelot.cli:cli',
|
||||
],
|
||||
},
|
||||
classifiers=[
|
||||
# Trove classifiers
|
||||
# Full list: https://pypi.python.org/pypi?%3Aaction=list_classifiers
|
||||
'License :: OSI Approved :: MIT License',
|
||||
'Programming Language :: Python :: 2.7',
|
||||
'Programming Language :: Python :: 3.5',
|
||||
'Programming Language :: Python :: 3.6',
|
||||
'Programming Language :: Python :: 3.7'
|
||||
])
|
||||
|
||||
try:
|
||||
from setuptools import setup
|
||||
|
|
@ -87,5 +85,5 @@ def setup_package():
|
|||
setup(**metadata)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
if __name__ == '__main__':
|
||||
setup_package()
|
||||
|
|
|
|||
|
|
@ -1,3 +1,2 @@
|
|||
import matplotlib
|
||||
|
||||
matplotlib.use("agg")
|
||||
matplotlib.use('agg')
|
||||
|
|
|
|||
3233
tests/data.py
3233
tests/data.py
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
Before Width: | Height: | Size: 8.1 KiB After Width: | Height: | Size: 8.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 8.2 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 35 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 48 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 66 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 33 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 46 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 64 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 6.6 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 6.7 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 6.6 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 14 KiB After Width: | Height: | Size: 13 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 8.9 KiB After Width: | Height: | Size: 8.8 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 19 KiB After Width: | Height: | Size: 18 KiB |
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -1,9 +1,7 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
import pytest
|
||||
from click.testing import CliRunner
|
||||
|
||||
from camelot.cli import cli
|
||||
|
|
@ -11,181 +9,109 @@ from camelot.utils import TemporaryDirectory
|
|||
|
||||
|
||||
testdir = os.path.dirname(os.path.abspath(__file__))
|
||||
testdir = os.path.join(testdir, "files")
|
||||
|
||||
skip_on_windows = pytest.mark.skipif(
|
||||
sys.platform.startswith("win"),
|
||||
reason="Ghostscript not installed in Windows test environment",
|
||||
)
|
||||
testdir = os.path.join(testdir, 'files')
|
||||
|
||||
|
||||
def test_help_output():
|
||||
runner = CliRunner()
|
||||
prog_name = runner.get_default_prog_name(cli)
|
||||
result = runner.invoke(cli, ["--help"])
|
||||
output = result.output
|
||||
|
||||
assert prog_name == "camelot"
|
||||
assert result.output.startswith("Usage: %(prog_name)s [OPTIONS] COMMAND" % locals())
|
||||
assert all(
|
||||
v in result.output
|
||||
for v in ["Options:", "--version", "--help", "Commands:", "lattice", "stream"]
|
||||
)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_cli_lattice():
|
||||
with TemporaryDirectory() as tempdir:
|
||||
infile = os.path.join(testdir, "foo.pdf")
|
||||
outfile = os.path.join(tempdir, "foo.csv")
|
||||
infile = os.path.join(testdir, 'foo.pdf')
|
||||
outfile = os.path.join(tempdir, 'foo.csv')
|
||||
runner = CliRunner()
|
||||
result = runner.invoke(
|
||||
cli, ["--format", "csv", "--output", outfile, "lattice", infile]
|
||||
)
|
||||
result = runner.invoke(cli, ['--format', 'csv', '--output', outfile,
|
||||
'lattice', infile])
|
||||
assert result.exit_code == 0
|
||||
assert "Found 1 tables" in result.output
|
||||
assert result.output == 'Found 1 tables\n'
|
||||
|
||||
result = runner.invoke(cli, ["--format", "csv", "lattice", infile])
|
||||
output_error = "Error: Please specify output file path using --output"
|
||||
result = runner.invoke(cli, ['--format', 'csv',
|
||||
'lattice', infile])
|
||||
output_error = 'Error: Please specify output file path using --output'
|
||||
assert output_error in result.output
|
||||
|
||||
result = runner.invoke(cli, ["--output", outfile, "lattice", infile])
|
||||
format_error = "Please specify output file format using --format"
|
||||
result = runner.invoke(cli, ['--output', outfile,
|
||||
'lattice', infile])
|
||||
format_error = 'Please specify output file format using --format'
|
||||
assert format_error in result.output
|
||||
|
||||
|
||||
def test_cli_stream():
|
||||
with TemporaryDirectory() as tempdir:
|
||||
infile = os.path.join(testdir, "budget.pdf")
|
||||
outfile = os.path.join(tempdir, "budget.csv")
|
||||
infile = os.path.join(testdir, 'budget.pdf')
|
||||
outfile = os.path.join(tempdir, 'budget.csv')
|
||||
runner = CliRunner()
|
||||
result = runner.invoke(
|
||||
cli, ["--format", "csv", "--output", outfile, "stream", infile]
|
||||
)
|
||||
result = runner.invoke(cli, ['--format', 'csv', '--output', outfile,
|
||||
'stream', infile])
|
||||
assert result.exit_code == 0
|
||||
assert result.output == "Found 1 tables\n"
|
||||
assert result.output == 'Found 1 tables\n'
|
||||
|
||||
result = runner.invoke(cli, ["--format", "csv", "stream", infile])
|
||||
output_error = "Error: Please specify output file path using --output"
|
||||
result = runner.invoke(cli, ['--format', 'csv', 'stream', infile])
|
||||
output_error = 'Error: Please specify output file path using --output'
|
||||
assert output_error in result.output
|
||||
|
||||
result = runner.invoke(cli, ["--output", outfile, "stream", infile])
|
||||
format_error = "Please specify output file format using --format"
|
||||
result = runner.invoke(cli, ['--output', outfile, 'stream', infile])
|
||||
format_error = 'Please specify output file format using --format'
|
||||
assert format_error in result.output
|
||||
|
||||
|
||||
def test_cli_password():
|
||||
with TemporaryDirectory() as tempdir:
|
||||
infile = os.path.join(testdir, "health_protected.pdf")
|
||||
outfile = os.path.join(tempdir, "health_protected.csv")
|
||||
infile = os.path.join(testdir, 'health_protected.pdf')
|
||||
outfile = os.path.join(tempdir, 'health_protected.csv')
|
||||
runner = CliRunner()
|
||||
result = runner.invoke(
|
||||
cli,
|
||||
[
|
||||
"--password",
|
||||
"userpass",
|
||||
"--format",
|
||||
"csv",
|
||||
"--output",
|
||||
outfile,
|
||||
"stream",
|
||||
infile,
|
||||
],
|
||||
)
|
||||
result = runner.invoke(cli, ['--password', 'userpass',
|
||||
'--format', 'csv', '--output', outfile,
|
||||
'stream', infile])
|
||||
assert result.exit_code == 0
|
||||
assert result.output == "Found 1 tables\n"
|
||||
assert result.output == 'Found 1 tables\n'
|
||||
|
||||
output_error = "file has not been decrypted"
|
||||
output_error = 'file has not been decrypted'
|
||||
# no password
|
||||
result = runner.invoke(
|
||||
cli, ["--format", "csv", "--output", outfile, "stream", infile]
|
||||
)
|
||||
result = runner.invoke(cli, ['--format', 'csv', '--output', outfile,
|
||||
'stream', infile])
|
||||
assert output_error in str(result.exception)
|
||||
|
||||
# bad password
|
||||
result = runner.invoke(
|
||||
cli,
|
||||
[
|
||||
"--password",
|
||||
"wrongpass",
|
||||
"--format",
|
||||
"csv",
|
||||
"--output",
|
||||
outfile,
|
||||
"stream",
|
||||
infile,
|
||||
],
|
||||
)
|
||||
result = runner.invoke(cli, ['--password', 'wrongpass',
|
||||
'--format', 'csv', '--output', outfile,
|
||||
'stream', infile])
|
||||
assert output_error in str(result.exception)
|
||||
|
||||
|
||||
def test_cli_output_format():
|
||||
with TemporaryDirectory() as tempdir:
|
||||
infile = os.path.join(testdir, "health.pdf")
|
||||
|
||||
infile = os.path.join(testdir, 'health.pdf')
|
||||
outfile = os.path.join(tempdir, 'health.{}')
|
||||
runner = CliRunner()
|
||||
|
||||
# json
|
||||
outfile = os.path.join(tempdir, "health.json")
|
||||
result = runner.invoke(
|
||||
cli,
|
||||
["--format", "json", "--output", outfile, "stream", infile],
|
||||
)
|
||||
assert result.exit_code == 0, f"Output: {result.output}"
|
||||
result = runner.invoke(cli, ['--format', 'json', '--output', outfile.format('json'),
|
||||
'stream', infile])
|
||||
assert result.exit_code == 0
|
||||
|
||||
# excel
|
||||
outfile = os.path.join(tempdir, "health.xlsx")
|
||||
result = runner.invoke(
|
||||
cli,
|
||||
["--format", "excel", "--output", outfile, "stream", infile],
|
||||
)
|
||||
assert result.exit_code == 0, f"Output: {result.output}"
|
||||
result = runner.invoke(cli, ['--format', 'excel', '--output', outfile.format('xlsx'),
|
||||
'stream', infile])
|
||||
assert result.exit_code == 0
|
||||
|
||||
# html
|
||||
outfile = os.path.join(tempdir, "health.html")
|
||||
result = runner.invoke(
|
||||
cli,
|
||||
["--format", "html", "--output", outfile, "stream", infile],
|
||||
)
|
||||
assert result.exit_code == 0, f"Output: {result.output}"
|
||||
|
||||
# markdown
|
||||
outfile = os.path.join(tempdir, "health.md")
|
||||
result = runner.invoke(
|
||||
cli,
|
||||
["--format", "markdown", "--output", outfile, "stream", infile],
|
||||
)
|
||||
assert result.exit_code == 0, f"Output: {result.output}"
|
||||
result = runner.invoke(cli, ['--format', 'html', '--output', outfile.format('html'),
|
||||
'stream', infile])
|
||||
assert result.exit_code == 0
|
||||
|
||||
# zip
|
||||
outfile = os.path.join(tempdir, "health.csv")
|
||||
result = runner.invoke(
|
||||
cli,
|
||||
[
|
||||
"--zip",
|
||||
"--format",
|
||||
"csv",
|
||||
"--output",
|
||||
outfile,
|
||||
"stream",
|
||||
infile,
|
||||
],
|
||||
)
|
||||
assert result.exit_code == 0, f"Output: {result.output}"
|
||||
|
||||
result = runner.invoke(cli, ['--zip', '--format', 'csv', '--output', outfile.format('csv'),
|
||||
'stream', infile])
|
||||
assert result.exit_code == 0
|
||||
|
||||
def test_cli_quiet():
|
||||
with TemporaryDirectory() as tempdir:
|
||||
infile = os.path.join(testdir, "empty.pdf")
|
||||
outfile = os.path.join(tempdir, "empty.csv")
|
||||
infile = os.path.join(testdir, 'blank.pdf')
|
||||
outfile = os.path.join(tempdir, 'blank.csv')
|
||||
runner = CliRunner()
|
||||
|
||||
result = runner.invoke(
|
||||
cli, ["--format", "csv", "--output", outfile, "stream", infile]
|
||||
)
|
||||
assert "No tables found on page-1" in result.output
|
||||
result = runner.invoke(cli, ['--format', 'csv', '--output', outfile,
|
||||
'stream', infile])
|
||||
assert 'No tables found on page-1' in result.output
|
||||
|
||||
result = runner.invoke(
|
||||
cli, ["--quiet", "--format", "csv", "--output", outfile, "stream", infile]
|
||||
)
|
||||
assert "No tables found on page-1" not in result.output
|
||||
result = runner.invoke(cli, ['--quiet', '--format', 'csv',
|
||||
'--output', outfile, 'stream', infile])
|
||||
assert 'No tables found on page-1' not in result.output
|
||||
|
|
|
|||
|
|
@ -1,47 +1,24 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
import pytest
|
||||
import pandas as pd
|
||||
from pandas.testing import assert_frame_equal
|
||||
|
||||
import camelot
|
||||
from camelot.io import PDFHandler
|
||||
from camelot.core import Table, TableList
|
||||
from camelot.__version__ import generate_version
|
||||
from camelot.backends import ImageConversionBackend
|
||||
|
||||
from .data import *
|
||||
|
||||
testdir = os.path.dirname(os.path.abspath(__file__))
|
||||
testdir = os.path.join(testdir, "files")
|
||||
|
||||
skip_on_windows = pytest.mark.skipif(
|
||||
sys.platform.startswith("win"),
|
||||
reason="Ghostscript not installed in Windows test environment",
|
||||
)
|
||||
|
||||
|
||||
def test_version_generation():
|
||||
version = (0, 7, 3)
|
||||
assert generate_version(version, prerelease=None, revision=None) == "0.7.3"
|
||||
|
||||
|
||||
def test_version_generation_with_prerelease_revision():
|
||||
version = (0, 7, 3)
|
||||
prerelease = "alpha"
|
||||
revision = 2
|
||||
assert (
|
||||
generate_version(version, prerelease=prerelease, revision=revision)
|
||||
== "0.7.3-alpha.2"
|
||||
)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_parsing_report():
|
||||
parsing_report = {"accuracy": 99.02, "whitespace": 12.24, "order": 1, "page": 1}
|
||||
parsing_report = {
|
||||
'accuracy': 99.02,
|
||||
'whitespace': 12.24,
|
||||
'order': 1,
|
||||
'page': 1
|
||||
}
|
||||
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename)
|
||||
|
|
@ -53,122 +30,161 @@ def test_password():
|
|||
|
||||
filename = os.path.join(testdir, "health_protected.pdf")
|
||||
tables = camelot.read_pdf(filename, password="ownerpass", flavor="stream")
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
tables = camelot.read_pdf(filename, password="userpass", flavor="stream")
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_repr_poppler():
|
||||
def test_stream():
|
||||
df = pd.DataFrame(data_stream)
|
||||
|
||||
filename = os.path.join(testdir, "health.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_stream_table_rotated():
|
||||
df = pd.DataFrame(data_stream_table_rotated)
|
||||
|
||||
filename = os.path.join(testdir, "clockwise_table_2.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
filename = os.path.join(testdir, "anticlockwise_table_2.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_stream_two_tables():
|
||||
df1 = pd.DataFrame(data_stream_two_tables_1)
|
||||
df2 = pd.DataFrame(data_stream_two_tables_2)
|
||||
|
||||
filename = os.path.join(testdir, "tabula/12s0324.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor='stream')
|
||||
|
||||
assert len(tables) == 2
|
||||
assert df1.equals(tables[0].df)
|
||||
assert df2.equals(tables[1].df)
|
||||
|
||||
|
||||
def test_stream_table_areas():
|
||||
df = pd.DataFrame(data_stream_table_areas)
|
||||
|
||||
filename = os.path.join(testdir, "tabula/us-007.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream", table_areas=["320,500,573,335"])
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_stream_columns():
|
||||
df = pd.DataFrame(data_stream_columns)
|
||||
|
||||
filename = os.path.join(testdir, "mexican_towns.pdf")
|
||||
tables = camelot.read_pdf(
|
||||
filename, flavor="stream", columns=["67,180,230,425,475"], row_close_tol=10)
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_stream_split_text():
|
||||
df = pd.DataFrame(data_stream_split_text)
|
||||
|
||||
filename = os.path.join(testdir, "tabula/m27.pdf")
|
||||
tables = camelot.read_pdf(
|
||||
filename, flavor="stream", columns=["72,95,209,327,442,529,566,606,683"], split_text=True)
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_stream_flag_size():
|
||||
df = pd.DataFrame(data_stream_flag_size)
|
||||
|
||||
filename = os.path.join(testdir, "superscript.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream", flag_size=True)
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_lattice():
|
||||
df = pd.DataFrame(data_lattice)
|
||||
|
||||
filename = os.path.join(
|
||||
testdir, "tabula/icdar2013-dataset/competition-dataset-us/us-030.pdf")
|
||||
tables = camelot.read_pdf(filename, pages="2")
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_lattice_table_rotated():
|
||||
df = pd.DataFrame(data_lattice_table_rotated)
|
||||
|
||||
filename = os.path.join(testdir, "clockwise_table_1.pdf")
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
filename = os.path.join(testdir, "anticlockwise_table_1.pdf")
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_lattice_two_tables():
|
||||
df1 = pd.DataFrame(data_lattice_two_tables_1)
|
||||
df2 = pd.DataFrame(data_lattice_two_tables_2)
|
||||
|
||||
filename = os.path.join(testdir, "twotables_2.pdf")
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert len(tables) == 2
|
||||
assert df1.equals(tables[0].df)
|
||||
assert df2.equals(tables[1].df)
|
||||
|
||||
|
||||
def test_lattice_table_areas():
|
||||
df = pd.DataFrame(data_lattice_table_areas)
|
||||
|
||||
filename = os.path.join(testdir, "twotables_2.pdf")
|
||||
tables = camelot.read_pdf(filename, table_areas=["80,693,535,448"])
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_lattice_process_background():
|
||||
df = pd.DataFrame(data_lattice_process_background)
|
||||
|
||||
filename = os.path.join(testdir, "background_lines_1.pdf")
|
||||
tables = camelot.read_pdf(filename, process_background=True)
|
||||
assert df.equals(tables[1].df)
|
||||
|
||||
|
||||
def test_lattice_copy_text():
|
||||
df = pd.DataFrame(data_lattice_copy_text)
|
||||
|
||||
filename = os.path.join(testdir, "row_span_1.pdf")
|
||||
tables = camelot.read_pdf(filename, line_size_scaling=60, copy_text="v")
|
||||
assert df.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_lattice_shift_text():
|
||||
df_lt = pd.DataFrame(data_lattice_shift_text_left_top)
|
||||
df_disable = pd.DataFrame(data_lattice_shift_text_disable)
|
||||
df_rb = pd.DataFrame(data_lattice_shift_text_right_bottom)
|
||||
|
||||
filename = os.path.join(testdir, "column_span_2.pdf")
|
||||
tables = camelot.read_pdf(filename, line_size_scaling=40)
|
||||
assert df_lt.equals(tables[0].df)
|
||||
|
||||
tables = camelot.read_pdf(filename, line_size_scaling=40, shift_text=[''])
|
||||
assert df_disable.equals(tables[0].df)
|
||||
|
||||
tables = camelot.read_pdf(filename, line_size_scaling=40, shift_text=['r', 'b'])
|
||||
assert df_rb.equals(tables[0].df)
|
||||
|
||||
|
||||
def test_repr():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename, backend="poppler")
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert repr(tables) == "<TableList n=1>"
|
||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
|
||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120.48 y1=218.42 x2=164.64 y2=233.89>"
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_repr_ghostscript():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename, backend="ghostscript")
|
||||
assert repr(tables) == "<TableList n=1>"
|
||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
|
||||
def test_arabic():
|
||||
df = pd.DataFrame(data_arabic)
|
||||
|
||||
|
||||
def test_url_poppler():
|
||||
url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
|
||||
tables = camelot.read_pdf(url, backend="poppler")
|
||||
assert repr(tables) == "<TableList n=1>"
|
||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_url_ghostscript():
|
||||
url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
|
||||
tables = camelot.read_pdf(url, backend="ghostscript")
|
||||
assert repr(tables) == "<TableList n=1>"
|
||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
|
||||
|
||||
|
||||
def test_pages_poppler():
|
||||
url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
|
||||
tables = camelot.read_pdf(url, backend="poppler")
|
||||
assert repr(tables) == "<TableList n=1>"
|
||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
|
||||
|
||||
tables = camelot.read_pdf(url, pages="1-end", backend="poppler")
|
||||
assert repr(tables) == "<TableList n=1>"
|
||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
|
||||
|
||||
tables = camelot.read_pdf(url, pages="all", backend="poppler")
|
||||
assert repr(tables) == "<TableList n=1>"
|
||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_pages_ghostscript():
|
||||
url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
|
||||
tables = camelot.read_pdf(url, backend="ghostscript")
|
||||
assert repr(tables) == "<TableList n=1>"
|
||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
|
||||
|
||||
tables = camelot.read_pdf(url, pages="1-end", backend="ghostscript")
|
||||
assert repr(tables) == "<TableList n=1>"
|
||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
|
||||
|
||||
tables = camelot.read_pdf(url, pages="all", backend="ghostscript")
|
||||
assert repr(tables) == "<TableList n=1>"
|
||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
|
||||
|
||||
|
||||
def test_table_order():
|
||||
def _make_table(page, order):
|
||||
t = Table([], [])
|
||||
t.page = page
|
||||
t.order = order
|
||||
return t
|
||||
|
||||
table_list = TableList(
|
||||
[_make_table(2, 1), _make_table(1, 1), _make_table(3, 4), _make_table(1, 2)]
|
||||
)
|
||||
|
||||
assert [(t.page, t.order) for t in sorted(table_list)] == [
|
||||
(1, 1),
|
||||
(1, 2),
|
||||
(2, 1),
|
||||
(3, 4),
|
||||
]
|
||||
assert [(t.page, t.order) for t in sorted(table_list, reverse=True)] == [
|
||||
(3, 4),
|
||||
(2, 1),
|
||||
(1, 2),
|
||||
(1, 1),
|
||||
]
|
||||
|
||||
|
||||
def test_handler_pages_generator():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
|
||||
handler = PDFHandler(filename)
|
||||
assert handler._get_pages("1") == [1]
|
||||
|
||||
handler = PDFHandler(filename)
|
||||
assert handler._get_pages("all") == [1]
|
||||
|
||||
handler = PDFHandler(filename)
|
||||
assert handler._get_pages("1-end") == [1]
|
||||
|
||||
handler = PDFHandler(filename)
|
||||
assert handler._get_pages("1,2,3,4") == [1, 2, 3, 4]
|
||||
|
||||
handler = PDFHandler(filename)
|
||||
assert handler._get_pages("1,2,5-10") == [1, 2, 5, 6, 7, 8, 9, 10]
|
||||
filename = os.path.join(testdir, "tabula/arabic.pdf")
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert df.equals(tables[0].df)
|
||||
|
|
|
|||
|
|
@ -1,7 +1,6 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import os
|
||||
import sys
|
||||
import warnings
|
||||
|
||||
import pytest
|
||||
|
|
@ -11,145 +10,94 @@ import camelot
|
|||
|
||||
testdir = os.path.dirname(os.path.abspath(__file__))
|
||||
testdir = os.path.join(testdir, "files")
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
|
||||
skip_on_windows = pytest.mark.skipif(
|
||||
sys.platform.startswith("win"),
|
||||
reason="Ghostscript not installed in Windows test environment",
|
||||
)
|
||||
filename = os.path.join(testdir, 'foo.pdf')
|
||||
|
||||
|
||||
def test_unknown_flavor():
|
||||
message = "Unknown flavor specified." " Use either 'lattice' or 'stream'"
|
||||
with pytest.raises(NotImplementedError, match=message):
|
||||
tables = camelot.read_pdf(filename, flavor="chocolate")
|
||||
message = ("Unknown flavor specified."
|
||||
" Use either 'lattice' or 'stream'")
|
||||
with pytest.raises(NotImplementedError, message=message):
|
||||
tables = camelot.read_pdf(filename, flavor='chocolate')
|
||||
|
||||
|
||||
def test_input_kwargs():
|
||||
message = "columns cannot be used with flavor='lattice'"
|
||||
with pytest.raises(ValueError, match=message):
|
||||
tables = camelot.read_pdf(filename, columns=["10,20,30,40"])
|
||||
with pytest.raises(ValueError, message=message):
|
||||
tables = camelot.read_pdf(filename, columns=['10,20,30,40'])
|
||||
|
||||
|
||||
def test_unsupported_format():
|
||||
message = "File format not supported"
|
||||
filename = os.path.join(testdir, "foo.csv")
|
||||
with pytest.raises(NotImplementedError, match=message):
|
||||
message = 'File format not supported'
|
||||
filename = os.path.join(testdir, 'foo.csv')
|
||||
with pytest.raises(NotImplementedError, message=message):
|
||||
tables = camelot.read_pdf(filename)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_stream_equal_length():
|
||||
message = ("Length of table_areas and columns"
|
||||
" should be equal")
|
||||
with pytest.raises(ValueError, message=message):
|
||||
tables = camelot.read_pdf(filename, flavor='stream',
|
||||
table_areas=['10,20,30,40'], columns=['10,20,30,40', '10,20,30,40'])
|
||||
|
||||
|
||||
def test_no_tables_found():
|
||||
filename = os.path.join(testdir, 'blank.pdf')
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter('error')
|
||||
with pytest.raises(UserWarning) as e:
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert str(e.value) == 'No tables found on page-1'
|
||||
|
||||
|
||||
def test_no_tables_found_logs_suppressed():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
filename = os.path.join(testdir, 'foo.pdf')
|
||||
with warnings.catch_warnings():
|
||||
# the test should fail if any warning is thrown
|
||||
warnings.simplefilter("error")
|
||||
warnings.simplefilter('error')
|
||||
try:
|
||||
tables = camelot.read_pdf(filename, suppress_stdout=True)
|
||||
except Warning as e:
|
||||
warning_text = str(e)
|
||||
pytest.fail(f"Unexpected warning: {warning_text}")
|
||||
pytest.fail('Unexpected warning: {}'.format(warning_text))
|
||||
|
||||
|
||||
def test_no_tables_found_warnings_suppressed():
|
||||
filename = os.path.join(testdir, "empty.pdf")
|
||||
filename = os.path.join(testdir, 'blank.pdf')
|
||||
with warnings.catch_warnings():
|
||||
# the test should fail if any warning is thrown
|
||||
warnings.simplefilter("error")
|
||||
warnings.simplefilter('error')
|
||||
try:
|
||||
tables = camelot.read_pdf(filename, suppress_stdout=True)
|
||||
except Warning as e:
|
||||
warning_text = str(e)
|
||||
pytest.fail(f"Unexpected warning: {warning_text}")
|
||||
pytest.fail('Unexpected warning: {}'.format(warning_text))
|
||||
|
||||
|
||||
def test_ghostscript_not_found(monkeypatch):
|
||||
import distutils
|
||||
|
||||
def _find_executable_patch(arg):
|
||||
return ''
|
||||
|
||||
monkeypatch.setattr(distutils.spawn, 'find_executable', _find_executable_patch)
|
||||
|
||||
message = ('Please make sure that Ghostscript is installed and available'
|
||||
' on the PATH environment variable')
|
||||
filename = os.path.join(testdir, 'foo.pdf')
|
||||
with pytest.raises(Exception, message=message):
|
||||
tables = camelot.read_pdf(filename)
|
||||
|
||||
|
||||
def test_no_password():
|
||||
filename = os.path.join(testdir, "health_protected.pdf")
|
||||
message = "file has not been decrypted"
|
||||
with pytest.raises(Exception, match=message):
|
||||
filename = os.path.join(testdir, 'health_protected.pdf')
|
||||
message = 'file has not been decrypted'
|
||||
with pytest.raises(Exception, message=message):
|
||||
tables = camelot.read_pdf(filename)
|
||||
|
||||
|
||||
def test_bad_password():
|
||||
filename = os.path.join(testdir, "health_protected.pdf")
|
||||
message = "file has not been decrypted"
|
||||
with pytest.raises(Exception, match=message):
|
||||
tables = camelot.read_pdf(filename, password="wrongpass")
|
||||
|
||||
|
||||
def test_stream_equal_length():
|
||||
message = "Length of table_areas and columns" " should be equal"
|
||||
with pytest.raises(ValueError, match=message):
|
||||
tables = camelot.read_pdf(
|
||||
filename,
|
||||
flavor="stream",
|
||||
table_areas=["10,20,30,40"],
|
||||
columns=["10,20,30,40", "10,20,30,40"],
|
||||
)
|
||||
|
||||
|
||||
def test_image_warning():
|
||||
filename = os.path.join(testdir, "image.pdf")
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("error", category=UserWarning)
|
||||
with pytest.raises(UserWarning) as e:
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert (
|
||||
str(e.value)
|
||||
== "page-1 is image-based, camelot only works on text-based pages."
|
||||
)
|
||||
|
||||
|
||||
def test_stream_no_tables_on_page():
|
||||
filename = os.path.join(testdir, "empty.pdf")
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("error")
|
||||
with pytest.raises(UserWarning) as e:
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
assert str(e.value) == "No tables found on page-1"
|
||||
|
||||
|
||||
def test_stream_no_tables_in_area():
|
||||
filename = os.path.join(testdir, "only_page_number.pdf")
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("error")
|
||||
with pytest.raises(UserWarning) as e:
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
assert str(e.value) == "No tables found in table area 1"
|
||||
|
||||
|
||||
def test_lattice_no_tables_on_page():
|
||||
filename = os.path.join(testdir, "empty.pdf")
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("error", category=UserWarning)
|
||||
with pytest.raises(UserWarning) as e:
|
||||
tables = camelot.read_pdf(filename, flavor="lattice")
|
||||
assert str(e.value) == "No tables found on page-1"
|
||||
|
||||
|
||||
def test_lattice_unknown_backend():
|
||||
message = "Unknown backend 'mupdf' specified. Please use either 'poppler' or 'ghostscript'."
|
||||
with pytest.raises(NotImplementedError, match=message):
|
||||
tables = camelot.read_pdf(filename, backend="mupdf")
|
||||
|
||||
|
||||
def test_lattice_no_convert_method():
|
||||
class ConversionBackend(object):
|
||||
pass
|
||||
|
||||
message = "must implement a 'convert' method"
|
||||
with pytest.raises(NotImplementedError, match=message):
|
||||
tables = camelot.read_pdf(filename, backend=ConversionBackend())
|
||||
|
||||
|
||||
def test_lattice_ghostscript_deprecation_warning():
|
||||
ghostscript_deprecation_warning = (
|
||||
"'ghostscript' will be replaced by 'poppler' as the default image conversion"
|
||||
" backend in v0.12.0. You can try out 'poppler' with backend='poppler'."
|
||||
)
|
||||
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("error")
|
||||
with pytest.raises(DeprecationWarning) as e:
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert str(e.value) == ghostscript_deprecation_warning
|
||||
filename = os.path.join(testdir, 'health_protected.pdf')
|
||||
message = 'file has not been decrypted'
|
||||
with pytest.raises(Exception, message=message):
|
||||
tables = camelot.read_pdf(filename, password='wrongpass')
|
||||
|
|
|
|||
|
|
@ -1,60 +0,0 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import pytest
|
||||
|
||||
import camelot.backends.image_conversion
|
||||
from camelot.backends import ImageConversionBackend
|
||||
|
||||
|
||||
class PopplerBackendError(object):
|
||||
def convert(self, pdf_path, png_path):
|
||||
raise ValueError("Image conversion failed")
|
||||
|
||||
|
||||
class GhostscriptBackendError(object):
|
||||
def convert(self, pdf_path, png_path):
|
||||
raise ValueError("Image conversion failed")
|
||||
|
||||
|
||||
class GhostscriptBackendNoError(object):
|
||||
def convert(self, pdf_path, png_path):
|
||||
pass
|
||||
|
||||
|
||||
def test_poppler_backend_error_when_no_use_fallback(monkeypatch):
|
||||
BACKENDS = {
|
||||
"poppler": PopplerBackendError,
|
||||
"ghostscript": GhostscriptBackendNoError,
|
||||
}
|
||||
monkeypatch.setattr(
|
||||
"camelot.backends.image_conversion.BACKENDS", BACKENDS, raising=True
|
||||
)
|
||||
backend = ImageConversionBackend(use_fallback=False)
|
||||
|
||||
message = "Image conversion failed with image conversion backend 'poppler'"
|
||||
with pytest.raises(ValueError, match=message):
|
||||
backend.convert("foo", "bar")
|
||||
|
||||
|
||||
def test_ghostscript_backend_when_use_fallback(monkeypatch):
|
||||
BACKENDS = {
|
||||
"poppler": PopplerBackendError,
|
||||
"ghostscript": GhostscriptBackendNoError,
|
||||
}
|
||||
monkeypatch.setattr(
|
||||
"camelot.backends.image_conversion.BACKENDS", BACKENDS, raising=True
|
||||
)
|
||||
backend = ImageConversionBackend()
|
||||
backend.convert("foo", "bar")
|
||||
|
||||
|
||||
def test_ghostscript_backend_error_when_use_fallback(monkeypatch):
|
||||
BACKENDS = {"poppler": PopplerBackendError, "ghostscript": GhostscriptBackendError}
|
||||
monkeypatch.setattr(
|
||||
"camelot.backends.image_conversion.BACKENDS", BACKENDS, raising=True
|
||||
)
|
||||
backend = ImageConversionBackend()
|
||||
|
||||
message = "Image conversion failed with image conversion backend 'ghostscript'"
|
||||
with pytest.raises(ValueError, match=message):
|
||||
backend.convert("foo", "bar")
|
||||
|
|
@ -1,120 +0,0 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
import pytest
|
||||
import pandas as pd
|
||||
from pandas.testing import assert_frame_equal
|
||||
|
||||
import camelot
|
||||
from camelot.core import Table, TableList
|
||||
from camelot.__version__ import generate_version
|
||||
|
||||
from .data import *
|
||||
|
||||
testdir = os.path.dirname(os.path.abspath(__file__))
|
||||
testdir = os.path.join(testdir, "files")
|
||||
|
||||
skip_on_windows = pytest.mark.skipif(
|
||||
sys.platform.startswith("win"),
|
||||
reason="Ghostscript not installed in Windows test environment",
|
||||
)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_lattice():
|
||||
df = pd.DataFrame(data_lattice)
|
||||
|
||||
filename = os.path.join(
|
||||
testdir, "tabula/icdar2013-dataset/competition-dataset-us/us-030.pdf"
|
||||
)
|
||||
tables = camelot.read_pdf(filename, pages="2")
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_lattice_table_rotated():
|
||||
df = pd.DataFrame(data_lattice_table_rotated)
|
||||
|
||||
filename = os.path.join(testdir, "clockwise_table_1.pdf")
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
filename = os.path.join(testdir, "anticlockwise_table_1.pdf")
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_lattice_two_tables():
|
||||
df1 = pd.DataFrame(data_lattice_two_tables_1)
|
||||
df2 = pd.DataFrame(data_lattice_two_tables_2)
|
||||
|
||||
filename = os.path.join(testdir, "twotables_2.pdf")
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert len(tables) == 2
|
||||
assert df1.equals(tables[0].df)
|
||||
assert df2.equals(tables[1].df)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_lattice_table_regions():
|
||||
df = pd.DataFrame(data_lattice_table_regions)
|
||||
|
||||
filename = os.path.join(testdir, "table_region.pdf")
|
||||
tables = camelot.read_pdf(filename, table_regions=["170,370,560,270"])
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_lattice_table_areas():
|
||||
df = pd.DataFrame(data_lattice_table_areas)
|
||||
|
||||
filename = os.path.join(testdir, "twotables_2.pdf")
|
||||
tables = camelot.read_pdf(filename, table_areas=["80,693,535,448"])
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_lattice_process_background():
|
||||
df = pd.DataFrame(data_lattice_process_background)
|
||||
|
||||
filename = os.path.join(testdir, "background_lines_1.pdf")
|
||||
tables = camelot.read_pdf(filename, process_background=True)
|
||||
assert_frame_equal(df, tables[1].df)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_lattice_copy_text():
|
||||
df = pd.DataFrame(data_lattice_copy_text)
|
||||
|
||||
filename = os.path.join(testdir, "row_span_1.pdf")
|
||||
tables = camelot.read_pdf(filename, line_scale=60, copy_text="v")
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_lattice_shift_text():
|
||||
df_lt = pd.DataFrame(data_lattice_shift_text_left_top)
|
||||
df_disable = pd.DataFrame(data_lattice_shift_text_disable)
|
||||
df_rb = pd.DataFrame(data_lattice_shift_text_right_bottom)
|
||||
|
||||
filename = os.path.join(testdir, "column_span_2.pdf")
|
||||
tables = camelot.read_pdf(filename, line_scale=40)
|
||||
assert df_lt.equals(tables[0].df)
|
||||
|
||||
tables = camelot.read_pdf(filename, line_scale=40, shift_text=[""])
|
||||
assert df_disable.equals(tables[0].df)
|
||||
|
||||
tables = camelot.read_pdf(filename, line_scale=40, shift_text=["r", "b"])
|
||||
assert df_rb.equals(tables[0].df)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
def test_lattice_arabic():
|
||||
df = pd.DataFrame(data_arabic)
|
||||
|
||||
filename = os.path.join(testdir, "tabula/arabic.pdf")
|
||||
tables = camelot.read_pdf(filename)
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
|
@ -1,98 +1,67 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
import pytest
|
||||
|
||||
import camelot
|
||||
|
||||
|
||||
testdir = os.path.dirname(os.path.abspath(__file__))
|
||||
testdir = os.path.join(testdir, "files")
|
||||
|
||||
skip_on_windows = pytest.mark.skipif(
|
||||
sys.platform.startswith("win"),
|
||||
reason="Ghostscript not installed in Windows test environment",
|
||||
)
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
||||
@pytest.mark.mpl_image_compare(
|
||||
baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_text_plot():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename)
|
||||
return camelot.plot(tables[0], kind="text")
|
||||
return camelot.plot(tables[0], kind='text')
|
||||
|
||||
|
||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_textedge_plot():
|
||||
filename = os.path.join(testdir, "tabula/12s0324.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
return camelot.plot(tables[0], kind="textedge")
|
||||
|
||||
|
||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_lattice_contour_plot_poppler():
|
||||
@pytest.mark.mpl_image_compare(
|
||||
baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_grid_plot():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename, backend="poppler")
|
||||
return camelot.plot(tables[0], kind="contour")
|
||||
tables = camelot.read_pdf(filename)
|
||||
return camelot.plot(tables[0], kind='grid')
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_lattice_contour_plot_ghostscript():
|
||||
@pytest.mark.mpl_image_compare(
|
||||
baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_lattice_contour_plot():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename, backend="ghostscript")
|
||||
return camelot.plot(tables[0], kind="contour")
|
||||
tables = camelot.read_pdf(filename)
|
||||
return camelot.plot(tables[0], kind='contour')
|
||||
|
||||
|
||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
||||
@pytest.mark.mpl_image_compare(
|
||||
baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_stream_contour_plot():
|
||||
filename = os.path.join(testdir, "tabula/12s0324.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
return camelot.plot(tables[0], kind="contour")
|
||||
tables = camelot.read_pdf(filename, flavor='stream')
|
||||
return camelot.plot(tables[0], kind='contour')
|
||||
|
||||
|
||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_line_plot_poppler():
|
||||
@pytest.mark.mpl_image_compare(
|
||||
baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_line_plot():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename, backend="poppler")
|
||||
return camelot.plot(tables[0], kind="line")
|
||||
tables = camelot.read_pdf(filename)
|
||||
return camelot.plot(tables[0], kind='line')
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_line_plot_ghostscript():
|
||||
@pytest.mark.mpl_image_compare(
|
||||
baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_joint_plot():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename, backend="ghostscript")
|
||||
return camelot.plot(tables[0], kind="line")
|
||||
tables = camelot.read_pdf(filename)
|
||||
return camelot.plot(tables[0], kind='joint')
|
||||
|
||||
|
||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_joint_plot_poppler():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename, backend="poppler")
|
||||
return camelot.plot(tables[0], kind="joint")
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_joint_plot_ghostscript():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename, backend="ghostscript")
|
||||
return camelot.plot(tables[0], kind="joint")
|
||||
|
||||
|
||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_grid_plot_poppler():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename, backend="poppler")
|
||||
return camelot.plot(tables[0], kind="grid")
|
||||
|
||||
|
||||
@skip_on_windows
|
||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_grid_plot_ghostscript():
|
||||
filename = os.path.join(testdir, "foo.pdf")
|
||||
tables = camelot.read_pdf(filename, backend="ghostscript")
|
||||
return camelot.plot(tables[0], kind="grid")
|
||||
@pytest.mark.mpl_image_compare(
|
||||
baseline_dir="files/baseline_plots", remove_text=True)
|
||||
def test_textedge_plot():
|
||||
filename = os.path.join(testdir, "tabula/12s0324.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor='stream')
|
||||
return camelot.plot(tables[0], kind='textedge')
|
||||
|
|
|
|||
|
|
@ -1,133 +0,0 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import os
|
||||
|
||||
import pytest
|
||||
import pandas as pd
|
||||
from pandas.testing import assert_frame_equal
|
||||
|
||||
import camelot
|
||||
from camelot.core import Table, TableList
|
||||
from camelot.__version__ import generate_version
|
||||
|
||||
from .data import *
|
||||
|
||||
testdir = os.path.dirname(os.path.abspath(__file__))
|
||||
testdir = os.path.join(testdir, "files")
|
||||
|
||||
|
||||
def test_stream():
|
||||
df = pd.DataFrame(data_stream)
|
||||
|
||||
filename = os.path.join(testdir, "health.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
def test_stream_table_rotated():
|
||||
df = pd.DataFrame(data_stream_table_rotated)
|
||||
|
||||
filename = os.path.join(testdir, "clockwise_table_2.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
filename = os.path.join(testdir, "anticlockwise_table_2.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
def test_stream_two_tables():
|
||||
df1 = pd.DataFrame(data_stream_two_tables_1)
|
||||
df2 = pd.DataFrame(data_stream_two_tables_2)
|
||||
|
||||
filename = os.path.join(testdir, "tabula/12s0324.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
|
||||
assert len(tables) == 2
|
||||
assert df1.equals(tables[0].df)
|
||||
assert df2.equals(tables[1].df)
|
||||
|
||||
|
||||
def test_stream_table_regions():
|
||||
df = pd.DataFrame(data_stream_table_areas)
|
||||
|
||||
filename = os.path.join(testdir, "tabula/us-007.pdf")
|
||||
tables = camelot.read_pdf(
|
||||
filename, flavor="stream", table_regions=["320,460,573,335"]
|
||||
)
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
def test_stream_table_areas():
|
||||
df = pd.DataFrame(data_stream_table_areas)
|
||||
|
||||
filename = os.path.join(testdir, "tabula/us-007.pdf")
|
||||
tables = camelot.read_pdf(
|
||||
filename, flavor="stream", table_areas=["320,500,573,335"]
|
||||
)
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
def test_stream_columns():
|
||||
df = pd.DataFrame(data_stream_columns)
|
||||
|
||||
filename = os.path.join(testdir, "mexican_towns.pdf")
|
||||
tables = camelot.read_pdf(
|
||||
filename, flavor="stream", columns=["67,180,230,425,475"], row_tol=10
|
||||
)
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
def test_stream_split_text():
|
||||
df = pd.DataFrame(data_stream_split_text)
|
||||
|
||||
filename = os.path.join(testdir, "tabula/m27.pdf")
|
||||
tables = camelot.read_pdf(
|
||||
filename,
|
||||
flavor="stream",
|
||||
columns=["72,95,209,327,442,529,566,606,683"],
|
||||
split_text=True,
|
||||
)
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
def test_stream_flag_size():
|
||||
df = pd.DataFrame(data_stream_flag_size)
|
||||
|
||||
filename = os.path.join(testdir, "superscript.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream", flag_size=True)
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
def test_stream_strip_text():
|
||||
df = pd.DataFrame(data_stream_strip_text)
|
||||
|
||||
filename = os.path.join(testdir, "detect_vertical_false.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream", strip_text=" ,\n")
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
def test_stream_edge_tol():
|
||||
df = pd.DataFrame(data_stream_edge_tol)
|
||||
|
||||
filename = os.path.join(testdir, "edge_tol.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream", edge_tol=500)
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
def test_stream_layout_kwargs():
|
||||
df = pd.DataFrame(data_stream_layout_kwargs)
|
||||
|
||||
filename = os.path.join(testdir, "detect_vertical_false.pdf")
|
||||
tables = camelot.read_pdf(
|
||||
filename, flavor="stream", layout_kwargs={"detect_vertical": False}
|
||||
)
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
|
||||
|
||||
def test_stream_duplicated_text():
|
||||
df = pd.DataFrame(data_stream_duplicated_text)
|
||||
|
||||
filename = os.path.join(testdir, "birdisland.pdf")
|
||||
tables = camelot.read_pdf(filename, flavor="stream")
|
||||
assert_frame_equal(df, tables[0].df)
|
||||
Loading…
Reference in New Issue