Compare commits
No commits in common. "master" and "v0.9.0" have entirely different histories.
|
|
@ -1,2 +1,3 @@
|
||||||
[run]
|
[run]
|
||||||
branch = True
|
branch = True
|
||||||
|
omit = camelot/ext/*
|
||||||
|
|
|
||||||
|
|
@ -10,25 +10,20 @@ assignees: ''
|
||||||
<!-- Please read the filing issues section of the contributor's guide first: https://camelot-py.readthedocs.io/en/master/dev/contributing.html -->
|
<!-- 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**
|
**Describe the bug**
|
||||||
|
A clear and concise description of what the bug is.
|
||||||
<!-- A clear and concise description of what the bug is. -->
|
|
||||||
|
|
||||||
**Steps to reproduce the bug**
|
**Steps to reproduce the bug**
|
||||||
|
Steps used to install `camelot`:
|
||||||
|
1. Add step here (you can add more steps too)
|
||||||
|
|
||||||
<!-- Steps used to install `camelot`:
|
Steps to reproduce the behavior:
|
||||||
1. Add step here (you can add more steps too) -->
|
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**
|
**Expected behavior**
|
||||||
|
A clear and concise description of what you expected to happen.
|
||||||
<!-- A clear and concise description of what you expected to happen. -->
|
|
||||||
|
|
||||||
**Code**
|
**Code**
|
||||||
|
Add the Camelot code snippet that you used.
|
||||||
<!-- Add the Camelot code snippet that you used. -->
|
|
||||||
|
|
||||||
```
|
```
|
||||||
import camelot
|
import camelot
|
||||||
|
|
||||||
|
|
@ -36,16 +31,13 @@ import camelot
|
||||||
```
|
```
|
||||||
|
|
||||||
**PDF**
|
**PDF**
|
||||||
|
Add the PDF file that you want to extract tables from.
|
||||||
<!-- Add the PDF file that you want to extract tables from. -->
|
|
||||||
|
|
||||||
**Screenshots**
|
**Screenshots**
|
||||||
|
If applicable, add screenshots to help explain your problem.
|
||||||
<!-- If applicable, add screenshots to help explain your problem. -->
|
|
||||||
|
|
||||||
**Environment**
|
**Environment**
|
||||||
|
- OS: [e.g. MacOS]
|
||||||
- OS: [e.g. macOS]
|
|
||||||
- Python version:
|
- Python version:
|
||||||
- Numpy version:
|
- Numpy version:
|
||||||
- OpenCV version:
|
- OpenCV version:
|
||||||
|
|
@ -53,5 +45,4 @@ import camelot
|
||||||
- Camelot version:
|
- Camelot version:
|
||||||
|
|
||||||
**Additional context**
|
**Additional context**
|
||||||
|
Add any other context about the problem here.
|
||||||
<!-- Add any other context about the problem here. -->
|
|
||||||
|
|
|
||||||
|
|
@ -7,28 +7,7 @@ jobs:
|
||||||
runs-on: ubuntu-latest
|
runs-on: ubuntu-latest
|
||||||
strategy:
|
strategy:
|
||||||
matrix:
|
matrix:
|
||||||
python-version: [3.6, 3.7, 3.8]
|
python-version: [3.6, 3.7, 3.8, 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
|
|
||||||
|
|
||||||
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:
|
steps:
|
||||||
- uses: actions/checkout@v2
|
- uses: actions/checkout@v2
|
||||||
|
|
|
||||||
|
|
@ -1,4 +1,3 @@
|
||||||
fontconfig/
|
|
||||||
__pycache__/
|
__pycache__/
|
||||||
*.py[cod]
|
*.py[cod]
|
||||||
*.so
|
*.so
|
||||||
|
|
|
||||||
17
HISTORY.md
17
HISTORY.md
|
|
@ -4,23 +4,6 @@ Release History
|
||||||
master
|
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)
|
0.9.0 (2021-06-15)
|
||||||
------------------
|
------------------
|
||||||
|
|
||||||
|
|
|
||||||
18
README.md
18
README.md
|
|
@ -4,7 +4,7 @@
|
||||||
|
|
||||||
# Camelot: PDF Table Extraction for Humans
|
# Camelot: PDF Table Extraction for Humans
|
||||||
|
|
||||||
[](https://github.com/camelot-dev/camelot/actions/workflows/tests.yml) [](https://camelot-py.readthedocs.io/en/master/)
|
 [](https://camelot-py.readthedocs.io/en/master/)
|
||||||
[](https://codecov.io/github/camelot-dev/camelot?branch=master)
|
[](https://codecov.io/github/camelot-dev/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://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)
|
[](https://github.com/ambv/black)
|
||||||
|
|
@ -22,7 +22,7 @@
|
||||||
>>> tables = camelot.read_pdf('foo.pdf')
|
>>> tables = camelot.read_pdf('foo.pdf')
|
||||||
>>> tables
|
>>> tables
|
||||||
<TableList n=1>
|
<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, sqlite
|
||||||
>>> tables[0]
|
>>> tables[0]
|
||||||
<Table shape=(7, 7)>
|
<Table shape=(7, 7)>
|
||||||
>>> tables[0].parsing_report
|
>>> tables[0].parsing_report
|
||||||
|
|
@ -32,7 +32,7 @@
|
||||||
'order': 1,
|
'order': 1,
|
||||||
'page': 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, to_sqlite
|
||||||
>>> tables[0].df # get a pandas DataFrame!
|
>>> tables[0].df # get a pandas DataFrame!
|
||||||
</pre>
|
</pre>
|
||||||
|
|
||||||
|
|
@ -49,13 +49,11 @@ Camelot also comes packaged with a [command-line interface](https://camelot-py.r
|
||||||
|
|
||||||
**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".)
|
**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?
|
## 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).
|
- **Configurability**: Camelot gives you control over the table extraction process with its [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.
|
- **Metrics**: Bad tables can be discarded 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.
|
- **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 and Sqlite.
|
||||||
|
|
||||||
See [comparison with similar libraries and tools](https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools).
|
See [comparison with similar libraries and tools](https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools).
|
||||||
|
|
||||||
|
|
@ -78,7 +76,7 @@ $ conda install -c conda-forge camelot-py
|
||||||
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/bionic/python/python-tk) and [ghostscript](https://www.ghostscript.com/)), you can also just use pip to install Camelot:
|
||||||
|
|
||||||
<pre>
|
<pre>
|
||||||
$ pip install "camelot-py[base]"
|
$ pip install "camelot-py[cv]"
|
||||||
</pre>
|
</pre>
|
||||||
|
|
||||||
### From the source code
|
### From the source code
|
||||||
|
|
@ -93,7 +91,7 @@ and install Camelot using pip:
|
||||||
|
|
||||||
<pre>
|
<pre>
|
||||||
$ cd camelot
|
$ cd camelot
|
||||||
$ pip install ".[base]"
|
$ pip install ".[cv]"
|
||||||
</pre>
|
</pre>
|
||||||
|
|
||||||
## Documentation
|
## Documentation
|
||||||
|
|
|
||||||
|
|
@ -1,6 +1,6 @@
|
||||||
# -*- coding: utf-8 -*-
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
VERSION = (0, 10, 1)
|
VERSION = (0, 9, 0)
|
||||||
PRERELEASE = None # alpha, beta or rc
|
PRERELEASE = None # alpha, beta or rc
|
||||||
REVISION = None
|
REVISION = None
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -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)
|
|
||||||
|
|
@ -43,7 +43,7 @@ pass_config = click.make_pass_decorator(Config)
|
||||||
@click.option(
|
@click.option(
|
||||||
"-f",
|
"-f",
|
||||||
"--format",
|
"--format",
|
||||||
type=click.Choice(["csv", "excel", "html", "json", "markdown", "sqlite"]),
|
type=click.Choice(["csv", "json", "excel", "html", "sqlite"]),
|
||||||
help="Output file format.",
|
help="Output file format.",
|
||||||
)
|
)
|
||||||
@click.option("-z", "--zip", is_flag=True, help="Create ZIP archive.")
|
@click.option("-z", "--zip", is_flag=True, help="Create ZIP archive.")
|
||||||
|
|
|
||||||
|
|
@ -288,10 +288,10 @@ class Cell(object):
|
||||||
self._text = ""
|
self._text = ""
|
||||||
|
|
||||||
def __repr__(self):
|
def __repr__(self):
|
||||||
x1 = round(self.x1)
|
x1 = round(self.x1, 2)
|
||||||
y1 = round(self.y1)
|
y1 = round(self.y1, 2)
|
||||||
x2 = round(self.x2)
|
x2 = round(self.x2, 2)
|
||||||
y2 = round(self.y2)
|
y2 = round(self.y2, 2)
|
||||||
return f"<Cell x1={x1} y1={y1} x2={x2} y2={y2}>"
|
return f"<Cell x1={x1} y1={y1} x2={x2} y2={y2}>"
|
||||||
|
|
||||||
@property
|
@property
|
||||||
|
|
@ -630,21 +630,6 @@ class Table(object):
|
||||||
with open(path, "w", encoding="utf-8") as f:
|
with open(path, "w", encoding="utf-8") as f:
|
||||||
f.write(html_string)
|
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):
|
def to_sqlite(self, path, **kwargs):
|
||||||
"""Writes Table to sqlite database.
|
"""Writes Table to sqlite database.
|
||||||
|
|
||||||
|
|
@ -726,7 +711,7 @@ class TableList(object):
|
||||||
path : str
|
path : str
|
||||||
Output filepath.
|
Output filepath.
|
||||||
f : str
|
f : str
|
||||||
File format. Can be csv, excel, html, json, markdown or sqlite.
|
File format. Can be csv, json, excel, html and sqlite.
|
||||||
compress : bool
|
compress : bool
|
||||||
Whether or not to add files to a ZIP archive.
|
Whether or not to add files to a ZIP archive.
|
||||||
|
|
||||||
|
|
@ -739,7 +724,7 @@ class TableList(object):
|
||||||
|
|
||||||
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)
|
self._write_file(f=f, **kwargs)
|
||||||
if compress:
|
if compress:
|
||||||
self._compress_dir(**kwargs)
|
self._compress_dir(**kwargs)
|
||||||
|
|
|
||||||
|
|
@ -0,0 +1,674 @@
|
||||||
|
GNU GENERAL PUBLIC LICENSE
|
||||||
|
Version 3, 29 June 2007
|
||||||
|
|
||||||
|
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
|
||||||
|
Everyone is permitted to copy and distribute verbatim copies
|
||||||
|
of this license document, but changing it is not allowed.
|
||||||
|
|
||||||
|
Preamble
|
||||||
|
|
||||||
|
The GNU General Public License is a free, copyleft license for
|
||||||
|
software and other kinds of works.
|
||||||
|
|
||||||
|
The licenses for most software and other practical works are designed
|
||||||
|
to take away your freedom to share and change the works. By contrast,
|
||||||
|
the GNU General Public License is intended to guarantee your freedom to
|
||||||
|
share and change all versions of a program--to make sure it remains free
|
||||||
|
software for all its users. We, the Free Software Foundation, use the
|
||||||
|
GNU General Public License for most of our software; it applies also to
|
||||||
|
any other work released this way by its authors. You can apply it to
|
||||||
|
your programs, too.
|
||||||
|
|
||||||
|
When we speak of free software, we are referring to freedom, not
|
||||||
|
price. Our General Public Licenses are designed to make sure that you
|
||||||
|
have the freedom to distribute copies of free software (and charge for
|
||||||
|
them if you wish), that you receive source code or can get it if you
|
||||||
|
want it, that you can change the software or use pieces of it in new
|
||||||
|
free programs, and that you know you can do these things.
|
||||||
|
|
||||||
|
To protect your rights, we need to prevent others from denying you
|
||||||
|
these rights or asking you to surrender the rights. Therefore, you have
|
||||||
|
certain responsibilities if you distribute copies of the software, or if
|
||||||
|
you modify it: responsibilities to respect the freedom of others.
|
||||||
|
|
||||||
|
For example, if you distribute copies of such a program, whether
|
||||||
|
gratis or for a fee, you must pass on to the recipients the same
|
||||||
|
freedoms that you received. You must make sure that they, too, receive
|
||||||
|
or can get the source code. And you must show them these terms so they
|
||||||
|
know their rights.
|
||||||
|
|
||||||
|
Developers that use the GNU GPL protect your rights with two steps:
|
||||||
|
(1) assert copyright on the software, and (2) offer you this License
|
||||||
|
giving you legal permission to copy, distribute and/or modify it.
|
||||||
|
|
||||||
|
For the developers' and authors' protection, the GPL clearly explains
|
||||||
|
that there is no warranty for this free software. For both users' and
|
||||||
|
authors' sake, the GPL requires that modified versions be marked as
|
||||||
|
changed, so that their problems will not be attributed erroneously to
|
||||||
|
authors of previous versions.
|
||||||
|
|
||||||
|
Some devices are designed to deny users access to install or run
|
||||||
|
modified versions of the software inside them, although the manufacturer
|
||||||
|
can do so. This is fundamentally incompatible with the aim of
|
||||||
|
protecting users' freedom to change the software. The systematic
|
||||||
|
pattern of such abuse occurs in the area of products for individuals to
|
||||||
|
use, which is precisely where it is most unacceptable. Therefore, we
|
||||||
|
have designed this version of the GPL to prohibit the practice for those
|
||||||
|
products. If such problems arise substantially in other domains, we
|
||||||
|
stand ready to extend this provision to those domains in future versions
|
||||||
|
of the GPL, as needed to protect the freedom of users.
|
||||||
|
|
||||||
|
Finally, every program is threatened constantly by software patents.
|
||||||
|
States should not allow patents to restrict development and use of
|
||||||
|
software on general-purpose computers, but in those that do, we wish to
|
||||||
|
avoid the special danger that patents applied to a free program could
|
||||||
|
make it effectively proprietary. To prevent this, the GPL assures that
|
||||||
|
patents cannot be used to render the program non-free.
|
||||||
|
|
||||||
|
The precise terms and conditions for copying, distribution and
|
||||||
|
modification follow.
|
||||||
|
|
||||||
|
TERMS AND CONDITIONS
|
||||||
|
|
||||||
|
0. Definitions.
|
||||||
|
|
||||||
|
"This License" refers to version 3 of the GNU General Public License.
|
||||||
|
|
||||||
|
"Copyright" also means copyright-like laws that apply to other kinds of
|
||||||
|
works, such as semiconductor masks.
|
||||||
|
|
||||||
|
"The Program" refers to any copyrightable work licensed under this
|
||||||
|
License. Each licensee is addressed as "you". "Licensees" and
|
||||||
|
"recipients" may be individuals or organizations.
|
||||||
|
|
||||||
|
To "modify" a work means to copy from or adapt all or part of the work
|
||||||
|
in a fashion requiring copyright permission, other than the making of an
|
||||||
|
exact copy. The resulting work is called a "modified version" of the
|
||||||
|
earlier work or a work "based on" the earlier work.
|
||||||
|
|
||||||
|
A "covered work" means either the unmodified Program or a work based
|
||||||
|
on the Program.
|
||||||
|
|
||||||
|
To "propagate" a work means to do anything with it that, without
|
||||||
|
permission, would make you directly or secondarily liable for
|
||||||
|
infringement under applicable copyright law, except executing it on a
|
||||||
|
computer or modifying a private copy. Propagation includes copying,
|
||||||
|
distribution (with or without modification), making available to the
|
||||||
|
public, and in some countries other activities as well.
|
||||||
|
|
||||||
|
To "convey" a work means any kind of propagation that enables other
|
||||||
|
parties to make or receive copies. Mere interaction with a user through
|
||||||
|
a computer network, with no transfer of a copy, is not conveying.
|
||||||
|
|
||||||
|
An interactive user interface displays "Appropriate Legal Notices"
|
||||||
|
to the extent that it includes a convenient and prominently visible
|
||||||
|
feature that (1) displays an appropriate copyright notice, and (2)
|
||||||
|
tells the user that there is no warranty for the work (except to the
|
||||||
|
extent that warranties are provided), that licensees may convey the
|
||||||
|
work under this License, and how to view a copy of this License. If
|
||||||
|
the interface presents a list of user commands or options, such as a
|
||||||
|
menu, a prominent item in the list meets this criterion.
|
||||||
|
|
||||||
|
1. Source Code.
|
||||||
|
|
||||||
|
The "source code" for a work means the preferred form of the work
|
||||||
|
for making modifications to it. "Object code" means any non-source
|
||||||
|
form of a work.
|
||||||
|
|
||||||
|
A "Standard Interface" means an interface that either is an official
|
||||||
|
standard defined by a recognized standards body, or, in the case of
|
||||||
|
interfaces specified for a particular programming language, one that
|
||||||
|
is widely used among developers working in that language.
|
||||||
|
|
||||||
|
The "System Libraries" of an executable work include anything, other
|
||||||
|
than the work as a whole, that (a) is included in the normal form of
|
||||||
|
packaging a Major Component, but which is not part of that Major
|
||||||
|
Component, and (b) serves only to enable use of the work with that
|
||||||
|
Major Component, or to implement a Standard Interface for which an
|
||||||
|
implementation is available to the public in source code form. A
|
||||||
|
"Major Component", in this context, means a major essential component
|
||||||
|
(kernel, window system, and so on) of the specific operating system
|
||||||
|
(if any) on which the executable work runs, or a compiler used to
|
||||||
|
produce the work, or an object code interpreter used to run it.
|
||||||
|
|
||||||
|
The "Corresponding Source" for a work in object code form means all
|
||||||
|
the source code needed to generate, install, and (for an executable
|
||||||
|
work) run the object code and to modify the work, including scripts to
|
||||||
|
control those activities. However, it does not include the work's
|
||||||
|
System Libraries, or general-purpose tools or generally available free
|
||||||
|
programs which are used unmodified in performing those activities but
|
||||||
|
which are not part of the work. For example, Corresponding Source
|
||||||
|
includes interface definition files associated with source files for
|
||||||
|
the work, and the source code for shared libraries and dynamically
|
||||||
|
linked subprograms that the work is specifically designed to require,
|
||||||
|
such as by intimate data communication or control flow between those
|
||||||
|
subprograms and other parts of the work.
|
||||||
|
|
||||||
|
The Corresponding Source need not include anything that users
|
||||||
|
can regenerate automatically from other parts of the Corresponding
|
||||||
|
Source.
|
||||||
|
|
||||||
|
The Corresponding Source for a work in source code form is that
|
||||||
|
same work.
|
||||||
|
|
||||||
|
2. Basic Permissions.
|
||||||
|
|
||||||
|
All rights granted under this License are granted for the term of
|
||||||
|
copyright on the Program, and are irrevocable provided the stated
|
||||||
|
conditions are met. This License explicitly affirms your unlimited
|
||||||
|
permission to run the unmodified Program. The output from running a
|
||||||
|
covered work is covered by this License only if the output, given its
|
||||||
|
content, constitutes a covered work. This License acknowledges your
|
||||||
|
rights of fair use or other equivalent, as provided by copyright law.
|
||||||
|
|
||||||
|
You may make, run and propagate covered works that you do not
|
||||||
|
convey, without conditions so long as your license otherwise remains
|
||||||
|
in force. You may convey covered works to others for the sole purpose
|
||||||
|
of having them make modifications exclusively for you, or provide you
|
||||||
|
with facilities for running those works, provided that you comply with
|
||||||
|
the terms of this License in conveying all material for which you do
|
||||||
|
not control copyright. Those thus making or running the covered works
|
||||||
|
for you must do so exclusively on your behalf, under your direction
|
||||||
|
and control, on terms that prohibit them from making any copies of
|
||||||
|
your copyrighted material outside their relationship with you.
|
||||||
|
|
||||||
|
Conveying under any other circumstances is permitted solely under
|
||||||
|
the conditions stated below. Sublicensing is not allowed; section 10
|
||||||
|
makes it unnecessary.
|
||||||
|
|
||||||
|
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
|
||||||
|
|
||||||
|
No covered work shall be deemed part of an effective technological
|
||||||
|
measure under any applicable law fulfilling obligations under article
|
||||||
|
11 of the WIPO copyright treaty adopted on 20 December 1996, or
|
||||||
|
similar laws prohibiting or restricting circumvention of such
|
||||||
|
measures.
|
||||||
|
|
||||||
|
When you convey a covered work, you waive any legal power to forbid
|
||||||
|
circumvention of technological measures to the extent such circumvention
|
||||||
|
is effected by exercising rights under this License with respect to
|
||||||
|
the covered work, and you disclaim any intention to limit operation or
|
||||||
|
modification of the work as a means of enforcing, against the work's
|
||||||
|
users, your or third parties' legal rights to forbid circumvention of
|
||||||
|
technological measures.
|
||||||
|
|
||||||
|
4. Conveying Verbatim Copies.
|
||||||
|
|
||||||
|
You may convey verbatim copies of the Program's source code as you
|
||||||
|
receive it, in any medium, provided that you conspicuously and
|
||||||
|
appropriately publish on each copy an appropriate copyright notice;
|
||||||
|
keep intact all notices stating that this License and any
|
||||||
|
non-permissive terms added in accord with section 7 apply to the code;
|
||||||
|
keep intact all notices of the absence of any warranty; and give all
|
||||||
|
recipients a copy of this License along with the Program.
|
||||||
|
|
||||||
|
You may charge any price or no price for each copy that you convey,
|
||||||
|
and you may offer support or warranty protection for a fee.
|
||||||
|
|
||||||
|
5. Conveying Modified Source Versions.
|
||||||
|
|
||||||
|
You may convey a work based on the Program, or the modifications to
|
||||||
|
produce it from the Program, in the form of source code under the
|
||||||
|
terms of section 4, provided that you also meet all of these conditions:
|
||||||
|
|
||||||
|
a) The work must carry prominent notices stating that you modified
|
||||||
|
it, and giving a relevant date.
|
||||||
|
|
||||||
|
b) The work must carry prominent notices stating that it is
|
||||||
|
released under this License and any conditions added under section
|
||||||
|
7. This requirement modifies the requirement in section 4 to
|
||||||
|
"keep intact all notices".
|
||||||
|
|
||||||
|
c) You must license the entire work, as a whole, under this
|
||||||
|
License to anyone who comes into possession of a copy. This
|
||||||
|
License will therefore apply, along with any applicable section 7
|
||||||
|
additional terms, to the whole of the work, and all its parts,
|
||||||
|
regardless of how they are packaged. This License gives no
|
||||||
|
permission to license the work in any other way, but it does not
|
||||||
|
invalidate such permission if you have separately received it.
|
||||||
|
|
||||||
|
d) If the work has interactive user interfaces, each must display
|
||||||
|
Appropriate Legal Notices; however, if the Program has interactive
|
||||||
|
interfaces that do not display Appropriate Legal Notices, your
|
||||||
|
work need not make them do so.
|
||||||
|
|
||||||
|
A compilation of a covered work with other separate and independent
|
||||||
|
works, which are not by their nature extensions of the covered work,
|
||||||
|
and which are not combined with it such as to form a larger program,
|
||||||
|
in or on a volume of a storage or distribution medium, is called an
|
||||||
|
"aggregate" if the compilation and its resulting copyright are not
|
||||||
|
used to limit the access or legal rights of the compilation's users
|
||||||
|
beyond what the individual works permit. Inclusion of a covered work
|
||||||
|
in an aggregate does not cause this License to apply to the other
|
||||||
|
parts of the aggregate.
|
||||||
|
|
||||||
|
6. Conveying Non-Source Forms.
|
||||||
|
|
||||||
|
You may convey a covered work in object code form under the terms
|
||||||
|
of sections 4 and 5, provided that you also convey the
|
||||||
|
machine-readable Corresponding Source under the terms of this License,
|
||||||
|
in one of these ways:
|
||||||
|
|
||||||
|
a) Convey the object code in, or embodied in, a physical product
|
||||||
|
(including a physical distribution medium), accompanied by the
|
||||||
|
Corresponding Source fixed on a durable physical medium
|
||||||
|
customarily used for software interchange.
|
||||||
|
|
||||||
|
b) Convey the object code in, or embodied in, a physical product
|
||||||
|
(including a physical distribution medium), accompanied by a
|
||||||
|
written offer, valid for at least three years and valid for as
|
||||||
|
long as you offer spare parts or customer support for that product
|
||||||
|
model, to give anyone who possesses the object code either (1) a
|
||||||
|
copy of the Corresponding Source for all the software in the
|
||||||
|
product that is covered by this License, on a durable physical
|
||||||
|
medium customarily used for software interchange, for a price no
|
||||||
|
more than your reasonable cost of physically performing this
|
||||||
|
conveying of source, or (2) access to copy the
|
||||||
|
Corresponding Source from a network server at no charge.
|
||||||
|
|
||||||
|
c) Convey individual copies of the object code with a copy of the
|
||||||
|
written offer to provide the Corresponding Source. This
|
||||||
|
alternative is allowed only occasionally and noncommercially, and
|
||||||
|
only if you received the object code with such an offer, in accord
|
||||||
|
with subsection 6b.
|
||||||
|
|
||||||
|
d) Convey the object code by offering access from a designated
|
||||||
|
place (gratis or for a charge), and offer equivalent access to the
|
||||||
|
Corresponding Source in the same way through the same place at no
|
||||||
|
further charge. You need not require recipients to copy the
|
||||||
|
Corresponding Source along with the object code. If the place to
|
||||||
|
copy the object code is a network server, the Corresponding Source
|
||||||
|
may be on a different server (operated by you or a third party)
|
||||||
|
that supports equivalent copying facilities, provided you maintain
|
||||||
|
clear directions next to the object code saying where to find the
|
||||||
|
Corresponding Source. Regardless of what server hosts the
|
||||||
|
Corresponding Source, you remain obligated to ensure that it is
|
||||||
|
available for as long as needed to satisfy these requirements.
|
||||||
|
|
||||||
|
e) Convey the object code using peer-to-peer transmission, provided
|
||||||
|
you inform other peers where the object code and Corresponding
|
||||||
|
Source of the work are being offered to the general public at no
|
||||||
|
charge under subsection 6d.
|
||||||
|
|
||||||
|
A separable portion of the object code, whose source code is excluded
|
||||||
|
from the Corresponding Source as a System Library, need not be
|
||||||
|
included in conveying the object code work.
|
||||||
|
|
||||||
|
A "User Product" is either (1) a "consumer product", which means any
|
||||||
|
tangible personal property which is normally used for personal, family,
|
||||||
|
or household purposes, or (2) anything designed or sold for incorporation
|
||||||
|
into a dwelling. In determining whether a product is a consumer product,
|
||||||
|
doubtful cases shall be resolved in favor of coverage. For a particular
|
||||||
|
product received by a particular user, "normally used" refers to a
|
||||||
|
typical or common use of that class of product, regardless of the status
|
||||||
|
of the particular user or of the way in which the particular user
|
||||||
|
actually uses, or expects or is expected to use, the product. A product
|
||||||
|
is a consumer product regardless of whether the product has substantial
|
||||||
|
commercial, industrial or non-consumer uses, unless such uses represent
|
||||||
|
the only significant mode of use of the product.
|
||||||
|
|
||||||
|
"Installation Information" for a User Product means any methods,
|
||||||
|
procedures, authorization keys, or other information required to install
|
||||||
|
and execute modified versions of a covered work in that User Product from
|
||||||
|
a modified version of its Corresponding Source. The information must
|
||||||
|
suffice to ensure that the continued functioning of the modified object
|
||||||
|
code is in no case prevented or interfered with solely because
|
||||||
|
modification has been made.
|
||||||
|
|
||||||
|
If you convey an object code work under this section in, or with, or
|
||||||
|
specifically for use in, a User Product, and the conveying occurs as
|
||||||
|
part of a transaction in which the right of possession and use of the
|
||||||
|
User Product is transferred to the recipient in perpetuity or for a
|
||||||
|
fixed term (regardless of how the transaction is characterized), the
|
||||||
|
Corresponding Source conveyed under this section must be accompanied
|
||||||
|
by the Installation Information. But this requirement does not apply
|
||||||
|
if neither you nor any third party retains the ability to install
|
||||||
|
modified object code on the User Product (for example, the work has
|
||||||
|
been installed in ROM).
|
||||||
|
|
||||||
|
The requirement to provide Installation Information does not include a
|
||||||
|
requirement to continue to provide support service, warranty, or updates
|
||||||
|
for a work that has been modified or installed by the recipient, or for
|
||||||
|
the User Product in which it has been modified or installed. Access to a
|
||||||
|
network may be denied when the modification itself materially and
|
||||||
|
adversely affects the operation of the network or violates the rules and
|
||||||
|
protocols for communication across the network.
|
||||||
|
|
||||||
|
Corresponding Source conveyed, and Installation Information provided,
|
||||||
|
in accord with this section must be in a format that is publicly
|
||||||
|
documented (and with an implementation available to the public in
|
||||||
|
source code form), and must require no special password or key for
|
||||||
|
unpacking, reading or copying.
|
||||||
|
|
||||||
|
7. Additional Terms.
|
||||||
|
|
||||||
|
"Additional permissions" are terms that supplement the terms of this
|
||||||
|
License by making exceptions from one or more of its conditions.
|
||||||
|
Additional permissions that are applicable to the entire Program shall
|
||||||
|
be treated as though they were included in this License, to the extent
|
||||||
|
that they are valid under applicable law. If additional permissions
|
||||||
|
apply only to part of the Program, that part may be used separately
|
||||||
|
under those permissions, but the entire Program remains governed by
|
||||||
|
this License without regard to the additional permissions.
|
||||||
|
|
||||||
|
When you convey a copy of a covered work, you may at your option
|
||||||
|
remove any additional permissions from that copy, or from any part of
|
||||||
|
it. (Additional permissions may be written to require their own
|
||||||
|
removal in certain cases when you modify the work.) You may place
|
||||||
|
additional permissions on material, added by you to a covered work,
|
||||||
|
for which you have or can give appropriate copyright permission.
|
||||||
|
|
||||||
|
Notwithstanding any other provision of this License, for material you
|
||||||
|
add to a covered work, you may (if authorized by the copyright holders of
|
||||||
|
that material) supplement the terms of this License with terms:
|
||||||
|
|
||||||
|
a) Disclaiming warranty or limiting liability differently from the
|
||||||
|
terms of sections 15 and 16 of this License; or
|
||||||
|
|
||||||
|
b) Requiring preservation of specified reasonable legal notices or
|
||||||
|
author attributions in that material or in the Appropriate Legal
|
||||||
|
Notices displayed by works containing it; or
|
||||||
|
|
||||||
|
c) Prohibiting misrepresentation of the origin of that material, or
|
||||||
|
requiring that modified versions of such material be marked in
|
||||||
|
reasonable ways as different from the original version; or
|
||||||
|
|
||||||
|
d) Limiting the use for publicity purposes of names of licensors or
|
||||||
|
authors of the material; or
|
||||||
|
|
||||||
|
e) Declining to grant rights under trademark law for use of some
|
||||||
|
trade names, trademarks, or service marks; or
|
||||||
|
|
||||||
|
f) Requiring indemnification of licensors and authors of that
|
||||||
|
material by anyone who conveys the material (or modified versions of
|
||||||
|
it) with contractual assumptions of liability to the recipient, for
|
||||||
|
any liability that these contractual assumptions directly impose on
|
||||||
|
those licensors and authors.
|
||||||
|
|
||||||
|
All other non-permissive additional terms are considered "further
|
||||||
|
restrictions" within the meaning of section 10. If the Program as you
|
||||||
|
received it, or any part of it, contains a notice stating that it is
|
||||||
|
governed by this License along with a term that is a further
|
||||||
|
restriction, you may remove that term. If a license document contains
|
||||||
|
a further restriction but permits relicensing or conveying under this
|
||||||
|
License, you may add to a covered work material governed by the terms
|
||||||
|
of that license document, provided that the further restriction does
|
||||||
|
not survive such relicensing or conveying.
|
||||||
|
|
||||||
|
If you add terms to a covered work in accord with this section, you
|
||||||
|
must place, in the relevant source files, a statement of the
|
||||||
|
additional terms that apply to those files, or a notice indicating
|
||||||
|
where to find the applicable terms.
|
||||||
|
|
||||||
|
Additional terms, permissive or non-permissive, may be stated in the
|
||||||
|
form of a separately written license, or stated as exceptions;
|
||||||
|
the above requirements apply either way.
|
||||||
|
|
||||||
|
8. Termination.
|
||||||
|
|
||||||
|
You may not propagate or modify a covered work except as expressly
|
||||||
|
provided under this License. Any attempt otherwise to propagate or
|
||||||
|
modify it is void, and will automatically terminate your rights under
|
||||||
|
this License (including any patent licenses granted under the third
|
||||||
|
paragraph of section 11).
|
||||||
|
|
||||||
|
However, if you cease all violation of this License, then your
|
||||||
|
license from a particular copyright holder is reinstated (a)
|
||||||
|
provisionally, unless and until the copyright holder explicitly and
|
||||||
|
finally terminates your license, and (b) permanently, if the copyright
|
||||||
|
holder fails to notify you of the violation by some reasonable means
|
||||||
|
prior to 60 days after the cessation.
|
||||||
|
|
||||||
|
Moreover, your license from a particular copyright holder is
|
||||||
|
reinstated permanently if the copyright holder notifies you of the
|
||||||
|
violation by some reasonable means, this is the first time you have
|
||||||
|
received notice of violation of this License (for any work) from that
|
||||||
|
copyright holder, and you cure the violation prior to 30 days after
|
||||||
|
your receipt of the notice.
|
||||||
|
|
||||||
|
Termination of your rights under this section does not terminate the
|
||||||
|
licenses of parties who have received copies or rights from you under
|
||||||
|
this License. If your rights have been terminated and not permanently
|
||||||
|
reinstated, you do not qualify to receive new licenses for the same
|
||||||
|
material under section 10.
|
||||||
|
|
||||||
|
9. Acceptance Not Required for Having Copies.
|
||||||
|
|
||||||
|
You are not required to accept this License in order to receive or
|
||||||
|
run a copy of the Program. Ancillary propagation of a covered work
|
||||||
|
occurring solely as a consequence of using peer-to-peer transmission
|
||||||
|
to receive a copy likewise does not require acceptance. However,
|
||||||
|
nothing other than this License grants you permission to propagate or
|
||||||
|
modify any covered work. These actions infringe copyright if you do
|
||||||
|
not accept this License. Therefore, by modifying or propagating a
|
||||||
|
covered work, you indicate your acceptance of this License to do so.
|
||||||
|
|
||||||
|
10. Automatic Licensing of Downstream Recipients.
|
||||||
|
|
||||||
|
Each time you convey a covered work, the recipient automatically
|
||||||
|
receives a license from the original licensors, to run, modify and
|
||||||
|
propagate that work, subject to this License. You are not responsible
|
||||||
|
for enforcing compliance by third parties with this License.
|
||||||
|
|
||||||
|
An "entity transaction" is a transaction transferring control of an
|
||||||
|
organization, or substantially all assets of one, or subdividing an
|
||||||
|
organization, or merging organizations. If propagation of a covered
|
||||||
|
work results from an entity transaction, each party to that
|
||||||
|
transaction who receives a copy of the work also receives whatever
|
||||||
|
licenses to the work the party's predecessor in interest had or could
|
||||||
|
give under the previous paragraph, plus a right to possession of the
|
||||||
|
Corresponding Source of the work from the predecessor in interest, if
|
||||||
|
the predecessor has it or can get it with reasonable efforts.
|
||||||
|
|
||||||
|
You may not impose any further restrictions on the exercise of the
|
||||||
|
rights granted or affirmed under this License. For example, you may
|
||||||
|
not impose a license fee, royalty, or other charge for exercise of
|
||||||
|
rights granted under this License, and you may not initiate litigation
|
||||||
|
(including a cross-claim or counterclaim in a lawsuit) alleging that
|
||||||
|
any patent claim is infringed by making, using, selling, offering for
|
||||||
|
sale, or importing the Program or any portion of it.
|
||||||
|
|
||||||
|
11. Patents.
|
||||||
|
|
||||||
|
A "contributor" is a copyright holder who authorizes use under this
|
||||||
|
License of the Program or a work on which the Program is based. The
|
||||||
|
work thus licensed is called the contributor's "contributor version".
|
||||||
|
|
||||||
|
A contributor's "essential patent claims" are all patent claims
|
||||||
|
owned or controlled by the contributor, whether already acquired or
|
||||||
|
hereafter acquired, that would be infringed by some manner, permitted
|
||||||
|
by this License, of making, using, or selling its contributor version,
|
||||||
|
but do not include claims that would be infringed only as a
|
||||||
|
consequence of further modification of the contributor version. For
|
||||||
|
purposes of this definition, "control" includes the right to grant
|
||||||
|
patent sublicenses in a manner consistent with the requirements of
|
||||||
|
this License.
|
||||||
|
|
||||||
|
Each contributor grants you a non-exclusive, worldwide, royalty-free
|
||||||
|
patent license under the contributor's essential patent claims, to
|
||||||
|
make, use, sell, offer for sale, import and otherwise run, modify and
|
||||||
|
propagate the contents of its contributor version.
|
||||||
|
|
||||||
|
In the following three paragraphs, a "patent license" is any express
|
||||||
|
agreement or commitment, however denominated, not to enforce a patent
|
||||||
|
(such as an express permission to practice a patent or covenant not to
|
||||||
|
sue for patent infringement). To "grant" such a patent license to a
|
||||||
|
party means to make such an agreement or commitment not to enforce a
|
||||||
|
patent against the party.
|
||||||
|
|
||||||
|
If you convey a covered work, knowingly relying on a patent license,
|
||||||
|
and the Corresponding Source of the work is not available for anyone
|
||||||
|
to copy, free of charge and under the terms of this License, through a
|
||||||
|
publicly available network server or other readily accessible means,
|
||||||
|
then you must either (1) cause the Corresponding Source to be so
|
||||||
|
available, or (2) arrange to deprive yourself of the benefit of the
|
||||||
|
patent license for this particular work, or (3) arrange, in a manner
|
||||||
|
consistent with the requirements of this License, to extend the patent
|
||||||
|
license to downstream recipients. "Knowingly relying" means you have
|
||||||
|
actual knowledge that, but for the patent license, your conveying the
|
||||||
|
covered work in a country, or your recipient's use of the covered work
|
||||||
|
in a country, would infringe one or more identifiable patents in that
|
||||||
|
country that you have reason to believe are valid.
|
||||||
|
|
||||||
|
If, pursuant to or in connection with a single transaction or
|
||||||
|
arrangement, you convey, or propagate by procuring conveyance of, a
|
||||||
|
covered work, and grant a patent license to some of the parties
|
||||||
|
receiving the covered work authorizing them to use, propagate, modify
|
||||||
|
or convey a specific copy of the covered work, then the patent license
|
||||||
|
you grant is automatically extended to all recipients of the covered
|
||||||
|
work and works based on it.
|
||||||
|
|
||||||
|
A patent license is "discriminatory" if it does not include within
|
||||||
|
the scope of its coverage, prohibits the exercise of, or is
|
||||||
|
conditioned on the non-exercise of one or more of the rights that are
|
||||||
|
specifically granted under this License. You may not convey a covered
|
||||||
|
work if you are a party to an arrangement with a third party that is
|
||||||
|
in the business of distributing software, under which you make payment
|
||||||
|
to the third party based on the extent of your activity of conveying
|
||||||
|
the work, and under which the third party grants, to any of the
|
||||||
|
parties who would receive the covered work from you, a discriminatory
|
||||||
|
patent license (a) in connection with copies of the covered work
|
||||||
|
conveyed by you (or copies made from those copies), or (b) primarily
|
||||||
|
for and in connection with specific products or compilations that
|
||||||
|
contain the covered work, unless you entered into that arrangement,
|
||||||
|
or that patent license was granted, prior to 28 March 2007.
|
||||||
|
|
||||||
|
Nothing in this License shall be construed as excluding or limiting
|
||||||
|
any implied license or other defenses to infringement that may
|
||||||
|
otherwise be available to you under applicable patent law.
|
||||||
|
|
||||||
|
12. No Surrender of Others' Freedom.
|
||||||
|
|
||||||
|
If conditions are imposed on you (whether by court order, agreement or
|
||||||
|
otherwise) that contradict the conditions of this License, they do not
|
||||||
|
excuse you from the conditions of this License. If you cannot convey a
|
||||||
|
covered work so as to satisfy simultaneously your obligations under this
|
||||||
|
License and any other pertinent obligations, then as a consequence you may
|
||||||
|
not convey it at all. For example, if you agree to terms that obligate you
|
||||||
|
to collect a royalty for further conveying from those to whom you convey
|
||||||
|
the Program, the only way you could satisfy both those terms and this
|
||||||
|
License would be to refrain entirely from conveying the Program.
|
||||||
|
|
||||||
|
13. Use with the GNU Affero General Public License.
|
||||||
|
|
||||||
|
Notwithstanding any other provision of this License, you have
|
||||||
|
permission to link or combine any covered work with a work licensed
|
||||||
|
under version 3 of the GNU Affero General Public License into a single
|
||||||
|
combined work, and to convey the resulting work. The terms of this
|
||||||
|
License will continue to apply to the part which is the covered work,
|
||||||
|
but the special requirements of the GNU Affero General Public License,
|
||||||
|
section 13, concerning interaction through a network will apply to the
|
||||||
|
combination as such.
|
||||||
|
|
||||||
|
14. Revised Versions of this License.
|
||||||
|
|
||||||
|
The Free Software Foundation may publish revised and/or new versions of
|
||||||
|
the GNU General Public License from time to time. Such new versions will
|
||||||
|
be similar in spirit to the present version, but may differ in detail to
|
||||||
|
address new problems or concerns.
|
||||||
|
|
||||||
|
Each version is given a distinguishing version number. If the
|
||||||
|
Program specifies that a certain numbered version of the GNU General
|
||||||
|
Public License "or any later version" applies to it, you have the
|
||||||
|
option of following the terms and conditions either of that numbered
|
||||||
|
version or of any later version published by the Free Software
|
||||||
|
Foundation. If the Program does not specify a version number of the
|
||||||
|
GNU General Public License, you may choose any version ever published
|
||||||
|
by the Free Software Foundation.
|
||||||
|
|
||||||
|
If the Program specifies that a proxy can decide which future
|
||||||
|
versions of the GNU General Public License can be used, that proxy's
|
||||||
|
public statement of acceptance of a version permanently authorizes you
|
||||||
|
to choose that version for the Program.
|
||||||
|
|
||||||
|
Later license versions may give you additional or different
|
||||||
|
permissions. However, no additional obligations are imposed on any
|
||||||
|
author or copyright holder as a result of your choosing to follow a
|
||||||
|
later version.
|
||||||
|
|
||||||
|
15. Disclaimer of Warranty.
|
||||||
|
|
||||||
|
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
|
||||||
|
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
|
||||||
|
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
|
||||||
|
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
|
||||||
|
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||||
|
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
|
||||||
|
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
|
||||||
|
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
|
||||||
|
|
||||||
|
16. Limitation of Liability.
|
||||||
|
|
||||||
|
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
|
||||||
|
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
|
||||||
|
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
|
||||||
|
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
|
||||||
|
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
|
||||||
|
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
|
||||||
|
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
|
||||||
|
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
|
||||||
|
SUCH DAMAGES.
|
||||||
|
|
||||||
|
17. Interpretation of Sections 15 and 16.
|
||||||
|
|
||||||
|
If the disclaimer of warranty and limitation of liability provided
|
||||||
|
above cannot be given local legal effect according to their terms,
|
||||||
|
reviewing courts shall apply local law that most closely approximates
|
||||||
|
an absolute waiver of all civil liability in connection with the
|
||||||
|
Program, unless a warranty or assumption of liability accompanies a
|
||||||
|
copy of the Program in return for a fee.
|
||||||
|
|
||||||
|
END OF TERMS AND CONDITIONS
|
||||||
|
|
||||||
|
How to Apply These Terms to Your New Programs
|
||||||
|
|
||||||
|
If you develop a new program, and you want it to be of the greatest
|
||||||
|
possible use to the public, the best way to achieve this is to make it
|
||||||
|
free software which everyone can redistribute and change under these terms.
|
||||||
|
|
||||||
|
To do so, attach the following notices to the program. It is safest
|
||||||
|
to attach them to the start of each source file to most effectively
|
||||||
|
state the exclusion of warranty; and each file should have at least
|
||||||
|
the "copyright" line and a pointer to where the full notice is found.
|
||||||
|
|
||||||
|
<one line to give the program's name and a brief idea of what it does.>
|
||||||
|
Copyright (C) <year> <name of author>
|
||||||
|
|
||||||
|
This program is free software: you can redistribute it and/or modify
|
||||||
|
it under the terms of the GNU General Public License as published by
|
||||||
|
the Free Software Foundation, either version 3 of the License, or
|
||||||
|
(at your option) any later version.
|
||||||
|
|
||||||
|
This program is distributed in the hope that it will be useful,
|
||||||
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||||
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||||
|
GNU General Public License for more details.
|
||||||
|
|
||||||
|
You should have received a copy of the GNU General Public License
|
||||||
|
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||||
|
|
||||||
|
Also add information on how to contact you by electronic and paper mail.
|
||||||
|
|
||||||
|
If the program does terminal interaction, make it output a short
|
||||||
|
notice like this when it starts in an interactive mode:
|
||||||
|
|
||||||
|
<program> Copyright (C) <year> <name of author>
|
||||||
|
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
|
||||||
|
This is free software, and you are welcome to redistribute it
|
||||||
|
under certain conditions; type `show c' for details.
|
||||||
|
|
||||||
|
The hypothetical commands `show w' and `show c' should show the appropriate
|
||||||
|
parts of the General Public License. Of course, your program's commands
|
||||||
|
might be different; for a GUI interface, you would use an "about box".
|
||||||
|
|
||||||
|
You should also get your employer (if you work as a programmer) or school,
|
||||||
|
if any, to sign a "copyright disclaimer" for the program, if necessary.
|
||||||
|
For more information on this, and how to apply and follow the GNU GPL, see
|
||||||
|
<http://www.gnu.org/licenses/>.
|
||||||
|
|
||||||
|
The GNU General Public License does not permit incorporating your program
|
||||||
|
into proprietary programs. If your program is a subroutine library, you
|
||||||
|
may consider it more useful to permit linking proprietary applications with
|
||||||
|
the library. If this is what you want to do, use the GNU Lesser General
|
||||||
|
Public License instead of this License. But first, please read
|
||||||
|
<http://www.gnu.org/philosophy/why-not-lgpl.html>.
|
||||||
|
|
@ -0,0 +1,98 @@
|
||||||
|
#!/usr/bin/env python
|
||||||
|
# -*- coding: utf-8 -*-
|
||||||
|
"""
|
||||||
|
ghostscript - A Python interface for the Ghostscript interpreter C-API
|
||||||
|
"""
|
||||||
|
#
|
||||||
|
# Modifications 2018 by Vinayak Mehta <vmehta94@gmail.com>
|
||||||
|
# Copyright 2010-2018 by Hartmut Goebel <h.goebel@crazy-compilers.com>
|
||||||
|
#
|
||||||
|
# This program is free software: you can redistribute it and/or modify
|
||||||
|
# it under the terms of the GNU General Public License as published by
|
||||||
|
# the Free Software Foundation, either version 3 of the License, or
|
||||||
|
# (at your option) any later version.
|
||||||
|
#
|
||||||
|
# This program is distributed in the hope that it will be useful, but
|
||||||
|
# WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||||
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||||
|
# General Public License for more details.
|
||||||
|
#
|
||||||
|
# You should have received a copy of the GNU General Public License
|
||||||
|
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||||
|
#
|
||||||
|
|
||||||
|
from . import _gsprint as gs
|
||||||
|
|
||||||
|
|
||||||
|
__author__ = "Hartmut Goebel <h.goebel@crazy-compilers.com>"
|
||||||
|
__copyright__ = "Copyright 2010-2018 by Hartmut Goebel <h.goebel@crazy-compilers.com>"
|
||||||
|
__license__ = "GNU General Public License version 3 (GPL v3)"
|
||||||
|
__version__ = "0.6"
|
||||||
|
|
||||||
|
|
||||||
|
class __Ghostscript(object):
|
||||||
|
def __init__(self, instance, args, stdin=None, stdout=None, stderr=None):
|
||||||
|
self._initialized = False
|
||||||
|
self._callbacks = None
|
||||||
|
if stdin or stdout or stderr:
|
||||||
|
self.set_stdio(stdin, stdout, stderr)
|
||||||
|
rc = gs.init_with_args(instance, args)
|
||||||
|
self._initialized = True
|
||||||
|
if rc == gs.e_Quit:
|
||||||
|
self.exit()
|
||||||
|
|
||||||
|
def __enter__(self):
|
||||||
|
return self
|
||||||
|
|
||||||
|
def __exit__(self, *args):
|
||||||
|
self.exit()
|
||||||
|
|
||||||
|
def set_stdio(self, stdin=None, stdout=None, stderr=None):
|
||||||
|
"""Set stdin, stdout and stderr of the ghostscript interpreter.
|
||||||
|
|
||||||
|
The ``stdin`` stream has to support the ``readline()``
|
||||||
|
interface. The ``stdout`` and ``stderr`` streams have to
|
||||||
|
support the ``write()`` and ``flush()`` interface.
|
||||||
|
|
||||||
|
Please note that this does not affect the input- and output-
|
||||||
|
streams of the devices. Esp. setting stdout does not allow
|
||||||
|
catching the devise-output even when using ``-sOutputFile=-``.
|
||||||
|
|
||||||
|
"""
|
||||||
|
global __instance__
|
||||||
|
self._callbacks = (
|
||||||
|
stdin and gs._wrap_stdin(stdin) or None,
|
||||||
|
stdout and gs._wrap_stdout(stdout) or None,
|
||||||
|
stderr and gs._wrap_stderr(stderr) or None,
|
||||||
|
)
|
||||||
|
gs.set_stdio(__instance__, *self._callbacks)
|
||||||
|
|
||||||
|
def __del__(self):
|
||||||
|
self.exit()
|
||||||
|
|
||||||
|
def exit(self):
|
||||||
|
global __instance__
|
||||||
|
if self._initialized:
|
||||||
|
if __instance__ is not None:
|
||||||
|
gs.exit(__instance__)
|
||||||
|
gs.delete_instance(__instance__)
|
||||||
|
__instance__ = None
|
||||||
|
self._initialized = False
|
||||||
|
|
||||||
|
|
||||||
|
def Ghostscript(*args, **kwargs):
|
||||||
|
"""Factory function for setting up a Ghostscript instance"""
|
||||||
|
global __instance__
|
||||||
|
# Ghostscript only supports a single instance
|
||||||
|
if __instance__ is None:
|
||||||
|
__instance__ = gs.new_instance()
|
||||||
|
return __Ghostscript(
|
||||||
|
__instance__,
|
||||||
|
args,
|
||||||
|
stdin=kwargs.get("stdin", None),
|
||||||
|
stdout=kwargs.get("stdout", None),
|
||||||
|
stderr=kwargs.get("stderr", None),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
__instance__ = None
|
||||||
|
|
@ -0,0 +1,270 @@
|
||||||
|
#!/usr/bin/env python
|
||||||
|
# -*- coding: utf-8 -*-
|
||||||
|
"""
|
||||||
|
ghostscript._gsprint - A low-level interface to the Ghostscript C-API using ctypes
|
||||||
|
"""
|
||||||
|
#
|
||||||
|
# Modifications 2018 by Vinayak Mehta <vmehta94@gmail.com>
|
||||||
|
# Copyright 2010-2018 by Hartmut Goebel <h.goebel@crazy-compilers.com>
|
||||||
|
#
|
||||||
|
# Display_callback Structure by Lasse Fister <commander@graphicore.de> in 2013
|
||||||
|
#
|
||||||
|
# This program is free software: you can redistribute it and/or modify
|
||||||
|
# it under the terms of the GNU General Public License as published by
|
||||||
|
# the Free Software Foundation, either version 3 of the License, or
|
||||||
|
# (at your option) any later version.
|
||||||
|
#
|
||||||
|
# This program is distributed in the hope that it will be useful, but
|
||||||
|
# WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||||
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||||
|
# General Public License for more details.
|
||||||
|
#
|
||||||
|
# You should have received a copy of the GNU General Public License
|
||||||
|
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||||
|
#
|
||||||
|
|
||||||
|
import sys
|
||||||
|
from ctypes import *
|
||||||
|
|
||||||
|
|
||||||
|
# base/gserrors.h
|
||||||
|
#
|
||||||
|
# Internal code for a normal exit when usage info is displayed.
|
||||||
|
# This allows Window versions of Ghostscript to pause until
|
||||||
|
# the message can be read.
|
||||||
|
#
|
||||||
|
e_Info = -110
|
||||||
|
|
||||||
|
#
|
||||||
|
# Internal code for the .quit operator.
|
||||||
|
# The real quit code is an integer on the operand stack.
|
||||||
|
# gs_interpret returns this only for a .quit with a zero exit code.
|
||||||
|
#
|
||||||
|
e_Quit = -101
|
||||||
|
|
||||||
|
__author__ = "Hartmut Goebel <h.goebel@crazy-compilers.com>"
|
||||||
|
__copyright__ = "Copyright 2010-2018 by Hartmut Goebel <h.goebel@crazy-compilers.com>"
|
||||||
|
__license__ = "GNU General Public License version 3 (GPL v3)"
|
||||||
|
__version__ = "0.6"
|
||||||
|
|
||||||
|
gs_main_instance = c_void_p
|
||||||
|
display_callback = c_void_p
|
||||||
|
|
||||||
|
# https://www.ghostscript.com/doc/current/API.htm
|
||||||
|
|
||||||
|
|
||||||
|
class GhostscriptError(Exception):
|
||||||
|
def __init__(self, ecode):
|
||||||
|
self.code = ecode
|
||||||
|
|
||||||
|
|
||||||
|
def new_instance():
|
||||||
|
"""Create a new instance of Ghostscript
|
||||||
|
|
||||||
|
This instance is passed to most other API functions.
|
||||||
|
"""
|
||||||
|
# :todo: The caller_handle will be provided to callback functions.
|
||||||
|
display_callback = None
|
||||||
|
instance = gs_main_instance()
|
||||||
|
rc = libgs.gsapi_new_instance(pointer(instance), display_callback)
|
||||||
|
if rc != 0:
|
||||||
|
raise GhostscriptError(rc)
|
||||||
|
return instance
|
||||||
|
|
||||||
|
|
||||||
|
def delete_instance(instance):
|
||||||
|
"""Destroy an instance of Ghostscript
|
||||||
|
|
||||||
|
Before you call this, Ghostscript must have finished.
|
||||||
|
If Ghostscript has been initialised, you must call exit()
|
||||||
|
before delete_instance()
|
||||||
|
"""
|
||||||
|
return libgs.gsapi_delete_instance(instance)
|
||||||
|
|
||||||
|
|
||||||
|
if sys.platform == "win32":
|
||||||
|
c_stdstream_call_t = WINFUNCTYPE(c_int, gs_main_instance, POINTER(c_char), c_int)
|
||||||
|
else:
|
||||||
|
c_stdstream_call_t = CFUNCTYPE(c_int, gs_main_instance, POINTER(c_char), c_int)
|
||||||
|
|
||||||
|
|
||||||
|
def _wrap_stdin(infp):
|
||||||
|
"""Wrap a filehandle into a C function to be used as `stdin` callback
|
||||||
|
for ``set_stdio``. The filehandle has to support the readline() method.
|
||||||
|
"""
|
||||||
|
|
||||||
|
def _wrap(instance, dest, count):
|
||||||
|
try:
|
||||||
|
data = infp.readline(count)
|
||||||
|
except:
|
||||||
|
count = -1
|
||||||
|
else:
|
||||||
|
if not data:
|
||||||
|
count = 0
|
||||||
|
else:
|
||||||
|
count = len(data)
|
||||||
|
memmove(dest, c_char_p(data), count)
|
||||||
|
return count
|
||||||
|
|
||||||
|
return c_stdstream_call_t(_wrap)
|
||||||
|
|
||||||
|
|
||||||
|
def _wrap_stdout(outfp):
|
||||||
|
"""Wrap a filehandle into a C function to be used as `stdout` or
|
||||||
|
`stderr` callback for ``set_stdio``. The filehandle has to support the
|
||||||
|
write() and flush() methods.
|
||||||
|
"""
|
||||||
|
|
||||||
|
def _wrap(instance, str, count):
|
||||||
|
outfp.write(str[:count])
|
||||||
|
outfp.flush()
|
||||||
|
return count
|
||||||
|
|
||||||
|
return c_stdstream_call_t(_wrap)
|
||||||
|
|
||||||
|
|
||||||
|
_wrap_stderr = _wrap_stdout
|
||||||
|
|
||||||
|
|
||||||
|
def set_stdio(instance, stdin, stdout, stderr):
|
||||||
|
"""Set the callback functions for stdio.
|
||||||
|
|
||||||
|
``stdin``, ``stdout`` and ``stderr`` have to be ``ctypes``
|
||||||
|
callback functions matching the ``_gsprint.c_stdstream_call_t``
|
||||||
|
prototype. You may want to use _wrap_* to wrap file handles.
|
||||||
|
|
||||||
|
Note 1: This function only changes stdio of the Postscript
|
||||||
|
interpreter, not that of the devices.
|
||||||
|
|
||||||
|
Note 2: Make sure you keep references to C function objects
|
||||||
|
as long as they are used from C code. Otherwise they may be
|
||||||
|
garbage collected, crashing your program when a callback is made.
|
||||||
|
|
||||||
|
The ``stdin`` callback function should return the number of
|
||||||
|
characters read, `0` for EOF, or `-1` for error. The `stdout` and
|
||||||
|
`stderr` callback functions should return the number of characters
|
||||||
|
written.
|
||||||
|
|
||||||
|
You may pass ``None`` for any of stdin, stdout or stderr , in which
|
||||||
|
case the system stdin, stdout resp. stderr will be used.
|
||||||
|
"""
|
||||||
|
rc = libgs.gsapi_set_stdio(instance, stdin, stdout, stderr)
|
||||||
|
if rc not in (0, e_Quit, e_Info):
|
||||||
|
raise GhostscriptError(rc)
|
||||||
|
return rc
|
||||||
|
|
||||||
|
|
||||||
|
def init_with_args(instance, argv):
|
||||||
|
"""Initialise the interpreter
|
||||||
|
|
||||||
|
1. If quit or EOF occur during init_with_args(), the return value
|
||||||
|
will be e_Quit. This is not an error. You must call exit() and
|
||||||
|
must not call any other functions.
|
||||||
|
|
||||||
|
2. If usage info should be displayed, the return value will be
|
||||||
|
e_Info which is not an error. Do not call exit().
|
||||||
|
|
||||||
|
3. Under normal conditions this returns 0. You would then call one
|
||||||
|
or more run_*() functions and then finish with exit()
|
||||||
|
"""
|
||||||
|
ArgArray = c_char_p * len(argv)
|
||||||
|
c_argv = ArgArray(*argv)
|
||||||
|
rc = libgs.gsapi_init_with_args(instance, len(argv), c_argv)
|
||||||
|
if rc not in (0, e_Quit, e_Info):
|
||||||
|
raise GhostscriptError(rc)
|
||||||
|
return rc
|
||||||
|
|
||||||
|
|
||||||
|
def exit(instance):
|
||||||
|
"""Exit the interpreter
|
||||||
|
|
||||||
|
This must be called on shutdown if init_with_args() has been
|
||||||
|
called, and just before delete_instance()
|
||||||
|
"""
|
||||||
|
rc = libgs.gsapi_exit(instance)
|
||||||
|
if rc != 0:
|
||||||
|
raise GhostscriptError(rc)
|
||||||
|
return rc
|
||||||
|
|
||||||
|
|
||||||
|
def __win32_finddll():
|
||||||
|
try:
|
||||||
|
import winreg
|
||||||
|
except ImportError:
|
||||||
|
# assume Python 2
|
||||||
|
from _winreg import (
|
||||||
|
OpenKey,
|
||||||
|
CloseKey,
|
||||||
|
EnumKey,
|
||||||
|
QueryValueEx,
|
||||||
|
QueryInfoKey,
|
||||||
|
HKEY_LOCAL_MACHINE,
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
from winreg import (
|
||||||
|
OpenKey,
|
||||||
|
CloseKey,
|
||||||
|
EnumKey,
|
||||||
|
QueryValueEx,
|
||||||
|
QueryInfoKey,
|
||||||
|
HKEY_LOCAL_MACHINE,
|
||||||
|
)
|
||||||
|
|
||||||
|
from distutils.version import LooseVersion
|
||||||
|
import os
|
||||||
|
|
||||||
|
dlls = []
|
||||||
|
# Look up different variants of Ghostscript and take the highest
|
||||||
|
# version for which the DLL is to be found in the filesystem.
|
||||||
|
for key_name in (
|
||||||
|
"AFPL Ghostscript",
|
||||||
|
"Aladdin Ghostscript",
|
||||||
|
"GNU Ghostscript",
|
||||||
|
"GPL Ghostscript",
|
||||||
|
):
|
||||||
|
try:
|
||||||
|
k1 = OpenKey(HKEY_LOCAL_MACHINE, "Software\\%s" % key_name)
|
||||||
|
for num in range(0, QueryInfoKey(k1)[0]):
|
||||||
|
version = EnumKey(k1, num)
|
||||||
|
try:
|
||||||
|
k2 = OpenKey(k1, version)
|
||||||
|
dll_path = QueryValueEx(k2, "GS_DLL")[0]
|
||||||
|
CloseKey(k2)
|
||||||
|
if os.path.exists(dll_path):
|
||||||
|
dlls.append((LooseVersion(version), dll_path))
|
||||||
|
except WindowsError:
|
||||||
|
pass
|
||||||
|
CloseKey(k1)
|
||||||
|
except WindowsError:
|
||||||
|
pass
|
||||||
|
if dlls:
|
||||||
|
dlls.sort()
|
||||||
|
return dlls[-1][-1]
|
||||||
|
else:
|
||||||
|
return None
|
||||||
|
|
||||||
|
|
||||||
|
if sys.platform == "win32":
|
||||||
|
libgs = __win32_finddll()
|
||||||
|
if not libgs:
|
||||||
|
import ctypes.util
|
||||||
|
|
||||||
|
libgs = ctypes.util.find_library(
|
||||||
|
"".join(("gsdll", str(ctypes.sizeof(ctypes.c_voidp) * 8), ".dll"))
|
||||||
|
) # finds in %PATH%
|
||||||
|
if not libgs:
|
||||||
|
raise RuntimeError("Please make sure that Ghostscript is installed")
|
||||||
|
libgs = windll.LoadLibrary(libgs)
|
||||||
|
else:
|
||||||
|
try:
|
||||||
|
libgs = cdll.LoadLibrary("libgs.so")
|
||||||
|
except OSError:
|
||||||
|
# shared object file not found
|
||||||
|
import ctypes.util
|
||||||
|
|
||||||
|
libgs = ctypes.util.find_library("gs")
|
||||||
|
if not libgs:
|
||||||
|
raise RuntimeError("Please make sure that Ghostscript is installed")
|
||||||
|
libgs = cdll.LoadLibrary(libgs)
|
||||||
|
|
||||||
|
del __win32_finddll
|
||||||
|
|
@ -38,8 +38,8 @@ class PDFHandler(object):
|
||||||
if is_url(filepath):
|
if is_url(filepath):
|
||||||
filepath = download_url(filepath)
|
filepath = download_url(filepath)
|
||||||
self.filepath = filepath
|
self.filepath = filepath
|
||||||
# if not filepath.lower().endswith(".pdf"):
|
if not filepath.lower().endswith(".pdf"):
|
||||||
# raise NotImplementedError("File format not supported")
|
raise NotImplementedError("File format not supported")
|
||||||
|
|
||||||
if password is None:
|
if password is None:
|
||||||
self.password = ""
|
self.password = ""
|
||||||
|
|
@ -47,9 +47,9 @@ class PDFHandler(object):
|
||||||
self.password = password
|
self.password = password
|
||||||
if sys.version_info[0] < 3:
|
if sys.version_info[0] < 3:
|
||||||
self.password = self.password.encode("ascii")
|
self.password = self.password.encode("ascii")
|
||||||
self.pages = self._get_pages(pages)
|
self.pages = self._get_pages(self.filepath, pages)
|
||||||
|
|
||||||
def _get_pages(self, pages):
|
def _get_pages(self, filepath, pages):
|
||||||
"""Converts pages string to list of ints.
|
"""Converts pages string to list of ints.
|
||||||
|
|
||||||
Parameters
|
Parameters
|
||||||
|
|
@ -67,16 +67,13 @@ class PDFHandler(object):
|
||||||
|
|
||||||
"""
|
"""
|
||||||
page_numbers = []
|
page_numbers = []
|
||||||
|
|
||||||
if pages == "1":
|
if pages == "1":
|
||||||
page_numbers.append({"start": 1, "end": 1})
|
page_numbers.append({"start": 1, "end": 1})
|
||||||
else:
|
else:
|
||||||
with open(self.filepath, "rb") as f:
|
instream = open(filepath, "rb")
|
||||||
infile = PdfFileReader(f, strict=False)
|
infile = PdfFileReader(instream, strict=False)
|
||||||
|
|
||||||
if infile.isEncrypted:
|
if infile.isEncrypted:
|
||||||
infile.decrypt(self.password)
|
infile.decrypt(self.password)
|
||||||
|
|
||||||
if pages == "all":
|
if pages == "all":
|
||||||
page_numbers.append({"start": 1, "end": infile.getNumPages()})
|
page_numbers.append({"start": 1, "end": infile.getNumPages()})
|
||||||
else:
|
else:
|
||||||
|
|
@ -88,7 +85,7 @@ class PDFHandler(object):
|
||||||
page_numbers.append({"start": int(a), "end": int(b)})
|
page_numbers.append({"start": int(a), "end": int(b)})
|
||||||
else:
|
else:
|
||||||
page_numbers.append({"start": int(r), "end": int(r)})
|
page_numbers.append({"start": int(r), "end": int(r)})
|
||||||
|
instream.close()
|
||||||
P = []
|
P = []
|
||||||
for p in page_numbers:
|
for p in page_numbers:
|
||||||
P.extend(range(p["start"], p["end"] + 1))
|
P.extend(range(p["start"], p["end"] + 1))
|
||||||
|
|
|
||||||
|
|
@ -17,4 +17,3 @@ class BaseParser(object):
|
||||||
self.vertical_text = get_text_objects(self.layout, ltype="vertical_text")
|
self.vertical_text = get_text_objects(self.layout, ltype="vertical_text")
|
||||||
self.pdf_width, self.pdf_height = self.dimensions
|
self.pdf_width, self.pdf_height = self.dimensions
|
||||||
self.rootname, __ = os.path.splitext(self.filename)
|
self.rootname, __ = os.path.splitext(self.filename)
|
||||||
self.imagename = "".join([self.rootname, ".png"])
|
|
||||||
|
|
|
||||||
|
|
@ -6,6 +6,7 @@ import copy
|
||||||
import locale
|
import locale
|
||||||
import logging
|
import logging
|
||||||
import warnings
|
import warnings
|
||||||
|
import subprocess
|
||||||
|
|
||||||
import numpy as np
|
import numpy as np
|
||||||
import pandas as pd
|
import pandas as pd
|
||||||
|
|
@ -28,7 +29,6 @@ from ..image_processing import (
|
||||||
find_contours,
|
find_contours,
|
||||||
find_joints,
|
find_joints,
|
||||||
)
|
)
|
||||||
from ..backends.image_conversion import BACKENDS
|
|
||||||
|
|
||||||
|
|
||||||
logger = logging.getLogger("camelot")
|
logger = logging.getLogger("camelot")
|
||||||
|
|
@ -111,8 +111,7 @@ class Lattice(BaseParser):
|
||||||
threshold_constant=-2,
|
threshold_constant=-2,
|
||||||
iterations=0,
|
iterations=0,
|
||||||
resolution=300,
|
resolution=300,
|
||||||
backend="ghostscript",
|
**kwargs
|
||||||
**kwargs,
|
|
||||||
):
|
):
|
||||||
self.table_regions = table_regions
|
self.table_regions = table_regions
|
||||||
self.table_areas = table_areas
|
self.table_areas = table_areas
|
||||||
|
|
@ -129,37 +128,6 @@ class Lattice(BaseParser):
|
||||||
self.threshold_constant = threshold_constant
|
self.threshold_constant = threshold_constant
|
||||||
self.iterations = iterations
|
self.iterations = iterations
|
||||||
self.resolution = resolution
|
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
|
|
||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def _reduce_index(t, idx, shift_text):
|
def _reduce_index(t, idx, shift_text):
|
||||||
|
|
@ -239,6 +207,19 @@ class Lattice(BaseParser):
|
||||||
t.cells[i][j].text = t.cells[i - 1][j].text
|
t.cells[i][j].text = t.cells[i - 1][j].text
|
||||||
return t
|
return t
|
||||||
|
|
||||||
|
def _generate_image(self):
|
||||||
|
from ..ext.ghostscript import Ghostscript
|
||||||
|
|
||||||
|
self.imagename = "".join([self.rootname, ".png"])
|
||||||
|
gs_call = "-q -sDEVICE=png16m -o {} -r{} {}".format(
|
||||||
|
self.imagename, self.resolution, self.filename
|
||||||
|
)
|
||||||
|
gs_call = gs_call.encode().split()
|
||||||
|
null = open(os.devnull, "wb")
|
||||||
|
with Ghostscript(*gs_call, stdout=null) as gs:
|
||||||
|
pass
|
||||||
|
null.close()
|
||||||
|
|
||||||
def _generate_table_bbox(self):
|
def _generate_table_bbox(self):
|
||||||
def scale_areas(areas):
|
def scale_areas(areas):
|
||||||
scaled_areas = []
|
scaled_areas = []
|
||||||
|
|
@ -418,8 +399,7 @@ class Lattice(BaseParser):
|
||||||
)
|
)
|
||||||
return []
|
return []
|
||||||
|
|
||||||
self.backend.convert(self.filename, self.imagename)
|
self._generate_image()
|
||||||
|
|
||||||
self._generate_table_bbox()
|
self._generate_table_bbox()
|
||||||
|
|
||||||
_tables = []
|
_tables = []
|
||||||
|
|
|
||||||
|
|
@ -54,7 +54,7 @@ Release v\ |version|. (:ref:`Installation <install>`)
|
||||||
>>> tables = camelot.read_pdf('foo.pdf')
|
>>> tables = camelot.read_pdf('foo.pdf')
|
||||||
>>> tables
|
>>> tables
|
||||||
<TableList n=1>
|
<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]
|
>>> tables[0]
|
||||||
<Table shape=(7, 7)>
|
<Table shape=(7, 7)>
|
||||||
>>> tables[0].parsing_report
|
>>> tables[0].parsing_report
|
||||||
|
|
@ -64,7 +64,7 @@ Release v\ |version|. (:ref:`Installation <install>`)
|
||||||
'order': 1,
|
'order': 1,
|
||||||
'page': 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!
|
>>> tables[0].df # get a pandas DataFrame!
|
||||||
|
|
||||||
.. csv-table::
|
.. csv-table::
|
||||||
|
|
@ -74,16 +74,14 @@ Camelot also comes packaged with a :ref:`command-line interface <cli>`!
|
||||||
|
|
||||||
.. 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".)
|
.. 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
|
.. _explains: https://github.com/tabulapdf/tabula#why-tabula
|
||||||
|
|
||||||
Why Camelot?
|
Why Camelot?
|
||||||
------------
|
------------
|
||||||
|
|
||||||
- **Configurability**: Camelot gives you control over the table extraction process with :ref:`tweakable settings <advanced>`.
|
- **Configurability**: Camelot gives you control over the table extraction process with its :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.
|
- **Metrics**: Bad tables can be discarded 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.
|
- **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 and Sqlite.
|
||||||
|
|
||||||
.. _ETL and data analysis workflows: https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873
|
.. _ETL and data analysis workflows: https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873
|
||||||
|
|
||||||
|
|
@ -112,7 +110,6 @@ This part of the documentation begins with some background information about why
|
||||||
user/how-it-works
|
user/how-it-works
|
||||||
user/quickstart
|
user/quickstart
|
||||||
user/advanced
|
user/advanced
|
||||||
user/faq
|
|
||||||
user/cli
|
user/cli
|
||||||
|
|
||||||
The API Documentation/Guide
|
The API Documentation/Guide
|
||||||
|
|
|
||||||
|
|
@ -623,26 +623,3 @@ To deal with such cases, you can tweak PDFMiner's `LAParams kwargs <https://gith
|
||||||
::
|
::
|
||||||
|
|
||||||
>>> tables = camelot.read_pdf('foo.pdf', layout_kwargs={'detect_vertical': False})
|
>>> 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())
|
|
||||||
|
|
|
||||||
|
|
@ -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())
|
|
||||||
|
|
@ -43,9 +43,8 @@ For Ubuntu/MacOS::
|
||||||
|
|
||||||
For Windows::
|
For Windows::
|
||||||
|
|
||||||
>>> import ctypes
|
|
||||||
>>> from ctypes.util import find_library
|
>>> from ctypes.util import find_library
|
||||||
>>> find_library("".join(("gsdll", str(ctypes.sizeof(ctypes.c_voidp) * 8), ".dll")))
|
>>> find_library("".join(("gsdll", str(ctypes.sizeof(ctypes.c_voidp) * 8), ".dll"))
|
||||||
<name-of-ghostscript-library-on-windows>
|
<name-of-ghostscript-library-on-windows>
|
||||||
|
|
||||||
**Check:** The output of the ``find_library`` function should not be empty.
|
**Check:** The output of the ``find_library`` function should not be empty.
|
||||||
|
|
|
||||||
|
|
@ -14,7 +14,7 @@ pip
|
||||||
|
|
||||||
To install Camelot from PyPI using ``pip``, please include the extra ``cv`` requirement as shown::
|
To install Camelot from PyPI using ``pip``, please include the extra ``cv`` requirement as shown::
|
||||||
|
|
||||||
$ pip install "camelot-py[base]"
|
$ pip install "camelot-py[cv]"
|
||||||
|
|
||||||
conda
|
conda
|
||||||
-----
|
-----
|
||||||
|
|
@ -37,4 +37,4 @@ After :ref:`installing the dependencies <install_deps>`, you can install Camelot
|
||||||
::
|
::
|
||||||
|
|
||||||
$ cd camelot
|
$ cd camelot
|
||||||
$ pip install ".[base]"
|
$ pip install ".[cv]"
|
||||||
|
|
|
||||||
|
|
@ -56,7 +56,7 @@ Woah! The accuracy is top-notch and there is less whitespace, which means the ta
|
||||||
.. csv-table::
|
.. csv-table::
|
||||||
:file: ../_static/csv/foo.csv
|
: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>` :meth:`to_html() <camelot.core.Table.to_html>` or :meth:`to_sqlite() <camelot.core.Table.to_sqlite>` methods to export the table as JSON, Excel, HTML files or a sqlite database respectively.
|
||||||
|
|
||||||
::
|
::
|
||||||
|
|
||||||
|
|
@ -76,7 +76,7 @@ You can also export all tables at once, using the :class:`tables <camelot.core.T
|
||||||
|
|
||||||
$ camelot --format csv --output foo.csv lattice foo.pdf
|
$ 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'``, ``f='html'`` or ``f='sqlite'``.
|
||||||
|
|
||||||
.. 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.
|
.. 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.
|
||||||
|
|
||||||
|
|
|
||||||
10
setup.py
10
setup.py
|
|
@ -21,10 +21,9 @@ requires = [
|
||||||
"pandas>=0.23.4",
|
"pandas>=0.23.4",
|
||||||
"pdfminer.six>=20200726",
|
"pdfminer.six>=20200726",
|
||||||
"PyPDF2>=1.26.0",
|
"PyPDF2>=1.26.0",
|
||||||
"tabulate>=0.8.9",
|
|
||||||
]
|
]
|
||||||
|
|
||||||
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 = [
|
plot_requires = [
|
||||||
"matplotlib>=2.2.3",
|
"matplotlib>=2.2.3",
|
||||||
|
|
@ -37,10 +36,9 @@ dev_requires = [
|
||||||
"pytest-mpl>=0.11",
|
"pytest-mpl>=0.11",
|
||||||
"pytest-runner>=5.2",
|
"pytest-runner>=5.2",
|
||||||
"Sphinx>=3.1.2",
|
"Sphinx>=3.1.2",
|
||||||
"sphinx-autobuild>=2021.3.14",
|
|
||||||
]
|
]
|
||||||
|
|
||||||
all_requires = base_requires + plot_requires
|
all_requires = cv_requires + plot_requires
|
||||||
dev_requires = dev_requires + all_requires
|
dev_requires = dev_requires + all_requires
|
||||||
|
|
||||||
|
|
||||||
|
|
@ -59,8 +57,7 @@ def setup_package():
|
||||||
install_requires=requires,
|
install_requires=requires,
|
||||||
extras_require={
|
extras_require={
|
||||||
"all": all_requires,
|
"all": all_requires,
|
||||||
"base": base_requires,
|
"cv": cv_requires,
|
||||||
"cv": base_requires, # deprecate
|
|
||||||
"dev": dev_requires,
|
"dev": dev_requires,
|
||||||
"plot": plot_requires,
|
"plot": plot_requires,
|
||||||
},
|
},
|
||||||
|
|
@ -76,6 +73,7 @@ def setup_package():
|
||||||
"Programming Language :: Python :: 3.6",
|
"Programming Language :: Python :: 3.6",
|
||||||
"Programming Language :: Python :: 3.7",
|
"Programming Language :: Python :: 3.7",
|
||||||
"Programming Language :: Python :: 3.8",
|
"Programming Language :: Python :: 3.8",
|
||||||
|
"Programming Language :: Python :: 3.9",
|
||||||
],
|
],
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
|
||||||
|
Before Width: | Height: | Size: 8.2 KiB After Width: | Height: | Size: 8.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 8.1 KiB |
|
Before Width: | Height: | Size: 48 KiB After Width: | Height: | Size: 48 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 66 KiB |
|
Before Width: | Height: | Size: 46 KiB After Width: | Height: | Size: 46 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 64 KiB |
|
Before Width: | Height: | Size: 6.7 KiB After Width: | Height: | Size: 6.7 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 6.6 KiB |
|
|
@ -1,9 +1,7 @@
|
||||||
# -*- coding: utf-8 -*-
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
import os
|
import os
|
||||||
import sys
|
|
||||||
|
|
||||||
import pytest
|
|
||||||
from click.testing import CliRunner
|
from click.testing import CliRunner
|
||||||
|
|
||||||
from camelot.cli import cli
|
from camelot.cli import cli
|
||||||
|
|
@ -13,11 +11,6 @@ from camelot.utils import TemporaryDirectory
|
||||||
testdir = os.path.dirname(os.path.abspath(__file__))
|
testdir = os.path.dirname(os.path.abspath(__file__))
|
||||||
testdir = os.path.join(testdir, "files")
|
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_help_output():
|
def test_help_output():
|
||||||
runner = CliRunner()
|
runner = CliRunner()
|
||||||
|
|
@ -33,7 +26,6 @@ def test_help_output():
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@skip_on_windows
|
|
||||||
def test_cli_lattice():
|
def test_cli_lattice():
|
||||||
with TemporaryDirectory() as tempdir:
|
with TemporaryDirectory() as tempdir:
|
||||||
infile = os.path.join(testdir, "foo.pdf")
|
infile = os.path.join(testdir, "foo.pdf")
|
||||||
|
|
@ -43,7 +35,7 @@ def test_cli_lattice():
|
||||||
cli, ["--format", "csv", "--output", outfile, "lattice", infile]
|
cli, ["--format", "csv", "--output", outfile, "lattice", infile]
|
||||||
)
|
)
|
||||||
assert result.exit_code == 0
|
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])
|
result = runner.invoke(cli, ["--format", "csv", "lattice", infile])
|
||||||
output_error = "Error: Please specify output file path using --output"
|
output_error = "Error: Please specify output file path using --output"
|
||||||
|
|
@ -131,7 +123,7 @@ def test_cli_output_format():
|
||||||
cli,
|
cli,
|
||||||
["--format", "json", "--output", outfile, "stream", infile],
|
["--format", "json", "--output", outfile, "stream", infile],
|
||||||
)
|
)
|
||||||
assert result.exit_code == 0, f"Output: {result.output}"
|
assert result.exit_code == 0
|
||||||
|
|
||||||
# excel
|
# excel
|
||||||
outfile = os.path.join(tempdir, "health.xlsx")
|
outfile = os.path.join(tempdir, "health.xlsx")
|
||||||
|
|
@ -139,7 +131,7 @@ def test_cli_output_format():
|
||||||
cli,
|
cli,
|
||||||
["--format", "excel", "--output", outfile, "stream", infile],
|
["--format", "excel", "--output", outfile, "stream", infile],
|
||||||
)
|
)
|
||||||
assert result.exit_code == 0, f"Output: {result.output}"
|
assert result.exit_code == 0
|
||||||
|
|
||||||
# html
|
# html
|
||||||
outfile = os.path.join(tempdir, "health.html")
|
outfile = os.path.join(tempdir, "health.html")
|
||||||
|
|
@ -147,15 +139,7 @@ def test_cli_output_format():
|
||||||
cli,
|
cli,
|
||||||
["--format", "html", "--output", outfile, "stream", infile],
|
["--format", "html", "--output", outfile, "stream", infile],
|
||||||
)
|
)
|
||||||
assert result.exit_code == 0, f"Output: {result.output}"
|
assert result.exit_code == 0
|
||||||
|
|
||||||
# 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}"
|
|
||||||
|
|
||||||
# zip
|
# zip
|
||||||
outfile = os.path.join(tempdir, "health.csv")
|
outfile = os.path.join(tempdir, "health.csv")
|
||||||
|
|
@ -171,7 +155,7 @@ def test_cli_output_format():
|
||||||
infile,
|
infile,
|
||||||
],
|
],
|
||||||
)
|
)
|
||||||
assert result.exit_code == 0, f"Output: {result.output}"
|
assert result.exit_code == 0
|
||||||
|
|
||||||
|
|
||||||
def test_cli_quiet():
|
def test_cli_quiet():
|
||||||
|
|
|
||||||
|
|
@ -1,45 +1,20 @@
|
||||||
# -*- coding: utf-8 -*-
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
import os
|
import os
|
||||||
import sys
|
|
||||||
|
|
||||||
import pytest
|
|
||||||
import pandas as pd
|
import pandas as pd
|
||||||
from pandas.testing import assert_frame_equal
|
from pandas.testing import assert_frame_equal
|
||||||
|
|
||||||
import camelot
|
import camelot
|
||||||
from camelot.io import PDFHandler
|
|
||||||
from camelot.core import Table, TableList
|
from camelot.core import Table, TableList
|
||||||
from camelot.__version__ import generate_version
|
from camelot.__version__ import generate_version
|
||||||
from camelot.backends import ImageConversionBackend
|
|
||||||
|
|
||||||
from .data import *
|
from .data import *
|
||||||
|
|
||||||
testdir = os.path.dirname(os.path.abspath(__file__))
|
testdir = os.path.dirname(os.path.abspath(__file__))
|
||||||
testdir = os.path.join(testdir, "files")
|
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():
|
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}
|
||||||
|
|
||||||
|
|
@ -59,75 +34,246 @@ def test_password():
|
||||||
assert_frame_equal(df, tables[0].df)
|
assert_frame_equal(df, 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_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_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)
|
||||||
|
|
||||||
|
|
||||||
|
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)
|
||||||
|
|
||||||
|
|
||||||
|
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_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)
|
||||||
|
|
||||||
|
|
||||||
|
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)
|
||||||
|
|
||||||
|
|
||||||
|
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)
|
||||||
|
|
||||||
|
|
||||||
|
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)
|
||||||
|
|
||||||
|
|
||||||
|
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)
|
||||||
|
|
||||||
|
|
||||||
|
def test_repr():
|
||||||
filename = os.path.join(testdir, "foo.pdf")
|
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) == "<TableList n=1>"
|
||||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
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=218.43 x2=164.64 y2=233.77>"
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
@skip_on_windows
|
def test_pages():
|
||||||
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_url_poppler():
|
|
||||||
url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
|
url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
|
||||||
tables = camelot.read_pdf(url, backend="poppler")
|
tables = camelot.read_pdf(url)
|
||||||
assert repr(tables) == "<TableList n=1>"
|
assert repr(tables) == "<TableList n=1>"
|
||||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
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=218.43 x2=164.64 y2=233.77>"
|
||||||
|
)
|
||||||
|
|
||||||
|
tables = camelot.read_pdf(url, pages="1-end")
|
||||||
|
assert repr(tables) == "<TableList n=1>"
|
||||||
|
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||||
|
assert (
|
||||||
|
repr(tables[0].cells[0][0]) == "<Cell x1=120.48 y1=218.43 x2=164.64 y2=233.77>"
|
||||||
|
)
|
||||||
|
|
||||||
|
tables = camelot.read_pdf(url, pages="all")
|
||||||
|
assert repr(tables) == "<TableList n=1>"
|
||||||
|
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||||
|
assert (
|
||||||
|
repr(tables[0].cells[0][0]) == "<Cell x1=120.48 y1=218.43 x2=164.64 y2=233.77>"
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
@skip_on_windows
|
def test_url():
|
||||||
def test_url_ghostscript():
|
|
||||||
url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
|
url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
|
||||||
tables = camelot.read_pdf(url, backend="ghostscript")
|
tables = camelot.read_pdf(url)
|
||||||
assert repr(tables) == "<TableList n=1>"
|
assert repr(tables) == "<TableList n=1>"
|
||||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
||||||
assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
|
assert (
|
||||||
|
repr(tables[0].cells[0][0]) == "<Cell x1=120.48 y1=218.43 x2=164.64 y2=233.77>"
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
def test_pages_poppler():
|
def test_arabic():
|
||||||
url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
|
df = pd.DataFrame(data_arabic)
|
||||||
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")
|
filename = os.path.join(testdir, "tabula/arabic.pdf")
|
||||||
assert repr(tables) == "<TableList n=1>"
|
tables = camelot.read_pdf(filename)
|
||||||
assert repr(tables[0]) == "<Table shape=(7, 7)>"
|
assert_frame_equal(df, tables[0].df)
|
||||||
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 test_table_order():
|
||||||
|
|
@ -155,20 +301,24 @@ def test_table_order():
|
||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
def test_handler_pages_generator():
|
def test_version_generation():
|
||||||
filename = os.path.join(testdir, "foo.pdf")
|
version = (0, 7, 3)
|
||||||
|
assert generate_version(version, prerelease=None, revision=None) == "0.7.3"
|
||||||
|
|
||||||
handler = PDFHandler(filename)
|
|
||||||
assert handler._get_pages("1") == [1]
|
|
||||||
|
|
||||||
handler = PDFHandler(filename)
|
def test_version_generation_with_prerelease_revision():
|
||||||
assert handler._get_pages("all") == [1]
|
version = (0, 7, 3)
|
||||||
|
prerelease = "alpha"
|
||||||
|
revision = 2
|
||||||
|
assert (
|
||||||
|
generate_version(version, prerelease=prerelease, revision=revision)
|
||||||
|
== "0.7.3-alpha.2"
|
||||||
|
)
|
||||||
|
|
||||||
handler = PDFHandler(filename)
|
|
||||||
assert handler._get_pages("1-end") == [1]
|
|
||||||
|
|
||||||
handler = PDFHandler(filename)
|
def test_stream_duplicated_text():
|
||||||
assert handler._get_pages("1,2,3,4") == [1, 2, 3, 4]
|
df = pd.DataFrame(data_stream_duplicated_text)
|
||||||
|
|
||||||
handler = PDFHandler(filename)
|
filename = os.path.join(testdir, "birdisland.pdf")
|
||||||
assert handler._get_pages("1,2,5-10") == [1, 2, 5, 6, 7, 8, 9, 10]
|
tables = camelot.read_pdf(filename, flavor="stream")
|
||||||
|
assert_frame_equal(df, tables[0].df)
|
||||||
|
|
|
||||||
|
|
@ -1,7 +1,6 @@
|
||||||
# -*- coding: utf-8 -*-
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
import os
|
import os
|
||||||
import sys
|
|
||||||
import warnings
|
import warnings
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
@ -13,11 +12,6 @@ testdir = os.path.dirname(os.path.abspath(__file__))
|
||||||
testdir = os.path.join(testdir, "files")
|
testdir = os.path.join(testdir, "files")
|
||||||
filename = os.path.join(testdir, "foo.pdf")
|
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",
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
def test_unknown_flavor():
|
def test_unknown_flavor():
|
||||||
message = "Unknown flavor specified." " Use either 'lattice' or 'stream'"
|
message = "Unknown flavor specified." " Use either 'lattice' or 'stream'"
|
||||||
|
|
@ -38,7 +32,56 @@ def test_unsupported_format():
|
||||||
tables = camelot.read_pdf(filename)
|
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, 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")
|
||||||
|
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_lattice_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="lattice")
|
||||||
|
assert str(e.value) == "No tables found on page-1"
|
||||||
|
|
||||||
|
|
||||||
|
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_no_tables_found_logs_suppressed():
|
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():
|
with warnings.catch_warnings():
|
||||||
|
|
@ -75,81 +118,3 @@ def test_bad_password():
|
||||||
message = "file has not been decrypted"
|
message = "file has not been decrypted"
|
||||||
with pytest.raises(Exception, match=message):
|
with pytest.raises(Exception, match=message):
|
||||||
tables = camelot.read_pdf(filename, password="wrongpass")
|
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
|
|
||||||
|
|
|
||||||
|
|
@ -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)
|
|
||||||
|
|
@ -1,22 +1,16 @@
|
||||||
# -*- coding: utf-8 -*-
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
import os
|
import os
|
||||||
import sys
|
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
||||||
import camelot
|
import camelot
|
||||||
|
|
||||||
|
|
||||||
testdir = os.path.dirname(os.path.abspath(__file__))
|
testdir = os.path.dirname(os.path.abspath(__file__))
|
||||||
testdir = os.path.join(testdir, "files")
|
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():
|
def test_text_plot():
|
||||||
filename = os.path.join(testdir, "foo.pdf")
|
filename = os.path.join(testdir, "foo.pdf")
|
||||||
|
|
@ -25,24 +19,16 @@ def test_text_plot():
|
||||||
|
|
||||||
|
|
||||||
@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_textedge_plot():
|
def test_grid_plot():
|
||||||
filename = os.path.join(testdir, "tabula/12s0324.pdf")
|
filename = os.path.join(testdir, "foo.pdf")
|
||||||
tables = camelot.read_pdf(filename, flavor="stream")
|
tables = camelot.read_pdf(filename)
|
||||||
return camelot.plot(tables[0], kind="textedge")
|
return camelot.plot(tables[0], kind="grid")
|
||||||
|
|
||||||
|
|
||||||
@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_lattice_contour_plot_poppler():
|
def test_lattice_contour_plot():
|
||||||
filename = os.path.join(testdir, "foo.pdf")
|
filename = os.path.join(testdir, "foo.pdf")
|
||||||
tables = camelot.read_pdf(filename, backend="poppler")
|
tables = camelot.read_pdf(filename)
|
||||||
return camelot.plot(tables[0], kind="contour")
|
|
||||||
|
|
||||||
|
|
||||||
@skip_on_windows
|
|
||||||
@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
|
|
||||||
def test_lattice_contour_plot_ghostscript():
|
|
||||||
filename = os.path.join(testdir, "foo.pdf")
|
|
||||||
tables = camelot.read_pdf(filename, backend="ghostscript")
|
|
||||||
return camelot.plot(tables[0], kind="contour")
|
return camelot.plot(tables[0], kind="contour")
|
||||||
|
|
||||||
|
|
||||||
|
|
@ -54,45 +40,21 @@ def test_stream_contour_plot():
|
||||||
|
|
||||||
|
|
||||||
@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_line_plot_poppler():
|
def test_line_plot():
|
||||||
filename = os.path.join(testdir, "foo.pdf")
|
filename = os.path.join(testdir, "foo.pdf")
|
||||||
tables = camelot.read_pdf(filename, backend="poppler")
|
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():
|
|
||||||
filename = os.path.join(testdir, "foo.pdf")
|
|
||||||
tables = camelot.read_pdf(filename, backend="ghostscript")
|
|
||||||
return camelot.plot(tables[0], kind="line")
|
return camelot.plot(tables[0], kind="line")
|
||||||
|
|
||||||
|
|
||||||
@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_joint_plot_poppler():
|
def test_joint_plot():
|
||||||
filename = os.path.join(testdir, "foo.pdf")
|
filename = os.path.join(testdir, "foo.pdf")
|
||||||
tables = camelot.read_pdf(filename, backend="poppler")
|
tables = camelot.read_pdf(filename)
|
||||||
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")
|
return camelot.plot(tables[0], kind="joint")
|
||||||
|
|
||||||
|
|
||||||
@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_grid_plot_poppler():
|
def test_textedge_plot():
|
||||||
filename = os.path.join(testdir, "foo.pdf")
|
filename = os.path.join(testdir, "tabula/12s0324.pdf")
|
||||||
tables = camelot.read_pdf(filename, backend="poppler")
|
tables = camelot.read_pdf(filename, flavor="stream")
|
||||||
return camelot.plot(tables[0], kind="grid")
|
return camelot.plot(tables[0], kind="textedge")
|
||||||
|
|
||||||
|
|
||||||
@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")
|
|
||||||
|
|
|
||||||
|
|
@ -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