Tolto un controllo inutile sul nome che finisce con .pdf

Change get backend method for Lattice and run tests

.coveragerc

@@ -1,3 +1,2 @@
 [run]
 branch = True
-omit = camelot/ext/*

.github/ISSUE_TEMPLATE/bug_report.md

@@ -10,20 +10,25 @@ assignees: ''
 <!-- Please read the filing issues section of the contributor's guide first: https://camelot-py.readthedocs.io/en/master/dev/contributing.html -->
 
 **Describe the bug**
-A clear and concise description of what the bug is.
+
+<!-- A clear and concise description of what the bug is. -->
 
 **Steps to reproduce the bug**
-Steps used to install `camelot`:
-1. Add step here (you can add more steps too)
 
-Steps to reproduce the behavior:
-1. Add step here (you can add more steps too)
+<!-- Steps used to install `camelot`:
+1. Add step here (you can add more steps too) -->
+
+<!-- Steps to be used to reproduce behavior:
+1. Add step here (you can add more steps too) -->
 
 **Expected behavior**
-A clear and concise description of what you expected to happen.
+
+<!-- A clear and concise description of what you expected to happen. -->
 
 **Code**
-Add the Camelot code snippet that you used.
+
+<!-- Add the Camelot code snippet that you used. -->
+
 ```
 import camelot
 
@@ -31,18 +36,22 @@ import camelot
 ```
 
 **PDF**
-Add the PDF file that you want to extract tables from.
+
+<!-- Add the PDF file that you want to extract tables from. -->
 
 **Screenshots**
-If applicable, add screenshots to help explain your problem.
+
+<!-- If applicable, add screenshots to help explain your problem. -->
 
 **Environment**
- - OS: [e.g. MacOS]
- - Python version:
- - Numpy version:
- - OpenCV version:
- - Ghostscript version:
- - Camelot version:
+
+- OS: [e.g. macOS]
+- Python version:
+- Numpy version:
+- OpenCV version:
+- Ghostscript version:
+- Camelot version:
 
 **Additional context**
-Add any other context about the problem here.
+
+<!-- Add any other context about the problem here. -->

.github/workflows/tests.yml

@@ -0,0 +1,44 @@
+name: tests
+
+on: [pull_request]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.6, 3.7, 3.8]
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install camelot with dependencies
+        run: |
+          make install
+      - name: Test with pytest
+        run: |
+          make test
+
+  test_latest:
+    name: Test on ${{ matrix.os }} with Python 3.9
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: [3.9]
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install camelot with dependencies
+        run: |
+          make install
+      - name: Test with pytest
+        run: |
+          make test

.gitignore

@@ -1,3 +1,4 @@
+fontconfig/
 __pycache__/
 *.py[cod]
 *.so

.travis.yml

@@ -1,29 +0,0 @@
-sudo: true
-language: python
-cache: pip
-addons:
-  apt:
-    update: true
-install:
-  - make install
-jobs:
-  include:
-    - stage: test
-      script:
-        - make test
-      python: '3.6'
-    - stage: test
-      script:
-        - make test
-      python: '3.7'
-      dist: xenial
-    - stage: test
-      script:
-        - make test
-      python: '3.8'
-      dist: xenial
-    - stage: coverage
-      python: '3.8'
-      script:
-        - make test
-        - codecov --verbose

HISTORY.md

@@ -4,6 +4,48 @@ Release History
 master
 ------
 
+0.10.1 (2021-07-11)
+------------------
+
+- Change extra requirements from `cv` to `base`. You can use `pip install "camelot-py[base]"` to install everything required to run camelot.
+
+0.10.0 (2021-07-11)
+------------------
+
+**Improvements**
+
+- Add support for multiple image conversion backends. [#198](https://github.com/camelot-dev/camelot/pull/198) and [#253](https://github.com/camelot-dev/camelot/pull/253) by Vinayak Mehta.
+- Add markdown export format. [#222](https://github.com/camelot-dev/camelot/pull/222/) by [Lucas Cimon](https://github.com/Lucas-C).
+
+**Documentation**
+
+- Add faq section. [#216](https://github.com/camelot-dev/camelot/pull/216) by [Stefano Fiorucci](https://github.com/anakin87).
+
+0.9.0 (2021-06-15)
+------------------
+
+**Bugfixes**
+
+- Fix use of resolution argument to generate image with ghostscript. [#231](https://github.com/camelot-dev/camelot/pull/231) by [Tiago Samaha Cordeiro](https://github.com/tiagosamaha).
+- [#15](https://github.com/camelot-dev/camelot/issues/15) Fix duplicate strings being assigned to the same cell. [#206](https://github.com/camelot-dev/camelot/pull/206) by [Eduardo Gonzalez Lopez de Murillas](https://github.com/edugonza).
+- Save plot when filename is specified. [#121](https://github.com/camelot-dev/camelot/pull/121) by [Jens Diemer](https://github.com/jedie).
+- Close file streams explicitly. [#202](https://github.com/camelot-dev/camelot/pull/202) by [Martin Abente Lahaye](https://github.com/tchx84).
+- Use correct re.sub signature. [#186](https://github.com/camelot-dev/camelot/pull/186) by [pevisscher](https://github.com/pevisscher).
+- [#183](https://github.com/camelot-dev/camelot/issues/183) Fix UnicodeEncodeError when using Stream flavor by adding encoding kwarg to `to_html`. [#188](https://github.com/camelot-dev/camelot/pull/188) by [Stefano Fiorucci](https://github.com/anakin87).
+- [#179](https://github.com/camelot-dev/camelot/issues/179) Fix `max() arg is an empty sequence` error on PDFs with blank pages. [#189](https://github.com/camelot-dev/camelot/pull/189) by Vinayak Mehta.
+
+**Improvements**
+
+- Add `line_overlap` and `boxes_flow` to `LAParams`. [#219](https://github.com/camelot-dev/camelot/pull/219) by [Arnie97](https://github.com/Arnie97).
+- [Add bug report template.](https://github.com/camelot-dev/camelot/commit/0a3944e54d133b701edfe9c7546ff11289301ba8)
+- Move from [Travis to GitHub Actions](https://github.com/camelot-dev/camelot/pull/241).
+- Update `.readthedocs.yml` and [remove requirements.txt](https://github.com/camelot-dev/camelot/commit/7ab5db39d07baa4063f975e9e00f6073340e04c1#diff-cde814ef2f549dc093f5b8fc533b7e8f47e7b32a8081e0760e57d5c25a1139d9)
+
+**Documentation**
+
+- [#193](https://github.com/camelot-dev/camelot/issues/193) Add better checks to confirm proper installation of ghostscript. [#196](https://github.com/camelot-dev/camelot/pull/196) by [jimhall](https://github.com/jimhall).
+- Update `advanced.rst` plotting examples. [#119](https://github.com/camelot-dev/camelot/pull/119) by [Jens Diemer](https://github.com/jedie).
+
 0.8.2 (2020-07-27)
 ------------------
 

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2019-2020 Camelot Developers
+Copyright (c) 2019-2021 Camelot Developers
 Copyright (c) 2018-2019 Peeply Private Ltd (Singapore)
 
 Permission is hereby granted, free of charge, to any person obtaining a copy

README.md

@@ -4,11 +4,10 @@
 
 # Camelot: PDF Table Extraction for Humans
 
-[![Build Status](https://travis-ci.org/camelot-dev/camelot.svg?branch=master)](https://travis-ci.org/camelot-dev/camelot) [![Documentation Status](https://readthedocs.org/projects/camelot-py/badge/?version=master)](https://camelot-py.readthedocs.io/en/master/)
+[![tests](https://github.com/camelot-dev/camelot/actions/workflows/tests.yml/badge.svg)](https://github.com/camelot-dev/camelot/actions/workflows/tests.yml) [![Documentation Status](https://readthedocs.org/projects/camelot-py/badge/?version=master)](https://camelot-py.readthedocs.io/en/master/)
  [![codecov.io](https://codecov.io/github/camelot-dev/camelot/badge.svg?branch=master&service=github)](https://codecov.io/github/camelot-dev/camelot?branch=master)
  [![image](https://img.shields.io/pypi/v/camelot-py.svg)](https://pypi.org/project/camelot-py/) [![image](https://img.shields.io/pypi/l/camelot-py.svg)](https://pypi.org/project/camelot-py/) [![image](https://img.shields.io/pypi/pyversions/camelot-py.svg)](https://pypi.org/project/camelot-py/) [![Gitter chat](https://badges.gitter.im/camelot-dev/Lobby.png)](https://gitter.im/camelot-dev/Lobby)
-[![image](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/ambv/black) [![image](https://img.shields.io/badge/continous%20quality-deepsource-lightgrey)](https://deepsource.io/gh/camelot-dev/camelot/?ref=repository-badge)
-
+[![image](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/ambv/black)
 
 **Camelot** is a Python library that can help you extract tables from PDFs!
 
@@ -23,7 +22,7 @@
 >>> tables = camelot.read_pdf('foo.pdf')
 >>> tables
 <TableList n=1>
->>> tables.export('foo.csv', f='csv', compress=True) # json, excel, html, sqlite
+>>> tables.export('foo.csv', f='csv', compress=True) # json, excel, html, markdown, sqlite
 >>> tables[0]
 <Table shape=(7, 7)>
 >>> tables[0].parsing_report
@@ -33,7 +32,7 @@
     'order': 1,
     'page': 1
 }
->>> tables[0].to_csv('foo.csv') # to_json, to_excel, to_html, to_sqlite
+>>> tables[0].to_csv('foo.csv') # to_json, to_excel, to_html, to_markdown, to_sqlite
 >>> tables[0].df # get a pandas DataFrame!
 </pre>
 
@@ -50,11 +49,13 @@ 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".)
 
+You can check out some frequently asked questions [here](https://camelot-py.readthedocs.io/en/master/user/faq.html).
+
 ## Why Camelot?
 
-- **Configurability**: Camelot gives you control over the table extraction process with its [tweakable settings](https://camelot-py.readthedocs.io/en/master/user/advanced.html).
-- **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 and Sqlite.
+- **Configurability**: Camelot gives you control over the table extraction process with [tweakable settings](https://camelot-py.readthedocs.io/en/master/user/advanced.html).
+- **Metrics**: You can discard bad tables based on metrics like accuracy and whitespace, without having to manually look at each table.
+- **Output**: Each table is extracted into a **pandas DataFrame**, which seamlessly integrates into [ETL and data analysis workflows](https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873). You can also export tables to multiple formats, which include CSV, JSON, Excel, HTML, Markdown, and Sqlite.
 
 See [comparison with similar libraries and tools](https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools).
 
@@ -77,7 +78,7 @@ $ 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:
 
 <pre>
-$ pip install "camelot-py[cv]"
+$ pip install "camelot-py[base]"
 </pre>
 
 ### From the source code
@@ -92,7 +93,7 @@ and install Camelot using pip:
 
 <pre>
 $ cd camelot
-$ pip install ".[cv]"
+$ pip install ".[base]"
 </pre>
 
 ## Documentation

camelot/__version__.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-VERSION = (0, 8, 2)
+VERSION = (0, 10, 1)
 PRERELEASE = None  # alpha, beta or rc
 REVISION = None
 

camelot/backends/__init__.py

@@ -0,0 +1,3 @@
+# -*- coding: utf-8 -*-
+
+from .image_conversion import ImageConversionBackend

camelot/backends/ghostscript_backend.py

@@ -0,0 +1,47 @@
+# -*- 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)

camelot/backends/image_conversion.py

@@ -0,0 +1,40 @@
+# -*- 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])

camelot/backends/poppler_backend.py

@@ -0,0 +1,22 @@
+# -*- 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)

camelot/cli.py

@@ -43,7 +43,7 @@ pass_config = click.make_pass_decorator(Config)
 @click.option(
     "-f",
     "--format",
-    type=click.Choice(["csv", "json", "excel", "html", "sqlite"]),
+    type=click.Choice(["csv", "excel", "html", "json", "markdown", "sqlite"]),
     help="Output file format.",
 )
 @click.option("-z", "--zip", is_flag=True, help="Create ZIP archive.")

camelot/core.py

@@ -55,7 +55,9 @@ class TextEdge(object):
         x = round(self.x, 2)
         y0 = round(self.y0, 2)
         y1 = round(self.y1, 2)
-        return f"<TextEdge x={x} y0={y0} y1={y1} align={self.align} valid={self.is_valid}>"
+        return (
+            f"<TextEdge x={x} y0={y0} y1={y1} align={self.align} valid={self.is_valid}>"
+        )
 
     def update_coords(self, x, y0, edge_tol=50):
         """Updates the text edge's x and bottom y coordinates and sets
@@ -102,8 +104,7 @@ class TextEdges(object):
         return None
 
     def add(self, textline, align):
-        """Adds a new text edge to the current dict.
-        """
+        """Adds a new text edge to the current dict."""
         x = self.get_x_coord(textline, align)
         y0 = textline.y0
         y1 = textline.y1
@@ -111,8 +112,7 @@ class TextEdges(object):
         self._textedges[align].append(te)
 
     def update(self, textline):
-        """Updates an existing text edge in the current dict.
-        """
+        """Updates an existing text edge in the current dict."""
         for align in ["left", "right", "middle"]:
             x_coord = self.get_x_coord(textline, align)
             idx = self.find(x_coord, align)
@@ -288,10 +288,10 @@ class Cell(object):
         self._text = ""
 
     def __repr__(self):
-        x1 = round(self.x1, 2)
-        y1 = round(self.y1, 2)
-        x2 = round(self.x2, 2)
-        y2 = round(self.y2, 2)
+        x1 = round(self.x1)
+        y1 = round(self.y1)
+        x2 = round(self.x2)
+        y2 = round(self.y2)
         return f"<Cell x1={x1} y1={y1} x2={x2} y2={y2}>"
 
     @property
@@ -304,8 +304,7 @@ class Cell(object):
 
     @property
     def bound(self):
-        """The number of sides on which the cell is bounded.
-        """
+        """The number of sides on which the cell is bounded."""
         return self.top + self.bottom + self.left + self.right
 
 
@@ -361,8 +360,7 @@ class Table(object):
 
     @property
     def data(self):
-        """Returns two-dimensional list of strings in table.
-        """
+        """Returns two-dimensional list of strings in table."""
         d = []
         for row in self.cells:
             d.append([cell.text.strip() for cell in row])
@@ -383,8 +381,7 @@ class Table(object):
         return report
 
     def set_all_edges(self):
-        """Sets all table edges to True.
-        """
+        """Sets all table edges to True."""
         for row in self.cells:
             for cell in row:
                 cell.left = cell.right = cell.top = cell.bottom = True
@@ -526,8 +523,7 @@ class Table(object):
         return self
 
     def set_border(self):
-        """Sets table border edges to True.
-        """
+        """Sets table border edges to True."""
         for r in range(len(self.rows)):
             self.cells[r][0].left = True
             self.cells[r][len(self.cols) - 1].right = True
@@ -634,6 +630,21 @@ class Table(object):
         with open(path, "w", encoding="utf-8") as f:
             f.write(html_string)
 
+    def to_markdown(self, path, **kwargs):
+        """Writes Table to a Markdown file.
+
+        For kwargs, check :meth:`pandas.DataFrame.to_markdown`.
+
+        Parameters
+        ----------
+        path : str
+            Output filepath.
+
+        """
+        md_string = self.df.to_markdown(**kwargs)
+        with open(path, "w", encoding="utf-8") as f:
+            f.write(md_string)
+
     def to_sqlite(self, path, **kwargs):
         """Writes Table to sqlite database.
 
@@ -715,7 +726,7 @@ class TableList(object):
         path : str
             Output filepath.
         f : str
-            File format. Can be csv, json, excel, html and sqlite.
+            File format. Can be csv, excel, html, json, markdown or sqlite.
         compress : bool
             Whether or not to add files to a ZIP archive.
 
@@ -728,7 +739,7 @@ class TableList(object):
 
         kwargs = {"path": path, "dirname": dirname, "root": root, "ext": ext}
 
-        if f in ["csv", "json", "html"]:
+        if f in ["csv", "html", "json", "markdown"]:
             self._write_file(f=f, **kwargs)
             if compress:
                 self._compress_dir(**kwargs)

camelot/ext/ghostscript/COPYING

@@ -1,674 +0,0 @@
-                    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>.

camelot/ext/ghostscript/__init__.py

@@ -1,99 +0,0 @@
-#!/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

camelot/ext/ghostscript/_gsprint.py

@@ -1,270 +0,0 @@
-#!/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

camelot/handlers.py

@@ -6,7 +6,7 @@ import sys
 from PyPDF2 import PdfFileReader, PdfFileWriter
 
 from .core import TableList
-from .parsers import Lattice, Stream, LatticeOCR, StreamOCR
+from .parsers import Stream, Lattice
 from .utils import (
     TemporaryDirectory,
     get_page_layout,
@@ -38,8 +38,8 @@ class PDFHandler(object):
         if is_url(filepath):
             filepath = download_url(filepath)
         self.filepath = filepath
-        if not filepath.lower().endswith(".pdf"):
-            raise NotImplementedError("File format not supported")
+        # if not filepath.lower().endswith(".pdf"):
+        #     raise NotImplementedError("File format not supported")
 
         if password is None:
             self.password = ""
@@ -47,9 +47,9 @@ class PDFHandler(object):
             self.password = password
             if sys.version_info[0] < 3:
                 self.password = self.password.encode("ascii")
-        self.pages = self._get_pages(self.filepath, pages)
+        self.pages = self._get_pages(pages)
 
-    def _get_pages(self, filepath, pages):
+    def _get_pages(self, pages):
         """Converts pages string to list of ints.
 
         Parameters
@@ -67,13 +67,16 @@ class PDFHandler(object):
 
         """
         page_numbers = []
+
         if pages == "1":
             page_numbers.append({"start": 1, "end": 1})
         else:
-            instream = open(filepath, "rb")
-            infile = PdfFileReader(instream, strict=False)
+            with open(self.filepath, "rb") as f:
+                infile = PdfFileReader(f, strict=False)
+
                 if infile.isEncrypted:
                     infile.decrypt(self.password)
+
                 if pages == "all":
                     page_numbers.append({"start": 1, "end": infile.getNumPages()})
                 else:
@@ -85,7 +88,7 @@ class PDFHandler(object):
                             page_numbers.append({"start": int(a), "end": int(b)})
                         else:
                             page_numbers.append({"start": int(r), "end": int(r)})
-            instream.close()
+
         P = []
         for p in page_numbers:
             P.extend(range(p["start"], p["end"] + 1))
@@ -163,19 +166,12 @@ class PDFHandler(object):
             List of tables found in PDF.
 
         """
-        parsers = {
-            "lattice": Lattice,
-            "stream": Stream,
-            "lattice_ocr": LatticeOCR,
-            "stream_ocr": StreamOCR,
-        }
-
         tables = []
         with TemporaryDirectory() as tempdir:
             for p in self.pages:
                 self._save_page(self.filepath, p, tempdir)
             pages = [os.path.join(tempdir, f"page-{p}.pdf") for p in self.pages]
-            parser = parsers[flavor](**kwargs)
+            parser = Lattice(**kwargs) if flavor == "lattice" else Stream(**kwargs)
             for p in pages:
                 t = parser.extract_tables(
                     p, suppress_stdout=suppress_stdout, layout_kwargs=layout_kwargs

camelot/io.py

@@ -98,10 +98,9 @@ def read_pdf(
     tables : camelot.core.TableList
 
     """
-    if flavor not in ["lattice", "stream", "lattice_ocr", "stream_ocr"]:
+    if flavor not in ["lattice", "stream"]:
         raise NotImplementedError(
-            "Unknown flavor specified. Use one of the following: "
-            "'lattice', 'stream', 'lattice_ocr', 'stream_ocr'"
+            "Unknown flavor specified." " Use either 'lattice' or 'stream'"
         )
 
     with warnings.catch_warnings():

camelot/parsers/__init__.py

@@ -1,6 +1,4 @@
 # -*- coding: utf-8 -*-
 
-from .lattice import Lattice
 from .stream import Stream
-from .lattice_ocr import LatticeOCR
-from .stream_ocr import StreamOCR
+from .lattice import Lattice

camelot/parsers/base.py

@@ -6,8 +6,7 @@ from ..utils import get_page_layout, get_text_objects
 
 
 class BaseParser(object):
-    """Defines a base parser.
-    """
+    """Defines a base parser."""
 
     def _generate_layout(self, filename, layout_kwargs):
         self.filename = filename
@@ -18,3 +17,4 @@ class BaseParser(object):
         self.vertical_text = get_text_objects(self.layout, ltype="vertical_text")
         self.pdf_width, self.pdf_height = self.dimensions
         self.rootname, __ = os.path.splitext(self.filename)
+        self.imagename = "".join([self.rootname, ".png"])

camelot/parsers/lattice.py

@@ -6,7 +6,6 @@ import copy
 import locale
 import logging
 import warnings
-import subprocess
 
 import numpy as np
 import pandas as pd
@@ -29,6 +28,7 @@ from ..image_processing import (
     find_contours,
     find_joints,
 )
+from ..backends.image_conversion import BACKENDS
 
 
 logger = logging.getLogger("camelot")
@@ -111,7 +111,8 @@ class Lattice(BaseParser):
         threshold_constant=-2,
         iterations=0,
         resolution=300,
-        **kwargs
+        backend="ghostscript",
+        **kwargs,
     ):
         self.table_regions = table_regions
         self.table_areas = table_areas
@@ -128,6 +129,37 @@ class Lattice(BaseParser):
         self.threshold_constant = threshold_constant
         self.iterations = iterations
         self.resolution = resolution
+        self.backend = Lattice._get_backend(backend)
+
+    @staticmethod
+    def _get_backend(backend):
+        def implements_convert():
+            methods = [
+                method for method in dir(backend) if method.startswith("__") is False
+            ]
+            return "convert" in methods
+
+        if isinstance(backend, str):
+            if backend not in BACKENDS.keys():
+                raise NotImplementedError(
+                    f"Unknown backend '{backend}' specified. Please use either 'poppler' or 'ghostscript'."
+                )
+
+            if backend == "ghostscript":
+                warnings.warn(
+                    "'ghostscript' will be replaced by 'poppler' as the default image conversion"
+                    " backend in v0.12.0. You can try out 'poppler' with backend='poppler'.",
+                    DeprecationWarning,
+                )
+
+            return BACKENDS[backend]()
+        else:
+            if not implements_convert():
+                raise NotImplementedError(
+                    f"'{backend}' must implement a 'convert' method"
+                )
+
+            return backend
 
     @staticmethod
     def _reduce_index(t, idx, shift_text):
@@ -207,19 +239,6 @@ class Lattice(BaseParser):
                                 t.cells[i][j].text = t.cells[i - 1][j].text
         return t
 
-    def _generate_image(self):
-        from ..ext.ghostscript import Ghostscript
-
-        self.imagename = "".join([self.rootname, ".png"])
-        gs_call = "-q -sDEVICE=png16m -o {} -r300 {}".format(
-            self.imagename, 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 scale_areas(areas):
             scaled_areas = []
@@ -399,7 +418,8 @@ class Lattice(BaseParser):
                 )
             return []
 
-        self._generate_image()
+        self.backend.convert(self.filename, self.imagename)
+
         self._generate_table_bbox()
 
         _tables = []

camelot/parsers/lattice_ocr.py

@@ -1,243 +0,0 @@
-# -*- coding: utf-8 -*-
-
-import os
-import copy
-import logging
-import subprocess
-
-try:
-    import easyocr
-except ImportError:
-    _HAS_EASYOCR = False
-else:
-    _HAS_EASYOCR = True
-
-import pandas as pd
-from PIL import Image
-
-from .base import BaseParser
-from ..core import Table
-from ..utils import TemporaryDirectory, merge_close_lines, scale_pdf, segments_in_bbox
-from ..image_processing import (
-    adaptive_threshold,
-    find_lines,
-    find_contours,
-    find_joints,
-)
-
-
-logger = logging.getLogger("camelot")
-
-
-class LatticeOCR(BaseParser):
-    def __init__(
-        self,
-        table_regions=None,
-        table_areas=None,
-        line_scale=15,
-        line_tol=2,
-        joint_tol=2,
-        threshold_blocksize=15,
-        threshold_constant=-2,
-        iterations=0,
-        resolution=300,
-    ):
-        self.table_regions = table_regions
-        self.table_areas = table_areas
-        self.line_scale = line_scale
-        self.line_tol = line_tol
-        self.joint_tol = joint_tol
-        self.threshold_blocksize = threshold_blocksize
-        self.threshold_constant = threshold_constant
-        self.iterations = iterations
-        self.resolution = resolution
-
-        if _HAS_EASYOCR:
-            self.reader = easyocr.Reader(['en'], gpu=False)
-        else:
-            raise ImportError("easyocr is required to run OCR on image-based PDFs.")
-
-    def _generate_image(self):
-        from ..ext.ghostscript import Ghostscript
-
-        self.imagename = "".join([self.rootname, ".png"])
-        gs_call = "-q -sDEVICE=png16m -o {} -r900 {}".format(
-            self.imagename, 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 scale_areas(areas, scalers):
-            scaled_areas = []
-            for area in areas:
-                x1, y1, x2, y2 = area.split(",")
-                x1 = float(x1)
-                y1 = float(y1)
-                x2 = float(x2)
-                y2 = float(y2)
-                x1, y1, x2, y2 = scale_pdf((x1, y1, x2, y2), scalers)
-                scaled_areas.append((x1, y1, abs(x2 - x1), abs(y2 - y1)))
-            return scaled_areas
-
-        self.image, self.threshold = adaptive_threshold(
-            self.imagename, blocksize=self.threshold_blocksize, c=self.threshold_constant
-        )
-
-        image_width = self.image.shape[1]
-        image_height = self.image.shape[0]
-        image_width_scaler = image_width / float(self.pdf_width)
-        image_height_scaler = image_height / float(self.pdf_height)
-        image_scalers = (image_width_scaler, image_height_scaler, self.pdf_height)
-
-        if self.table_areas is None:
-            regions = None
-            if self.table_regions is not None:
-                regions = scale_areas(self.table_regions, image_scalers)
-
-            vertical_mask, vertical_segments = find_lines(
-                self.threshold,
-                regions=regions,
-                direction="vertical",
-                line_scale=self.line_scale,
-                iterations=self.iterations,
-            )
-            horizontal_mask, horizontal_segments = find_lines(
-                self.threshold,
-                regions=regions,
-                direction="horizontal",
-                line_scale=self.line_scale,
-                iterations=self.iterations,
-            )
-
-            contours = find_contours(vertical_mask, horizontal_mask)
-            table_bbox = find_joints(contours, vertical_mask, horizontal_mask)
-        else:
-            vertical_mask, vertical_segments = find_lines(
-                self.threshold,
-                direction="vertical",
-                line_scale=self.line_scale,
-                iterations=self.iterations,
-            )
-            horizontal_mask, horizontal_segments = find_lines(
-                self.threshold,
-                direction="horizontal",
-                line_scale=self.line_scale,
-                iterations=self.iterations,
-            )
-
-            areas = scale_areas(self.table_areas, image_scalers)
-            table_bbox = find_joints(areas, vertical_mask, horizontal_mask)
-
-        self.table_bbox_unscaled = copy.deepcopy(table_bbox)
-
-        self.table_bbox = table_bbox
-        self.vertical_segments = vertical_segments
-        self.horizontal_segments = horizontal_segments
-
-    def _generate_columns_and_rows(self, table_idx, tk):
-        cols, rows = zip(*self.table_bbox[tk])
-        cols, rows = list(cols), list(rows)
-        cols.extend([tk[0], tk[2]])
-        rows.extend([tk[1], tk[3]])
-        # sort horizontal and vertical segments
-        cols = merge_close_lines(sorted(cols), line_tol=self.line_tol)
-        rows = merge_close_lines(sorted(rows), line_tol=self.line_tol)
-        # make grid using x and y coord of shortlisted rows and cols
-        cols = [(cols[i], cols[i + 1]) for i in range(0, len(cols) - 1)]
-        rows = [(rows[i], rows[i + 1]) for i in range(0, len(rows) - 1)]
-
-        return cols, rows
-
-
-    def _generate_table(self, table_idx, cols, rows, **kwargs):
-        table = Table(cols, rows)
-        # set table edges to True using ver+hor lines
-        table = table.set_edges(self.vertical_segments, self.horizontal_segments, joint_tol=self.joint_tol)
-        # set table border edges to True
-        table = table.set_border()
-        # set spanning cells to True
-        table = table.set_span()
-
-        _seen = set()
-        for r_idx in range(len(table.cells)):
-            for c_idx in range(len(table.cells[r_idx])):
-                if (r_idx, c_idx) in _seen:
-                    continue
-
-                _seen.add((r_idx, c_idx))
-
-                _r_idx = r_idx
-                _c_idx = c_idx
-
-                if table.cells[r_idx][_c_idx].hspan:
-                    while not table.cells[r_idx][_c_idx].right:
-                        _c_idx += 1
-                        _seen.add((r_idx, _c_idx))
-
-                if table.cells[_r_idx][c_idx].vspan:
-                    while not table.cells[_r_idx][c_idx].bottom:
-                        _r_idx += 1
-                        _seen.add((_r_idx, c_idx))
-
-                for i in range(r_idx, _r_idx + 1):
-                    for j in range(c_idx, _c_idx + 1):
-                        _seen.add((i, j))
-
-                x1 = int(table.cells[r_idx][c_idx].x1)
-                y1 = int(table.cells[_r_idx][_c_idx].y1)
-
-                x2 = int(table.cells[_r_idx][_c_idx].x2)
-                y2 = int(table.cells[r_idx][c_idx].y2)
-
-                with TemporaryDirectory() as tempdir:
-                    temp_image_path = os.path.join(tempdir, f"{table_idx}_{r_idx}_{c_idx}.png")
-
-                    cell_image = Image.fromarray(self.image[y2:y1, x1:x2])
-                    cell_image.save(temp_image_path)
-
-                    text = self.reader.readtext(temp_image_path, detail=0)
-                    text = " ".join(text)
-
-                table.cells[r_idx][c_idx].text = text
-
-        data = table.data
-        table.df = pd.DataFrame(data)
-        table.shape = table.df.shape
-
-        table.flavor = "lattice_ocr"
-        table.accuracy = 0
-        table.whitespace = 0
-        table.order = table_idx + 1
-        table.page = int(os.path.basename(self.rootname).replace("page-", ""))
-
-        # for plotting
-        table._text = None
-        table._image = (self.image, self.table_bbox_unscaled)
-        table._segments = (self.vertical_segments, self.horizontal_segments)
-        table._textedges = None
-
-        return table
-
-    def extract_tables(self, filename, suppress_stdout=False, layout_kwargs={}):
-        self._generate_layout(filename, layout_kwargs)
-        if not suppress_stdout:
-            logger.info("Processing {}".format(os.path.basename(self.rootname)))
-
-        self._generate_image()
-        self._generate_table_bbox()
-
-        _tables = []
-        # sort tables based on y-coord
-        for table_idx, tk in enumerate(
-            sorted(self.table_bbox.keys(), key=lambda x: x[1], reverse=True)
-        ):
-            cols, rows = self._generate_columns_and_rows(table_idx, tk)
-            table = self._generate_table(table_idx, cols, rows)
-            table._bbox = tk
-            _tables.append(table)
-
-        return _tables

camelot/parsers/stream.py

@@ -65,7 +65,7 @@ class Stream(BaseParser):
         edge_tol=50,
         row_tol=2,
         column_tol=0,
-        **kwargs
+        **kwargs,
     ):
         self.table_regions = table_regions
         self.table_areas = table_areas
@@ -362,10 +362,10 @@ class Stream(BaseParser):
                     if len(elements):
                         ncols = max(set(elements), key=elements.count)
                     else:
-                        warnings.warn(
-                            f"No tables found in table area {table_idx + 1}"
-                        )
-                cols = [(t.x0, t.x1) for r in rows_grouped if len(r) == ncols for t in r]
+                        warnings.warn(f"No tables found in table area {table_idx + 1}")
+                cols = [
+                    (t.x0, t.x1) for r in rows_grouped if len(r) == ncols for t in r
+                ]
                 cols = self._merge_columns(sorted(cols), column_tol=self.column_tol)
                 inner_text = []
                 for i in range(1, len(cols)):

camelot/parsers/stream_ocr.py

@@ -1,7 +0,0 @@
-# -*- coding: utf-8 -*-
-
-from .base import BaseParser
-
-
-class StreamOCR(BaseParser):
-    pass

camelot/plotting.py

@@ -34,13 +34,9 @@ class PlotMethods(object):
             raise ImportError("matplotlib is required for plotting.")
 
         if table.flavor == "lattice" and kind in ["textedge"]:
-            raise NotImplementedError(
-                f"Lattice flavor does not support kind='{kind}'"
-            )
+            raise NotImplementedError(f"Lattice flavor does not support kind='{kind}'")
         elif table.flavor == "stream" and kind in ["joint", "line"]:
-            raise NotImplementedError(
-                f"Stream flavor does not support kind='{kind}'"
-            )
+            raise NotImplementedError(f"Stream flavor does not support kind='{kind}'")
 
         plot_method = getattr(self, kind)
         fig = plot_method(table)

camelot/utils.py

@@ -93,6 +93,7 @@ def download_url(url):
     return filepath
 
 
+stream_kwargs = ["columns", "edge_tol", "row_tol", "column_tol"]
 lattice_kwargs = [
     "process_background",
     "line_scale",
@@ -105,7 +106,6 @@ lattice_kwargs = [
     "iterations",
     "resolution",
 ]
-stream_kwargs = ["columns", "edge_tol", "row_tol", "column_tol"]
 
 
 def validate_input(kwargs, flavor="lattice"):
@@ -116,14 +116,14 @@ def validate_input(kwargs, flavor="lattice"):
                 f"{','.join(sorted(isec))} cannot be used with flavor='{flavor}'"
             )
 
-    if flavor in ["lattice", "lattice_ocr"]:
+    if flavor == "lattice":
         check_intersection(stream_kwargs, kwargs)
     else:
         check_intersection(lattice_kwargs, kwargs)
 
 
 def remove_extra(kwargs, flavor="lattice"):
-    if flavor in ["lattice", "lattice_ocr"]:
+    if flavor == "lattice":
         for key in kwargs.keys():
             if key in stream_kwargs:
                 kwargs.pop(key)
@@ -838,23 +838,27 @@ def compute_whitespace(d):
 
 def get_page_layout(
     filename,
+    line_overlap=0.5,
     char_margin=1.0,
     line_margin=0.5,
     word_margin=0.1,
+    boxes_flow=0.5,
     detect_vertical=True,
     all_texts=True,
 ):
     """Returns a PDFMiner LTPage object and page dimension of a single
-    page pdf. See https://euske.github.io/pdfminer/ to get definitions
-    of kwargs.
+    page pdf. To get the definitions of kwargs, see
+    https://pdfminersix.rtfd.io/en/latest/reference/composable.html.
 
     Parameters
     ----------
     filename : string
         Path to pdf file.
+    line_overlap : float
     char_margin : float
     line_margin : float
     word_margin : float
+    boxes_flow : float
     detect_vertical : bool
     all_texts : bool
 
@@ -870,11 +874,15 @@ def get_page_layout(
         parser = PDFParser(f)
         document = PDFDocument(parser)
         if not document.is_extractable:
-            raise PDFTextExtractionNotAllowed(f"Text extraction is not allowed: {filename}")
+            raise PDFTextExtractionNotAllowed(
+                f"Text extraction is not allowed: {filename}"
+            )
         laparams = LAParams(
+            line_overlap=line_overlap,
             char_margin=char_margin,
             line_margin=line_margin,
             word_margin=word_margin,
+            boxes_flow=boxes_flow,
             detect_vertical=detect_vertical,
             all_texts=all_texts,
         )

docs/_themes/flask_theme_support.py

@@ -1,7 +1,19 @@
 # flasky pygments style based on tango style
 from pygments.style import Style
-from pygments.token import Keyword, Name, Comment, String, Error, \
-     Number, Operator, Generic, Whitespace, Punctuation, Other, Literal
+from pygments.token import (
+    Keyword,
+    Name,
+    Comment,
+    String,
+    Error,
+    Number,
+    Operator,
+    Generic,
+    Whitespace,
+    Punctuation,
+    Other,
+    Literal,
+)
 
 
 class FlaskyStyle(Style):
@@ -14,10 +26,8 @@ class FlaskyStyle(Style):
         Whitespace: "underline #f8f8f8",  # class: 'w'
         Error: "#a40000 border:#ef2929",  # class: 'err'
         Other: "#000000",  # class 'x'
-
         Comment: "italic #8f5902",  # class: 'c'
         Comment.Preproc: "noitalic",  # class: 'cp'
-
         Keyword: "bold #004461",  # class: 'k'
         Keyword.Constant: "bold #004461",  # class: 'kc'
         Keyword.Declaration: "bold #004461",  # class: 'kd'
@@ -25,12 +35,9 @@ class FlaskyStyle(Style):
         Keyword.Pseudo: "bold #004461",  # class: 'kp'
         Keyword.Reserved: "bold #004461",  # class: 'kr'
         Keyword.Type: "bold #004461",  # class: 'kt'
-
         Operator: "#582800",  # class: 'o'
         Operator.Word: "bold #004461",  # class: 'ow' - like keywords
-
         Punctuation: "bold #000000",  # class: 'p'
-
         # because special names such as Name.Class, Name.Function, etc.
         # are not recognized as such later in the parsing, we choose them
         # to look the same as ordinary variables.
@@ -53,12 +60,9 @@ class FlaskyStyle(Style):
         Name.Variable.Class: "#000000",  # class: 'vc' - to be revised
         Name.Variable.Global: "#000000",  # class: 'vg' - to be revised
         Name.Variable.Instance: "#000000",  # class: 'vi' - to be revised
-
         Number: "#990000",  # class: 'm'
-
         Literal: "#000000",  # class: 'l'
         Literal.Date: "#000000",  # class: 'ld'
-
         String: "#4e9a06",  # class: 's'
         String.Backtick: "#4e9a06",  # class: 'sb'
         String.Char: "#4e9a06",  # class: 'sc'
@@ -71,7 +75,6 @@ class FlaskyStyle(Style):
         String.Regex: "#4e9a06",  # class: 'sr'
         String.Single: "#4e9a06",  # class: 's1'
         String.Symbol: "#4e9a06",  # class: 'ss'
-
         Generic: "#000000",  # class: 'g'
         Generic.Deleted: "#a40000",  # class: 'gd'
         Generic.Emph: "italic #000000",  # class: 'ge'

docs/conf.py

@@ -22,8 +22,8 @@ import sys
 # sys.path.insert(0, os.path.abspath('..'))
 
 # Insert Camelot's path into the system.
-sys.path.insert(0, os.path.abspath('..'))
-sys.path.insert(0, os.path.abspath('_themes'))
+sys.path.insert(0, os.path.abspath(".."))
+sys.path.insert(0, os.path.abspath("_themes"))
 
 import camelot
 
@@ -38,33 +38,33 @@ import camelot
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
-    'sphinx.ext.autodoc',
-    'sphinx.ext.napoleon',
-    'sphinx.ext.intersphinx',
-    'sphinx.ext.todo',
-    'sphinx.ext.viewcode',
+    "sphinx.ext.autodoc",
+    "sphinx.ext.napoleon",
+    "sphinx.ext.intersphinx",
+    "sphinx.ext.todo",
+    "sphinx.ext.viewcode",
 ]
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # The suffix(es) of source filenames.
 # You can specify multiple suffix as a list of string:
 #
 # source_suffix = ['.rst', '.md']
-source_suffix = '.rst'
+source_suffix = ".rst"
 
 # The encoding of source files.
 #
 # source_encoding = 'utf-8-sig'
 
 # The master toctree document.
-master_doc = 'index'
+master_doc = "index"
 
 # General information about the project.
-project = u'Camelot'
-copyright = u'2020, Camelot Developers'
-author = u'Vinayak Mehta'
+project = u"Camelot"
+copyright = u"2021, Camelot Developers"
+author = u"Vinayak Mehta"
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
@@ -94,7 +94,7 @@ language = None
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This patterns also effect to html_static_path and html_extra_path
-exclude_patterns = ['_build']
+exclude_patterns = ["_build"]
 
 # The reST default role (used for this markup: `text`) to use for all
 # documents.
@@ -114,7 +114,7 @@ add_module_names = True
 # show_authors = False
 
 # The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'flask_theme_support.FlaskyStyle'
+pygments_style = "flask_theme_support.FlaskyStyle"
 
 # A list of ignored prefixes for module index sorting.
 # modindex_common_prefix = []
@@ -130,18 +130,18 @@ todo_include_todos = True
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
-html_theme = 'alabaster'
+html_theme = "alabaster"
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
 # documentation.
 html_theme_options = {
-    'show_powered_by': False,
-    'github_user': 'camelot-dev',
-    'github_repo': 'camelot',
-    'github_banner': True,
-    'show_related': False,
-    'note_bg': '#FFF59C'
+    "show_powered_by": False,
+    "github_user": "camelot-dev",
+    "github_repo": "camelot",
+    "github_banner": True,
+    "show_related": False,
+    "note_bg": "#FFF59C",
 }
 
 # Add any paths that contain custom themes here, relative to this directory.
@@ -164,12 +164,12 @@ html_theme_options = {
 # The name of an image file (relative to this directory) to use as a favicon of
 # the docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
 # pixels large.
-html_favicon = '_static/favicon.ico'
+html_favicon = "_static/favicon.ico"
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]
 
 # Add any extra paths that contain custom files (such as robots.txt or
 # .htaccess) here, relative to this directory. These files are copied
@@ -189,10 +189,21 @@ html_use_smartypants = True
 
 # Custom sidebar templates, maps document names to template names.
 html_sidebars = {
-    'index': ['sidebarintro.html', 'relations.html', 'sourcelink.html',
-              'searchbox.html', 'hacks.html'],
-    '**': ['sidebarlogo.html', 'localtoc.html', 'relations.html',
-           'sourcelink.html', 'searchbox.html', 'hacks.html']
+    "index": [
+        "sidebarintro.html",
+        "relations.html",
+        "sourcelink.html",
+        "searchbox.html",
+        "hacks.html",
+    ],
+    "**": [
+        "sidebarlogo.html",
+        "localtoc.html",
+        "relations.html",
+        "sourcelink.html",
+        "searchbox.html",
+        "hacks.html",
+    ],
 }
 
 # Additional templates that should be rendered to pages, maps page names to
@@ -249,7 +260,7 @@ html_show_copyright = True
 # html_search_scorer = 'scorer.js'
 
 # Output file base name for HTML help builder.
-htmlhelp_basename = 'Camelotdoc'
+htmlhelp_basename = "Camelotdoc"
 
 # -- Options for LaTeX output ---------------------------------------------
 
@@ -257,15 +268,12 @@ latex_elements = {
     # The paper size ('letterpaper' or 'a4paper').
     #
     # 'papersize': 'letterpaper',
-
     # The font size ('10pt', '11pt' or '12pt').
     #
     # 'pointsize': '10pt',
-
     # Additional stuff for the LaTeX preamble.
     #
     # 'preamble': '',
-
     # Latex figure (float) alignment
     #
     # 'figure_align': 'htbp',
@@ -275,8 +283,7 @@ latex_elements = {
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, 'Camelot.tex', u'Camelot Documentation',
-     u'Vinayak Mehta', 'manual'),
+    (master_doc, "Camelot.tex", u"Camelot Documentation", u"Vinayak Mehta", "manual"),
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
@@ -316,10 +323,7 @@ latex_documents = [
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [
-    (master_doc, 'Camelot', u'Camelot Documentation',
-     [author], 1)
-]
+man_pages = [(master_doc, "Camelot", u"Camelot Documentation", [author], 1)]
 
 # If true, show URL addresses after external links.
 #
@@ -332,9 +336,15 @@ man_pages = [
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-    (master_doc, 'Camelot', u'Camelot Documentation',
-     author, 'Camelot', 'One line description of project.',
-     'Miscellaneous'),
+    (
+        master_doc,
+        "Camelot",
+        u"Camelot Documentation",
+        author,
+        "Camelot",
+        "One line description of project.",
+        "Miscellaneous",
+    ),
 ]
 
 # Documents to append as an appendix to all manuals.
@@ -356,6 +366,6 @@ texinfo_documents = [
 
 # Example configuration for intersphinx: refer to the Python standard library.
 intersphinx_mapping = {
-    'https://docs.python.org/2': None,
-    'http://pandas.pydata.org/pandas-docs/stable': None
+    "https://docs.python.org/2": None,
+    "http://pandas.pydata.org/pandas-docs/stable": None,
 }

docs/index.rst

@@ -54,7 +54,7 @@ Release v\ |version|. (:ref:`Installation <install>`)
     >>> tables = camelot.read_pdf('foo.pdf')
     >>> tables
     <TableList n=1>
-    >>> tables.export('foo.csv', f='csv', compress=True) # json, excel, html
+    >>> tables.export('foo.csv', f='csv', compress=True) # json, excel, html, markdown, sqlite
     >>> tables[0]
     <Table shape=(7, 7)>
     >>> tables[0].parsing_report
@@ -64,7 +64,7 @@ Release v\ |version|. (:ref:`Installation <install>`)
         'order': 1,
         'page': 1
     }
-    >>> tables[0].to_csv('foo.csv') # to_json, to_excel, to_html
+    >>> tables[0].to_csv('foo.csv') # to_json, to_excel, to_html, to_markdown, to_sqlite
     >>> tables[0].df # get a pandas DataFrame!
 
 .. csv-table::
@@ -74,14 +74,16 @@ 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".)
 
+You can check out some frequently asked questions :ref:`here <faq>`.
+
 .. _explains: https://github.com/tabulapdf/tabula#why-tabula
 
 Why Camelot?
 ------------
 
-- **Configurability**: Camelot gives you control over the table extraction process with its :ref:`tweakable settings <advanced>`.
-- **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 and Sqlite.
+- **Configurability**: Camelot gives you control over the table extraction process with :ref:`tweakable settings <advanced>`.
+- **Metrics**: You can discard bad tables based on metrics like accuracy and whitespace, without having to manually look at each table.
+- **Output**: Each table is extracted into a **pandas DataFrame**, which seamlessly integrates into `ETL and data analysis workflows`_. You can also export tables to multiple formats, which include CSV, JSON, Excel, HTML, Markdown, and Sqlite.
 
 .. _ETL and data analysis workflows: https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873
 
@@ -110,6 +112,7 @@ This part of the documentation begins with some background information about why
    user/how-it-works
    user/quickstart
    user/advanced
+   user/faq
    user/cli
 
 The API Documentation/Guide

docs/user/advanced.rst

@@ -618,8 +618,31 @@ Tweak layout generation
 
 Camelot is built on top of PDFMiner's functionality of grouping characters on a page into words and sentences. In some cases (such as `#170 <https://github.com/camelot-dev/camelot/issues/170>`_ and `#215 <https://github.com/camelot-dev/camelot/issues/215>`_), PDFMiner can group characters that should belong to the same sentence into separate sentences.
 
-To deal with such cases, you can tweak PDFMiner's `LAParams kwargs <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ to improve layout generation, by passing the keyword arguments as a dict using ``layout_kwargs`` in :meth:`read_pdf() <camelot.read_pdf>`. To know more about the parameters you can tweak, you can check out `PDFMiner docs <https://euske.github.io/pdfminer/>`_.
+To deal with such cases, you can tweak PDFMiner's `LAParams kwargs <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ to improve layout generation, by passing the keyword arguments as a dict using ``layout_kwargs`` in :meth:`read_pdf() <camelot.read_pdf>`. To know more about the parameters you can tweak, you can check out `PDFMiner docs <https://pdfminersix.rtfd.io/en/latest/reference/composable.html>`_.
 
 ::
 
     >>> tables = camelot.read_pdf('foo.pdf', layout_kwargs={'detect_vertical': False})
+
+.. _image-conversion-backend:
+
+Use alternate image conversion backends
+---------------------------------------
+
+When using the :ref:`Lattice <lattice>` flavor, Camelot uses ``ghostscript`` to convert PDF pages to images for line recognition. If you face installation issues with ``ghostscript``, you can use an alternate image conversion backend called ``poppler``. You can specify which image conversion backend you want to use with::
+
+    >>> tables = camelot.read_pdf(filename, backend="ghostscript")  # default
+    >>> tables = camelot.read_pdf(filename, backend="poppler")
+
+.. note:: ``ghostscript`` will be replaced by ``poppler`` as the default image conversion backend in ``v0.12.0``.
+
+If you face issues with both ``ghostscript`` and ``poppler``, you can supply your own image conversion backend::
+
+    >>> class ConversionBackend(object):
+    >>>     def convert(pdf_path, png_path):
+    >>>         # read pdf page from pdf_path
+    >>>         # convert pdf page to image
+    >>>         # write image to png_path
+    >>>         pass
+    >>>
+    >>> tables = camelot.read_pdf(filename, backend=ConversionBackend())

docs/user/faq.rst

@@ -0,0 +1,70 @@
+.. _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())

docs/user/install-deps.rst

@@ -43,8 +43,9 @@ For Ubuntu/MacOS::
 
 For Windows::
 
+    >>> import ctypes
     >>> 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>
 
 **Check:** The output of the ``find_library`` function should not be empty.

docs/user/install.rst

@@ -14,7 +14,7 @@ pip
 
 To install Camelot from PyPI using ``pip``, please include the extra ``cv`` requirement as shown::
 
-    $ pip install "camelot-py[cv]"
+    $ pip install "camelot-py[base]"
 
 conda
 -----
@@ -37,4 +37,4 @@ After :ref:`installing the dependencies <install_deps>`, you can install Camelot
 ::
 
     $ cd camelot
-    $ pip install ".[cv]"
+    $ pip install ".[base]"

docs/user/quickstart.rst

@@ -56,7 +56,7 @@ Woah! The accuracy is top-notch and there is less whitespace, which means the ta
 .. csv-table::
   :file: ../_static/csv/foo.csv
 
-Looks good! You can now export the table as a CSV file using its :meth:`to_csv() <camelot.core.Table.to_csv>` method. Alternatively you can use :meth:`to_json() <camelot.core.Table.to_json>`, :meth:`to_excel() <camelot.core.Table.to_excel>` :meth:`to_html() <camelot.core.Table.to_html>` 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>` :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.
 
 ::
 
@@ -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
 
-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'``.
+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'``.
 
 .. 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.
 

setup.py

@@ -6,80 +6,78 @@ from setuptools import find_packages
 
 here = os.path.abspath(os.path.dirname(__file__))
 about = {}
-with open(os.path.join(here, 'camelot', '__version__.py'), 'r') as f:
+with open(os.path.join(here, "camelot", "__version__.py"), "r") as f:
     exec(f.read(), about)
 
-with open('README.md', 'r') as f:
+with open("README.md", "r") as f:
     readme = f.read()
 
 
 requires = [
-    'chardet>=3.0.4',
-    'click>=6.7',
-    'numpy>=1.13.3',
-    'openpyxl>=2.5.8',
-    'pandas>=0.23.4',
-    'pdfminer.six>=20200726',
-    'PyPDF2>=1.26.0'
+    "chardet>=3.0.4",
+    "click>=6.7",
+    "numpy>=1.13.3",
+    "openpyxl>=2.5.8",
+    "pandas>=0.23.4",
+    "pdfminer.six>=20200726",
+    "PyPDF2>=1.26.0",
+    "tabulate>=0.8.9",
 ]
 
-cv_requires = [
-    'opencv-python>=3.4.2.17'
-]
-
-ocr_requires = [
-    'easyocr>=1.1.10'
-]
+base_requires = ["ghostscript>=0.7", "opencv-python>=3.4.2.17", "pdftopng>=0.2.3"]
 
 plot_requires = [
-    'matplotlib>=2.2.3',
+    "matplotlib>=2.2.3",
 ]
 
 dev_requires = [
-    'codecov>=2.0.15',
-    'pytest>=5.4.3',
-    'pytest-cov>=2.10.0',
-    'pytest-mpl>=0.11',
-    'pytest-runner>=5.2',
-    'Sphinx>=3.1.2'
+    "codecov>=2.0.15",
+    "pytest>=5.4.3",
+    "pytest-cov>=2.10.0",
+    "pytest-mpl>=0.11",
+    "pytest-runner>=5.2",
+    "Sphinx>=3.1.2",
+    "sphinx-autobuild>=2021.3.14",
 ]
 
-all_requires = cv_requires + ocr_requires + plot_requires
+all_requires = base_requires + plot_requires
 dev_requires = dev_requires + all_requires
 
 
 def setup_package():
-    metadata = dict(name=about['__title__'],
-                    version=about['__version__'],
-                    description=about['__description__'],
+    metadata = dict(
+        name=about["__title__"],
+        version=about["__version__"],
+        description=about["__description__"],
         long_description=readme,
         long_description_content_type="text/markdown",
-                    url=about['__url__'],
-                    author=about['__author__'],
-                    author_email=about['__author_email__'],
-                    license=about['__license__'],
-                    packages=find_packages(exclude=('tests',)),
+        url=about["__url__"],
+        author=about["__author__"],
+        author_email=about["__author_email__"],
+        license=about["__license__"],
+        packages=find_packages(exclude=("tests",)),
         install_requires=requires,
         extras_require={
-                        'cv': cv_requires,
-                        'ocr': ocr_requires,
-                        'plot': plot_requires,
-                        'all': all_requires,
-                        'dev': dev_requires,
+            "all": all_requires,
+            "base": base_requires,
+            "cv": base_requires,  # deprecate
+            "dev": dev_requires,
+            "plot": plot_requires,
         },
         entry_points={
-                        'console_scripts': [
-                            'camelot = camelot.cli:cli',
+            "console_scripts": [
+                "camelot = camelot.cli:cli",
             ],
         },
         classifiers=[
             # Trove classifiers
             # Full list: https://pypi.python.org/pypi?%3Aaction=list_classifiers
-                        'License :: OSI Approved :: MIT License',
-                        'Programming Language :: Python :: 3.6',
-                        'Programming Language :: Python :: 3.7',
-                        'Programming Language :: Python :: 3.8'
-                    ])
+            "License :: OSI Approved :: MIT License",
+            "Programming Language :: Python :: 3.6",
+            "Programming Language :: Python :: 3.7",
+            "Programming Language :: Python :: 3.8",
+        ],
+    )
 
     try:
         from setuptools import setup
@@ -89,5 +87,5 @@ def setup_package():
     setup(**metadata)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     setup_package()

tests/data.py

@@ -2800,49 +2800,467 @@ data_stream_layout_kwargs = [
 ]
 
 data_stream_duplicated_text = [
-    ['', '2012 BETTER VARIETIES Harvest Report for Minnesota Central  [ MNCE ]', '', '', '', '', '', '', '', '',
-     'ALL SEASON TEST'],
-    ['', 'Doug Toreen, Renville County, MN 55310          [ BIRD ISLAND ]', '', '', '', '', '', '', '', '',
-     '1.3 - 2.0 MAT. GROUP'],
-    ['PREV. CROP/HERB:', 'Corn / Surpass, Roundup', '', '', '', '', '', '', '', '', 'S2MNCE01'],
-    ['SOIL DESCRIPTION:', '', 'Canisteo clay loam, mod. well drained, non-irrigated', '', '', '', '', '', '', '', ''],
-    ['SOIL CONDITIONS:', '', 'High P, high K, 6.7 pH, 3.9% OM, Low SCN', '', '', '', '', '', '', '', '30" ROW SPACING'],
-    ['TILLAGE/CULTIVATION:', 'conventional w/ fall till', '', '', '', '', '', '', '', '', ''],
-    ['PEST MANAGEMENT:', 'Roundup twice', '', '', '', '', '', '', '', '', ''],
-    ['SEEDED - RATE:', 'May 15', '140 000 /A', '', '', '', '', '', '', 'TOP 30 for YIELD of 63 TESTED', ''],
-    ['HARVESTED - STAND:', 'Oct 3', '122 921 /A', '', '', '', '', '', '', 'AVERAGE of (3) REPLICATIONS', ''],
-    ['', '', '', '', 'SCN', 'Seed', 'Yield', 'Moisture', 'Lodging', 'Stand', 'Gross'],
-    ['Company/Brand', 'Product/Brand†', 'Technol.†', 'Mat.', 'Resist.', 'Trmt.†', 'Bu/A', '%', '%', '(x 1000)',
-     'Income'], ['Kruger', 'K2 1901', 'RR2Y', '1.9', 'R', 'Ac,PV', '56.4', '7.6', '0', '126.3', '$846'],
-    ['Stine', '19RA02 §', 'RR2Y', '1.9', 'R', 'CMB', '55.3', '7.6', '0', '120.0', '$830'],
-    ['Wensman', 'W 3190NR2', 'RR2Y', '1.9', 'R', 'Ac', '54.5', '7.6', '0', '119.5', '$818'],
-    ['Hefty', 'H17Y12', 'RR2Y', '1.7', 'MR', 'I', '53.7', '7.7', '0', '124.4', '$806'],
-    ['Dyna-Gro', 'S15RY53', 'RR2Y', '1.5', 'R', 'Ac', '53.6', '7.7', '0', '126.8', '$804'],
-    ['LG Seeds', 'C2050R2', 'RR2Y', '2.1', 'R', 'Ac', '53.6', '7.7', '0', '123.9', '$804'],
-    ['Titan Pro', '19M42', 'RR2Y', '1.9', 'R', 'CMB', '53.6', '7.7', '0', '121.0', '$804'],
-    ['Stine', '19RA02 (2) §', 'RR2Y', '1.9', 'R', 'CMB', '53.4', '7.7', '0', '123.9', '$801'],
-    ['Asgrow', 'AG1832 §', 'RR2Y', '1.8', 'MR', 'Ac,PV', '52.9', '7.7', '0', '122.0', '$794'],
-    ['Prairie Brand', 'PB-1566R2', 'RR2Y', '1.5', 'R', 'CMB', '52.8', '7.7', '0', '122.9', '$792'],
-    ['Channel', '1901R2', 'RR2Y', '1.9', 'R', 'Ac,PV', '52.8', '7.6', '0', '123.4', '$791'],
-    ['Titan Pro', '20M1', 'RR2Y', '2.0', 'R', 'Am', '52.5', '7.5', '0', '124.4', '$788'],
-    ['Kruger', 'K2-2002', 'RR2Y', '2.0', 'R', 'Ac,PV', '52.4', '7.9', '0', '125.4', '$786'],
-    ['Channel', '1700R2', 'RR2Y', '1.7', 'R', 'Ac,PV', '52.3', '7.9', '0', '123.9', '$784'],
-    ['Hefty', 'H16Y11', 'RR2Y', '1.6', 'MR', 'I', '51.4', '7.6', '0', '123.9', '$771'],
-    ['Anderson', '162R2Y', 'RR2Y', '1.6', 'R', 'None', '51.3', '7.5', '0', '119.5', '$770'],
-    ['Titan Pro', '15M22', 'RR2Y', '1.5', 'R', 'CMB', '51.3', '7.8', '0', '125.4', '$769'],
-    ['Dairyland', 'DSR-1710R2Y', 'RR2Y', '1.7', 'R', 'CMB', '51.3', '7.7', '0', '122.0', '$769'],
-    ['Hefty', 'H20R3', 'RR2Y', '2.0', 'MR', 'I', '50.5', '8.2', '0', '121.0', '$757'],
-    ['Prairie Brand', 'PB 1743R2', 'RR2Y', '1.7', 'R', 'CMB', '50.2', '7.7', '0', '125.8', '$752'],
-    ['Gold Country', '1741', 'RR2Y', '1.7', 'R', 'Ac', '50.1', '7.8', '0', '123.9', '$751'],
-    ['Trelay', '20RR43', 'RR2Y', '2.0', 'R', 'Ac,Ex', '49.9', '7.6', '0', '127.8', '$749'],
-    ['Hefty', 'H14R3', 'RR2Y', '1.4', 'MR', 'I', '49.7', '7.7', '0', '122.9', '$746'],
-    ['Prairie Brand', 'PB-2099NRR2', 'RR2Y', '2.0', 'R', 'CMB', '49.6', '7.8', '0', '126.3', '$743'],
-    ['Wensman', 'W 3174NR2', 'RR2Y', '1.7', 'R', 'Ac', '49.3', '7.6', '0', '122.5', '$740'],
-    ['Kruger', 'K2 1602', 'RR2Y', '1.6', 'R', 'Ac,PV', '48.7', '7.6', '0', '125.4', '$731'],
-    ['NK Brand', 'S18-C2 §', 'RR2Y', '1.8', 'R', 'CMB', '48.7', '7.7', '0', '126.8', '$731'],
-    ['Kruger', 'K2 1902', 'RR2Y', '1.9', 'R', 'Ac,PV', '48.7', '7.5', '0', '124.4', '$730'],
-    ['Prairie Brand', 'PB-1823R2', 'RR2Y', '1.8', 'R', 'None', '48.5', '7.6', '0', '121.0', '$727'],
-    ['Gold Country', '1541', 'RR2Y', '1.5', 'R', 'Ac', '48.4', '7.6', '0', '110.4', '$726'],
-    ['', '', '', '', '', 'Test Average  =', '47.6', '7.7', '0', '122.9', '$713'],
-    ['', '', '', '', '', 'LSD (0.10)  =', '5.7', '0.3', 'ns', '37.8', '566.4']
+    [
+        "",
+        "2012 BETTER VARIETIES Harvest Report for Minnesota Central  [ MNCE ]",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "ALL SEASON TEST",
+    ],
+    [
+        "",
+        "Doug Toreen, Renville County, MN 55310          [ BIRD ISLAND ]",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "1.3 - 2.0 MAT. GROUP",
+    ],
+    [
+        "PREV. CROP/HERB:",
+        "Corn / Surpass, Roundup",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "S2MNCE01",
+    ],
+    [
+        "SOIL DESCRIPTION:",
+        "",
+        "Canisteo clay loam, mod. well drained, non-irrigated",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+    ],
+    [
+        "SOIL CONDITIONS:",
+        "",
+        "High P, high K, 6.7 pH, 3.9% OM, Low SCN",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        '30" ROW SPACING',
+    ],
+    [
+        "TILLAGE/CULTIVATION:",
+        "conventional w/ fall till",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+    ],
+    ["PEST MANAGEMENT:", "Roundup twice", "", "", "", "", "", "", "", "", ""],
+    [
+        "SEEDED - RATE:",
+        "May 15",
+        "140 000 /A",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "TOP 30 for YIELD of 63 TESTED",
+        "",
+    ],
+    [
+        "HARVESTED - STAND:",
+        "Oct 3",
+        "122 921 /A",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "AVERAGE of (3) REPLICATIONS",
+        "",
+    ],
+    ["", "", "", "", "SCN", "Seed", "Yield", "Moisture", "Lodging", "Stand", "Gross"],
+    [
+        "Company/Brand",
+        "Product/Brand†",
+        "Technol.†",
+        "Mat.",
+        "Resist.",
+        "Trmt.†",
+        "Bu/A",
+        "%",
+        "%",
+        "(x 1000)",
+        "Income",
+    ],
+    [
+        "Kruger",
+        "K2 1901",
+        "RR2Y",
+        "1.9",
+        "R",
+        "Ac,PV",
+        "56.4",
+        "7.6",
+        "0",
+        "126.3",
+        "$846",
+    ],
+    [
+        "Stine",
+        "19RA02 §",
+        "RR2Y",
+        "1.9",
+        "R",
+        "CMB",
+        "55.3",
+        "7.6",
+        "0",
+        "120.0",
+        "$830",
+    ],
+    [
+        "Wensman",
+        "W 3190NR2",
+        "RR2Y",
+        "1.9",
+        "R",
+        "Ac",
+        "54.5",
+        "7.6",
+        "0",
+        "119.5",
+        "$818",
+    ],
+    ["Hefty", "H17Y12", "RR2Y", "1.7", "MR", "I", "53.7", "7.7", "0", "124.4", "$806"],
+    [
+        "Dyna-Gro",
+        "S15RY53",
+        "RR2Y",
+        "1.5",
+        "R",
+        "Ac",
+        "53.6",
+        "7.7",
+        "0",
+        "126.8",
+        "$804",
+    ],
+    [
+        "LG Seeds",
+        "C2050R2",
+        "RR2Y",
+        "2.1",
+        "R",
+        "Ac",
+        "53.6",
+        "7.7",
+        "0",
+        "123.9",
+        "$804",
+    ],
+    [
+        "Titan Pro",
+        "19M42",
+        "RR2Y",
+        "1.9",
+        "R",
+        "CMB",
+        "53.6",
+        "7.7",
+        "0",
+        "121.0",
+        "$804",
+    ],
+    [
+        "Stine",
+        "19RA02 (2) §",
+        "RR2Y",
+        "1.9",
+        "R",
+        "CMB",
+        "53.4",
+        "7.7",
+        "0",
+        "123.9",
+        "$801",
+    ],
+    [
+        "Asgrow",
+        "AG1832 §",
+        "RR2Y",
+        "1.8",
+        "MR",
+        "Ac,PV",
+        "52.9",
+        "7.7",
+        "0",
+        "122.0",
+        "$794",
+    ],
+    [
+        "Prairie Brand",
+        "PB-1566R2",
+        "RR2Y",
+        "1.5",
+        "R",
+        "CMB",
+        "52.8",
+        "7.7",
+        "0",
+        "122.9",
+        "$792",
+    ],
+    [
+        "Channel",
+        "1901R2",
+        "RR2Y",
+        "1.9",
+        "R",
+        "Ac,PV",
+        "52.8",
+        "7.6",
+        "0",
+        "123.4",
+        "$791",
+    ],
+    [
+        "Titan Pro",
+        "20M1",
+        "RR2Y",
+        "2.0",
+        "R",
+        "Am",
+        "52.5",
+        "7.5",
+        "0",
+        "124.4",
+        "$788",
+    ],
+    [
+        "Kruger",
+        "K2-2002",
+        "RR2Y",
+        "2.0",
+        "R",
+        "Ac,PV",
+        "52.4",
+        "7.9",
+        "0",
+        "125.4",
+        "$786",
+    ],
+    [
+        "Channel",
+        "1700R2",
+        "RR2Y",
+        "1.7",
+        "R",
+        "Ac,PV",
+        "52.3",
+        "7.9",
+        "0",
+        "123.9",
+        "$784",
+    ],
+    ["Hefty", "H16Y11", "RR2Y", "1.6", "MR", "I", "51.4", "7.6", "0", "123.9", "$771"],
+    [
+        "Anderson",
+        "162R2Y",
+        "RR2Y",
+        "1.6",
+        "R",
+        "None",
+        "51.3",
+        "7.5",
+        "0",
+        "119.5",
+        "$770",
+    ],
+    [
+        "Titan Pro",
+        "15M22",
+        "RR2Y",
+        "1.5",
+        "R",
+        "CMB",
+        "51.3",
+        "7.8",
+        "0",
+        "125.4",
+        "$769",
+    ],
+    [
+        "Dairyland",
+        "DSR-1710R2Y",
+        "RR2Y",
+        "1.7",
+        "R",
+        "CMB",
+        "51.3",
+        "7.7",
+        "0",
+        "122.0",
+        "$769",
+    ],
+    ["Hefty", "H20R3", "RR2Y", "2.0", "MR", "I", "50.5", "8.2", "0", "121.0", "$757"],
+    [
+        "Prairie Brand",
+        "PB 1743R2",
+        "RR2Y",
+        "1.7",
+        "R",
+        "CMB",
+        "50.2",
+        "7.7",
+        "0",
+        "125.8",
+        "$752",
+    ],
+    [
+        "Gold Country",
+        "1741",
+        "RR2Y",
+        "1.7",
+        "R",
+        "Ac",
+        "50.1",
+        "7.8",
+        "0",
+        "123.9",
+        "$751",
+    ],
+    [
+        "Trelay",
+        "20RR43",
+        "RR2Y",
+        "2.0",
+        "R",
+        "Ac,Ex",
+        "49.9",
+        "7.6",
+        "0",
+        "127.8",
+        "$749",
+    ],
+    ["Hefty", "H14R3", "RR2Y", "1.4", "MR", "I", "49.7", "7.7", "0", "122.9", "$746"],
+    [
+        "Prairie Brand",
+        "PB-2099NRR2",
+        "RR2Y",
+        "2.0",
+        "R",
+        "CMB",
+        "49.6",
+        "7.8",
+        "0",
+        "126.3",
+        "$743",
+    ],
+    [
+        "Wensman",
+        "W 3174NR2",
+        "RR2Y",
+        "1.7",
+        "R",
+        "Ac",
+        "49.3",
+        "7.6",
+        "0",
+        "122.5",
+        "$740",
+    ],
+    [
+        "Kruger",
+        "K2 1602",
+        "RR2Y",
+        "1.6",
+        "R",
+        "Ac,PV",
+        "48.7",
+        "7.6",
+        "0",
+        "125.4",
+        "$731",
+    ],
+    [
+        "NK Brand",
+        "S18-C2 §",
+        "RR2Y",
+        "1.8",
+        "R",
+        "CMB",
+        "48.7",
+        "7.7",
+        "0",
+        "126.8",
+        "$731",
+    ],
+    [
+        "Kruger",
+        "K2 1902",
+        "RR2Y",
+        "1.9",
+        "R",
+        "Ac,PV",
+        "48.7",
+        "7.5",
+        "0",
+        "124.4",
+        "$730",
+    ],
+    [
+        "Prairie Brand",
+        "PB-1823R2",
+        "RR2Y",
+        "1.8",
+        "R",
+        "None",
+        "48.5",
+        "7.6",
+        "0",
+        "121.0",
+        "$727",
+    ],
+    [
+        "Gold Country",
+        "1541",
+        "RR2Y",
+        "1.5",
+        "R",
+        "Ac",
+        "48.4",
+        "7.6",
+        "0",
+        "110.4",
+        "$726",
+    ],
+    ["", "", "", "", "", "Test Average  =", "47.6", "7.7", "0", "122.9", "$713"],
+    ["", "", "", "", "", "LSD (0.10)  =", "5.7", "0.3", "ns", "37.8", "566.4"],
 ]

tests/test_cli.py

@@ -1,7 +1,9 @@
 # -*- coding: utf-8 -*-
 
 import os
+import sys
 
+import pytest
 from click.testing import CliRunner
 
 from camelot.cli import cli
@@ -11,6 +13,11 @@ from camelot.utils import TemporaryDirectory
 testdir = os.path.dirname(os.path.abspath(__file__))
 testdir = os.path.join(testdir, "files")
 
+skip_on_windows = pytest.mark.skipif(
+    sys.platform.startswith("win"),
+    reason="Ghostscript not installed in Windows test environment",
+)
+
 
 def test_help_output():
     runner = CliRunner()
@@ -26,6 +33,7 @@ def test_help_output():
     )
 
 
+@skip_on_windows
 def test_cli_lattice():
     with TemporaryDirectory() as tempdir:
         infile = os.path.join(testdir, "foo.pdf")
@@ -35,7 +43,7 @@ def test_cli_lattice():
             cli, ["--format", "csv", "--output", outfile, "lattice", infile]
         )
         assert result.exit_code == 0
-        assert result.output == "Found 1 tables\n"
+        assert "Found 1 tables" in result.output
 
         result = runner.invoke(cli, ["--format", "csv", "lattice", infile])
         output_error = "Error: Please specify output file path using --output"
@@ -123,7 +131,7 @@ def test_cli_output_format():
             cli,
             ["--format", "json", "--output", outfile, "stream", infile],
         )
-        assert result.exit_code == 0
+        assert result.exit_code == 0, f"Output: {result.output}"
 
         # excel
         outfile = os.path.join(tempdir, "health.xlsx")
@@ -131,7 +139,7 @@ def test_cli_output_format():
             cli,
             ["--format", "excel", "--output", outfile, "stream", infile],
         )
-        assert result.exit_code == 0
+        assert result.exit_code == 0, f"Output: {result.output}"
 
         # html
         outfile = os.path.join(tempdir, "health.html")
@@ -139,7 +147,15 @@ def test_cli_output_format():
             cli,
             ["--format", "html", "--output", outfile, "stream", infile],
         )
-        assert result.exit_code == 0
+        assert result.exit_code == 0, f"Output: {result.output}"
+
+        # markdown
+        outfile = os.path.join(tempdir, "health.md")
+        result = runner.invoke(
+            cli,
+            ["--format", "markdown", "--output", outfile, "stream", infile],
+        )
+        assert result.exit_code == 0, f"Output: {result.output}"
 
         # zip
         outfile = os.path.join(tempdir, "health.csv")
@@ -155,7 +171,7 @@ def test_cli_output_format():
                 infile,
             ],
         )
-        assert result.exit_code == 0
+        assert result.exit_code == 0, f"Output: {result.output}"
 
 
 def test_cli_quiet():

tests/test_common.py

@@ -1,20 +1,45 @@
 # -*- coding: utf-8 -*-
 
 import os
+import sys
 
+import pytest
 import pandas as pd
 from pandas.testing import assert_frame_equal
 
 import camelot
+from camelot.io import PDFHandler
 from camelot.core import Table, TableList
 from camelot.__version__ import generate_version
+from camelot.backends import ImageConversionBackend
 
 from .data import *
 
 testdir = os.path.dirname(os.path.abspath(__file__))
 testdir = os.path.join(testdir, "files")
 
+skip_on_windows = pytest.mark.skipif(
+    sys.platform.startswith("win"),
+    reason="Ghostscript not installed in Windows test environment",
+)
 
+
+def test_version_generation():
+    version = (0, 7, 3)
+    assert generate_version(version, prerelease=None, revision=None) == "0.7.3"
+
+
+def test_version_generation_with_prerelease_revision():
+    version = (0, 7, 3)
+    prerelease = "alpha"
+    revision = 2
+    assert (
+        generate_version(version, prerelease=prerelease, revision=revision)
+        == "0.7.3-alpha.2"
+    )
+
+
+@skip_on_windows
 def test_parsing_report():
     parsing_report = {"accuracy": 99.02, "whitespace": 12.24, "order": 1, "page": 1}
 
@@ -34,246 +59,75 @@ def test_password():
     assert_frame_equal(df, tables[0].df)
 
 
-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():
+def test_repr_poppler():
     filename = os.path.join(testdir, "foo.pdf")
-    tables = camelot.read_pdf(filename)
+    tables = camelot.read_pdf(filename, 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=120.48 y1=218.43 x2=164.64 y2=233.77>"
-    )
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
 
 
-def test_pages():
+@skip_on_windows
+def test_repr_ghostscript():
+    filename = os.path.join(testdir, "foo.pdf")
+    tables = camelot.read_pdf(filename, backend="ghostscript")
+    assert repr(tables) == "<TableList n=1>"
+    assert repr(tables[0]) == "<Table shape=(7, 7)>"
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
+
+
+def test_url_poppler():
     url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
-    tables = camelot.read_pdf(url)
+    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=120.48 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>"
-    )
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
 
 
-def test_url():
+@skip_on_windows
+def test_url_ghostscript():
     url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
-    tables = camelot.read_pdf(url)
+    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=120.48 y1=218.43 x2=164.64 y2=233.77>"
-    )
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
 
 
-def test_arabic():
-    df = pd.DataFrame(data_arabic)
+def test_pages_poppler():
+    url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
+    tables = camelot.read_pdf(url, backend="poppler")
+    assert repr(tables) == "<TableList n=1>"
+    assert repr(tables[0]) == "<Table shape=(7, 7)>"
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
 
-    filename = os.path.join(testdir, "tabula/arabic.pdf")
-    tables = camelot.read_pdf(filename)
-    assert_frame_equal(df, tables[0].df)
+    tables = camelot.read_pdf(url, pages="1-end", backend="poppler")
+    assert repr(tables) == "<TableList n=1>"
+    assert repr(tables[0]) == "<Table shape=(7, 7)>"
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
+
+    tables = camelot.read_pdf(url, pages="all", backend="poppler")
+    assert repr(tables) == "<TableList n=1>"
+    assert repr(tables[0]) == "<Table shape=(7, 7)>"
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=219 x2=165 y2=234>"
+
+
+@skip_on_windows
+def test_pages_ghostscript():
+    url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
+    tables = camelot.read_pdf(url, backend="ghostscript")
+    assert repr(tables) == "<TableList n=1>"
+    assert repr(tables[0]) == "<Table shape=(7, 7)>"
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
+
+    tables = camelot.read_pdf(url, pages="1-end", backend="ghostscript")
+    assert repr(tables) == "<TableList n=1>"
+    assert repr(tables[0]) == "<Table shape=(7, 7)>"
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
+
+    tables = camelot.read_pdf(url, pages="all", backend="ghostscript")
+    assert repr(tables) == "<TableList n=1>"
+    assert repr(tables[0]) == "<Table shape=(7, 7)>"
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120 y1=218 x2=165 y2=234>"
 
 
 def test_table_order():
@@ -301,24 +155,20 @@ def test_table_order():
     ]
 
 
-def test_version_generation():
-    version = (0, 7, 3)
-    assert generate_version(version, prerelease=None, revision=None) == "0.7.3"
+def test_handler_pages_generator():
+    filename = os.path.join(testdir, "foo.pdf")
 
+    handler = PDFHandler(filename)
+    assert handler._get_pages("1") == [1]
 
-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"
-    )
+    handler = PDFHandler(filename)
+    assert handler._get_pages("all") == [1]
 
+    handler = PDFHandler(filename)
+    assert handler._get_pages("1-end") == [1]
 
-def test_stream_duplicated_text():
-    df = pd.DataFrame(data_stream_duplicated_text)
+    handler = PDFHandler(filename)
+    assert handler._get_pages("1,2,3,4") == [1, 2, 3, 4]
 
-    filename = os.path.join(testdir, "birdisland.pdf")
-    tables = camelot.read_pdf(filename, flavor="stream")
-    assert_frame_equal(df, tables[0].df)
+    handler = PDFHandler(filename)
+    assert handler._get_pages("1,2,5-10") == [1, 2, 5, 6, 7, 8, 9, 10]

tests/test_errors.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 
 import os
+import sys
 import warnings
 
 import pytest
@@ -12,6 +13,11 @@ testdir = os.path.dirname(os.path.abspath(__file__))
 testdir = os.path.join(testdir, "files")
 filename = os.path.join(testdir, "foo.pdf")
 
+skip_on_windows = pytest.mark.skipif(
+    sys.platform.startswith("win"),
+    reason="Ghostscript not installed in Windows test environment",
+)
+
 
 def test_unknown_flavor():
     message = "Unknown flavor specified." " Use either 'lattice' or 'stream'"
@@ -32,56 +38,7 @@ def test_unsupported_format():
         tables = camelot.read_pdf(filename)
 
 
-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"
-
-
+@skip_on_windows
 def test_no_tables_found_logs_suppressed():
     filename = os.path.join(testdir, "foo.pdf")
     with warnings.catch_warnings():
@@ -118,3 +75,81 @@ def test_bad_password():
     message = "file has not been decrypted"
     with pytest.raises(Exception, match=message):
         tables = camelot.read_pdf(filename, password="wrongpass")
+
+
+def test_stream_equal_length():
+    message = "Length of table_areas and columns" " should be equal"
+    with pytest.raises(ValueError, match=message):
+        tables = camelot.read_pdf(
+            filename,
+            flavor="stream",
+            table_areas=["10,20,30,40"],
+            columns=["10,20,30,40", "10,20,30,40"],
+        )
+
+
+def test_image_warning():
+    filename = os.path.join(testdir, "image.pdf")
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", category=UserWarning)
+        with pytest.raises(UserWarning) as e:
+            tables = camelot.read_pdf(filename)
+            assert (
+                str(e.value)
+                == "page-1 is image-based, camelot only works on text-based pages."
+            )
+
+
+def test_stream_no_tables_on_page():
+    filename = os.path.join(testdir, "empty.pdf")
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
+        with pytest.raises(UserWarning) as e:
+            tables = camelot.read_pdf(filename, flavor="stream")
+        assert str(e.value) == "No tables found on page-1"
+
+
+def test_stream_no_tables_in_area():
+    filename = os.path.join(testdir, "only_page_number.pdf")
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
+        with pytest.raises(UserWarning) as e:
+            tables = camelot.read_pdf(filename, flavor="stream")
+        assert str(e.value) == "No tables found in table area 1"
+
+
+def test_lattice_no_tables_on_page():
+    filename = os.path.join(testdir, "empty.pdf")
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", category=UserWarning)
+        with pytest.raises(UserWarning) as e:
+            tables = camelot.read_pdf(filename, flavor="lattice")
+        assert str(e.value) == "No tables found on page-1"
+
+
+def test_lattice_unknown_backend():
+    message = "Unknown backend 'mupdf' specified. Please use either 'poppler' or 'ghostscript'."
+    with pytest.raises(NotImplementedError, match=message):
+        tables = camelot.read_pdf(filename, backend="mupdf")
+
+
+def test_lattice_no_convert_method():
+    class ConversionBackend(object):
+        pass
+
+    message = "must implement a 'convert' method"
+    with pytest.raises(NotImplementedError, match=message):
+        tables = camelot.read_pdf(filename, backend=ConversionBackend())
+
+
+def test_lattice_ghostscript_deprecation_warning():
+    ghostscript_deprecation_warning = (
+        "'ghostscript' will be replaced by 'poppler' as the default image conversion"
+        " backend in v0.12.0. You can try out 'poppler' with backend='poppler'."
+    )
+
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
+        with pytest.raises(DeprecationWarning) as e:
+            tables = camelot.read_pdf(filename)
+            assert str(e.value) == ghostscript_deprecation_warning

tests/test_image_conversion_backend.py

@@ -0,0 +1,60 @@
+# -*- 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")

tests/test_lattice.py

@@ -0,0 +1,120 @@
+# -*- 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)

tests/test_plotting.py

@@ -1,16 +1,22 @@
 # -*- coding: utf-8 -*-
 
 import os
+import sys
 
 import pytest
 
 import camelot
 
-
 testdir = os.path.dirname(os.path.abspath(__file__))
 testdir = os.path.join(testdir, "files")
 
+skip_on_windows = pytest.mark.skipif(
+    sys.platform.startswith("win"),
+    reason="Ghostscript not installed in Windows test environment",
+)
 
+
+@skip_on_windows
 @pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
 def test_text_plot():
     filename = os.path.join(testdir, "foo.pdf")
@@ -19,16 +25,24 @@ def test_text_plot():
 
 
 @pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
-def test_grid_plot():
-    filename = os.path.join(testdir, "foo.pdf")
-    tables = camelot.read_pdf(filename)
-    return camelot.plot(tables[0], kind="grid")
+def test_textedge_plot():
+    filename = os.path.join(testdir, "tabula/12s0324.pdf")
+    tables = camelot.read_pdf(filename, flavor="stream")
+    return camelot.plot(tables[0], kind="textedge")
 
 
 @pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
-def test_lattice_contour_plot():
+def test_lattice_contour_plot_poppler():
     filename = os.path.join(testdir, "foo.pdf")
-    tables = camelot.read_pdf(filename)
+    tables = camelot.read_pdf(filename, backend="poppler")
+    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")
 
 
@@ -40,21 +54,45 @@ def test_stream_contour_plot():
 
 
 @pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
-def test_line_plot():
+def test_line_plot_poppler():
     filename = os.path.join(testdir, "foo.pdf")
-    tables = camelot.read_pdf(filename)
+    tables = camelot.read_pdf(filename, backend="poppler")
+    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")
 
 
 @pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
-def test_joint_plot():
+def test_joint_plot_poppler():
     filename = os.path.join(testdir, "foo.pdf")
-    tables = camelot.read_pdf(filename)
+    tables = camelot.read_pdf(filename, backend="poppler")
+    return camelot.plot(tables[0], kind="joint")
+
+
+@skip_on_windows
+@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
+def test_joint_plot_ghostscript():
+    filename = os.path.join(testdir, "foo.pdf")
+    tables = camelot.read_pdf(filename, backend="ghostscript")
     return camelot.plot(tables[0], kind="joint")
 
 
 @pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
-def test_textedge_plot():
-    filename = os.path.join(testdir, "tabula/12s0324.pdf")
-    tables = camelot.read_pdf(filename, flavor="stream")
-    return camelot.plot(tables[0], kind="textedge")
+def test_grid_plot_poppler():
+    filename = os.path.join(testdir, "foo.pdf")
+    tables = camelot.read_pdf(filename, backend="poppler")
+    return camelot.plot(tables[0], kind="grid")
+
+
+@skip_on_windows
+@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
+def test_grid_plot_ghostscript():
+    filename = os.path.join(testdir, "foo.pdf")
+    tables = camelot.read_pdf(filename, backend="ghostscript")
+    return camelot.plot(tables[0], kind="grid")

tests/test_stream.py

@@ -0,0 +1,133 @@
+# -*- 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)