Bump version

Update HISTORY.md
Merge pull request #219 from Arnie97/master
2021-06-15 03:58:30 +05:30 · 2021-06-15 03:55:46 +05:30 · 2021-06-15 03:53:40 +05:30 · 2021-06-15 03:53:23 +05:30 · 2021-06-15 03:51:00 +05:30 · 2021-06-15 03:46:07 +05:30
48 changed files with 1270 additions and 684 deletions
@@ -1,10 +0,0 @@
 root = true
 [*]
 end_of_line = lf
 insert_final_newline = true
 [*.py]
 charset = utf-8
 indent_style = space
 indent_size = 4
@@ -0,0 +1 @@
 open_collective: camelot
@@ -0,0 +1,48 @@
 ---
 name: Bug report
 about: Please follow this template to submit bug reports.
 title: ''
 labels: bug
 assignees: ''
 ---
 <!-- Please read the filing issues section of the contributor's guide first: https://camelot-py.readthedocs.io/en/master/dev/contributing.html -->
 **Describe the bug**
 A clear and concise description of what the bug is.
 **Steps to reproduce the bug**
 Steps used to install `camelot`:
 1. Add step here (you can add more steps too)
 Steps to reproduce the behavior:
 1. Add step here (you can add more steps too)
 **Expected behavior**
 A clear and concise description of what you expected to happen.
 **Code**
 Add the Camelot code snippet that you used.
 ```
 import camelot
 # add your code here
 ```
 **PDF**
 Add the PDF file that you want to extract tables from.
 **Screenshots**
 If applicable, add screenshots to help explain your problem.
 **Environment**
 - OS: [e.g. MacOS]
 - Python version:
 - Numpy version:
 - OpenCV version:
 - Ghostscript version:
 - Camelot version:
 **Additional context**
 Add any other context about the problem here.
@@ -0,0 +1,23 @@
 name: tests
 on: [pull_request]
 jobs:
  test:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        python-version: [3.6, 3.7, 3.8, 3.9]
    steps:
      - uses: actions/checkout@v2
      - name: Set up Python ${{ matrix.python-version }}
        uses: actions/setup-python@v2
        with:
          python-version: ${{ matrix.python-version }}
      - name: Install camelot with dependencies
        run: |
          make install
      - name: Test with pytest
        run: |
          make test
@@ -0,0 +1,27 @@
 # .readthedocs.yml
 # Read the Docs configuration file
 # See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
 # Required
 version: 2
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
  configuration: docs/conf.py
 # Build documentation with MkDocs
 #mkdocs:
 #  configuration: mkdocs.yml
 # Optionally build your docs in additional formats such as PDF
 formats:
  - pdf
 # Optionally set the version of Python and requirements required to build your docs
 python:
  version: 3.8
  install:
    - method: pip
      path: .
      extra_requirements:
        - dev
@@ -1,32 +0,0 @@
 sudo: true
 language: python
 cache: pip
 addons:
  apt:
    update: true
 install:
  - make install
 jobs:
  include:
    - stage: test
      script:
        - make test
      python: '2.7'
    - stage: test
      script:
        - make test
      python: '3.5'
    - stage: test
      script:
        - make test
      python: '3.6'
    - stage: test
      script:
        - make test
      python: '3.7'
      dist: xenial
    - stage: coverage
      python: '3.6'
      script:
        - make test
        - codecov --verbose
@@ -23,7 +23,7 @@ A great way to start contributing to Camelot is to pick an issue tagged with the
 To install the dependencies needed for development, you can use pip:
 <pre>
-$ pip install camelot-py[dev]
+$ pip install "camelot-py[dev]"
 </pre>
 Alternatively, you can clone the project repository, and install using pip:
@@ -4,6 +4,55 @@ Release History
 master
 ------
 0.9.0 (2021-06-15)
 ------------------
 **Bugfixes**
 - Fix use of resolution argument to generate image with ghostscript. [#231](https://github.com/camelot-dev/camelot/pull/231) by [Tiago Samaha Cordeiro](https://github.com/tiagosamaha).
 - [#15](https://github.com/camelot-dev/camelot/issues/15) Fix duplicate strings being assigned to the same cell. [#206](https://github.com/camelot-dev/camelot/pull/206) by [Eduardo Gonzalez Lopez de Murillas](https://github.com/edugonza).
 - Save plot when filename is specified. [#121](https://github.com/camelot-dev/camelot/pull/121) by [Jens Diemer](https://github.com/jedie).
 - Close file streams explicitly. [#202](https://github.com/camelot-dev/camelot/pull/202) by [Martin Abente Lahaye](https://github.com/tchx84).
 - Use correct re.sub signature. [#186](https://github.com/camelot-dev/camelot/pull/186) by [pevisscher](https://github.com/pevisscher).
 - [#183](https://github.com/camelot-dev/camelot/issues/183) Fix UnicodeEncodeError when using Stream flavor by adding encoding kwarg to `to_html`. [#188](https://github.com/camelot-dev/camelot/pull/188) by [Stefano Fiorucci](https://github.com/anakin87).
 - [#179](https://github.com/camelot-dev/camelot/issues/179) Fix `max() arg is an empty sequence` error on PDFs with blank pages. [#189](https://github.com/camelot-dev/camelot/pull/189) by Vinayak Mehta.
 **Improvements**
 - Add `line_overlap` and `boxes_flow` to `LAParams`. [#219](https://github.com/camelot-dev/camelot/pull/219) by [Arnie97](https://github.com/Arnie97).
 - [Add bug report template.](https://github.com/camelot-dev/camelot/commit/0a3944e54d133b701edfe9c7546ff11289301ba8)
 - Move from [Travis to GitHub Actions](https://github.com/camelot-dev/camelot/pull/241).
 - Update `.readthedocs.yml` and [remove requirements.txt](https://github.com/camelot-dev/camelot/commit/7ab5db39d07baa4063f975e9e00f6073340e04c1#diff-cde814ef2f549dc093f5b8fc533b7e8f47e7b32a8081e0760e57d5c25a1139d9)
 **Documentation**
 - [#193](https://github.com/camelot-dev/camelot/issues/193) Add better checks to confirm proper installation of ghostscript. [#196](https://github.com/camelot-dev/camelot/pull/196) by [jimhall](https://github.com/jimhall).
 - Update `advanced.rst` plotting examples. [#119](https://github.com/camelot-dev/camelot/pull/119) by [Jens Diemer](https://github.com/jedie).
 0.8.2 (2020-07-27)
 ------------------
 * Revert the changes in `0.8.1`.
 0.8.1 (2020-07-21)
 ------------------
 **Bugfixes**
 * [#169](https://github.com/camelot-dev/camelot/issues/169) Fix import error caused by `pdfminer.six==20200720`. [#171](https://github.com/camelot-dev/camelot/pull/171) by Vinayak Mehta.
 0.8.0 (2020-05-24)
 ------------------
 **Improvements**
 * Drop Python 2 support!
    * Remove Python 2.7 and 3.5 support.
    * Replace all instances of `.format` with f-strings.
    * Remove all `__future__` imports.
    * Fix HTTP 403 forbidden exception in read_pdf(url) and remove Python 2 urllib support.
    * Fix test data.
 **Bugfixes**
 * Fix library discovery on Windows. [#32](https://github.com/camelot-dev/camelot/pull/32) by [KOLANICH](https://github.com/KOLANICH).
@@ -1,12 +1,7 @@
 MIT License
-Modifications:
+Copyright (c) 2019-2021 Camelot Developers
-
+Copyright (c) 2018-2019 Peeply Private Ltd (Singapore)
 Copyright (c) 2019 Camelot Developers
 Original project:
 Copyright (c) 2018 Peeply Private Ltd (Singapore)
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
@@ -4,19 +4,18 @@
 # 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/)
+![Build Status](https://github.com/camelot-dev/camelot/actions/workflows/tests.yml/badge.svg) [![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)
 **Camelot** is a Python library that can help you extract tables from PDFs!
-**Camelot** is a Python library that makes it easy for *anyone* to extract tables from PDF files!
+**Note:** You can also check out [Excalibur](https://github.com/camelot-dev/excalibur), the web interface to Camelot!
 **Note:** You can also check out [Excalibur](https://github.com/camelot-dev/excalibur), which is a web interface for Camelot!
 ---
-**Here's how you can extract tables from PDF files.** Check out the PDF used in this example [here](https://github.com/camelot-dev/camelot/blob/master/docs/_static/pdf/foo.pdf).
+**Here's how you can extract tables from PDFs.** You can check out the PDF used in this example [here](https://github.com/camelot-dev/camelot/blob/master/docs/_static/pdf/foo.pdf).
 <pre>
 >>> import camelot
@@ -46,24 +45,27 @@
 | 2032_2     | 0.17      | 57.8          | 21.7%                | 0.3%            | 2.7%            | 1.2%           |
 | 4171_1     | 0.07      | 173.9         | 58.1%                | 1.6%            | 2.1%            | 0.5%           |
-There's a [command-line interface](https://camelot-py.readthedocs.io/en/master/user/cli.html) too!
+Camelot also comes packaged with a [command-line interface](https://camelot-py.readthedocs.io/en/master/user/cli.html)!
 **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".)
 ## Why Camelot?
- **You are in control.**: Unlike other libraries and tools which either give a nice output or fail miserably (with no in-between), Camelot gives you the power to tweak table extraction. (This is important since everything in the real world, including PDF table extraction, is fuzzy.)
+- **Configurability**: Camelot gives you control over the table extraction process with its [tweakable settings](https://camelot-py.readthedocs.io/en/master/user/advanced.html).
- *Bad* tables can be discarded based on **metrics** like accuracy and whitespace, without ever having to manually look at each table.
+- **Metrics**: Bad tables can be discarded based on metrics like accuracy and whitespace, without having to manually look at each table.
- Each table is a **pandas DataFrame**, which seamlessly integrates into [ETL and data analysis workflows](https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873).
+- **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.
 - **Export** to multiple formats, including JSON, Excel, HTML and Sqlite.
-See [comparison with other PDF table extraction libraries and tools](https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools).
+See [comparison with similar libraries and tools](https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools).
 ## Support the development
 If Camelot has helped you, please consider supporting its development with a one-time or monthly donation [on OpenCollective](https://opencollective.com/camelot).
 ## Installation
 ### Using conda
-The easiest way to install Camelot is to install it with [conda](https://conda.io/docs/), which is a package manager and  environment management system for the [Anaconda](http://docs.continuum.io/anaconda/) distribution.
+The easiest way to install Camelot is with [conda](https://conda.io/docs/), which is a package manager and environment management system for the [Anaconda](http://docs.continuum.io/anaconda/) distribution.
 <pre>
 $ conda install -c conda-forge camelot-py
@@ -71,10 +73,10 @@ $ conda install -c conda-forge camelot-py
 ### Using pip
-After [installing the dependencies](https://camelot-py.readthedocs.io/en/master/user/install-deps.html) ([tk](https://packages.ubuntu.com/bionic/python/python-tk) and [ghostscript](https://www.ghostscript.com/)), you can simply use pip to install Camelot:
+After [installing the dependencies](https://camelot-py.readthedocs.io/en/master/user/install-deps.html) ([tk](https://packages.ubuntu.com/bionic/python/python-tk) and [ghostscript](https://www.ghostscript.com/)), you can also just use pip to install Camelot:
 <pre>
-$ pip install camelot-py[cv]
+$ pip install "camelot-py[cv]"
 </pre>
 ### From the source code
@@ -94,35 +96,15 @@ $ pip install ".[cv]"
 ## Documentation
-Great documentation is available at [http://camelot-py.readthedocs.io/](http://camelot-py.readthedocs.io/).
+The documentation is available at [http://camelot-py.readthedocs.io/](http://camelot-py.readthedocs.io/).
-## Development
+## Wrappers
-The [Contributor's Guide](https://camelot-py.readthedocs.io/en/master/dev/contributing.html) has detailed information about contributing code, documentation, tests and more. We've included some basic information in this README.
+- [camelot-php](https://github.com/randomstate/camelot-php) provides a [PHP](https://www.php.net/) wrapper on Camelot.
-### Source code
+## Contributing
-You can check the latest sources with:
+The [Contributor's Guide](https://camelot-py.readthedocs.io/en/master/dev/contributing.html) has detailed information about contributing issues, documentation, code, and tests.
 <pre>
 $ git clone https://www.github.com/camelot-dev/camelot
 </pre>
 ### Setting up a development environment
 You can install the development dependencies easily, using pip:
 <pre>
 $ pip install camelot-py[dev]
 </pre>
 ### Testing
 After installation, you can run tests using:
 <pre>
 $ python setup.py test
 </pre>
 ## Versioning
@@ -131,9 +113,3 @@ Camelot uses [Semantic Versioning](https://semver.org/). For the available versi
 ## License
 This project is licensed under the MIT License, see the [LICENSE](https://github.com/camelot-dev/camelot/blob/master/LICENSE) file for details.
 ## Support the development
 You can support our work on Camelot with a one-time or monthly donation [on OpenCollective](https://opencollective.com/camelot). Organizations who use camelot can also sponsor the project for an acknowledgement on [our documentation site](https://camelot-py.readthedocs.io/en/master/) and this README.
 Special thanks to all the users, organizations and contributors that support Camelot!
@@ -1,7 +1,5 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import
 __all__ = ("main",)
@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
-VERSION = (0, 7, 3)
+VERSION = (0, 9, 0)
 PRERELEASE = None  # alpha, beta or rc
 REVISION = None
@@ -8,9 +8,9 @@ REVISION = None
 def generate_version(version, prerelease=None, revision=None):
    version_parts = [".".join(map(str, version))]
    if prerelease is not None:
-        version_parts.append("-{}".format(prerelease))
+        version_parts.append(f"-{prerelease}")
    if revision is not None:
-        version_parts.append(".{}".format(revision))
+        version_parts.append(f".{revision}")
    return "".join(version_parts)
@@ -204,7 +204,7 @@ def lattice(c, *args, **kwargs):
    tables = read_pdf(
        filepath, pages=pages, flavor="lattice", suppress_stdout=quiet, **kwargs
    )
-    click.echo("Found {} tables".format(tables.n))
+    click.echo(f"Found {tables.n} tables")
    if plot_type is not None:
        for table in tables:
            plot(table, kind=plot_type)
@@ -295,7 +295,7 @@ def stream(c, *args, **kwargs):
    tables = read_pdf(
        filepath, pages=pages, flavor="stream", suppress_stdout=quiet, **kwargs
    )
-    click.echo("Found {} tables".format(tables.n))
+    click.echo(f"Found {tables.n} tables")
    if plot_type is not None:
        for table in tables:
            plot(table, kind=plot_type)
@@ -52,12 +52,11 @@ class TextEdge(object):
        self.is_valid = False
    def __repr__(self):
-        return "<TextEdge x={} y0={} y1={} align={} valid={}>".format(
+        x = round(self.x, 2)
-            round(self.x, 2),
+        y0 = round(self.y0, 2)
-            round(self.y0, 2),
+        y1 = round(self.y1, 2)
-            round(self.y1, 2),
+        return (
-            self.align,
+            f"<TextEdge x={x} y0={y0} y1={y1} align={self.align} valid={self.is_valid}>"
            self.is_valid,
        )
    def update_coords(self, x, y0, edge_tol=50):
@@ -105,8 +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
@@ -114,8 +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)
@@ -291,9 +288,11 @@ class Cell(object):
        self._text = ""
    def __repr__(self):
-        return "<Cell x1={} y1={} x2={} y2={}>".format(
+        x1 = round(self.x1, 2)
-            round(self.x1, 2), round(self.y1, 2), round(self.x2, 2), round(self.y2, 2)
+        y1 = round(self.y1, 2)
-        )
+        x2 = round(self.x2, 2)
        y2 = round(self.y2, 2)
        return f"<Cell x1={x1} y1={y1} x2={x2} y2={y2}>"
    @property
    def text(self):
@@ -305,8 +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
@@ -351,7 +349,7 @@ class Table(object):
        self.page = None
    def __repr__(self):
-        return "<{} shape={}>".format(self.__class__.__name__, self.shape)
+        return f"<{self.__class__.__name__} shape={self.shape}>"
    def __lt__(self, other):
        if self.page == other.page:
@@ -362,8 +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])
@@ -384,8 +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
@@ -527,8 +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
@@ -612,7 +607,7 @@ class Table(object):
        """
        kw = {
-            "sheet_name": "page-{}-table-{}".format(self.page, self.order),
+            "sheet_name": f"page-{self.page}-table-{self.order}",
            "encoding": "utf-8",
        }
        kw.update(kwargs)
@@ -632,7 +627,7 @@ class Table(object):
        """
        html_string = self.df.to_html(**kwargs)
-        with open(path, "w") as f:
+        with open(path, "w", encoding="utf-8") as f:
            f.write(html_string)
    def to_sqlite(self, path, **kwargs):
@@ -649,7 +644,7 @@ class Table(object):
        kw = {"if_exists": "replace", "index": False}
        kw.update(kwargs)
        conn = sqlite3.connect(path)
-        table_name = "page-{}-table-{}".format(self.page, self.order)
+        table_name = f"page-{self.page}-table-{self.order}"
        self.df.to_sql(table_name, conn, **kw)
        conn.commit()
        conn.close()
@@ -670,7 +665,7 @@ class TableList(object):
        self._tables = tables
    def __repr__(self):
-        return "<{} n={}>".format(self.__class__.__name__, self.n)
+        return f"<{self.__class__.__name__} n={self.n}>"
    def __len__(self):
        return len(self._tables)
@@ -680,7 +675,7 @@ class TableList(object):
    @staticmethod
    def _format_func(table, f):
-        return getattr(table, "to_{}".format(f))
+        return getattr(table, f"to_{f}")
    @property
    def n(self):
@@ -691,9 +686,7 @@ class TableList(object):
        root = kwargs.get("root")
        ext = kwargs.get("ext")
        for table in self._tables:
-            filename = os.path.join(
+            filename = f"{root}-page-{table.page}-table-{table.order}{ext}"
                "{}-page-{}-table-{}{}".format(root, table.page, table.order, ext)
            )
            filepath = os.path.join(dirname, filename)
            to_format = self._format_func(table, f)
            to_format(filepath)
@@ -706,9 +699,7 @@ class TableList(object):
        zipname = os.path.join(os.path.dirname(path), root) + ".zip"
        with zipfile.ZipFile(zipname, "w", allowZip64=True) as z:
            for table in self._tables:
-                filename = os.path.join(
+                filename = f"{root}-page-{table.page}-table-{table.order}{ext}"
                    "{}-page-{}-table-{}{}".format(root, table.page, table.order, ext)
                )
                filepath = os.path.join(dirname, filename)
                z.write(filepath, os.path.basename(filepath))
@@ -741,7 +732,7 @@ class TableList(object):
            filepath = os.path.join(dirname, basename)
            writer = pd.ExcelWriter(filepath)
            for table in self._tables:
-                sheet_name = "page-{}-table-{}".format(table.page, table.order)
+                sheet_name = f"page-{table.page}-table-{table.order}"
                table.df.to_excel(writer, sheet_name=sheet_name, encoding="utf-8")
            writer.save()
            if compress:
@@ -81,8 +81,7 @@ class __Ghostscript(object):
 def Ghostscript(*args, **kwargs):
-    """Factory function for setting up a Ghostscript instance
+    """Factory function for setting up a Ghostscript instance"""
    """
    global __instance__
    # Ghostscript only supports a single instance
    if __instance__ is None:
@@ -81,6 +81,7 @@ def delete_instance(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:
@@ -247,7 +248,10 @@ 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%
+
        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)
@@ -70,7 +70,8 @@ class PDFHandler(object):
        if pages == "1":
            page_numbers.append({"start": 1, "end": 1})
        else:
-            infile = PdfFileReader(open(filepath, "rb"), strict=False)
+            instream = open(filepath, "rb")
            infile = PdfFileReader(instream, strict=False)
            if infile.isEncrypted:
                infile.decrypt(self.password)
            if pages == "all":
@@ -84,6 +85,7 @@ 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))
@@ -106,7 +108,7 @@ class PDFHandler(object):
            infile = PdfFileReader(fileobj, strict=False)
            if infile.isEncrypted:
                infile.decrypt(self.password)
-            fpath = os.path.join(temp, "page-{0}.pdf".format(page))
+            fpath = os.path.join(temp, f"page-{page}.pdf")
            froot, fext = os.path.splitext(fpath)
            p = infile.getPage(page - 1)
            outfile = PdfFileWriter()
@@ -122,7 +124,8 @@ class PDFHandler(object):
            if rotation != "":
                fpath_new = "".join([froot.replace("page", "p"), "_rotated", fext])
                os.rename(fpath, fpath_new)
-                infile = PdfFileReader(open(fpath_new, "rb"), strict=False)
+                instream = open(fpath_new, "rb")
                infile = PdfFileReader(instream, strict=False)
                if infile.isEncrypted:
                    infile.decrypt(self.password)
                outfile = PdfFileWriter()
@@ -134,6 +137,7 @@ class PDFHandler(object):
                outfile.addPage(p)
                with open(fpath, "wb") as f:
                    outfile.write(f)
                instream.close()
    def parse(
        self, flavor="lattice", suppress_stdout=False, layout_kwargs={}, **kwargs
@@ -163,9 +167,7 @@ class PDFHandler(object):
        with TemporaryDirectory() as tempdir:
            for p in self.pages:
                self._save_page(self.filepath, p, tempdir)
-            pages = [
+            pages = [os.path.join(tempdir, f"page-{p}.pdf") for p in self.pages]
                os.path.join(tempdir, "page-{0}.pdf".format(p)) for p in self.pages
            ]
            parser = Lattice(**kwargs) if flavor == "lattice" else Stream(**kwargs)
            for p in pages:
                t = parser.extract_tables(
@@ -1,7 +1,5 @@
 # -*- coding: utf-8 -*-
 from __future__ import division
 import cv2
 import numpy as np
@@ -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
@@ -1,6 +1,5 @@
 # -*- coding: utf-8 -*-
 from __future__ import division
 import os
 import sys
 import copy
@@ -212,8 +211,8 @@ class Lattice(BaseParser):
        from ..ext.ghostscript import Ghostscript
        self.imagename = "".join([self.rootname, ".png"])
-        gs_call = "-q -sDEVICE=png16m -o {} -r300 {}".format(
+        gs_call = "-q -sDEVICE=png16m -o {} -r{} {}".format(
-            self.imagename, self.filename
+            self.imagename, self.resolution, self.filename
        )
        gs_call = gs_call.encode().split()
        null = open(os.devnull, "wb")
@@ -1,6 +1,5 @@
 # -*- coding: utf-8 -*-
 from __future__ import division
 import os
 import logging
 import warnings
@@ -66,7 +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
@@ -122,6 +121,7 @@ class Stream(BaseParser):
        row_y = 0
        rows = []
        temp = []
        for t in text:
            # is checking for upright necessary?
            # if t.get_text().strip() and all([obj.upright for obj in t._objs if
@@ -132,8 +132,10 @@ class Stream(BaseParser):
                    temp = []
                    row_y = t.y0
                temp.append(t)
        rows.append(sorted(temp, key=lambda t: t.x0))
-        __ = rows.pop(0)  # TODO: hacky
+        if len(rows) > 1:
            __ = rows.pop(0)  # TODO: hacky
        return rows
    @staticmethod
@@ -346,43 +348,46 @@ class Stream(BaseParser):
        else:
            # calculate mode of the list of number of elements in
            # each row to guess the number of columns
-            ncols = max(set(elements), key=elements.count)
+            if not len(elements):
-            if ncols == 1:
+                cols = [(text_x_min, text_x_max)]
-                # if mode is 1, the page usually contains not tables
+            else:
-                # but there can be cases where the list can be skewed,
+                ncols = max(set(elements), key=elements.count)
-                # try to remove all 1s from list in this case and
+                if ncols == 1:
-                # see if the list contains elements, if yes, then use
+                    # if mode is 1, the page usually contains not tables
-                # the mode after removing 1s
+                    # but there can be cases where the list can be skewed,
-                elements = list(filter(lambda x: x != 1, elements))
+                    # try to remove all 1s from list in this case and
-                if len(elements):
+                    # see if the list contains elements, if yes, then use
-                    ncols = max(set(elements), key=elements.count)
+                    # the mode after removing 1s
-                else:
+                    elements = list(filter(lambda x: x != 1, elements))
-                    warnings.warn(
+                    if len(elements):
-                        "No tables found in table area {}".format(table_idx + 1)
+                        ncols = max(set(elements), key=elements.count)
                    else:
                        warnings.warn(f"No tables found in table area {table_idx + 1}")
                cols = [
                    (t.x0, t.x1) for r in rows_grouped if len(r) == ncols for t in r
                ]
                cols = self._merge_columns(sorted(cols), column_tol=self.column_tol)
                inner_text = []
                for i in range(1, len(cols)):
                    left = cols[i - 1][1]
                    right = cols[i][0]
                    inner_text.extend(
                        [
                            t
                            for direction in self.t_bbox
                            for t in self.t_bbox[direction]
                            if t.x0 > left and t.x1 < right
                        ]
                    )
-            cols = [(t.x0, t.x1) for r in rows_grouped if len(r) == ncols for t in r]
+                outer_text = [
-            cols = self._merge_columns(sorted(cols), column_tol=self.column_tol)
+                    t
-            inner_text = []
+                    for direction in self.t_bbox
-            for i in range(1, len(cols)):
+                    for t in self.t_bbox[direction]
-                left = cols[i - 1][1]
+                    if t.x0 > cols[-1][1] or t.x1 < cols[0][0]
-                right = cols[i][0]
+                ]
-                inner_text.extend(
+                inner_text.extend(outer_text)
-                    [
+                cols = self._add_columns(cols, inner_text, self.row_tol)
-                        t
+                cols = self._join_columns(cols, text_x_min, text_x_max)
                        for direction in self.t_bbox
                        for t in self.t_bbox[direction]
                        if t.x0 > left and t.x1 < right
                    ]
                )
            outer_text = [
                t
                for direction in self.t_bbox
                for t in self.t_bbox[direction]
                if t.x0 > cols[-1][1] or t.x1 < cols[0][0]
            ]
            inner_text.extend(outer_text)
            cols = self._add_columns(cols, inner_text, self.row_tol)
            cols = self._join_columns(cols, text_x_min, text_x_max)
        return cols, rows
@@ -433,19 +438,19 @@ class Stream(BaseParser):
    def extract_tables(self, filename, suppress_stdout=False, layout_kwargs={}):
        self._generate_layout(filename, layout_kwargs)
        base_filename = os.path.basename(self.rootname)
        if not suppress_stdout:
-            logger.info("Processing {}".format(os.path.basename(self.rootname)))
+            logger.info(f"Processing {base_filename}")
        if not self.horizontal_text:
            if self.images:
                warnings.warn(
-                    "{} is image-based, camelot only works on"
+                    f"{base_filename} is image-based, camelot only works on"
-                    " text-based pages.".format(os.path.basename(self.rootname))
+                    " text-based pages."
                )
            else:
-                warnings.warn(
+                warnings.warn(f"No tables found on {base_filename}")
                    "No tables found on {}".format(os.path.basename(self.rootname))
                )
            return []
        self._generate_table_bbox()
@@ -34,16 +34,18 @@ class PlotMethods(object):
            raise ImportError("matplotlib is required for plotting.")
        if table.flavor == "lattice" and kind in ["textedge"]:
-            raise NotImplementedError(
+            raise NotImplementedError(f"Lattice flavor does not support kind='{kind}'")
                "Lattice flavor does not support kind='{}'".format(kind)
            )
        elif table.flavor == "stream" and kind in ["joint", "line"]:
-            raise NotImplementedError(
+            raise NotImplementedError(f"Stream flavor does not support kind='{kind}'")
                "Stream flavor does not support kind='{}'".format(kind)
            )
        plot_method = getattr(self, kind)
-        return plot_method(table)
+        fig = plot_method(table)
        if filename is not None:
            fig.savefig(filename)
            return None
        return fig
    def text(self, table):
        """Generates a plot for all text elements present
@@ -1,9 +1,7 @@
 # -*- coding: utf-8 -*-
 from __future__ import division
 import re
 import os
-import sys
+import re
 import random
 import shutil
 import string
@@ -29,16 +27,9 @@ from pdfminer.layout import (
    LTImage,
 )
-
+from urllib.request import Request, urlopen
-PY3 = sys.version_info[0] >= 3
+from urllib.parse import urlparse as parse_url
-if PY3:
+from urllib.parse import uses_relative, uses_netloc, uses_params
    from urllib.request import urlopen
    from urllib.parse import urlparse as parse_url
    from urllib.parse import uses_relative, uses_netloc, uses_params
 else:
    from urllib2 import urlopen
    from urlparse import urlparse as parse_url
    from urlparse import uses_relative, uses_netloc, uses_params
 _VALID_URLS = set(uses_relative + uses_netloc + uses_params)
@@ -88,13 +79,12 @@ def download_url(url):
        Temporary filepath.
    """
-    filename = "{}.pdf".format(random_string(6))
+    filename = f"{random_string(6)}.pdf"
    with tempfile.NamedTemporaryFile("wb", delete=False) as f:
-        obj = urlopen(url)
+        headers = {"User-Agent": "Mozilla/5.0"}
-        if PY3:
+        request = Request(url, None, headers)
-            content_type = obj.info().get_content_type()
+        obj = urlopen(request)
-        else:
+        content_type = obj.info().get_content_type()
            content_type = obj.info().getheader("Content-Type")
        if content_type != "application/pdf":
            raise NotImplementedError("File format not supported")
        f.write(obj.read())
@@ -123,9 +113,7 @@ def validate_input(kwargs, flavor="lattice"):
        isec = set(parser_kwargs).intersection(set(input_kwargs.keys()))
        if isec:
            raise ValueError(
-                "{} cannot be used with flavor='{}'".format(
+                f"{','.join(sorted(isec))} cannot be used with flavor='{flavor}'"
                    ",".join(sorted(isec)), flavor
                )
            )
    if flavor == "lattice":
@@ -365,7 +353,7 @@ def text_in_bbox(bbox, text):
    Returns
    -------
    t_bbox : list
-        List of PDFMiner text objects that lie inside table.
+        List of PDFMiner text objects that lie inside table, discarding the overlapping ones
    """
    lb = (bbox[0], bbox[1])
@@ -376,7 +364,97 @@ def text_in_bbox(bbox, text):
        if lb[0] - 2 <= (t.x0 + t.x1) / 2.0 <= rt[0] + 2
        and lb[1] - 2 <= (t.y0 + t.y1) / 2.0 <= rt[1] + 2
    ]
-    return t_bbox
+
    # Avoid duplicate text by discarding overlapping boxes
    rest = {t for t in t_bbox}
    for ba in t_bbox:
        for bb in rest.copy():
            if ba == bb:
                continue
            if bbox_intersect(ba, bb):
                # if the intersection is larger than 80% of ba's size, we keep the longest
                if (bbox_intersection_area(ba, bb) / bbox_area(ba)) > 0.8:
                    if bbox_longer(bb, ba):
                        rest.discard(ba)
    unique_boxes = list(rest)
    return unique_boxes
 def bbox_intersection_area(ba, bb) -> float:
    """Returns area of the intersection of the bounding boxes of two PDFMiner objects.
    Parameters
    ----------
    ba : PDFMiner text object
    bb : PDFMiner text object
    Returns
    -------
    intersection_area : float
        Area of the intersection of the bounding boxes of both objects
    """
    x_left = max(ba.x0, bb.x0)
    y_top = min(ba.y1, bb.y1)
    x_right = min(ba.x1, bb.x1)
    y_bottom = max(ba.y0, bb.y0)
    if x_right < x_left or y_bottom > y_top:
        return 0.0
    intersection_area = (x_right - x_left) * (y_top - y_bottom)
    return intersection_area
 def bbox_area(bb) -> float:
    """Returns area of the bounding box of a PDFMiner object.
    Parameters
    ----------
    bb : PDFMiner text object
    Returns
    -------
    area : float
        Area of the bounding box of the object
    """
    return (bb.x1 - bb.x0) * (bb.y1 - bb.y0)
 def bbox_intersect(ba, bb) -> bool:
    """Returns True if the bounding boxes of two PDFMiner objects intersect.
    Parameters
    ----------
    ba : PDFMiner text object
    bb : PDFMiner text object
    Returns
    -------
    overlaps : bool
        True if the bounding boxes intersect
    """
    return ba.x1 >= bb.x0 and bb.x1 >= ba.x0 and ba.y1 >= bb.y0 and bb.y1 >= ba.y0
 def bbox_longer(ba, bb) -> bool:
    """Returns True if the bounding box of the first PDFMiner object is longer or equal to the second.
    Parameters
    ----------
    ba : PDFMiner text object
    bb : PDFMiner text object
    Returns
    -------
    longer : bool
        True if the bounding box of the first object is longer or equal
    """
    return (ba.x1 - ba.x0) >= (bb.x1 - bb.x0)
 def merge_close_lines(ar, line_tol=2):
@@ -423,7 +501,7 @@ def text_strip(text, strip=""):
        return text
    stripped = re.sub(
-        r"[{}]".format("".join(map(re.escape, strip))), "", text, re.UNICODE
+        fr"[{''.join(map(re.escape, strip))}]", "", text, flags=re.UNICODE
    )
    return stripped
@@ -660,9 +738,7 @@ def get_table_index(
                text_range = (t.x0, t.x1)
                col_range = (table.cols[0][0], table.cols[-1][1])
                warnings.warn(
-                    "{} {} does not lie in column range {}".format(
+                    f"{text} {text_range} does not lie in column range {col_range}"
                        text, text_range, col_range
                    )
                )
            r_idx = r
            c_idx = lt_col_overlap.index(max(lt_col_overlap))
@@ -762,23 +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
+    page pdf. To get the definitions of kwargs, see
-    of kwargs.
+    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
@@ -794,11 +874,15 @@ def get_page_layout(
        parser = PDFParser(f)
        document = PDFDocument(parser)
        if not document.is_extractable:
-            raise PDFTextExtractionNotAllowed
+            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,
        )
@@ -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, \
+from pygments.token import (
-     Number, Operator, Generic, Whitespace, Punctuation, Other, Literal
+    Keyword,
    Name,
    Comment,
    String,
    Error,
    Number,
    Operator,
    Generic,
    Whitespace,
    Punctuation,
    Other,
    Literal,
 )
 class FlaskyStyle(Style):
@@ -11,76 +23,67 @@ class FlaskyStyle(Style):
    styles = {
        # No corresponding class for the following:
        # Text:                    "", # class:  ''
-        Whitespace:                "underline #f8f8f8",       # class: 'w'
+        Whitespace: "underline #f8f8f8",  # class: 'w'
-        Error:                     "#a40000 border:#ef2929",  # class: 'err'
+        Error: "#a40000 border:#ef2929",  # class: 'err'
-        Other:                     "#000000",                 # class 'x'
+        Other: "#000000",  # class 'x'
-
+        Comment: "italic #8f5902",  # class: 'c'
-        Comment:                   "italic #8f5902",  # class: 'c'
+        Comment.Preproc: "noitalic",  # class: 'cp'
-        Comment.Preproc:           "noitalic",        # class: 'cp'
+        Keyword: "bold #004461",  # class: 'k'
-
+        Keyword.Constant: "bold #004461",  # class: 'kc'
-        Keyword:                   "bold #004461",    # class: 'k'
+        Keyword.Declaration: "bold #004461",  # class: 'kd'
-        Keyword.Constant:          "bold #004461",    # class: 'kc'
+        Keyword.Namespace: "bold #004461",  # class: 'kn'
-        Keyword.Declaration:       "bold #004461",    # class: 'kd'
+        Keyword.Pseudo: "bold #004461",  # class: 'kp'
-        Keyword.Namespace:         "bold #004461",    # class: 'kn'
+        Keyword.Reserved: "bold #004461",  # class: 'kr'
-        Keyword.Pseudo:            "bold #004461",    # class: 'kp'
+        Keyword.Type: "bold #004461",  # class: 'kt'
-        Keyword.Reserved:          "bold #004461",    # class: 'kr'
+        Operator: "#582800",  # class: 'o'
-        Keyword.Type:              "bold #004461",    # class: 'kt'
+        Operator.Word: "bold #004461",  # class: 'ow' - like keywords
-
+        Punctuation: "bold #000000",  # class: 'p'
        Operator:                  "#582800",   # class: 'o'
        Operator.Word:             "bold #004461",   # class: 'ow' - like keywords
        Punctuation:               "bold #000000",   # class: 'p'
        # because special names such as Name.Class, Name.Function, etc.
        # are not recognized as such later in the parsing, we choose them
        # to look the same as ordinary variables.
-        Name:                      "#000000",         # class: 'n'
+        Name: "#000000",  # class: 'n'
-        Name.Attribute:            "#c4a000",         # class: 'na' - to be revised
+        Name.Attribute: "#c4a000",  # class: 'na' - to be revised
-        Name.Builtin:              "#004461",         # class: 'nb'
+        Name.Builtin: "#004461",  # class: 'nb'
-        Name.Builtin.Pseudo:       "#3465a4",         # class: 'bp'
+        Name.Builtin.Pseudo: "#3465a4",  # class: 'bp'
-        Name.Class:                "#000000",         # class: 'nc' - to be revised
+        Name.Class: "#000000",  # class: 'nc' - to be revised
-        Name.Constant:             "#000000",         # class: 'no' - to be revised
+        Name.Constant: "#000000",  # class: 'no' - to be revised
-        Name.Decorator:            "#888",            # class: 'nd' - to be revised
+        Name.Decorator: "#888",  # class: 'nd' - to be revised
-        Name.Entity:               "#ce5c00",         # class: 'ni'
+        Name.Entity: "#ce5c00",  # class: 'ni'
-        Name.Exception:            "bold #cc0000",    # class: 'ne'
+        Name.Exception: "bold #cc0000",  # class: 'ne'
-        Name.Function:             "#000000",         # class: 'nf'
+        Name.Function: "#000000",  # class: 'nf'
-        Name.Property:             "#000000",         # class: 'py'
+        Name.Property: "#000000",  # class: 'py'
-        Name.Label:                "#f57900",         # class: 'nl'
+        Name.Label: "#f57900",  # class: 'nl'
-        Name.Namespace:            "#000000",         # class: 'nn' - to be revised
+        Name.Namespace: "#000000",  # class: 'nn' - to be revised
-        Name.Other:                "#000000",         # class: 'nx'
+        Name.Other: "#000000",  # class: 'nx'
-        Name.Tag:                  "bold #004461",    # class: 'nt' - like a keyword
+        Name.Tag: "bold #004461",  # class: 'nt' - like a keyword
-        Name.Variable:             "#000000",         # class: 'nv' - to be revised
+        Name.Variable: "#000000",  # class: 'nv' - to be revised
-        Name.Variable.Class:       "#000000",         # class: 'vc' - to be revised
+        Name.Variable.Class: "#000000",  # class: 'vc' - to be revised
-        Name.Variable.Global:      "#000000",         # class: 'vg' - to be revised
+        Name.Variable.Global: "#000000",  # class: 'vg' - to be revised
-        Name.Variable.Instance:    "#000000",         # class: 'vi' - to be revised
+        Name.Variable.Instance: "#000000",  # class: 'vi' - to be revised
-
+        Number: "#990000",  # class: 'm'
-        Number:                    "#990000",         # class: 'm'
+        Literal: "#000000",  # class: 'l'
-
+        Literal.Date: "#000000",  # class: 'ld'
-        Literal:                   "#000000",         # class: 'l'
+        String: "#4e9a06",  # class: 's'
-        Literal.Date:              "#000000",         # class: 'ld'
+        String.Backtick: "#4e9a06",  # class: 'sb'
-
+        String.Char: "#4e9a06",  # class: 'sc'
-        String:                    "#4e9a06",         # class: 's'
+        String.Doc: "italic #8f5902",  # class: 'sd' - like a comment
-        String.Backtick:           "#4e9a06",         # class: 'sb'
+        String.Double: "#4e9a06",  # class: 's2'
-        String.Char:               "#4e9a06",         # class: 'sc'
+        String.Escape: "#4e9a06",  # class: 'se'
-        String.Doc:                "italic #8f5902",  # class: 'sd' - like a comment
+        String.Heredoc: "#4e9a06",  # class: 'sh'
-        String.Double:             "#4e9a06",         # class: 's2'
+        String.Interpol: "#4e9a06",  # class: 'si'
-        String.Escape:             "#4e9a06",         # class: 'se'
+        String.Other: "#4e9a06",  # class: 'sx'
-        String.Heredoc:            "#4e9a06",         # class: 'sh'
+        String.Regex: "#4e9a06",  # class: 'sr'
-        String.Interpol:           "#4e9a06",         # class: 'si'
+        String.Single: "#4e9a06",  # class: 's1'
-        String.Other:              "#4e9a06",         # class: 'sx'
+        String.Symbol: "#4e9a06",  # class: 'ss'
-        String.Regex:              "#4e9a06",         # class: 'sr'
+        Generic: "#000000",  # class: 'g'
-        String.Single:             "#4e9a06",         # class: 's1'
+        Generic.Deleted: "#a40000",  # class: 'gd'
-        String.Symbol:             "#4e9a06",         # class: 'ss'
+        Generic.Emph: "italic #000000",  # class: 'ge'
-
+        Generic.Error: "#ef2929",  # class: 'gr'
-        Generic:                   "#000000",         # class: 'g'
+        Generic.Heading: "bold #000080",  # class: 'gh'
-        Generic.Deleted:           "#a40000",         # class: 'gd'
+        Generic.Inserted: "#00A000",  # class: 'gi'
-        Generic.Emph:              "italic #000000",  # class: 'ge'
+        Generic.Output: "#888",  # class: 'go'
-        Generic.Error:             "#ef2929",         # class: 'gr'
+        Generic.Prompt: "#745334",  # class: 'gp'
-        Generic.Heading:           "bold #000080",    # class: 'gh'
+        Generic.Strong: "bold #000000",  # class: 'gs'
-        Generic.Inserted:          "#00A000",         # class: 'gi'
+        Generic.Subheading: "bold #800080",  # class: 'gu'
-        Generic.Output:            "#888",            # class: 'go'
+        Generic.Traceback: "bold #a40000",  # class: 'gt'
        Generic.Prompt:            "#745334",         # class: 'gp'
        Generic.Strong:            "bold #000000",    # class: 'gs'
        Generic.Subheading:        "bold #800080",    # class: 'gu'
        Generic.Traceback:         "bold #a40000",    # class: 'gt'
    }
@@ -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(".."))
-sys.path.insert(0, os.path.abspath('_themes'))
+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.autodoc",
-    'sphinx.ext.napoleon',
+    "sphinx.ext.napoleon",
-    'sphinx.ext.intersphinx',
+    "sphinx.ext.intersphinx",
-    'sphinx.ext.todo',
+    "sphinx.ext.todo",
-    'sphinx.ext.viewcode',
+    "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'
+project = u"Camelot"
-copyright = u'2019, Camelot Developers'
+copyright = u"2021, Camelot Developers"
-author = u'Vinayak Mehta'
+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,
+    "show_powered_by": False,
-    'github_user': 'camelot-dev',
+    "github_user": "camelot-dev",
-    'github_repo': 'camelot',
+    "github_repo": "camelot",
-    'github_banner': True,
+    "github_banner": True,
-    'show_related': False,
+    "show_related": False,
-    'note_bg': '#FFF59C'
+    "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',
+    "index": [
-              'searchbox.html', 'hacks.html'],
+        "sidebarintro.html",
-    '**': ['sidebarlogo.html', 'localtoc.html', 'relations.html',
+        "relations.html",
-           'sourcelink.html', 'searchbox.html', 'hacks.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
@@ -249,34 +260,30 @@ html_show_copyright = True
 # html_search_scorer = 'scorer.js'
 # Output file base name for HTML help builder.
-htmlhelp_basename = 'Camelotdoc'
+htmlhelp_basename = "Camelotdoc"
 # -- Options for LaTeX output ---------------------------------------------
 latex_elements = {
-     # The paper size ('letterpaper' or 'a4paper').
+    # The paper size ('letterpaper' or 'a4paper').
-     #
+    #
-     # 'papersize': 'letterpaper',
+    # 'papersize': 'letterpaper',
-
+    # The font size ('10pt', '11pt' or '12pt').
-     # The font size ('10pt', '11pt' or '12pt').
+    #
-     #
+    # 'pointsize': '10pt',
-     # 'pointsize': '10pt',
+    # Additional stuff for the LaTeX preamble.
-
+    #
-     # Additional stuff for the LaTeX preamble.
+    # 'preamble': '',
-     #
+    # Latex figure (float) alignment
-     # 'preamble': '',
+    #
-
+    # 'figure_align': 'htbp',
     # Latex figure (float) alignment
     #
     # 'figure_align': 'htbp',
 }
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, 'Camelot.tex', u'Camelot Documentation',
+    (master_doc, "Camelot.tex", u"Camelot Documentation", u"Vinayak Mehta", "manual"),
     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 = [
+man_pages = [(master_doc, "Camelot", u"Camelot Documentation", [author], 1)]
    (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.',
+        master_doc,
-     'Miscellaneous'),
+        "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,
+    "https://docs.python.org/2": None,
-    'http://pandas.pydata.org/pandas-docs/stable': None
+    "http://pandas.pydata.org/pandas-docs/stable": None,
 }
@@ -37,7 +37,7 @@ Setting up a development environment
 To install the dependencies needed for development, you can use pip::
-    $ pip install camelot-py[dev]
+    $ pip install "camelot-py[dev]"
 Alternatively, you can clone the project repository, and install using pip::
@@ -33,15 +33,18 @@ Release v\ |version|. (:ref:`Installation <install>`)
 .. image:: https://img.shields.io/badge/code%20style-black-000000.svg
    :target: https://github.com/ambv/black
-**Camelot** is a Python library that makes it easy for *anyone* to extract tables from PDF files!
+.. image:: https://img.shields.io/badge/continous%20quality-deepsource-lightgrey
    :target: https://deepsource.io/gh/camelot-dev/camelot/?ref=repository-badge
-.. note:: You can also check out `Excalibur`_, which is a web interface for Camelot!
+**Camelot** is a Python library that can help you extract tables from PDFs!
 .. note:: You can also check out `Excalibur`_, the web interface to Camelot!
 .. _Excalibur: https://github.com/camelot-dev/excalibur
 ----
-**Here's how you can extract tables from PDF files.** Check out the PDF used in this example `here`_.
+**Here's how you can extract tables from PDFs.** You can check out the PDF used in this example `here`_.
 .. _here: _static/pdf/foo.pdf
@@ -67,7 +70,7 @@ Release v\ |version|. (:ref:`Installation <install>`)
 .. csv-table::
  :file: _static/csv/foo.csv
-There's a :ref:`command-line interface <cli>` too!
+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".)
@@ -76,27 +79,27 @@ There's a :ref:`command-line interface <cli>` too!
 Why Camelot?
 ------------
- **You are in control.** Unlike other libraries and tools which either give a nice output or fail miserably (with no in-between), Camelot gives you the power to tweak table extraction. (This is important since everything in the real world, including PDF table extraction, is fuzzy.)
+- **Configurability**: Camelot gives you control over the table extraction process with its :ref:`tweakable settings <advanced>`.
- *Bad* tables can be discarded based on **metrics** like accuracy and whitespace, without ever having to manually look at each table.
+- **Metrics**: Bad tables can be discarded based on metrics like accuracy and whitespace, without having to manually look at each table.
- Each table is a **pandas DataFrame**, which seamlessly integrates into `ETL and data analysis workflows`_.
+- **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.
 - **Export** to multiple formats, including JSON, Excel and HTML.
 See `comparison with other PDF table extraction libraries and tools`_.
 .. _ETL and data analysis workflows: https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873
 .. _comparison with other PDF table extraction libraries and tools: https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools
-Support us on OpenCollective
+See `comparison with similar libraries and tools`_.
 ----------------------------
-If Camelot helped you extract tables from PDFs, please consider supporting its development by `becoming a backer or a sponsor on OpenCollective`_!
+.. _comparison with similar libraries and tools: https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools
-.. _becoming a backer or a sponsor on OpenCollective: https://opencollective.com/camelot
+Support the development
 -----------------------
 If Camelot has helped you, please consider supporting its development with a one-time or monthly donation `on OpenCollective`_!
 .. _on OpenCollective: https://opencollective.com/camelot
 The User Guide
 --------------
-This part of the documentation begins with some background information about why Camelot was created, takes a small dip into the implementation details and then focuses on step-by-step instructions for getting the most out of Camelot.
+This part of the documentation begins with some background information about why Camelot was created, takes you through some implementation details, and then focuses on step-by-step instructions for getting the most out of Camelot.
 .. toctree::
   :maxdepth: 2
@@ -112,8 +115,7 @@ This part of the documentation begins with some background information about why
 The API Documentation/Guide
 ---------------------------
-If you are looking for information on a specific function, class, or method,
+If you are looking for information on a specific function, class, or method, this part of the documentation is for you.
 this part of the documentation is for you.
 .. toctree::
   :maxdepth: 2
@@ -123,8 +125,7 @@ this part of the documentation is for you.
 The Contributor Guide
 ---------------------
-If you want to contribute to the project, this part of the documentation is for
+If you want to contribute to the project, this part of the documentation is for you.
 you.
 .. toctree::
   :maxdepth: 2
@@ -66,8 +66,7 @@ Let's plot all the text present on the table's PDF page.
 ::
-    >>> camelot.plot(tables[0], kind='text')
+    >>> camelot.plot(tables[0], kind='text').show()
    >>> plt.show()
 .. tip::
    Here's how you can do the same with the :ref:`command-line interface <cli>`.
@@ -93,8 +92,7 @@ Let's plot the table (to see if it was detected correctly or not). This plot typ
 ::
-    >>> camelot.plot(tables[0], kind='grid')
+    >>> camelot.plot(tables[0], kind='grid').show()
    >>> plt.show()
 .. tip::
    Here's how you can do the same with the :ref:`command-line interface <cli>`.
@@ -118,8 +116,7 @@ Now, let's plot all table boundaries present on the table's PDF page.
 ::
-    >>> camelot.plot(tables[0], kind='contour')
+    >>> camelot.plot(tables[0], kind='contour').show()
    >>> plt.show()
 .. tip::
    Here's how you can do the same with the :ref:`command-line interface <cli>`.
@@ -141,8 +138,7 @@ Cool, let's plot all line segments present on the table's PDF page.
 ::
-    >>> camelot.plot(tables[0], kind='line')
+    >>> camelot.plot(tables[0], kind='line').show()
    >>> plt.show()
 .. tip::
    Here's how you can do the same with the :ref:`command-line interface <cli>`.
@@ -164,8 +160,7 @@ Finally, let's plot all line intersections present on the table's PDF page.
 ::
-    >>> camelot.plot(tables[0], kind='joint')
+    >>> camelot.plot(tables[0], kind='joint').show()
    >>> plt.show()
 .. tip::
    Here's how you can do the same with the :ref:`command-line interface <cli>`.
@@ -187,8 +182,7 @@ You can also visualize the textedges found on a page by specifying ``kind='texte
 ::
-    >>> camelot.plot(tables[0], kind='textedge')
+    >>> camelot.plot(tables[0], kind='textedge').show()
    >>> plt.show()
 .. tip::
    Here's how you can do the same with the :ref:`command-line interface <cli>`.
@@ -375,8 +369,7 @@ Let's see the table area that is detected by default.
 ::
    >>> tables = camelot.read_pdf('edge_tol.pdf', flavor='stream')
-    >>> camelot.plot(tables[0], kind='contour')
+    >>> camelot.plot(tables[0], kind='contour').show()
    >>> plt.show()
 .. tip::
    Here's how you can do the same with the :ref:`command-line interface <cli>`.
@@ -396,8 +389,7 @@ To improve the detected area, you can increase the ``edge_tol`` (default: 50) va
 ::
    >>> tables = camelot.read_pdf('edge_tol.pdf', flavor='stream', edge_tol=500)
-    >>> camelot.plot(tables[0], kind='contour')
+    >>> camelot.plot(tables[0], kind='contour').show()
    >>> plt.show()
 .. tip::
    Here's how you can do the same with the :ref:`command-line interface <cli>`.
@@ -472,8 +464,7 @@ Let's plot the table for this PDF.
 ::
    >>> tables = camelot.read_pdf('short_lines.pdf')
-    >>> camelot.plot(tables[0], kind='grid')
+    >>> camelot.plot(tables[0], kind='grid').show()
    >>> plt.show()
 .. figure:: ../_static/png/short_lines_1.png
    :alt: A plot of the PDF table with short lines
@@ -484,8 +475,7 @@ Clearly, the smaller lines separating the headers, couldn't be detected. Let's t
 ::
    >>> tables = camelot.read_pdf('short_lines.pdf', line_scale=40)
-    >>> camelot.plot(tables[0], kind='grid')
+    >>> camelot.plot(tables[0], kind='grid').show()
    >>> plt.show()
 .. tip::
    Here's how you can do the same with the :ref:`command-line interface <cli>`.
@@ -628,7 +618,7 @@ 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>`_.
 ::
@@ -16,11 +16,11 @@ Stream can be used to parse tables that have whitespaces between cells to simula
 1. Words on the PDF page are grouped into text rows based on their *y* axis overlaps.
-2. Textedges are calculated and then used to guess interesting table areas on the PDF page. You can read `Anssi Nurminen's master's thesis <http://dspace.cc.tut.fi/dpub/bitstream/handle/123456789/21520/Nurminen.pdf?sequence=3>`_ to know more about this table detection technique. [See pages 20, 35 and 40]
+2. Textedges are calculated and then used to guess interesting table areas on the PDF page. You can read `Anssi Nurminen's master's thesis <https://pdfs.semanticscholar.org/a9b1/67a86fb189bfcd366c3839f33f0404db9c10.pdf>`_ to know more about this table detection technique. [See pages 20, 35 and 40]
 3. The number of columns inside each table area are then guessed. This is done by calculating the mode of number of words in each text row. Based on this mode, words in each text row are chosen to calculate a list of column *x* ranges.
-4. Words that lie inside/outside the current column *x* ranges are then used to extend extend the current list of columns.
+4. Words that lie inside/outside the current column *x* ranges are then used to extend the current list of columns.
 5. Finally, a table is formed using the text rows' *y* ranges and column *x* ranges and words found on the page are assigned to the table's cells based on their *x* and *y* coordinates.
@@ -3,72 +3,59 @@
 Installation of dependencies
 ============================
-The dependencies `Tkinter`_ and `ghostscript`_ can be installed using your system's package manager. You can run one of the following, based on your OS.
+The dependencies `Ghostscript <https://www.ghostscript.com>`_ and `Tkinter <https://wiki.python.org/moin/TkInter>`_ can be installed using your system's package manager or by running their installer.
 .. _Tkinter: https://wiki.python.org/moin/TkInter
 .. _ghostscript: https://www.ghostscript.com
 OS-specific instructions
 ------------------------
-For Ubuntu
+Ubuntu
-^^^^^^^^^^
+^^^^^^
 ::
-    $ apt install python-tk ghostscript
+    $ apt install ghostscript python3-tk
-Or for Python 3::
+MacOS
-
+^^^^^
    $ apt install python3-tk ghostscript
 For macOS
 ^^^^^^^^^
 ::
-    $ brew install tcl-tk ghostscript
+    $ brew install ghostscript tcl-tk
-For Windows
+Windows
-^^^^^^^^^^^
+^^^^^^^
-For Tkinter, you can download the `ActiveTcl Community Edition`_ from ActiveState. For ghostscript, you can get the installer at the `ghostscript downloads page`_.
+For Ghostscript, you can get the installer at their `downloads page <https://www.ghostscript.com/download/gsdnld.html>`_. And for Tkinter, you can download the `ActiveTcl Community Edition <https://www.activestate.com/activetcl/downloads>`_ from ActiveState.
-.. _ActiveTcl Community Edition: https://www.activestate.com/activetcl/downloads
+Checks to see if dependencies are installed correctly
-.. _ghostscript downloads page: https://www.ghostscript.com/download/gsdnld.html
+-----------------------------------------------------
 .. _as shown here: https://java.com/en/download/help/path.xml
-Checks to see if dependencies were installed correctly
+You can run the following checks to see if the dependencies were installed correctly.
 ------------------------------------------------------
-You can do the following checks to see if the dependencies were installed correctly.
+For Ghostscript
 ^^^^^^^^^^^^^^^
 Open the Python REPL and run the following:
 For Ubuntu/MacOS::
    >>> from ctypes.util import find_library
    >>> find_library("gs")
    "libgs.so.9"
 For Windows::
    >>> from ctypes.util import find_library
    >>> find_library("".join(("gsdll", str(ctypes.sizeof(ctypes.c_voidp) * 8), ".dll"))
    <name-of-ghostscript-library-on-windows>
 **Check:** The output of the ``find_library`` function should not be empty.
 If the output is empty, then it's possible that the Ghostscript library is not available one of the ``LD_LIBRARY_PATH``/``DYLD_LIBRARY_PATH``/``PATH`` variables depending on your operating system. In this case, you may have to modify one of those path variables.
 For Tkinter
 ^^^^^^^^^^^
-Launch Python, and then at the prompt, type::
+Launch Python and then import Tkinter::
    >>> import Tkinter
 Or in Python 3::
    >>> import tkinter
-If you have Tkinter, Python will not print an error message, and if not, you will see an ``ImportError``.
+**Check:** Importing ``tkinter`` should not raise an import error.
 For ghostscript
 ^^^^^^^^^^^^^^^
 Run the following to check the ghostscript version.
 For Ubuntu/macOS::
    $ gs -version
 For Windows::
    C:\> gswin64c.exe -version
 Or for Windows 32-bit::
    C:\> gswin32c.exe -version
 If you have ghostscript, you should see the ghostscript version and copyright information.
@@ -5,42 +5,35 @@ Installation of Camelot
 This part of the documentation covers the steps to install Camelot.
-Using conda
+After :ref:`installing the dependencies <install_deps>`, which include `Ghostscript <https://www.ghostscript.com>`_ and `Tkinter <https://wiki.python.org/moin/TkInter>`_, you can use one of the following methods to install Camelot:
 -----------
-The easiest way to install Camelot is to install it with `conda`_, which is a package manager and environment management system for the `Anaconda`_ distribution.
+.. warning:: The ``lattice`` flavor will fail to run if Ghostscript is not installed. You may run into errors as shown in `issue #193 <https://github.com/camelot-dev/camelot/issues/193>`_.
-::
+
 pip
 ---
 To install Camelot from PyPI using ``pip``, please include the extra ``cv`` requirement as shown::
    $ pip install "camelot-py[cv]"
 conda
 -----
 `conda`_ is a package manager and environment management system for the `Anaconda <https://anaconda.org>`_ distribution. It can be used to install Camelot from the ``conda-forge`` channel::
    $ conda install -c conda-forge camelot-py
 .. note:: Camelot is available for Python 2.7, 3.5, 3.6 and 3.7 on Linux, macOS and Windows. For Windows, you will need to install ghostscript which you can get from their `downloads page`_.
 .. _conda: https://conda.io/docs/
 .. _Anaconda: http://docs.continuum.io/anaconda/
 .. _downloads page: https://www.ghostscript.com/download/gsdnld.html
 .. _conda-forge: https://conda-forge.org/
 Using pip
 ---------
 After :ref:`installing the dependencies <install_deps>`, which include `Tkinter`_ and `ghostscript`_, you can simply use pip to install Camelot::
    $ pip install camelot-py[cv]
 .. _Tkinter: https://wiki.python.org/moin/TkInter
 .. _ghostscript: https://www.ghostscript.com
 From the source code
 --------------------
-After :ref:`installing the dependencies <install_deps>`, you can install from the source by:
+After :ref:`installing the dependencies <install_deps>`, you can install Camelot from source by:
 1. Cloning the GitHub repository.
 ::
    $ git clone https://www.github.com/camelot-dev/camelot
-2. Then simply using pip again.
+2. And then simply using pip again.
 ::
    $ cd camelot
@@ -1,8 +0,0 @@
 click>=6.7
 matplotlib>=2.2.3
 numpy>=1.13.3
 opencv-python>=3.4.2.17
 openpyxl>=2.5.8
 pandas>=0.23.4
 pdfminer.six>=20170720
 PyPDF2>=1.26.0
@@ -6,38 +6,36 @@ 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',
+    "chardet>=3.0.4",
-    'click>=6.7',
+    "click>=6.7",
-    'numpy>=1.13.3',
+    "numpy>=1.13.3",
-    'openpyxl>=2.5.8',
+    "openpyxl>=2.5.8",
-    'pandas>=0.23.4',
+    "pandas>=0.23.4",
-    'pdfminer.six>=20170720',
+    "pdfminer.six>=20200726",
-    'PyPDF2>=1.26.0'
+    "PyPDF2>=1.26.0",
 ]
-cv_requires = [
+cv_requires = ["opencv-python>=3.4.2.17"]
    'opencv-python>=3.4.2.17'
 ]
 plot_requires = [
-    'matplotlib>=2.2.3',
+    "matplotlib>=2.2.3",
 ]
 dev_requires = [
-    'codecov>=2.0.15',
+    "codecov>=2.0.15",
-    'pytest>=3.8.0',
+    "pytest>=5.4.3",
-    'pytest-cov>=2.6.0',
+    "pytest-cov>=2.10.0",
-    'pytest-mpl>=0.10',
+    "pytest-mpl>=0.11",
-    'pytest-runner>=4.2',
+    "pytest-runner>=5.2",
-    'Sphinx>=1.7.9'
+    "Sphinx>=3.1.2",
 ]
 all_requires = cv_requires + plot_requires
@@ -45,37 +43,39 @@ dev_requires = dev_requires + all_requires
 def setup_package():
-    metadata = dict(name=about['__title__'],
+    metadata = dict(
-                    version=about['__version__'],
+        name=about["__title__"],
-                    description=about['__description__'],
+        version=about["__version__"],
-                    long_description=readme,
+        description=about["__description__"],
-                    long_description_content_type="text/markdown",
+        long_description=readme,
-                    url=about['__url__'],
+        long_description_content_type="text/markdown",
-                    author=about['__author__'],
+        url=about["__url__"],
-                    author_email=about['__author_email__'],
+        author=about["__author__"],
-                    license=about['__license__'],
+        author_email=about["__author_email__"],
-                    packages=find_packages(exclude=('tests',)),
+        license=about["__license__"],
-                    install_requires=requires,
+        packages=find_packages(exclude=("tests",)),
-                    extras_require={
+        install_requires=requires,
-                        'all': all_requires,
+        extras_require={
-                        'cv': cv_requires,
+            "all": all_requires,
-                        'dev': dev_requires,
+            "cv": cv_requires,
-                        'plot': plot_requires
+            "dev": dev_requires,
-                    },
+            "plot": plot_requires,
-                    entry_points={
+        },
-                        'console_scripts': [
+        entry_points={
-                            'camelot = camelot.cli:cli',
+            "console_scripts": [
-                        ],
+                "camelot = camelot.cli:cli",
-                    },
+            ],
-                    classifiers=[
+        },
-                        # Trove classifiers
+        classifiers=[
-                        # Full list: https://pypi.python.org/pypi?%3Aaction=list_classifiers
+            # Trove classifiers
-                        'License :: OSI Approved :: MIT License',
+            # Full list: https://pypi.python.org/pypi?%3Aaction=list_classifiers
-                        'Programming Language :: Python :: 2.7',
+            "License :: OSI Approved :: MIT License",
-                        'Programming Language :: Python :: 3.5',
+            "Programming Language :: Python :: 3.6",
-                        'Programming Language :: Python :: 3.6',
+            "Programming Language :: Python :: 3.7",
-                        'Programming Language :: Python :: 3.7'
+            "Programming Language :: Python :: 3.8",
-                    ])
+            "Programming Language :: Python :: 3.9",
        ],
    )
    try:
        from setuptools import setup
@@ -85,5 +85,5 @@ def setup_package():
    setup(**metadata)
-if __name__ == '__main__':
+if __name__ == "__main__":
    setup_package()
@@ -1,2 +1,3 @@
 import matplotlib
-matplotlib.use('agg')
+
 matplotlib.use("agg")
@@ -1,19 +1,7 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 data_stream = [
    [
        "",
        "Table: 5            Public Health Outlay 2012-13 (Budget Estimates)        (Rs. in 000)",
        "",
        "",
        "",
        "",
        "",
        "",
    ],
    ["States-A", "Revenue", "", "Capital", "", "Total", "Others(1)", "Total"],
    ["", "", "", "", "", "Revenue &", "", ""],
    ["", "Medical &", "Family", "Medical &", "Family", "", "", ""],
@@ -829,18 +817,6 @@ data_stream_table_rotated = [
 ]
 data_stream_two_tables_1 = [
    [
        "[In thousands (11,062.6 represents 11,062,600) For year ending December 31. Based on Uniform Crime Reporting (UCR)",
        "",
        "",
        "",
        "",
        "",
        "",
        "",
        "",
        "",
    ],
    [
        "Program. Represents arrests reported (not charged) by 12,910 agencies with a total population of 247,526,916 as estimated",
        "",
@@ -915,7 +891,7 @@ data_stream_two_tables_1 = [
        "2,330 .9",
    ],
    [
-        "Violent crime  .  .  .  .  .  .  .  .\n .  .\n .  .\n .  .\n .  .\n .  .",
+        "Violent crime   .  .  .  .  .  .  .  .\n .  .\n .  .\n .  .\n .  .\n .  .",
        "467 .9",
        "69 .1",
        "398 .8",
@@ -1300,29 +1276,10 @@ data_stream_two_tables_1 = [
        "",
        "",
    ],
    [
        "",
        "Source: U.S. Department of Justice, Federal Bureau of Investigation, Uniform Crime Reports, Arrests Master Files.",
        "",
        "",
        "",
        "",
        "",
        "",
        "",
        "",
    ],
 ]
 data_stream_two_tables_2 = [
    [
        "",
        "Source: U.S. Department of Justice, Federal Bureau of Investigation, Uniform Crime Reports, Arrests Master Files.",
        "",
        "",
        "",
        "",
    ],
    ["Table 325. Arrests by Race: 2009", "", "", "", "", ""],
    [
        "[Based on Uniform Crime Reporting (UCR) Program. Represents arrests reported (not charged) by 12,371 agencies",
@@ -1352,7 +1309,7 @@ data_stream_two_tables_2 = [
        "123,656",
    ],
    [
-        "Violent crime  .  .  .  .  .  .  .  .\n .  .\n .  .\n .  .\n .  .\n .\n .\n .  .\n .  .\n .\n .\n .\n .\n .  .",
+        "Violent crime   .  .  .  .  .  .  .  .\n .  .\n .  .\n .  .\n .  .\n .\n .\n .  .\n .  .\n .\n .\n .\n .\n .  .",
        "456,965",
        "268,346",
        "177,766",
@@ -1600,16 +1557,9 @@ data_stream_two_tables_2 = [
        "3,950",
    ],
    ["1 Except forcible rape and prostitution.", "", "", "", "", ""],
    [
        "",
        "Source: U.S. Department of Justice, Federal Bureau of Investigation, “Crime in the United States, Arrests,” September 2010,",
        "",
        "",
        "",
        "",
    ],
 ]
 data_stream_table_areas = [
    ["", "One Withholding"],
    ["Payroll Period", "Allowance"],
@@ -1776,18 +1726,7 @@ data_stream_columns = [
 ]
 data_stream_split_text = [
-    [
+    ["FEB", "RUAR", "Y 2014 M27 (BUS)", "", "", "", "", "", "", ""],
        "FEB",
        "RUAR",
        "Y 2014 M27 (BUS)",
        "",
        "ALPHABETIC LISTING BY T",
        "YPE",
        "",
        "",
        "",
        "ABLPDM27",
    ],
    ["", "", "", "", "OF ACTIVE LICENSES", "", "", "", "", "3/19/2014"],
    ["", "", "", "", "OKLAHOMA ABLE COMMIS", "SION", "", "", "", ""],
    ["LICENSE", "", "", "", "PREMISE", "", "", "", "", ""],
@@ -2121,6 +2060,7 @@ data_stream_split_text = [
    ],
 ]
 data_stream_flag_size = [
    [
        "States",
@@ -2820,7 +2760,7 @@ data_arabic = [
 ]
 data_stream_layout_kwargs = [
-    ["V i n s   a u   Ve r r e", ""],
+    ["V i n s   a u   V e r r e", ""],
    ["Les Blancs", "12.5CL"],
    ["A.O.P Côtes du Rhône", ""],
    ["Domaine de la Guicharde «  Autour de la chapelle » 2016", "8 €"],
@@ -2858,3 +2798,469 @@ data_stream_layout_kwargs = [
    ["A.O.P Cornas", ""],
    ["Domaine Lionnet « Terre Brûlée » 2012", "15 €"],
 ]
 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"],
 ]
@@ -114,31 +114,35 @@ def test_cli_password():
 def test_cli_output_format():
    with TemporaryDirectory() as tempdir:
        infile = os.path.join(testdir, "health.pdf")
-        outfile = os.path.join(tempdir, "health.{}")
+
        runner = CliRunner()
        # json
        outfile = os.path.join(tempdir, "health.json")
        result = runner.invoke(
            cli,
-            ["--format", "json", "--output", outfile.format("json"), "stream", infile],
+            ["--format", "json", "--output", outfile, "stream", infile],
        )
        assert result.exit_code == 0
        # excel
        outfile = os.path.join(tempdir, "health.xlsx")
        result = runner.invoke(
            cli,
-            ["--format", "excel", "--output", outfile.format("xlsx"), "stream", infile],
+            ["--format", "excel", "--output", outfile, "stream", infile],
        )
        assert result.exit_code == 0
        # html
        outfile = os.path.join(tempdir, "health.html")
        result = runner.invoke(
            cli,
-            ["--format", "html", "--output", outfile.format("html"), "stream", infile],
+            ["--format", "html", "--output", outfile, "stream", infile],
        )
        assert result.exit_code == 0
        # zip
        outfile = os.path.join(tempdir, "health.csv")
        result = runner.invoke(
            cli,
            [
@@ -146,7 +150,7 @@ def test_cli_output_format():
                "--format",
                "csv",
                "--output",
-                outfile.format("csv"),
+                outfile,
                "stream",
                infile,
            ],
@@ -156,8 +160,8 @@ def test_cli_output_format():
 def test_cli_quiet():
    with TemporaryDirectory() as tempdir:
-        infile = os.path.join(testdir, "blank.pdf")
+        infile = os.path.join(testdir, "empty.pdf")
-        outfile = os.path.join(tempdir, "blank.csv")
+        outfile = os.path.join(tempdir, "empty.csv")
        runner = CliRunner()
        result = runner.invoke(
@@ -3,9 +3,11 @@
 import os
 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 *
@@ -26,10 +28,10 @@ def test_password():
    filename = os.path.join(testdir, "health_protected.pdf")
    tables = camelot.read_pdf(filename, password="ownerpass", flavor="stream")
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
    tables = camelot.read_pdf(filename, password="userpass", flavor="stream")
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_stream():
@@ -37,7 +39,7 @@ def test_stream():
    filename = os.path.join(testdir, "health.pdf")
    tables = camelot.read_pdf(filename, flavor="stream")
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_stream_table_rotated():
@@ -45,11 +47,11 @@ def test_stream_table_rotated():
    filename = os.path.join(testdir, "clockwise_table_2.pdf")
    tables = camelot.read_pdf(filename, flavor="stream")
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
    filename = os.path.join(testdir, "anticlockwise_table_2.pdf")
    tables = camelot.read_pdf(filename, flavor="stream")
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_stream_two_tables():
@@ -71,7 +73,7 @@ def test_stream_table_regions():
    tables = camelot.read_pdf(
        filename, flavor="stream", table_regions=["320,460,573,335"]
    )
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_stream_table_areas():
@@ -81,7 +83,7 @@ def test_stream_table_areas():
    tables = camelot.read_pdf(
        filename, flavor="stream", table_areas=["320,500,573,335"]
    )
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_stream_columns():
@@ -91,7 +93,7 @@ def test_stream_columns():
    tables = camelot.read_pdf(
        filename, flavor="stream", columns=["67,180,230,425,475"], row_tol=10
    )
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_stream_split_text():
@@ -104,7 +106,7 @@ def test_stream_split_text():
        columns=["72,95,209,327,442,529,566,606,683"],
        split_text=True,
    )
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_stream_flag_size():
@@ -112,7 +114,7 @@ def test_stream_flag_size():
    filename = os.path.join(testdir, "superscript.pdf")
    tables = camelot.read_pdf(filename, flavor="stream", flag_size=True)
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_stream_strip_text():
@@ -120,7 +122,7 @@ def test_stream_strip_text():
    filename = os.path.join(testdir, "detect_vertical_false.pdf")
    tables = camelot.read_pdf(filename, flavor="stream", strip_text=" ,\n")
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_stream_edge_tol():
@@ -128,7 +130,7 @@ def test_stream_edge_tol():
    filename = os.path.join(testdir, "edge_tol.pdf")
    tables = camelot.read_pdf(filename, flavor="stream", edge_tol=500)
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_stream_layout_kwargs():
@@ -138,7 +140,7 @@ def test_stream_layout_kwargs():
    tables = camelot.read_pdf(
        filename, flavor="stream", layout_kwargs={"detect_vertical": False}
    )
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_lattice():
@@ -148,7 +150,7 @@ def test_lattice():
        testdir, "tabula/icdar2013-dataset/competition-dataset-us/us-030.pdf"
    )
    tables = camelot.read_pdf(filename, pages="2")
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_lattice_table_rotated():
@@ -156,11 +158,11 @@ def test_lattice_table_rotated():
    filename = os.path.join(testdir, "clockwise_table_1.pdf")
    tables = camelot.read_pdf(filename)
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
    filename = os.path.join(testdir, "anticlockwise_table_1.pdf")
    tables = camelot.read_pdf(filename)
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_lattice_two_tables():
@@ -179,7 +181,7 @@ def test_lattice_table_regions():
    filename = os.path.join(testdir, "table_region.pdf")
    tables = camelot.read_pdf(filename, table_regions=["170,370,560,270"])
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_lattice_table_areas():
@@ -187,7 +189,7 @@ def test_lattice_table_areas():
    filename = os.path.join(testdir, "twotables_2.pdf")
    tables = camelot.read_pdf(filename, table_areas=["80,693,535,448"])
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_lattice_process_background():
@@ -195,7 +197,7 @@ def test_lattice_process_background():
    filename = os.path.join(testdir, "background_lines_1.pdf")
    tables = camelot.read_pdf(filename, process_background=True)
-    assert df.equals(tables[1].df)
+    assert_frame_equal(df, tables[1].df)
 def test_lattice_copy_text():
@@ -203,7 +205,7 @@ def test_lattice_copy_text():
    filename = os.path.join(testdir, "row_span_1.pdf")
    tables = camelot.read_pdf(filename, line_scale=60, copy_text="v")
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_lattice_shift_text():
@@ -271,7 +273,7 @@ def test_arabic():
    filename = os.path.join(testdir, "tabula/arabic.pdf")
    tables = camelot.read_pdf(filename)
-    assert df.equals(tables[0].df)
+    assert_frame_equal(df, tables[0].df)
 def test_table_order():
@@ -297,3 +299,26 @@ def test_table_order():
        (1, 2),
        (1, 1),
    ]
 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"
    )
 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)
@@ -10,88 +10,111 @@ import camelot
 testdir = os.path.dirname(os.path.abspath(__file__))
 testdir = os.path.join(testdir, "files")
-filename = os.path.join(testdir, 'foo.pdf')
+filename = os.path.join(testdir, "foo.pdf")
 def test_unknown_flavor():
-    message = ("Unknown flavor specified."
+    message = "Unknown flavor specified." " Use either 'lattice' or 'stream'"
               " Use either 'lattice' or 'stream'")
    with pytest.raises(NotImplementedError, match=message):
-        tables = camelot.read_pdf(filename, flavor='chocolate')
+        tables = camelot.read_pdf(filename, flavor="chocolate")
 def test_input_kwargs():
    message = "columns cannot be used with flavor='lattice'"
    with pytest.raises(ValueError, match=message):
-        tables = camelot.read_pdf(filename, columns=['10,20,30,40'])
+        tables = camelot.read_pdf(filename, columns=["10,20,30,40"])
 def test_unsupported_format():
-    message = 'File format not supported'
+    message = "File format not supported"
-    filename = os.path.join(testdir, 'foo.csv')
+    filename = os.path.join(testdir, "foo.csv")
    with pytest.raises(NotImplementedError, match=message):
        tables = camelot.read_pdf(filename)
 def test_stream_equal_length():
-    message = ("Length of table_areas and columns"
+    message = "Length of table_areas and columns" " should be equal"
               " should be equal")
    with pytest.raises(ValueError, match=message):
-        tables = camelot.read_pdf(filename, flavor='stream',
+        tables = camelot.read_pdf(
-            table_areas=['10,20,30,40'], columns=['10,20,30,40', '10,20,30,40'])
+            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')
+    filename = os.path.join(testdir, "image.pdf")
    with warnings.catch_warnings():
-        warnings.simplefilter('error')
+        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.'
+            assert (
                str(e.value)
                == "page-1 is image-based, camelot only works on text-based pages."
            )
-def test_no_tables_found():
+def test_lattice_no_tables_on_page():
-    filename = os.path.join(testdir, 'blank.pdf')
+    filename = os.path.join(testdir, "empty.pdf")
    with warnings.catch_warnings():
-        warnings.simplefilter('error')
+        warnings.simplefilter("error")
        with pytest.raises(UserWarning) as e:
-            tables = camelot.read_pdf(filename)
+            tables = camelot.read_pdf(filename, flavor="lattice")
-        assert str(e.value) == 'No tables found on page-1'
+        assert str(e.value) == "No tables found on page-1"
 def test_stream_no_tables_on_page():
    filename = os.path.join(testdir, "empty.pdf")
    with warnings.catch_warnings():
        warnings.simplefilter("error")
        with pytest.raises(UserWarning) as e:
            tables = camelot.read_pdf(filename, flavor="stream")
        assert str(e.value) == "No tables found on page-1"
 def test_stream_no_tables_in_area():
    filename = os.path.join(testdir, "only_page_number.pdf")
    with warnings.catch_warnings():
        warnings.simplefilter("error")
        with pytest.raises(UserWarning) as e:
            tables = camelot.read_pdf(filename, flavor="stream")
        assert str(e.value) == "No tables found in table area 1"
 def test_no_tables_found_logs_suppressed():
-    filename = os.path.join(testdir, 'foo.pdf')
+    filename = os.path.join(testdir, "foo.pdf")
    with warnings.catch_warnings():
        # the test should fail if any warning is thrown
-        warnings.simplefilter('error')
+        warnings.simplefilter("error")
        try:
            tables = camelot.read_pdf(filename, suppress_stdout=True)
        except Warning as e:
            warning_text = str(e)
-            pytest.fail('Unexpected warning: {}'.format(warning_text))
+            pytest.fail(f"Unexpected warning: {warning_text}")
 def test_no_tables_found_warnings_suppressed():
-    filename = os.path.join(testdir, 'blank.pdf')
+    filename = os.path.join(testdir, "empty.pdf")
    with warnings.catch_warnings():
        # the test should fail if any warning is thrown
-        warnings.simplefilter('error')
+        warnings.simplefilter("error")
        try:
            tables = camelot.read_pdf(filename, suppress_stdout=True)
        except Warning as e:
            warning_text = str(e)
-            pytest.fail('Unexpected warning: {}'.format(warning_text))
+            pytest.fail(f"Unexpected warning: {warning_text}")
 def test_no_password():
-    filename = os.path.join(testdir, 'health_protected.pdf')
+    filename = os.path.join(testdir, "health_protected.pdf")
-    message = 'file has not been decrypted'
+    message = "file has not been decrypted"
    with pytest.raises(Exception, match=message):
        tables = camelot.read_pdf(filename)
 def test_bad_password():
-    filename = os.path.join(testdir, 'health_protected.pdf')
+    filename = os.path.join(testdir, "health_protected.pdf")
-    message = 'file has not been decrypted'
+    message = "file has not been decrypted"
    with pytest.raises(Exception, match=message):
-        tables = camelot.read_pdf(filename, password='wrongpass')
+        tables = camelot.read_pdf(filename, password="wrongpass")
@@ -11,57 +11,50 @@ testdir = os.path.dirname(os.path.abspath(__file__))
 testdir = os.path.join(testdir, "files")
-@pytest.mark.mpl_image_compare(
+@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
    baseline_dir="files/baseline_plots", remove_text=True)
 def test_text_plot():
    filename = os.path.join(testdir, "foo.pdf")
    tables = camelot.read_pdf(filename)
-    return camelot.plot(tables[0], kind='text')
+    return camelot.plot(tables[0], kind="text")
-@pytest.mark.mpl_image_compare(
+@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
    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')
+    return camelot.plot(tables[0], kind="grid")
-@pytest.mark.mpl_image_compare(
+@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
    baseline_dir="files/baseline_plots", remove_text=True)
 def test_lattice_contour_plot():
    filename = os.path.join(testdir, "foo.pdf")
    tables = camelot.read_pdf(filename)
-    return camelot.plot(tables[0], kind='contour')
+    return camelot.plot(tables[0], kind="contour")
-@pytest.mark.mpl_image_compare(
+@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
    baseline_dir="files/baseline_plots", remove_text=True)
 def test_stream_contour_plot():
    filename = os.path.join(testdir, "tabula/12s0324.pdf")
-    tables = camelot.read_pdf(filename, flavor='stream')
+    tables = camelot.read_pdf(filename, flavor="stream")
-    return camelot.plot(tables[0], kind='contour')
+    return camelot.plot(tables[0], kind="contour")
-@pytest.mark.mpl_image_compare(
+@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
    baseline_dir="files/baseline_plots", remove_text=True)
 def test_line_plot():
    filename = os.path.join(testdir, "foo.pdf")
    tables = camelot.read_pdf(filename)
-    return camelot.plot(tables[0], kind='line')
+    return camelot.plot(tables[0], kind="line")
-@pytest.mark.mpl_image_compare(
+@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
    baseline_dir="files/baseline_plots", remove_text=True)
 def test_joint_plot():
    filename = os.path.join(testdir, "foo.pdf")
    tables = camelot.read_pdf(filename)
-    return camelot.plot(tables[0], kind='joint')
+    return camelot.plot(tables[0], kind="joint")
-@pytest.mark.mpl_image_compare(
+@pytest.mark.mpl_image_compare(baseline_dir="files/baseline_plots", remove_text=True)
    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')
+    tables = camelot.read_pdf(filename, flavor="stream")
-    return camelot.plot(tables[0], kind='textedge')
+    return camelot.plot(tables[0], kind="textedge")
Author	SHA1	Message	Date
Vinayak Mehta	c647f573d8	Bump version	2021-06-15 03:58:30 +05:30
Vinayak Mehta	9a3865c716	Update HISTORY.md	2021-06-15 03:55:46 +05:30
Vinayak Mehta	ec21904595	Merge pull request #219 from Arnie97/master [MRG] Add line_overlap and boxes_flow to LAParams	2021-06-15 03:53:40 +05:30
Vinayak Mehta	f53be3c73e	Update HISTORY.md	2021-06-15 03:53:23 +05:30
Vinayak Mehta	38370cf3f4	Merge pull request #231 from tiagosamaha/master Fix use resolution argument to generate image with GS	2021-06-15 03:51:00 +05:30
Tiago Samaha Cordeiro	3a8f988740	use resolution argument to generate image with GS	2021-06-15 03:46:07 +05:30
Vinayak Mehta	021be79bf7	Fix README	2021-06-15 03:30:34 +05:30
Vinayak Mehta	2c59e7b0f7	Blacken code	2021-06-15 03:29:35 +05:30
Vinayak Mehta	f7c14bf1d4	Update HISTORY.md	2021-06-15 03:28:23 +05:30
Vinayak Mehta	a2bb555292	Merge pull request #241 from camelot-dev/add-github-workflow Add github test workflow and remove travis	2021-06-15 03:06:18 +05:30
Vinayak Mehta	cf954a7f6d	Rename file and fix badge	2021-06-15 02:41:20 +05:30
Vinayak Mehta	0c9504e1bc	Fix workflow and job names	2021-06-15 02:36:18 +05:30
Vinayak Mehta	b5cf8a235d	Add github test workflow and remove travis	2021-06-15 02:29:25 +05:30
Arnie97	0dee385578	Add line_overlap and boxes_flow to LAParams	2020-12-17 22:12:24 +08:00
Vinayak Mehta	7709e58d64	Merge pull request #206 from edugonza/fix-15 [MRG] Fix #15 extraction of cell data discarding overlapping text boxes	2020-10-28 14:44:35 +05:30
Eduardo Gonzalez Lopez de Murillas	7695d35449	Fix #15 extraction of cell data discarding overlapping text boxes	2020-10-27 18:06:57 +01:00
Vinayak Mehta	8ca30f3a3c	Merge pull request #202 from tchx84/close-streams-explicitly [MRG] handlers: Close file streams explicitly	2020-10-25 05:34:38 +05:30
Martin Abente Lahaye	13a50e2ba2	handlers: Close file streams explicitly No harm in closing these streams explicitly. Best case scenario, this prevents descriptors leaks, worse case scenario, it reduces the amount of messages like the following during tests: ResourceWarning: unclosed file	2020-10-22 11:43:01 -03:00
Vinayak Mehta	d17dc43ab2	Merge pull request #196 from jimhall/gs-install-deps Language added to confirm proper installation of ghostscript libraries	2020-10-18 03:14:24 +05:30
Vinayak Mehta	de6faa7af1	Add new checks	2020-10-18 03:13:21 +05:30
Jim Hall	468512a8cd	Language added to confirm proper installation of ghostscript libraries	2020-10-08 08:21:34 -04:00
Vinayak Mehta	4edca28c53	Merge branch 'master' of github.com:camelot-dev/camelot	2020-09-08 00:35:57 +05:30
Vinayak Mehta	2a7a4f5b34	Update README and index.rst	2020-09-08 00:35:32 +05:30
Vinayak Mehta	0a3944e54d	Add bug report template	2020-09-07 23:39:49 +05:30
Vinayak Mehta	6b42094db5	Update year	2020-08-28 17:52:21 +05:30
Vinayak Mehta	937185412a	Merge pull request #189 from camelot-dev/fix-179 [MRG] Prevent taking max of an empty set	2020-08-25 23:03:20 +05:30
Vinayak Mehta	5d20d56e48	Prevent taking max of an empty set	2020-08-25 22:50:31 +05:30
Vinayak Mehta	9087429501	Merge pull request #188 from anakin87/master [MRG] Add encoding kwarg to camelot.core.Table.to_html method	2020-08-25 19:16:50 +05:30
Vinayak Mehta	cc905ff2d9	Merge pull request #186 from pevisscher/patch-1 Use correct re.sub signature	2020-08-25 19:14:58 +05:30
anakin87	eadc54ad25	Merge pull request #1 from anakin87/anakin87-patch-1 Update core.py	2020-08-25 15:28:48 +02:00
anakin87	579bc16be5	Update core.py Correct method camelot.core.Table.to_html	2020-08-25 15:27:17 +02:00
pevisscher	aae2c6b3d4	use correct re.sub signature `text_strip` currently passes the regex flags as the count parameters, which is hardcoded to `re.UNICODE` (value 32), and thus only replaces the first 32 values. see https://docs.python.org/3/library/re.html#re.sub for the signature	2020-08-24 16:51:06 +02:00
Vinayak Mehta	705473198f	Merge pull request #121 from jedie/patch-2 [MRG] Save plot when filename is specified	2020-08-14 02:36:28 +05:30
Vinayak Mehta	b741c0a9e9	Check for none and return none	2020-08-14 02:35:50 +05:30
Vinayak Mehta	a6bee88053	Merge pull request #119 from jedie/patch-1 Update advanced.rst	2020-08-14 02:27:49 +05:30
Vinayak Mehta	1e050e1960	Remove plt.show() usage	2020-08-14 02:27:07 +05:30
Vinayak Mehta	28371817db	Fix doc link	2020-08-14 02:09:56 +05:30
Vinayak Mehta	7ab5db39d0	Update .readthedocs.yml and remove requirements.txt	2020-08-04 04:37:37 +05:30
Vinayak Mehta	9a5c4b6865	Merge pull request #175 from camelot-dev/revert-0-8-1 [MRG] Revert the changes in v0.8.1	2020-07-27 17:56:48 +05:30
Vinayak Mehta	fbe576ffcb	Revert the changes in v0.8.1	2020-07-27 17:38:14 +05:30
Vinayak Mehta	fcad5067b9	Fix failing test	2020-07-23 00:54:41 +05:30
Vinayak Mehta	1b8ce1d560	Bump requirement versions	2020-07-23 00:40:26 +05:30
Vinayak Mehta	16beb15c43	Bump version and update HISTORY.md	2020-07-21 21:48:29 +05:30
Vinayak Mehta	be25e6dbdb	Merge pull request #171 from camelot-dev/fix-169 Change error name and update pdfminer.six version	2020-07-21 21:30:14 +05:30
Vinayak Mehta	a13e2f6f1f	Change error name and update pdfminer.six version	2020-07-21 21:21:01 +05:30
Vinayak Mehta	4b08165328	Merge pull request #166 from stevestock/patch-1 Update install.rst	2020-07-20 16:00:43 +05:30
Vinayak Mehta	e5b143d9a8	Update install instructions	2020-07-20 15:59:42 +05:30
Steven Stockhamer	8e5a8e6712	Update install.rst MacOS now uses zsh by default. Square brackets must be escaped in zsh	2020-07-19 20:44:16 -04:00
Vinayak Mehta	5efbcdcebb	Update requirements.txt	2020-05-24 19:04:50 +05:30
Vinayak Mehta	189fe58bf2	Update requirements.txt	2020-05-24 19:01:03 +05:30
Vinayak Mehta	1575ec1bf0	Add .readthedocs.yml	2020-05-24 18:56:33 +05:30
Vinayak Mehta	d5d6a5962b	Bump version and update HISTORY.md	2020-05-24 18:36:13 +05:30
Vinayak Mehta	420d5aa624	Merge pull request #146 from camelot-dev/add-python38-travis [MRG] Fix test data and drop python2 support	2020-05-24 18:31:27 +05:30
Vinayak Mehta	a22fa63c4e	Fix syntax errors	2020-05-24 18:19:48 +05:30
Vinayak Mehta	52b2a595b4	Add f-strings and remove python3.5 test job	2020-05-24 18:14:43 +05:30
Vinayak Mehta	afa1ba7c1f	Fix test indent	2020-05-24 17:38:48 +05:30
Vinayak Mehta	f725f04223	Remove future imports	2020-05-24 17:33:13 +05:30
Vinayak Mehta	3afb72b872	Fix read_pdf(url) and test data	2020-05-24 17:26:52 +05:30
Vinayak Mehta	6dd9b6ce01	Create FUNDING.yml	2020-05-24 16:14:43 +05:30
Vinayak Mehta	fc1b6f6227	Add python38 test job for travis	2020-05-24 15:27:48 +05:30
Vinayak Mehta	7d4c9e53c6	Update README	2020-03-21 18:07:29 +05:30
Jens Diemer	f8b6181988	Fix #120 - Save plot	2020-03-15 13:20:27 +01:00
Jens Diemer	dbdbc5f19e	Update advanced.rst Bugfix plot example.	2020-03-15 13:12:17 +01:00
Vinayak Mehta	44193e0d26	Add deepsource badge to docs	2019-12-24 13:08:46 +05:30
Vinayak Mehta	a9918a78cf	Add deepsource badge	2019-12-24 13:07:11 +05:30
Vinayak Mehta	47bb839d7a	Create .deepsource.toml	2019-12-24 13:03:45 +05:30
Vinayak Mehta	1b30f8ecf9	Merge pull request #94 from miltonArango/improving-coverage [MRG] Unit tests for the version generation	2019-11-15 10:50:42 +05:30
Milton Arango	8e28a0cac0	Moved the version tests to test_common PR #94 Applied black formatting	2019-11-14 20:26:20 -05:00
Vinayak Mehta	eb2badbbd0	Merge pull request #91 from vasantvohra/patch-1 [MRG] Update how-it-works.rst	2019-11-15 03:36:02 +05:30
Milton Arango	0d1db4b09e	Unit Tests for the Version Generation Unit tests for the __version__.py generate_version method.	2019-10-26 15:41:41 -05:00
Vasant Vohra	167ee9ac69	Update how-it-works.rst minor typo	2019-10-17 14:04:18 +05:30
Vinayak Mehta	83f816f104	Merge pull request #48 from jnothman/assert_frame_equal [MRG] Use assert_frame_equal for more informative errors in tests	2019-10-15 15:51:26 +05:30
Joel Nothman	9eb15c09dc	Use assert_frame_equal for more informative errors in tests	2019-08-06 11:38:44 +10:00