Bump version

[MRG] Add support to read from url

HISTORY.md

@@ -4,6 +4,60 @@ Release History
 master
 ------
 
+0.6.0 (2018-12-24)
+------------------
+
+**Improvements**
+
+* [#91](https://github.com/socialcopsdev/camelot/issues/91) Add support to read from url. [#236](https://github.com/socialcopsdev/camelot/pull/236) by Vinayak Mehta.
+* [#229](https://github.com/socialcopsdev/camelot/issues/229), [#230](https://github.com/socialcopsdev/camelot/issues/230) and [#233](https://github.com/socialcopsdev/camelot/issues/233) New configuration parameters. [#234](https://github.com/socialcopsdev/camelot/pull/234) by Vinayak Mehta.
+    * `strip_text`: To define characters that should be stripped from each string.
+    * `edge_tol`: Tolerance parameter for extending textedges vertically.
+    * `resolution`: Resolution used for PDF to PNG conversion.
+    * Check out the [advanced docs](https://camelot-py.readthedocs.io/en/master/user/advanced.html#strip-characters-from-text) for usage details.
+* [#170](https://github.com/socialcopsdev/camelot/issues/170) Add option to pass pdfminer layout kwargs. [#232](https://github.com/socialcopsdev/camelot/pull/232) by Vinayak Mehta.
+    * Keyword arguments for [pdfminer.layout.LAParams](https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33) can now be passed using `layout_kwargs` in `read_pdf()`.
+    * The `margins` keyword argument in `read_pdf()` is now deprecated.
+
+0.5.0 (2018-12-13)
+------------------
+
+**Improvements**
+
+* [#207](https://github.com/socialcopsdev/camelot/issues/207) Add a plot type for Stream text edges and detected table areas. [#224](https://github.com/socialcopsdev/camelot/pull/224) by Vinayak Mehta.
+* [#204](https://github.com/socialcopsdev/camelot/issues/204) `suppress_warnings` is now called `suppress_stdout`. [#225](https://github.com/socialcopsdev/camelot/pull/225) by Vinayak Mehta.
+
+**Bugfixes**
+
+* [#217](https://github.com/socialcopsdev/camelot/issues/217) Fix IndexError when scale is large.
+* [#105](https://github.com/socialcopsdev/camelot/issues/105), [#192](https://github.com/socialcopsdev/camelot/issues/192) and [#215](https://github.com/socialcopsdev/camelot/issues/215) in [#227](https://github.com/socialcopsdev/camelot/pull/227) by Vinayak Mehta.
+
+**Documentation**
+
+* Add pdfplumber comparison and update Tabula (stream) comparison. Check out the [wiki page](https://github.com/socialcopsdev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools).
+
+0.4.1 (2018-12-05)
+------------------
+
+**Bugfixes**
+
+* Add chardet to `install_requires` to fix [#210](https://github.com/socialcopsdev/camelot/issues/210). More details in [pdfminer.six#213](https://github.com/pdfminer/pdfminer.six/issues/213).
+
+0.4.0 (2018-11-23)
+------------------
+
+**Improvements**
+
+* [#102](https://github.com/socialcopsdev/camelot/issues/102) Detect tables automatically when Stream is used. [#206](https://github.com/socialcopsdev/camelot/pull/206) Add implementation of Anssi Nurminen's table detection algorithm by Vinayak Mehta.
+
+0.3.2 (2018-11-04)
+------------------
+
+**Improvements**
+
+* [#186](https://github.com/socialcopsdev/camelot/issues/186) Add `_bbox` attribute to table. [#193](https://github.com/socialcopsdev/camelot/pull/193) by Vinayak Mehta.
+    * You can use `table._bbox` to get coordinates of the detected table.
+
 0.3.1 (2018-11-02)
 ------------------
 

Makefile

@@ -15,7 +15,7 @@ install:
 	pip install ".[dev]"
 
 test:
-	pytest --verbose --cov-config .coveragerc --cov-report term --cov-report xml --cov=camelot --mpl tests
+	pytest --verbose --cov-config .coveragerc --cov-report term --cov-report xml --cov=camelot --mpl
 
 docs:
 	cd docs && make html

README.md

@@ -69,7 +69,7 @@ $ conda install -c conda-forge camelot-py
 
 ### Using pip
 
-After [installing the dependencies](https://camelot-py.readthedocs.io/en/master/user/install.html#using-pip) ([tk](https://packages.ubuntu.com/trusty/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/trusty/python-tk) and [ghostscript](https://www.ghostscript.com/)), you can simply use pip to install Camelot:
 
 <pre>
 $ pip install camelot-py[cv]

camelot/__version__.py

@@ -1,11 +1,23 @@
 # -*- coding: utf-8 -*-
 
-VERSION = (0, 3, 1)
+VERSION = (0, 6, 0)
+PRERELEASE = None # alpha, beta or rc
+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))
+    if revision is not None:
+        version_parts.append('.{}'.format(revision))
+    return ''.join(version_parts)
+
 
 __title__ = 'camelot-py'
 __description__ = 'PDF Table Extraction for Humans.'
 __url__ = 'http://camelot-py.readthedocs.io/'
-__version__ = '.'.join(map(str, VERSION))
+__version__ = generate_version(VERSION, prerelease=PRERELEASE, revision=REVISION)
 __author__ = 'Vinayak Mehta'
 __author_email__ = 'vmehta94@gmail.com'
 __license__ = 'MIT License'

camelot/cli.py

@@ -30,6 +30,7 @@ pass_config = click.make_pass_decorator(Config)
 
 @click.group()
 @click.version_option(version=__version__)
+@click.option('-q', '--quiet', is_flag=False, help='Suppress logs and warnings.')
 @click.option('-p', '--pages', default='1', help='Comma-separated page numbers.'
               ' Example: 1,3,4 or 1,4-end.')
 @click.option('-pw', '--password', help='Password for decryption.')
@@ -42,9 +43,10 @@ pass_config = click.make_pass_decorator(Config)
               help='Split text that spans across multiple cells.')
 @click.option('-flag', '--flag_size', is_flag=True, help='Flag text based on'
               ' font size. Useful to detect super/subscripts.')
+@click.option('-strip', '--strip_text', help='Characters that should be stripped from a string before'
+              ' assigning it to a cell.')
 @click.option('-M', '--margins', nargs=3, default=(1.0, 0.5, 0.1),
               help='PDFMiner char_margin, line_margin and word_margin.')
-@click.option('-q', '--quiet', is_flag=True, help='Suppress warnings.')
 @click.pass_context
 def cli(ctx, *args, **kwargs):
     """Camelot: PDF Table Extraction for Humans"""
@@ -68,10 +70,10 @@ def cli(ctx, *args, **kwargs):
 @click.option('-shift', '--shift_text', default=['l', 't'],
               type=click.Choice(['', 'l', 'r', 't', 'b']), multiple=True,
               help='Direction in which text in a spanning cell will flow.')
-@click.option('-l', '--line_close_tol', default=2,
+@click.option('-l', '--line_tol', default=2,
               help='Tolerance parameter used to merge close vertical'
               ' and horizontal lines.')
-@click.option('-j', '--joint_close_tol', default=2,
+@click.option('-j', '--joint_tol', default=2,
               help='Tolerance parameter used to decide whether'
               ' the detected lines and points lie close to each other.')
 @click.option('-block', '--threshold_blocksize', default=15,
@@ -84,6 +86,8 @@ def cli(ctx, *args, **kwargs):
               ' may be zero or negative as well.')
 @click.option('-I', '--iterations', default=0,
               help='Number of times for erosion/dilation will be applied.')
+@click.option('-res', '--resolution', default=300,
+              help='Resolution used for PDF to PNG conversion.')
 @click.option('-plot', '--plot_type',
               type=click.Choice(['text', 'grid', 'contour', 'joint', 'line']),
               help='Plot elements found on PDF page for visual debugging.')
@@ -96,7 +100,7 @@ def lattice(c, *args, **kwargs):
     output = conf.pop('output')
     f = conf.pop('format')
     compress = conf.pop('zip')
-    suppress_warnings = conf.pop('quiet')
+    quiet = conf.pop('quiet')
     plot_type = kwargs.pop('plot_type')
     filepath = kwargs.pop('filepath')
     kwargs.update(conf)
@@ -117,7 +121,7 @@ def lattice(c, *args, **kwargs):
             raise click.UsageError('Please specify output file format using --format')
 
     tables = read_pdf(filepath, pages=pages, flavor='lattice',
-                      suppress_warnings=suppress_warnings, **kwargs)
+                      suppress_stdout=quiet, **kwargs)
     click.echo('Found {} tables'.format(tables.n))
     if plot_type is not None:
         for table in tables:
@@ -133,12 +137,14 @@ def lattice(c, *args, **kwargs):
               ' where x1, y1 -> left-top and x2, y2 -> right-bottom.')
 @click.option('-C', '--columns', default=[], multiple=True,
               help='X coordinates of column separators.')
-@click.option('-r', '--row_close_tol', default=2, help='Tolerance parameter'
+@click.option('-e', '--edge_tol', default=50, help='Tolerance parameter'
+              ' for extending textedges vertically.')
+@click.option('-r', '--row_tol', default=2, help='Tolerance parameter'
               ' used to combine text vertically, to generate rows.')
-@click.option('-c', '--col_close_tol', default=0, help='Tolerance parameter'
+@click.option('-c', '--column_tol', default=0, help='Tolerance parameter'
               ' used to combine text horizontally, to generate columns.')
 @click.option('-plot', '--plot_type',
-              type=click.Choice(['text', 'grid']),
+              type=click.Choice(['text', 'grid', 'contour', 'textedge']),
               help='Plot elements found on PDF page for visual debugging.')
 @click.argument('filepath', type=click.Path(exists=True))
 @pass_config
@@ -149,7 +155,7 @@ def stream(c, *args, **kwargs):
     output = conf.pop('output')
     f = conf.pop('format')
     compress = conf.pop('zip')
-    suppress_warnings = conf.pop('quiet')
+    quiet = conf.pop('quiet')
     plot_type = kwargs.pop('plot_type')
     filepath = kwargs.pop('filepath')
     kwargs.update(conf)
@@ -169,7 +175,7 @@ def stream(c, *args, **kwargs):
             raise click.UsageError('Please specify output file format using --format')
 
     tables = read_pdf(filepath, pages=pages, flavor='stream',
-                      suppress_warnings=suppress_warnings, **kwargs)
+                      suppress_stdout=quiet, **kwargs)
     click.echo('Found {} tables'.format(tables.n))
     if plot_type is not None:
         for table in tables:

camelot/core.py

@@ -3,11 +3,210 @@
 import os
 import zipfile
 import tempfile
+from itertools import chain
+from operator import itemgetter
 
 import numpy as np
 import pandas as pd
 
 
+# minimum number of vertical textline intersections for a textedge
+# to be considered valid
+TEXTEDGE_REQUIRED_ELEMENTS = 4
+# padding added to table area on the left, right and bottom
+TABLE_AREA_PADDING = 10
+
+
+class TextEdge(object):
+    """Defines a text edge coordinates relative to a left-bottom
+    origin. (PDF coordinate space)
+
+    Parameters
+    ----------
+    x : float
+        x-coordinate of the text edge.
+    y0 : float
+        y-coordinate of bottommost point.
+    y1 : float
+        y-coordinate of topmost point.
+    align : string, optional (default: 'left')
+        {'left', 'right', 'middle'}
+
+    Attributes
+    ----------
+    intersections: int
+        Number of intersections with horizontal text rows.
+    is_valid: bool
+        A text edge is valid if it intersections with at least
+        TEXTEDGE_REQUIRED_ELEMENTS horizontal text rows.
+
+    """
+    def __init__(self, x, y0, y1, align='left'):
+        self.x = x
+        self.y0 = y0
+        self.y1 = y1
+        self.align = align
+        self.intersections = 0
+        self.is_valid = False
+
+    def __repr__(self):
+        return '<TextEdge x={} y0={} y1={} align={} valid={}>'.format(
+            round(self.x, 2), round(self.y0, 2), round(self.y1, 2), self.align, self.is_valid)
+
+    def update_coords(self, x, y0, edge_tol=50):
+        """Updates the text edge's x and bottom y coordinates and sets
+        the is_valid attribute.
+        """
+        if np.isclose(self.y0, y0, atol=edge_tol):
+            self.x = (self.intersections * self.x + x) / float(self.intersections + 1)
+            self.y0 = y0
+            self.intersections += 1
+            # a textedge is valid only if it extends uninterrupted
+            # over a required number of textlines
+            if self.intersections > TEXTEDGE_REQUIRED_ELEMENTS:
+                self.is_valid = True
+
+
+class TextEdges(object):
+    """Defines a dict of left, right and middle text edges found on
+    the PDF page. The dict has three keys based on the alignments,
+    and each key's value is a list of camelot.core.TextEdge objects.
+    """
+    def __init__(self, edge_tol=50):
+        self.edge_tol = edge_tol
+        self._textedges = {'left': [], 'right': [], 'middle': []}
+
+    @staticmethod
+    def get_x_coord(textline, align):
+        """Returns the x coordinate of a text row based on the
+        specified alignment.
+        """
+        x_left = textline.x0
+        x_right = textline.x1
+        x_middle = x_left + (x_right - x_left) / 2.0
+        x_coord = {'left': x_left, 'middle': x_middle, 'right': x_right}
+        return x_coord[align]
+
+    def find(self, x_coord, align):
+        """Returns the index of an existing text edge using
+        the specified x coordinate and alignment.
+        """
+        for i, te in enumerate(self._textedges[align]):
+            if np.isclose(te.x, x_coord, atol=0.5):
+                return i
+        return None
+
+    def add(self, textline, align):
+        """Adds a new text edge to the current dict.
+        """
+        x = self.get_x_coord(textline, align)
+        y0 = textline.y0
+        y1 = textline.y1
+        te = TextEdge(x, y0, y1, align=align)
+        self._textedges[align].append(te)
+
+    def update(self, textline):
+        """Updates an existing text edge in the current dict.
+        """
+        for align in ['left', 'right', 'middle']:
+            x_coord = self.get_x_coord(textline, align)
+            idx = self.find(x_coord, align)
+            if idx is None:
+                self.add(textline, align)
+            else:
+                self._textedges[align][idx].update_coords(
+                    x_coord, textline.y0, edge_tol=self.edge_tol)
+
+    def generate(self, textlines):
+        """Generates the text edges dict based on horizontal text
+        rows.
+        """
+        for tl in textlines:
+            if len(tl.get_text().strip()) > 1: # TODO: hacky
+                self.update(tl)
+
+    def get_relevant(self):
+        """Returns the list of relevant text edges (all share the same
+        alignment) based on which list intersects horizontal text rows
+        the most.
+        """
+        intersections_sum = {
+            'left': sum(te.intersections for te in self._textedges['left'] if te.is_valid),
+            'right': sum(te.intersections for te in self._textedges['right'] if te.is_valid),
+            'middle': sum(te.intersections for te in self._textedges['middle'] if te.is_valid)
+        }
+
+        # TODO: naive
+        # get vertical textedges that intersect maximum number of
+        # times with horizontal textlines
+        relevant_align = max(intersections_sum.items(), key=itemgetter(1))[0]
+        return self._textedges[relevant_align]
+
+    def get_table_areas(self, textlines, relevant_textedges):
+        """Returns a dict of interesting table areas on the PDF page
+        calculated using relevant text edges.
+        """
+        def pad(area, average_row_height):
+            x0 = area[0] - TABLE_AREA_PADDING
+            y0 = area[1] - TABLE_AREA_PADDING
+            x1 = area[2] + TABLE_AREA_PADDING
+            # add a constant since table headers can be relatively up
+            y1 = area[3] + average_row_height * 5
+            return (x0, y0, x1, y1)
+
+        # sort relevant textedges in reading order
+        relevant_textedges.sort(key=lambda te: (-te.y0, te.x))
+
+        table_areas = {}
+        for te in relevant_textedges:
+            if te.is_valid:
+                if not table_areas:
+                    table_areas[(te.x, te.y0, te.x, te.y1)] = None
+                else:
+                    found = None
+                    for area in table_areas:
+                        # check for overlap
+                        if te.y1 >= area[1] and te.y0 <= area[3]:
+                            found = area
+                            break
+                    if found is None:
+                        table_areas[(te.x, te.y0, te.x, te.y1)] = None
+                    else:
+                        table_areas.pop(found)
+                        updated_area = (
+                            found[0], min(te.y0, found[1]), max(found[2], te.x), max(found[3], te.y1))
+                        table_areas[updated_area] = None
+
+        # extend table areas based on textlines that overlap
+        # vertically. it's possible that these textlines were
+        # eliminated during textedges generation since numbers and
+        # chars/words/sentences are often aligned differently.
+        # drawback: table areas that have paragraphs on their sides
+        # will include the paragraphs too.
+        sum_textline_height = 0
+        for tl in textlines:
+            sum_textline_height += tl.y1 - tl.y0
+            found = None
+            for area in table_areas:
+                # check for overlap
+                if tl.y0 >= area[1] and tl.y1 <= area[3]:
+                    found = area
+                    break
+            if found is not None:
+                table_areas.pop(found)
+                updated_area = (
+                    min(tl.x0, found[0]), min(tl.y0, found[1]), max(found[2], tl.x1), max(found[3], tl.y1))
+                table_areas[updated_area] = None
+        average_textline_height = sum_textline_height / float(len(textlines))
+
+        # add some padding to table areas
+        table_areas_padded = {}
+        for area in table_areas:
+            table_areas_padded[pad(area, average_textline_height)] = None
+
+        return table_areas_padded
+
+
 class Cell(object):
     """Defines a cell in a table with coordinates relative to a
     left-bottom origin. (PDF coordinate space)
@@ -160,7 +359,7 @@ class Table(object):
                 cell.left = cell.right = cell.top = cell.bottom = True
         return self
 
-    def set_edges(self, vertical, horizontal, joint_close_tol=2):
+    def set_edges(self, vertical, horizontal, joint_tol=2):
         """Sets a cell's edges to True depending on whether the cell's
         coordinates overlap with the line's coordinates within a
         tolerance.
@@ -177,11 +376,11 @@ class Table(object):
             # find closest x coord
             # iterate over y coords and find closest start and end points
             i = [i for i, t in enumerate(self.cols)
-                 if np.isclose(v[0], t[0], atol=joint_close_tol)]
+                 if np.isclose(v[0], t[0], atol=joint_tol)]
             j = [j for j, t in enumerate(self.rows)
-                 if np.isclose(v[3], t[0], atol=joint_close_tol)]
+                 if np.isclose(v[3], t[0], atol=joint_tol)]
             k = [k for k, t in enumerate(self.rows)
-                 if np.isclose(v[1], t[0], atol=joint_close_tol)]
+                 if np.isclose(v[1], t[0], atol=joint_tol)]
             if not j:
                 continue
             J = j[0]
@@ -228,11 +427,11 @@ class Table(object):
             # find closest y coord
             # iterate over x coords and find closest start and end points
             i = [i for i, t in enumerate(self.rows)
-                 if np.isclose(h[1], t[0], atol=joint_close_tol)]
+                 if np.isclose(h[1], t[0], atol=joint_tol)]
             j = [j for j, t in enumerate(self.cols)
-                 if np.isclose(h[0], t[0], atol=joint_close_tol)]
+                 if np.isclose(h[0], t[0], atol=joint_tol)]
             k = [k for k, t in enumerate(self.cols)
-                 if np.isclose(h[2], t[0], atol=joint_close_tol)]
+                 if np.isclose(h[2], t[0], atol=joint_tol)]
             if not j:
                 continue
             J = j[0]
@@ -249,7 +448,7 @@ class Table(object):
                         self.cells[L][J].top = True
                         J += 1
             elif i == []:  # only bottom edge
-                I = len(self.rows) - 1
+                L = len(self.rows) - 1
                 if k:
                     K = k[0]
                     while J < K:

camelot/handlers.py

@@ -8,7 +8,7 @@ from PyPDF2 import PdfFileReader, PdfFileWriter
 from .core import TableList
 from .parsers import Stream, Lattice
 from .utils import (TemporaryDirectory, get_page_layout, get_text_objects,
-                    get_rotation)
+                    get_rotation, is_url, download_url)
 
 
 class PDFHandler(object):
@@ -18,8 +18,8 @@ class PDFHandler(object):
 
     Parameters
     ----------
-    filename : str
-        Path to PDF file.
+    filepath : str
+        Filepath or URL of the PDF file.
     pages : str, optional (default: '1')
         Comma-separated page numbers.
         Example: '1,3,4' or '1,4-end'.
@@ -27,11 +27,13 @@ class PDFHandler(object):
         Password for decryption.
 
     """
-    def __init__(self, filename, pages='1', password=None):
-        self.filename = filename
-        if not filename.lower().endswith('.pdf'):
+    def __init__(self, filepath, pages='1', password=None):
+        if is_url(filepath):
+            filepath = download_url(filepath)
+        self.filepath = filepath
+        if not filepath.lower().endswith('.pdf'):
             raise NotImplementedError("File format not supported")
-        self.pages = self._get_pages(self.filename, pages)
+        self.pages = self._get_pages(self.filepath, pages)
         if password is None:
             self.password = ''
         else:
@@ -39,13 +41,13 @@ class PDFHandler(object):
             if sys.version_info[0] < 3:
                 self.password = self.password.encode('ascii')
 
-    def _get_pages(self, filename, pages):
+    def _get_pages(self, filepath, pages):
         """Converts pages string to list of ints.
 
         Parameters
         ----------
-        filename : str
-            Path to PDF file.
+        filepath : str
+            Filepath or URL of the PDF file.
         pages : str, optional (default: '1')
             Comma-separated page numbers.
             Example: 1,3,4 or 1,4-end.
@@ -60,7 +62,7 @@ class PDFHandler(object):
         if pages == '1':
             page_numbers.append({'start': 1, 'end': 1})
         else:
-            infile = PdfFileReader(open(filename, 'rb'), strict=False)
+            infile = PdfFileReader(open(filepath, 'rb'), strict=False)
             if infile.isEncrypted:
                 infile.decrypt(self.password)
             if pages == 'all':
@@ -79,20 +81,20 @@ class PDFHandler(object):
             P.extend(range(p['start'], p['end'] + 1))
         return sorted(set(P))
 
-    def _save_page(self, filename, page, temp):
+    def _save_page(self, filepath, page, temp):
         """Saves specified page from PDF into a temporary directory.
 
         Parameters
         ----------
-        filename : str
-            Path to PDF file.
+        filepath : str
+            Filepath or URL of the PDF file.
         page : int
             Page number.
         temp : str
             Tmp directory.
 
         """
-        with open(filename, 'rb') as fileobj:
+        with open(filepath, 'rb') as fileobj:
             infile = PdfFileReader(fileobj, strict=False)
             if infile.isEncrypted:
                 infile.decrypt(self.password)
@@ -125,7 +127,7 @@ class PDFHandler(object):
                 with open(fpath, 'wb') as f:
                     outfile.write(f)
 
-    def parse(self, flavor='lattice', **kwargs):
+    def parse(self, flavor='lattice', suppress_stdout=False, layout_kwargs={}, **kwargs):
         """Extracts tables by calling parser.get_tables on all single
         page PDFs.
 
@@ -134,6 +136,10 @@ class PDFHandler(object):
         flavor : str (default: 'lattice')
             The parsing method to use ('lattice' or 'stream').
             Lattice is used by default.
+        suppress_stdout : str (default: False)
+            Suppress logs and warnings.
+        layout_kwargs : dict, optional (default: {})
+            A dict of `pdfminer.layout.LAParams <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ kwargs.
         kwargs : dict
             See camelot.read_pdf kwargs.
 
@@ -146,11 +152,12 @@ class PDFHandler(object):
         tables = []
         with TemporaryDirectory() as tempdir:
             for p in self.pages:
-                self._save_page(self.filename, p, tempdir)
+                self._save_page(self.filepath, p, tempdir)
             pages = [os.path.join(tempdir, 'page-{0}.pdf'.format(p))
                      for p in self.pages]
             parser = Lattice(**kwargs) if flavor == 'lattice' else Stream(**kwargs)
             for p in pages:
-                t = parser.extract_tables(p)
+                t = parser.extract_tables(p, suppress_stdout=suppress_stdout,
+                                          layout_kwargs=layout_kwargs)
                 tables.extend(t)
         return TableList(tables)

camelot/io.py

@@ -6,7 +6,7 @@ from .utils import validate_input, remove_extra
 
 
 def read_pdf(filepath, pages='1', password=None, flavor='lattice',
-             suppress_warnings=False, **kwargs):
+             suppress_stdout=False, layout_kwargs={}, **kwargs):
     """Read PDF and return extracted tables.
 
     Note: kwargs annotated with ^ can only be used with flavor='stream'
@@ -15,7 +15,7 @@ def read_pdf(filepath, pages='1', password=None, flavor='lattice',
     Parameters
     ----------
     filepath : str
-        Path to PDF file.
+        Filepath or URL of the PDF file.
     pages : str, optional (default: '1')
         Comma-separated page numbers.
         Example: '1,3,4' or '1,4-end'.
@@ -24,8 +24,10 @@ def read_pdf(filepath, pages='1', password=None, flavor='lattice',
     flavor : str (default: 'lattice')
         The parsing method to use ('lattice' or 'stream').
         Lattice is used by default.
-    suppress_warnings : bool, optional (default: False)
-        Prevent warnings from being emitted by Camelot.
+    suppress_stdout : bool, optional (default: True)
+        Print all logs and warnings.
+    layout_kwargs : dict, optional (default: {})
+        A dict of `pdfminer.layout.LAParams <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ kwargs.
     table_areas : list, optional (default: None)
         List of table area strings of the form x1,y1,x2,y2
         where (x1, y1) -> left-top and (x2, y2) -> right-bottom
@@ -38,10 +40,13 @@ def read_pdf(filepath, pages='1', password=None, flavor='lattice',
     flag_size : bool, optional (default: False)
         Flag text based on font size. Useful to detect
         super/subscripts. Adds <s></s> around flagged text.
-    row_close_tol^ : int, optional (default: 2)
+    strip_text : str, optional (default: '')
+        Characters that should be stripped from a string before
+        assigning it to a cell.
+    row_tol^ : int, optional (default: 2)
         Tolerance parameter used to combine text vertically,
         to generate rows.
-    col_close_tol^ : int, optional (default: 0)
+    column_tol^ : int, optional (default: 0)
         Tolerance parameter used to combine text horizontally,
         to generate columns.
     process_background* : bool, optional (default: False)
@@ -57,10 +62,10 @@ def read_pdf(filepath, pages='1', password=None, flavor='lattice',
     shift_text* : list, optional (default: ['l', 't'])
         {'l', 'r', 't', 'b'}
         Direction in which text in a spanning cell will flow.
-    line_close_tol* : int, optional (default: 2)
+    line_tol* : int, optional (default: 2)
         Tolerance parameter used to merge close vertical and horizontal
         lines.
-    joint_close_tol* : int, optional (default: 2)
+    joint_tol* : int, optional (default: 2)
         Tolerance parameter used to decide whether the detected lines
         and points lie close to each other.
     threshold_blocksize* : int, optional (default: 15)
@@ -77,10 +82,8 @@ def read_pdf(filepath, pages='1', password=None, flavor='lattice',
         Number of times for erosion/dilation is applied.
 
         For more information, refer `OpenCV's dilate <https://docs.opencv.org/2.4/modules/imgproc/doc/filtering.html#dilate>`_.
-    margins : tuple
-        PDFMiner char_margin, line_margin and word_margin.
-
-        For more information, refer `PDFMiner docs <https://euske.github.io/pdfminer/>`_.
+    resolution* : int, optional (default: 300)
+        Resolution used for PDF to PNG conversion.
 
     Returns
     -------
@@ -92,11 +95,12 @@ def read_pdf(filepath, pages='1', password=None, flavor='lattice',
                                   " Use either 'lattice' or 'stream'")
 
     with warnings.catch_warnings():
-        if suppress_warnings:
+        if suppress_stdout:
             warnings.simplefilter("ignore")
 
         validate_input(kwargs, flavor=flavor)
         p = PDFHandler(filepath, pages=pages, password=password)
         kwargs = remove_extra(kwargs, flavor=flavor)
-        tables = p.parse(flavor=flavor, **kwargs)
+        tables = p.parse(flavor=flavor, suppress_stdout=suppress_stdout,
+                         layout_kwargs=layout_kwargs, **kwargs)
         return tables

camelot/parsers/base.py

@@ -8,13 +8,11 @@ from ..utils import get_page_layout, get_text_objects
 class BaseParser(object):
     """Defines a base parser.
     """
-    def _generate_layout(self, filename):
+    def _generate_layout(self, filename, layout_kwargs):
         self.filename = filename
+        self.layout_kwargs = layout_kwargs
         self.layout, self.dimensions = get_page_layout(
-            self.filename,
-            char_margin=self.char_margin,
-            line_margin=self.line_margin,
-            word_margin=self.word_margin)
+            filename, **layout_kwargs)
         self.horizontal_text = get_text_objects(self.layout, ltype="lh")
         self.vertical_text = get_text_objects(self.layout, ltype="lv")
         self.pdf_width, self.pdf_height = self.dimensions

camelot/parsers/lattice.py

@@ -50,10 +50,13 @@ class Lattice(BaseParser):
     flag_size : bool, optional (default: False)
         Flag text based on font size. Useful to detect
         super/subscripts. Adds <s></s> around flagged text.
-    line_close_tol : int, optional (default: 2)
+    strip_text : str, optional (default: '')
+        Characters that should be stripped from a string before
+        assigning it to a cell.
+    line_tol : int, optional (default: 2)
         Tolerance parameter used to merge close vertical and horizontal
         lines.
-    joint_close_tol : int, optional (default: 2)
+    joint_tol : int, optional (default: 2)
         Tolerance parameter used to decide whether the detected lines
         and points lie close to each other.
     threshold_blocksize : int, optional (default: 15)
@@ -70,17 +73,15 @@ class Lattice(BaseParser):
         Number of times for erosion/dilation is applied.
 
         For more information, refer `OpenCV's dilate <https://docs.opencv.org/2.4/modules/imgproc/doc/filtering.html#dilate>`_.
-    margins : tuple
-        PDFMiner char_margin, line_margin and word_margin.
-
-        For more information, refer `PDFMiner docs <https://euske.github.io/pdfminer/>`_.
+    resolution : int, optional (default: 300)
+        Resolution used for PDF to PNG conversion.
 
     """
     def __init__(self, table_areas=None, process_background=False,
                  line_size_scaling=15, copy_text=None, shift_text=['l', 't'],
-                 split_text=False, flag_size=False, line_close_tol=2,
-                 joint_close_tol=2, threshold_blocksize=15, threshold_constant=-2,
-                 iterations=0, margins=(1.0, 0.5, 0.1), **kwargs):
+                 split_text=False, flag_size=False, strip_text='', line_tol=2,
+                 joint_tol=2, threshold_blocksize=15, threshold_constant=-2,
+                 iterations=0, resolution=300, **kwargs):
         self.table_areas = table_areas
         self.process_background = process_background
         self.line_size_scaling = line_size_scaling
@@ -88,12 +89,13 @@ class Lattice(BaseParser):
         self.shift_text = shift_text
         self.split_text = split_text
         self.flag_size = flag_size
-        self.line_close_tol = line_close_tol
-        self.joint_close_tol = joint_close_tol
+        self.strip_text = strip_text
+        self.line_tol = line_tol
+        self.joint_tol = joint_tol
         self.threshold_blocksize = threshold_blocksize
         self.threshold_constant = threshold_constant
         self.iterations = iterations
-        self.char_margin, self.line_margin, self.word_margin = margins
+        self.resolution = resolution
 
     @staticmethod
     def _reduce_index(t, idx, shift_text):
@@ -214,7 +216,7 @@ class Lattice(BaseParser):
             '-sDEVICE=png16m',
             '-o',
             self.imagename,
-            '-r600',
+            '-r{}'.format(self.resolution),
             self.filename
         ]
         gs = get_executable()
@@ -271,10 +273,11 @@ class Lattice(BaseParser):
             tk, self.vertical_segments, self.horizontal_segments)
         t_bbox['horizontal'] = text_in_bbox(tk, self.horizontal_text)
         t_bbox['vertical'] = text_in_bbox(tk, self.vertical_text)
-        self.t_bbox = t_bbox
 
-        for direction in t_bbox:
-            t_bbox[direction].sort(key=lambda x: (-x.y0, x.x0))
+        t_bbox['horizontal'].sort(key=lambda x: (-x.y0, x.x0))
+        t_bbox['vertical'].sort(key=lambda x: (x.x0, -x.y0))
+
+        self.t_bbox = t_bbox
 
         cols, rows = zip(*self.table_bbox[tk])
         cols, rows = list(cols), list(rows)
@@ -282,9 +285,9 @@ class Lattice(BaseParser):
         rows.extend([tk[1], tk[3]])
         # sort horizontal and vertical segments
         cols = merge_close_lines(
-            sorted(cols), line_close_tol=self.line_close_tol)
+            sorted(cols), line_tol=self.line_tol)
         rows = merge_close_lines(
-            sorted(rows, reverse=True), line_close_tol=self.line_close_tol)
+            sorted(rows, reverse=True), line_tol=self.line_tol)
         # make grid using x and y coord of shortlisted rows and cols
         cols = [(cols[i], cols[i + 1])
                 for i in range(0, len(cols) - 1)]
@@ -301,18 +304,20 @@ class Lattice(BaseParser):
 
         table = Table(cols, rows)
         # set table edges to True using ver+hor lines
-        table = table.set_edges(v_s, h_s, joint_close_tol=self.joint_close_tol)
+        table = table.set_edges(v_s, h_s, joint_tol=self.joint_tol)
         # set table border edges to True
         table = table.set_border()
         # set spanning cells to True
         table = table.set_span()
 
         pos_errors = []
-        for direction in self.t_bbox:
+        # TODO: have a single list in place of two directional ones?
+        # sorted on x-coordinate based on reading order i.e. LTR or RTL
+        for direction in ['vertical', 'horizontal']:
             for t in self.t_bbox[direction]:
                 indices, error = get_table_index(
                     table, t, direction, split_text=self.split_text,
-                    flag_size=self.flag_size)
+                    flag_size=self.flag_size, strip_text=self.strip_text)
                 if indices[:2] != (-1, -1):
                     pos_errors.append(error)
                     indices = Lattice._reduce_index(table, indices, shift_text=self.shift_text)
@@ -341,12 +346,14 @@ class Lattice(BaseParser):
         table._text = _text
         table._image = (self.image, self.table_bbox_unscaled)
         table._segments = (self.vertical_segments, self.horizontal_segments)
+        table._textedges = None
 
         return table
 
-    def extract_tables(self, filename):
-        self._generate_layout(filename)
-        logger.info('Processing {}'.format(os.path.basename(self.rootname)))
+    def extract_tables(self, filename, suppress_stdout=False, layout_kwargs={}):
+        self._generate_layout(filename, layout_kwargs)
+        if not suppress_stdout:
+            logger.info('Processing {}'.format(os.path.basename(self.rootname)))
 
         if not self.horizontal_text:
             warnings.warn("No tables found on {}".format(
@@ -362,6 +369,7 @@ class Lattice(BaseParser):
                 self.table_bbox.keys(), key=lambda x: x[1], reverse=True)):
             cols, rows, v_s, h_s = self._generate_columns_and_rows(table_idx, tk)
             table = self._generate_table(table_idx, cols, rows, v_s=v_s, h_s=h_s)
+            table._bbox = tk
             _tables.append(table)
 
         return _tables

camelot/parsers/stream.py

@@ -9,7 +9,7 @@ import numpy as np
 import pandas as pd
 
 from .base import BaseParser
-from ..core import Table
+from ..core import TextEdges, Table
 from ..utils import (text_in_bbox, get_table_index, compute_accuracy,
                      compute_whitespace)
 
@@ -38,29 +38,31 @@ class Stream(BaseParser):
     flag_size : bool, optional (default: False)
         Flag text based on font size. Useful to detect
         super/subscripts. Adds <s></s> around flagged text.
-    row_close_tol : int, optional (default: 2)
+    strip_text : str, optional (default: '')
+        Characters that should be stripped from a string before
+        assigning it to a cell.
+    edge_tol : int, optional (default: 50)
+        Tolerance parameter for extending textedges vertically.
+    row_tol : int, optional (default: 2)
         Tolerance parameter used to combine text vertically,
         to generate rows.
-    col_close_tol : int, optional (default: 0)
+    column_tol : int, optional (default: 0)
         Tolerance parameter used to combine text horizontally,
         to generate columns.
-    margins : tuple, optional (default: (1.0, 0.5, 0.1))
-        PDFMiner char_margin, line_margin and word_margin.
-
-        For more information, refer `PDFMiner docs <https://euske.github.io/pdfminer/>`_.
 
     """
     def __init__(self, table_areas=None, columns=None, split_text=False,
-                 flag_size=False, row_close_tol=2, col_close_tol=0,
-                 margins=(1.0, 0.5, 0.1), **kwargs):
+                 flag_size=False, strip_text='', edge_tol=50, row_tol=2,
+                 column_tol=0, **kwargs):
         self.table_areas = table_areas
         self.columns = columns
         self._validate_columns()
         self.split_text = split_text
         self.flag_size = flag_size
-        self.row_close_tol = row_close_tol
-        self.col_close_tol = col_close_tol
-        self.char_margin, self.line_margin, self.word_margin = margins
+        self.strip_text = strip_text
+        self.edge_tol = edge_tol
+        self.row_tol = row_tol
+        self.column_tol = column_tol
 
     @staticmethod
     def _text_bbox(t_bbox):
@@ -86,7 +88,7 @@ class Stream(BaseParser):
         return text_bbox
 
     @staticmethod
-    def _group_rows(text, row_close_tol=2):
+    def _group_rows(text, row_tol=2):
         """Groups PDFMiner text objects into rows vertically
         within a tolerance.
 
@@ -94,7 +96,7 @@ class Stream(BaseParser):
         ----------
         text : list
             List of PDFMiner text objects.
-        row_close_tol : int, optional (default: 2)
+        row_tol : int, optional (default: 2)
 
         Returns
         -------
@@ -110,17 +112,17 @@ class Stream(BaseParser):
             # if t.get_text().strip() and all([obj.upright for obj in t._objs if
             # type(obj) is LTChar]):
             if t.get_text().strip():
-                if not np.isclose(row_y, t.y0, atol=row_close_tol):
+                if not np.isclose(row_y, t.y0, atol=row_tol):
                     rows.append(sorted(temp, key=lambda t: t.x0))
                     temp = []
                     row_y = t.y0
                 temp.append(t)
         rows.append(sorted(temp, key=lambda t: t.x0))
-        __ = rows.pop(0)  # hacky
+        __ = rows.pop(0)  # TODO: hacky
         return rows
 
     @staticmethod
-    def _merge_columns(l, col_close_tol=0):
+    def _merge_columns(l, column_tol=0):
         """Merges column boundaries horizontally if they overlap
         or lie within a tolerance.
 
@@ -128,7 +130,7 @@ class Stream(BaseParser):
         ----------
         l : list
             List of column x-coordinate tuples.
-        col_close_tol : int, optional (default: 0)
+        column_tol : int, optional (default: 0)
 
         Returns
         -------
@@ -142,17 +144,17 @@ class Stream(BaseParser):
                 merged.append(higher)
             else:
                 lower = merged[-1]
-                if col_close_tol >= 0:
+                if column_tol >= 0:
                     if (higher[0] <= lower[1] or
-                            np.isclose(higher[0], lower[1], atol=col_close_tol)):
+                            np.isclose(higher[0], lower[1], atol=column_tol)):
                         upper_bound = max(lower[1], higher[1])
                         lower_bound = min(lower[0], higher[0])
                         merged[-1] = (lower_bound, upper_bound)
                     else:
                         merged.append(higher)
-                elif col_close_tol < 0:
+                elif column_tol < 0:
                     if higher[0] <= lower[1]:
-                        if np.isclose(higher[0], lower[1], atol=abs(col_close_tol)):
+                        if np.isclose(higher[0], lower[1], atol=abs(column_tol)):
                             merged.append(higher)
                         else:
                             upper_bound = max(lower[1], higher[1])
@@ -189,7 +191,7 @@ class Stream(BaseParser):
         return rows
 
     @staticmethod
-    def _add_columns(cols, text, row_close_tol):
+    def _add_columns(cols, text, row_tol):
         """Adds columns to existing list by taking into account
         the text that lies outside the current column x-coordinates.
 
@@ -208,7 +210,7 @@ class Stream(BaseParser):
 
         """
         if text:
-            text = Stream._group_rows(text, row_close_tol=row_close_tol)
+            text = Stream._group_rows(text, row_tol=row_tol)
             elements = [len(r) for r in text]
             new_cols = [(t.x0, t.x1)
                         for r in text if len(r) == max(elements) for t in r]
@@ -246,7 +248,33 @@ class Stream(BaseParser):
                 raise ValueError("Length of table_areas and columns"
                                  " should be equal")
 
+    def _nurminen_table_detection(self, textlines):
+        """A general implementation of the table detection algorithm
+        described by Anssi Nurminen's master's thesis.
+        Link: https://dspace.cc.tut.fi/dpub/bitstream/handle/123456789/21520/Nurminen.pdf?sequence=3
+
+        Assumes that tables are situated relatively far apart
+        vertically.
+        """
+        # TODO: add support for arabic text #141
+        # sort textlines in reading order
+        textlines.sort(key=lambda x: (-x.y0, x.x0))
+        textedges = TextEdges(edge_tol=self.edge_tol)
+        # generate left, middle and right textedges
+        textedges.generate(textlines)
+        # select relevant edges
+        relevant_textedges = textedges.get_relevant()
+        self.textedges.extend(relevant_textedges)
+        # guess table areas using textlines and relevant edges
+        table_bbox = textedges.get_table_areas(textlines, relevant_textedges)
+        # treat whole page as table area if no table areas found
+        if not len(table_bbox):
+            table_bbox = {(0, 0, self.pdf_width, self.pdf_height): None}
+
+        return table_bbox
+
     def _generate_table_bbox(self):
+        self.textedges = []
         if self.table_areas is not None:
             table_bbox = {}
             for area in self.table_areas:
@@ -257,7 +285,8 @@ class Stream(BaseParser):
                 y2 = float(y2)
                 table_bbox[(x1, y2, x2, y1)] = None
         else:
-            table_bbox = {(0, 0, self.pdf_width, self.pdf_height): None}
+            # find tables based on nurminen's detection algorithm
+            table_bbox = self._nurminen_table_detection(self.horizontal_text)
         self.table_bbox = table_bbox
 
     def _generate_columns_and_rows(self, table_idx, tk):
@@ -265,13 +294,14 @@ class Stream(BaseParser):
         t_bbox = {}
         t_bbox['horizontal'] = text_in_bbox(tk, self.horizontal_text)
         t_bbox['vertical'] = text_in_bbox(tk, self.vertical_text)
+
+        t_bbox['horizontal'].sort(key=lambda x: (-x.y0, x.x0))
+        t_bbox['vertical'].sort(key=lambda x: (x.x0, -x.y0))
+
         self.t_bbox = t_bbox
 
-        for direction in self.t_bbox:
-            self.t_bbox[direction].sort(key=lambda x: (-x.y0, x.x0))
-
         text_x_min, text_y_min, text_x_max, text_y_max = self._text_bbox(self.t_bbox)
-        rows_grouped = self._group_rows(self.t_bbox['horizontal'], row_close_tol=self.row_close_tol)
+        rows_grouped = self._group_rows(self.t_bbox['horizontal'], row_tol=self.row_tol)
         rows = self._join_rows(rows_grouped, text_y_max, text_y_min)
         elements = [len(r) for r in rows_grouped]
 
@@ -286,12 +316,23 @@ class Stream(BaseParser):
             cols.append(text_x_max)
             cols = [(cols[i], cols[i + 1]) for i in range(0, len(cols) - 1)]
         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 ncols == 1:
-                warnings.warn("No tables found on {}".format(
-                    os.path.basename(self.rootname)))
+                # if mode is 1, the page usually contains not tables
+                # but there can be cases where the list can be skewed,
+                # try to remove all 1s from list in this case and
+                # see if the list contains elements, if yes, then use
+                # the mode after removing 1s
+                elements = list(filter(lambda x: x != 1, elements))
+                if len(elements):
+                    ncols = max(set(elements), key=elements.count)
+                else:
+                    warnings.warn("No tables found in table area {}".format(
+                        table_idx + 1))
             cols = [(t.x0, t.x1) for r in rows_grouped if len(r) == ncols for t in r]
-            cols = self._merge_columns(sorted(cols), col_close_tol=self.col_close_tol)
+            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]
@@ -303,7 +344,7 @@ class Stream(BaseParser):
                             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_close_tol)
+            cols = self._add_columns(cols, inner_text, self.row_tol)
             cols = self._join_columns(cols, text_x_min, text_x_max)
 
         return cols, rows
@@ -311,12 +352,15 @@ class Stream(BaseParser):
     def _generate_table(self, table_idx, cols, rows, **kwargs):
         table = Table(cols, rows)
         table = table.set_all_edges()
+
         pos_errors = []
-        for direction in self.t_bbox:
+        # TODO: have a single list in place of two directional ones?
+        # sorted on x-coordinate based on reading order i.e. LTR or RTL
+        for direction in ['vertical', 'horizontal']:
             for t in self.t_bbox[direction]:
                 indices, error = get_table_index(
                     table, t, direction, split_text=self.split_text,
-                    flag_size=self.flag_size)
+                    flag_size=self.flag_size, strip_text=self.strip_text)
                 if indices[:2] != (-1, -1):
                     pos_errors.append(error)
                     for r_idx, c_idx, text in indices:
@@ -341,12 +385,14 @@ class Stream(BaseParser):
         table._text = _text
         table._image = None
         table._segments = None
+        table._textedges = self.textedges
 
         return table
 
-    def extract_tables(self, filename):
-        self._generate_layout(filename)
-        logger.info('Processing {}'.format(os.path.basename(self.rootname)))
+    def extract_tables(self, filename, suppress_stdout=False, layout_kwargs={}):
+        self._generate_layout(filename, layout_kwargs)
+        if not suppress_stdout:
+            logger.info('Processing {}'.format(os.path.basename(self.rootname)))
 
         if not self.horizontal_text:
             warnings.warn("No tables found on {}".format(
@@ -361,6 +407,7 @@ class Stream(BaseParser):
                 self.table_bbox.keys(), key=lambda x: x[1], reverse=True)):
             cols, rows = self._generate_columns_and_rows(table_idx, tk)
             table = self._generate_table(table_idx, cols, rows)
+            table._bbox = tk
             _tables.append(table)
 
         return _tables

camelot/plotting.py

@@ -33,7 +33,10 @@ class PlotMethods(object):
         if not _HAS_MPL:
             raise ImportError('matplotlib is required for plotting.')
 
-        if table.flavor == 'stream' and kind in ['contour', 'joint', 'line']:
+        if table.flavor == 'lattice' and kind in ['textedge']:
+            raise NotImplementedError("Lattice flavor does not support kind='{}'".format(
+                                      kind))
+        elif table.flavor == 'stream' and kind in ['joint', 'line']:
             raise NotImplementedError("Stream flavor does not support kind='{}'".format(
                                       kind))
 
@@ -114,20 +117,82 @@ class PlotMethods(object):
         fig : matplotlib.fig.Figure
 
         """
-        img, table_bbox = table._image
+        try:
+            img, table_bbox = table._image
+            _FOR_LATTICE = True
+        except TypeError:
+            img, table_bbox = (None, {table._bbox: None})
+            _FOR_LATTICE = False
         fig = plt.figure()
         ax = fig.add_subplot(111, aspect='equal')
+
+        xs, ys = [], []
+        if not _FOR_LATTICE:
+            for t in table._text:
+                xs.extend([t[0], t[2]])
+                ys.extend([t[1], t[3]])
+                ax.add_patch(
+                    patches.Rectangle(
+                        (t[0], t[1]),
+                        t[2] - t[0],
+                        t[3] - t[1],
+                        color='blue'
+                    )
+                )
+
         for t in table_bbox.keys():
             ax.add_patch(
                 patches.Rectangle(
                     (t[0], t[1]),
                     t[2] - t[0],
                     t[3] - t[1],
-                    fill=None,
-                    edgecolor='red'
+                    fill=False,
+                    color='red'
                 )
             )
-        ax.imshow(img)
+            if not _FOR_LATTICE:
+                xs.extend([t[0], t[2]])
+                ys.extend([t[1], t[3]])
+                ax.set_xlim(min(xs) - 10, max(xs) + 10)
+                ax.set_ylim(min(ys) - 10, max(ys) + 10)
+
+        if _FOR_LATTICE:
+            ax.imshow(img)
+        return fig
+
+    def textedge(self, table):
+        """Generates a plot for relevant textedges.
+
+        Parameters
+        ----------
+        table : camelot.core.Table
+
+        Returns
+        -------
+        fig : matplotlib.fig.Figure
+
+        """
+        fig = plt.figure()
+        ax = fig.add_subplot(111, aspect='equal')
+        xs, ys = [], []
+        for t in table._text:
+            xs.extend([t[0], t[2]])
+            ys.extend([t[1], t[3]])
+            ax.add_patch(
+                patches.Rectangle(
+                    (t[0], t[1]),
+                    t[2] - t[0],
+                    t[3] - t[1],
+                    color='blue'
+                )
+            )
+        ax.set_xlim(min(xs) - 10, max(xs) + 10)
+        ax.set_ylim(min(ys) - 10, max(ys) + 10)
+
+        for te in table._textedges:
+            ax.plot([te.x, te.x],
+                    [te.y0, te.y1])
+
         return fig
 
     def joint(self, table):

camelot/utils.py

@@ -1,12 +1,17 @@
+# -*- coding: utf-8 -*-
 from __future__ import division
+
+import os
+import sys
+import random
 import shutil
+import string
 import tempfile
 import warnings
 from itertools import groupby
 from operator import itemgetter
 
 import numpy as np
-
 from pdfminer.pdfparser import PDFParser
 from pdfminer.pdfdocument import PDFDocument
 from pdfminer.pdfpage import PDFPage
@@ -18,18 +23,89 @@ from pdfminer.layout import (LAParams, LTAnno, LTChar, LTTextLineHorizontal,
                              LTTextLineVertical)
 
 
+PY3 = sys.version_info[0] >= 3
+if PY3:
+    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)
+_VALID_URLS.discard('')
+
+
+# https://github.com/pandas-dev/pandas/blob/master/pandas/io/common.py
+def is_url(url):
+    """Check to see if a URL has a valid protocol.
+
+    Parameters
+    ----------
+    url : str or unicode
+
+    Returns
+    -------
+    isurl : bool
+        If url has a valid protocol return True otherwise False.
+
+    """
+    try:
+        return parse_url(url).scheme in _VALID_URLS
+    except Exception:
+        return False
+
+
+def random_string(length):
+    ret = ''
+    while length:
+        ret += random.choice(string.digits + string.ascii_lowercase + string.ascii_uppercase)
+        length -= 1
+    return ret
+
+
+def download_url(url):
+    """Download file from specified URL.
+
+    Parameters
+    ----------
+    url : str or unicode
+
+    Returns
+    -------
+    filepath : str or unicode
+        Temporary filepath.
+
+    """
+    filename = '{}.pdf'.format(random_string(6))
+    with tempfile.NamedTemporaryFile('wb', delete=False) as f:
+        obj = urlopen(url)
+        if PY3:
+            content_type = obj.info().get_content_type()
+        else:
+            content_type = obj.info().getheader('Content-Type')
+        if content_type != 'application/pdf':
+            raise NotImplementedError("File format not supported")
+        f.write(obj.read())
+    filepath = os.path.join(os.path.dirname(f.name), filename)
+    shutil.move(f.name, filepath)
+    return filepath
+
+
 stream_kwargs = [
     'columns',
-    'row_close_tol',
-    'col_close_tol'
+    'row_tol',
+    'column_tol'
 ]
 lattice_kwargs = [
     'process_background',
     'line_size_scaling',
     'copy_text',
     'shift_text',
-    'line_close_tol',
-    'joint_close_tol',
+    'line_tol',
+    'joint_tol',
     'threshold_blocksize',
     'threshold_constant',
     'iterations'
@@ -281,14 +357,14 @@ def text_in_bbox(bbox, text):
     return t_bbox
 
 
-def merge_close_lines(ar, line_close_tol=2):
+def merge_close_lines(ar, line_tol=2):
     """Merges lines which are within a tolerance by calculating a
     moving mean, based on their x or y axis projections.
 
     Parameters
     ----------
     ar : list
-    line_close_tol : int, optional (default: 2)
+    line_tol : int, optional (default: 2)
 
     Returns
     -------
@@ -301,7 +377,7 @@ def merge_close_lines(ar, line_close_tol=2):
             ret.append(a)
         else:
             temp = ret[-1]
-            if np.isclose(temp, a, atol=line_close_tol):
+            if np.isclose(temp, a, atol=line_tol):
                 temp = (temp + a) / 2.0
                 ret[-1] = temp
             else:
@@ -309,7 +385,12 @@ def merge_close_lines(ar, line_close_tol=2):
     return ret
 
 
-def flag_font_size(textline, direction):
+# TODO: combine the following functions into a TextProcessor class which
+# applies corresponding transformations sequentially
+# (inspired from sklearn.pipeline.Pipeline)
+
+
+def flag_font_size(textline, direction, strip_text=''):
     """Flags super/subscripts in text by enclosing them with <s></s>.
     May give false positives.
 
@@ -319,6 +400,9 @@ def flag_font_size(textline, direction):
         List of PDFMiner LTChar objects.
     direction : string
         Direction of the PDFMiner LTTextLine object.
+    strip_text : str, optional (default: '')
+        Characters that should be stripped from a string before
+        assigning it to a cell.
 
     Returns
     -------
@@ -344,13 +428,13 @@ def flag_font_size(textline, direction):
                 fchars = [t[0] for t in chars]
                 if ''.join(fchars).strip():
                     flist.append(''.join(fchars))
-        fstring = ''.join(flist).strip('\n')
+        fstring = ''.join(flist).strip(strip_text)
     else:
-        fstring = ''.join([t.get_text() for t in textline]).strip('\n')
+        fstring = ''.join([t.get_text() for t in textline]).strip(strip_text)
     return fstring
 
 
-def split_textline(table, textline, direction, flag_size=False):
+def split_textline(table, textline, direction, flag_size=False, strip_text=''):
     """Splits PDFMiner LTTextLine into substrings if it spans across
     multiple rows/columns.
 
@@ -365,6 +449,9 @@ def split_textline(table, textline, direction, flag_size=False):
         Whether or not to highlight a substring using <s></s>
         if its size is different from rest of the string. (Useful for
         super and subscripts.)
+    strip_text : str, optional (default: '')
+        Characters that should be stripped from a string before
+        assigning it to a cell.
 
     Returns
     -------
@@ -416,14 +503,15 @@ def split_textline(table, textline, direction, flag_size=False):
     grouped_chars = []
     for key, chars in groupby(cut_text, itemgetter(0, 1)):
         if flag_size:
-            grouped_chars.append((key[0], key[1], flag_font_size([t[2] for t in chars], direction)))
+            grouped_chars.append((key[0], key[1],
+                flag_font_size([t[2] for t in chars], direction, strip_text=strip_text)))
         else:
             gchars = [t[2].get_text() for t in chars]
-            grouped_chars.append((key[0], key[1], ''.join(gchars).strip('\n')))
+            grouped_chars.append((key[0], key[1], ''.join(gchars).strip(strip_text)))
     return grouped_chars
 
 
-def get_table_index(table, t, direction, split_text=False, flag_size=False):
+def get_table_index(table, t, direction, split_text=False, flag_size=False, strip_text='',):
     """Gets indices of the table cell where given text object lies by
     comparing their y and x-coordinates.
 
@@ -441,6 +529,9 @@ def get_table_index(table, t, direction, split_text=False, flag_size=False):
         Whether or not to highlight a substring using <s></s>
         if its size is different from rest of the string. (Useful for
         super and subscripts)
+    strip_text : str, optional (default: '')
+        Characters that should be stripped from a string before
+        assigning it to a cell.
 
     Returns
     -------
@@ -495,12 +586,12 @@ def get_table_index(table, t, direction, split_text=False, flag_size=False):
     error = ((X * (y0_offset + y1_offset)) + (Y * (x0_offset + x1_offset))) / charea
 
     if split_text:
-        return split_textline(table, t, direction, flag_size=flag_size), error
+        return split_textline(table, t, direction, flag_size=flag_size, strip_text=strip_text), error
     else:
         if flag_size:
-            return [(r_idx, c_idx, flag_font_size(t._objs, direction))], error
+            return [(r_idx, c_idx, flag_font_size(t._objs, direction, strip_text=strip_text))], error
         else:
-            return [(r_idx, c_idx, t.get_text().strip('\n'))], error
+            return [(r_idx, c_idx, t.get_text().strip(strip_text))], error
 
 
 def compute_accuracy(error_weights):
@@ -558,7 +649,7 @@ def compute_whitespace(d):
 
 
 def get_page_layout(filename, char_margin=1.0, line_margin=0.5, word_margin=0.1,
-               detect_vertical=True, all_texts=True):
+                    detect_vertical=True, all_texts=True):
     """Returns a PDFMiner LTPage object and page dimension of a single
     page pdf. See https://euske.github.io/pdfminer/ to get definitions
     of kwargs.

docs/benchmark/lattice/agstat/agstat-data-pdfplumber.csv

@@ -0,0 +1,96 @@
+"0","1","2","3","4","5","6","7","8","9","10"
+"Sl.
+No.","District","n
+o
+i
+t
+a
+l3
+opu2-1hs)
+P1k
+d 20 la
+er n
+cto(I
+ef
+j
+o
+r
+P","%
+8
+8
+o )
+s
+ult t  tkh
+dna
+Aalen l
+v(I
+i
+u
+q
+E",")
+y
+n a
+umptiomentadult/donnes)
+nsres/h t
+ouimk
+Cqga
+al re00n L
+ot  4(I
+T @
+(","menteds, age)nes)
+uireg sewastton
+qn h 
+Reudis &ak
+al cld L
+tnen
+To(Ife(I","","","","",""
+"","","","","","","f
+i
+r
+a
+h
+K","i
+b
+a
+R","l
+a
+t
+o
+T","e
+c
+i
+R","y
+d
+d
+a
+P"
+"1","Balasore","23.65","20.81","3.04","3.47","2.78","0.86","3.64","0.17","0.25"
+"2","Bhadrak","15.34","13.50","1.97","2.25","3.50","0.05","3.55","1.30","1.94"
+"3","Balangir","17.01","14.97","2.19","2.50","6.23","0.10","6.33","3.83","5.72"
+"4","Subarnapur","6.70","5.90","0.86","0.98","4.48","1.13","5.61","4.63","6.91"
+"5","Cuttack","26.63","23.43","3.42","3.91","3.75","0.06","3.81","-0.10","-0.15"
+"6","Jagatsingpur","11.49","10.11","1.48","1.69","2.10","0.02","2.12","0.43","0.64"
+"7","Jajpur","18.59","16.36","2.39","2.73","2.13","0.04","2.17","-0.56","-0.84"
+"8","Kendrapara","14.62","12.87","1.88","2.15","2.60","0.07","2.67","0.52","0.78"
+"9","Dhenkanal","12.13","10.67","1.56","1.78","2.26","0.02","2.28","0.50","0.75"
+"10","Angul","12.93","11.38","1.66","1.90","1.73","0.02","1.75","-0.15","-0.22"
+"11","Ganjam","35.77","31.48","4.60","5.26","4.57","0.00","4.57","-0.69","-1.03"
+"12","Gajapati","5.85","5.15","0.75","0.86","0.68","0.01","0.69","-0.17","-0.25"
+"13","Kalahandi","16.12","14.19","2.07","2.37","5.42","1.13","6.55","4.18","6.24"
+"14","Nuapada","6.18","5.44","0.79","0.90","1.98","0.08","2.06","1.16","1.73"
+"15","Keonjhar","18.42","16.21","2.37","2.71","2.76","0.08","2.84","0.13","0.19"
+"16","Koraput","14.09","12.40","1.81","2.07","2.08","0.34","2.42","0.35","0.52"
+"17","Malkangiri","6.31","5.55","0.81","0.93","1.78","0.04","1.82","0.89","1.33"
+"18","Nabarangpur","12.50","11.00","1.61","1.84","3.26","0.02","3.28","1.44","2.15"
+"19","Rayagada","9.83","8.65","1.26","1.44","1.15","0.03","1.18","-0.26","-0.39"
+"20","Mayurbhanj","25.61","22.54","3.29","3.76","4.90","0.06","4.96","1.20","1.79"
+"21","Kandhamal","7.45","6.56","0.96","1.10","0.70","0.01","0.71","-0.39","-0.58"
+"22","Boudh","4.51","3.97","0.58","0.66","1.73","0.03","1.76","1.10","1.64"
+"23","Puri","17.29","15.22","2.22","2.54","2.45","0.99","3.44","0.90","1.34"
+"24","Khordha","23.08","20.31","2.97","3.39","2.02","0.03","2.05","-1.34","-2.00"
+"25","Nayagarh","9.78","8.61","1.26","1.44","2.10","0.00","2.10","0.66","0.99"
+"26","Sambalpur","10.62","9.35","1.37","1.57","3.45","0.71","4.16","2.59","3.87"
+"27","Bargarh","15.00","13.20","1.93","2.21","6.87","2.65","9.52","7.31","10.91"
+"28","Deogarh","3.18","2.80","0.41","0.47","1.12","0.07","1.19","0.72","1.07"
+"29","Jharsuguda","5.91","5.20","0.76","0.87","0.99","0.01","1.00","0.13","0.19"
+"30","","","18.66","2.72","3.11","4.72","0.02","4.74","1.63","2.43"

docs/benchmark/lattice/column_span_1/column_span_1-data-pdfplumber.csv

@@ -0,0 +1,56 @@
+"0","1","2","3","4","5","6","7"
+"Rate of Accidental Deaths & Suicides and Population Growth During 1967 to 2013","","","","","","",""
+"Sl. 
+No.","Year","Population 
+(in Lakh)","Accidental Deaths","","Suicides","","Percentage 
+Population 
+growth"
+"","","","Incidence","Rate","Incidence","Rate",""
+"(1)","(2)","(3)","(4)","(5)","(6)","(7)","(8)"
+"1.","1967","4999","126762","25.4","38829","7.8","2.2"
+"2.","1968","5111","126232","24.7","40688","8.0","2.2"
+"3.","1969","5225","130755","25.0","43633","8.4","2.2"
+"4.","1970","5343","139752","26.2","48428","9.1","2.3"
+"5.","1971","5512","105601","19.2","43675","7.9","3.2"
+"6.","1972","5635","106184","18.8","43601","7.7","2.2"
+"7.","1973","5759","130654","22.7","40807","7.1","2.2"
+"8.","1974","5883","110624","18.8","46008","7.8","2.2"
+"9.","1975","6008","113016","18.8","42890","7.1","2.1"
+"10.","1976","6136","111611","18.2","41415","6.7","2.1"
+"11.","1977","6258","117338","18.8","39718","6.3","2.0"
+"12.","1978","6384","118594","18.6","40207","6.3","2.0"
+"13.","1979","6510","108987","16.7","38217","5.9","2.0"
+"14.","1980","6636","116912","17.6","41663","6.3","1.9"
+"15.","1981","6840","122221","17.9","40245","5.9","3.1"
+"16.","1982","7052","125993","17.9","44732","6.3","3.1"
+"17.","1983","7204","128576","17.8","46579","6.5","2.2"
+"18.","1984","7356","134628","18.3","50571","6.9","2.1"
+"19.","1985","7509","139657","18.6","52811","7.0","2.1"
+"20.","1986","7661","147023","19.2","54357","7.1","2.0"
+"21.","1987","7814","152314","19.5","58568","7.5","2.0"
+"22.","1988","7966","163522","20.5","64270","8.1","1.9"
+"23.","1989","8118","169066","20.8","68744","8.5","1.9"
+"24.","1990","8270","174401","21.1","73911","8.9","1.9"
+"25.","1991","8496","188003","22.1","78450","9.2","2.7"
+"26.","1992","8677","194910","22.5","80149","9.2","2.1"
+"27.","1993","8838","192357","21.8","84244","9.5","1.9"
+"28.","1994","8997","190435","21.2","89195","9.9","1.8"
+"29.","1995","9160","222487","24.3","89178","9.7","1.8"
+"30.","1996","9319","220094","23.6","88241","9.5","1.7"
+"31.","1997","9552","233903","24.5","95829","10.0","2.5"
+"32.","1998","9709","258409","26.6","104713","10.8","1.6"
+"33.","1999","9866","271918","27.6","110587","11.2","1.6"
+"34.","2000","10021","255883","25.5","108593","10.8","1.6"
+"35.","2001","10270","271019","26.4","108506","10.6","2.5"
+"36.","2002","10506","260122","24.8","110417","10.5","2.3"
+"37.","2003","10682","259625","24.3","110851","10.4","1.7"
+"38.","2004","10856","277263","25.5","113697","10.5","1.6"
+"39.","2005","11028","294175","26.7","113914","10.3","1.6"
+"40.","2006","11198","314704","28.1","118112","10.5","1.5"
+"41.","2007","11366","340794","30.0","122637","10.8","1.5"
+"42.","2008","11531","342309","29.7","125017","10.8","1.4"
+"43.","2009","11694","357021","30.5","127151","10.9","1.4"
+"44.","2010","11858","384649","32.4","134599","11.4","1.4"
+"45.","2011","12102","390884","32.3","135585","11.2","2.1"
+"46.","2012","12134","394982","32.6","135445","11.2","1.0"
+"47.","2013","12288","400517","32.6","134799","11.0","1.0"

docs/benchmark/lattice/rotated/rotated-data-pdfplumber.csv

@@ -0,0 +1,18 @@
+"0","1","2"
+"","e
+bl
+a
+ail
+v
+a
+ 
+t
+o
+n
+ 
+a
+t
+a
+D
+ 
+*",""

docs/benchmark/lattice/twotables_1/twotables_1-data-pdfplumber.csv

@@ -0,0 +1,3 @@
+"0"
+"Sl."
+"No."

docs/benchmark/lattice/twotables_2/twotables_2-data-pdfplumber.csv

@@ -0,0 +1,3 @@
+"0"
+"Table 6 : DISTRIBUTION (%) OF HOUSEHOLDS BY LITERACY STATUS OF"
+"MALE HEAD OF THE HOUSEHOLD"

docs/benchmark/stream/12s0324/12s0324-data-camelot-page-1-table-1.csv

@@ -1,3 +1,7 @@
+"[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","","","","","","","","",""
+"by the FBI. Some persons may be arrested more than once during a year, therefore, the data in this table, in some cases,","","","","","","","","",""
+"could represent multiple arrests of the same person. See text, this section and source]","","","","","","","","",""
 "","","Total","","","Male","","","Female",""
 "Offense charged","","Under 18","18 years","","Under 18","18 years","","Under 18","18 years"
 "","Total","years","and over","Total","years","and over","Total","years","and over"
@@ -36,3 +40,4 @@
 "Curfew and loitering law violations  ..","91.0","91.0","(X)","63.1","63.1","(X)","28.0","28.0","(X)"
 "Runaways  . . . . . . . .. .. .. .. .. ....","75.8","75.8","(X)","34.0","34.0","(X)","41.8","41.8","(X)"
 "","– Represents zero. X Not applicable. 1 Buying, receiving, possessing stolen property. 2 Except forcible rape and prostitution.","","","","","","","",""
+"","Source: U.S. Department of Justice, Federal Bureau of Investigation, Uniform Crime Reports, Arrests Master Files.","","","","","","","",""

docs/benchmark/stream/12s0324/12s0324-data-camelot-page-1-table-2.csv

@@ -1,3 +1,7 @@
+"","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","","","","",""
+"with a total population of 239,839,971 as estimated by the FBI. See headnote, Table 324]","","","","",""
 "","","","","American",""
 "Offense charged","","","","Indian/Alaskan","Asian Pacific"
 "","Total","White","Black","Native","Islander"
@@ -34,3 +38,4 @@
 "Curfew and loitering law violations  . .. ... .. ....","89,578","54,439","33,207","872","1,060"
 "Runaways  . . . . . . . .. .. .. .. .. .. .... .. ..... .","73,616","48,343","19,670","1,653","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,","","","",""

docs/benchmark/stream/birdisland/birdisland-data-camelot-page-1-table-1.csv

@@ -1,35 +1,43 @@
-"","","","","","SCN","Seed","Yield","Moisture","Lodgingg","g","Stand","","Gross"
-"Company/Brandpy","","Product/Brand†","Technol.†","Mat.","Resist.","Trmt.†","Bu/A","%","%","","(x 1000)(",")","Income"
-"KrugerKruger","","K2-1901K2 1901","RR2YRR2Y","1.91.9","RR","Ac,PVAc,PV","56.456.4","7.67.6","00","","126.3126.3","","$846$846"
-"StineStine","","19RA02 §19RA02 §","RR2YRR2Y","1 91.9","RR","CMBCMB","55.355.3","7 67.6","00","","120 0120.0","","$830$830"
-"WensmanWensman","","W 3190NR2W 3190NR2","RR2YRR2Y","1 91.9","RR","AcAc","54 554.5","7 67.6","00","","119 5119.5","","$818$818"
-"H ftHefty","","H17Y12H17Y12","RR2YRR2Y","1 71.7","MRMR","II","53 753.7","7 77.7","00","","124 4124.4","","$806$806"
-"Dyna-Gro","","S15RY53","RR2Y","1.5","R","Ac","53.6","7.7","0","","126.8","","$804"
-"LG SeedsLG Seeds","","C2050R2C2050R2","RR2YRR2Y","2.12.1","RR","AcAc","53.653.6","7.77.7","00","","123.9123.9","","$804$804"
-"Titan ProTitan Pro","","19M4219M42","RR2YRR2Y","1.91.9","RR","CMBCMB","53.653.6","7.77.7","00","","121.0121.0","","$804$804"
-"StineStine","","19RA02 (2) §19RA02 (2) §","RR2YRR2Y","1 91.9","RR","CMBCMB","53 453.4","7 77.7","00","","123 9123.9","","$801$801"
-"AsgrowAsgrow","","AG1832 §AG1832 §","RR2YRR2Y","1 81.8","MRMR","Ac PVAc,PV","52 952.9","7 77.7","00","","122 0122.0","","$794$794"
-"Prairie Brandiid","","PB-1566R2662","RR2Y2","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 ProTitan Pro","","20M120M1","RR2YRR2Y","2.02.0","RR","AmAm","52.552.5","7.57.5","00","","124.4124.4","","$788$788"
-"KrugerKruger","","K2-2002K2-2002","RR2YRR2Y","2 02.0","RR","Ac PVAc,PV","52 452.4","7 97.9","00","","125 4125.4","","$786$786"
-"ChannelChannel","","1700R21700R2","RR2YRR2Y","1 71.7","RR","Ac PVAc,PV","52 352.3","7 97.9","00","","123 9123.9","","$784$784"
-"H ftHefty","","H16Y11H16Y11","RR2YRR2Y","1 61.6","MRMR","II","51 451.4","7 67.6","00","","123 9123.9","","$771$771"
-"Anderson","","162R2Y","RR2Y","1.6","R","None","51.3","7.5","0","","119.5","","$770"
-"Titan ProTitan Pro","","15M2215M22","RR2YRR2Y","1.51.5","RR","CMBCMB","51.351.3","7.87.8","00","","125.4125.4","","$769$769"
-"DairylandDairyland","","DSR-1710R2YDSR-1710R2Y","RR2YRR2Y","1 71.7","RR","CMBCMB","51 351.3","7 77.7","00","","122 0122.0","","$769$769"
-"HeftyHefty","","H20R3H20R3","RR2YRR2Y","2 02.0","MRMR","II","50 550.5","8 28.2","00","","121 0121.0","","$757$757"
-"PPrairie BrandiiBd","","PB 1743R2PB-1743R2","RR2YRR2Y","1 71.7","RR","CMBCMB","50 250.2","7 77.7","00","","125 8125.8","","$752$752"
-"Gold Country","","1741","RR2Y","1.7","R","Ac","50.1","7.8","0","","123.9","","$751"
-"Trelaye ay","","20RR4303","RR2Y","2.00","R","Ac,Exc,","49.99 9","7.66","00","","127.88","","$749$9"
-"HeftyHefty","","H14R3H14R3","RR2YRR2Y","1.41.4","MRMR","II","49.749.7","7.77.7","00","","122.9122.9","","$746$746"
-"Prairie BrandPrairie Brand","","PB-2099NRR2PB-2099NRR2","RR2YRR2Y","2 02.0","RR","CMBCMB","49 649.6","7 87.8","00","","126 3126.3","","$743$743"
-"WensmanWensman","","W 3174NR2W 3174NR2","RR2YRR2Y","1 71.7","RR","AcAc","49 349.3","7 67.6","00","","122 5122.5","","$740$740"
-"KKruger","","K2 1602K2-1602","RR2YRR2Y","1 61.6","R","Ac,PV","48.78","7.66","00","","125.412","","$731$31"
-"NK Brand","","S18-C2 §§","RR2Y","1.8","R","CMB","48.7","7.7","0","","126.8","","$731$"
-"KrugerKruger","","K2-1902K2 1902","RR2YRR2Y","1.91.9","RR","Ac,PVAc,PV","48.748.7","7.57.5","00","","124.4124.4","","$730$730"
-"Prairie BrandPrairie Brand","","PB-1823R2PB-1823R2","RR2YRR2Y","1 81.8","RR","NoneNone","48 548.5","7 67.6","00","","121 0121.0","","$727$727"
-"Gold CountryGold Country","","15411541","RR2YRR2Y","1 51.5","RR","AcAc","48 448.4","7 67.6","00","","110 4110.4","","$726$726"
-"","","","","","","Test Average  =","47 647.6","7 77.7","00","","122 9122.9","","$713$713"
-"","","","","","","LSD (0.10)  =","5.7","0.3","ns","","37.8","","566.4"
-"","F.I.R.S.T. Managerg","","","","","C.V.  =","8.8","2.9","","","56.4","","846.2"
+"","2012 BETTER VARIETIES Harvest Report for Minnesota Central  [ MNCE ]2012 BETTER VARIETIES Harvest Report for Minnesota Central  [ MNCE ]","","","","","","","","","","","","ALL SEASON TESTALL SEASON TEST",""
+"","Doug Toreen, Renville County, MN 55310          [ BIRD ISLAND ]Doug Toreen, Renville County, MN 55310","","","","","[ BIRD ISLAND ]","","","","","","","1.3 - 2.0 MAT. GROUP1.3 - 2.0 MAT. GROUP",""
+"PREVPREV. CROP/HERB:","CROP/HERB","C/ S","Corn / Surpass, RoundupR","d","","","","","","","","","","S2MNCE01S2MNCE01"
+"SOIL DESCRIPTION:","","C","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:TILLAGE/CULTIVATION:","","","conventional w/ fall tillconventional w/ fall till","","","","","","","","","","",""
+"PEST MANAGEMENT:PEST MANAGEMENT:","","Roundup twiceRoundup twice","","","","","","","","","","","",""
+"SEEDED - RATE:","","May 15M15","140,000 /A140 000 /A","","","","","","","","TOP 30 foTOP 30 for YIELD of 63 TESTED","","YIELD of 63 TESTED",""
+"HARVESTEDHARVESTED - STAND:","STAND","O t 3Oct 3","122 921 /A122,921 /A","","","","","","","","","AVERAGE of (3) REPLICATIONSAVERAGE of (3) REPLICATIONS","",""
+"","","","","","","SCN","Seed","Yield","Moisture","Lodgingg","g","Stand","","Gross"
+"","Company/Brandpy","Product/Brand†","","Technol.†","Mat.","Resist.","Trmt.†","Bu/A","%","%","","(x 1000)(",")","Income"
+"","KrugerKruger","K2-1901K2 1901","","RR2YRR2Y","1.91.9","RR","Ac,PVAc,PV","56.456.4","7.67.6","00","","126.3126.3","","$846$846"
+"","StineStine","19RA02 §19RA02 §","","RR2YRR2Y","1 91.9","RR","CMBCMB","55.355.3","7 67.6","00","","120 0120.0","","$830$830"
+"","WensmanWensman","W 3190NR2W 3190NR2","","RR2YRR2Y","1 91.9","RR","AcAc","54 554.5","7 67.6","00","","119 5119.5","","$818$818"
+"","H ftHefty","H17Y12H17Y12","","RR2YRR2Y","1 71.7","MRMR","II","53 753.7","7 77.7","00","","124 4124.4","","$806$806"
+"","Dyna-Gro","S15RY53","","RR2Y","1.5","R","Ac","53.6","7.7","0","","126.8","","$804"
+"","LG SeedsLG Seeds","C2050R2C2050R2","","RR2YRR2Y","2.12.1","RR","AcAc","53.653.6","7.77.7","00","","123.9123.9","","$804$804"
+"","Titan ProTitan Pro","19M4219M42","","RR2YRR2Y","1.91.9","RR","CMBCMB","53.653.6","7.77.7","00","","121.0121.0","","$804$804"
+"","StineStine","19RA02 (2) §19RA02 (2) §","","RR2YRR2Y","1 91.9","RR","CMBCMB","53 453.4","7 77.7","00","","123 9123.9","","$801$801"
+"","AsgrowAsgrow","AG1832 §AG1832 §","","RR2YRR2Y","1 81.8","MRMR","Ac PVAc,PV","52 952.9","7 77.7","00","","122 0122.0","","$794$794"
+"","Prairie Brandiid","PB-1566R2662","","RR2Y2","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 ProTitan Pro","20M120M1","","RR2YRR2Y","2.02.0","RR","AmAm","52.552.5","7.57.5","00","","124.4124.4","","$788$788"
+"","KrugerKruger","K2-2002K2-2002","","RR2YRR2Y","2 02.0","RR","Ac PVAc,PV","52 452.4","7 97.9","00","","125 4125.4","","$786$786"
+"","ChannelChannel","1700R21700R2","","RR2YRR2Y","1 71.7","RR","Ac PVAc,PV","52 352.3","7 97.9","00","","123 9123.9","","$784$784"
+"","H ftHefty","H16Y11H16Y11","","RR2YRR2Y","1 61.6","MRMR","II","51 451.4","7 67.6","00","","123 9123.9","","$771$771"
+"","Anderson","162R2Y","","RR2Y","1.6","R","None","51.3","7.5","0","","119.5","","$770"
+"","Titan ProTitan Pro","15M2215M22","","RR2YRR2Y","1.51.5","RR","CMBCMB","51.351.3","7.87.8","00","","125.4125.4","","$769$769"
+"","DairylandDairyland","DSR-1710R2YDSR-1710R2Y","","RR2YRR2Y","1 71.7","RR","CMBCMB","51 351.3","7 77.7","00","","122 0122.0","","$769$769"
+"","HeftyHefty","H20R3H20R3","","RR2YRR2Y","2 02.0","MRMR","II","50 550.5","8 28.2","00","","121 0121.0","","$757$757"
+"","PPrairie BrandiiBd","PB 1743R2PB-1743R2","","RR2YRR2Y","1 71.7","RR","CMBCMB","50 250.2","7 77.7","00","","125 8125.8","","$752$752"
+"","Gold Country","1741","","RR2Y","1.7","R","Ac","50.1","7.8","0","","123.9","","$751"
+"","Trelaye ay","20RR4303","","RR2Y","2.00","R","Ac,Exc,","49.99 9","7.66","00","","127.88","","$749$9"
+"","HeftyHefty","H14R3H14R3","","RR2YRR2Y","1.41.4","MRMR","II","49.749.7","7.77.7","00","","122.9122.9","","$746$746"
+"","Prairie BrandPrairie Brand","PB-2099NRR2PB-2099NRR2","","RR2YRR2Y","2 02.0","RR","CMBCMB","49 649.6","7 87.8","00","","126 3126.3","","$743$743"
+"","WensmanWensman","W 3174NR2W 3174NR2","","RR2YRR2Y","1 71.7","RR","AcAc","49 349.3","7 67.6","00","","122 5122.5","","$740$740"
+"","KKruger","K2 1602K2-1602","","RR2YRR2Y","1 61.6","R","Ac,PV","48.78","7.66","00","","125.412","","$731$31"
+"","NK Brand","S18-C2 §§","","RR2Y","1.8","R","CMB","48.7","7.7","0","","126.8","","$731$"
+"","KrugerKruger","K2-1902K2 1902","","RR2YRR2Y","1.91.9","RR","Ac,PVAc,PV","48.748.7","7.57.5","00","","124.4124.4","","$730$730"
+"","Prairie BrandPrairie Brand","PB-1823R2PB-1823R2","","RR2YRR2Y","1 81.8","RR","NoneNone","48 548.5","7 67.6","00","","121 0121.0","","$727$727"
+"","Gold CountryGold Country","15411541","","RR2YRR2Y","1 51.5","RR","AcAc","48 448.4","7 67.6","00","","110 4110.4","","$726$726"
+"","","","","","","","Test Average  =","47 647.6","7 77.7","00","","122 9122.9","","$713$713"
+"","","","","","","","LSD (0.10)  =","5.7","0.3","ns","","37.8","","566.4"

docs/benchmark/stream/birdisland/birdisland-data-camelot-page-1-table-2.csv

@@ -0,0 +1,39 @@
+"TILLAGE/CULTIVATION:TILLAGE/CULTIVATION:","","conventional w/ fall tillconventional w/ fall till","","","","","","","","","","",""
+"PEST MANAGEMENT:PEST MANAGEMENT:","","Roundup twiceRoundup twice","","","","","","","","","","",""
+"SEEDED - RATE:","","May 15M15","140,000 /A140 000 /A","","","","","","","TOP 30 foTOP 30 for YIELD of 63 TESTED","","YIELD of 63 TESTED",""
+"HARVESTEDHARVESTED - STAND:STAND","","O t 3Oct 3","122 921 /A122,921 /A","","","","","","","","AVERAGE of (3) REPLICATIONSAVERAGE of (3) REPLICATIONS","",""
+"","","","","","SCN","Seed","Yield","Moisture","Lodgingg","g","Stand","","Gross"
+"Company/Brandpy","","Product/Brand†","Technol.†","Mat.","Resist.","Trmt.†","Bu/A","%","%","","(x 1000)(",")","Income"
+"KrugerKruger","","K2-1901K2 1901","RR2YRR2Y","1.91.9","RR","Ac,PVAc,PV","56.456.4","7.67.6","00","","126.3126.3","","$846$846"
+"StineStine","","19RA02 §19RA02 §","RR2YRR2Y","1 91.9","RR","CMBCMB","55.355.3","7 67.6","00","","120 0120.0","","$830$830"
+"WensmanWensman","","W 3190NR2W 3190NR2","RR2YRR2Y","1 91.9","RR","AcAc","54 554.5","7 67.6","00","","119 5119.5","","$818$818"
+"H ftHefty","","H17Y12H17Y12","RR2YRR2Y","1 71.7","MRMR","II","53 753.7","7 77.7","00","","124 4124.4","","$806$806"
+"Dyna-Gro","","S15RY53","RR2Y","1.5","R","Ac","53.6","7.7","0","","126.8","","$804"
+"LG SeedsLG Seeds","","C2050R2C2050R2","RR2YRR2Y","2.12.1","RR","AcAc","53.653.6","7.77.7","00","","123.9123.9","","$804$804"
+"Titan ProTitan Pro","","19M4219M42","RR2YRR2Y","1.91.9","RR","CMBCMB","53.653.6","7.77.7","00","","121.0121.0","","$804$804"
+"StineStine","","19RA02 (2) §19RA02 (2) §","RR2YRR2Y","1 91.9","RR","CMBCMB","53 453.4","7 77.7","00","","123 9123.9","","$801$801"
+"AsgrowAsgrow","","AG1832 §AG1832 §","RR2YRR2Y","1 81.8","MRMR","Ac PVAc,PV","52 952.9","7 77.7","00","","122 0122.0","","$794$794"
+"Prairie Brandiid","","PB-1566R2662","RR2Y2","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 ProTitan Pro","","20M120M1","RR2YRR2Y","2.02.0","RR","AmAm","52.552.5","7.57.5","00","","124.4124.4","","$788$788"
+"KrugerKruger","","K2-2002K2-2002","RR2YRR2Y","2 02.0","RR","Ac PVAc,PV","52 452.4","7 97.9","00","","125 4125.4","","$786$786"
+"ChannelChannel","","1700R21700R2","RR2YRR2Y","1 71.7","RR","Ac PVAc,PV","52 352.3","7 97.9","00","","123 9123.9","","$784$784"
+"H ftHefty","","H16Y11H16Y11","RR2YRR2Y","1 61.6","MRMR","II","51 451.4","7 67.6","00","","123 9123.9","","$771$771"
+"Anderson","","162R2Y","RR2Y","1.6","R","None","51.3","7.5","0","","119.5","","$770"
+"Titan ProTitan Pro","","15M2215M22","RR2YRR2Y","1.51.5","RR","CMBCMB","51.351.3","7.87.8","00","","125.4125.4","","$769$769"
+"DairylandDairyland","","DSR-1710R2YDSR-1710R2Y","RR2YRR2Y","1 71.7","RR","CMBCMB","51 351.3","7 77.7","00","","122 0122.0","","$769$769"
+"HeftyHefty","","H20R3H20R3","RR2YRR2Y","2 02.0","MRMR","II","50 550.5","8 28.2","00","","121 0121.0","","$757$757"
+"PPrairie BrandiiBd","","PB 1743R2PB-1743R2","RR2YRR2Y","1 71.7","RR","CMBCMB","50 250.2","7 77.7","00","","125 8125.8","","$752$752"
+"Gold Country","","1741","RR2Y","1.7","R","Ac","50.1","7.8","0","","123.9","","$751"
+"Trelaye ay","","20RR4303","RR2Y","2.00","R","Ac,Exc,","49.99 9","7.66","00","","127.88","","$749$9"
+"HeftyHefty","","H14R3H14R3","RR2YRR2Y","1.41.4","MRMR","II","49.749.7","7.77.7","00","","122.9122.9","","$746$746"
+"Prairie BrandPrairie Brand","","PB-2099NRR2PB-2099NRR2","RR2YRR2Y","2 02.0","RR","CMBCMB","49 649.6","7 87.8","00","","126 3126.3","","$743$743"
+"WensmanWensman","","W 3174NR2W 3174NR2","RR2YRR2Y","1 71.7","RR","AcAc","49 349.3","7 67.6","00","","122 5122.5","","$740$740"
+"KKruger","","K2 1602K2-1602","RR2YRR2Y","1 61.6","R","Ac,PV","48.78","7.66","00","","125.412","","$731$31"
+"NK Brand","","S18-C2 §§","RR2Y","1.8","R","CMB","48.7","7.7","0","","126.8","","$731$"
+"KrugerKruger","","K2-1902K2 1902","RR2YRR2Y","1.91.9","RR","Ac,PVAc,PV","48.748.7","7.57.5","00","","124.4124.4","","$730$730"
+"Prairie BrandPrairie Brand","","PB-1823R2PB-1823R2","RR2YRR2Y","1 81.8","RR","NoneNone","48 548.5","7 67.6","00","","121 0121.0","","$727$727"
+"Gold CountryGold Country","","15411541","RR2YRR2Y","1 51.5","RR","AcAc","48 448.4","7 67.6","00","","110 4110.4","","$726$726"
+"","","","","","","Test Average  =","47 647.6","7 77.7","00","","122 9122.9","","$713$713"
+"","","","","","","LSD (0.10)  =","5.7","0.3","ns","","37.8","","566.4"
+"","F.I.R.S.T. Managerg","","","","","C.V.  =","8.8","2.9","","","56.4","","846.2"

docs/benchmark/stream/district_health/district_health-data-pdfplumber.csv

@@ -0,0 +1,66 @@
+"0","1","2","3","4"
+"","DLHS-4 (2012-13)","","DLHS-3 (2007-08)",""
+"Indicators","TOTAL","RURAL","TOTAL","RURAL"
+"Child feeding practices (based on last-born child in the reference period) (%)","","","",""
+"Children age 0-5 months exclusively breastfed9 ..........................................................................  76.9  80.0 
+Children age 6-9 months receiving solid/semi-solid food and breast milk ....................................  78.6  75.0 
+Children age 12-23 months receiving breast feeding along with complementary feeding ...........  31.8  24.2   
+Children age 6-35 months exclusively breastfed for at least 6 months ........................................  4.7  3.4 
+Children under 3 years breastfed within one hour of birth ............................................................  42.9  46.5","","","NA","NA"
+"","","","85.9","89.3"
+"","","","NA","NA"
+"","","","30.0","27.7"
+"","","","50.6","52.9"
+"Birth Weight (%) (age below 36 months)","","","",""
+"Percentage of Children weighed at birth ......................................................................................  38.8  41.0  NA  NA 
+Percentage of Children with low birth weight (out of those who weighted) ( below 2.5 kg) .........  12.8  14.6  NA  NA","","","",""
+"Awareness about Diarrhoea (%)","","","",""
+"Women know about  what to do when a child gets  diarrhoea .....................................................  96.3  96.2","","","94.4","94.2"
+"Awareness about ARI (%)","","","",""
+"Women aware about danger signs of ARI10 .................................................................................  55.9  59.7","","","32.8","34.7"
+"Treatment of childhood diseases (based on last two surviving children born during the","","","",""
+"","","","",""
+"reference period) (%)","","","",""
+"","","","",""
+"Prevalence of diarrhoea in last 2 weeks for under 5 years old children .......................................  1.6  1.3  6.5  7.0 
+Children with diarrhoea in the last 2 weeks and received ORS11 .................................................  100.0  100.0  54.8  53.3 
+Children with diarrhoea in the last 2 weeks and sought advice/treatment ...................................  100.0  50.0  72.9  73.3 
+Prevalence of ARI in last 2 weeks for under 5 years old children ............................................   4.3  3.9  3.9  4.2 
+Children with acute respiratory infection or fever in last 2 weeks and sought advice/treatment  37.5  33.3  69.8  68.0 
+Children with diarrhoea in the last 2 weeks given Zinc along with ORS ......................................  66.6  50.0  NA  NA","","","6.5","7.0"
+"","","","54.8","53.3"
+"","","","72.9","73.3"
+"","","","3.9","4.2"
+"","","","69.8","68.0"
+"Awareness of RTI/STI and HIV/AIDS (%)","","","",""
+"Women who have heard of RTI/STI .............................................................................................  55.8  57.1 
+Women who have heard of HIV/AIDS ..........................................................................................  98.9  99.0 
+Women who have any symptoms of RTI/STI  ..............................................................................  13.9  13.5 
+Women who know the place to go for testing of HIV/AIDS12 .......................................................  59.9  57.1 
+Women underwent test for detecting HIV/AIDS12 ........................................................................  37.3  36.8","","","34.8","38.2"
+"","","","98.3","98.1"
+"","","","15.6","16.1"
+"","","","48.6","46.3"
+"","","","14.1","12.3"
+"Utilization of Government Health Services (%)","","","",""
+"Antenatal care ..............................................................................................................................  69.7  66.7  79.0  81.0 
+Treatment for pregnancy complications .......................................................................................  57.1  59.3  88.0  87.8 
+Treatment for post-delivery complications ...................................................................................  33.3  33.3  68.4  68.4 
+Treatment for vaginal discharge ...................................................................................................  20.0  25.0  73.9  71.4 
+Treatment for children with diarrhoea13 ........................................................................................  50.0  100.0  NA  NA 
+Treatment for children with ARI13 .................................................................................................  NA  NA  NA  NA","","","79.0","81.0"
+"","","","88.0","87.8"
+"","","","68.4","68.4"
+"","","","73.9","71.4"
+"Birth Registration (%)","","","",""
+"Children below age 5 years having birth registration done ..........................................................  40.6  44.3  NA  NA 
+Children below age 5 years who received birth certificate (out of those registered) ....................  65.9  63.6  NA  NA","","","",""
+"Personal Habits (age 15 years and above) (%)","","","",""
+"Men who use any kind of smokeless tobacco  .............................................................................  74.6  74.2  NA  NA 
+Women who use any kind of smokeless tobacco ........................................................................  59.5  58.9  NA  NA 
+Men who smoke ...........................................................................................................................  56.0  56.4  NA  NA 
+Women who smoke ......................................................................................................................  18.4  18.0  NA  NA 
+Men who consume alcohol ...........................................................................................................  58.4  58.2  NA  NA 
+Women who consume alcohol .....................................................................................................  10.9  9.3  NA  NA","","","",""
+"9 Children Who were given nothing but breast milk till the survey date  10Acute Respiratory Infections11Oral Rehydration Solutions/Salts.12Based on","","","",""
+"the women who have heard of HIV/AIDS.13 Last two weeks","","","",""

docs/benchmark/stream/health/health-data-pdfplumber.csv

@@ -0,0 +1,44 @@
+"0","1","2","3","4","5","6","7","8","9","10","11","12","13","14","15","16","17","18","19","20","21","22","23"
+"","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 
+Public  Welfare  Public  Welfare 
+Health  Health","","","","","","","","","","","","","","","","","","","",""
+"","","","","","","","","","","","","","","","","Capital","","","","","","",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"","Andhra Pradesh","","","47,824,589","","","9,967,837","","","1,275,000","","","15,000","","","59,082,426","","","14,898,243","","","73,980,669",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"Arunachal Pradesh   2,241,609  107,549  23,000  0  2,372,158  86,336  2,458,494","","","","","","","","","","","","","","","","","","","","","","",""
+"","Assam","","","14,874,821","","","2,554,197","","","161,600","","","0","","","17,590,618","","","4,408,505","","","21,999,123",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"Bihar   21,016,708  4,332,141  5,329,000  0  30,677,849  2,251,571  32,929,420","","","","","","","","","","","","","","","","","","","","","","",""
+"","Chhattisgarh","","","11,427,311","","","1,415,660","","","2,366,592","","","0","","","15,209,563","","","311,163","","","15,520,726",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"Delhi  28,084,780  411,700  4,550,000  0  33,046,480  5,000  33,051,480","","","","","","","","","","","","","","","","","","","","","","",""
+"","Goa","","","4,055,567","","","110,000","","","330,053","","","0","","","4,495,620","","","12,560","","","4,508,180",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"Gujarat  26,328,400  6,922,900  12,664,000  42,000  45,957,300  455,860  46,413,160","","","","","","","","","","","","","","","","","","","","","","",""
+"","Haryana","","","15,156,681","","","1,333,527","","","40,100","","","0","","","16,530,308","","","1,222,698","","","17,753,006",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"Himachal Pradesh  8,647,229  1,331,529  580,800  0  10,559,558  725,315  11,284,873","","","","","","","","","","","","","","","","","","","","","","",""
+"","Jammu & Kashmir","","","14,411,984","","","270,840","","","3,188,550","","","0","","","17,871,374","","","166,229","","","18,037,603",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"Jharkhand  8,185,079  3,008,077  3,525,558  0  14,718,714  745,139  15,463,853","","","","","","","","","","","","","","","","","","","","","","",""
+"","Karnataka","","","34,939,843","","","4,317,801","","","3,669,700","","","0","","","42,927,344","","","631,088","","","43,558,432",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"Kerala  27,923,965  3,985,473  929,503  0  32,838,941  334,640  33,173,581","","","","","","","","","","","","","","","","","","","","","","",""
+"","Madhya Pradesh","","","28,459,540","","","4,072,016","","","3,432,711","","","0","","","35,964,267","","","472,139","","","36,436,406",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"Maharashtra  55,011,100  6,680,721  5,038,576  0  66,730,397  313,762  67,044,159","","","","","","","","","","","","","","","","","","","","","","",""
+"","Manipur","","","2,494,600","","","187,700","","","897,400","","","0","","","3,579,700","","","0","","","3,579,700",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"Meghalaya  2,894,093  342,893  705,500  5,000  3,947,486  24,128  3,971,614","","","","","","","","","","","","","","","","","","","","","","",""
+"","Mizoram","","","1,743,501","","","84,185","","","10,250","","","0","","","1,837,936","","","17,060","","","1,854,996",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"Nagaland   2,368,724  204,329  226,400  0  2,799,453  783,054  3,582,507","","","","","","","","","","","","","","","","","","","","","","",""
+"","Odisha","","","14,317,179","","","2,552,292","","","1,107,250","","","0","","","17,976,721","","","451,438","","","18,428,159",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
+"Puducherry  4,191,757  52,249  192,400  0  4,436,406  2,173  4,438,579","","","","","","","","","","","","","","","","","","","","","","",""
+"","Punjab","","","19,775,485","","","2,208,343","","","2,470,882","","","0","","","24,454,710","","","1,436,522","","","25,891,232",""
+"","","","","","","","","","","","","","","","","","","","","","","",""

docs/benchmark/stream/missing_values/missing_values-data-pdfplumber.csv

@@ -0,0 +1,71 @@
+"0","1","2","3","4"
+"","DLHS-4 (2012-13)","","DLHS-3 (2007-08)",""
+"Indicators","TOTAL","RURAL","TOTAL","RURAL"
+"Reported Prevalence of Morbidity","","","",""
+"Any Injury .....................................................................................................................................   1.9  2.1   
+Acute Illness .................................................................................................................................   4.5  5.6   
+Chronic Illness ..............................................................................................................................   5.1  4.1","","","",""
+"","","","",""
+"","","","",""
+"Reported Prevalence of Chronic Illness during last one year (%)","","","",""
+"Disease of respiratory system ......................................................................................................   11.7  15.0   
+Disease of cardiovascular system ................................................................................................   8.9  9.3   
+Persons suffering from tuberculosis .............................................................................................   2.2  1.5","","","",""
+"","","","",""
+"","","","",""
+"Anaemia Status by Haemoglobin Level14 (%)","","","",""
+"Children (6-59 months) having anaemia ......................................................................................   68.5  71.9   
+Children (6-59 months) having severe anaemia ..........................................................................   6.7  9.4   
+Children (6-9 Years) having anaemia - Male ................................................................................   67.1  71.4   
+Children (6-9 Years) having severe anaemia - Male ....................................................................   4.4  2.4   
+Children (6-9 Years) having anaemia - Female ...........................................................................   52.4  48.8   
+Children (6-9 Years) having severe anaemia - Female ................................................................   1.2  0.0   
+Children (6-14 years) having  anaemia - Male .............................................................................   50.8  62.5   
+Children (6-14 years) having severe anaemia - Male ..................................................................   3.7  3.6   
+Children (6-14 years) having  anaemia - Female .........................................................................   48.3  50.0   
+Children (6-14 years) having severe anaemia - Female ..............................................................   4.3  6.1   
+Children (10-19 Years15) having anaemia - Male .........................................................................   37.9  51.2   
+Children (10-19 Years15) having severe anaemia - Male .............................................................   3.5  4.0   
+Children (10-19 Years15) having anaemia - Female .....................................................................   46.6  52.1   
+Children (10-19 Years15) having severe anaemia - Female .........................................................   6.4  6.5   
+Adolescents (15-19 years) having  anaemia ................................................................................   39.4  46.5   
+Adolescents (15-19 years) having severe anaemia .....................................................................   5.4  5.1   
+Pregnant women (15-49 aged) having anaemia ..........................................................................   48.8  51.5   
+Pregnant women (15-49 aged) having severe anaemia ..............................................................   7.1  8.8   
+Women (15-49 aged) having anaemia .........................................................................................   45.2  51.7   
+Women (15-49 aged) having severe anaemia .............................................................................   4.8  5.9   
+Persons (20 years and above) having anaemia ...........................................................................   37.8  42.1   
+Persons (20 years and above) having Severe anaemia ..............................................................   4.6  4.8","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"","","","",""
+"Blood Sugar Level (age 18 years and above) (%)","","","",""
+"Blood Sugar Level >140 mg/dl (high) ...........................................................................................   12.9  11.1   
+Blood Sugar Level >160 mg/dl (very high) ...................................................................................   7.0  5.1","","","",""
+"","","","",""
+"Hypertension (age 18 years and above) (%)","","","",""
+"Above Normal Range (Systolic >140 mm of Hg & Diastolic >90 mm of Hg )  ..............................   23.8  22.8   
+Moderately High (Systolic >160 mm of Hg & Diastolic >100 mm of Hg ) .....................................   8.2  7.1   
+Very High (Systolic >180 mm of Hg & Diastolic >110 mm of Hg ) ...............................................   3.7  3.1","","","",""
+"","","","",""
+"","","","",""
+"14 Any anaemia below 11g/dl, severe anaemia below 7g/dl. 15 Excluding age group 19 years","","","",""
+"Chronic Illness :Any person with symptoms persisting for longer than one month is defined as suffering from chronic illness","","","",""

docs/dev/contributing.rst

@@ -7,7 +7,7 @@ If you're reading this, you're probably looking to contributing to Camelot. *Tim
 
 This document will help you get started with contributing documentation, code, testing and filing issues. If you have any questions, feel free to reach out to `Vinayak Mehta`_, the author and maintainer.
 
-.. _Vinayak Mehta: https://vinayak-mehta.github.io
+.. _Vinayak Mehta: https://www.vinayakmehta.com
 
 Code Of Conduct
 ---------------

docs/index.rst

@@ -92,6 +92,7 @@ This part of the documentation begins with some background information about why
    :maxdepth: 2
 
    user/intro
+   user/install-deps
    user/install
    user/how-it-works
    user/quickstart

docs/user/advanced.rst

@@ -24,6 +24,12 @@ To process background lines, you can pass ``process_background=True``.
     >>> tables = camelot.read_pdf('background_lines.pdf', process_background=True)
     >>> tables[1].df
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot lattice -back background_lines.pdf
+
 .. csv-table::
   :file: ../_static/csv/background_lines.csv
 
@@ -41,8 +47,9 @@ You can specify the type of element you want to plot using the ``kind`` keyword
 - 'contour'
 - 'line'
 - 'joint'
+- 'textedge'
 
-.. note:: The last three plot types can only be used with :ref:`Lattice <lattice>`, i.e. when ``flavor='lattice'``.
+.. note:: 'line' and 'joint' can only be used with :ref:`Lattice <lattice>` and 'textedge' can only be used with :ref:`Stream <stream>`.
 
 Let's generate a plot for each type using this `PDF <../_static/pdf/foo.pdf>`__ as an example. First, let's get all the tables out.
 
@@ -62,6 +69,12 @@ Let's plot all the text present on the table's PDF page.
     >>> camelot.plot(tables[0], kind='text')
     >>> plt.show()
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot lattice -plot text foo.pdf
+
 .. figure:: ../_static/png/plot_text.png
     :height: 674
     :width: 1366
@@ -80,9 +93,15 @@ Let's plot the table (to see if it was detected correctly or not). This plot typ
 
 ::
 
-    >>> camelot.plot(tables[0], kind='table')
+    >>> camelot.plot(tables[0], kind='grid')
     >>> plt.show()
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot lattice -plot grid foo.pdf
+
 .. figure:: ../_static/png/plot_table.png
     :height: 674
     :width: 1366
@@ -102,6 +121,12 @@ Now, let's plot all table boundaries present on the table's PDF page.
     >>> camelot.plot(tables[0], kind='contour')
     >>> plt.show()
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot lattice -plot contour foo.pdf
+
 .. figure:: ../_static/png/plot_contour.png
     :height: 674
     :width: 1366
@@ -119,6 +144,12 @@ Cool, let's plot all line segments present on the table's PDF page.
     >>> camelot.plot(tables[0], kind='line')
     >>> plt.show()
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot lattice -plot line foo.pdf
+
 .. figure:: ../_static/png/plot_line.png
     :height: 674
     :width: 1366
@@ -136,6 +167,12 @@ Finally, let's plot all line intersections present on the table's PDF page.
     >>> camelot.plot(tables[0], kind='joint')
     >>> plt.show()
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot lattice -plot joint foo.pdf
+
 .. figure:: ../_static/png/plot_joint.png
     :height: 674
     :width: 1366
@@ -143,10 +180,33 @@ Finally, let's plot all line intersections present on the table's PDF page.
     :alt: A plot of all line intersections on a PDF page
     :align: left
 
+textedge
+^^^^^^^^
+
+You can also visualize the textedges found on a page by specifying ``kind='textedge'``. To know more about what a "textedge" is, you can see pages 20, 35 and 40 of `Anssi Nurminen's master's thesis <http://dspace.cc.tut.fi/dpub/bitstream/handle/123456789/21520/Nurminen.pdf?sequence=3>`_.
+
+::
+
+    >>> camelot.plot(tables[0], kind='textedge')
+    >>> plt.show()
+
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot stream -plot textedge foo.pdf
+
+.. figure:: ../_static/png/plot_textedge.png
+    :height: 674
+    :width: 1366
+    :scale: 50%
+    :alt: A plot of relevant textedges on a PDF page
+    :align: left
+
 Specify table areas
 -------------------
 
-Since :ref:`Stream <stream>` treats the whole page as a table, `for now`_, it's useful to specify table boundaries in cases such as `these <../_static/pdf/table_areas.pdf>`__. You can plot the text on this page and note the top left and bottom right coordinates of the table.
+In cases such as `these <../_static/pdf/table_areas.pdf>`__, it can be useful to specify table boundaries. You can plot the text on this page and note the top left and bottom right coordinates of the table.
 
 Table areas that you want Camelot to analyze can be passed as a list of comma-separated strings to :meth:`read_pdf() <camelot.read_pdf>`, using the ``table_areas`` keyword argument.
 
@@ -157,6 +217,12 @@ Table areas that you want Camelot to analyze can be passed as a list of comma-se
     >>> tables = camelot.read_pdf('table_areas.pdf', flavor='stream', table_areas=['316,499,566,337'])
     >>> tables[0].df
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot stream -T 316,499,566,337 table_areas.pdf
+
 .. csv-table::
   :file: ../_static/csv/table_areas.csv
 
@@ -169,7 +235,7 @@ You can pass the column separators as a list of comma-separated strings to :meth
 
 In case you passed a single column separators string list, and no table area is specified, the separators will be applied to the whole page. When a list of table areas is specified and you need to specify column separators as well, **the length of both lists should be equal**. Each table area will be mapped to each column separators' string using their indices.
 
-For example, if you have specified two table areas, ``table_areas=['12,23,43,54', '20,33,55,67']``, and only want to specify column separators for the first table, you can pass an empty string for the second table in the column separators' list like this, ``columns=['10,120,200,400', '']``.
+For example, if you have specified two table areas, ``table_areas=['12,54,43,23', '20,67,55,33']``, and only want to specify column separators for the first table, you can pass an empty string for the second table in the column separators' list like this, ``columns=['10,120,200,400', '']``.
 
 Let's get back to the *x* coordinates we got from plotting the text that exists on this `PDF <../_static/pdf/column_separators.pdf>`__, and get the table out!
 
@@ -178,6 +244,12 @@ Let's get back to the *x* coordinates we got from plotting the text that exists
     >>> tables = camelot.read_pdf('column_separators.pdf', flavor='stream', columns=['72,95,209,327,442,529,566,606,683'])
     >>> tables[0].df
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot stream -C 72,95,209,327,442,529,566,606,683 column_separators.pdf
+
 .. csv-table::
 
     "...","...","...","...","...","...","...","...","...","..."
@@ -197,6 +269,12 @@ To deal with cases like the output from the previous section, you can pass ``spl
     >>> tables = camelot.read_pdf('column_separators.pdf', flavor='stream', columns=['72,95,209,327,442,529,566,606,683'], split_text=True)
     >>> tables[0].df
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot -split stream -C 72,95,209,327,442,529,566,606,683 column_separators.pdf
+
 .. csv-table::
 
     "...","...","...","...","...","...","...","...","...","..."
@@ -224,6 +302,12 @@ You can solve this by passing ``flag_size=True``, which will enclose the supersc
     >>> tables = camelot.read_pdf('superscript.pdf', flavor='stream', flag_size=True)
     >>> tables[0].df
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot -flag stream superscript.pdf
+
 .. csv-table::
 
     "...","...","...","...","...","...","...","...","...","...","..."
@@ -232,10 +316,87 @@ You can solve this by passing ``flag_size=True``, which will enclose the supersc
     "Madhya Pradesh","27.13","23.57","-","-","3.56","0.38","-","1.86","-","1.28"
     "...","...","...","...","...","...","...","...","...","...","..."
 
-Control how text is grouped into rows
--------------------------------------
+Strip characters from text
+--------------------------
 
-You can pass ``row_close_tol=<+int>`` to group the rows closer together, as shown below.
+You can strip unwanted characters like spaces, dots and newlines from a string using the ``strip_text`` keyword argument. Take a look at `this PDF <https://github.com/socialcopsdev/camelot/blob/master/tests/files/tabula/12s0324.pdf>`_ as an example, the text at the start of each row contains a lot of unwanted spaces, dots and newlines.
+
+::
+
+    >>> tables = camelot.read_pdf('12s0324.pdf', flavor='stream', strip_text=' .\n')
+    >>> tables[0].df
+
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot -strip ' .\n' stream 12s0324.pdf
+
+.. csv-table::
+
+    "...","...","...","...","...","...","...","...","...","..."
+    "Forcible rape","17.5","2.6","14.9","17.2","2.5","14.7","–","–","–"
+    "Robbery","102.1","25.5","76.6","90.0","22.9","67.1","12.1","2.5","9.5"
+    "Aggravated assault","338.4","40.1","298.3","264.0","30.2","233.8","74.4","9.9","64.5"
+    "Property crime","1,396 .4","338 .7","1,057 .7","875 .9","210 .8","665 .1","608 .2","127 .9","392 .6"
+    "Burglary","240.9","60.3","180.6","205.0","53.4","151.7","35.9","6.9","29.0"
+    "...","...","...","...","...","...","...","...","...","..."
+
+Improve guessed table areas
+---------------------------
+
+While using :ref:`Stream <stream>`, automatic table detection can fail for PDFs like `this one <https://github.com/socialcopsdev/camelot/blob/master/tests/files/edge_tol.pdf>`_. That's because the text is relatively far apart vertically, which can lead to shorter textedges being calculated.
+
+.. note:: To know more about how textedges are calculated to guess table areas, you can see pages 20, 35 and 40 of `Anssi Nurminen's master's thesis <http://dspace.cc.tut.fi/dpub/bitstream/handle/123456789/21520/Nurminen.pdf?sequence=3>`_.
+
+Let's see the table area that is detected by default.
+
+::
+
+    >>> tables = camelot.read_pdf('edge_tol.pdf', flavor='stream')
+    >>> camelot.plot(tables[0], kind='contour')
+    >>> plt.show()
+
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot stream -plot contour edge.pdf
+
+.. figure:: ../_static/png/edge_tol_1.png
+    :height: 674
+    :width: 1366
+    :scale: 50%
+    :alt: Table area with default edge_tol
+    :align: left
+
+To improve the detected area, you can increase the ``edge_tol`` (default: 50) value to counter the effect of text being placed relatively far apart vertically. Larger ``edge_tol`` will lead to longer textedges being detected, leading to an improved guess of the table area. Let's use a value of 500.
+
+::
+
+    >>> tables = camelot.read_pdf('edge_tol.pdf', flavor='stream', edge_tol=500)
+    >>> camelot.plot(tables[0], kind='contour')
+    >>> plt.show()
+
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot stream -e 500 -plot contour edge.pdf
+
+.. figure:: ../_static/png/edge_tol_2.png
+    :height: 674
+    :width: 1366
+    :scale: 50%
+    :alt: Table area with default edge_tol
+    :align: left
+
+As you can see, the guessed table area has improved!
+
+Improve guessed table rows
+--------------------------
+
+You can pass ``row_tol=<+int>`` to group the rows closer together, as shown below.
 
 ::
 
@@ -253,9 +414,15 @@ You can pass ``row_close_tol=<+int>`` to group the rows closer together, as show
 
 ::
 
-    >>> tables = camelot.read_pdf('group_rows.pdf', flavor='stream', row_close_tol=10)
+    >>> tables = camelot.read_pdf('group_rows.pdf', flavor='stream', row_tol=10)
     >>> tables[0].df
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot stream -r 10 group_rows.pdf
+
 .. csv-table::
 
     "Clave","Nombre Entidad","Clave","","Nombre Municipio","Clave","Nombre Localidad"
@@ -284,7 +451,7 @@ Let's plot the table for this PDF.
 ::
 
     >>> tables = camelot.read_pdf('short_lines.pdf')
-    >>> camelot.plot(tables[0], kind='table')
+    >>> camelot.plot(tables[0], kind='grid')
     >>> plt.show()
 
 .. figure:: ../_static/png/short_lines_1.png
@@ -296,9 +463,15 @@ Clearly, the smaller lines separating the headers, couldn't be detected. Let's t
 ::
 
     >>> tables = camelot.read_pdf('short_lines.pdf', line_size_scaling=40)
-    >>> camelot.plot(tables[0], kind='table')
+    >>> camelot.plot(tables[0], kind='grid')
     >>> plt.show()
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot lattice -scale 40 -plot grid short_lines.pdf
+
 .. figure:: ../_static/png/short_lines_2.png
     :alt: An improved plot of the PDF table with short lines
     :align: left
@@ -362,6 +535,12 @@ No surprises there — it did remain in place (observe the strings "2400" and "A
     >>> tables = camelot.read_pdf('short_lines.pdf', line_size_scaling=40, shift_text=['r', 'b'])
     >>> tables[0].df
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot lattice -scale 40 -shift r -shift b short_lines.pdf
+
 .. csv-table::
 
     "Investigations","No. ofHHs","Age/Sex/Physiological  Group","Preva-lence","C.I*","RelativePrecision","Sample sizeper State"
@@ -407,6 +586,12 @@ We don't need anything else. Now, let's pass ``copy_text=['v']`` to copy text in
     >>> tables = camelot.read_pdf('copy_text.pdf', copy_text=['v'])
     >>> tables[0].df
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot lattice -copy v copy_text.pdf
+
 .. csv-table::
 
     "Sl. No.","Name of State/UT","Name of District","Disease/ Illness","No. of Cases","No. of Deaths","Date of start of outbreak","Date of reporting","Current Status","..."
@@ -416,3 +601,14 @@ We don't need anything else. Now, let's pass ``copy_text=['v']`` to copy text in
     "4","West Bengal","West Medinipur","iv. Acute Diarrhoeal Disease","145","0","04/01/14","05/01/14","Under control","..."
     "4","West Bengal","Birbhum","v.  Food Poisoning","199","0","31/12/13","31/12/13","Under control","..."
     "4","West Bengal","Howrah","vi. Viral Hepatitis A &E","85","0","26/12/13","27/12/13","Under surveillance","..."
+
+Tweak layout generation
+-----------------------
+
+Camelot is built on top of PDFMiner's functionality of grouping characters on a page into words and sentences. In some cases (such as `#170 <https://github.com/socialcopsdev/camelot/issues/170>`_ and `#215 <https://github.com/socialcopsdev/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/>`_.
+
+::
+
+    >>> tables = camelot.read_pdf('foo.pdf', layout_kwargs={'detect_vertical': False})

docs/user/cli.rst

@@ -15,6 +15,7 @@ You can print the help for the interface by typing ``camelot --help`` in your fa
 
   Options:
     --version                       Show the version and exit.
+    -q, --quiet TEXT                Suppress logs and warnings.
     -p, --pages TEXT                Comma-separated page numbers. Example: 1,3,4
                                     or 1,4-end.
     -pw, --password TEXT            Password for decryption.
@@ -28,7 +29,6 @@ You can print the help for the interface by typing ``camelot --help`` in your fa
     -M, --margins <FLOAT FLOAT FLOAT>...
                                     PDFMiner char_margin, line_margin and
                                     word_margin.
-    -q, --quiet                     Suppress warnings.
     --help                          Show this message and exit.
 
   Commands:

docs/user/how-it-works.rst

@@ -5,24 +5,24 @@ How It Works
 
 This part of the documentation includes a high-level explanation of how Camelot extracts tables from PDF files.
 
-You can choose between two table parsing methods, *Stream* and *Lattice*. These names for parsing methods inside Camelot were inspired from `Tabula`_.
-
-.. _Tabula: https://github.com/tabulapdf/tabula
+You can choose between two table parsing methods, *Stream* and *Lattice*. These names for parsing methods inside Camelot were inspired from `Tabula <https://github.com/tabulapdf/tabula>`_.
 
 .. _stream:
 
 Stream
 ------
 
-Stream can be used to parse tables that have whitespaces between cells to simulate a table structure. It looks for these spaces between text to form a table representation.
+Stream can be used to parse tables that have whitespaces between cells to simulate a table structure. It is built on top of PDFMiner's functionality of grouping characters on a page into words and sentences, using `margins <https://euske.github.io/pdfminer/#tools>`_.
 
-It is built on top of PDFMiner's functionality of grouping characters on a page into words and sentences, using `margins`_. After getting the words on a page, it groups them into rows based on their *y* coordinates. It then tries to guess the number of columns the table might have by calculating the mode of the number of words in each row. This mode is used to calculate *x* ranges for the table's columns. It then adds columns to this column range list based on any words that may lie outside or inside the current column *x* ranges.
+1. Words on the PDF page are grouped into text rows based on their *y* axis overlaps.
 
-.. _margins: https://euske.github.io/pdfminer/#tools
+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]
 
-.. note:: By default, Stream treats the whole PDF page as a table, which isn't ideal when there are more than two tables on a page with different number of columns. Automatic table detection for Stream is `in the works`_.
+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.
 
-.. _in the works: https://github.com/socialcopsdev/camelot/issues/102
+4. Words that lie inside/outside the current column *x* ranges are then used to extend extend the current list of columns.
+
+5. Finally, a table is formed using the text rows' *y* ranges and column *x* ranges and words found on the page are assigned to the table's cells based on their *x* and *y* coordinates.
 
 .. _lattice:
 

docs/user/install-deps.rst

@@ -0,0 +1,76 @@
+.. _install_deps:
+
+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.
+
+.. _Tkinter: https://wiki.python.org/moin/TkInter
+.. _ghostscript: https://www.ghostscript.com
+
+OS-specific instructions
+------------------------
+
+For Ubuntu
+^^^^^^^^^^
+::
+
+    $ apt install python-tk ghostscript
+
+Or for Python 3::
+
+    $ apt install python3-tk ghostscript
+
+For macOS
+^^^^^^^^^
+::
+
+    $ brew install tcl-tk ghostscript
+
+For Windows
+^^^^^^^^^^^
+
+For Tkinter, you can download the `ActiveTcl Community Edition`_ from ActiveState. For ghostscript, you can get the installer at the `ghostscript downloads page`_.
+
+After installing ghostscript, you'll need to reboot your system to make sure that the ghostscript executable's path is in the windows PATH environment variable. In case you don't want to reboot, you can manually add the ghostscript executable's path to the PATH variable, `as shown here`_.
+
+.. _ActiveTcl Community Edition: https://www.activestate.com/activetcl/downloads
+.. _ghostscript downloads page: https://www.ghostscript.com/download/gsdnld.html
+.. _as shown here: https://java.com/en/download/help/path.xml
+
+Checks to see if dependencies were installed correctly
+------------------------------------------------------
+
+You can do the following checks to see if the dependencies were installed correctly.
+
+For Tkinter
+^^^^^^^^^^^
+
+Launch Python, and then at the prompt, type::
+
+    >>> 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``.
+
+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.

docs/user/install.rst

@@ -3,7 +3,7 @@
 Installation of Camelot
 =======================
 
-This part of the documentation covers how to install Camelot.
+This part of the documentation covers the steps to install Camelot.
 
 Using conda
 -----------
@@ -23,84 +23,17 @@ The easiest way to install Camelot is to install it with `conda`_, which is a pa
 Using pip
 ---------
 
-First, you'll need to install the dependencies, which include `Tkinter`_ and `ghostscript`_.
+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
 
-These can be installed using your system's package manager. You can run one of the following, based on your OS.
-
-For Ubuntu
-^^^^^^^^^^
-::
-
-    $ apt install python-tk ghostscript
-
-Or for Python 3::
-
-    $ apt install python3-tk ghostscript
-
-For macOS
-^^^^^^^^^
-::
-
-    $ brew install tcl-tk ghostscript
-
-For Windows
-^^^^^^^^^^^
-
-For Tkinter, you can download the `ActiveTcl Community Edition`_ from ActiveState. For ghostscript, you can get the installer at the `ghostscript downloads page`_.
-
-After installing ghostscript, you'll need to reboot your system to make sure that the ghostscript executable's path is in the windows PATH environment variable. In case you don't want to reboot, you can manually add the ghostscript executable's path to the PATH variable, `as shown here`_.
-
-.. _ActiveTcl Community Edition: https://www.activestate.com/activetcl/downloads
-.. _ghostscript downloads page: https://www.ghostscript.com/download/gsdnld.html
-.. _as shown here: https://java.com/en/download/help/path.xml
-
-----
-
-You can do the following checks to see if the dependencies were installed correctly.
-
-For Tkinter
-^^^^^^^^^^^
-
-Launch Python, and then at the prompt, type::
-
-    >>> 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``.
-
-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.
-
-Finally, you can use pip to install Camelot::
-
-    $ pip install camelot-py[cv]
-
 From the source code
 --------------------
 
-After `installing the dependencies`_, you can install from the source by:
+After :ref:`installing the dependencies <install_deps>`, you can install from the source by:
 
 1. Cloning the GitHub repository.
 ::
@@ -112,5 +45,3 @@ After `installing the dependencies`_, you can install from the source by:
 
     $ cd camelot
     $ pip install ".[cv]"
-
-.. _installing the dependencies: https://camelot-py.readthedocs.io/en/master/user/install.html#using-pip

docs/user/quickstart.rst

@@ -70,6 +70,12 @@ You can also export all tables at once, using the :class:`tables <camelot.core.T
 
     >>> tables.export('foo.csv', f='csv')
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot --format csv --output foo.csv lattice foo.pdf
+
 This will export all tables as CSV files at the path specified. Alternatively, you can use ``f='json'``, ``f='excel'`` or ``f='html'``.
 
 .. note:: The :meth:`export() <camelot.core.TableList.export>` method exports files with a ``page-*-table-*`` suffix. In the example above, the single table in the list will be exported to ``foo-page-1-table-1.csv``. If the list contains multiple tables, multiple CSV files will be created. To avoid filling up your path with multiple files, you can use ``compress=True``, which will create a single ZIP file at your path with all the CSV files.
@@ -85,6 +91,12 @@ By default, Camelot only uses the first page of the PDF to extract tables. To sp
 
     >>> camelot.read_pdf('your.pdf', pages='1,2,3')
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot --pages 1,2,3 lattice your.pdf
+
 The ``pages`` keyword argument accepts pages as comma-separated string of page numbers. You can also specify page ranges — for example, ``pages=1,4-10,20-30`` or ``pages=1,4-10,20-end``.
 
 Reading encrypted PDFs
@@ -98,6 +110,12 @@ To extract tables from encrypted PDF files you must provide a password when call
     >>> tables
     <TableList n=1>
 
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot --password userpass lattice foo.pdf
+
 Currently Camelot only supports PDFs encrypted with ASCII passwords and algorithm `code 1 or 2`_. An exception is thrown if the PDF cannot be read. This may be due to no password being provided, an incorrect password, or an unsupported encryption algorithm.
 
 Further encryption support may be added in future, however in the meantime if your PDF files are using unsupported encryption algorithms you are advised to remove encryption before calling :meth:`read_pdf() <camelot.read_pdf>`. This can been successfully achieved with third-party tools such as `QPDF`_.

setup.cfg

@@ -2,5 +2,5 @@
 test=pytest
 
 [tool:pytest]
-addopts = --verbose --cov-config .coveragerc --cov-report term --cov-report xml --cov=camelot --mpl tests
+addopts = --verbose --cov-config .coveragerc --cov-report term --cov-report xml --cov=camelot --mpl
 python_files = tests/test_*.py

setup.py

@@ -14,6 +14,7 @@ with open('README.md', 'r') as f:
 
 
 requires = [
+    'chardet>=3.0.4',
     'click>=6.7',
     'numpy>=1.13.3',
     'openpyxl>=2.5.8',

tests/data.py

@@ -33,58 +33,141 @@ data_stream = [
     ["Nagaland", "2,368,724", "204,329", "226,400", "0", "2,799,453", "783,054", "3,582,507"],
     ["Odisha", "14,317,179", "2,552,292", "1,107,250", "0", "17,976,721", "451,438", "18,428,159"],
     ["Puducherry", "4,191,757", "52,249", "192,400", "0", "4,436,406", "2,173", "4,438,579"],
-    ["Punjab", "19,775,485", "2,208,343", "2,470,882", "0", "24,454,710", "1,436,522", "25,891,232"],
-    ["", "Health Sector Financing by Centre and States/UTs in India [2009-10 to 2012-13](Revised)                               P a g e  |23", "", "", "", "", "", ""]
+    ["Punjab", "19,775,485", "2,208,343", "2,470,882", "0", "24,454,710", "1,436,522", "25,891,232"]
 ]
 
 data_stream_table_rotated = [
-    ["", "", "Table 21  Current use of contraception by background characteristics\u2014Continued", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
-    ["", "", "", "", "", "", "Modern method", "", "", "", "", "", "", "Traditional method", "", "", "", ""],
-    ["", "", "", "Any", "", "", "", "", "", "", "Other", "Any", "", "", "", "Not", "", "Number"],
-    ["", "", "Any", "modern", "Female", "Male", "", "", "", "Condom/", "modern", "traditional", "", "With-", "Folk", "currently", "", "of"],
-    ["", "Background characteristic", "method", "method", "sterilization", "sterilization", "Pill", "IUD", "Injectables", "Nirodh", "method", "method", "Rhythm", "drawal", "method", "using", "Total", "women"],
-    ["", "Caste/tribe", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
-    ["", "Scheduled caste", "74.8", "55.8", "42.9", "0.9", "9.7", "0.0", "0.2", "2.2", "0.0", "19.0", "11.2", "7.4", "0.4", "25.2", "100.0", "1,363"],
-    ["", "Scheduled tribe", "59.3", "39.0", "26.8", "0.6", "6.4", "0.6", "1.2", "3.5", "0.0", "20.3", "10.4", "5.8", "4.1", "40.7", "100.0", "256"],
-    ["", "Other backward class", "71.4", "51.1", "34.9", "0.0", "8.6", "1.4", "0.0", "6.2", "0.0", "20.4", "12.6", "7.8", "0.0", "28.6", "100.0", "211"],
-    ["", "Other", "71.1", "48.8", "28.2", "0.8", "13.3", "0.9", "0.3", "5.2", "0.1", "22.3", "12.9", "9.1", "0.3", "28.9", "100.0", "3,319"],
-    ["", "Wealth index", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
-    ["", "Lowest", "64.5", "48.6", "34.3", "0.5", "10.5", "0.6", "0.7", "2.0", "0.0", "15.9", "9.9", "4.6", "1.4", "35.5", "100.0", "1,258"],
-    ["", "Second", "68.5", "50.4", "36.2", "1.1", "11.4", "0.5", "0.1", "1.1", "0.0", "18.1", "11.2", "6.7", "0.2", "31.5", "100.0", "1,317"],
-    ["", "Middle", "75.5", "52.8", "33.6", "0.6", "14.2", "0.4", "0.5", "3.4", "0.1", "22.7", "13.4", "8.9", "0.4", "24.5", "100.0", "1,018"],
-    ["", "Fourth", "73.9", "52.3", "32.0", "0.5", "12.5", "0.6", "0.2", "6.3", "0.2", "21.6", "11.5", "9.9", "0.2", "26.1", "100.0", "908"],
-    ["", "Highest", "78.3", "44.4", "19.5", "1.0", "9.7", "1.4", "0.0", "12.7", "0.0", "33.8", "18.2", "15.6", "0.0", "21.7", "100.0", "733"],
-    ["", "Number of living children", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
-    ["", "No children", "25.1", "7.6", "0.3", "0.5", "2.0", "0.0",
+    ["Table 21  Current use of contraception by background characteristics\u2014Continued", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
+    ["", "", "", "", "", "Modern method", "", "", "", "", "", "", "Traditional method", "", "", "", ""],
+    ["", "", "Any", "", "", "", "", "", "", "Other", "Any", "", "", "", "Not", "", "Number"],
+    ["", "Any", "modern", "Female", "Male", "", "", "", "Condom/", "modern", "traditional", "", "With-", "Folk", "currently", "", "of"],
+    ["Background characteristic", "method", "method", "sterilization", "sterilization", "Pill", "IUD", "Injectables", "Nirodh", "method", "method", "Rhythm", "drawal", "method", "using", "Total", "women"],
+    ["Caste/tribe", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
+    ["Scheduled caste", "74.8", "55.8", "42.9", "0.9", "9.7", "0.0", "0.2", "2.2", "0.0", "19.0", "11.2", "7.4", "0.4", "25.2", "100.0", "1,363"],
+    ["Scheduled tribe", "59.3", "39.0", "26.8", "0.6", "6.4", "0.6", "1.2", "3.5", "0.0", "20.3", "10.4", "5.8", "4.1", "40.7", "100.0", "256"],
+    ["Other backward class", "71.4", "51.1", "34.9", "0.0", "8.6", "1.4", "0.0", "6.2", "0.0", "20.4", "12.6", "7.8", "0.0", "28.6", "100.0", "211"],
+    ["Other", "71.1", "48.8", "28.2", "0.8", "13.3", "0.9", "0.3", "5.2", "0.1", "22.3", "12.9", "9.1", "0.3", "28.9", "100.0", "3,319"],
+    ["Wealth index", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
+    ["Lowest", "64.5", "48.6", "34.3", "0.5", "10.5", "0.6", "0.7", "2.0", "0.0", "15.9", "9.9", "4.6", "1.4", "35.5", "100.0", "1,258"],
+    ["Second", "68.5", "50.4", "36.2", "1.1", "11.4", "0.5", "0.1", "1.1", "0.0", "18.1", "11.2", "6.7", "0.2", "31.5", "100.0", "1,317"],
+    ["Middle", "75.5", "52.8", "33.6", "0.6", "14.2", "0.4", "0.5", "3.4", "0.1", "22.7", "13.4", "8.9", "0.4", "24.5", "100.0", "1,018"],
+    ["Fourth", "73.9", "52.3", "32.0", "0.5", "12.5", "0.6", "0.2", "6.3", "0.2", "21.6", "11.5", "9.9", "0.2", "26.1", "100.0", "908"],
+    ["Highest", "78.3", "44.4", "19.5", "1.0", "9.7", "1.4", "0.0", "12.7", "0.0", "33.8", "18.2", "15.6", "0.0", "21.7", "100.0", "733"],
+    ["Number of living children", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
+    ["No children", "25.1", "7.6", "0.3", "0.5", "2.0", "0.0",
     "0.0", "4.8", "0.0", "17.5", "9.0", "8.5", "0.0", "74.9", "100.0", "563"],
-    ["", "1 child", "66.5", "32.1", "3.7", "0.7", "20.1", "0.7", "0.1", "6.9", "0.0", "34.3", "18.9", "15.2", "0.3", "33.5", "100.0", "1,190"],
-    ["\x18\x18", "1 son", "66.8", "33.2", "4.1", "0.7", "21.1", "0.5", "0.3", "6.6", "0.0", "33.5", "21.2", "12.3", "0.0", "33.2", "100.0", "672"],
-    ["", "No sons", "66.1", "30.7", "3.1", "0.6", "18.8", "0.8", "0.0", "7.3", "0.0", "35.4", "15.8", "19.0", "0.6", "33.9", "100.0", "517"],
-    ["", "2 children", "81.6", "60.5", "41.8", "0.9", "11.6", "0.8", "0.3", "4.8", "0.2", "21.1", "12.2", "8.3", "0.6", "18.4", "100.0", "1,576"],
-    ["", "1 or more sons", "83.7", "64.2", "46.4", "0.9", "10.8", "0.8", "0.4", "4.8", "0.1", "19.5", "11.1", "7.6", "0.7", "16.3", "100.0", "1,268"],
-    ["", "No sons", "73.2", "45.5", "23.2", "1.0", "15.1", "0.9", "0.0", "4.8", "0.5", "27.7", "16.8", "11.0", "0.0", "26.8", "100.0", "308"],
-    ["", "3 children", "83.9", "71.2", "57.7", "0.8", "9.8", "0.6", "0.5", "1.8", "0.0", "12.7", "8.7", "3.3", "0.8", "16.1", "100.0", "961"],
-    ["", "1 or more sons", "85.0", "73.2", "60.3", "0.9", "9.4", "0.5", "0.5", "1.6", "0.0", "11.8", "8.1", "3.0", "0.7", "15.0", "100.0", "860"],
-    ["", "No sons", "74.7", "53.8", "35.3", "0.0", "13.7", "1.6", "0.0", "3.2", "0.0", "20.9", "13.4", "6.1", "1.5", "25.3", "100.0", "101"],
-    ["", "4+ children", "74.3", "58.1", "45.1", "0.6", "8.7", "0.6", "0.7", "2.4", "0.0", "16.1", "9.9", "5.4", "0.8", "25.7", "100.0", "944"],
-    ["", "1 or more sons", "73.9", "58.2", "46.0", "0.7", "8.3", "0.7", "0.7", "1.9", "0.0", "15.7", "9.4", "5.5", "0.8", "26.1", "100.0", "901"],
-    ["", "No sons", "(82.1)", "(57.3)", "(25.6)", "(0.0)", "(17.8)", "(0.0)", "(0.0)", "(13.9)", "(0.0)", "(24.8)", "(21.3)", "(3.5)", "(0.0)", "(17.9)", "100.0", "43"],
-    ["", "Total", "71.2", "49.9", "32.2",
+    ["1 child", "66.5", "32.1", "3.7", "0.7", "20.1", "0.7", "0.1", "6.9", "0.0", "34.3", "18.9", "15.2", "0.3", "33.5", "100.0", "1,190"],
+    ["1 son", "66.8", "33.2", "4.1", "0.7", "21.1", "0.5", "0.3", "6.6", "0.0", "33.5", "21.2", "12.3", "0.0", "33.2", "100.0", "672"],
+    ["No sons", "66.1", "30.7", "3.1", "0.6", "18.8", "0.8", "0.0", "7.3", "0.0", "35.4", "15.8", "19.0", "0.6", "33.9", "100.0", "517"],
+    ["2 children", "81.6", "60.5", "41.8", "0.9", "11.6", "0.8", "0.3", "4.8", "0.2", "21.1", "12.2", "8.3", "0.6", "18.4", "100.0", "1,576"],
+    ["1 or more sons", "83.7", "64.2", "46.4", "0.9", "10.8", "0.8", "0.4", "4.8", "0.1", "19.5", "11.1", "7.6", "0.7", "16.3", "100.0", "1,268"],
+    ["No sons", "73.2", "45.5", "23.2", "1.0", "15.1", "0.9", "0.0", "4.8", "0.5", "27.7", "16.8", "11.0", "0.0", "26.8", "100.0", "308"],
+    ["3 children", "83.9", "71.2", "57.7", "0.8", "9.8", "0.6", "0.5", "1.8", "0.0", "12.7", "8.7", "3.3", "0.8", "16.1", "100.0", "961"],
+    ["1 or more sons", "85.0", "73.2", "60.3", "0.9", "9.4", "0.5", "0.5", "1.6", "0.0", "11.8", "8.1", "3.0", "0.7", "15.0", "100.0", "860"],
+    ["No sons", "74.7", "53.8", "35.3", "0.0", "13.7", "1.6", "0.0", "3.2", "0.0", "20.9", "13.4", "6.1", "1.5", "25.3", "100.0", "101"],
+    ["4+ children", "74.3", "58.1", "45.1", "0.6", "8.7", "0.6", "0.7", "2.4", "0.0", "16.1", "9.9", "5.4", "0.8", "25.7", "100.0", "944"],
+    ["1 or more sons", "73.9", "58.2", "46.0", "0.7", "8.3", "0.7", "0.7", "1.9", "0.0", "15.7", "9.4", "5.5", "0.8", "26.1", "100.0", "901"],
+    ["No sons", "(82.1)", "(57.3)", "(25.6)", "(0.0)", "(17.8)", "(0.0)", "(0.0)", "(13.9)", "(0.0)", "(24.8)", "(21.3)", "(3.5)", "(0.0)", "(17.9)", "100.0", "43"],
+    ["Total", "71.2", "49.9", "32.2",
     "0.7", "11.7", "0.6", "0.3", "4.3", "0.1", "21.3", "12.3", "8.4", "0.5", "28.8", "100.0", "5,234"],
-    ["", "NFHS-2 (1998-99)", "66.6", "47.3", "32.0", "1.8", "9.2", "1.4", "na", "2.9", "na", "na", "8.7", "9.8", "na", "33.4", "100.0", "4,116"],
-    ["", "NFHS-1 (1992-93)", "57.7", "37.6", "26.5", "4.3", "3.6", "1.3", "0.1", "1.9", "na", "na", "11.3", "8.3", "na", "42.3", "100.0", "3,970"],
-    ["", "", "Note: If more than one method is used, only the most effective method is considered in this tabulation. Total includes women for whom caste/tribe was not known or is missing, who are", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
-    ["", "not shown separately.", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
-    ["", "na = Not available", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
-    ["", "", "ns = Not shown; see table 2b, footnote 1", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
-    ["", "( ) Based on 25-49 unweighted cases.", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""],
-    ["", "", "", "", "", "", "", "", "54", "", "", "", "", "", "", "", "", ""]
+    ["NFHS-2 (1998-99)", "66.6", "47.3", "32.0", "1.8", "9.2", "1.4", "na", "2.9", "na", "na", "8.7", "9.8", "na", "33.4", "100.0", "4,116"],
+    ["NFHS-1 (1992-93)", "57.7", "37.6", "26.5", "4.3", "3.6", "1.3", "0.1", "1.9", "na", "na", "11.3", "8.3", "na", "42.3", "100.0", "3,970"]
+]
+
+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", "", "", "", "", "", "", "", "", ""],
+    ["by the FBI. Some persons may be arrested more than once during a year, therefore, the data in this table, in some cases,", "", "", "", "", "", "", "", "", ""],
+    ["could represent multiple arrests of the same person. See text, this section and source]", "", "", "", "", "", "", "", "", ""],
+    ["", "", "Total", "", "", "Male", "", "", "Female", ""],
+    ["Offense charged", "", "Under 18", "18 years", "", "Under 18", "18 years", "", "Under 18", "18 years"],
+    ["", "Total", "years", "and over", "Total", "years", "and over", "Total", "years", "and over"],
+    ["Total   .\n .\n .  .  .  .  .  .\n .  .\n .  .\n .  .\n .  .\n .  .\n .  .\n .  .\n .  .  .", "11,062 .6", "1,540 .0", "9,522 .6", "8,263 .3", "1,071 .6", "7,191 .7", "2,799 .2", "468 .3", "2,330 .9"],
+    ["Violent crime  .  .  .  .  .  .  .  .\n .  .\n .  .\n .  .\n .  .\n .  .", "467 .9", "69 .1", "398 .8", "380 .2", "56 .5", "323 .7", "87 .7", "12 .6", "75 .2"],
+    ["Murder and nonnegligent", "", "", "", "", "", "", "", "", ""],
+    ["manslaughter . . . . . . . .\n. .\n. .\n. .\n. .\n.", "10.0", "0.9", "9.1", "9.0", "0.9", "8.1", "1.1", "–", "1.0"],
+    ["Forcible rape . . . . . . . .\n. .\n. .\n. .\n. .\n. .", "17.5", "2.6", "14.9", "17.2", "2.5", "14.7", "–", "–", "–"],
+    ["Robbery . . . .\n. .\n. . .\n. . .\n.\n. . .\n.\n. . .\n.\n.", "102.1", "25.5", "76.6", "90.0", "22.9", "67.1", "12.1", "2.5", "9.5"],
+    ["Aggravated assault  . . . . . . . .\n. .\n. .\n.", "338.4", "40.1", "298.3", "264.0", "30.2", "233.8", "74.4", "9.9", "64.5"],
+    ["Property crime  .  .  .  .\n .  .\n .  .  .\n .  .  .\n .\n .  .  .  .", "1,396 .4", "338 .7", "1,057 .7", "875 .9", "210 .8", "665 .1", "608 .2", "127 .9", "392 .6"],
+    ["Burglary . .\n. . . . . .\n. .\n.\n. .\n.\n.\n. .\n.\n.\n. .\n.", "240.9", "60.3", "180.6", "205.0", "53.4", "151.7", "35.9", "6.9", "29.0"],
+    ["Larceny-theft . . . . . . . .\n. .\n. .\n. .\n. .\n. .", "1,080.1", "258.1", "822.0", "608.8", "140.5", "468.3", "471.3", "117.6", "353.6"],
+    ["Motor vehicle theft . . . . .\n. .\n. . .\n.\n.\n. .", "65.6", "16.0", "49.6", "53.9", "13.3", "40.7", "11.7", "2.7", "8.9"],
+    ["Arson .\n. . . . .\n. . .\n.\n. .\n.\n.\n. .\n.\n.\n. .\n.\n.\n. .", "9.8", "4.3", "5.5", "8.1", "3.7", "4.4", "1.7", "0.6", "1.1"],
+    ["Other assaults .\n. . . . . .\n. . .\n.\n. . .\n.\n. .\n.", "1,061.3", "175.3", "886.1", "785.4", "115.4", "670.0", "276.0", "59.9", "216.1"],
+    ["Forgery and counterfeiting .\n. . . . . . .\n.", "68.9", "1.7", "67.2", "42.9", "1.2", "41.7", "26.0", "0.5", "25.5"],
+    ["Fraud .\n.\n.\n. .\n. . . .\n. .\n.\n. .\n.\n.\n. .\n.\n.\n. .\n.\n.\n.", "173.7", "5.1", "168.5", "98.4", "3.3", "95.0", "75.3", "1.8", "73.5"],
+    ["Embezzlement . . .\n. . . . .\n. . .\n.\n. . .\n.\n.\n.", "14.6", "–", "14.1", "7.2", "–", "6.9", "7.4", "–", "7.2"],
+    ["Stolen property 1  . . . . . . .\n. . .\n. .\n. .\n.\n.", "84.3", "15.1", "69.2", "66.7", "12.2", "54.5", "17.6", "2.8", "14.7"],
+    ["Vandalism  . . . . . . . .\n. .\n. .\n. .\n. .\n. .\n.\n.\n.", "217.4", "72.7", "144.7", "178.1", "62.8", "115.3", "39.3", "9.9", "29.4"],
+    ["Weapons; carrying, possessing, etc. .", "132.9", "27.1", "105.8", "122.1", "24.3", "97.8", "10.8", "2.8", "8.0"],
+    ["Prostitution and commercialized vice", "56.9", "1.1", "55.8", "17.3", "–", "17.1", "39.6", "0.8", "38.7"],
+    ["Sex offenses 2  . . . . .\n. . . . .\n. .\n. .\n. . .\n.", "61.5", "10.7", "50.7", "56.1", "9.6", "46.5", "5.4", "1.1", "4.3"],
+    ["Drug abuse violations  . . . . . . . .\n. .\n.\n.", "1,333.0", "136.6", "1,196.4", "1,084.3", "115.2", "969.1", "248.7", "21.4", "227.3"],
+    ["Gambling .\n. . . . . .\n. .\n.\n. . .\n.\n. . .\n.\n. .\n.\n.", "8.2", "1.4", "6.8", "7.2", "1.4", "5.9", "0.9", "–", "0.9"],
+    ["Offenses against the family and", "", "", "", "", "", "", "", "", ""],
+    ["children . . . .\n. . . .\n. .\n. .\n. .\n. .\n. .\n. . .\n.", "92.4", "3.7", "88.7", "68.9", "2.4", "66.6", "23.4", "1.3", "22.1"],
+    ["Driving under the influence . . . . . .\n. .", "1,158.5", "109.2", "1,147.5", "895.8", "8.2", "887.6", "262.7", "2.7", "260.0"],
+    ["Liquor laws  . . . . . . . .\n. .\n. .\n. .\n. .\n. .\n. .", "48.2", "90.2", "368.0", "326.8", "55.4", "271.4", "131.4", "34.7", "96.6"],
+    ["Drunkenness . . .\n. . . . .\n. . .\n.\n. . .\n.\n. .\n.", "488.1", "11.4", "476.8", "406.8", "8.5", "398.3", "81.3", "2.9", "78.4"],
+    ["Disorderly conduct . .\n. . . . . . .\n. .\n. .\n. .", "529.5", "136.1", "393.3", "387.1", "90.8", "296.2", "142.4", "45.3", "97.1"],
+    ["Vagrancy . . . .\n. . . . .\n.\n. .\n.\n.\n. .\n.\n.\n. .\n.\n.", "26.6", "2.2", "24.4", "20.9", "1.6", "19.3", "5.7", "0.6", "5.1"],
+    ["All other offenses (except traffic) . . .\n.", "306.1", "263.4", "2,800.8", "2,337.1", "194.2", "2,142.9", "727.0", "69.2", "657.9"],
+    ["Suspicion . . . .\n. . . .\n. .\n. .\n. .\n. .\n. .\n. . .\n.", "1.6", "–", "1.4", "1.2", "–", "1.0", "–", "–", "–"],
+    ["Curfew and loitering law violations  .\n.", "91.0", "91.0", "(X)", "63.1", "63.1", "(X)", "28.0", "28.0", "(X)"],
+    ["Runaways  . . . . . . . .\n. .\n. .\n. .\n. .\n. .\n.\n.\n.", "75.8", "75.8", "(X)", "34.0", "34.0", "(X)", "41.8", "41.8", "(X)"],
+    ["", "– Represents zero. X Not applicable. 1 Buying, receiving, possessing stolen property. 2 Except forcible rape and prostitution.", "", "", "", "", "", "", "", ""],
+    ["", "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", "", "", "", "", ""],
+    ["with a total population of 239,839,971 as estimated by the FBI. See headnote, Table 324]", "", "", "", "", ""],
+    ["", "", "", "", "American", ""],
+    ["Offense charged", "", "", "", "Indian/Alaskan", "Asian Pacific"],
+    ["", "Total", "White", "Black", "Native", "Islander"],
+    ["Total  .\n .\n .\n .\n .  .\n .  .  .\n .  .  .\n .\n .  .  .\n .\n .  .  .\n .  .\n .\n .  .  .\n .\n .\n .\n .  .\n .  .\n .  .", "10,690,561", "7,389,208", "3,027,153", "150,544", "123,656"],
+    ["Violent crime  .  .  .  .  .  .  .  .\n .  .\n .  .\n .  .\n .  .\n .\n .\n .  .\n .  .\n .\n .\n .\n .\n .  .", "456,965", "268,346", "177,766", "5,608", "5,245"],
+    ["Murder and nonnegligent manslaughter . .\n. .\n.\n. .", "9,739", "4,741", "4,801", "100", "97"],
+    ["Forcible rape . . . . . . . .\n. .\n. .\n. .\n. .\n.\n.\n. .\n. .\n.\n.\n.\n.\n. .", "16,362", "10,644", "5,319", "169", "230"],
+    ["Robbery . . . . .\n. . . . .\n.\n. . .\n.\n. . .\n.\n.\n. .\n.\n.\n. .\n.\n.\n. . . .", "100,496", "43,039", "55,742", "726", "989"],
+    ["Aggravated assault  . . . . . . . .\n. .\n. .\n.\n.\n.\n.\n. .\n. .\n.\n.\n.", "330,368", "209,922", "111,904", "4,613", "3,929"],
+    ["Property crime  .  .  .  .  .\n .  .  .  .  .\n .\n .  .  .\n .\n .  .\n .\n .\n .\n .  .\n .\n .  .\n .\n .", "1,364,409", "922,139", "406,382", "17,599", "18,289"],
+    ["Burglary . . .\n. . . . .\n. . .\n.\n.\n. .\n.\n.\n. .\n.\n.\n. .\n.\n.\n. .\n.\n. . . .", "234,551", "155,994", "74,419", "2,021", "2,117"],
+    ["Larceny-theft . . . . . . . .\n. .\n. .\n. .\n. .\n.\n.\n. .\n. .\n.\n.\n.\n.\n. .", "1,056,473", "719,983", "306,625", "14,646", "15,219"],
+    ["Motor vehicle theft . . . . . .\n. .\n.\n. . .\n.\n. .\n.\n.\n.\n. .\n.\n. .\n.", "63,919", "39,077", "23,184", "817", "841"],
+    ["Arson .\n. . . .\n. .\n. .\n. .\n.\n. .\n.\n.\n. .\n.\n.\n. .\n.\n.\n. .\n.\n.\n. . . . . .", "9,466", "7,085", "2,154", "115", "112"],
+    ["Other assaults .\n. . . . . . .\n.\n. . .\n.\n. . .\n.\n. .\n.\n.\n.\n. .\n.\n. .\n.", "1,032,502", "672,865", "332,435", "15,127", "12,075"],
+    ["Forgery and counterfeiting .\n. . . . . . .\n.\n. .\n.\n.\n.\n. .\n. .\n.", "67,054", "44,730", "21,251", "345", "728"],
+    ["Fraud .\n.\n. . . . . .\n. .\n. .\n. .\n. .\n. .\n. .\n. .\n. .\n. .\n.\n.\n. . . . . . .", "161,233", "108,032", "50,367", "1,315", "1,519"],
+    ["Embezzlement . . . .\n. . . . .\n.\n. . .\n.\n. . .\n.\n.\n. .\n.\n. .\n.\n.\n.\n.", "13,960", "9,208", "4,429", "75", "248"],
+    ["Stolen property; buying, receiving, possessing .\n. .", "82,714", "51,953", "29,357", "662", "742"],
+    ["Vandalism  . . . . . . . .\n. .\n. .\n. .\n. .\n. .\n. .\n.\n.\n. .\n. .\n.\n.\n.\n. .", "212,173", "157,723", "48,746", "3,352", "2,352"],
+    ["Weapons—carrying, possessing, etc. .\n. .\n. .\n.\n. .\n. .", "130,503", "74,942", "53,441", "951", "1,169"],
+    ["Prostitution and commercialized vice  . .\n.\n. .\n. .\n. .\n.", "56,560", "31,699", "23,021", "427", "1,413"],
+    ["Sex offenses 1 . . . . . . . .\n. .\n. .\n. .\n. .\n.\n.\n. .\n. .\n.\n.\n.\n.\n. .", "60,175", "44,240", "14,347", "715", "873"],
+    ["Drug abuse violations  . . . . . . . .\n. . .\n.\n.\n.\n. .\n. .\n.\n.\n.\n.", "1,301,629", "845,974", "437,623", "8,588", "9,444"],
+    ["Gambling . . . . .\n. . . . .\n.\n. . .\n.\n. . .\n. .\n.\n. . .\n.\n.\n.\n.\n. .\n. .", "8,046", "2,290", "5,518", "27", "211"],
+    ["Offenses against the family and children .\n.\n. .\n. .\n. .", "87,232", "58,068", "26,850", "1,690", "624"],
+    ["Driving under the influence . . . . . . .\n. .\n.\n. .\n.\n.\n.\n.\n. .", "1,105,401", "954,444", "121,594", "14,903", "14,460"],
+    ["Liquor laws  . . . . . . . .\n. .\n. .\n. .\n. .\n. . .\n.\n.\n.\n. .\n. .\n.\n.\n.\n.", "444,087", "373,189", "50,431", "14,876", "5,591"],
+    ["Drunkenness . .\n. . . . . . .\n.\n. . .\n.\n. . .\n.\n.\n.\n. . .\n.\n.\n.\n.\n.\n.", "469,958", "387,542", "71,020", "8,552", "2,844"],
+    ["Disorderly conduct . . .\n. . . . . .\n. .\n. . .\n.\n.\n.\n. .\n. .\n.\n.\n.\n.", "515,689", "326,563", "176,169", "8,783", "4,174"],
+    ["Vagrancy . . .\n. .\n. . . .\n. .\n.\n. .\n.\n.\n. .\n.\n.\n. .\n.\n.\n. .\n.\n.\n. . . .", "26,347", "14,581", "11,031", "543", "192"],
+    ["All other offenses (except traffic) . .\n. .\n. .\n. .\n.\n.\n.\n. .\n.", "2,929,217", "1,937,221", "911,670", "43,880", "36,446"],
+    ["Suspicion . . .\n. . . . .\n. .\n. .\n. .\n. .\n. .\n. .\n. .\n.\n.\n.\n.\n. .\n. . . .", "1,513", "677", "828", "1", "7"],
+    ["Curfew and loitering law violations  . .\n. .\n.\n. .\n. .\n.\n.\n.", "89,578", "54,439", "33,207", "872", "1,060"],
+    ["Runaways  . . . . . . . .\n. .\n. .\n. .\n. .\n. .\n. .\n.\n.\n. .\n. .\n.\n.\n.\n. .", "73,616", "48,343", "19,670", "1,653", "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"],
-    ["Weekly", "$71.15"],
+    ["Weekly", "$\n71.15"],
     ["Biweekly", "142.31"],
     ["Semimonthly", "154.17"],
     ["Monthly", "308.33"],
@@ -187,14 +270,10 @@ data_stream_split_text = [
     ["", "", "", "", "1522 WEST LINDSEY", "", "", "", "", ""],
     ["632575", "BAW", "BASHU LEGENDS", "HYH HE CHUANG LLC", "STREET", "NORMAN", "OK", "73069", "-", "2014/07/21"],
     ["", "", "", "DEEP FORK HOLDINGS", "", "", "", "", "", ""],
-    ["543149", "BAW", "BEDLAM BAR-B-Q", "LLC", "610 NORTHEAST 50TH", "OKLAHOMA CITY", "OK", "73105", "(405) 528-7427", "2015/02/23"],
-    ["", "", "", "", "Page 1 of 151", "", "", "", "", ""]
+    ["543149", "BAW", "BEDLAM BAR-B-Q", "LLC", "610 NORTHEAST 50TH", "OKLAHOMA CITY", "OK", "73105", "(405) 528-7427", "2015/02/23"]
 ]
 
 data_stream_flag_size = [
-    ["", "TABLE 125: STATE-WISE COMPOSITION OF OUTSTANDING LIABILITIES - 1997 <s>(Contd.)</s>", "", "", "", "", "", "", "", "", ""],
-    ["", "", "", "", "(As at end-March)", "", "", "", "", "", ""],
-    ["", "", "", "", "", "", "", "", "", "", "(<s>`</s> Billion)"],
     ["States", "Total", "Market", "NSSF", "WMA", "Loans", "Loans", "Loans", "Loans", "Loans", "Loans"],
     ["", "Internal", "Loans", "", "from", "from", "from", "from", "from", "from SBI", "from"],
     ["", "Debt", "", "", "RBI", "Banks", "LIC", "GIC", "NABARD", "& Other", "NCDC"],
@@ -230,14 +309,69 @@ data_stream_flag_size = [
     ["Uttar Pradesh", "80.62", "74.89", "-", "4.34", "1.34", "0.6", "-", "-0.21", "0.18", "0.03"],
     ["West Bengal", "34.23", "32.19", "-", "-", "2.04", "0.77", "-", "0.06", "-", "0.51"],
     ["NCT Delhi", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-"],
-    ["ALL STATES", "513.38", "436.02", "-", "25.57", "51.06", "14.18", "-", "8.21", "11.83", "11.08"],
-    ["<s>2</s> Includes `2.45 crore outstanding under “Market Loan Suspense”.", "", "", "", "", "", "", "", "", "", ""],
-    ["", "", "", "", "445", "", "", "", "", "", ""]
+    ["ALL STATES", "513.38", "436.02", "-", "25.57", "51.06", "14.18", "-", "8.21", "11.83", "11.08"]
+]
+
+data_stream_strip_text = [
+    ["V i n s   a u   Ve r r e", ""],
+    ["Les Blancs", "12.5CL"],
+    ["A.O.P Côtes du Rhône", ""],
+    ["Domaine de la Guicharde «  Autour de la chapelle » 2016", "8 €"],
+    ["A.O.P Vacqueyras", ""],
+    ["Domaine de Montvac  « Melodine » 2016", "10 €"],
+    ["A.O.P Châteauneuf du Pape", ""],
+    ["Domaine de Beaurenard 2017", "13 €"],
+    ["A.O.P Côteaux du Languedoc", ""],
+    ["Villa Tempora « Un temps pour elle » 2014", "9 €"],
+    ["A.O.P Côtes de Provence", ""],
+    ["Château Grand Boise 2017", "9 €"],
+    ["Les Rosés", "12,5 CL"],
+    ["A.O.P Côtes du Rhône", ""],
+    ["Domaine de la Florane « A fleur de Pampre » 2016", "8 €"],
+    ["Famille Coulon (Domaine Beaurenard) Biotifulfox 2017", "8 €"],
+    ["A.O.P Vacqueyras", ""],
+    ["Domaine de Montvac 2017", "9 €"],
+    ["A.O.P Languedoc", ""],
+    ["Domaine de Joncas « Nébla » 2015", "8 €"],
+    ["Villa Tempora « L’arroseur arrosé » 2015", "9 €"],
+    ["A.O.P Côtes de Provence", ""],
+    ["Château Grand Boise « Sainte Victoire » 2017", "9 €"],
+    ["Château Léoube 2016", "10 €"]
+]
+
+data_stream_edge_tol = [
+    ["Key figures", ""],
+    ["", "2016"],
+    ["(all amounts in EUR)", ""],
+    ["C\nlass A", ""],
+    ["N\net Asset Value at 31 December", "5,111,372"],
+    ["N\number of outstanding units at 31 December", "49,136"],
+    ["N\net Asset Value per unit at 31 December", "104.03"],
+    ["C\nlass B", ""],
+    ["N\net Asset Value at 31 December", "49,144,825"],
+    ["N\number of outstanding units at 31 December", "471,555"],
+    ["N\net Asset Value per unit at 31 December", "104.22"],
+    ["T\notal for the Fund", ""],
+    ["N\net Asset Value at 31 December", "54,256,197"],
+    ["N\number of outstanding units at 31 December", "520,691"],
+    ["I\nnvestment result", ""],
+    ["Direct result", "-"],
+    ["Revaluation", "2,076,667"],
+    ["Costs", "(106,870)"],
+    ["T\notal investment result for the period1", "1,969,797"],
+    ["I\nnvestment result per unit2", ""],
+    ["Direct result", "-"],
+    ["Revaluation", "3.99"],
+    ["Costs", "(0.21)"],
+    ["T\notal investment result per unit", "3.78"],
+    ["1 The results cover the period from inception of the Fund at 8 April 2016 through 31 December 2016.", ""],
+    ["2 The result per unit is calculated using the total number of outstanding unit as per the end of the", ""],
+    ["period.", ""]
 ]
 
 data_lattice = [
-    ["Cycle Name", "KI (1/km)", "Distance (mi)", "Percent Fuel Savings", "", "", ""],
-    ["", "", "", "Improved Speed", "Decreased Accel", "Eliminate Stops", "Decreased Idle"],
+    ["Cycle \nName", "KI \n(1/km)", "Distance \n(mi)", "Percent Fuel Savings", "", "", ""],
+    ["", "", "", "Improved \nSpeed", "Decreased \nAccel", "Eliminate \nStops", "Decreased \nIdle"],
     ["2012_2", "3.30", "1.3", "5.9%", "9.5%", "29.2%", "17.4%"],
     ["2145_1", "0.68", "11.2", "2.4%", "0.1%", "9.5%", "2.7%"],
     ["4234_1", "0.59", "58.7", "8.5%", "1.3%", "8.5%", "3.3%"],
@@ -246,7 +380,7 @@ data_lattice = [
 ]
 
 data_lattice_table_rotated = [
-    ["State", "Nutritional Assessment  (No. of individuals)", "", "", "", "IYCF Practices  (No. of mothers: 2011-12)", "Blood Pressure  (No. of adults: 2011-12)", "", "Fasting  Blood Sugar (No. of adults:2011-12)", ""],
+    ["State", "Nutritional Assessment  \n(No. of individuals)", "", "", "", "IYCF Practices  \n(No. of mothers: \n2011-12)", "Blood Pressure  \n(No. of adults: \n2011-12)", "", "Fasting  Blood Sugar \n(No. of adults:\n2011-12)", ""],
     ["", "1975-79", "1988-90", "1996-97", "2011-12", "", "Men", "Women", "Men", "Women"],
     ["Kerala", "5738", "6633", "8864", "8297", "245", "2161", "3195", "1645", "2391"],
     ["Tamil Nadu", "7387", "10217", "5813", "7851", "413", "2134", "2858", "1119", "1739"],
@@ -261,10 +395,42 @@ data_lattice_table_rotated = [
     ["Pooled", "38742", "53618", "60601", "86898", "4459", "21918", "27041", "14312", "18519"]
 ]
 
+data_lattice_two_tables_1 = [
+    ["State", "n", "Literacy Status", "", "", "", "", ""],
+    ["", "", "Illiterate", "Read & \nWrite", "1-4 std.", "5-8 std.", "9-12 std.", "College"],
+    ["Kerala", "2400", "7.2", "0.5", "25.3", "20.1", "41.5", "5.5"],
+    ["Tamil Nadu", "2400", "21.4", "2.3", "8.8", "35.5", "25.8", "6.2"],
+    ["Karnataka", "2399", "37.4", "2.8", "12.5", "18.3", "23.1", "5.8"],
+    ["Andhra Pradesh", "2400", "54.0", "1.7", "8.4", "13.2", "18.8", "3.9"],
+    ["Maharashtra", "2400", "22.0", "0.9", "17.3", "20.3", "32.6", "7.0"],
+    ["Gujarat", "2390", "28.6", "0.1", "14.4", "23.1", "26.9", "6.8"],
+    ["Madhya Pradesh", "2402", "29.1", "3.4", "8.5", "35.1", "13.3", "10.6"],
+    ["Orissa", "2405", "33.2", "1.0", "10.4", "25.7", "21.2", "8.5"],
+    ["West Bengal", "2293", "41.7", "4.4", "13.2", "17.1", "21.2", "2.4"],
+    ["Uttar Pradesh", "2400", "35.3", "2.1", "4.5", "23.3", "27.1", "7.6"],
+    ["Pooled", "23889", "30.9", "1.9", "12.3", "23.2", "25.2", "6.4"]
+]
+
+data_lattice_two_tables_2 = [
+    ["State", "n", "Literacy Status", "", "", "", "", ""],
+    ["", "", "Illiterate", "Read & \nWrite", "1-4 std.", "5-8 std.", "9-12 std.", "College"],
+    ["Kerala", "2400", "8.8", "0.3", "20.1", "17.0", "45.6", "8.2"],
+    ["Tamil Nadu", "2400", "29.9", "1.5", "8.5", "33.1", "22.3", "4.8"],
+    ["Karnataka", "2399", "47.9", "2.5", "10.2", "18.8", "18.4", "2.3"],
+    ["Andhra Pradesh", "2400", "66.4", "0.7", "6.8", "12.9", "11.4", "1.8"],
+    ["Maharashtra", "2400", "41.3", "0.6", "14.1", "20.1", "21.6", "2.2"],
+    ["Gujarat", "2390", "57.6", "0.1", "10.3", "16.5", "12.9", "2.7"],
+    ["Madhya Pradesh", "2402", "58.7", "2.2", "6.6", "24.1", "5.3", "3.0"],
+    ["Orissa", "2405", "50.0", "0.9", "8.1", "21.9", "15.1", "4.0"],
+    ["West Bengal", "2293", "49.1", "4.8", "11.2", "16.8", "17.1", "1.1"],
+    ["Uttar Pradesh", "2400", "67.3", "2.0", "3.1", "17.2", "7.7", "2.7"],
+    ["Pooled", "23889", "47.7", "1.5", "9.9", "19.9", "17.8", "3.3"]
+]
+
 data_lattice_table_areas = [
     ["", "", "", "", "", "", "", "", ""],
     ["State", "n", "Literacy Status", "", "", "", "", "", ""],
-    ["", "", "Illiterate", "Read & Write", "1-4 std.", "5-8 std.", "9-12 std.", "College", ""],
+    ["", "", "Illiterate", "Read & \nWrite", "1-4 std.", "5-8 std.", "9-12 std.", "College", ""],
     ["Kerala", "2400", "7.2", "0.5", "25.3", "20.1", "41.5", "5.5", ""],
     ["Tamil Nadu", "2400", "21.4", "2.3", "8.8", "35.5", "25.8", "6.2", ""],
     ["Karnataka", "2399", "37.4", "2.8", "12.5", "18.3", "23.1", "5.8", ""],
@@ -280,13 +446,13 @@ data_lattice_table_areas = [
 ]
 
 data_lattice_process_background = [
-    ["State", "Date", "Halt stations", "Halt days", "Persons directly reached(in lakh)", "Persons trained", "Persons counseled" ,"Persons testedfor HIV"],
+    ["State", "Date", "Halt \nstations", "Halt \ndays", "Persons \ndirectly \nreached\n(in lakh)", "Persons \ntrained", "Persons \ncounseled", "Persons \ntested\nfor HIV"],
     ["Delhi", "1.12.2009", "8", "17", "1.29", "3,665", "2,409", "1,000"],
-    ["Rajasthan", "2.12.2009 to 19.12.2009", "", "", "", "", "", ""],
-    ["Gujarat", "20.12.2009 to 3.1.2010", "6", "13", "6.03", "3,810", "2,317", "1,453"],
-    ["Maharashtra", "4.01.2010 to 1.2.2010", "13", "26", "1.27", "5,680", "9,027", "4,153"],
-    ["Karnataka", "2.2.2010 to 22.2.2010", "11", "19", "1.80", "5,741", "3,658", "3,183"],
-    ["Kerala", "23.2.2010 to 11.3.2010", "9", "17", "1.42", "3,559", "2,173", "855"],
+    ["Rajasthan", "2.12.2009 to \n19.12.2009", "", "", "", "", "", ""],
+    ["Gujarat", "20.12.2009 to \n3.1.2010", "6", "13", "6.03", "3,810", "2,317", "1,453"],
+    ["Maharashtra", "4.01.2010 to \n1.2.2010", "13", "26", "1.27", "5,680", "9,027", "4,153"],
+    ["Karnataka", "2.2.2010 to \n22.2.2010", "11", "19", "1.80", "5,741", "3,658", "3,183"],
+    ["Kerala", "23.2.2010 to \n11.3.2010", "9", "17", "1.42", "3,559", "2,173", "855"],
     ["Total", "", "47", "92", "11.81", "22,455", "19,584", "10,644"]
 ]
 
@@ -330,11 +496,11 @@ data_lattice_copy_text = [
     ["PCCM", "San Francisco", "Family Mosaic", "25"],
     ["PCCM", "Total PHP Enrollment", "", "853"],
     ["All Models Total Enrollments", "", "", "10,132,875"],
-    ["Source:   Data Warehouse 12/14/15", "", "", ""]
+    ["Source:   Data Warehouse \n12/14/15", "", "", ""]
 ]
 
 data_lattice_shift_text_left_top = [
-    ["Investigations", "No. ofHHs", "Age/Sex/Physiological  Group", "Preva-lence", "C.I*", "RelativePrecision", "Sample sizeper State"],
+    ["Investigations", "No. of\nHHs", "Age/Sex/\nPhysiological  Group", "Preva-\nlence", "C.I*", "Relative\nPrecision", "Sample size\nper State"],
     ["Anthropometry", "2400", "All the available individuals", "", "", "", ""],
     ["Clinical Examination", "", "", "", "", "", ""],
     ["History of morbidity", "", "", "", "", "", ""],
@@ -343,12 +509,12 @@ data_lattice_shift_text_left_top = [
     ["", "", "Women (≥ 18 yrs)", "", "", "", "1728"],
     ["Fasting blood glucose", "2400", "Men (≥ 18 yrs)", "5%", "95%", "20%", "1825"],
     ["", "", "Women (≥ 18 yrs)", "", "", "", "1825"],
-    ["Knowledge &Practices on HTN &DM", "2400", "Men (≥ 18 yrs)", "-", "-", "-", "1728"],
+    ["Knowledge &\nPractices on HTN &\nDM", "2400", "Men (≥ 18 yrs)", "-", "-", "-", "1728"],
     ["", "2400", "Women (≥ 18 yrs)", "-", "-", "-", "1728"]
 ]
 
 data_lattice_shift_text_disable = [
-    ["Investigations", "No. ofHHs", "Age/Sex/Physiological  Group", "Preva-lence", "C.I*", "RelativePrecision", "Sample sizeper State"],
+    ["Investigations", "No. of\nHHs", "Age/Sex/\nPhysiological  Group", "Preva-\nlence", "C.I*", "Relative\nPrecision", "Sample size\nper State"],
     ["Anthropometry", "", "", "", "", "", ""],
     ["Clinical Examination", "2400", "", "All the available individuals", "", "", ""],
     ["History of morbidity", "", "", "", "", "", ""],
@@ -357,12 +523,12 @@ data_lattice_shift_text_disable = [
     ["Blood Pressure #", "2400", "Women (≥ 18 yrs)", "10%", "95%", "20%", "1728"],
     ["", "", "Men (≥ 18 yrs)", "", "", "", "1825"],
     ["Fasting blood glucose", "2400", "Women (≥ 18 yrs)", "5%", "95%", "20%", "1825"],
-    ["Knowledge &Practices on HTN &", "2400", "Men (≥ 18 yrs)", "-", "-", "-", "1728"],
+    ["Knowledge &\nPractices on HTN &", "2400", "Men (≥ 18 yrs)", "-", "-", "-", "1728"],
     ["DM", "2400", "Women (≥ 18 yrs)", "-", "-", "-", "1728"]
 ]
 
 data_lattice_shift_text_right_bottom = [
-    ["Investigations", "No. ofHHs", "Age/Sex/Physiological  Group", "Preva-lence", "C.I*", "RelativePrecision", "Sample sizeper State"],
+    ["Investigations", "No. of\nHHs", "Age/Sex/\nPhysiological  Group", "Preva-\nlence", "C.I*", "Relative\nPrecision", "Sample size\nper State"],
     ["Anthropometry", "", "", "", "", "", ""],
     ["Clinical Examination", "", "", "", "", "", ""],
     ["History of morbidity", "2400", "", "", "", "", "All the available individuals"],
@@ -372,5 +538,53 @@ data_lattice_shift_text_right_bottom = [
     ["", "", "Men (≥ 18 yrs)", "", "", "", "1825"],
     ["Fasting blood glucose", "2400", "Women (≥ 18 yrs)", "5%", "95%", "20%", "1825"],
     ["", "2400", "Men (≥ 18 yrs)", "-", "-", "-", "1728"],
-    ["Knowledge &Practices on HTN &DM", "2400", "Women (≥ 18 yrs)", "-", "-", "-", "1728"]
+    ["Knowledge &\nPractices on HTN &\nDM", "2400", "Women (≥ 18 yrs)", "-", "-", "-", "1728"]
+]
+
+data_arabic = [
+    ["ً\n\xa0\nﺎﺒﺣﺮﻣ", "ﻥﺎﻄﻠﺳ\xa0ﻲﻤﺳﺍ"],
+    ["ﻝﺎﻤﺸﻟﺍ\xa0ﺎﻨﻴﻟﻭﺭﺎﻛ\xa0ﺔﻳﻻﻭ\xa0ﻦﻣ\xa0ﺎﻧﺍ", "؟ﺖﻧﺍ\xa0ﻦﻳﺍ\xa0ﻦﻣ"],
+    ["1234", "ﻂﻄﻗ\xa047\xa0ﻱﺪﻨﻋ"],
+    ["؟ﻙﺎﺒﺷ\xa0ﺖﻧﺍ\xa0ﻞﻫ", "ﺔﻳﺰﻴﻠﺠﻧﻻﺍ\xa0ﻲﻓ\xa0Jeremy\xa0ﻲﻤﺳﺍ"],
+    ["Jeremy\xa0is\xa0ﻲﻣﺮﺟ\xa0in\xa0Arabic", ""]
+]
+
+data_stream_layout_kwargs = [
+    ["V i n s   a u   Ve r r e", ""],
+    ["Les Blancs", "12.5CL"],
+    ["A.O.P Côtes du Rhône", ""],
+    ["Domaine de la Guicharde «  Autour de la chapelle » 2016", "8 €"],
+    ["A.O.P Vacqueyras", ""],
+    ["Domaine de Montvac  « Melodine » 2016", "10 €"],
+    ["A.O.P Châteauneuf du Pape", ""],
+    ["Domaine de Beaurenard 2017", "13 €"],
+    ["A.O.P Côteaux du Languedoc", ""],
+    ["Villa Tempora « Un temps pour elle » 2014", "9 €"],
+    ["A.O.P Côtes de Provence", ""],
+    ["Château Grand Boise 2017", "9 €"],
+    ["Les Rosés", "12,5 CL"],
+    ["A.O.P Côtes du Rhône", ""],
+    ["Domaine de la Florane « A fleur de Pampre » 2016", "8 €"],
+    ["Famille Coulon (Domaine Beaurenard) Biotifulfox 2017", "8 €"],
+    ["A.O.P Vacqueyras", ""],
+    ["Domaine de Montvac 2017", "9 €"],
+    ["A.O.P Languedoc", ""],
+    ["Domaine de Joncas « Nébla » 2015", "8 €"],
+    ["Villa Tempora « L’arroseur arrosé » 2015", "9 €"],
+    ["A.O.P Côtes de Provence", ""],
+    ["Château Grand Boise « Sainte Victoire » 2017", "9 €"],
+    ["Château Léoube 2016", "10 €"],
+    ["Les Rouges", "12,CL"],
+    ["A.O.P Côtes du Rhône", ""],
+    ["Domaine de Dionysos « La Cigalette »", "8 €"],
+    ["Château Saint Estève d’Uchaux « Grande Réserve » 2014", "9 €"],
+    ["Domaine de la Guicharde « Cuvée Massillan » 2016", "9 €"],
+    ["Domaine de la Florane « Terre Pourpre » 2014", "10 €"],
+    ["L’Oratoire St Martin « Réserve des Seigneurs » 2015", "11 €"],
+    ["A.O.P Saint Joseph", ""],
+    ["Domaine Monier Perréol « Châtelet » 2015", "13 €"],
+    ["A.O.P Châteauneuf du Pape", ""],
+    ["Domaine de Beaurenard 2011", "15 €"],
+    ["A.O.P Cornas", ""],
+    ["Domaine Lionnet « Terre Brûlée » 2012", "15 €"]
 ]

tests/test_common.py

@@ -56,6 +56,18 @@ def test_stream_table_rotated():
     assert df.equals(tables[0].df)
 
 
+def test_stream_two_tables():
+    df1 = pd.DataFrame(data_stream_two_tables_1)
+    df2 = pd.DataFrame(data_stream_two_tables_2)
+
+    filename = os.path.join(testdir, "tabula/12s0324.pdf")
+    tables = camelot.read_pdf(filename, flavor='stream')
+
+    assert len(tables) == 2
+    assert df1.equals(tables[0].df)
+    assert df2.equals(tables[1].df)
+
+
 def test_stream_table_areas():
     df = pd.DataFrame(data_stream_table_areas)
 
@@ -69,7 +81,7 @@ def test_stream_columns():
 
     filename = os.path.join(testdir, "mexican_towns.pdf")
     tables = camelot.read_pdf(
-        filename, flavor="stream", columns=["67,180,230,425,475"], row_close_tol=10)
+        filename, flavor="stream", columns=["67,180,230,425,475"], row_tol=10)
     assert df.equals(tables[0].df)
 
 
@@ -90,6 +102,31 @@ def test_stream_flag_size():
     assert df.equals(tables[0].df)
 
 
+def test_stream_strip_text():
+    df = pd.DataFrame(data_stream_strip_text)
+
+    filename = os.path.join(testdir, "detect_vertical_false.pdf")
+    tables = camelot.read_pdf(filename, flavor="stream", strip_text="\n")
+    assert df.equals(tables[0].df)
+
+
+def test_stream_edge_tol():
+    df = pd.DataFrame(data_stream_edge_tol)
+
+    filename = os.path.join(testdir, "edge_tol.pdf")
+    tables = camelot.read_pdf(filename, flavor="stream", edge_tol=500)
+    assert df.equals(tables[0].df)
+
+
+def test_stream_layout_kwargs():
+    df = pd.DataFrame(data_stream_layout_kwargs)
+
+    filename = os.path.join(testdir, "detect_vertical_false.pdf")
+    tables = camelot.read_pdf(
+        filename, flavor="stream", layout_kwargs={"detect_vertical": False})
+    assert df.equals(tables[0].df)
+
+
 def test_lattice():
     df = pd.DataFrame(data_lattice)
 
@@ -111,6 +148,17 @@ def test_lattice_table_rotated():
     assert df.equals(tables[0].df)
 
 
+def test_lattice_two_tables():
+    df1 = pd.DataFrame(data_lattice_two_tables_1)
+    df2 = pd.DataFrame(data_lattice_two_tables_2)
+
+    filename = os.path.join(testdir, "twotables_2.pdf")
+    tables = camelot.read_pdf(filename)
+    assert len(tables) == 2
+    assert df1.equals(tables[0].df)
+    assert df2.equals(tables[1].df)
+
+
 def test_lattice_table_areas():
     df = pd.DataFrame(data_lattice_table_areas)
 
@@ -156,4 +204,20 @@ def test_repr():
     tables = camelot.read_pdf(filename)
     assert repr(tables) == "<TableList n=1>"
     assert repr(tables[0]) == "<Table shape=(7, 7)>"
-    assert repr(tables[0].cells[0][0]) == "<Cell x1=120.48 y1=218.42 x2=164.64 y2=233.89>"
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120.48 y1=218.43 x2=164.64 y2=233.77>"
+
+
+def test_url():
+    url = "https://camelot-py.readthedocs.io/en/master/_static/pdf/foo.pdf"
+    tables = camelot.read_pdf(url)
+    assert repr(tables) == "<TableList n=1>"
+    assert repr(tables[0]) == "<Table shape=(7, 7)>"
+    assert repr(tables[0].cells[0][0]) == "<Cell x1=120.48 y1=218.43 x2=164.64 y2=233.77>"
+
+
+def test_arabic():
+    df = pd.DataFrame(data_arabic)
+
+    filename = os.path.join(testdir, "tabula/arabic.pdf")
+    tables = camelot.read_pdf(filename)
+    assert df.equals(tables[0].df)

tests/test_errors.py

@@ -50,13 +50,25 @@ def test_no_tables_found():
         assert str(e.value) == 'No tables found on page-1'
 
 
+def test_no_tables_found_logs_suppressed():
+    filename = os.path.join(testdir, 'foo.pdf')
+    with warnings.catch_warnings():
+        # the test should fail if any warning is thrown
+        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))
+
+
 def test_no_tables_found_warnings_suppressed():
     filename = os.path.join(testdir, 'blank.pdf')
     with warnings.catch_warnings():
         # the test should fail if any warning is thrown
         warnings.simplefilter('error')
         try:
-            tables = camelot.read_pdf(filename, suppress_warnings=True)
+            tables = camelot.read_pdf(filename, suppress_stdout=True)
         except Warning as e:
             warning_text = str(e)
             pytest.fail('Unexpected warning: {}'.format(warning_text))

tests/test_plotting.py

@@ -29,12 +29,20 @@ def test_grid_plot():
 
 @pytest.mark.mpl_image_compare(
     baseline_dir="files/baseline_plots", remove_text=True)
-def test_contour_plot():
+def test_lattice_contour_plot():
     filename = os.path.join(testdir, "foo.pdf")
     tables = camelot.read_pdf(filename)
     return camelot.plot(tables[0], kind='contour')
 
 
+@pytest.mark.mpl_image_compare(
+    baseline_dir="files/baseline_plots", remove_text=True)
+def test_stream_contour_plot():
+    filename = os.path.join(testdir, "tabula/12s0324.pdf")
+    tables = camelot.read_pdf(filename, flavor='stream')
+    return camelot.plot(tables[0], kind='contour')
+
+
 @pytest.mark.mpl_image_compare(
     baseline_dir="files/baseline_plots", remove_text=True)
 def test_line_plot():
@@ -49,3 +57,11 @@ def test_joint_plot():
     filename = os.path.join(testdir, "foo.pdf")
     tables = camelot.read_pdf(filename)
     return camelot.plot(tables[0], kind='joint')
+
+
+@pytest.mark.mpl_image_compare(
+    baseline_dir="files/baseline_plots", remove_text=True)
+def test_textedge_plot():
+    filename = os.path.join(testdir, "tabula/12s0324.pdf")
+    tables = camelot.read_pdf(filename, flavor='stream')
+    return camelot.plot(tables[0], kind='textedge')