Update HISTORY.md and bump version

Update HISTORY.md
Merge pull request #227 from socialcopsdev/fix-050-bugs
2018-12-13 16:46:17 +05:30 · 2018-12-13 16:29:47 +05:30 · 2018-12-13 16:06:48 +05:30 · 2018-12-13 14:36:50 +05:30 · 2018-12-13 13:13:07 +05:30 · 2018-12-13 12:50:30 +05:30
42 changed files with 1227 additions and 241 deletions
@@ -4,6 +4,45 @@ Release History
 master
 ------

+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)
 ------------------

@@ -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
@@ -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]
@@ -1,11 +1,23 @@
 # -*- coding: utf-8 -*-

-VERSION = (0, 3, 1)
+VERSION = (0, 5, 0)
+PRERELEASE = None # alpha, beta or rc
+REVISION = None
+
+
+def generate_version(version, prerelease=None, revision=None):
+    version_parts = ['.'.join(map(str, version))]
+    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'
@@ -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.')
@@ -44,7 +45,6 @@ pass_config = click.make_pass_decorator(Config)
              ' font size. Useful to detect super/subscripts.')
@click.option('-M', '--margins', nargs=3, default=(1.0, 0.5, 0.1),
              help='PDFMiner char_margin, line_margin and word_margin.')
-@click.option('-q', '--quiet', is_flag=True, help='Suppress warnings.')
@click.pass_context
 def cli(ctx, *args, **kwargs):
    """Camelot: PDF Table Extraction for Humans"""
@@ -96,7 +96,7 @@ 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 +117,7 @@ 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:
@@ -138,7 +138,7 @@ def lattice(c, *args, **kwargs):
@click.option('-c', '--col_close_tol', default=0, help='Tolerance parameter'
              ' used to combine text horizontally, to generate columns.')
@click.option('-plot', '--plot_type',
-              type=click.Choice(['text', 'grid']),
+              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 +149,7 @@ 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 +169,7 @@ 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:
@@ -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
+# y coordinate tolerance for extending textedge
+TEXTEDGE_EXTEND_TOLERANCE = 50
+# padding added to table area on the left, right and bottom
+TABLE_AREA_PADDING = 10
+
+
+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):
+        """Updates the text edge's x and bottom y coordinates and sets
+        the is_valid attribute.
+        """
+        if np.isclose(self.y0, y0, atol=TEXTEDGE_EXTEND_TOLERANCE):
+            self.x = (self.intersections * self.x + x) / float(self.intersections + 1)
+            self.y0 = y0
+            self.intersections += 1
+            # 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):
+        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)
+
+    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)
@@ -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:
@@ -125,7 +125,7 @@ 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, **kwargs):
        """Extracts tables by calling parser.get_tables on all single
        page PDFs.

@@ -134,6 +134,8 @@ 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.
        kwargs : dict
            See camelot.read_pdf kwargs.

@@ -151,6 +153,6 @@ class PDFHandler(object):
                     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)
                tables.extend(t)
        return TableList(tables)
@@ -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, **kwargs):
    """Read PDF and return extracted tables.

    Note: kwargs annotated with ^ can only be used with flavor='stream'
@@ -24,8 +24,8 @@ 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.
    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
@@ -92,11 +92,11 @@ 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, **kwargs)
        return tables
@@ -271,10 +271,11 @@ 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)
@@ -308,7 +309,9 @@ class Lattice(BaseParser):
        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,
@@ -341,12 +344,14 @@ 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):
+    def extract_tables(self, filename, suppress_stdout=False):
        self._generate_layout(filename)
-        logger.info('Processing {}'.format(os.path.basename(self.rootname)))
+        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 +367,7 @@ 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
@@ -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)

@@ -116,7 +116,7 @@ class Stream(BaseParser):
                    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
@@ -246,7 +246,34 @@ 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()
+        # 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 +284,8 @@ 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):
@@ -265,10 +293,11 @@ 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)
-        self.t_bbox = t_bbox

-        for direction in self.t_bbox:
-            self.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

        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)
@@ -286,10 +315,21 @@ 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)
            inner_text = []
@@ -311,8 +351,11 @@ 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,
@@ -341,12 +384,14 @@ class Stream(BaseParser):
        table._text = _text
        table._image = None
        table._segments = None
+        table._textedges = self.textedges

        return table

-    def extract_tables(self, filename):
+    def extract_tables(self, filename, suppress_stdout=False):
        self._generate_layout(filename)
-        logger.info('Processing {}'.format(os.path.basename(self.rootname)))
+        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 +406,7 @@ 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
@@ -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):
@@ -344,9 +344,9 @@ 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)
    else:
-        fstring = ''.join([t.get_text() for t in textline]).strip('\n')
+        fstring = ''.join([t.get_text() for t in textline])
    return fstring


@@ -419,7 +419,7 @@ def split_textline(table, textline, direction, flag_size=False):
            grouped_chars.append((key[0], key[1], flag_font_size([t[2] for t in chars], direction)))
        else:
            gchars = [t[2].get_text() for t in chars]
-            grouped_chars.append((key[0], key[1], ''.join(gchars).strip('\n')))
+            grouped_chars.append((key[0], key[1], ''.join(gchars)))
    return grouped_chars


@@ -500,7 +500,7 @@ def get_table_index(table, t, direction, split_text=False, flag_size=False):
        if flag_size:
            return [(r_idx, c_idx, flag_font_size(t._objs, direction))], error
        else:
-            return [(r_idx, c_idx, t.get_text().strip('\n'))], error
+            return [(r_idx, c_idx, t.get_text())], error


 def compute_accuracy(error_weights):
@@ -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"
@@ -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"
@@ -0,0 +1,18 @@
+"0","1","2"
+"","e
+bl
+a
+ail
+v
+a
+ 
+t
+o
+n
+ 
+a
+t
+a
+D
+ 
+*",""
@@ -0,0 +1,3 @@
+"0"
+"Sl."
+"No."
@@ -0,0 +1,3 @@
+"0"
+"Table 6 : DISTRIBUTION (%) OF HOUSEHOLDS BY LITERACY STATUS OF"
+"MALE HEAD OF THE HOUSEHOLD"
@@ -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.","","","","","","","",""
@@ -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,","","","",""
@@ -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"
@@ -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"
@@ -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","","","",""
@@ -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",""
+"","","","","","","","","","","","","","","","","","","","","","","",""
@@ -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","","","",""
@@ -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
 ---------------
@@ -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
@@ -41,8 +41,9 @@ 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.

@@ -80,7 +81,7 @@ 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()

 .. figure:: ../_static/png/plot_table.png
@@ -143,10 +144,27 @@ 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()
+
+.. 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.

@@ -169,7 +187,7 @@ 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!

@@ -284,7 +302,7 @@ 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
@@ -296,7 +314,7 @@ 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()

 .. figure:: ../_static/png/short_lines_2.png
@@ -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.
+    -v, --verbose                   Verbose.
    -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:
@@ -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:

@@ -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.
@@ -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
@@ -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
@@ -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',
@@ -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 +309,12 @@ 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_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 +323,7 @@ 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 +338,42 @@ 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 +389,13 @@ 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 +439,11 @@ 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 +452,12 @@ 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 +466,12 @@ 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 +481,13 @@ 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', '']
 ]
@@ -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)

@@ -111,6 +123,17 @@ 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)

@@ -157,3 +180,11 @@ def test_repr():
    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>"
+
+
+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)
@@ -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))
@@ -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')
Author	SHA1	Message	Date
Vinayak Mehta	153869fda2	Update HISTORY.md and bump version Update HISTORY.md	2018-12-13 16:46:17 +05:30
Vinayak Mehta	f8eaec4ce4	Merge pull request #227 from socialcopsdev/fix-050-bugs Fix v0.5.0 bugs	2018-12-13 16:29:47 +05:30
Vinayak Mehta	d83d5fae42	Fix tests Fix tests	2018-12-13 16:06:48 +05:30
Vinayak Mehta	69136431b6	Fix #215	2018-12-13 14:36:50 +05:30
Vinayak Mehta	ff4d8ce228	Add test for arabic	2018-12-13 13:13:07 +05:30
Vinayak Mehta	5e71f0b0e6	Fix #192	2018-12-13 12:50:30 +05:30
Vinayak Mehta	33cea45346	Fix #105	2018-12-13 00:45:22 +05:30
Vinayak Mehta	40217bea46	Merge pull request #225 from socialcopsdev/fix-204 [MRG] Change suppress_warnings to suppress_stdout	2018-12-12 10:34:08 +05:30
Vinayak Mehta	591cfd5291	Change kwarg name	2018-12-12 10:15:04 +05:30
Vinayak Mehta	de0079a711	Update HISTORY.md	2018-12-12 09:59:22 +05:30
Vinayak Mehta	e50f9c8847	Change suppress_warnings to verbose	2018-12-12 09:58:34 +05:30
Vinayak Mehta	50780e24f8	Merge pull request #224 from socialcopsdev/fix-207 [MRG] Add plot types and update docs	2018-12-12 08:53:58 +05:30
Vinayak Mehta	92e02fa03d	Update HISTORY.md	2018-12-12 08:26:59 +05:30
Vinayak Mehta	656c4e09bc	Update docs	2018-12-12 08:18:49 +05:30
Vinayak Mehta	b56d2246ad	Add new plot type tests	2018-12-12 08:09:52 +05:30
Vinayak Mehta	87a2f4fdc9	Add textedge plot type	2018-12-12 07:36:07 +05:30
Vinayak Mehta	451fac9e53	Add updated stream benchmark	2018-12-11 21:28:42 +05:30
Vinayak Mehta	649fd67c44	Rename file	2018-12-11 21:17:50 +05:30
Vinayak Mehta	e45e7478bf	Add updated stream benchmark	2018-12-11 21:16:16 +05:30
Vinayak Mehta	d6ffe0f1a9	Add pdfplumber benchmark	2018-12-11 20:34:43 +05:30
Vinayak Mehta	423e5f8aad	Merge pull request #221 from socialcopsdev/fix-217 [MRG] Fix variable name	2018-12-07 20:51:13 +05:30
Vinayak Mehta	619ce2e2a4	Fix grid plot baseline image	2018-12-07 20:22:56 +05:30
Vinayak Mehta	8d8ca6e435	Fix variable name	2018-12-07 18:45:23 +05:30
Vinayak Mehta	1f0a1c0c68	Merge pull request #218 from socialcopsdev/add-chardet Add chardet to install_requires	2018-12-05 21:00:22 +05:30
Vinayak Mehta	cb3e76726b	Bump version	2018-12-05 20:10:25 +05:30
Vinayak Mehta	2635f910e4	Add chardet to install_requires	2018-12-05 20:08:37 +05:30
Vinayak Mehta	7bdd9a3156	Update docs	2018-12-01 06:29:35 +05:30
Vinayak Mehta	6df88f90fb	Update HISTORY.md	2018-11-23 21:39:42 +05:30
Vinayak Mehta	e4af252280	Update HISTORY.md	2018-11-23 21:37:40 +05:30
Vinayak Mehta	e7835cac33	Merge pull request #206 from socialcopsdev/stream-nurminen-detection [MRG] Add implementation of Anssi Nurminen's table detection algorithm	2018-11-23 21:35:03 +05:30
Vinayak Mehta	23ec6b55f7	Add docstrings and update docs	2018-11-23 21:04:10 +05:30
Vinayak Mehta	1f71513004	Fix no table found warning and add tests for two tables	2018-11-23 19:28:55 +05:30
Vinayak Mehta	bf894116d2	Update test data	2018-11-23 04:25:04 +05:30
Vinayak Mehta	0251422e33	Add fix to include table headers	2018-11-23 03:27:23 +05:30
Vinayak Mehta	a1e1fd781d	Fix comments	2018-11-23 02:51:22 +05:30
Vinayak Mehta	9b67b271e4	Add atol and fix variable declaration	2018-11-23 02:44:55 +05:30
Vinayak Mehta	9b5782f9ba	Fix indent	2018-11-22 20:05:30 +05:30
Vinayak Mehta	bcde67fe17	Add constant to include table headers	2018-11-22 19:56:16 +05:30
Vinayak Mehta	529914eb6f	Update comment	2018-11-22 19:50:59 +05:30
Vinayak Mehta	4e2aee18c3	Add get_table_areas textedges method	2018-11-22 19:48:51 +05:30
Vinayak Mehta	a587ea3782	Add get_relevant textedges method	2018-11-22 18:24:31 +05:30
Vinayak Mehta	378408a271	Remove debug statements	2018-11-22 05:42:10 +05:30
Vinayak Mehta	123227aa8c	Add TextEdge and TextEdges helper classes	2018-11-22 05:31:02 +05:30
Vinayak Mehta	cd3aa38f7e	Change table to grid (#196 )	2018-11-06 19:18:45 +05:30
Vinayak Mehta	b310f16dba	Bump version and update HISTORY.md	2018-11-04 01:37:27 +05:30
Vinayak Mehta	defaead679	Add table bbox attribute (#193 )	2018-11-04 01:33:41 +05:30
Palash Chatterjee	a60ce38d4d	[MRG + 1] Fix the order of coordinates in docs (#191 )	2018-11-03 01:06:44 +05:30