pdfminer.six/pdfminer/layout.py

791 lines
26 KiB
Python
Raw Normal View History

import heapq
import logging
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
from .utils import INF
2014-06-26 09:12:39 +00:00
from .utils import Plane
from .utils import apply_matrix_pt
2014-06-26 09:12:39 +00:00
from .utils import bbox2str
from .utils import fsplit
from .utils import get_bound
2014-06-26 09:12:39 +00:00
from .utils import matrix2str
from .utils import uniq
logger = logging.getLogger(__name__)
class IndexAssigner:
2011-05-14 06:51:40 +00:00
def __init__(self, index=0):
self.index = index
return
def run(self, obj):
if isinstance(obj, LTTextBox):
obj.index = self.index
self.index += 1
elif isinstance(obj, LTTextGroup):
for x in obj:
2011-05-14 07:32:09 +00:00
self.run(x)
2011-05-14 06:51:40 +00:00
return
class LAParams:
"""Parameters for layout analysis
:param line_overlap: If two characters have more overlap than this they
are considered to be on the same line. The overlap is specified
relative to the minimum height of both characters.
:param char_margin: If two characters are closer together than this
margin they are considered to be part of the same word. If
characters are on the same line but not part of the same word, an
intermediate space is inserted. The margin is specified relative to
the width of the character.
:param word_margin: If two words are are closer together than this
margin they are considered to be part of the same line. A space is
added in between for readability. The margin is specified relative
to the width of the word.
:param line_margin: If two lines are are close together they are
considered to be part of the same paragraph. The margin is
specified relative to the height of a line.
:param boxes_flow: Specifies how much a horizontal and vertical position
of a text matters when determining the order of text boxes. The value
should be within the range of -1.0 (only horizontal position
matters) to +1.0 (only vertical position matters).
:param detect_vertical: If vertical text should be considered during
layout analysis
:param all_texts: If layout analysis should be performed on text in
figures.
"""
def __init__(self,
line_overlap=0.5,
char_margin=2.0,
line_margin=0.5,
word_margin=0.1,
2011-02-14 14:41:23 +00:00
boxes_flow=0.5,
detect_vertical=False,
all_texts=False):
self.line_overlap = line_overlap
self.char_margin = char_margin
self.line_margin = line_margin
self.word_margin = word_margin
2010-12-26 08:26:39 +00:00
self.boxes_flow = boxes_flow
self.detect_vertical = detect_vertical
self.all_texts = all_texts
return
def __repr__(self):
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
return '<LAParams: char_margin=%.1f, line_margin=%.1f, ' \
'word_margin=%.1f all_texts=%r>' % \
(self.char_margin, self.line_margin, self.word_margin,
self.all_texts)
class LTItem:
"""Interface for things that can be analyzed"""
def analyze(self, laparams):
"""Perform the layout analysis."""
return
class LTText:
"""Interface for things that have text"""
def __repr__(self):
return ('<%s %r>' %
(self.__class__.__name__, self.get_text()))
def get_text(self):
"""Text contained in this object"""
raise NotImplementedError
class LTComponent(LTItem):
"""Object with a bounding box"""
def __init__(self, bbox):
LTItem.__init__(self)
self.set_bbox(bbox)
return
def __repr__(self):
return ('<%s %s>' %
(self.__class__.__name__, bbox2str(self.bbox)))
# Disable comparison.
def __lt__(self, _):
raise ValueError
def __le__(self, _):
raise ValueError
def __gt__(self, _):
raise ValueError
def __ge__(self, _):
raise ValueError
2014-06-15 03:12:13 +00:00
def set_bbox(self, bbox):
(x0, y0, x1, y1) = bbox
self.x0 = x0
self.y0 = y0
self.x1 = x1
self.y1 = y1
self.width = x1-x0
self.height = y1-y0
2014-06-15 03:12:13 +00:00
self.bbox = bbox
return
2011-03-01 11:47:20 +00:00
def is_empty(self):
return self.width <= 0 or self.height <= 0
2013-11-07 07:14:53 +00:00
def is_hoverlap(self, obj):
assert isinstance(obj, LTComponent), str(type(obj))
return obj.x0 <= self.x1 and self.x0 <= obj.x1
def hdistance(self, obj):
assert isinstance(obj, LTComponent), str(type(obj))
if self.is_hoverlap(obj):
return 0
else:
return min(abs(self.x0-obj.x1), abs(self.x1-obj.x0))
def hoverlap(self, obj):
assert isinstance(obj, LTComponent), str(type(obj))
if self.is_hoverlap(obj):
return min(abs(self.x0-obj.x1), abs(self.x1-obj.x0))
else:
return 0
def is_voverlap(self, obj):
assert isinstance(obj, LTComponent), str(type(obj))
return obj.y0 <= self.y1 and self.y0 <= obj.y1
def vdistance(self, obj):
assert isinstance(obj, LTComponent), str(type(obj))
if self.is_voverlap(obj):
return 0
else:
return min(abs(self.y0-obj.y1), abs(self.y1-obj.y0))
def voverlap(self, obj):
assert isinstance(obj, LTComponent), str(type(obj))
if self.is_voverlap(obj):
return min(abs(self.y0-obj.y1), abs(self.y1-obj.y0))
else:
return 0
class LTCurve(LTComponent):
"""A generic Bezier curve"""
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
def __init__(self, linewidth, pts, stroke=False, fill=False, evenodd=False,
stroking_color=None, non_stroking_color=None):
LTComponent.__init__(self, get_bound(pts))
self.pts = pts
self.linewidth = linewidth
self.stroke = stroke
self.fill = fill
self.evenodd = evenodd
self.stroking_color = stroking_color
self.non_stroking_color = non_stroking_color
return
def get_pts(self):
2013-11-07 08:35:04 +00:00
return ','.join('%.3f,%.3f' % p for p in self.pts)
2011-04-20 13:05:25 +00:00
class LTLine(LTCurve):
"""A single straight line.
Could be used for separating text or figures.
"""
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
def __init__(self, linewidth, p0, p1, stroke=False, fill=False,
evenodd=False, stroking_color=None, non_stroking_color=None):
LTCurve.__init__(self, linewidth, [p0, p1], stroke, fill, evenodd,
stroking_color, non_stroking_color)
return
2011-04-20 13:05:25 +00:00
class LTRect(LTCurve):
"""A rectangle.
Could be used for framing another pictures or figures.
"""
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
def __init__(self, linewidth, bbox, stroke=False, fill=False,
evenodd=False, stroking_color=None, non_stroking_color=None):
2014-06-15 03:12:13 +00:00
(x0, y0, x1, y1) = bbox
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
LTCurve.__init__(self, linewidth,
[(x0, y0), (x1, y0), (x1, y1), (x0, y1)], stroke,
fill, evenodd, stroking_color, non_stroking_color)
return
class LTImage(LTComponent):
"""An image object.
Embedded images can be in JPEG, Bitmap or JBIG2.
"""
def __init__(self, name, stream, bbox):
LTComponent.__init__(self, bbox)
self.name = name
self.stream = stream
self.srcsize = (stream.get_any(('W', 'Width')),
stream.get_any(('H', 'Height')))
self.imagemask = stream.get_any(('IM', 'ImageMask'))
self.bits = stream.get_any(('BPC', 'BitsPerComponent'), 1)
self.colorspace = stream.get_any(('CS', 'ColorSpace'))
if not isinstance(self.colorspace, list):
self.colorspace = [self.colorspace]
return
def __repr__(self):
return ('<%s(%s) %s %r>' %
(self.__class__.__name__, self.name,
bbox2str(self.bbox), self.srcsize))
2013-11-11 10:17:45 +00:00
class LTAnno(LTItem, LTText):
"""Actual letter in the text as a Unicode string.
Note that, while a LTChar object has actual boundaries, LTAnno objects does
not, as these are "virtual" characters, inserted by a layout analyzer
according to the relationship between two characters (e.g. a space).
"""
def __init__(self, text):
self._text = text
return
def get_text(self):
return self._text
class LTChar(LTComponent, LTText):
"""Actual letter in the text as a Unicode string."""
2013-11-11 11:46:30 +00:00
def __init__(self, matrix, font, fontsize, scaling, rise,
text, textwidth, textdisp, ncs, graphicstate):
LTText.__init__(self)
self._text = text
self.matrix = matrix
self.fontname = font.fontname
self.ncs = ncs
self.graphicstate = graphicstate
self.adv = textwidth * fontsize * scaling
# compute the boundary rectangle.
if font.is_vertical():
# vertical
2013-11-07 08:35:04 +00:00
(vx, vy) = textdisp
if vx is None:
vx = fontsize * 0.5
else:
vx = vx * fontsize * .001
vy = (1000 - vy) * fontsize * .001
bbox_lower_left = (-vx, vy + rise + self.adv)
bbox_upper_right = (-vx + fontsize, vy + rise)
else:
# horizontal
descent = font.get_descent() * fontsize
bbox_lower_left = (0, descent + rise)
bbox_upper_right = (self.adv, descent + rise + fontsize)
2013-11-07 08:35:04 +00:00
(a, b, c, d, e, f) = self.matrix
self.upright = (0 < a*d*scaling and b*c <= 0)
(x0, y0) = apply_matrix_pt(self.matrix, bbox_lower_left)
(x1, y1) = apply_matrix_pt(self.matrix, bbox_upper_right)
if x1 < x0:
2013-11-07 08:35:04 +00:00
(x0, x1) = (x1, x0)
if y1 < y0:
2013-11-07 08:35:04 +00:00
(y0, y1) = (y1, y0)
LTComponent.__init__(self, (x0, y0, x1, y1))
if font.is_vertical():
self.size = self.width
else:
self.size = self.height
return
def __repr__(self):
return ('<%s %s matrix=%s font=%r adv=%s text=%r>' %
2013-11-07 07:14:53 +00:00
(self.__class__.__name__, bbox2str(self.bbox),
matrix2str(self.matrix), self.fontname, self.adv,
self.get_text()))
def get_text(self):
return self._text
def is_compatible(self, obj):
"""Returns True if two characters can coexist in the same line."""
return True
2013-11-07 07:14:53 +00:00
class LTContainer(LTComponent):
"""Object that can be extended and analyzed"""
def __init__(self, bbox):
LTComponent.__init__(self, bbox)
self._objs = []
return
def __iter__(self):
return iter(self._objs)
def __len__(self):
return len(self._objs)
def add(self, obj):
self._objs.append(obj)
return
def extend(self, objs):
for obj in objs:
self.add(obj)
return
2011-05-14 05:17:39 +00:00
def analyze(self, laparams):
for obj in self._objs:
obj.analyze(laparams)
return
2013-11-07 07:14:53 +00:00
class LTExpandableContainer(LTContainer):
def __init__(self):
2013-11-07 08:35:04 +00:00
LTContainer.__init__(self, (+INF, +INF, -INF, -INF))
return
def add(self, obj):
LTContainer.add(self, obj)
self.set_bbox((min(self.x0, obj.x0), min(self.y0, obj.y0),
max(self.x1, obj.x1), max(self.y1, obj.y1)))
return
class LTTextContainer(LTExpandableContainer, LTText):
def __init__(self):
LTText.__init__(self)
LTExpandableContainer.__init__(self)
return
def get_text(self):
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
return ''.join(obj.get_text() for obj in self
if isinstance(obj, LTText))
2013-11-07 07:14:53 +00:00
class LTTextLine(LTTextContainer):
"""Contains a list of LTChar objects that represent a single text line.
The characters are aligned either horizontally or vertically, depending on
the text's writing mode.
"""
def __init__(self, word_margin):
LTTextContainer.__init__(self)
self.word_margin = word_margin
return
def __repr__(self):
return ('<%s %s %r>' %
(self.__class__.__name__, bbox2str(self.bbox),
self.get_text()))
def analyze(self, laparams):
LTTextContainer.analyze(self, laparams)
2013-11-11 10:17:45 +00:00
LTContainer.add(self, LTAnno('\n'))
2011-05-14 05:17:39 +00:00
return
def find_neighbors(self, plane, ratio):
raise NotImplementedError
2013-11-07 08:35:04 +00:00
class LTTextLineHorizontal(LTTextLine):
def __init__(self, word_margin):
LTTextLine.__init__(self, word_margin)
self._x1 = +INF
return
def add(self, obj):
if isinstance(obj, LTChar) and self.word_margin:
2013-11-05 09:25:19 +00:00
margin = self.word_margin * max(obj.width, obj.height)
if self._x1 < obj.x0-margin:
2013-11-11 10:17:45 +00:00
LTContainer.add(self, LTAnno(' '))
self._x1 = obj.x1
LTTextLine.add(self, obj)
return
def find_neighbors(self, plane, ratio):
d = ratio*self.height
objs = plane.find((self.x0, self.y0-d, self.x1, self.y1+d))
2013-11-07 08:35:04 +00:00
return [obj for obj in objs
if (isinstance(obj, LTTextLineHorizontal) and
abs(obj.height-self.height) < d and
(abs(obj.x0-self.x0) < d or
abs(obj.x1-self.x1) < d))]
2013-11-07 07:14:53 +00:00
class LTTextLineVertical(LTTextLine):
def __init__(self, word_margin):
LTTextLine.__init__(self, word_margin)
self._y0 = -INF
return
def add(self, obj):
if isinstance(obj, LTChar) and self.word_margin:
2013-11-05 09:25:19 +00:00
margin = self.word_margin * max(obj.width, obj.height)
if obj.y1+margin < self._y0:
2013-11-11 10:17:45 +00:00
LTContainer.add(self, LTAnno(' '))
self._y0 = obj.y0
LTTextLine.add(self, obj)
return
2013-11-07 07:14:53 +00:00
def find_neighbors(self, plane, ratio):
d = ratio*self.width
objs = plane.find((self.x0-d, self.y0, self.x1+d, self.y1))
2013-11-07 08:35:04 +00:00
return [obj for obj in objs
if (isinstance(obj, LTTextLineVertical) and
abs(obj.width-self.width) < d and
(abs(obj.y0-self.y0) < d or
abs(obj.y1-self.y1) < d))]
2013-11-07 07:14:53 +00:00
class LTTextBox(LTTextContainer):
"""Represents a group of text chunks in a rectangular area.
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
Note that this box is created by geometric analysis and does not
necessarily represents a logical boundary of the text. It contains a list
of LTTextLine objects.
"""
def __init__(self):
LTTextContainer.__init__(self)
self.index = -1
return
def __repr__(self):
2011-05-14 05:17:39 +00:00
return ('<%s(%s) %s %r>' %
(self.__class__.__name__,
self.index, bbox2str(self.bbox), self.get_text()))
2013-11-07 08:35:04 +00:00
class LTTextBoxHorizontal(LTTextBox):
def analyze(self, laparams):
2011-05-14 05:17:39 +00:00
LTTextBox.analyze(self, laparams)
self._objs.sort(key=lambda obj: -obj.y1)
2011-05-14 05:17:39 +00:00
return
def get_writing_mode(self):
return 'lr-tb'
2013-11-07 08:35:04 +00:00
class LTTextBoxVertical(LTTextBox):
def analyze(self, laparams):
2011-05-14 05:17:39 +00:00
LTTextBox.analyze(self, laparams)
2018-04-11 00:15:32 +00:00
self._objs.sort(key=lambda obj: -obj.x1)
2011-05-14 05:17:39 +00:00
return
def get_writing_mode(self):
return 'tb-rl'
class LTTextGroup(LTTextContainer):
def __init__(self, objs):
LTTextContainer.__init__(self)
self.extend(objs)
return
2013-11-07 08:35:04 +00:00
class LTTextGroupLRTB(LTTextGroup):
def analyze(self, laparams):
2011-05-14 05:17:39 +00:00
LTTextGroup.analyze(self, laparams)
# reorder the objects from top-left to bottom-right.
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
self._objs.sort(
key=lambda obj: (1 - laparams.boxes_flow) * obj.x0
- (1 + laparams.boxes_flow) * (obj.y0 + obj.y1))
2011-05-14 05:17:39 +00:00
return
2013-11-07 08:35:04 +00:00
class LTTextGroupTBRL(LTTextGroup):
def analyze(self, laparams):
2011-05-14 05:17:39 +00:00
LTTextGroup.analyze(self, laparams)
# reorder the objects from top-right to bottom-left.
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
self._objs.sort(
key=lambda obj: - (1 + laparams.boxes_flow) * (obj.x0 + obj.x1)
- (1 - laparams.boxes_flow) * obj.y1)
2011-05-14 05:17:39 +00:00
return
class LTLayoutContainer(LTContainer):
def __init__(self, bbox):
LTContainer.__init__(self, bbox)
2011-05-14 06:51:40 +00:00
self.groups = None
return
2013-11-07 07:14:53 +00:00
# group_objects: group text object to textlines.
def group_objects(self, laparams, objs):
obj0 = None
line = None
for obj1 in objs:
if obj0 is not None:
2013-11-11 11:46:30 +00:00
# halign: obj0 and obj1 is horizontally aligned.
#
# +------+ - - -
# | obj0 | - - +------+ -
# | | | obj1 | | (line_overlap)
# +------+ - - | | -
# - - - +------+
#
# |<--->|
# (char_margin)
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
halign = \
obj0.is_compatible(obj1) \
and obj0.is_voverlap(obj1) \
and min(obj0.height, obj1.height) * laparams.line_overlap \
< obj0.voverlap(obj1) \
and obj0.hdistance(obj1) \
< max(obj0.width, obj1.width) * laparams.char_margin
2013-11-11 11:46:30 +00:00
# valign: obj0 and obj1 is vertically aligned.
#
# +------+
# | obj0 |
# | |
# +------+ - - -
# | | | (char_margin)
# +------+ - -
# | obj1 |
# | |
# +------+
#
# |<-->|
# (line_overlap)
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
valign = \
laparams.detect_vertical \
and obj0.is_compatible(obj1) \
and obj0.is_hoverlap(obj1) \
and min(obj0.width, obj1.width) * laparams.line_overlap \
< obj0.hoverlap(obj1) \
and obj0.vdistance(obj1) \
< max(obj0.height, obj1.height) * laparams.char_margin
2013-11-11 11:46:30 +00:00
if ((halign and isinstance(line, LTTextLineHorizontal)) or
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
(valign and isinstance(line, LTTextLineVertical))):
line.add(obj1)
elif line is not None:
2011-05-14 05:17:39 +00:00
yield line
line = None
else:
2013-11-11 11:46:30 +00:00
if valign and not halign:
line = LTTextLineVertical(laparams.word_margin)
line.add(obj0)
line.add(obj1)
2013-11-11 11:46:30 +00:00
elif halign and not valign:
line = LTTextLineHorizontal(laparams.word_margin)
line.add(obj0)
line.add(obj1)
else:
line = LTTextLineHorizontal(laparams.word_margin)
line.add(obj0)
2011-05-14 05:17:39 +00:00
yield line
line = None
obj0 = obj1
if line is None:
line = LTTextLineHorizontal(laparams.word_margin)
line.add(obj0)
2011-05-14 05:17:39 +00:00
yield line
return
def group_textlines(self, laparams, lines):
"""Group neighboring lines to textboxes"""
plane = Plane(self.bbox)
plane.extend(lines)
boxes = {}
for line in lines:
neighbors = line.find_neighbors(plane, laparams.line_margin)
members = [line]
for obj1 in neighbors:
members.append(obj1)
if obj1 in boxes:
members.extend(boxes.pop(obj1))
if isinstance(line, LTTextLineHorizontal):
box = LTTextBoxHorizontal()
else:
box = LTTextBoxVertical()
for obj in uniq(members):
box.add(obj)
boxes[obj] = box
done = set()
for line in lines:
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
if line not in boxes:
continue
box = boxes[line]
2013-11-07 08:35:04 +00:00
if box in done:
continue
done.add(box)
2013-10-09 13:13:22 +00:00
if not box.is_empty():
yield box
return
def group_textboxes(self, laparams, boxes):
"""Group textboxes hierarchically.
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
Get pair-wise distances, via dist func defined below, and then merge
from the closest textbox pair. Once obj1 and obj2 are merged /
grouped, the resulting group is considered as a new object, and its
distances to other objects & groups are added to the process queue.
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
For performance reason, pair-wise distances and object pair info are
maintained in a heap of (idx, dist, id(obj1), id(obj2), obj1, obj2)
tuples. It ensures quick access to the smallest element. Note that
since comparison operators, e.g., __lt__, are disabled for
LTComponent, id(obj) has to appear before obj in element tuples.
:param laparams: LAParams object.
:param boxes: All textbox objects to be grouped.
:return: a list that has only one element, the final top level textbox.
"""
2013-11-07 08:35:04 +00:00
2011-05-14 05:17:39 +00:00
def dist(obj1, obj2):
"""A distance function between two TextBoxes.
2013-11-07 07:14:53 +00:00
Consider the bounding rectangle for obj1 and obj2.
2013-11-07 07:14:53 +00:00
Return its area less the areas of obj1 and obj2,
shown as 'www' below. This value may be negative.
2013-11-07 08:35:04 +00:00
+------+..........+ (x1, y1)
2011-02-14 14:41:23 +00:00
| obj1 |wwwwwwwwww:
+------+www+------+
:wwwwwwwwww| obj2 |
2013-11-07 08:35:04 +00:00
(x0, y0) +..........+------+
"""
2013-11-07 08:35:04 +00:00
x0 = min(obj1.x0, obj2.x0)
y0 = min(obj1.y0, obj2.y0)
x1 = max(obj1.x1, obj2.x1)
y1 = max(obj1.y1, obj2.y1)
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
return (x1 - x0) * (y1 - y0) \
- obj1.width*obj1.height - obj2.width*obj2.height
2013-11-07 08:35:04 +00:00
def isany(obj1, obj2):
"""Check if there's any other object between obj1 and obj2."""
2013-11-07 08:35:04 +00:00
x0 = min(obj1.x0, obj2.x0)
y0 = min(obj1.y0, obj2.y0)
x1 = max(obj1.x1, obj2.x1)
y1 = max(obj1.y1, obj2.y1)
objs = set(plane.find((x0, y0, x1, y1)))
return objs.difference((obj1, obj2))
dists = []
2014-09-03 13:26:08 +00:00
for i in range(len(boxes)):
2011-05-14 05:17:39 +00:00
obj1 = boxes[i]
2014-09-03 13:26:08 +00:00
for j in range(i+1, len(boxes)):
2011-05-14 05:17:39 +00:00
obj2 = boxes[j]
dists.append((False, dist(obj1, obj2), id(obj1), id(obj2),
obj1, obj2))
heapq.heapify(dists)
plane = Plane(self.bbox)
plane.extend(boxes)
done = set()
while len(dists) > 0:
(skip_isany, d, id1, id2, obj1, obj2) = heapq.heappop(dists)
# Skip objects that are already merged
if (id1 not in done) and (id2 not in done):
if skip_isany and isany(obj1, obj2):
heapq.heappush(dists, (True, d, id1, id2, obj1, obj2))
continue
if isinstance(obj1, (LTTextBoxVertical, LTTextGroupTBRL)) or \
isinstance(obj2, (LTTextBoxVertical, LTTextGroupTBRL)):
group = LTTextGroupTBRL([obj1, obj2])
else:
group = LTTextGroupLRTB([obj1, obj2])
plane.remove(obj1)
plane.remove(obj2)
done.update([id1, id2])
for other in plane:
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
heapq.heappush(dists, (False, dist(group, other),
id(group), id(other), group, other))
plane.add(group)
2011-05-14 06:51:40 +00:00
return list(plane)
2013-11-07 07:14:53 +00:00
def analyze(self, laparams):
# textobjs is a list of LTChar objects, i.e.
# it has all the individual characters in the page.
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
(textobjs, otherobjs) = fsplit(lambda obj: isinstance(obj, LTChar),
self)
for obj in otherobjs:
obj.analyze(laparams)
2013-11-07 08:35:04 +00:00
if not textobjs:
return
textlines = list(self.group_objects(laparams, textobjs))
(empties, textlines) = fsplit(lambda obj: obj.is_empty(), textlines)
for obj in empties:
obj.analyze(laparams)
textboxes = list(self.group_textlines(laparams, textlines))
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
if -1 <= laparams.boxes_flow and laparams.boxes_flow <= +1 \
and textboxes:
2013-10-09 13:13:22 +00:00
self.groups = self.group_textboxes(laparams, textboxes)
assigner = IndexAssigner()
for group in self.groups:
group.analyze(laparams)
assigner.run(group)
2013-11-07 08:35:04 +00:00
textboxes.sort(key=lambda box: box.index)
else:
def getkey(box):
if isinstance(box, LTTextBoxVertical):
return (0, -box.x1, box.y0)
else:
return (1, box.y0, box.x0)
textboxes.sort(key=getkey)
self._objs = textboxes + otherobjs + empties
return
class LTFigure(LTLayoutContainer):
"""Represents an area used by PDF Form objects.
PDF Forms can be used to present figures or pictures by embedding yet
another PDF document within a page. Note that LTFigure objects can appear
recursively.
"""
def __init__(self, name, bbox, matrix):
self.name = name
self.matrix = matrix
2013-11-07 08:35:04 +00:00
(x, y, w, h) = bbox
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
bounds = ((x, y), (x + w, y), (x, y + h), (x + w, y + h))
bbox = get_bound(apply_matrix_pt(matrix, (p, q)) for (p, q) in bounds)
LTLayoutContainer.__init__(self, bbox)
return
def __repr__(self):
return ('<%s(%s) %s matrix=%s>' %
(self.__class__.__name__, self.name,
bbox2str(self.bbox), matrix2str(self.matrix)))
def analyze(self, laparams):
2013-11-07 08:35:04 +00:00
if not laparams.all_texts:
return
2011-05-14 05:17:39 +00:00
LTLayoutContainer.analyze(self, laparams)
2013-11-07 07:14:53 +00:00
return
class LTPage(LTLayoutContainer):
"""Represents an entire page.
May contain child objects like LTTextBox, LTFigure, LTImage, LTRect,
LTCurve and LTLine.
"""
def __init__(self, pageid, bbox, rotate=0):
LTLayoutContainer.__init__(self, bbox)
self.pageid = pageid
self.rotate = rotate
return
def __repr__(self):
return ('<%s(%r) %s rotate=%r>' %
(self.__class__.__name__, self.pageid,
bbox2str(self.bbox), self.rotate))