Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixes #672 and #630 #801

Merged
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
- Output converter for the hOCR format ([#651](https://github.com/pdfminer/pdfminer.six/pull/651))
- Font name aliases for Arial, Courier New and Times New Roman ([#790](https://github.com/pdfminer/pdfminer.six/pull/790))
- Documentation on why special characters can sometimes not be extracted ([#829](https://github.com/pdfminer/pdfminer.six/pull/829))
- Storing Bezier path and dashing style of line in LTCurve ([#801](https://github.com/pdfminer/pdfminer.six/pull/801))

### Fixed

Expand Down
22 changes: 21 additions & 1 deletion pdfminer/converter.py
Original file line number Diff line number Diff line change
Expand Up @@ -138,6 +138,19 @@ def paint_path(
]
pts = [apply_matrix_pt(self.ctm, pt) for pt in raw_pts]

operators = [str(operation[0]) for operation in path]
transformed_points = [
[
apply_matrix_pt(self.ctm, (float(operand1), float(operand2)))
for operand1, operand2 in zip(operation[1::2], operation[2::2])
]
for operation in path
]
transformed_path = [
cast(PathSegment, (o, *p))
for o, p in zip(operators, transformed_points)
]

if shape in {"mlh", "ml"}:
# single line segment
#
Expand All @@ -152,6 +165,8 @@ def paint_path(
evenodd,
gstate.scolor,
gstate.ncolor,
original_path=transformed_path,
dashing_style=gstate.dash,
)
self.cur_item.add(line)

Expand All @@ -171,6 +186,8 @@ def paint_path(
evenodd,
gstate.scolor,
gstate.ncolor,
transformed_path,
gstate.dash,
)
self.cur_item.add(rect)
else:
Expand All @@ -182,9 +199,10 @@ def paint_path(
evenodd,
gstate.scolor,
gstate.ncolor,
transformed_path,
gstate.dash,
)
self.cur_item.add(curve)

else:
curve = LTCurve(
gstate.linewidth,
Expand All @@ -194,6 +212,8 @@ def paint_path(
evenodd,
gstate.scolor,
gstate.ncolor,
transformed_path,
gstate.dash,
)
self.cur_item.add(curve)

Expand Down
23 changes: 21 additions & 2 deletions pdfminer/layout.py
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
from .pdfinterp import Color
from .pdfinterp import PDFGraphicState
from .pdftypes import PDFStream
from .utils import INF
from .utils import INF, PathSegment
from .utils import LTComponentT
from .utils import Matrix
from .utils import Plane
Expand Down Expand Up @@ -210,7 +210,14 @@ def voverlap(self, obj: "LTComponent") -> float:


class LTCurve(LTComponent):
"""A generic Bezier curve"""
"""
A generic Bezier curve

The parameter `original_path` contains the original
pathing information from the pdf (e.g. for reconstructing Bezier Curves).

`dashing_style` contains the Dashing information if any.
"""

def __init__(
self,
Expand All @@ -221,6 +228,8 @@ def __init__(
evenodd: bool = False,
stroking_color: Optional[Color] = None,
non_stroking_color: Optional[Color] = None,
original_path: Optional[List[PathSegment]] = None,
dashing_style: Optional[Tuple[object, object]] = None,
) -> None:
LTComponent.__init__(self, get_bound(pts))
self.pts = pts
Expand All @@ -230,6 +239,8 @@ def __init__(
self.evenodd = evenodd
self.stroking_color = stroking_color
self.non_stroking_color = non_stroking_color
self.original_path = original_path
self.dashing_style = dashing_style

def get_pts(self) -> str:
return ",".join("%.3f,%.3f" % p for p in self.pts)
Expand All @@ -251,6 +262,8 @@ def __init__(
evenodd: bool = False,
stroking_color: Optional[Color] = None,
non_stroking_color: Optional[Color] = None,
original_path: Optional[List[PathSegment]] = None,
dashing_style: Optional[Tuple[object, object]] = None,
) -> None:
LTCurve.__init__(
self,
Expand All @@ -261,6 +274,8 @@ def __init__(
evenodd,
stroking_color,
non_stroking_color,
original_path,
dashing_style,
)


Expand All @@ -279,6 +294,8 @@ def __init__(
evenodd: bool = False,
stroking_color: Optional[Color] = None,
non_stroking_color: Optional[Color] = None,
original_path: Optional[List[PathSegment]] = None,
dashing_style: Optional[Tuple[object, object]] = None,
) -> None:
(x0, y0, x1, y1) = bbox
LTCurve.__init__(
Expand All @@ -290,6 +307,8 @@ def __init__(
evenodd,
stroking_color,
non_stroking_color,
original_path,
dashing_style,
)


Expand Down
39 changes: 39 additions & 0 deletions tests/test_converter.py
Original file line number Diff line number Diff line change
Expand Up @@ -216,6 +216,45 @@ def parse(path):
(71.41, 434.89),
]

def test_paint_path_beziers_check_raw(self):
"""See section 4.4, table 4.9 of the PDF reference manual"""

def parse(path):
analyzer = self._get_analyzer()
analyzer.cur_item = LTContainer([0, 1000, 0, 1000])
analyzer.paint_path(PDFGraphicState(), False, False, False, path)
return analyzer.cur_item._objs

# "c" operator
assert parse(
[
("m", 72.41, 433.89),
("c", 72.41, 434.45, 71.96, 434.89, 71.41, 434.89),
]
)[0].original_path == [
("m", (72.41, 433.89)),
("c", (72.41, 434.45), (71.96, 434.89), (71.41, 434.89)),
]

def test_paint_path_dashed(self):
"""See section 4.4, table 4.9 of the PDF reference manual"""

def parse(path):
analyzer = self._get_analyzer()
analyzer.cur_item = LTContainer([0, 1000, 0, 1000])
graphicstate = PDFGraphicState()
graphicstate.dash = ([1, 1], 0)
analyzer.paint_path(graphicstate, False, False, False, path)
return analyzer.cur_item._objs

# "c" operator
assert parse(
[
("m", 72.41, 433.89),
("c", 72.41, 434.45, 71.96, 434.89, 71.41, 434.89),
]
)[0].dashing_style == ([1, 1], 0)

def test_paint_path_without_starting_m(self):
gs = PDFGraphicState()
analyzer = self._get_analyzer()
Expand Down