def __handle_lt_figure(self, element: LTFigure):
"""
sometimes pieces of text are wrongly detected as LTFigure, e.g. in slide-sets with border lines.
-> extract text from LTFigure line by line put them into a LTTextBoxHorizontal as a workaround
@return: LTTextBoxHorizontal containing found texts line by line
"""
# check if text is hold within figure element, forward
line = LTTextLineHorizontal(0)
wrapper = LTTextBoxHorizontal()
wrapper.add(line)
y_prior = element._objs[0].y0
for letter in element:
if isinstance(letter, LTChar):
if abs(letter.y0 - y_prior) > 0.05:
# new line, yield wrapper
wrapper.analyze(self.la_params)
yield wrapper
wrapper = LTTextBoxHorizontal()
line = LTTextLineHorizontal(0)
wrapper.add(line)
y_prior = letter.y0
line.add(letter)
def create_container(self, text):
box = LTTextBoxHorizontal()
line = LTTextLineHorizontal(0)
for c in text:
line.add(self.create_char(c))
box.add(line)
return box
def test_bad_investor_info(self):
from casparser.extract.pdfminer import parse_investor_info
with pytest.raises(CASParseError) as exc_info:
box = LTTextBoxHorizontal()
box.get_text()
parse_investor_info([], 0, 0)
assert "Unable to parse investor data" in str(exc_info)
def split_boxes_by_style(
self, container: LTTextContainer
) -> Generator[LTTextContainer, LTTextContainer, None]:
"""
pdfminers paragraphs are sometimes too broad and contain lines that should be splitted into header and content
@param container: the extracted original paragraph
"""
line: LTTextLineHorizontal
wrapper = LTTextBoxHorizontal()
wrapper.page = container.page
stack = []
for line in container:
size = max([
obj.size for obj in itertools.islice(line, 10)
if isinstance(obj, LTChar)
])
if not stack:
wrapper.add(line)
stack.append(size)
else:
prior = stack.pop()
stack.append(size)
diff = abs(prior - size)
if diff != 0 and max(prior, size) / min(prior, size) > 1.15:
# break paragraph
yield wrapper
wrapper = LTTextBoxHorizontal()
wrapper.add(line)
yield wrapper
def group_textlines(self, laparams, lines):
"""Patched class method that fixes empty line aggregation, and allows
run-time line margin detection"""
plane = Plane(self.bbox)
plane.extend(lines)
boxes = {}
for line in lines:
neighbors = line.find_neighbors(plane, laparams.line_margin)
if line not in neighbors or not line.get_text().strip():
continue
# Correct margin to paragraph specific
true_margin = laparams.line_margin
for obj1 in neighbors:
if obj1 is line:
continue
margin = min(abs(obj1.y0 - line.y1), abs(obj1.y1 - line.y0))
margin = margin * 1.05 / line.height
if margin < true_margin:
true_margin = margin
neighbors = line.find_neighbors(plane, true_margin)
if line not in neighbors:
continue
members = []
for obj1 in neighbors:
if not obj1.get_text().strip():
continue
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:
if line not in boxes:
continue
box = boxes[line]
if box in done:
continue
done.add(box)
if not box.is_empty():
yield box
return
def group_textlines(self, laparams: LAParams,
lines: List[LTTextContainer]) -> Generator:
plane = Plane(self.bbox)
plane.extend(lines)
boxes: Dict[LTText, LTTextBox] = {}
for line in lines:
if isinstance(line, LTTextLineHorizontalExtended):
box = LTTextBoxHorizontal()
if self.rsrcmgr:
klass = line.maybe_classify(self.rsrcmgr)
if klass == LTTitle:
self.rsrcmgr.after_title = True
elif not self.rsrcmgr.after_abstract and klass == LTSectionHeader:
self.rsrcmgr.after_abstract = True
elif klass == LTSectionHeader and 'references' in line.get_text(
).lower():
self.rsrcmgr.after_ref = True
box = klass()
else:
box = LTTextBoxVertical()
if not isinstance(box, LTTitle) and not isinstance(
box, LTSectionHeader):
neighbors = line.find_neighbors_with_rsrcmgr(
plane, laparams.line_margin, self.rsrcmgr)
if line not in neighbors:
continue
else:
neighbors = [line]
members = []
for obj1 in neighbors:
members.append(obj1)
if obj1 in boxes:
members.extend(boxes.pop(obj1))
for obj in uniq(members):
box.add(obj)
boxes[obj] = box
done: Set[LTTextBox] = set()
for line in lines:
if line not in boxes:
continue
box = boxes[line]
if box in done:
continue
done.add(box)
if not box.is_empty():
yield box
return