Skip to content
This repository was archived by the owner on Apr 11, 2025. It is now read-only.

Fixes: IndexError while using split_text #21

Merged
merged 2 commits into from
Aug 12, 2024
Merged

Fixes: IndexError while using split_text #21

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
601612f
Fixed IndexError when split_text is True and table has empty rows or …
snanda85 Jun 26, 2024
e519e5e
Added tests for split_text in lattice
snanda85 Jun 27, 2024
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
9 changes: 7 additions & 2 deletions camelot/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -592,6 +592,9 @@ def split_textline(table, textline, direction, flag_size=False, strip_text=""):
cut_text = []
bbox = textline.bbox
try:
if textline.is_empty():
return [(-1, -1, textline.get_text())]

if direction == "horizontal" and not textline.is_empty():
x_overlap = [
i
Expand Down Expand Up @@ -622,7 +625,8 @@ def split_textline(table, textline, direction, flag_size=False, strip_text=""):
else:
# TODO: add test
if cut == x_cuts[-1]:
cut_text.append((r, cut[0] + 1, obj))
new_idx = min(cut[0] + 1, len(table.cols) - 1)
cut_text.append((r, new_idx, obj))
elif isinstance(obj, LTAnno):
cut_text.append((r, cut[0], obj))
elif direction == "vertical" and not textline.is_empty():
Expand Down Expand Up @@ -655,7 +659,8 @@ def split_textline(table, textline, direction, flag_size=False, strip_text=""):
else:
# TODO: add test
if cut == y_cuts[-1]:
cut_text.append((cut[0] - 1, c, obj))
new_idx = max(cut[0] - 1, 0)
cut_text.append((new_idx, c, obj))
elif isinstance(obj, LTAnno):
cut_text.append((cut[0], c, obj))
except IndexError:
Expand Down
Loading