Skip to content

Port opt break test and change #184

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.

Sign up for GitHub

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

Merged
merged 2 commits into from
May 29, 2025
Merged

Port opt break test and change #184

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
be98043
Port opt break test and change
Enkidu93 May 27, 2025
408641d
Add paragraph marker back into test
Enkidu93 May 28, 2025
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
2 changes: 2 additions & 0 deletions machine/corpora/usfm_text_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,6 +178,8 @@ def end_note(self, state: UsfmParserState, marker: str, closed: bool) -> None:

def opt_break(self, state: UsfmParserState) -> None:
super().opt_break(state)
if len(self._row_texts_stack) == 0:
return
if self._text._include_markers:
self._row_texts_stack[-1] += "//"
elif self._current_text_type != ScriptureTextType.VERSE or state.is_verse_text:
Expand Down
16 changes: 16 additions & 0 deletions tests/corpora/test_usfm_memory_text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,6 +136,22 @@ def test_get_rows_verse_para_comment_first() -> None:
assert len(rows) == 2, str.join(",", [tr.text for tr in rows])


def test_get_rows_opt_break_outside_of_segment() -> None:
rows: List[TextRow] = get_rows(
r"""\id MAT - Test
\c 1
//
\p
\v 1 This is the first verse.
""",
include_all_text=True,
include_markers=True,
)
assert len(rows) == 2, str.join(",", [tr.text for tr in rows])
assert rows[0].text == ""
assert rows[1].text == "This is the first verse."


def get_rows(usfm: str, include_markers: bool = False, include_all_text: bool = False) -> List[TextRow]:
text = UsfmMemoryText(
UsfmStylesheet("usfm.sty"),
Expand Down