Ensure page break after line 29 and preserve all transcript text
Mirror and run GitLab CI / build (push) Waiting to run
Ruff / ruff (push) Waiting to run

- Insert page break after every 29 visual lines.
- Wrap long lines instead of truncating to preserve all words.
- No text is dropped; content wraps onto new lines as needed.
This commit is contained in:
admin
2026-06-19 15:25:49 +00:00
parent 327c05ea16
commit 2c0998579c
+36 -8
View File
@@ -528,29 +528,57 @@ def create_transcript_docx(text: str, filename: str):
content_lines.append(current)
# First visual line: include label if present, ensuring total <= max_chars
# If too long, split into multiple lines instead of dropping text.
if content_lines:
ensure_new_page_if_needed()
first_content = content_lines.pop(0)
if label_text:
prefix = label_text + " "
# If too long, trim first_content at word boundary
# If prefix + first_content is too long, wrap first_content
if len(prefix) + len(first_content) > max_chars:
allowed = max_chars - len(prefix)
if allowed < 1:
allowed = 1
# Truncate at word boundary
candidate = first_content[:allowed]
last_space = candidate.rfind(" ")
if last_space > 0:
candidate = candidate[:last_space]
first_content = candidate
first_line_text = prefix + first_content
kept = candidate[:last_space]
rest = first_content[last_space:].strip()
else: # no space found; break mid-word to preserve everything
kept = candidate
rest = first_content[allowed:].strip()
first_line_text = prefix + kept
line_number += 1
_add_transcript_paragraph(doc, first_line_text, line_number=line_number)
# Prepend any remaining text as continuation lines
if rest:
# Re-wrap the rest into content_lines
extra_words = rest.split()
new_lines = []
buf = ""
for ew in extra_words:
if len(buf) == 0:
buf = ew
elif len(buf) + 1 + len(ew) <= max_chars:
buf += " " + ew
else:
new_lines.append(buf)
buf = ew
if buf:
new_lines.append(buf)
# Insert these before existing content_lines
content_lines = new_lines + content_lines
else:
first_line_text = prefix + first_content
line_number += 1
_add_transcript_paragraph(doc, first_line_text, line_number=line_number)
else:
first_line_text = first_content
line_number += 1
_add_transcript_paragraph(doc, first_line_text, line_number=line_number)
line_number += 1
_add_transcript_paragraph(doc, first_line_text, line_number=line_number)
# Subsequent visual lines: no label, just content
for cl in content_lines: