document-ocr / ocr_studio /export_text.py
alirezaaminzadeh's picture
Expand document OCR with PDF support, bilingual UI, and extra exports
98e1d9f verified
Raw
History Blame Contribute Delete
854 Bytes
from __future__ import annotations
from pathlib import Path
from ocr_studio.config import PAGE_BREAK
PAGE_SEPARATOR = PAGE_BREAK
def write_text_file(text: str, destination: Path) -> Path:
destination.write_text(text or "", encoding="utf-8-sig")
return destination
def split_pages(text: str, expected: int) -> list[str]:
if expected <= 1:
return [text or ""]
if PAGE_SEPARATOR in (text or ""):
parts = (text or "").split(PAGE_SEPARATOR)
else:
parts = [text or ""]
if len(parts) == expected:
return parts
if len(parts) > expected:
head = parts[: expected - 1]
tail = PAGE_SEPARATOR.join(parts[expected - 1 :])
return head + [tail]
padded = list(parts)
while len(padded) < expected:
padded.append("")
return padded