mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-11-21 04:52:40 +00:00
Chore: render zone OCR pages through the shared pdftoppm helper
pdftoppm was called in three places with different options. Missing-binary handling is dropped since pdftoppm and tesseract are required at startup.
This commit is contained in:
1 parent
c1bb327f1f
commit
409539d4d1
7 files changed
+217
-176
No files matched your search
+10
-29
@@ -37,6 +37,8 @@ from documents.models import CustomFieldInstance
|
||||
from documents.models import Document
|
||||
from documents.models import OcrTemplate
|
||||
from documents.models import OcrTemplateZone
|
||||
from documents.parsers import ParseError
|
||||
from documents.parsers import rasterize_pdf_page_to_png
|
||||
from documents.permissions import permitted_object_ids
|
||||
from documents.regex import safe_regex_fullmatch
|
||||
from documents.signals.handlers import add_to_index
|
||||
@@ -400,41 +402,23 @@ def _render_pages(
|
||||
if actual_page < 0 or (page_count and actual_page >= page_count):
|
||||
continue
|
||||
|
||||
output_prefix = tmp_dir / f"page_{actual_page}"
|
||||
rendered = tmp_dir / f"page_{actual_page}.png"
|
||||
try:
|
||||
subprocess.run(
|
||||
[
|
||||
"pdftoppm",
|
||||
"-png",
|
||||
"-singlefile",
|
||||
"-r",
|
||||
"300",
|
||||
"-f",
|
||||
str(actual_page + 1), # pdftoppm is 1-indexed
|
||||
"-l",
|
||||
str(actual_page + 1),
|
||||
str(doc_path),
|
||||
str(output_prefix),
|
||||
],
|
||||
check=True,
|
||||
capture_output=True,
|
||||
rasterize_pdf_page_to_png(
|
||||
doc_path,
|
||||
rendered,
|
||||
dpi=300,
|
||||
page=actual_page + 1, # pdftoppm is 1-indexed
|
||||
timeout=60,
|
||||
)
|
||||
except subprocess.TimeoutExpired:
|
||||
logger.error("Zone OCR: pdftoppm timed out for page %d", actual_page)
|
||||
continue
|
||||
except subprocess.CalledProcessError as e:
|
||||
except ParseError as e:
|
||||
logger.exception(
|
||||
"Zone OCR: pdftoppm failed for page %d: %s",
|
||||
actual_page,
|
||||
e.stderr.decode(errors="replace") if e.stderr else str(e),
|
||||
e,
|
||||
)
|
||||
continue
|
||||
except FileNotFoundError:
|
||||
logger.error("Zone OCR: pdftoppm not found")
|
||||
return result
|
||||
|
||||
rendered = output_prefix.with_suffix(".png")
|
||||
if rendered.is_file():
|
||||
result[actual_page] = rendered
|
||||
|
||||
@@ -520,9 +504,6 @@ def _ocr_text(cropped: Image.Image, zone: OcrTemplateZone, tmp_dir: Path) -> str
|
||||
e.stderr[:200] if e.stderr else str(e),
|
||||
)
|
||||
return None
|
||||
except FileNotFoundError:
|
||||
logger.error("Zone OCR: Tesseract not found")
|
||||
return None
|
||||
|
||||
|
||||
def _extract_zone(
|
||||
|
||||
Reference in new issue
Block a user