paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

new setting: PAPERLESS_OCR_PAGES

Browse Source
This commit is contained in:
Jonas Winkler
2020-11-22 12:54:08 +01:00
parent 0e301e4563
commit ae198f0767
6 changed files with 54 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/paperless/settings.py
View File

@@ -322,6 +322,8 @@ CONSUMER_DELETE_DUPLICATES = __get_boolean("PAPERLESS_CONSUMER_DELETE_DUPLICATES
OPTIMIZE_THUMBNAILS = __get_boolean("PAPERLESS_OPTIMIZE_THUMBNAILS", "true")
OCR_PAGES = int(os.getenv('PAPERLESS_OCR_PAGES', 0))
# The default language that tesseract will attempt to use when parsing
# documents. It should be a 3-letter language code consistent with ISO 639.
OCR_LANGUAGE = os.getenv("PAPERLESS_OCR_LANGUAGE", "eng")

17
src/paperless_tesseract/parsers.py
View File

@@ -147,18 +147,25 @@ class RasterisedDocumentParser(DocumentParser):
Greyscale images are easier for Tesseract to OCR
"""
# Convert PDF to multiple PNMs
input_file = self.document_path
if settings.OCR_PAGES == 1:
input_file += "[0]"
elif settings.OCR_PAGES > 1:
input_file += f"[0-{settings.OCR_PAGES - 1}]"
self.log(
"debug",
f"Converting document {self.document_path} into greyscale images")
f"Converting document {input_file} into greyscale images")
# Convert PDF to multiple PNMs
pnm = os.path.join(self.tempdir, "convert-%04d.pnm")
output_files = os.path.join(self.tempdir, "convert-%04d.pnm")
run_convert(density=settings.CONVERT_DENSITY,
depth="8",
type="grayscale",
input_file=self.document_path,
output_file=pnm,
input_file=input_file,
output_file=output_files,
logging_group=self.logging_group)
# Get a list of converted images