menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Allow title, subject, author, and keywords to be unset with an empty string argument (#1117)

Browse Source 
Co-authored-by: Frederick D. Hansen <frederick.hansen@gmail.com>
This commit is contained in:
f-hansen
2023-06-20 01:07:23 -07:00
committed by GitHub
co-authored by Frederick D. Hansen
parent e44a57aec0
commit 050dd1f5a8
3 changed files with 187 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ocrmypdf/_pipeline.py
+28 -9
View File
@@ -852,24 +852,43 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
with pikepdf.open(context.origin) as original, pikepdf.open(working_file) as pdf:
docinfo = get_docinfo(original, context)
with pdf.open_metadata() as meta:
meta.load_from_docinfo(docinfo, delete_missing=False, raise_failure=False)
with pdf.open_metadata() as meta_pdf:
meta_pdf.load_from_docinfo(docinfo, delete_missing=False, raise_failure=False)
# If xmp:CreateDate is missing, set it to the modify date to
# match Ghostscript, for consistency
if 'xmp:CreateDate' not in meta:
meta['xmp:CreateDate'] = meta.get('xmp:ModifyDate', '')
# ensure consistency with Ghostscript.
if 'xmp:CreateDate' not in meta_pdf:
meta_pdf['xmp:CreateDate'] = meta_pdf.get('xmp:ModifyDate', '')
with original.open_metadata(
set_pikepdf_as_editor=False, update_docinfo=False, strict=False
) as meta_original:
if meta.get('dc:title') == 'Untitled':
if meta_pdf.get('dc:title') == 'Untitled':
# Ghostscript likes to set title to Untitled if omitted from input.
# Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
# and the XMP Spec do not make this recommendation.
if 'dc:title' not in meta_original:
del meta['dc:title']
missing = set(meta_original.keys()) - set(meta.keys())
report_on_metadata(missing)
del meta_pdf['dc:title']
# If the user explicitly specified an empty string for any of the
# following, they should be unset and not reported as missing in
# the output pdf. Note that some metadata fields use differing names
# between PDF-A and PDF.
for meta in [meta_pdf, meta_original]:
if options.title == '' and 'dc:title' in meta:
del meta['dc:title'] # PDF-A and PDF
if options.author == '':
if 'dc:creator' in meta:
del meta['dc:creator'] # PDF-A (Not xmp:CreatorTool)
if 'pdf:Author' in meta:
del meta['pdf:Author'] # PDF
if options.subject == '':
if 'dc:description' in meta:
del meta['dc:description'] # PDF-A
if 'dc:subject' in meta:
del meta['dc:subject'] # PDF
if options.keywords == '' and 'pdf:Keywords' in meta:
del meta['pdf:Keywords'] # PDF-A and PDF
meta_missing = set(meta_original.keys()) - set(meta_pdf.keys())
report_on_metadata(meta_missing)
optimizing = context.plugin_manager.hook.is_optimization_enabled(
context=context