def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> Dict[str, str]:
options = context.options
def from_document_info(key):
try:
s = base_pdf.docinfo[key]
return str(s)
except (KeyError, TypeError):
return ''
pdfmark = {
k: from_document_info(k)
for k in ('/Title', '/Author', '/Keywords', '/Subject',
'/CreationDate')
}
if options is not None:
if options.title:
pdfmark['/Title'] = options.title
if options.author:
pdfmark['/Author'] = options.author
if options.keywords:
pdfmark['/Keywords'] = options.keywords
if options.subject:
pdfmark['/Subject'] = options.subject
creator_tag = context.plugin_manager.hook.get_ocr_engine().creator_tag(
options)
pdfmark['/Creator'] = f'{PROGRAM_NAME} {VERSION} / {creator_tag}'
pdfmark['/Producer'] = f'pikepdf {pikepdf.__version__}'
pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
return pdfmark
def get_docinfo(base_pdf, options):
def from_document_info(key):
try:
s = base_pdf.docinfo[key]
return str(s)
except (KeyError, TypeError):
return ''
pdfmark = {
k: from_document_info(k)
for k in ('/Title', '/Author', '/Keywords', '/Subject', '/CreationDate')
}
renderer_tag = 'OCR'
if options is not None:
if options.title:
pdfmark['/Title'] = options.title
if options.author:
pdfmark['/Author'] = options.author
if options.keywords:
pdfmark['/Keywords'] = options.keywords
if options.subject:
pdfmark['/Subject'] = options.subject
if options.pdf_renderer == 'sandwich':
renderer_tag = 'OCR-PDF'
pdfmark['/Creator'] = (
f'{PROGRAM_NAME} {VERSION} / ' f'Tesseract {renderer_tag} {tesseract.version()}'
)
pdfmark['/Producer'] = f'pikepdf {pikepdf.__version__}'
if 'OCRMYPDF_CREATOR' in os.environ:
pdfmark['/Creator'] = os.environ['OCRMYPDF_CREATOR']
if 'OCRMYPDF_PRODUCER' in os.environ:
pdfmark['/Producer'] = os.environ['OCRMYPDF_PRODUCER']
pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
return pdfmark
def get_docinfo(base_pdf, options):
def from_document_info(key):
try:
s = base_pdf.docinfo[key]
return str(s)
except (KeyError, TypeError):
return ''
pdfmark = {
k: from_document_info(k)
for k in ('/Title', '/Author', '/Keywords', '/Subject', '/CreationDate')
}
if options.title:
pdfmark['/Title'] = options.title
if options.author:
pdfmark['/Author'] = options.author
if options.keywords:
pdfmark['/Keywords'] = options.keywords
if options.subject:
pdfmark['/Subject'] = options.subject
if options.pdf_renderer == 'sandwich':
renderer_tag = 'OCR-PDF'
else:
renderer_tag = 'OCR'
pdfmark['/Creator'] = (
f'{PROGRAM_NAME} {VERSION} / ' f'Tesseract {renderer_tag} {tesseract.version()}'
)
pdfmark['/Producer'] = f'pikepdf {pikepdf.__version__}'
if 'OCRMYPDF_CREATOR' in os.environ:
pdfmark['/Creator'] = os.environ['OCRMYPDF_CREATOR']
if 'OCRMYPDF_PRODUCER' in os.environ:
pdfmark['/Producer'] = os.environ['OCRMYPDF_PRODUCER']
pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
return pdfmark
def get_docinfo(base_pdf, options):
def from_document_info(key):
try:
s = base_pdf.docinfo[key]
return str(s)
except (KeyError, TypeError):
return ''
pdfmark = {k: from_document_info(k) for k in
('/Title', '/Author', '/Keywords', '/Subject', '/CreationDate')}
if options.title:
pdfmark['/Title'] = options.title
if options.author:
pdfmark['/Author'] = options.author
if options.keywords:
pdfmark['/Keywords'] = options.keywords
if options.subject:
pdfmark['/Subject'] = options.subject
if options.pdf_renderer == 'sandwich':
renderer_tag = 'OCR-PDF'
else:
renderer_tag = 'OCR'
pdfmark['/Creator'] = '{0} {1} / Tesseract {2} {3}'.format(
PROGRAM_NAME, VERSION,
renderer_tag,
tesseract.version())
pdfmark['/Producer'] = 'pikepdf ' + pikepdf.__version__
if 'OCRMYPDF_CREATOR' in os.environ:
pdfmark['/Creator'] = os.environ['OCRMYPDF_CREATOR']
if 'OCRMYPDF_PRODUCER' in os.environ:
pdfmark['/Producer'] = os.environ['OCRMYPDF_PRODUCER']
pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
return pdfmark
