MCPcopy Create free account
hub / github.com/pymupdf/PyMuPDF / pdfocr_save

Method pdfocr_save

src/__init__.py:13696–13715  ·  view source on GitHub ↗

Save pixmap as an OCR-ed PDF page.

(self, filename, compress=1, language=None, tessdata=None)

Source from the content-addressed store, hash-verified

13694 return mupdf.fz_pixmap_components(self.this)
13695
13696 def pdfocr_save(self, filename, compress=1, language=None, tessdata=None):
13697 '''
13698 Save pixmap as an OCR-ed PDF page.
13699 '''
13700 tessdata = get_tessdata(tessdata)
13701 opts = mupdf.FzPdfocrOptions()
13702 opts.compress = compress
13703 if language:
13704 opts.language_set2( language)
13705 if tessdata:
13706 opts.datadir_set2( tessdata)
13707 pix = self.this
13708 if isinstance(filename, str):
13709 mupdf.fz_save_pixmap_as_pdfocr( pix, filename, 0, opts)
13710 else:
13711 out = JM_new_output_fileptr( filename)
13712 try:
13713 mupdf.fz_write_pixmap_as_pdfocr( out, pix, opts)
13714 finally:
13715 out.fz_close_output() # Avoid MuPDF warning.
13716
13717 def pdfocr_tobytes(self, compress=True, language="eng", tessdata=None):
13718 """Save pixmap as an OCR-ed PDF page.

Callers 1

pdfocr_tobytesMethod · 0.95

Calls 2

get_tessdataFunction · 0.85
JM_new_output_fileptrFunction · 0.85

Tested by

no test coverage detected