(page, space_guess)
| 107 | print(f'Have written to: {out}') |
| 108 | |
| 109 | def get_text(page, space_guess): |
| 110 | buffer_ = pymupdf.mupdf.FzBuffer( 10) |
| 111 | out = pymupdf.mupdf.FzOutput( buffer_) |
| 112 | writer = pymupdf.mupdf.FzDocumentWriter( |
| 113 | out, |
| 114 | f'text,space-guess={space_guess}', |
| 115 | pymupdf.mupdf.FzDocumentWriter.OutputType_DOCX, |
| 116 | ) |
| 117 | device = pymupdf.mupdf.fz_begin_page(writer, pymupdf.mupdf.fz_bound_page(page)) |
| 118 | pymupdf.mupdf.fz_run_page(page, device, pymupdf.mupdf.FzMatrix(), pymupdf.mupdf.FzCookie()) |
| 119 | pymupdf.mupdf.fz_end_page(writer) |
| 120 | pymupdf.mupdf.fz_close_document_writer(writer) |
| 121 | text = buffer_.fz_buffer_extract() |
| 122 | text = text.decode('utf8') |
| 123 | n = text.count(' ') |
| 124 | print(f'{space_guess=}: {n=}') |
| 125 | return text, n |
| 126 | page = document[4] |
| 127 | text0, n0 = get_text(page, 0) |
| 128 | text1, n1 = get_text(page, 0.5) |
no outgoing calls
no test coverage detected
searching dependent graphs…