Returns list of results from `Page.get_text()`, optionally using concurrency for speed. Args: path: Path of document. pages: List of page numbers to process, or None to include all pages. method: 'single' D
(
path,
*,
pages=None,
method='single',
concurrency=None,
option='text',
clip=None,
flags=None,
textpage=None,
sort=False,
delimiters=None,
_stats=False,
)
| 24776 | |
| 24777 | |
| 24778 | def get_text( |
| 24779 | path, |
| 24780 | *, |
| 24781 | pages=None, |
| 24782 | method='single', |
| 24783 | concurrency=None, |
| 24784 | |
| 24785 | option='text', |
| 24786 | clip=None, |
| 24787 | flags=None, |
| 24788 | textpage=None, |
| 24789 | sort=False, |
| 24790 | delimiters=None, |
| 24791 | |
| 24792 | _stats=False, |
| 24793 | ): |
| 24794 | ''' |
| 24795 | Returns list of results from `Page.get_text()`, optionally using |
| 24796 | concurrency for speed. |
| 24797 | |
| 24798 | Args: |
| 24799 | path: |
| 24800 | Path of document. |
| 24801 | pages: |
| 24802 | List of page numbers to process, or None to include all pages. |
| 24803 | method: |
| 24804 | 'single' |
| 24805 | Do not use concurrency. |
| 24806 | 'mp' |
| 24807 | Operate concurrently using Python's `multiprocessing` module. |
| 24808 | 'fork' |
| 24809 | Operate concurrently using custom implementation with |
| 24810 | `os.fork`. Does not work on Windows. |
| 24811 | concurrency: |
| 24812 | Number of worker processes to use when operating concurrently. If |
| 24813 | None, we use the number of available CPUs. |
| 24814 | option |
| 24815 | clip |
| 24816 | flags |
| 24817 | textpage |
| 24818 | sort |
| 24819 | delimiters: |
| 24820 | Passed to internal calls to `Page.get_text()`. |
| 24821 | ''' |
| 24822 | args_dict = dict( |
| 24823 | option=option, |
| 24824 | clip=clip, |
| 24825 | flags=flags, |
| 24826 | textpage=textpage, |
| 24827 | sort=sort, |
| 24828 | delimiters=delimiters, |
| 24829 | ) |
| 24830 | |
| 24831 | return apply_pages( |
| 24832 | path, |
| 24833 | Page.get_text, |
| 24834 | pagefn_kwargs=args_dict, |
| 24835 | pages=pages, |
nothing calls this directly
no test coverage detected
searching dependent graphs…