From 11b26a913d39edb7f36cd0a3b3d8e74c96738579 Mon Sep 17 00:00:00 2001 From: Matthias Baumgartner Date: Fri, 28 Jul 2023 11:31:24 +0200 Subject: document digestion: * plaintext reader * text metrics extractor * text summary extractor --- bsie/reader/document/_plain.py | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 bsie/reader/document/_plain.py (limited to 'bsie/reader/document/_plain.py') diff --git a/bsie/reader/document/_plain.py b/bsie/reader/document/_plain.py new file mode 100644 index 0000000..a589265 --- /dev/null +++ b/bsie/reader/document/_plain.py @@ -0,0 +1,38 @@ + +# standard imports +import typing + +# bsie imports +from bsie.utils import errors, filematcher + +# inner-module imports +from .. import base + +# constants +MATCH_RULE = 'mime=text/plain' + +# exports +__all__: typing.Sequence[str] = ( + 'Plain', + ) + + +## code ## + +class Plain(base.Reader): + + _match: filematcher.Matcher + + def __init__(self): + self._match = filematcher.parse(MATCH_RULE) + + def __call__(self, path: str) -> typing.Sequence[str]: + # perform quick checks first + if not self._match(path): + raise errors.UnsupportedFileFormatError(path) + + # open file in text mode + with open(path, 'rt') as ifile: + return [line.strip() for line in ifile.read().split('\n') if len(line.strip()) > 0] + +## EOF ## -- cgit v1.2.3