added newspaper bill

This commit is contained in:
Karl Voit 2020-03-04 16:24:49 +01:00
parent 644cdb9da4
commit 7ea74a2e8e
2 changed files with 14 additions and 2 deletions

View file

@ -1,6 +1,6 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
PROG_VERSION = u"Time-stamp: <2020-03-01 14:20:34 vk>" PROG_VERSION = u"Time-stamp: <2020-03-04 16:22:37 vk>"
# TODO: # TODO:
@ -171,6 +171,9 @@ class GuessFilename(object):
# 2019-12-04: "Die Presse (31.10.2019) - Unknown.pdf" -> "2019-10-31 Die Presse.pdf" # 2019-12-04: "Die Presse (31.10.2019) - Unknown.pdf" -> "2019-10-31 Die Presse.pdf"
NEWSPAPER1_REGEX = re.compile('(?P<description>.+) \((?P<day>\d{2})\.(?P<month>\d{2})\.(?P<year>\d{4})\)(?P<misc>.*)\.(?P<extension>pdf)', re.UNICODE) NEWSPAPER1_REGEX = re.compile('(?P<description>.+) \((?P<day>\d{2})\.(?P<month>\d{2})\.(?P<year>\d{4})\)(?P<misc>.*)\.(?P<extension>pdf)', re.UNICODE)
# 2020-03-04: "2020-03-04_DiePresse_Faktura-123456789.pdf" → "2020-03-04 Die Presse - Aborechnung Faktura-123456789 -- bill.pdf"
PRESSE_REGEX = re.compile(DATESTAMP_REGEX + '.+Presse.+Faktura-(?P<number>.+)\.pdf')
# OLD # # MediathekView: Settings > modify Set > Targetfilename: "%DT%d h%i %s %t - %T - %N.mp4" (limited to 120 characters) # OLD # # MediathekView: Settings > modify Set > Targetfilename: "%DT%d h%i %s %t - %T - %N.mp4" (limited to 120 characters)
# OLD # # results in files like: # OLD # # results in files like:
# OLD # # 20161227T201500 h115421 ORF Das Sacher. In bester Gesellschaft 1.mp4 # OLD # # 20161227T201500 h115421 ORF Das Sacher. In bester Gesellschaft 1.mp4
@ -670,6 +673,12 @@ class GuessFilename(object):
if regex_match: if regex_match:
return self.get_datetime_description_extension_filename(regex_match, replace_description_underscores=True) return self.get_datetime_description_extension_filename(regex_match, replace_description_underscores=True)
# 2020-03-04: "2020-03-04_DiePresse_Faktura-123456789.pdf" → "2020-03-04 Die Presse - Aborechnung Faktura-123456789 -- bill.pdf"
# PRESSE_REGEX = re.compile(DATESTAMP_REGEX + '.+Presse.+Faktura-(.+)\.pdf'
regex_match = re.match(self.PRESSE_REGEX, oldfilename)
if regex_match:
return self.get_date_string_from_named_groups(regex_match) + ' Die Presse - Aborechnung Faktura-' + regex_match.group('number') + " -- bill.pdf"
# FIXXME: more cases! # FIXXME: more cases!

View file

@ -1,6 +1,6 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
# -*- coding: utf-8; mode: python; -*- # -*- coding: utf-8; mode: python; -*-
# Time-stamp: <2020-03-01 14:14:56 vk> # Time-stamp: <2020-03-04 15:46:02 vk>
import unittest import unittest
import logging import logging
@ -981,6 +981,9 @@ class TestGuessFilename(unittest.TestCase):
self.assertEqual(self.guess_filename.derive_new_filename_from_old_filename('2017-11-05T10.56.11_IKS-00000000512345678901234567890.csv'), self.assertEqual(self.guess_filename.derive_new_filename_from_old_filename('2017-11-05T10.56.11_IKS-00000000512345678901234567890.csv'),
'2017-11-05T10.56.11 Bank Austria Umsatzliste IKS-00000000512345678901234567890.csv') '2017-11-05T10.56.11 Bank Austria Umsatzliste IKS-00000000512345678901234567890.csv')
# 2020-03-04: "2020-03-04_DiePresse_Faktura-123456789.pdf" → "2020-03-04 Die Presse - Aborechnung Faktura-123456789 -- bill.pdf"
self.assertEqual(self.guess_filename.derive_new_filename_from_old_filename('2020-03-04_DiePresse_Faktura-123456789.pdf'),
'2020-03-04 Die Presse - Aborechnung Faktura-123456789 -- bill.pdf')
# self.assertEqual(self.guess_filename.derive_new_filename_from_old_filename(''), # self.assertEqual(self.guess_filename.derive_new_filename_from_old_filename(''),
# '') # '')