fergalmoran/picard
1
0
Fork 0
mirror of https://github.com/fergalmoran/picard.git synced 2025-12-25 19:04:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

PICARD-2236: Fullwidth slash is treated as directory separator

Browse Source 
A full width slash U+FF0F, e.g. in イニシエノウタ／デボル, in combination with replace non-ascii gets turned into an ASCII slash, leading to a directory being created.
This commit is contained in:
Philipp Wolfer
2021-06-24 17:28:11 +02:00
parent 2422d74cb3
commit d509dd83a0
2 changed files with 25 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
test/test_textencoding.py
View File

@@ -6,7 +6,7 @@
# Copyright (C) 2015, 2018, 2020 Laurent Monin
# Copyright (C) 2017 Ville Skyttä
# Copyright (C) 2018 Wieland Hoffmann
# Copyright (C) 2018-2019 Philipp Wolfer
# Copyright (C) 2018-2019, 2021 Philipp Wolfer
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
@@ -138,6 +138,9 @@ class CompatibilityTest(PicardTestCase):
self.assertEqual(util.textencoding.unicode_simplify_compatibility(combinations_from), combinations_from)
self.assertEqual(util.textencoding.unicode_simplify_compatibility(ascii_chars), ascii_chars)
def test_pathsave(self):
self.assertEqual(util.textencoding.unicode_simplify_compatibility('\uff0f', pathsave=True), '_')
def test_incorrect(self):
pass
@@ -225,13 +228,14 @@ class ReplaceNonAsciiTest(PicardTestCase):
self.assertEqual(util.textencoding.replace_non_ascii("⑴⑵⑶"), "(1)(2)(3)") # Parenthesised numbers
self.assertEqual(util.textencoding.replace_non_ascii("⒈ ⒉ ⒊"), "1. 2. 3.") # Digit full stop
self.assertEqual(util.textencoding.replace_non_ascii("１２３"), "123") # Fullwidth digits
self.assertEqual(util.textencoding.replace_non_ascii("\u2216\u2044\u2215\uff0f"), "\\///") # Slashes
def test_pathsave(self):
expected = '__/8 1_2\\' if IS_WIN else '\\_/8 1_2\\'
self.assertEqual(util.textencoding.replace_non_ascii('\u2216\u2044/8½\\', pathsave=True), expected)
expected = '____/8 1_2\\' if IS_WIN else '\\___/8 1_2\\'
self.assertEqual(util.textencoding.replace_non_ascii('\u2216\u2044\u2215\uff0f/8½\\', pathsave=True), expected)
def test_win_compat(self):
self.assertEqual(util.textencoding.replace_non_ascii('\u2216\u2044/8½\\', pathsave=True, win_compat=True), '__/8 1_2\\')
self.assertEqual(util.textencoding.replace_non_ascii('\u2216\u2044\u2215\uff0f/8½\\', pathsave=True, win_compat=True), '____/8 1_2\\')
def test_incorrect(self):
self.assertNotEqual(util.textencoding.replace_non_ascii("Lukáš"), "Lukáš")