diff options
author | hut <hut@lavabit.com> | 2010-05-17 20:12:35 +0200 |
---|---|---|
committer | hut <hut@lavabit.com> | 2010-05-17 20:12:35 +0200 |
commit | c184e88b5caa66e1cda90019e6e74e0036a24959 (patch) | |
tree | 58cdbaee5a54f9a039396faf9789d242afd47ec8 | |
parent | ce421875249b2ce9c6eacbade9b750e46ae80a20 (diff) | |
parent | d213c6b6eb252df03e4fbbe97e7e71876da8c309 (diff) | |
download | ranger-c184e88b5caa66e1cda90019e6e74e0036a24959.tar.gz |
Merge branch 'utf'
Conflicts: ranger/__main__.py
-rw-r--r-- | ranger/__main__.py | 15 | ||||
-rw-r--r-- | ranger/ext/utfwidth.py | 109 | ||||
-rw-r--r-- | ranger/gui/bar.py | 4 | ||||
-rw-r--r-- | ranger/gui/widgets/console.py | 35 | ||||
-rw-r--r-- | test/tc_utfwidth.py | 42 |
5 files changed, 180 insertions, 25 deletions
diff --git a/ranger/__main__.py b/ranger/__main__.py index 916c5a0e..9317d428 100644 --- a/ranger/__main__.py +++ b/ranger/__main__.py @@ -147,7 +147,7 @@ def main(): print(errormessage) print('ranger requires the python curses module. Aborting.') sys.exit(1) - from locale import getdefaultlocale, setlocale, LC_ALL + import locale import ranger from ranger.ext import curses_interrupt_handler from ranger.core.runner import Runner @@ -158,17 +158,8 @@ def main(): from ranger.shared import (EnvironmentAware, FileManagerAware, SettingsAware) - # Ensure that a utf8 locale is set. - try: - if getdefaultlocale()[1] not in ('utf8', 'UTF-8'): - for locale in ('en_US.utf8', 'en_US.UTF-8'): - try: setlocale(LC_ALL, locale) - except: pass - else: break - else: setlocale(LC_ALL, '') - else: setlocale(LC_ALL, '') - except: - print("Warning: Unable to set locale. Expect encoding problems.") + try: locale.setlocale(locale.LC_ALL, '') + except: print("Warning: Unable to set locale. Expect encoding problems.") arg = parse_arguments() ranger.arg = arg diff --git a/ranger/ext/utfwidth.py b/ranger/ext/utfwidth.py new file mode 100644 index 00000000..a506c676 --- /dev/null +++ b/ranger/ext/utfwidth.py @@ -0,0 +1,109 @@ +# -*- encoding: utf8 -*- +# Copyright (C) 2009, 2010 Roman Zimbelmann <romanz@lavabit.com> +# Copyright (C) 2004, 2005 Timo Hirvonen +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# +# ---- +# This file contains portions of code from cmus (uchar.c). + +NARROW = 1 +WIDE = 2 + +def uwid(string): + """Return the width of a string""" + end = len(string) + i = 0 + width = 0 + while i < end: + bytelen = utf_byte_length(string[i:]) + width += utf_char_width(string[i:i+bytelen]) + i += bytelen + return width + +def uchars(string): + """Return a list with one string for each character""" + end = len(string) + i = 0 + result = [] + while i < end: + bytelen = utf_byte_length(string[i:]) + result.append(string[i:i+bytelen]) + i += bytelen + return result + +def utf_byte_length(string): + """Return the byte length of one utf character""" + firstord = ord(string[0]) + if firstord < 0b01111111: + return 1 + if firstord < 0b10111111: + return 1 # invalid + if firstord < 0b11011111: + return 2 + if firstord < 0b11101111: + return 3 + if firstord < 0b11110100: + return 4 + return 1 # invalid + +def utf_char_width(string): + """Return the width of a single character""" + u = _utf_char_to_int(string) + if u < 0x1100: + return NARROW + # Hangul Jamo init. constonants + if u <= 0x115F: + return WIDE + # Angle Brackets + if u == 0x2329 or u == 0x232A: + return WIDE + if u < 0x2e80: + return NARROW + # CJK ... Yi + if u < 0x302A: + return WIDE + if u <= 0x302F: + return NARROW + if u == 0x303F or u == 0x3099 or u == 0x309a: + return NARROW + # CJK ... Yi + if u <= 0xA4CF: + return WIDE + # Hangul Syllables + if u >= 0xAC00 and u <= 0xD7A3: + return WIDE + # CJK Compatibility Ideographs + if u >= 0xF900 and u <= 0xFAFF: + return WIDE + # CJK Compatibility Forms + if u >= 0xFE30 and u <= 0xFE6F: + return WIDE + # Fullwidth Forms + if u >= 0xFF00 and u <= 0xFF60 or u >= 0xFFE0 and u <= 0xFFE6: + return WIDE + # CJK Extra Stuff + if u >= 0x20000 and u <= 0x2FFFD: + return WIDE + # ? + if u >= 0x30000 and u <= 0x3FFFD: + return WIDE + return NARROW # invalid (?) + +def _utf_char_to_int(string): + # Squash the last 6 bits of each byte together to an integer + u = 0 + for c in string: + u = (u << 6) | (ord(c) & 0b00111111) + return u diff --git a/ranger/gui/bar.py b/ranger/gui/bar.py index f5e34eb1..03ed2f78 100644 --- a/ranger/gui/bar.py +++ b/ranger/gui/bar.py @@ -13,6 +13,8 @@ # You should have received a copy of the GNU General Public License # along with this program. If not, see <http://www.gnu.org/licenses/>. +from ranger.ext.utfwidth import uwid + class Bar(object): left = None right = None @@ -132,7 +134,7 @@ class ColoredString(object): self.string = self.string[:n] def __len__(self): - return len(self.string) + return uwid(self.string) def __str__(self): return self.string diff --git a/ranger/gui/widgets/console.py b/ranger/gui/widgets/console.py index fa9e438e..3bb41482 100644 --- a/ranger/gui/widgets/console.py +++ b/ranger/gui/widgets/console.py @@ -27,9 +27,11 @@ from ranger.gui.widgets.console_mode import is_valid_mode, mode_to_class from ranger import log, relpath_conf from ranger.core.runner import ALLOWED_FLAGS from ranger.ext.shell_escape import shell_quote +from ranger.ext.utfwidth import uwid from ranger.container.keymap import CommandArgs from ranger.ext.get_executables import get_executables from ranger.ext.direction import Direction +from ranger.ext.utfwidth import uwid, uchars from ranger.container import History from ranger.container.history import HistoryEmptyException import ranger @@ -97,16 +99,17 @@ class Console(Widget): self.win.erase() self.addstr(0, 0, self.prompt) - overflow = -self.wid + len(self.prompt) + len(self.line) + 1 + overflow = -self.wid + len(self.prompt) + uwid(self.line) + 1 if overflow > 0: + #XXX: cut uft-char-wise, consider width self.addstr(self.line[overflow:]) else: self.addstr(self.line) def finalize(self): try: - self.fm.ui.win.move(self.y, - self.x + min(self.wid-1, self.pos + len(self.prompt))) + xpos = uwid(self.line[0:self.pos]) + len(self.prompt) + self.fm.ui.win.move(self.y, self.x + min(self.wid-1, xpos)) except: pass @@ -221,11 +224,15 @@ class Console(Widget): def move(self, **keywords): direction = Direction(keywords) if direction.horizontal(): - self.pos = direction.move( + # Ensure that the pointer is moved utf-char-wise + uc = uchars(self.line) + upos = len(uchars(self.line[:self.pos])) + newupos = direction.move( direction=direction.right(), minimum=0, - maximum=len(self.line) + 1, - current=self.pos) + maximum=len(uc) + 1, + current=upos) + self.pos = len(''.join(uc[:newupos])) def delete_rest(self, direction): self.tab_deque = None @@ -259,12 +266,16 @@ class Console(Widget): def delete(self, mod): self.tab_deque = None - if mod == -1 and len(self.line) == 0: - self.close() - pos = self.pos + mod - - self.line = self.line[0:pos] + self.line[pos+1:] - self.move(right=mod) + if mod == -1 and self.pos == 0: + if not self.line: + self.close() + return + # Delete utf-char-wise + uc = uchars(self.line) + upos = len(uchars(self.line[:self.pos])) + mod + left_part = ''.join(uc[:upos]) + self.pos = len(left_part) + self.line = left_part + ''.join(uc[upos+1:]) self.on_line_change() def execute(self): diff --git a/test/tc_utfwidth.py b/test/tc_utfwidth.py new file mode 100644 index 00000000..d8ffbe1d --- /dev/null +++ b/test/tc_utfwidth.py @@ -0,0 +1,42 @@ +# -*- encoding: utf8 -*- +# Copyright (C) 2009, 2010 Roman Zimbelmann <romanz@lavabit.com> +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +if __name__ == '__main__': from __init__ import init; init() + +from unittest import TestCase, main +from ranger.ext.utfwidth import * + +a_ascii = "a" # width = 1, bytes = 1 +a_umlaut = "ä" # width = 1, bytes = 2 +a_katakana = "ア" # width = 2, bytes = 3 +# need one with width = 1 & bytes = 3 + +class Test(TestCase): + def test_utf_byte_length(self): + self.assertEqual(1, utf_byte_length(a_ascii)) + self.assertEqual(2, utf_byte_length(a_umlaut)) + self.assertEqual(3, utf_byte_length(a_katakana)) + + def test_uwid(self): + self.assertEqual(1, uwid(a_ascii)) + self.assertEqual(1, uwid(a_umlaut)) + self.assertEqual(2, uwid(a_katakana)) + self.assertEqual(3, uwid(a_katakana + a_umlaut)) + self.assertEqual(4, uwid("asdf")) + self.assertEqual(5, uwid("löööl")) + self.assertEqual(6, uwid("バババ")) + +if __name__ == '__main__': main() |