Skip to content

Use locale.getpreferredencoding rather than locale.getlocale as latter can fail if Python doesn't know the locale #11384

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michaelDCurran merged 3 commits into from
Jul 20, 2020
Merged

Use locale.getpreferredencoding rather than locale.getlocale as latter can fail if Python doesn't know the locale #11384

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ab5f1d6
Use locale.getpreferredencoding rather than locale.getlocale as latte…
lukaszgo1 Jul 15, 2020
5ccac96
Merge branch 'master' into I11155
lukaszgo1 Jul 16, 2020
078ed89
Review actions
lukaszgo1 Jul 16, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions source/NVDAObjects/window/scintilla.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,6 @@
from . import Window
from .. import NVDAObjectTextInfo
from ..behaviors import EditableTextWithAutoSelectDetection
import locale
import watchdog
import eventHandler
import locationHelper
Expand Down Expand Up @@ -82,7 +81,7 @@ def _get_encoding(self):
if cp==SC_CP_UTF8:
return "utf-8"
else:
return locale.getlocale()[1]
return textUtils.USERANSICODEPAGE

def _getOffsetFromPoint(self,x,y):
x, y = winUser.ScreenToClient(self.obj.windowHandle, x, y)
Expand Down
4 changes: 2 additions & 2 deletions source/appModules/winamp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,12 +11,12 @@
from NVDAObjects.IAccessible import IAccessible
import appModuleHandler
import speech
import locale
import controlTypes
import api
import watchdog
import braille
import ui
import textUtils

# message used to sent many messages to winamp's main window.
# most all of the IPC_* messages involve sending the message in the form of:
Expand Down Expand Up @@ -116,7 +116,7 @@ def _get_name(self):
winKernel.virtualFreeEx(self.processHandle,internalInfo,0,winKernel.MEM_RELEASE)
# file title is fetched in the current locale encoding.
# We need to decode it to unicode first.
encoding=locale.getlocale()[1]
encoding = textUtils.USERANSICODEPAGE
fileTitle=info.filetitle.decode(encoding,errors="replace")
return "%d.\t%s\t%s"%(curIndex+1,fileTitle,info.filelength)

Expand Down
9 changes: 4 additions & 5 deletions source/textInfos/offsets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,6 @@
import textUtils
from dataclasses import dataclass
from typing import Optional, Tuple
import locale
from logHandler import log

@dataclass
Expand Down Expand Up @@ -282,7 +281,7 @@ def _getTextRange(self,start,end):
if self.encoding == textUtils.WCHAR_ENCODING:
offsetConverter = textUtils.WideStringOffsetConverter(text)
start, end = offsetConverter.wideToStrOffsets(start, end)
elif self.encoding not in (None, "utf_32_le", locale.getlocale()[1]):
elif self.encoding not in (None, "utf_32_le", textUtils.USERANSICODEPAGE):
raise NotImplementedError
return text[start:end]

Expand Down Expand Up @@ -346,7 +345,7 @@ def _calculateUniscribeOffsets(self, lineText: str, unit: str, relOffset: int) -
return None

def _getCharacterOffsets(self, offset):
if self.encoding not in (textUtils.WCHAR_ENCODING, None, "utf_32_le", locale.getlocale()[1]):
if self.encoding not in (textUtils.WCHAR_ENCODING, None, "utf_32_le", textUtils.USERANSICODEPAGE):
raise NotImplementedError
lineStart, lineEnd = self._getLineOffsets(offset)
lineText = self._getTextRange(lineStart, lineEnd)
Expand All @@ -363,7 +362,7 @@ def _getCharacterOffsets(self, offset):
return (offset, offset + 1)

def _getWordOffsets(self,offset):
if self.encoding not in (textUtils.WCHAR_ENCODING, None, "utf_32_le", locale.getlocale()[1]):
if self.encoding not in (textUtils.WCHAR_ENCODING, None, "utf_32_le", textUtils.USERANSICODEPAGE):
Comment thread
lukaszgo1 marked this conversation as resolved.
Outdated
raise NotImplementedError
lineStart, lineEnd = self._getLineOffsets(offset)
lineText = self._getTextRange(lineStart,lineEnd)
Expand Down Expand Up @@ -397,7 +396,7 @@ def _getLineOffsets(self,offset):
strStart=findStartOfLine(text, strOffset)
strEnd=findEndOfLine(text, strOffset)
return offsetConverter.strToWideOffsets(strStart, strEnd)
elif self.encoding not in (None, "utf_32_le", locale.getlocale()[1]):
elif self.encoding not in (None, "utf_32_le", textUtils.USERANSICODEPAGE):
raise NotImplementedError
start=findStartOfLine(text,offset)
end=findEndOfLine(text,offset)
Expand Down
13 changes: 7 additions & 6 deletions source/textUtils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,8 @@
# -*- coding: UTF-8 -*-
Comment thread
lukaszgo1 marked this conversation as resolved.
Outdated
#textUtils.py
#A part of NonVisual Desktop Access (NVDA)
#This file is covered by the GNU General Public License.
#See the file COPYING for more details.
#Copyright (C) 2018-2019 NV Access Limited, Babbage B.V.
# A part of NonVisual Desktop Access (NVDA)
# This file is covered by the GNU General Public License.
# See the file COPYING for more details.
# Copyright (C) 2018-2020 NV Access Limited, Babbage B.V., Łukasz Golonka

"""
Classes and utilities to deal with offsets variable width encodings, particularly utf_16.
Expand All @@ -18,6 +17,8 @@
from logHandler import log

WCHAR_ENCODING = "utf_16_le"
USERANSICODEPAGE = locale.getpreferredencoding()

@LeonarddeR LeonarddeR Jul 16, 2020

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please follow the style used for constants here:

Suggested change
USERANSICODEPAGE = locale.getpreferredencoding()
USER_ANSI_CODE_PAGE = locale.getpreferredencoding()

Or rather

Suggested change
USERANSICODEPAGE = locale.getpreferredencoding()
SYSTEM_PREFERRED_ENCODING = locale.getpreferredencoding()

@lukaszgo1 lukaszgo1 Jul 16, 2020

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I've renamed it to USER_ANSI_CODE_PAGE because it can be set per Windows user account and is not global to the system.



class WideStringOffsetConverter:
R"""
Expand Down Expand Up @@ -201,7 +202,7 @@ def getTextFromRawBytes(
if numChars > 1 and any(buf[numChars:]):
encoding = WCHAR_ENCODING
else:
encoding = locale.getlocale()[1]
encoding = USERANSICODEPAGE
else:
encoding = encodings.normalize_encoding(encoding).lower()
if encoding.startswith("utf_16"):
Expand Down