Skip to content

gh-130197: Test various encodings with pygettext #132244

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

Draft
wants to merge 4 commits into
base: main
Choose a base branch
from
+97 −0
Draft

gh-130197: Test various encodings with pygettext #132244

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e28559c
Test various encodings with pygettext
tomasr8 Apr 7, 2025
e12bb90
Update test subdirs
tomasr8 Apr 7, 2025
cad1efd
Use latin2 encoding
tomasr8 Apr 12, 2025
067807f
Lint fix
tomasr8 Apr 12, 2025
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
27 changes: 27 additions & 0 deletions Lib/test/test_tools/i18n_data/encodings/ascii.pot
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) YEAR ORGANIZATION
# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
#
msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\n"
"POT-Creation-Date: 2000-01-01 00:00+0000\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <[email protected]>\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: pygettext.py 1.5\n"


#. ascii text
#: ascii.py:7
msgid "foo"
msgstr ""

#. non-ascii text
#: ascii.py:10
msgid "α β"
msgstr ""

10 changes: 10 additions & 0 deletions Lib/test/test_tools/i18n_data/encodings/ascii.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
# -*- coding: ascii -*-

from gettext import gettext as _


# ascii text
_('foo')

# non-ascii text
_('\u03b1 \u03b2')
27 changes: 27 additions & 0 deletions Lib/test/test_tools/i18n_data/encodings/ascii_escaped.pot
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) YEAR ORGANIZATION
# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
#
msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\n"
"POT-Creation-Date: 2000-01-01 00:00+0000\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <[email protected]>\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: pygettext.py 1.5\n"


#. ascii text
#: ascii.py:7
msgid "foo"
msgstr ""

#. non-ascii text
#: ascii.py:10
msgid "\316\261 \316\262"
msgstr ""

32 changes: 32 additions & 0 deletions Lib/test/test_tools/i18n_data/encodings/latin1.pot
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) YEAR ORGANIZATION
# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
#
msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\n"
"POT-Creation-Date: 2000-01-01 00:00+0000\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <[email protected]>\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: pygettext.py 1.5\n"


#. ascii text
#: latin1.py:7
msgid "foo"
msgstr ""

#. latin-1 text
#: latin1.py:10
msgid "Å ø"
msgstr ""

#. non-latin-1 text
#: latin1.py:13
msgid "α β"
msgstr ""

13 changes: 13 additions & 0 deletions Lib/test/test_tools/i18n_data/encodings/latin1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
# -*- coding: latin-1 -*-

from gettext import gettext as _


# ascii text
_('foo')

# latin-1 text
_('Å ø')

# non-latin-1 text
_('\u03b1 \u03b2')
32 changes: 32 additions & 0 deletions Lib/test/test_tools/i18n_data/encodings/latin1_escaped.pot
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) YEAR ORGANIZATION
# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
#
msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\n"
"POT-Creation-Date: 2000-01-01 00:00+0000\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <[email protected]>\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: pygettext.py 1.5\n"


#. ascii text
#: latin1.py:7
msgid "foo"
msgstr ""

#. latin-1 text
#: latin1.py:10
msgid "\303\205 \303\270"
msgstr ""

#. non-latin-1 text
#: latin1.py:13
msgid "\316\261 \316\262"
msgstr ""

32 changes: 32 additions & 0 deletions Lib/test/test_tools/i18n_data/encodings/windows1252.pot
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) YEAR ORGANIZATION
# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
#
msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\n"
"POT-Creation-Date: 2000-01-01 00:00+0000\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <[email protected]>\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: pygettext.py 1.5\n"


#. ascii text
#: windows1252.py:7
msgid "foo"
msgstr ""

#. windows-1252 text
#: windows1252.py:10
msgid "€ ƒ"
msgstr ""

#. non-windows-1252 text
#: windows1252.py:13
msgid "α β"
msgstr ""

13 changes: 13 additions & 0 deletions Lib/test/test_tools/i18n_data/encodings/windows1252.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
# -*- coding: windows-1252 -*-

from gettext import gettext as _


# ascii text
_('foo')

# windows-1252 text
_('€ ƒ')

# non-windows-1252 text
_('\u03b1 \u03b2')
32 changes: 32 additions & 0 deletions Lib/test/test_tools/i18n_data/encodings/windows1252_escaped.pot
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) YEAR ORGANIZATION
# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
#
msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\n"
"POT-Creation-Date: 2000-01-01 00:00+0000\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <[email protected]>\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: pygettext.py 1.5\n"


#. ascii text
#: windows1252.py:7
msgid "foo"
msgstr ""

#. windows-1252 text
#: windows1252.py:10
msgid "\342\202\254 \306\222"
msgstr ""

#. non-windows-1252 text
#: windows1252.py:13
msgid "\316\261 \316\262"
msgstr ""

7 changes: 7 additions & 0 deletions Lib/test/test_tools/test_i18n.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -531,6 +531,13 @@ def extract_from_snapshots():
'escapes.py': ('--escape', '--add-comments='),
# Escape only ascii and let unicode pass through:
('escapes.py', 'ascii-escapes.pot'): ('--add-comments=',),
# Test input files with various encodings:
('encodings/ascii.py', 'encodings/ascii.pot'): ('--add-comments=',),
('encodings/ascii.py', 'encodings/ascii_escaped.pot'): ('--add-comments=', '--escape'),
('encodings/latin1.py', 'encodings/latin1.pot'): ('--add-comments=',),
('encodings/latin1.py', 'encodings/latin1_escaped.pot'): ('--add-comments=', '--escape'),
('encodings/windows1252.py', 'encodings/windows1252.pot'): ('--add-comments=',),
('encodings/windows1252.py', 'encodings/windows1252_escaped.pot'): ('--add-comments=', '--escape'),
}

for filename, args in snapshots.items():
Expand Down
1 change: 1 addition & 0 deletions Makefile.pre.in
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2644,6 +2644,7 @@ TESTSUBDIRS= idlelib/idle_test \
test/test_tomllib/data/valid/multiline-basic-str \
test/test_tools \
test/test_tools/i18n_data \
test/test_tools/i18n_data/encodings \
test/test_tools/msgfmt_data \
test/test_ttk \
test/test_unittest \
Expand Down
Loading