gh-104400: Add more tests to pygettext (GH-108173)

Author: tomasr8

Lib/test/test_tools/i18n_data/docstrings.pot

@@ -0,0 +1,40 @@
+# 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 <LL@li.org>\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"
+
+
+#: docstrings.py:7
+#, docstring
+msgid ""
+msgstr ""
+
+#: docstrings.py:18
+#, docstring
+msgid ""
+"multiline\n"
+"    docstring\n"
+"    "
+msgstr ""
+
+#: docstrings.py:25
+#, docstring
+msgid "docstring1"
+msgstr ""
+
+#: docstrings.py:30
+#, docstring
+msgid "Hello, {}!"
+msgstr ""
+

Lib/test/test_tools/i18n_data/docstrings.py

@@ -0,0 +1,41 @@
+# Test docstring extraction
+from gettext import gettext as _
+
+
+# Empty docstring
+def test(x):
+    """"""
+
+
+# Leading empty line
+def test2(x):
+
+    """docstring"""  # XXX This should be extracted but isn't.
+
+
+# XXX Multiline docstrings should be cleaned with `inspect.cleandoc`.
+def test3(x):
+    """multiline
+    docstring
+    """
+
+
+# Multiple docstrings - only the first should be extracted
+def test4(x):
+    """docstring1"""
+    """docstring2"""
+
+
+def test5(x):
+    """Hello, {}!""".format("world!")  # XXX This should not be extracted.
+
+
+# Nested docstrings
+def test6(x):
+    def inner(y):
+        """nested docstring"""  # XXX This should be extracted but isn't.
+
+
+class Outer:
+    class Inner:
+        "nested class docstring"  # XXX This should be extracted but isn't.

Lib/test/test_tools/i18n_data/fileloc.pot

@@ -0,0 +1,35 @@
+# 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 <LL@li.org>\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"
+
+
+#: fileloc.py:5 fileloc.py:6
+msgid "foo"
+msgstr ""
+
+#: fileloc.py:9
+msgid "bar"
+msgstr ""
+
+#: fileloc.py:14 fileloc.py:18
+#, docstring
+msgid "docstring"
+msgstr ""
+
+#: fileloc.py:22 fileloc.py:26
+#, docstring
+msgid "baz"
+msgstr ""
+

Lib/test/test_tools/i18n_data/fileloc.py

@@ -0,0 +1,26 @@
+# Test file locations
+from gettext import gettext as _
+
+# Duplicate strings
+_('foo')
+_('foo')
+
+# Duplicate strings on the same line should only add one location to the output
+_('bar'), _('bar')
+
+
+# Duplicate docstrings
+class A:
+    """docstring"""
+
+
+def f():
+    """docstring"""
+
+
+# Duplicate message and docstring
+_('baz')
+
+
+def g():
+    """baz"""

Lib/test/test_tools/i18n_data/messages.pot

@@ -0,0 +1,67 @@
+# 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 <LL@li.org>\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"
+
+
+#: messages.py:5
+msgid ""
+msgstr ""
+
+#: messages.py:8 messages.py:9
+msgid "parentheses"
+msgstr ""
+
+#: messages.py:12
+msgid "Hello, world!"
+msgstr ""
+
+#: messages.py:15
+msgid ""
+"Hello,\n"
+"    multiline!\n"
+msgstr ""
+
+#: messages.py:29
+msgid "Hello, {}!"
+msgstr ""
+
+#: messages.py:33
+msgid "1"
+msgstr ""
+
+#: messages.py:33
+msgid "2"
+msgstr ""
+
+#: messages.py:34 messages.py:35
+msgid "A"
+msgstr ""
+
+#: messages.py:34 messages.py:35
+msgid "B"
+msgstr ""
+
+#: messages.py:36
+msgid "set"
+msgstr ""
+
+#: messages.py:42
+msgid "nested string"
+msgstr ""
+
+#: messages.py:47
+msgid "baz"
+msgstr ""
+

Lib/test/test_tools/i18n_data/messages.py

@@ -0,0 +1,64 @@
+# Test message extraction
+from gettext import gettext as _
+
+# Empty string
+_("")
+
+# Extra parentheses
+(_("parentheses"))
+((_("parentheses")))
+
+# Multiline strings
+_("Hello, "
+  "world!")
+
+_("""Hello,
+    multiline!
+""")
+
+# Invalid arguments
+_()
+_(None)
+_(1)
+_(False)
+_(x="kwargs are not allowed")
+_("foo", "bar")
+_("something", x="something else")
+
+# .format()
+_("Hello, {}!").format("world")  # valid
+_("Hello, {}!".format("world"))  # invalid
+
+# Nested structures
+_("1"), _("2")
+arr = [_("A"), _("B")]
+obj = {'a': _("A"), 'b': _("B")}
+{{{_('set')}}}
+
+
+# Nested functions and classes
+def test():
+    _("nested string")  # XXX This should be extracted but isn't.
+    [_("nested string")]
+
+
+class Foo:
+    def bar(self):
+        return _("baz")
+
+
+def bar(x=_('default value')):  # XXX This should be extracted but isn't.
+    pass
+
+
+def baz(x=[_('default value')]):  # XXX This should be extracted but isn't.
+    pass
+
+
+# Shadowing _()
+def _(x):
+    pass
+
+
+def _(x="don't extract me"):
+    pass