def test_extract_strings(self):
template, strings = extract_strings("""
<p><b>Bread</b>\xa0is a\xa0<a href="https://en.wikipedia.org/wiki/Staple_food">staple food</a>\xa0prepared from a\xa0<a href="https://en.wikipedia.org/wiki/Dough">dough</a>\xa0of\xa0<a href="https://en.wikipedia.org/wiki/Flour">flour</a>\xa0and\xa0<a href="https://en.wikipedia.org/wiki/Water">water</a>, usually by\xa0<a href="https://en.wikipedia.org/wiki/Baking">baking</a>. Throughout recorded history it has been popular around the world and is one of the oldest artificial foods, having been of importance since the dawn of\xa0<a href="https://en.wikipedia.org/wiki/Agriculture#History">agriculture</a>.</p>
<p>Proportions of types of flour and other ingredients vary widely, as do modes of preparation. As a result, types, shapes, sizes, and textures of breads differ around the world. Bread may be\xa0<a href="https://en.wikipedia.org/wiki/Leaven">leavened</a>\xa0by processes such as reliance on naturally occurring\xa0<a href="https://en.wikipedia.org/wiki/Sourdough">sourdough</a>\xa0microbes, chemicals, industrially produced yeast, or high-pressure aeration. Some bread is cooked before it can leaven, including for traditional or religious reasons. Non-cereal ingredients such as fruits, nuts and fats may be included. Commercial bread commonly contains additives to improve flavor, texture, color, shelf life, and ease of manufacturing.</p>
""")
self.assertHTMLEqual(
template,
"""
<p><text position="0"></text></p>
<p><text position="1"></text></p>
""",
)
self.assertEqual(
strings,
[
StringValue.from_html(
'<b>Bread</b>\xa0is a\xa0<a href="https://en.wikipedia.org/wiki/Staple_food">staple food</a>\xa0prepared from a\xa0<a href="https://en.wikipedia.org/wiki/Dough">dough</a>\xa0of\xa0<a href="https://en.wikipedia.org/wiki/Flour">flour</a>\xa0and\xa0<a href="https://en.wikipedia.org/wiki/Water">water</a>, usually by\xa0<a href="https://en.wikipedia.org/wiki/Baking">baking</a>. Throughout recorded history it has been popular around the world and is one of the oldest artificial foods, having been of importance since the dawn of\xa0<a href="https://en.wikipedia.org/wiki/Agriculture#History">agriculture</a>.'
),
StringValue.from_html(
'Proportions of types of flour and other ingredients vary widely, as do modes of preparation. As a result, types, shapes, sizes, and textures of breads differ around the world. Bread may be\xa0<a href="https://en.wikipedia.org/wiki/Leaven">leavened</a>\xa0by processes such as reliance on naturally occurring\xa0<a href="https://en.wikipedia.org/wiki/Sourdough">sourdough</a>\xa0microbes, chemicals, industrially produced yeast, or high-pressure aeration. Some bread is cooked before it can leaven, including for traditional or religious reasons. Non-cereal ingredients such as fruits, nuts and fats may be included. Commercial bread commonly contains additives to improve flavor, texture, color, shelf life, and ease of manufacturing.'
),
],
)
def test_render_html(self):
# Note, I swapped the first two links around to check that the attrs are restored to the correct one
string = StringValue(
'<b>Bread</b> is a <a id="a2">dough</a> prepared from a <a id="a1">staple food</a> of <a id="a3">flour</a> and <a id="a4">water</a>',
)
attrs = {
'a1': {
'href': 'https://en.wikipedia.org/wiki/Staple_food'
},
'a2': {
'href': 'https://en.wikipedia.org/wiki/Dough'
},
'a3': {
'href': 'https://en.wikipedia.org/wiki/Flour'
},
'a4': {
'href': 'https://en.wikipedia.org/wiki/Water'
},
}
self.assertEqual(
string.render_html(attrs),
'<b>Bread</b> is a <a href="https://en.wikipedia.org/wiki/Dough">dough</a> prepared from a <a href="https://en.wikipedia.org/wiki/Staple_food">staple food</a> of <a href="https://en.wikipedia.org/wiki/Flour">flour</a> and <a href="https://en.wikipedia.org/wiki/Water">water</a>',
)
def test_string_render_text(self):
string = StringValue(
"This is a paragraph. <b>This is some bold <i>and now italic</i></b> text"
)
self.assertEqual(
string.render_text(),
"This is a paragraph. This is some bold and now italic text")
def translate(self, source_locale, target_locale, strings):
translator = googletrans.Translator()
google_translations = translator.translate(
[string.render_text() for string in strings],
src=language_code(source_locale.language_code),
dest=language_code(target_locale.language_code),
)
return {
StringValue.from_plaintext(translation.origin): StringValue.from_plaintext(translation.text) for translation in google_translations
}
def test_block_tag_in_inline_tag(self):
# If an inline tag contains a block tag. The inline tag must be in the template.
# Testing for issue https://github.com/mozilla/donate-wagtail/issues/586
template, strings = extract_strings("<p><i>Foo <p>Bar</p></i></p>")
self.assertHTMLEqual(
template,
'<p><i><text position="0"></text> <p><text position="1"></text></p></i></p>',
)
self.assertEqual(
strings,
[StringValue.from_html("Foo"),
StringValue.from_html("Bar")])
def test_string_from_html(self):
string, attrs = StringValue.from_html(
'<b>Bread</b>\xa0is a\xa0<a href="https://en.wikipedia.org/wiki/Staple_food">staple food</a>\xa0prepared from a\xa0<a href="https://en.wikipedia.org/wiki/Dough">dough</a>\xa0of\xa0<a href="https://en.wikipedia.org/wiki/Flour">flour</a>\xa0and\xa0<a href="https://en.wikipedia.org/wiki/Water">water</a>'
)
self.assertEqual(
string.data,
'<b>Bread</b> is a <a id="a1">staple food</a> prepared from a <a id="a2">dough</a> of <a id="a3">flour</a> and <a id="a4">water</a>',
)
self.assertEqual(
attrs, {
'a1': {
'href': 'https://en.wikipedia.org/wiki/Staple_food'
},
'a2': {
'href': 'https://en.wikipedia.org/wiki/Dough'
},
'a3': {
'href': 'https://en.wikipedia.org/wiki/Flour'
},
'a4': {
'href': 'https://en.wikipedia.org/wiki/Water'
},
})
def test_empty_inline_tag(self):
template, strings = extract_strings("<p><i></i>Foo</p>")
self.assertHTMLEqual(template,
'<p><i></i><text position="0"></text></p>')
self.assertEqual(strings, [StringValue.from_html("Foo")])
def test_br_tag_is_removed_when_it_appears_at_end_of_segment(self):
template, strings = extract_strings("<p><i>Foo</i><br/></p>")
self.assertHTMLEqual(template,
'<p><i><text position="0"></text></i><br/></p>')
self.assertEqual(strings, [StringValue.from_html("Foo")])
def setUp(self):
self.snippet = TestSnippet.objects.create(field="Test snippet content")
self.page = create_test_page(
title="Test page",
slug="test-page",
test_charfield="This is some test content",
test_snippet=self.snippet,
)
self.source = TranslationSource.from_instance(self.page)[0]
self.source_locale = Locale.objects.get(language_code="en")
self.dest_locale = Locale.objects.create(language_code="fr")
# Translate the snippet
self.translated_snippet = self.snippet.copy_for_translation(
self.dest_locale)
self.translated_snippet.field = "Tester le contenu de l'extrait"
self.translated_snippet.save()
# Add translation for test_charfield
self.string = String.from_value(
self.source_locale,
StringValue.from_plaintext("This is some test content"))
self.translation = StringTranslation.objects.create(
translation_of=self.string,
locale=self.dest_locale,
context=TranslationContext.objects.get(
object_id=self.page.translation_key, path="test_charfield"),
data="Ceci est du contenu de test",
)
def test_br_tag_is_treated_as_inline_tag(self):
template, strings = extract_strings(
"<p><b>Foo <i>Bar<br/>Baz</i></b></p>")
self.assertHTMLEqual(template,
'<p><b><text position="0"></text></b></p>')
self.assertEqual(strings,
[StringValue.from_html("Foo <i>Bar<br/>Baz</i>")])
def test_extract_strings_2(self):
template, strings = extract_strings("""
<h1>Foo bar baz</h1>
<p>This is a paragraph. <b>This is some bold <i>and now italic</i></b> text</p>
<p><script> this should be interpreted as text.</p>
<ul>
<li>List item one</li>
<li><b>List item two</li>
</ul>
<img src="foo" alt="This bit isn't translatable">
""")
self.assertHTMLEqual(
template,
"""
<h1><text position="0"></text></h1>
<p><text position="1"></text></p>
<p><text position="2"></text></p>
<ul>
<li><text position="3"></text></li>
<li><b><text position="4"></text></b></li>
</ul>
<img alt="This bit isn\'t translatable" src="foo">
""",
)
self.assertEqual(
strings,
[
StringValue.from_html("Foo bar baz"),
StringValue.from_html(
"This is a paragraph. <b>This is some bold <i>and now italic</i></b> text"
),
StringValue.from_html(
"<script> this should be interpreted as text."),
StringValue.from_html("List item one"),
StringValue.from_html("List item two"),
],
)
def test_string_from_plaintext(self):
string = StringValue.from_plaintext("This is a test <Foo> bar 'baz'", )
# Django 2.x HTML escape function escapes quotes differently
if DJANGO_VERSION >= (3, 0):
self.assertEqual(
string.data,
"This is a test <Foo> bar 'baz'",
)
else:
self.assertEqual(
string.data,
"This is a test <Foo> bar 'baz'",
)
TemplateSegmentValue(
"",
"html",
'<h1><text position="0"></text></h1><p><text position="1"></text></p><ul><li><text position="2"></text></li></ul>',
3,
order=9,
),
StringSegmentValue("", "Ceci est une rubrique", order=10),
StringSegmentValue.from_html(
"",
'Ceci est un paragraphe. <foo> <b>Texte en gras</b>',
order=11,
),
StringSegmentValue(
"",
StringValue('<a id="a1">Ceci est un lien</a>'),
attrs={"a1": {
"href": "http://example.com"
}},
order=12,
),
]
RICH_TEXT_TEST_OUTPUT = '<h1>Ceci est une rubrique</h1><p>Ceci est un paragraphe. <foo> <b>Texte en gras</b></p><ul><li><a href="http://example.com">Ceci est un lien</a></li></ul>'
class TestSegmentIngestion(TestCase):
def setUp(self):
self.src_locale = Locale.objects.default()
self.locale = Locale.objects.create(language_code="fr")
def test_br_tags_converted_to_newlines(self):
string = StringValue("foo<br>bar<br>baz")
self.assertEqual(string.render_text(), "foo\nbar\nbaz")
string = StringValue("<br/><b>foo</b><br/><i>bar</i><br/>")
self.assertEqual(string.render_text(), "\nfoo\nbar\n")
RICH_TEXT_TEST_OUTPUT = [
TemplateSegmentValue(
"",
"html",
'<h1><text position="0"></text></h1><p><text position="1"></text></p><ul><li><text position="2"></text></li></ul>',
3,
),
StringSegmentValue("", "This is a heading"),
StringSegmentValue.from_html(
"",
'This is a paragraph. <foo> <b>Bold text</b>',
),
StringSegmentValue(
"",
StringValue('<a id="a1">This is a link</a>.'),
attrs={
"a1": {"href": "http://example.com"}
}
),
]
class TestSegmentExtraction(TestCase):
def test_charfield(self):
page = make_test_page(test_charfield="Test content")
segments = extract_segments(page)
self.assertEqual(segments, [StringSegmentValue("test_charfield", "Test content")])
def test_textfield(self):
def test_special_chars_unescaped(self):
string = StringValue("<b>foo</b><i> & bar</i>")
self.assertEqual(string.render_text(), "foo & bar")
def test_special_chars_escaped(self):
string = StringValue.from_plaintext("foo & bar")
self.assertEqual(string.data, "foo & bar")
def test_newlines_converted_to_br_tags(self):
string = StringValue.from_plaintext("foo\nbar\nbaz")
self.assertEqual(string.data, "foo<br>bar<br>baz")
string = StringValue.from_plaintext("\nfoo\nbar\n")
self.assertEqual(string.data, "<br>foo<br>bar<br>")