def test_title_attribute(self):
self.assertContainsSameWords(
html_to_plaintext('<p title="title">content</p>'), 'title content')
self.assertContainsSameWords(
html_to_plaintext(
'<p title="title">content</p><p title="title2">content2</p>'),
'title content title2 content2')
def test_alt_attribute(self):
self.assertContainsSameWords(
html_to_plaintext('<img alt="image description" />'),
'image description')
self.assertContainsSameWords(
html_to_plaintext('<p>content</p><img alt="image description" />'),
'content image description')
def test_comments(self):
self.assertContainsSameWords(
html_to_plaintext("<!-- comment --><p>content</p>"), 'content')
self.assertContainsSameWords(
html_to_plaintext("<p>content<!-- comment --></p>"),
'content',
)
def test_alt_attribute(self):
self.assertContainsSameWords(
html_to_plaintext('<img alt="image description" />'),
'image description'
)
self.assertContainsSameWords(
html_to_plaintext('<p>content</p><img alt="image description" />'),
'content image description'
)
def test_title_attribute(self):
self.assertContainsSameWords(
html_to_plaintext('<p title="title">content</p>'),
'title content'
)
self.assertContainsSameWords(
html_to_plaintext('<p title="title">content</p><p title="title2">content2</p>'),
'title content title2 content2'
)
def test_comments(self):
self.assertContainsSameWords(
html_to_plaintext("<!-- comment --><p>content</p>"),
'content'
)
self.assertContainsSameWords(
html_to_plaintext("<p>content<!-- comment --></p>"),
'content',
)
def test_non_text(self):
self.assertContainsSameWords(
html_to_plaintext("<script>javascript</script><p>content</p>"),
'content')
self.assertContainsSameWords(
html_to_plaintext("<style>css</style><p>content<p>"), 'content')
self.assertContainsSameWords(
html_to_plaintext(
"<script>javascript<p>javascript</p></script><p>content</p>"),
'content')
def test_other_attributes(self):
self.assertContainsSameWords(
html_to_plaintext('<a href="http://example.com">example.com</a>'),
'example.com')
self.assertContainsSameWords(
html_to_plaintext(
'<body onload="javascript:alert(\'hello\')">content</body>'),
'content')
self.assertContainsSameWords(
html_to_plaintext(
'<span lang="en" onclick="javascript:void(0)">content</span>'),
'content')
def test_non_text(self):
self.assertContainsSameWords(
html_to_plaintext("<script>javascript</script><p>content</p>"),
'content'
)
self.assertContainsSameWords(
html_to_plaintext("<style>css</style><p>content<p>"),
'content'
)
self.assertContainsSameWords(
html_to_plaintext("<script>javascript<p>javascript</p></script><p>content</p>"),
'content'
)
def test_other_attributes(self):
self.assertContainsSameWords(
html_to_plaintext('<a href="http://example.com">example.com</a>'),
'example.com'
)
self.assertContainsSameWords(
html_to_plaintext('<body onload="javascript:alert(\'hello\')">content</body>'),
'content'
)
self.assertContainsSameWords(
html_to_plaintext('<span lang="en" onclick="javascript:void(0)">content</span>'),
'content'
)
def prepare(self, obj):
self.prepared_data = super(BlogIndex, self).prepare(obj)
request = fake_request()
node = obj.content.get_published_node(request)
if node is not None:
# prepare() has to work on unpublished blogs because haystack
# filters them out at query time, not index time.
blog_layout = node.content
ctx = {
'request': fake_request(),
'root_node_override': node,
}
html = render_root(ctx, obj, 'content')
content = [
html_to_plaintext(html),
blog_layout.title,
blog_layout.summary,
]
self.prepared_data['title'] = blog_layout.title
self.prepared_data['text'] = ' '.join(content)
self.prepared_data['get_absolute_url'] = obj.get_absolute_url_with_layout(blog_layout)
return self.prepared_data
def prepare(self, obj):
self.prepared_data = super(BlogIndex, self).prepare(obj)
request = fake_request()
node = obj.content.get_published_node(request)
if node is not None:
# prepare() has to work on unpublished blogs because haystack
# filters them out at query time, not index time.
blog_layout = node.content
ctx = {
'request': fake_request(),
'root_node_override': node,
}
html = render_root(ctx, obj, 'content')
content = [
html_to_plaintext(html),
blog_layout.title,
blog_layout.summary,
]
self.prepared_data['title'] = blog_layout.title
self.prepared_data['text'] = ' '.join(content)
self.prepared_data[
'get_absolute_url'] = obj.get_absolute_url_with_layout(
blog_layout)
return self.prepared_data
def prepare_text(self, obj):
context = {'_current_page': obj.page_ptr, 'page': obj.page_ptr}
html = render_root(context, obj, 'root_node')
content = html_to_plaintext(html)
keywords = ' '.join(self.prepare_keywords(obj))
return ' '.join([obj.title, keywords, obj.description,
content])
def test_basic_conversion(self):
self.assertContainsSameWords(html_to_plaintext("<p>content</p>"),
'content')
self.assertContainsSameWords(
html_to_plaintext("<p>content with multiple words</p>"),
'content with multiple words')
self.assertContainsSameWords(
html_to_plaintext("<p>multiple</p><p>content</p>"),
'multiple content')
self.assertContainsSameWords(
html_to_plaintext('''<div><p>complex</p><p>content</p></div>
<p>with <a href="#">encapsulation</a></p>'''),
'complex content with encapsulation')
def prepare_text(self, obj):
content = html_to_plaintext(obj.content)
categories = ' '.join(prepare_attribute_list(obj, 'categories'))
authors = ' '.join(prepare_attribute_list(obj, 'authors'))
tags = ' '.join([force_text(k) for k in obj.tags_list])
return ' '.join([
obj.title, content, categories, authors, tags, obj.slug,
obj.image_caption, obj.model_subtitle
])
def test_basic_conversion(self):
self.assertContainsSameWords(
html_to_plaintext("<p>content</p>"),
'content'
)
self.assertContainsSameWords(
html_to_plaintext("<p>content with multiple words</p>"),
'content with multiple words'
)
self.assertContainsSameWords(
html_to_plaintext("<p>multiple</p><p>content</p>"),
'multiple content'
)
self.assertContainsSameWords(
html_to_plaintext(
'''<div><p>complex</p><p>content</p></div>
<p>with <a href="#">encapsulation</a></p>'''
),
'complex content with encapsulation'
)
def prepare(self, obj):
self.prepared_data = super(BlogIndex, self).prepare(obj)
request = fake_request()
node = obj.content.get_published_node(request)
blog_layout = node.content
ctx = {
'request': fake_request(),
'root_node_override': node,
}
html = render_root(ctx, obj, 'content')
content = [
html_to_plaintext(html),
blog_layout.title,
blog_layout.summary,
]
self.prepared_data['title'] = blog_layout.title
self.prepared_data['text'] = ' '.join(content)
self.prepared_data['get_absolute_url'] = obj.get_absolute_url_with_layout(blog_layout)
return self.prepared_data
def prepare(self, obj):
self.prepared_data = super(BlogIndex, self).prepare(obj)
request = fake_request()
node = obj.content.get_published_node(request)
blog_layout = node.content
ctx = {
'request': fake_request(),
'root_node_override': node,
}
html = render_root(ctx, obj, 'content')
content = [
html_to_plaintext(html),
blog_layout.title,
blog_layout.summary,
]
self.prepared_data['title'] = blog_layout.title
self.prepared_data['text'] = ' '.join(content)
self.prepared_data[
'get_absolute_url'] = obj.get_absolute_url_with_layout(blog_layout)
return self.prepared_data
def prepare_text(self, obj):
html = render_root({}, obj, "root_node")
content = html_to_plaintext(html)
keywords = " ".join(self.prepare_keywords(obj))
return " ".join([obj.title, keywords, obj.description, content])
def prepare_text(self, obj):
context = {"_current_page": obj.page_ptr, "page": obj.page_ptr}
html = render_root(context, obj, "root_node")
content = html_to_plaintext(html)
keywords = " ".join(self.prepare_keywords(obj))
return " ".join([obj.title, keywords, obj.description, content])
