github/pelican
1
0
Fork 1
mirror of https://github.com/getpelican/pelican.git synced 2025-10-15 20:28:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

get tests passing

Browse source
This commit is contained in:
dave mankoff 2013-01-28 22:11:06 -05:00
commit 7b59b34a73
4 changed files with 17 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

10
pelican/readers.py
View file

@ -223,10 +223,10 @@ class HTMLReader(Reader):
self._data_buffer += self.build_tag(tag, attrs, True) self._data_buffer += self.build_tag(tag, attrs, True)
def handle_comment(self, data): def handle_comment(self, data):
if self._in_body and data.strip() == 'PELICAN_END_SUMMARY': # if self._in_body and data.strip() == 'PELICAN_END_SUMMARY':
self.metadata['summary'] = self._data_buffer # self.metadata['summary'] = self._data_buffer
else: # else:
self._data_buffer += '<!--{}-->'.format(data) self._data_buffer += '<!--{}-->'.format(data)
def handle_data(self, data): def handle_data(self, data):
self._data_buffer += data self._data_buffer += data
@ -258,7 +258,7 @@ class HTMLReader(Reader):
def read(self, filename): def read(self, filename):
"""Parse content and metadata of HTML files""" """Parse content and metadata of HTML files"""
with open(filename) as content: with pelican_open(filename) as content:
parser = self._HTMLParser(self.settings) parser = self._HTMLParser(self.settings)
parser.feed(content) parser.feed(content)
parser.close() parser.close()

7
tests/content/article_with_comments.html
View file

@ -1,7 +1,8 @@
<html> <html>
<head>
</head>
<body> <body>
Summary comment is not included. Body content
<!-- PELICAN_END_SUMMARY --> <!-- This comment is included (including extra whitespace) -->
<!-- But this comment is (including extra whitespace) -->
</body> </body>
</html> </html>

2
tests/content/article_with_metadata.html
View file

@ -5,11 +5,11 @@
<meta name="date" contents="2010-12-02 10:14" /> <meta name="date" contents="2010-12-02 10:14" />
<meta name="category" contents="yeah" /> <meta name="category" contents="yeah" />
<meta name="author" contents="Alexis Métaireau" /> <meta name="author" contents="Alexis Métaireau" />
<meta name="summary" contents="Summary and stuff" />
<meta name="custom_field" contents="http://notmyidea.org" /> <meta name="custom_field" contents="http://notmyidea.org" />
</head> </head>
<body> <body>
Multi-line metadata should be supported Multi-line metadata should be supported
as well as <strong>inline markup</strong>. as well as <strong>inline markup</strong>.
<!-- PELICAN_END_SUMMARY -->
</body> </body>
</html> </html>

26
tests/test_readers.py
View file

@ -264,25 +264,16 @@ class AdReaderTest(unittest.TestCase):
class HTMLReaderTest(unittest.TestCase): class HTMLReaderTest(unittest.TestCase):
def test_article_with_comments(self): def test_article_with_comments(self):
reader = readers.HTMLReader({}) reader = readers.HTMLReader({})
content, metadata = reader.read(_filename('article_with_comments.html')) content, metadata = reader.read(_path('article_with_comments.html'))
expected = {
'summary': '''
Summary comment is not included.
''',
}
for key, value in expected.items():
self.assertEquals(value, metadata[key], key)
self.assertEquals(''' self.assertEquals('''
Summary comment is not included. Body content
<!-- This comment is included (including extra whitespace) -->
<!-- But this comment is (including extra whitespace) -->
''', content) ''', content)
def test_article_with_keywords(self): def test_article_with_keywords(self):
reader = readers.HTMLReader({}) reader = readers.HTMLReader({})
content, metadata = reader.read(_filename('article_with_keywords.html')) content, metadata = reader.read(_path('article_with_keywords.html'))
expected = { expected = {
'tags': ['foo', 'bar', 'foobar'], 'tags': ['foo', 'bar', 'foobar'],
} }
@ -292,15 +283,12 @@ class HTMLReaderTest(unittest.TestCase):
def test_article_with_metadata(self): def test_article_with_metadata(self):
reader = readers.HTMLReader({}) reader = readers.HTMLReader({})
content, metadata = reader.read(_filename('article_with_metadata.html')) content, metadata = reader.read(_path('article_with_metadata.html'))
expected = { expected = {
'category': 'yeah', 'category': 'yeah',
'author': u'Alexis Métaireau', 'author': u'Alexis Métaireau',
'title': 'This is a super article !', 'title': 'This is a super article !',
'summary': u''' 'summary': u'''Summary and stuff''',
Multi-line metadata should be supported
as well as <strong>inline markup</strong>.
''',
'date': datetime.datetime(2010, 12, 2, 10, 14), 'date': datetime.datetime(2010, 12, 2, 10, 14),
'tags': ['foo', 'bar', 'foobar'], 'tags': ['foo', 'bar', 'foobar'],
'custom_field': 'http://notmyidea.org', 'custom_field': 'http://notmyidea.org',
@ -313,6 +301,6 @@ class HTMLReaderTest(unittest.TestCase):
def test_article_metadata_key_lowercase(self): def test_article_metadata_key_lowercase(self):
"""Keys of metadata should be lowercase.""" """Keys of metadata should be lowercase."""
reader = readers.HTMLReader({}) reader = readers.HTMLReader({})
content, metadata = reader.read(_filename('article_with_uppercase_metadata.html')) content, metadata = reader.read(_path('article_with_uppercase_metadata.html'))
self.assertIn('category', metadata, "Key should be lowercase.") self.assertIn('category', metadata, "Key should be lowercase.")
self.assertEquals('Yeah', metadata.get('category'), "Value keeps cases.") self.assertEquals('Yeah', metadata.get('category'), "Value keeps cases.")