def verify_xpath(self):
testfile = 'tests/data/filter/category-one.xml'
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
self.assertEqual('', output)
testfile = 'tests/data/filter/category-two.xml'
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
self.assertNotEqual('', output)
def verify_xpath(self):
testfile = 'tests/data/filter/category-one.xml'
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
self.assertEqual('', output)
testfile = 'tests/data/filter/category-two.xml'
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
self.assertNotEqual('', output)
def test_xhtml2html_filter(self):
testfile = 'tests/data/filter/index.html'
the_filter = 'xhtml2html.plugin?quote_attr_values=True'
with open(testfile) as fp:
output = shell.run(the_filter, fp.read(), mode="filter")
self.assertTrue(output.find('/>') < 0)
self.assertTrue(output.find('</script>') >= 0)
def test_addsearch_filter(self):
testfile = 'tests/data/filter/index.html'
filter = 'addsearch.xslt'
output = shell.run(filter, open(testfile).read(), mode="filter")
self.assertTrue(output.find('<h2>Search</h2>')>=0)
self.assertTrue(output.find('<form><input name="q"/></form>')>=0)
self.assertTrue(output.find(' href="http://planet.intertwingly.net/opensearchdescription.xml"')>=0)
self.assertTrue(output.find('</script>')>=0)
def test_coral_cdn(self):
testfile = 'tests/data/filter/coral_cdn.xml'
filter = 'coral_cdn_filter.py'
output = shell.run(filter, open(testfile).read(), mode="filter")
dom = xml.dom.minidom.parseString(output)
imgsrc = dom.getElementsByTagName('img')[0].getAttribute('src')
self.assertEqual('http://example.com.nyud.net:8080/foo.png', imgsrc)
def test_addsearch_filter(self):
testfile = 'tests/data/filter/index.html'
filter = 'addsearch.genshi'
output = shell.run(filter, open(testfile).read(), mode="filter")
self.assertTrue(output.find('<h2>Search</h2>')>=0)
self.assertTrue(output.find('<form><input name="q"/></form>')>=0)
self.assertTrue(output.find(' href="http://planet.intertwingly.net/opensearchdescription.xml"')>=0)
self.assertTrue(output.find('</script>')>=0)
def test_regexp_filter2(self):
config.load('tests/data/filter/regexp-sifter2.ini')
testfile = 'tests/data/filter/category-one.xml'
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
self.assertNotEqual('', output)
testfile = 'tests/data/filter/category-two.xml'
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
self.assertEqual('', output)
def test_xslt_filter(self):
config.load('tests/data/filter/translate.ini')
testfile = 'tests/data/filter/category-one.xml'
input = open(testfile).read()
output = shell.run(config.filters()[0], input, mode="filter")
dom = xml.dom.minidom.parseString(output)
catterm = dom.getElementsByTagName('category')[0].getAttribute('term')
self.assertEqual('OnE', catterm)
def test_regexp_filter2(self):
config.load('tests/data/filter/regexp-sifter2.ini')
testfile = 'tests/data/filter/category-one.xml'
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
self.assertNotEqual('', output)
testfile = 'tests/data/filter/category-two.xml'
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
self.assertEqual('', output)
def test_xslt_filter(self):
config.load('tests/data/filter/translate.ini')
testfile = 'tests/data/filter/category-one.xml'
input = open(testfile).read()
output = shell.run(config.filters()[0], input, mode="filter")
dom = xml.dom.minidom.parseString(output)
catterm = dom.getElementsByTagName('category')[0].getAttribute('term')
self.assertEqual('OnE', catterm)
def test_stripAd_yahoo(self):
testfile = 'tests/data/filter/stripAd-yahoo.xml'
config.load('tests/data/filter/stripAd-yahoo.ini')
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
dom = xml.dom.minidom.parseString(output)
excerpt = dom.getElementsByTagName('content')[0]
self.assertEqual(u'before--after',
excerpt.firstChild.firstChild.nodeValue)
def test_stripAd_yahoo(self):
testfile = 'tests/data/filter/stripAd-yahoo.xml'
config.load('tests/data/filter/stripAd-yahoo.ini')
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
dom = xml.dom.minidom.parseString(output)
excerpt = dom.getElementsByTagName('content')[0]
self.assertEqual(u'before--after',
excerpt.firstChild.firstChild.nodeValue)
def data2config(data, cached_config):
if content_type(list).find('opml')>=0:
opml.opml2config(data, cached_config)
elif content_type(list).find('foaf')>=0:
foaf.foaf2config(data, cached_config)
else:
from planet import shell
import StringIO
cached_config.readfp(StringIO.StringIO(shell.run(
content_type(list), data.getvalue(), mode="filter")))
if cached_config.sections() in [[], [list]]:
raise Exception
def test_excerpt_lorem_ipsum(self):
testfile = 'tests/data/filter/excerpt-lorem-ipsum.xml'
config.load('tests/data/filter/excerpt-lorem-ipsum.ini')
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
dom = xml.dom.minidom.parseString(output)
excerpt = dom.getElementsByTagName('planet:excerpt')[0]
self.assertEqual(u'Lorem ipsum dolor sit amet, consectetuer ' +
u'adipiscing elit. Nullam velit. Vivamus tincidunt, erat ' +
u'in \u2026', excerpt.firstChild.firstChild.nodeValue)
def verify_images(self):
testfile = 'tests/data/filter/excerpt-images.xml'
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
dom = xml.dom.minidom.parseString(output)
excerpt = dom.getElementsByTagName('planet:excerpt')[0]
anchors = excerpt.getElementsByTagName('a')
hrefs = [a.getAttribute('href') for a in anchors]
texts = [a.lastChild.nodeValue for a in anchors]
self.assertEqual(['inner', 'outer1', 'outer2'], hrefs)
self.assertEqual(['bar', 'bar', '<img>'], texts)
def verify_images(self):
testfile = 'tests/data/filter/excerpt-images.xml'
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
dom = xml.dom.minidom.parseString(output)
excerpt = dom.getElementsByTagName('planet:excerpt')[0]
anchors = excerpt.getElementsByTagName('a')
hrefs = [a.getAttribute('href') for a in anchors]
texts = [a.lastChild.nodeValue for a in anchors]
self.assertEqual(['inner','outer1','outer2'], hrefs)
self.assertEqual(['bar','bar','<img>'], texts)
def test_excerpt_lorem_ipsum(self):
testfile = 'tests/data/filter/excerpt-lorem-ipsum.xml'
config.load('tests/data/filter/excerpt-lorem-ipsum.ini')
output = open(testfile).read()
for filter in config.filters():
output = shell.run(filter, output, mode="filter")
dom = xml.dom.minidom.parseString(output)
excerpt = dom.getElementsByTagName('planet:excerpt')[0]
self.assertEqual(
u'Lorem ipsum dolor sit amet, consectetuer ' +
u'adipiscing elit. Nullam velit. Vivamus tincidunt, erat ' +
u'in \u2026', excerpt.firstChild.firstChild.nodeValue)
def test_excerpt_lorem_ipsum_summary(self):
testfile = 'tests/data/filter/excerpt-lorem-ipsum.xml'
config.load('tests/data/filter/excerpt-lorem-ipsum.ini')
config.parser.set('excerpt.py', 'target', 'atom:summary')
with open(testfile) as fp:
output = fp.read()
for each_filter in config.filters():
output = shell.run(each_filter, output, mode="filter")
dom = xml.dom.minidom.parseString(output)
excerpt = dom.getElementsByTagName('summary')[0]
self.assertEqual(
u'Lorem ipsum dolor sit amet, consectetuer ' +
u'adipiscing elit. Nullam velit. Vivamus tincidunt, erat ' +
u'in \u2026', excerpt.firstChild.firstChild.nodeValue)
def data2config(data, cached_config):
if content_type(list).find('opml')>=0:
opml.opml2config(data, cached_config)
elif content_type(list).find('foaf')>=0:
foaf.foaf2config(data, cached_config)
elif content_type(list).find('csv')>=0:
csv_config.csv2config(data, cached_config)
elif content_type(list).find('config')>=0:
cached_config.readfp(data)
else:
from planet import shell
import StringIO
cached_config.readfp(StringIO.StringIO(shell.run(
content_type(list), data.getvalue(), mode="filter")))
if cached_config.sections() in [[], [list]]:
raise Exception
def test_coral_cdn(self):
testfile = 'tests/data/filter/coral_cdn.xml'
filter = 'coral_cdn_filter.py'
output = shell.run(filter, open(testfile).read(), mode="filter")
dom = xml.dom.minidom.parseString(output)
imgsrcs = [
img.getAttribute('src') for img in dom.getElementsByTagName('img')
]
self.assertEqual('http://example.com.nyud.net:8080/foo.png',
imgsrcs[0])
self.assertEqual('http://example.com.1234.nyud.net:8080/foo.png',
imgsrcs[1])
self.assertEqual('http://*****:*****@example.com.nyud.net:8080/foo.png',
imgsrcs[2])
self.assertEqual('http://*****:*****@example.com.1234.nyud.net:8080/foo.png',
imgsrcs[3])
def test_xhtml2html_filter(self):
testfile = 'tests/data/filter/index.html'
filter = 'xhtml2html.plugin?quote_attr_values=True'
output = shell.run(filter, open(testfile).read(), mode="filter")
self.assertTrue(output.find('/>')<0)
self.assertTrue(output.find('</script>')>=0)
