def test_humane_labels(self):
self.assertEqual(u'Politician',
schema.get_schema('Politician')['label'])
self.assertEqual(
u'Politicians',
schema.humane_property('Politician', 'politicalParty', True))
self.assertEqual(
u'Political Party',
schema.humane_property('Politician', 'politicalParty'))
def rendered_data(self):
try:
data = self.data
except ValueError:
data = {}
data = [
(n, v, schema.humane_property(self.itemtype, n))
for n, v in data.items()
if (n not in ["schema", "name", "datePageModified"])
and (not isinstance(v, schema.Property) or v.ptype != "LongText")
]
if len(data) == 0:
return ""
html = [u'<div class="structured-data">', u"<h1>Structured data</h1>", u"<dl>"]
data = sorted(data, key=operator.itemgetter(2))
render_data_item = (
lambda itemname, itemvalue: u'<dd class="value value-%s"><span itemprop="%s">%s</span></dd>'
% (itemname, itemname, itemvalue.render())
)
for name, value, humane_name in data:
html.append(u'<dt class="key key-%s">%s</dt>' % (name, humane_name))
if type(value) == list:
html += [render_data_item(name, v) for v in value]
else:
html.append(render_data_item(name, value))
html.append(u"</dl></div>")
return "\n".join(html)
def rendered_data(self):
try:
data = self.data
except ValueError:
data = {}
data = [
(n, v, schema.humane_property(self.itemtype, n))
for n, v in data.items()
if (n not in ['schema', 'name', 'datePageModified']) and (not isinstance(v, schema.Property) or v.ptype != 'LongText')
]
if len(data) == 0:
return ''
html = [
u'<div class="structured-data">',
u'<h1>Structured data</h1>',
u'<dl>',
]
data = sorted(data, key=operator.itemgetter(2))
render_data_item = lambda itemname, itemvalue: u'<dd class="value value-%s"><span itemprop="%s">%s</span></dd>' % (itemname, itemname, itemvalue.render())
for name, value, humane_name in data:
html.append(u'<dt class="key key-%s">%s</dt>' % (name, humane_name))
if type(value) == list:
html += [render_data_item(name, v) for v in value]
else:
html.append(render_data_item(name, value))
html.append(u'</dl></div>')
return '\n'.join(html)
def render_body(
cls, title, body, rendered_data="", inlinks={}, related_links_by_score={}, older_title=None, newer_title=None
):
# body
body_parts = [cls.remove_metadata(body)]
# incoming links
if len(inlinks) > 0:
lines = [u"# Incoming Links"]
for i, (rel, links) in enumerate(inlinks.items()):
itemtype, rel = rel.split("/")
lines.append(
u'## %s <span class="hidden">(%s %d)</span>'
% (schema.humane_property(itemtype, rel, True), itemtype, i)
)
# remove dups and sort
links = list(set(links))
links.sort()
lines += [u"* [[%s]]" % t for t in links]
body_parts.append(u"\n".join(lines))
# related links
related_links = related_links_by_score
if len(related_links) > 0:
lines = [u"# Suggested Pages"]
lines += [u"* {{.score::%.3f}} [[%s]]\n{.noli}" % (score, t) for t, score in related_links.items()[:10]]
body_parts.append(u"\n".join(lines))
body_parts.append(u"* [More suggestions...](/+%s)\n{.more-suggestions}" % (cls.title_to_path(title)))
# other posts
if older_title or newer_title:
lines = [u"# Other Posts"]
if newer_title:
lines.append(u"* {{.newer::newer}} [[%s]]\n{.noli}" % newer_title)
if older_title:
lines.append(u"* {{.older::older}} [[%s]]\n{.noli}" % older_title)
body_parts.append(u"\n".join(lines))
# remove yaml/schema block
joined = u"\n".join(body_parts)
joined = re.sub(PageOperationMixin.re_yaml_schema, u"\n", joined)
# render to html
rendered = md.convert(joined)
# add table of contents
rendered = TocGenerator(rendered).add_toc()
# add class for embedded image
rendered = PageOperationMixin.re_img.sub(ur'<\1 class="img-container"><img\2/></\3>', rendered)
# add structured data block
rendered = rendered_data + rendered
return cls.sanitize_html(rendered)
def rendered_body(self):
final = cache.get_rendered_body(self.title)
if final is not None:
return final
# body
body_parts = [WikiPage.remove_metadata(self.body)]
# incoming links
if len(self.inlinks) > 0:
lines = [u'# Incoming Links']
for rel, links in self.inlinks.items():
itemtype, rel = rel.split('/')
humane_rel = schema.humane_property(itemtype, rel, True)
lines.append(u'## %s' % humane_rel)
lines += [u'* [[%s]]' % title for title in set(links)]
body_parts.append(u'\n'.join(lines))
# related links
related_links = self.related_links_by_score
if len(related_links) > 0:
lines = [u'# Suggested Pages']
lines += [u'* {{.score::%.2f}} [[%s]]' % (score, title)
for title, score in related_links.items()[:10]]
body_parts.append(u'\n'.join(lines))
# other posts
if self.older_title or self.newer_title:
lines = [u'# Other Posts']
if self.newer_title:
lines.append(u'* {{.newer::newer}} [[%s]]' % self.newer_title)
if self.older_title:
lines.append(u'* {{.older::older}} [[%s]]' % self.older_title)
body_parts.append(u'\n'.join(lines))
# render to html
rendered = md.convert(u'\n'.join(body_parts))
# add table of contents
final = TocGenerator(rendered).add_toc()
# add class for embedded image
final = WikiPage.re_img.sub(u'<p class="img-container"><img \\1/></p>', final)
# sanitize
if final:
cleaner = Cleaner(safe_attrs_only=False)
final = cleaner.clean_html(final)
cache.set_rendered_body(self.title, final)
return final
def render_body(cls, title, body, rendered_data='', inlinks={}, related_links_by_score={}, older_title=None, newer_title=None):
# body
body_parts = [cls.remove_metadata(body)]
# incoming links
if len(inlinks) > 0:
lines = [u'# Incoming Links']
for i, (rel, links) in enumerate(inlinks.items()):
itemtype, rel = rel.split('/')
lines.append(u'## %s <span class="hidden">(%s %d)</span>' % (schema.humane_property(itemtype, rel, True), itemtype, i))
# remove dups and sort
links = list(set(links))
links.sort()
lines += [u'* [[%s]]' % t for t in links]
body_parts.append(u'\n'.join(lines))
# related links
related_links = related_links_by_score
if len(related_links) > 0:
lines = [u'# Suggested Pages']
lines += [u'* {{.score::%.3f}} [[%s]]\n{.noli}' % (score, t)
for t, score in related_links.items()[:10]]
body_parts.append(u'\n'.join(lines))
body_parts.append(u'* [More suggestions...](/+%s)\n{.more-suggestions}' % (cls.title_to_path(title)))
# other posts
if older_title or newer_title:
lines = [u'# Other Posts']
if newer_title:
lines.append(u'* {{.newer::newer}} [[%s]]\n{.noli}' % newer_title)
if older_title:
lines.append(u'* {{.older::older}} [[%s]]\n{.noli}' % older_title)
body_parts.append(u'\n'.join(lines))
# remove yaml/schema block
joined = u'\n'.join(body_parts)
joined = re.sub(PageOperationMixin.re_yaml_schema, u'\n', joined)
# render to html
rendered = md.convert(joined)
# add table of contents
rendered = TocGenerator(rendered).add_toc()
# add class for embedded image
rendered = PageOperationMixin.re_img.sub(ur'<\1 class="img-container"><img\2/></\3>', rendered)
# add structured data block
rendered = rendered_data + rendered
return cls.sanitize_html(rendered)
def render_body(cls, body, rendered_data='', inlinks={}, related_links_by_score={}, older_title=None, newer_title=None):
# body
body_parts = [cls.remove_metadata(body)]
# incoming links
if len(inlinks) > 0:
lines = [u'# Incoming Links']
for rel, links in inlinks.items():
itemtype, rel = rel.split('/')
lines.append(u'## %s' % schema.humane_property(itemtype, rel, True))
# remove dups and sort
links = list(set(links))
links.sort()
lines += [u'* [[%s]]' % title for title in links]
body_parts.append(u'\n'.join(lines))
# related links
related_links = related_links_by_score
if len(related_links) > 0:
lines = [u'# Suggested Pages']
lines += [u'* {{.score::%.3f}} [[%s]]\n{.noli}' % (score, title)
for title, score in related_links.items()[:10]]
body_parts.append(u'\n'.join(lines))
# other posts
if older_title or newer_title:
lines = [u'# Other Posts']
if newer_title:
lines.append(u'* {{.newer::newer}} [[%s]]\n{.noli}' % newer_title)
if older_title:
lines.append(u'* {{.older::older}} [[%s]]\n{.noli}' % older_title)
body_parts.append(u'\n'.join(lines))
# remove yaml/schema block
joined = u'\n'.join(body_parts)
joined = re.sub(PageOperationMixin.re_yaml_schema, u'\n', joined)
# render to html
rendered = md.convert(joined)
# add table of contents
rendered = TocGenerator(rendered).add_toc()
# add class for embedded image
rendered = PageOperationMixin.re_img.sub(ur'<\1 class="img-container"><img\2/></\3>', rendered)
# add structured data block
rendered = rendered_data + rendered
return cls.sanitize_html(rendered)
def rendered_data(self):
data = [(n, v, schema.humane_property(self.itemtype, n)) for n, v in self.data.items() if n != 'schema']
if len(data) == 1:
# only name and schema?
return ''
html = [
u'<div class="structured-data">',
u'<h1>Structured data</h1>',
u'<dl>',
]
data = sorted(data, key=operator.itemgetter(2))
render_data_item = lambda itemname, itemvalue: u'<dd class="value value-%s"><span itemprop="%s">%s</span></dd>' % (itemname, itemname, itemvalue.render())
for name, value, humane_name in data:
html.append(u'<dt class="key key-%s">%s</dt>' % (name, humane_name))
if type(value) == list:
html += [render_data_item(name, v) for v in value]
else:
html.append(render_data_item(name, value))
html.append(u'</dl></div>')
return '\n'.join(html)
def rendered_data(self):
data = [
(n, v, schema.humane_property(self.itemtype, n, False))
for n, v in self.data.items()
if n not in ["schema", "inlinks", "outlinks"]
]
if len(data) == 1:
# only name and schema?
return ""
html = [u'<div class="structured-data">', u"<h1>Structured data</h1>", u"<dl>"]
data = sorted(data, key=operator.itemgetter(2))
for name, value, humane_name in data:
html.append(u'<dt class="key key-%s">%s</dt>' % (name, humane_name))
if type(value) == list:
for v in value:
html.append(u'<dd class="value value-%s">%s</dd>' % (name, self._render_data_item(name, v)))
else:
html.append(u'<dd class="value value-%s">%s</dd>' % (name, self._render_data_item(name, value)))
html.append(u"</dl></div>")
return "\n".join(html)
def test_humane_property(self):
self.assertEqual('Publications',
schema.humane_property('Book', 'datePublished', True))
self.assertEqual(
'Published date',
schema.humane_property('Book', 'datePublished', False))
def rendered_body(self):
# body
body_parts = [PageOperationMixin.remove_metadata(self.body)]
# incoming links
if len(self.inlinks) > 0:
lines = [u"# Incoming Links"]
for rel, links in self.inlinks.items():
itemtype, rel = rel.split("/")
humane_rel = schema.humane_property(itemtype, rel, True)
lines.append(u"## %s" % humane_rel)
# remove dups and sort
links = list(set(links))
links.sort()
lines += [u"* [[%s]]" % title for title in links]
body_parts.append(u"\n".join(lines))
# related links
related_links = self.related_links_by_score
if len(related_links) > 0:
lines = [u"# Suggested Pages"]
lines += [
u"* {{.score::%.3f}} [[%s]]\n{.noli}" % (score, title) for title, score in related_links.items()[:10]
]
body_parts.append(u"\n".join(lines))
# other posts
if self.older_title or self.newer_title:
lines = [u"# Other Posts"]
if self.newer_title:
lines.append(u"* {{.newer::newer}} [[%s]]\n{.noli}" % self.newer_title)
if self.older_title:
lines.append(u"* {{.older::older}} [[%s]]\n{.noli}" % self.older_title)
body_parts.append(u"\n".join(lines))
# remove yaml/schema block
joined = u"\n".join(body_parts)
joined = re.sub(PageOperationMixin.re_yaml_schema, u"\n", joined)
# render to html
rendered = md.convert(joined)
# add table of contents
rendered = TocGenerator(rendered).add_toc()
# add class for embedded image
rendered = PageOperationMixin.re_img.sub(u'<p class="img-container"><img \\1/></p>', rendered)
# add structured data block
rendered = self.rendered_data + rendered
# sanitize
if rendered:
cleaner = Cleaner(safe_attrs_only=False)
cleaner.host_whitelist = ("www.youtube.com", "player.vimeo.com")
rendered = cleaner.clean_html(rendered)
# remove div wrapper if there is one
if rendered.startswith("<div>"):
rendered = rendered[5:-6]
return rendered
def test_incoming_links(self):
self.assertEqual(u'Related People', schema.humane_property('Person', 'relatedTo', True))
self.assertEqual(u'Children (People)', schema.humane_property('Person', 'parent', True))
def test_humane_labels(self):
self.assertEqual(u'Politician', schema.get_schema('Politician')['label'])
self.assertEqual(u'Politicians', schema.humane_property('Politician', 'politicalParty', True))
self.assertEqual(u'Political Party', schema.humane_property('Politician', 'politicalParty'))
def test_humane_property(self):
self.assertEqual('Published Books',
schema.humane_property('Book', 'datePublished', True))
self.assertEqual('Date Published',
schema.humane_property('Book', 'datePublished'))
def test_humane_property(self):
self.assertEqual('Published Books',
schema.humane_property('Book', 'datePublished', True))
self.assertEqual('Date Published',
schema.humane_property('Book', 'datePublished'))
def test_incoming_links(self):
self.assertEqual(u'Related People',
schema.humane_property('Person', 'relatedTo', True))
self.assertEqual(u'Children (People)',
schema.humane_property('Person', 'parent', True))
def test_humane_property(self):
self.assertEqual('Publications',
schema.humane_property('Book', 'datePublished', True))
self.assertEqual('Published date',
schema.humane_property('Book', 'datePublished', False))
def test_humane_property(self):
self.assertEqual("Publications", schema.humane_property("Book", "datePublished", True))
self.assertEqual("Published date", schema.humane_property("Book", "datePublished", False))