Newer
Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
from xml.sax.saxutils import escape
import sgmllib, time, os, sys, new, urlparse, re
from planet import config, feedparser
import htmltmpl
voids=feedparser._BaseHTMLProcessor.elements_no_end_tag
empty=re.compile(r"<((%s)[^>]*)></\2>" % '|'.join(voids))
class stripHtml(sgmllib.SGMLParser):
"remove all tags from the data"
def __init__(self, data):
sgmllib.SGMLParser.__init__(self)
self.result=''
if isinstance(data, str):
try:
self.feed(data.decode('utf-8'))
except:
self.feed(data)
else:
self.feed(data)
self.close()
def __str__(self):
if isinstance(self.result, unicode):
return self.result.encode('utf-8')
return self.result
def handle_entityref(self, ref):
import htmlentitydefs
if ref in htmlentitydefs.entitydefs:
ref=htmlentitydefs.entitydefs[ref]
if len(ref)==1:
self.result+=unichr(ord(ref))
elif ref.startswith('&#') and ref.endswith(';'):
self.handle_charref(ref[2:-1])
else:
self.result+='&%s;' % ref
else:
self.result+='&%s;' % ref
def handle_charref(self, ref):
try:
if ref.startswith('x'):
self.result+=unichr(int(ref[1:],16))
else:
self.result+=unichr(int(ref))
except:
self.result+='&#%s;' % ref
def handle_data(self, data):
if data: self.result+=data
# Data format mappers
def String(value):
if isinstance(value, unicode): return value.encode('utf-8')
return value
def Plain(value):
return str(stripHtml(value))
def PlanetDate(value):
return time.strftime(config.date_format(), value)
def NewDate(value):
return time.strftime(config.new_date_format(), value)
def Rfc822(value):
return time.strftime("%a, %d %b %Y %H:%M:%S +0000", value)
def Rfc3399(value):
return time.strftime("%Y-%m-%dT%H:%M:%S+00:00", value)
# Map from FeedParser path to Planet tmpl names
Base = [
['author', String, 'author'],
['author_name', String, 'author_detail', 'name'],
['generator', String, 'generator'],
['id', String, 'id'],
['icon', String, 'icon'],
['last_updated_822', Rfc822, 'updated_parsed'],
['last_updated_iso', Rfc3399, 'updated_parsed'],
['last_updated', PlanetDate, 'updated_parsed'],
['link', String, 'link'],
['logo', String, 'logo'],
['rights', String, 'rights_detail', 'value'],
['subtitle', String, 'subtitle_detail', 'value'],
['title', String, 'title_detail', 'value'],
['title_plain', Plain, 'title_detail', 'value'],
['url', String, 'links', {'rel':'self'}, 'href'],
['url', String, 'planet_http_location'],
]
Items = [
['author', String, 'author'],
['author_email', String, 'author_detail', 'email'],
['author_name', String, 'author_detail', 'name'],
['author_uri', String, 'author_detail', 'href'],
['content_language', String, 'content', 0, 'language'],
['content', String, 'summary_detail', 'value'],
['content', String, 'content', 0, 'value'],
['date', PlanetDate, 'published_parsed'],
['date', PlanetDate, 'updated_parsed'],
['date_822', Rfc822, 'published_parsed'],
['date_822', Rfc822, 'updated_parsed'],
['date_iso', Rfc3399, 'published_parsed'],
['date_iso', Rfc3399, 'updated_parsed'],
['enclosure_href', String, 'links', {'rel': 'enclosure'}, 'href'],
['enclosure_length', String, 'links', {'rel': 'enclosure'}, 'length'],
['enclosure_type', String, 'links', {'rel': 'enclosure'}, 'type'],
['id', String, 'id'],
['link', String, 'links', {'rel': 'alternate'}, 'href'],
['new_channel', String, 'source', 'id'],
['new_date', NewDate, 'published_parsed'],
['new_date', NewDate, 'updated_parsed'],
['rights', String, 'rights_detail', 'value'],
['title_language', String, 'title_detail', 'language'],
['title_plain', Plain, 'title_detail', 'value'],
['title', String, 'title_detail', 'value'],
['summary_language', String, 'summary_detail', 'language'],
['updated', PlanetDate, 'updated_parsed'],
['updated_822', Rfc822, 'updated_parsed'],
['updated_iso', Rfc3399, 'updated_parsed'],
['published', PlanetDate, 'published_parsed'],
['published_822', Rfc822, 'published_parsed'],
['published_iso', Rfc3399, 'published_parsed'],
]
# Add additional rules for source information
for rule in Base:
Items.append(['channel_'+rule[0], rule[1], 'source'] + rule[2:])
def tmpl_mapper(source, rules):
"Apply specified rules to the source, and return a template dictionary"
output = {}
for rule in rules:
node = source
for path in rule[2:]:
if isinstance(path, str) and path in node:
if path == 'value':
if node.get('type','')=='text/plain':
node['value'] = escape(node['value'])
node['type'] = 'text/html'
elif node.get('type','')=='application/xhtml+xml':
node['value'] = empty.sub(r"<\1 />", node['value'])
node = node[path]
elif isinstance(path, int):
node = node[path]
elif isinstance(path, dict):
for test in node:
for key, value in path.items():
if test.get(key,None) != value: break
else:
node = test
break
else:
break
else:
break
else:
if node: output[rule[0]] = rule[1](node)
# copy over all planet namespaced elements from parent source
for name,value in source.items():
if name.startswith('planet_'):
output[name[7:]] = String(value)
if not output.get('name') and source.has_key('title_detail'):
output['name'] = Plain(source.title_detail.value)
# copy over all planet namespaced elements from child source element
if 'source' in source:
for name,value in source.source.items():
if name.startswith('planet_'):
output['channel_' + name[7:]] = String(value)
if not output.get('channel_name') and \
source.source.has_key('title_detail'):
output['channel_name'] = Plain(source.source.title_detail.value)
return output
def _end_planet_source(self):
self._end_source()
context = self._getContext()
if not context.has_key('sources'): context['sources'] = []
context.sources.append(context.source)
del context['source']
def template_info(source):
""" get template information from a feedparser output """
# wire in support for planet:source, call feedparser, unplug planet:source
mixin=feedparser._FeedParserMixin
mixin._start_planet_source = mixin._start_source
mixin._end_planet_source = \
new.instancemethod(_end_planet_source, None, mixin)
data=feedparser.parse(source)
del mixin._start_planet_source
del mixin._end_planet_source
# apply rules to convert feed parser output to htmltmpl input
output = {'Channels': [], 'Items': []}
output.update(tmpl_mapper(data.feed, Base))
sources = [(source.get('planet_name',None),source)
for source in data.feed.get('sources',[])]
sources.sort()
for name, feed in sources:
output['Channels'].append(tmpl_mapper(feed, Base))
for entry in data.entries:
output['Items'].append(tmpl_mapper(entry, Items))
# synthesize isPermaLink attribute
for item in output['Items']:
if item.get('id') == item.get('link'):
item['guid_isPermaLink']='true'
else:
item['guid_isPermaLink']='false'
# feed level information
output['generator'] = config.generator_uri()
output['name'] = config.name()
output['link'] = config.link()
output['owner_name'] = config.owner_name()
output['owner_email'] = config.owner_email()
if config.feed():
output['feed'] = config.feed()
output['feedtype'] = config.feed().find('rss')>=0 and 'rss' or 'atom'
# date/time information
date = time.gmtime()
output['date'] = PlanetDate(date)
output['date_iso'] = Rfc3399(date)
output['date_822'] = Rfc822(date)
# remove new_dates and new_channels that aren't "new"
date = channel = None
for item in output['Items']:
if item.has_key('new_date'):
if item['new_date'] == date:
del item['new_date']
else:
date = item['new_date']
if item.has_key('new_channel'):
if item['new_channel'] == channel and not item.has_key('new_date'):
del item['new_channel']
else:
channel = item['new_channel']
return output
def run(script, doc, output_file=None, options={}):
""" process an HTMLTMPL file """
manager = htmltmpl.TemplateManager()
template = manager.prepare(script)
tp = htmltmpl.TemplateProcessor(html_escape=0)
for key,value in template_info(doc).items():
tp.set(key, value)
if output_file:
reluri = os.path.splitext(os.path.basename(output_file))[0]
tp.set('url', urlparse.urljoin(config.link(),reluri))
output = open(output_file, "w")
output.write(tp.process(template))
output.close()
else:
return tp.process(template)
if __name__ == '__main__':
sys.path.insert(0, os.path.split(sys.path[0])[0])
for test in sys.argv[1:]:
from pprint import pprint
pprint(template_info('/home/rubys/bzr/venus/tests/data/filter/tmpl/'+test))