forked from adamlaska/datatracker
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathfeeds.py
More file actions
182 lines (140 loc) · 6.97 KB
/
feeds.py
File metadata and controls
182 lines (140 loc) · 6.97 KB
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
# Copyright The IETF Trust 2007-2020, All Rights Reserved
# -*- coding: utf-8 -*-
import datetime
import unicodedata
from django.contrib.syndication.views import Feed, FeedDoesNotExist
from django.utils.feedgenerator import Atom1Feed, Rss201rev2Feed
from django.urls import reverse as urlreverse
from django.template.defaultfilters import truncatewords, truncatewords_html, date as datefilter
from django.template.defaultfilters import linebreaks # type: ignore
from django.utils.html import strip_tags
from ietf.doc.models import Document, State, LastCallDocEvent, DocEvent
from ietf.doc.utils import augment_events_with_revision
from ietf.doc.templatetags.ietf_filters import format_textarea
def strip_control_characters(s):
"""Remove Unicode control / non-printing characters from a string"""
replacement_char = unicodedata.lookup('REPLACEMENT CHARACTER')
return ''.join(
replacement_char if unicodedata.category(c)[0] == 'C' else c
for c in s
)
class DocumentChangesFeed(Feed):
feed_type = Atom1Feed
def get_object(self, request, name):
return Document.objects.get(docalias__name=name)
def title(self, obj):
return "Changes for %s" % obj.display_name()
def link(self, obj):
if obj is None:
raise FeedDoesNotExist
return urlreverse('ietf.doc.views_doc.document_history', kwargs=dict(name=obj.canonical_name()))
def subtitle(self, obj):
return "History of change entries for %s." % obj.display_name()
def items(self, obj):
events = obj.docevent_set.all().order_by("-time","-id")
augment_events_with_revision(obj, events)
return events
def item_title(self, item):
return strip_control_characters("[%s] %s [rev. %s]" % (
item.by,
truncatewords(strip_tags(item.desc), 15),
item.rev,
))
def item_description(self, item):
return strip_control_characters(truncatewords_html(format_textarea(item.desc), 20))
def item_pubdate(self, item):
return item.time
def item_author_name(self, item):
return str(item.by)
def item_link(self, item):
return urlreverse('ietf.doc.views_doc.document_history', kwargs=dict(name=item.doc.canonical_name())) + "#history-%s" % item.pk
class InLastCallFeed(Feed):
title = "Documents in Last Call"
subtitle = "Announcements for documents in last call."
feed_type = Atom1Feed
author_name = 'IESG Secretary'
link = "/doc/iesg/last-call/"
def items(self):
docs = list(Document.objects.filter(type="draft", states=State.objects.get(type="draft-iesg", slug="lc")))
for d in docs:
d.lc_event = d.latest_event(LastCallDocEvent, type="sent_last_call")
docs = [d for d in docs if d.lc_event]
docs.sort(key=lambda d: d.lc_event.expires)
return docs
def item_title(self, item):
return "%s (%s - %s)" % (item.name,
datefilter(item.lc_event.time, "F j"),
datefilter(item.lc_event.expires, "F j, Y"))
def item_description(self, item):
return strip_control_characters(linebreaks(item.lc_event.desc))
def item_pubdate(self, item):
return item.lc_event.time
class Rss201WithNamespacesFeed(Rss201rev2Feed):
def root_attributes(self):
attrs = super(Rss201WithNamespacesFeed, self).root_attributes()
attrs['xmlns:dcterms'] = 'http://purl.org/dc/terms/'
attrs['xmlns:media'] = 'http://search.yahoo.com/mrss/'
attrs['xmlns:xsi'] = 'http://www.w3.org/2001/XMLSchema-instance'
return attrs
def add_item_elements(self, handler, item):
super(Rss201WithNamespacesFeed, self).add_item_elements(handler, item)
for element_name in ['abstract','accessRights', 'format', 'publisher',]:
dc_item_name = 'dcterms_%s' % element_name
dc_element_name = 'dcterms:%s' % element_name
attrs= {'xsi:type':'dcterms:local'} if element_name == 'publisher' else {}
if dc_item_name in item and item[dc_item_name] is not None:
handler.addQuickElement(dc_element_name,item[dc_item_name],attrs)
if 'doi' in item and item['doi'] is not None:
handler.addQuickElement('dcterms:identifier',item['doi'],{'xsi:type':'dcterms:doi'})
if 'doiuri' in item and item['doiuri'] is not None:
handler.addQuickElement('dcterms:identifier',item['doiuri'],{'xsi:type':'dcterms:uri'})
if 'media_content' in item and item['media_content'] is not None:
handler.startElement('media:content',{'url':item['media_content']['url'],'type':'text/plain'})
handler.addQuickElement('dcterms:isFormatOf',item['media_content']['link_url'])
handler.endElement('media:content')
class RfcFeed(Feed):
feed_type = Rss201WithNamespacesFeed
title = "RFCs"
author_name = "RFC Editor"
link = "https://www.rfc-editor.org/rfc-index2.html"
def get_object(self,request,year=None):
self.year = year
def items(self):
if self.year:
rfc_events = DocEvent.objects.filter(type='published_rfc',time__year=self.year).order_by('-time')
else:
cutoff = datetime.datetime.now() - datetime.timedelta(days=8)
rfc_events = DocEvent.objects.filter(type='published_rfc',time__gte=cutoff).order_by('-time')
results = [(e.doc, e.time) for e in rfc_events]
for doc,time in results:
doc.publication_time = time
return [doc for doc,time in results]
def item_title(self, item):
return "%s : %s" % (item.canonical_name(),item.title)
def item_description(self, item):
return item.abstract
def item_link(self, item):
return "https://rfc-editor.org/info/%s"%item.canonical_name()
def item_pubdate(self, item):
return item.publication_time
def item_extra_kwargs(self, item):
extra = super(RfcFeed, self).item_extra_kwargs(item)
extra.update({'dcterms_accessRights': 'gratis'})
extra.update({'dcterms_format': 'text/html'})
extra.update({'media_content': {'url': 'https://rfc-editor.org/rfc/%s.txt' % item.canonical_name(),
'link_url': self.item_link(item)
}
})
extra.update({'doi':'10.17487/%s' % item.canonical_name().upper()})
extra.update({'doiuri':'http://dx.doi.org/10.17487/%s' % item.canonical_name().upper()})
#TODO
# R104 Publisher (Mandatory - but we need a string from them first)
extra.update({'dcterms_publisher':'rfc-editor.org'})
#TODO MAYBE (Optional stuff)
# R108 License
# R115 Creator/Contributor (which would we use?)
# F305 Checksum (do they use it?) (or should we put the our digital signature in here somewhere?)
# F308 Holder of rights (copyright)
# Stuff we can't do yet given what's in the datatracker
# R118 Keyword
return extra