whistle 0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/History.txt +3 -0
- data/README.txt +38 -0
- data/bin/whistle +90 -0
- data/lib/config.rb +19 -0
- data/lib/phash.rb +16 -0
- data/lib/relay.rb +24 -0
- data/lib/resource.rb +113 -0
- data/lib/ssl_patch.rb +15 -0
- data/lib/switchbox.rb +54 -0
- data/lib/time_ext.rb +30 -0
- data/lib/version.rb +3 -0
- data/sample/config.yml +12 -0
- data/vendor/rscm-0.5.1-patched-stripped/README +218 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm.rb +14 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/abstract_log_parser.rb +35 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/base.rb +289 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/command_line.rb +146 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/difftool.rb +44 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/line_editor.rb +46 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/mockit.rb +157 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/parser.rb +39 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/path_converter.rb +60 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/platform.rb +26 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/revision.rb +103 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/revision_file.rb +85 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/revision_poller.rb +93 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/revisions.rb +79 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/clearcase.rb +182 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/cvs.rb +374 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/cvs_log_parser.rb +154 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/darcs.rb +120 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/darcs_log_parser.rb +65 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/monotone.rb +338 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/monotone_log_parser.rb +109 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/mooky.rb +6 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/perforce.rb +216 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/star_team.rb +104 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/subversion.rb +397 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/scm/subversion_log_parser.rb +165 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/tempdir.rb +17 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/time_ext.rb +11 -0
- data/vendor/rscm-0.5.1-patched-stripped/lib/rscm/version.rb +13 -0
- data/vendor/ruby-feedparser-0.5-stripped/README +14 -0
- data/vendor/ruby-feedparser-0.5-stripped/lib/feedparser.rb +28 -0
- data/vendor/ruby-feedparser-0.5-stripped/lib/feedparser/feedparser.rb +300 -0
- data/vendor/ruby-feedparser-0.5-stripped/lib/feedparser/filesizes.rb +12 -0
- data/vendor/ruby-feedparser-0.5-stripped/lib/feedparser/html-output.rb +126 -0
- data/vendor/ruby-feedparser-0.5-stripped/lib/feedparser/html2text-parser.rb +409 -0
- data/vendor/ruby-feedparser-0.5-stripped/lib/feedparser/rexml_patch.rb +28 -0
- data/vendor/ruby-feedparser-0.5-stripped/lib/feedparser/sgml-parser.rb +332 -0
- data/vendor/ruby-feedparser-0.5-stripped/lib/feedparser/text-output.rb +83 -0
- data/vendor/ruby-feedparser-0.5-stripped/lib/feedparser/textconverters.rb +120 -0
- metadata +132 -0
|
@@ -0,0 +1,165 @@
|
|
|
1
|
+
require 'rscm/parser'
|
|
2
|
+
require 'rscm/revision'
|
|
3
|
+
require 'rscm/revisions'
|
|
4
|
+
require 'rscm/revision_file'
|
|
5
|
+
require 'time'
|
|
6
|
+
|
|
7
|
+
module RSCM
|
|
8
|
+
|
|
9
|
+
class SubversionLogParser
|
|
10
|
+
def initialize(io, url, exclude_below_and_including=nil, exclude_above_and_including=nil, path=nil)
|
|
11
|
+
@io = io
|
|
12
|
+
@revision_parser = SubversionLogEntryParser.new(url, path)
|
|
13
|
+
@exclude_below_and_including = exclude_below_and_including
|
|
14
|
+
@exclude_above_and_including = exclude_above_and_including
|
|
15
|
+
end
|
|
16
|
+
|
|
17
|
+
def parse_revisions(&line_proc)
|
|
18
|
+
# skip over the first ------
|
|
19
|
+
@revision_parser.parse(@io, true, &line_proc)
|
|
20
|
+
revisions = Revisions.new
|
|
21
|
+
while(!@io.eof?)
|
|
22
|
+
revision = @revision_parser.parse(@io, &line_proc)
|
|
23
|
+
unless(revision.nil?)
|
|
24
|
+
# Filter out the lower bound to avoid inclusiveness of the lower bound (see contract)
|
|
25
|
+
# We're doing this instead of increasing the from_identifer with 1, since that causes an error.
|
|
26
|
+
too_low = false
|
|
27
|
+
too_high = false
|
|
28
|
+
next if revision.time.nil?
|
|
29
|
+
if(@exclude_below_and_including.is_a? Time)
|
|
30
|
+
too_low = revision.time <= @exclude_below_and_including
|
|
31
|
+
elsif(@exclude_below_and_including.is_a? Numeric)
|
|
32
|
+
too_low = revision.identifier <= @exclude_below_and_including
|
|
33
|
+
end
|
|
34
|
+
|
|
35
|
+
if(@exclude_above_and_including.is_a? Time)
|
|
36
|
+
too_high = revision.time >= @exclude_above_and_including
|
|
37
|
+
elsif(@exclude_above_and_including.is_a? Numeric)
|
|
38
|
+
too_high = revision.identifier >= @exclude_above_and_including
|
|
39
|
+
end
|
|
40
|
+
revisions.add(revision) unless too_low || too_high
|
|
41
|
+
end
|
|
42
|
+
end
|
|
43
|
+
revisions
|
|
44
|
+
end
|
|
45
|
+
end
|
|
46
|
+
|
|
47
|
+
class SubversionLogEntryParser < Parser
|
|
48
|
+
|
|
49
|
+
def initialize(url, path=nil)
|
|
50
|
+
super(/^------------------------------------------------------------------------/)
|
|
51
|
+
@url = url
|
|
52
|
+
@path = path
|
|
53
|
+
end
|
|
54
|
+
|
|
55
|
+
def parse(io, skip_line_parsing=false, &line_proc)
|
|
56
|
+
# We have to trim off the last newline - it's not meant to be part of the message
|
|
57
|
+
revision = super
|
|
58
|
+
revision.message = revision.message[0..-2] if revision
|
|
59
|
+
revision
|
|
60
|
+
end
|
|
61
|
+
|
|
62
|
+
def relative_path(url, path_from_root)
|
|
63
|
+
path_from_root = path_from_root.chomp
|
|
64
|
+
url_tokens = url.split('/')
|
|
65
|
+
path_from_root_tokens = path_from_root.split('/')
|
|
66
|
+
|
|
67
|
+
max_similar = path_from_root_tokens.length
|
|
68
|
+
while(max_similar > 0)
|
|
69
|
+
url = url_tokens[-max_similar..-1]
|
|
70
|
+
path = path_from_root_tokens[0..max_similar-1]
|
|
71
|
+
if(url == path)
|
|
72
|
+
break
|
|
73
|
+
end
|
|
74
|
+
max_similar -= 1
|
|
75
|
+
end
|
|
76
|
+
|
|
77
|
+
if(max_similar == 0)
|
|
78
|
+
if(@path.nil? || @path == "")
|
|
79
|
+
path_from_root
|
|
80
|
+
else
|
|
81
|
+
nil
|
|
82
|
+
end
|
|
83
|
+
else
|
|
84
|
+
path_from_root_tokens[max_similar..-1].join("/")
|
|
85
|
+
end
|
|
86
|
+
end
|
|
87
|
+
|
|
88
|
+
protected
|
|
89
|
+
|
|
90
|
+
def parse_line(line)
|
|
91
|
+
if(@revision.nil?)
|
|
92
|
+
parse_header(line)
|
|
93
|
+
elsif(line.strip == "")
|
|
94
|
+
@parse_state = :parse_message
|
|
95
|
+
elsif(line =~ /Changed paths/)
|
|
96
|
+
@parse_state = :parse_files
|
|
97
|
+
elsif(@parse_state == :parse_files)
|
|
98
|
+
file = parse_file(line)
|
|
99
|
+
if(file && file.path)
|
|
100
|
+
previously_added_file = @revision[-1]
|
|
101
|
+
if(previously_added_file)
|
|
102
|
+
# remove previous revision_file if it's a dir
|
|
103
|
+
previous_tokens = previously_added_file.path.split("/")
|
|
104
|
+
current_tokens = file.path.split("/")
|
|
105
|
+
current_tokens.pop
|
|
106
|
+
if(previous_tokens == current_tokens)
|
|
107
|
+
@revision.pop
|
|
108
|
+
end
|
|
109
|
+
end
|
|
110
|
+
@revision.add file
|
|
111
|
+
end
|
|
112
|
+
elsif(@parse_state == :parse_message)
|
|
113
|
+
@revision.message << line.chomp << "\n"
|
|
114
|
+
end
|
|
115
|
+
end
|
|
116
|
+
|
|
117
|
+
def next_result
|
|
118
|
+
result = @revision
|
|
119
|
+
@revision = nil
|
|
120
|
+
result
|
|
121
|
+
end
|
|
122
|
+
|
|
123
|
+
private
|
|
124
|
+
|
|
125
|
+
STATES = {"M" => RevisionFile::MODIFIED, "A" => RevisionFile::ADDED, "D" => RevisionFile::DELETED} unless defined? STATES
|
|
126
|
+
|
|
127
|
+
def parse_header(line)
|
|
128
|
+
@revision = Revision.new
|
|
129
|
+
@revision.message = ""
|
|
130
|
+
revision, developer, time, the_rest = line.split("|")
|
|
131
|
+
@revision.identifier = revision.strip[1..-1].to_i unless revision.nil?
|
|
132
|
+
developer.strip!
|
|
133
|
+
@revision.developer = developer unless developer.nil? || developer == "(no author)"
|
|
134
|
+
time.strip!
|
|
135
|
+
@revision.time = Time.parse(time).utc unless time.nil? || time == "(no date)"
|
|
136
|
+
end
|
|
137
|
+
|
|
138
|
+
def parse_file(line)
|
|
139
|
+
file = RevisionFile.new
|
|
140
|
+
path_from_root = nil
|
|
141
|
+
if(line =~ /^ [M|A|D|R] ([^\s]+) \(from (.*)\)/)
|
|
142
|
+
path_from_root = $1
|
|
143
|
+
file.status = RevisionFile::MOVED
|
|
144
|
+
elsif(line =~ /^ ([M|A|D|R]) (.+)$/)
|
|
145
|
+
status = $1
|
|
146
|
+
path_from_root = $2
|
|
147
|
+
file.status = STATES[status]
|
|
148
|
+
else
|
|
149
|
+
raise "could not parse file line: '#{line}'"
|
|
150
|
+
end
|
|
151
|
+
|
|
152
|
+
path_from_root.gsub!(/\\/, "/")
|
|
153
|
+
path_from_root = path_from_root[1..-1]
|
|
154
|
+
rp = relative_path(@url, path_from_root)
|
|
155
|
+
return if rp.nil?
|
|
156
|
+
|
|
157
|
+
file.path = rp
|
|
158
|
+
file.native_revision_identifier = @revision.identifier
|
|
159
|
+
# http://jira.codehaus.org/browse/DC-204
|
|
160
|
+
file.previous_native_revision_identifier = file.native_revision_identifier.to_i - 1;
|
|
161
|
+
file
|
|
162
|
+
end
|
|
163
|
+
end
|
|
164
|
+
|
|
165
|
+
end
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
require 'fileutils'
|
|
2
|
+
|
|
3
|
+
module RSCM
|
|
4
|
+
|
|
5
|
+
def method_name
|
|
6
|
+
/\`([^\']+)\'/.match(caller.first)[1]
|
|
7
|
+
end
|
|
8
|
+
|
|
9
|
+
def new_temp_dir(suffix="", basedir=File.dirname(__FILE__) + "/../../target")
|
|
10
|
+
identifier = identifier.to_s
|
|
11
|
+
identifier.gsub!(/\(|:|\)/, '_')
|
|
12
|
+
dir = "#{basedir}/temp_#{identifier}_#{Time.new.to_i}#{suffix}"
|
|
13
|
+
FileUtils.mkdir_p(dir)
|
|
14
|
+
dir
|
|
15
|
+
end
|
|
16
|
+
module_function :new_temp_dir
|
|
17
|
+
end
|
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
Ruby-Feedparser
|
|
2
|
+
-----------------
|
|
3
|
+
by Lucas Nussbaum <lucas@lucas-nussbaum.net>
|
|
4
|
+
|
|
5
|
+
Currently, all the information is provided on
|
|
6
|
+
|
|
7
|
+
http://home.gna.org/ruby-feedparser/
|
|
8
|
+
|
|
9
|
+
If you need to ask questions, feel free to ask them on the
|
|
10
|
+
ruby-feedparser-devel@gna.org mailing list.
|
|
11
|
+
|
|
12
|
+
Ruby-Feedparser is released under the Ruby license (see the LICENSE file),
|
|
13
|
+
which is compatible with the GNU GPL (see the COPYING file) via an explicit
|
|
14
|
+
dual-licensing clause.
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
# =Ruby-feedparser - ATOM/RSS feed parser for Ruby
|
|
2
|
+
# License:: Ruby's license (see the LICENSE file) or GNU GPL, at your option.
|
|
3
|
+
# Website::http://home.gna.org/ruby-feedparser/
|
|
4
|
+
#
|
|
5
|
+
# ==Introduction
|
|
6
|
+
#
|
|
7
|
+
# Ruby-Feedparser is an RSS and Atom parser for Ruby.
|
|
8
|
+
# Ruby-feedparser is :
|
|
9
|
+
# * based on REXML
|
|
10
|
+
# * built for robustness : most feeds are not valid, a parser can't ignore that
|
|
11
|
+
# * fully unit-tested
|
|
12
|
+
# * easy to use (it can output text or HTML easily)
|
|
13
|
+
#
|
|
14
|
+
# ==Example
|
|
15
|
+
# require 'net/http'
|
|
16
|
+
# require 'feedparser'
|
|
17
|
+
# require 'uri'
|
|
18
|
+
# s = Net::HTTP::get URI::parse('http://rss.slashdot.org/Slashdot/slashdot')
|
|
19
|
+
# f = FeedParser::Feed::new(s)
|
|
20
|
+
# f.title
|
|
21
|
+
# => "Slashdot"
|
|
22
|
+
# f.items.each { |i| puts i.title }
|
|
23
|
+
# [...]
|
|
24
|
+
# require 'feedparser/html-output'
|
|
25
|
+
# f.items.each { |i| puts i.to_html }
|
|
26
|
+
#
|
|
27
|
+
|
|
28
|
+
require 'feedparser/feedparser'
|
|
@@ -0,0 +1,300 @@
|
|
|
1
|
+
require 'rexml/document'
|
|
2
|
+
require 'time'
|
|
3
|
+
require 'feedparser/textconverters'
|
|
4
|
+
require 'feedparser/rexml_patch'
|
|
5
|
+
require 'feedparser/text-output'
|
|
6
|
+
require 'base64'
|
|
7
|
+
|
|
8
|
+
module FeedParser
|
|
9
|
+
|
|
10
|
+
VERSION = "0.5"
|
|
11
|
+
|
|
12
|
+
class UnknownFeedTypeException < RuntimeError
|
|
13
|
+
end
|
|
14
|
+
|
|
15
|
+
# an RSS/Atom feed
|
|
16
|
+
class Feed
|
|
17
|
+
attr_reader :type, :title, :link, :description, :creator, :encoding, :items
|
|
18
|
+
|
|
19
|
+
# REXML::Element for this feed.
|
|
20
|
+
attr_reader :xml
|
|
21
|
+
|
|
22
|
+
# parse str to build a Feed
|
|
23
|
+
def initialize(str = nil)
|
|
24
|
+
parse(str) if str
|
|
25
|
+
end
|
|
26
|
+
|
|
27
|
+
# Determines all the fields using a string containing an
|
|
28
|
+
# XML document
|
|
29
|
+
def parse(str)
|
|
30
|
+
# Dirty hack: some feeds contain the & char. It must be changed to &
|
|
31
|
+
str.gsub!(/&(\s+)/, '&\1')
|
|
32
|
+
doc = REXML::Document.new(str)
|
|
33
|
+
@xml = doc.root
|
|
34
|
+
# get feed info
|
|
35
|
+
@encoding = doc.encoding
|
|
36
|
+
@title,@link,@description,@creator = nil
|
|
37
|
+
@items = []
|
|
38
|
+
if doc.root.elements['channel'] || doc.root.elements['rss:channel']
|
|
39
|
+
@type = "rss"
|
|
40
|
+
# We have a RSS feed!
|
|
41
|
+
# Title
|
|
42
|
+
if (e = doc.root.elements['channel/title'] ||
|
|
43
|
+
doc.root.elements['rss:channel/rss:title']) && e.text
|
|
44
|
+
@title = e.text.unescape_html.toUTF8(@encoding).rmWhiteSpace!
|
|
45
|
+
end
|
|
46
|
+
# Link
|
|
47
|
+
if (e = doc.root.elements['channel/link'] ||
|
|
48
|
+
doc.root.elements['rss:channel/rss:link']) && e.text
|
|
49
|
+
@link = e.text.rmWhiteSpace!
|
|
50
|
+
end
|
|
51
|
+
# Description
|
|
52
|
+
if (e = doc.root.elements['channel/description'] ||
|
|
53
|
+
doc.root.elements['rss:channel/rss:description']) && e.text
|
|
54
|
+
@description = e.text.toUTF8(@encoding).rmWhiteSpace!
|
|
55
|
+
end
|
|
56
|
+
# Creator
|
|
57
|
+
if ((e = doc.root.elements['channel/dc:creator']) && e.text) ||
|
|
58
|
+
((e = doc.root.elements['channel/author'] ||
|
|
59
|
+
doc.root.elements['rss:channel/rss:author']) && e.text)
|
|
60
|
+
@creator = e.text.unescape_html.toUTF8(@encoding).rmWhiteSpace!
|
|
61
|
+
end
|
|
62
|
+
# Items
|
|
63
|
+
if doc.root.elements['channel/item']
|
|
64
|
+
query = 'channel/item'
|
|
65
|
+
elsif doc.root.elements['item']
|
|
66
|
+
query = 'item'
|
|
67
|
+
elsif doc.root.elements['rss:channel/rss:item']
|
|
68
|
+
query = 'rss:channel/rss:item'
|
|
69
|
+
else
|
|
70
|
+
query = 'rss:item'
|
|
71
|
+
end
|
|
72
|
+
doc.root.each_element(query) { |e| @items << RSSItem::new(e, self) }
|
|
73
|
+
|
|
74
|
+
elsif doc.root.elements['/feed']
|
|
75
|
+
# We have an ATOM feed!
|
|
76
|
+
@type = "atom"
|
|
77
|
+
# Title
|
|
78
|
+
if (e = doc.root.elements['/feed/title']) && e.text
|
|
79
|
+
@title = e.text.unescape_html.toUTF8(@encoding).rmWhiteSpace!
|
|
80
|
+
end
|
|
81
|
+
# Link
|
|
82
|
+
doc.root.each_element('/feed/link') do |e|
|
|
83
|
+
if e.attribute('type') and (
|
|
84
|
+
e.attribute('type').value == 'text/html' or
|
|
85
|
+
e.attribute('type').value == 'application/xhtml' or
|
|
86
|
+
e.attribute('type').value == 'application/xhtml+xml')
|
|
87
|
+
if (h = e.attribute('href')) && h
|
|
88
|
+
@link = h.value.rmWhiteSpace!
|
|
89
|
+
end
|
|
90
|
+
end
|
|
91
|
+
end
|
|
92
|
+
# Description
|
|
93
|
+
if e = doc.root.elements['/feed/info']
|
|
94
|
+
e = e.elements['div'] || e
|
|
95
|
+
@description = e.to_s.toUTF8(@encoding).rmWhiteSpace!
|
|
96
|
+
end
|
|
97
|
+
# Items
|
|
98
|
+
doc.root.each_element('/feed/entry') do |e|
|
|
99
|
+
@items << AtomItem::new(e, self)
|
|
100
|
+
end
|
|
101
|
+
else
|
|
102
|
+
raise UnknownFeedTypeException::new
|
|
103
|
+
end
|
|
104
|
+
end
|
|
105
|
+
|
|
106
|
+
def to_s(localtime = true)
|
|
107
|
+
s = ''
|
|
108
|
+
s += "Type: #{@type}\n"
|
|
109
|
+
s += "Encoding: #{@encoding}\n"
|
|
110
|
+
s += "Title: #{@title}\n"
|
|
111
|
+
s += "Link: #{@link}\n"
|
|
112
|
+
s += "Description: #{@description}\n"
|
|
113
|
+
s += "Creator: #{@creator}\n"
|
|
114
|
+
s += "\n"
|
|
115
|
+
@items.each { |i| s += i.to_s(localtime) }
|
|
116
|
+
s
|
|
117
|
+
end
|
|
118
|
+
end
|
|
119
|
+
|
|
120
|
+
# an Item from a feed
|
|
121
|
+
class FeedItem
|
|
122
|
+
attr_accessor :title, :link, :content, :date, :creator, :subject,
|
|
123
|
+
:category, :cacheditem
|
|
124
|
+
|
|
125
|
+
# The item's enclosures childs. An array of (url, length, type) triplets.
|
|
126
|
+
attr_accessor :enclosures
|
|
127
|
+
|
|
128
|
+
attr_reader :feed
|
|
129
|
+
|
|
130
|
+
# REXML::Element for this item
|
|
131
|
+
attr_reader :xml
|
|
132
|
+
|
|
133
|
+
def initialize(item = nil, feed = nil)
|
|
134
|
+
@xml = item
|
|
135
|
+
@feed = feed
|
|
136
|
+
@title, @link, @content, @date, @creator, @subject, @category = nil
|
|
137
|
+
@enclosures = []
|
|
138
|
+
parse(item) if item
|
|
139
|
+
end
|
|
140
|
+
|
|
141
|
+
def parse(item)
|
|
142
|
+
raise "parse() should be implemented by subclasses!"
|
|
143
|
+
end
|
|
144
|
+
|
|
145
|
+
def to_s(localtime = true)
|
|
146
|
+
s = "--------------------------------\n" +
|
|
147
|
+
"Title: #{@title}\nLink: #{@link}\n"
|
|
148
|
+
if localtime or @date.nil?
|
|
149
|
+
s += "Date: #{@date.to_s}\n"
|
|
150
|
+
else
|
|
151
|
+
s += "Date: #{@date.getutc.to_s}\n"
|
|
152
|
+
end
|
|
153
|
+
s += "Creator: #{@creator}\n" +
|
|
154
|
+
"Subject: #{@subject}\nCategory: #{@category}\nContent:\n#{content}\n"
|
|
155
|
+
if defined?(@enclosures) and @enclosures.length > 0
|
|
156
|
+
s2 = "Enclosures:\n"
|
|
157
|
+
@enclosures.each do |e|
|
|
158
|
+
s2 += e.join(' ') + "\n"
|
|
159
|
+
end
|
|
160
|
+
s += s2
|
|
161
|
+
end
|
|
162
|
+
return s
|
|
163
|
+
end
|
|
164
|
+
end
|
|
165
|
+
|
|
166
|
+
class RSSItem < FeedItem
|
|
167
|
+
|
|
168
|
+
|
|
169
|
+
def parse(item)
|
|
170
|
+
# Title. If no title, use the pubDate as fallback.
|
|
171
|
+
if ((e = item.elements['title'] || item.elements['rss:title']) &&
|
|
172
|
+
e.text) ||
|
|
173
|
+
((e = item.elements['pubDate'] || item.elements['rss:pubDate']) &&
|
|
174
|
+
e.text)
|
|
175
|
+
@title = e.text.unescape_html.toUTF8(@feed.encoding).html2text.rmWhiteSpace!
|
|
176
|
+
end
|
|
177
|
+
# Link
|
|
178
|
+
if ((e = item.elements['link'] || item.elements['rss:link']) && e.text)||
|
|
179
|
+
(e = item.elements['guid'] || item.elements['rss:guid'] and
|
|
180
|
+
not (e.attribute('isPermaLink') and
|
|
181
|
+
e.attribute('isPermaLink').value == 'false'))
|
|
182
|
+
@link = e.text.rmWhiteSpace!
|
|
183
|
+
end
|
|
184
|
+
# Content
|
|
185
|
+
if (e = item.elements['content:encoded']) ||
|
|
186
|
+
(e = item.elements['description'] || item.elements['rss:description'])
|
|
187
|
+
@content = FeedParser::getcontent(e, @feed)
|
|
188
|
+
end
|
|
189
|
+
# Date
|
|
190
|
+
if e = item.elements['dc:date'] || item.elements['pubDate'] ||
|
|
191
|
+
item.elements['rss:pubDate']
|
|
192
|
+
begin
|
|
193
|
+
@date = Time::xmlschema(e.text)
|
|
194
|
+
rescue
|
|
195
|
+
begin
|
|
196
|
+
@date = Time::rfc2822(e.text)
|
|
197
|
+
rescue
|
|
198
|
+
begin
|
|
199
|
+
@date = Time::parse(e.text)
|
|
200
|
+
rescue
|
|
201
|
+
@date = nil
|
|
202
|
+
end
|
|
203
|
+
end
|
|
204
|
+
end
|
|
205
|
+
end
|
|
206
|
+
# Creator
|
|
207
|
+
@creator = @feed.creator
|
|
208
|
+
if (e = item.elements['dc:creator'] || item.elements['author'] ||
|
|
209
|
+
item.elements['rss:author']) && e.text
|
|
210
|
+
@creator = e.text.unescape_html.toUTF8(@feed.encoding).rmWhiteSpace!
|
|
211
|
+
end
|
|
212
|
+
# Subject
|
|
213
|
+
if (e = item.elements['dc:subject']) && e.text
|
|
214
|
+
@subject = e.text.unescape_html.toUTF8(@feed.encoding).rmWhiteSpace!
|
|
215
|
+
end
|
|
216
|
+
# Category
|
|
217
|
+
if (e = item.elements['dc:category'] || item.elements['category'] ||
|
|
218
|
+
item.elements['rss:category']) && e.text
|
|
219
|
+
@category = e.text.unescape_html.toUTF8(@feed.encoding).rmWhiteSpace!
|
|
220
|
+
end
|
|
221
|
+
# Enclosures
|
|
222
|
+
item.each_element('enclosure') do |e|
|
|
223
|
+
url = e.attribute('url').value if e.attribute('url')
|
|
224
|
+
length = e.attribute('length').value if e.attribute('length')
|
|
225
|
+
type = e.attribute('type').value if e.attribute('type')
|
|
226
|
+
@enclosures << [ url, length, type ] if url
|
|
227
|
+
end
|
|
228
|
+
end
|
|
229
|
+
end
|
|
230
|
+
|
|
231
|
+
class AtomItem < FeedItem
|
|
232
|
+
def parse(item)
|
|
233
|
+
# Title
|
|
234
|
+
if (e = item.elements['title']) && e.text
|
|
235
|
+
@title = e.text.unescape_html.toUTF8(@feed.encoding).html2text.rmWhiteSpace!
|
|
236
|
+
end
|
|
237
|
+
# Link
|
|
238
|
+
item.each_element('link') do |e|
|
|
239
|
+
if (h = e.attribute('href')) && h.value
|
|
240
|
+
@link = h.value
|
|
241
|
+
end
|
|
242
|
+
end
|
|
243
|
+
# Content
|
|
244
|
+
if e = item.elements['content'] || item.elements['summary']
|
|
245
|
+
if (e.attribute('mode') and e.attribute('mode').value == 'escaped') &&
|
|
246
|
+
e.text
|
|
247
|
+
@content = e.text.toUTF8(@feed.encoding).rmWhiteSpace!
|
|
248
|
+
else
|
|
249
|
+
@content = FeedParser::getcontent(e, @feed)
|
|
250
|
+
end
|
|
251
|
+
end
|
|
252
|
+
# Date
|
|
253
|
+
if (e = item.elements['issued'] || e = item.elements['created'] || e = item.elements['updated'] || e = item.elements['published']) && e.text
|
|
254
|
+
begin
|
|
255
|
+
@date = Time::xmlschema(e.text)
|
|
256
|
+
rescue
|
|
257
|
+
begin
|
|
258
|
+
@date = Time::rfc2822(e.text)
|
|
259
|
+
rescue
|
|
260
|
+
begin
|
|
261
|
+
@date = Time::parse(e.text)
|
|
262
|
+
rescue
|
|
263
|
+
@date = nil
|
|
264
|
+
end
|
|
265
|
+
end
|
|
266
|
+
end
|
|
267
|
+
end
|
|
268
|
+
# Creator
|
|
269
|
+
@creator = @feed.creator
|
|
270
|
+
if (e = item.elements['author/name']) && e.text
|
|
271
|
+
@creator = e.text.unescape_html.toUTF8(@feed.encoding).rmWhiteSpace!
|
|
272
|
+
end
|
|
273
|
+
end
|
|
274
|
+
end
|
|
275
|
+
|
|
276
|
+
def FeedParser::getcontent(e, feed = nil)
|
|
277
|
+
encoding = feed ? feed.encoding : 'utf-8'
|
|
278
|
+
children = e.children.reject do |i|
|
|
279
|
+
i.class == REXML::Text and i.to_s.chomp == ''
|
|
280
|
+
end
|
|
281
|
+
if children.length > 1
|
|
282
|
+
s = ''
|
|
283
|
+
children.each do |c|
|
|
284
|
+
s += c.to_s if c.class != REXML::Comment
|
|
285
|
+
end
|
|
286
|
+
return s.toUTF8(encoding).rmWhiteSpace!.text2html(feed)
|
|
287
|
+
elsif children.length == 1
|
|
288
|
+
c = children[0]
|
|
289
|
+
if c.class == REXML::Text
|
|
290
|
+
return e.text.toUTF8(encoding).rmWhiteSpace!.text2html(feed)
|
|
291
|
+
else
|
|
292
|
+
if c.class == REXML::CData
|
|
293
|
+
return c.to_s.toUTF8(encoding).rmWhiteSpace!.text2html(feed)
|
|
294
|
+
elsif c.text
|
|
295
|
+
return c.text.toUTF8(encoding).text2html(feed)
|
|
296
|
+
end
|
|
297
|
+
end
|
|
298
|
+
end
|
|
299
|
+
end
|
|
300
|
+
end
|