htmlclipping 0.1.6 → 0.1.7
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/lib/htmlclipping.rb +11 -6
- data/lib/htmlclipping.rb~ +5 -2
- metadata +2 -2
data/lib/htmlclipping.rb
CHANGED
|
@@ -33,7 +33,7 @@
|
|
|
33
33
|
require 'iconv'
|
|
34
34
|
|
|
35
35
|
class HtmlClipping
|
|
36
|
-
Version = '0.1.
|
|
36
|
+
Version = '0.1.7'
|
|
37
37
|
|
|
38
38
|
# html:: The HTML of the referring web page.
|
|
39
39
|
# referred_uri:: The URI that is being referred to.
|
|
@@ -57,11 +57,16 @@ class HtmlClipping
|
|
|
57
57
|
|
|
58
58
|
# Returns the clipping as a string suitable for use as XML text.
|
|
59
59
|
def to_s
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
60
|
+
regexes = [
|
|
61
|
+
%r{<body[^>]*>(.*)</body>}mi, %r{<body[^>]*>(.*)}mi,
|
|
62
|
+
%r{</head>(.*)</(body|html)>}mi
|
|
63
|
+
]
|
|
64
|
+
to_detokenize = nil
|
|
65
|
+
until to_detokenize or regexes.empty?
|
|
66
|
+
regex = regexes.shift
|
|
67
|
+
if @contents =~ regex
|
|
68
|
+
to_detokenize = $1
|
|
69
|
+
end
|
|
65
70
|
end
|
|
66
71
|
excerpt = Detokenizer.new( to_detokenize, @referred_uri ).execute
|
|
67
72
|
excerpt = Clipper.new( excerpt, @excerpt_limit ).execute
|
data/lib/htmlclipping.rb~
CHANGED
|
@@ -33,7 +33,7 @@
|
|
|
33
33
|
require 'iconv'
|
|
34
34
|
|
|
35
35
|
class HtmlClipping
|
|
36
|
-
Version = '0.1.
|
|
36
|
+
Version = '0.1.6'
|
|
37
37
|
|
|
38
38
|
# html:: The HTML of the referring web page.
|
|
39
39
|
# referred_uri:: The URI that is being referred to.
|
|
@@ -43,7 +43,7 @@ class HtmlClipping
|
|
|
43
43
|
if @contents =~ %r{<meta[^>]*charset=("|')?(.*?)('|")}i
|
|
44
44
|
begin
|
|
45
45
|
@converter = Iconv.new( 'utf8', $2 )
|
|
46
|
-
rescue Errno::EINVAL
|
|
46
|
+
rescue Errno::EINVAL, Iconv::InvalidEncoding
|
|
47
47
|
# skip it
|
|
48
48
|
end
|
|
49
49
|
end
|
|
@@ -63,8 +63,11 @@ class HtmlClipping
|
|
|
63
63
|
@contents =~ %r{<body[^>]*>(.*)}mi
|
|
64
64
|
to_detokenize = $1
|
|
65
65
|
end
|
|
66
|
+
p to_detokenize
|
|
66
67
|
excerpt = Detokenizer.new( to_detokenize, @referred_uri ).execute
|
|
68
|
+
p 'DETOKENIZED ' + excerpt
|
|
67
69
|
excerpt = Clipper.new( excerpt, @excerpt_limit ).execute
|
|
70
|
+
p excerpt
|
|
68
71
|
excerpt.gsub( /[\200-\377]/ ) { |c| "&#%04d;" % c[0] }
|
|
69
72
|
convert( excerpt )
|
|
70
73
|
end
|
metadata
CHANGED
|
@@ -3,8 +3,8 @@ rubygems_version: 0.8.11
|
|
|
3
3
|
specification_version: 1
|
|
4
4
|
name: htmlclipping
|
|
5
5
|
version: !ruby/object:Gem::Version
|
|
6
|
-
version: 0.1.
|
|
7
|
-
date: 2006-
|
|
6
|
+
version: 0.1.7
|
|
7
|
+
date: 2006-08-26 00:00:00 -04:00
|
|
8
8
|
summary: HtmlClipping generates excerpts from an HTML page that has a link pointing to a particular URI.
|
|
9
9
|
require_paths:
|
|
10
10
|
- lib
|