xapian-indexer 1.2.3.1 → 1.2.3.2
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.
|
@@ -95,7 +95,12 @@ module Xapian
|
|
|
95
95
|
html.search("form").remove
|
|
96
96
|
html.css('.noindex').remove
|
|
97
97
|
|
|
98
|
-
|
|
98
|
+
|
|
99
|
+
body = html.at('html/body')
|
|
100
|
+
|
|
101
|
+
if body
|
|
102
|
+
result[:content] = body.inner_text.gsub(/\s+/, " ")
|
|
103
|
+
end
|
|
99
104
|
|
|
100
105
|
return result
|
|
101
106
|
end
|
|
@@ -135,7 +135,6 @@ module Xapian
|
|
|
135
135
|
@database.replace_document(resource.name_digest, doc)
|
|
136
136
|
else
|
|
137
137
|
@logger.warn "Resource was not indexable #{resource.name}!"
|
|
138
|
-
@logger.warn "Links = #{(fetch.links || []).map(&block).compact.inspect}"
|
|
139
138
|
end
|
|
140
139
|
else
|
|
141
140
|
@logger.warn "Could not fetch resource #{resource.name}!"
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: xapian-indexer
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
hash:
|
|
4
|
+
hash: 71
|
|
5
5
|
prerelease: false
|
|
6
6
|
segments:
|
|
7
7
|
- 1
|
|
8
8
|
- 2
|
|
9
9
|
- 3
|
|
10
|
-
-
|
|
11
|
-
version: 1.2.3.
|
|
10
|
+
- 2
|
|
11
|
+
version: 1.2.3.2
|
|
12
12
|
platform: ruby
|
|
13
13
|
authors:
|
|
14
14
|
- Samuel Williams
|
|
@@ -16,10 +16,23 @@ autorequire:
|
|
|
16
16
|
bindir: bin
|
|
17
17
|
cert_chain: []
|
|
18
18
|
|
|
19
|
-
date: 2010-12-
|
|
19
|
+
date: 2010-12-22 00:00:00 +13:00
|
|
20
20
|
default_executable:
|
|
21
|
-
dependencies:
|
|
22
|
-
|
|
21
|
+
dependencies:
|
|
22
|
+
- !ruby/object:Gem::Dependency
|
|
23
|
+
name: xapian-core
|
|
24
|
+
prerelease: false
|
|
25
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
|
26
|
+
none: false
|
|
27
|
+
requirements:
|
|
28
|
+
- - ">="
|
|
29
|
+
- !ruby/object:Gem::Version
|
|
30
|
+
hash: 3
|
|
31
|
+
segments:
|
|
32
|
+
- 0
|
|
33
|
+
version: "0"
|
|
34
|
+
type: :runtime
|
|
35
|
+
version_requirements: *id001
|
|
23
36
|
description:
|
|
24
37
|
email: samuel.williams@oriontransfer.co.nz
|
|
25
38
|
executables: []
|
|
@@ -69,6 +82,6 @@ rubyforge_project:
|
|
|
69
82
|
rubygems_version: 1.3.7
|
|
70
83
|
signing_key:
|
|
71
84
|
specification_version: 3
|
|
72
|
-
summary: Xapian
|
|
85
|
+
summary: Xapian::Indexer provides a flexible spider for indexing resources.
|
|
73
86
|
test_files: []
|
|
74
87
|
|