ebook_tools 0.1.5 → 0.1.6
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/CHANGELOG +6 -0
- data/ebook_tools.gemspec +3 -3
- data/lib/paras_in_mongo.rb +35 -21
- data/lib/utils.rb +10 -0
- metadata +3 -3
data/CHANGELOG
CHANGED
data/ebook_tools.gemspec
CHANGED
@@ -2,11 +2,11 @@
|
|
2
2
|
|
3
3
|
Gem::Specification.new do |s|
|
4
4
|
s.name = %q{ebook_tools}
|
5
|
-
s.version = '0.1.
|
5
|
+
s.version = '0.1.6'
|
6
6
|
|
7
7
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
8
8
|
s.authors = ["Aaron"]
|
9
|
-
s.date = %q{2013-06-
|
9
|
+
s.date = %q{2013-06-07}
|
10
10
|
s.description = %q{电子书工具集.}
|
11
11
|
s.email = %q{yalong1976@gmail.com}
|
12
12
|
s.require_paths = ["lib"]
|
@@ -20,9 +20,9 @@ Gem::Specification.new do |s|
|
|
20
20
|
s.files = [
|
21
21
|
"README",
|
22
22
|
"CHANGELOG",
|
23
|
+
"bin/doc_book_import_mongo",
|
23
24
|
"bin/ebook_tools",
|
24
25
|
"bin/para_import_mongo",
|
25
|
-
"bin/doc_book_import_mongo",
|
26
26
|
"bin/para_import_scheduling",
|
27
27
|
"bin/xml2json",
|
28
28
|
"lib/doc_book_in_mongo.rb",
|
data/lib/paras_in_mongo.rb
CHANGED
@@ -11,32 +11,46 @@ module ParasInMongo
|
|
11
11
|
options = options.stringify_keys
|
12
12
|
session = Moped::Session.new([ "#{options['host']}:#{options['port']}" ])
|
13
13
|
session.use options['database']
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
book_id = doc.search("book")[0]['id']
|
18
|
-
title = doc.search("book info title")[0].text
|
19
|
-
author = doc.search("book info author")[0].text
|
20
|
-
pubdate = doc.search("book info pubdate")[0].text
|
21
|
-
publisher = doc.search("book info publisher")[0].text
|
22
|
-
|
14
|
+
doc =Nokogiri::XML(File.open(filename).read)
|
15
|
+
book = extract_book_info(doc)
|
16
|
+
source ={book: book}
|
23
17
|
paras = doc.search("para[key=yes]")
|
18
|
+
section = nil
|
19
|
+
section_title = ''
|
20
|
+
para_mongo_attrs = paras.map do |para|
|
21
|
+
unless para.parent == section
|
22
|
+
section_title = para.parent.search("info[1]/title").text
|
23
|
+
section = para.parent
|
24
|
+
end
|
25
|
+
extract_para_attrs(para,source.merge(location: {section: section_title}))
|
26
|
+
end
|
27
|
+
para_mongo_attrs.each do |attrs|
|
28
|
+
session[options['collection']].insert(attrs)
|
29
|
+
end
|
30
|
+
end
|
24
31
|
|
25
|
-
|
26
|
-
|
27
|
-
|
32
|
+
private
|
33
|
+
def extract_book_info(doc)
|
34
|
+
book_id = doc.search("book")[0]['id']
|
35
|
+
book_info = doc.search("book/info[1]")
|
36
|
+
title = book_info.search("title[1]").text
|
37
|
+
author = book_info.search("authorgroup/author/personname[1]").text
|
38
|
+
pubdate = book_info.search("pubdate[1]").text
|
39
|
+
publisher = book_info.search("publisher/publishername[1]").text
|
40
|
+
{title: title,book_id: book_id, author: author,pubdate: pubdate, publisher: publisher}
|
41
|
+
end
|
42
|
+
|
43
|
+
def extract_para_attrs(para,source)
|
28
44
|
para_attrs = {'_id' => para['id']}
|
29
|
-
content = para.search("content")
|
45
|
+
content = para.search("content[1]").text
|
30
46
|
|
31
47
|
keywords = []
|
32
|
-
|
33
|
-
|
34
|
-
|
48
|
+
para.search("keyword").each do |keyword|
|
49
|
+
keywords << {keyword: keyword.text, weight: keyword['weight'].to_i}
|
50
|
+
end
|
35
51
|
|
36
52
|
para_attrs = para_attrs.merge(keywords: keywords, content: content)
|
37
|
-
section = para.parent.search("info
|
38
|
-
para_attrs
|
39
|
-
|
40
|
-
end
|
41
|
-
end
|
53
|
+
#section = timer{para.parent.search("info[1]/title").text}
|
54
|
+
para_attrs.merge(source: source)
|
55
|
+
end
|
42
56
|
end
|
data/lib/utils.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: ebook_tools
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.6
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2013-06-
|
12
|
+
date: 2013-06-07 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: uuid
|
@@ -166,9 +166,9 @@ extra_rdoc_files: []
|
|
166
166
|
files:
|
167
167
|
- README
|
168
168
|
- CHANGELOG
|
169
|
+
- bin/doc_book_import_mongo
|
169
170
|
- bin/ebook_tools
|
170
171
|
- bin/para_import_mongo
|
171
|
-
- bin/doc_book_import_mongo
|
172
172
|
- bin/para_import_scheduling
|
173
173
|
- bin/xml2json
|
174
174
|
- lib/doc_book_in_mongo.rb
|