msworddoc-extractor 0.1.0 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/msworddoc/extractor.rb +1 -3
- metadata +14 -24
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: 622c425fb667d63b152a6c80b6325799628e26b0
|
|
4
|
+
data.tar.gz: f678a0e211adc56840f592bde9cdd7e9f3da3896
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 446f278b754c5ca34d5ba6d2ce26c9b285bec030e9db392d804afebb0c25452ef621a0599d25ef1ad2ebabe8a2b147e7ee6ff137f57cfdf28ba3dc8fee06fd9a
|
|
7
|
+
data.tar.gz: 6155fb4bdfef8d9b84d6c0be56062244bc3a02083a96c54c4d1017c79af1e0e9a12672e92160c316e8d7c62e38ca76016313238d61659ec6198a751e9deb3a5e
|
data/lib/msworddoc/extractor.rb
CHANGED
|
@@ -3,7 +3,7 @@ require 'ole/storage'
|
|
|
3
3
|
|
|
4
4
|
module MSWordDoc
|
|
5
5
|
module Extractor
|
|
6
|
-
VERSION = '0.
|
|
6
|
+
VERSION = '0.2.0'
|
|
7
7
|
|
|
8
8
|
def self.load(file)
|
|
9
9
|
doc = Essence.new()
|
|
@@ -308,8 +308,6 @@ module MSWordDoc
|
|
|
308
308
|
"\x0d" => "\n", # ASIS: Line Feed
|
|
309
309
|
"\x09" => "\t", # ASIS: Tab
|
|
310
310
|
|
|
311
|
-
"\x0d" => "\n", # Paragraph ends; \n + U+2029?
|
|
312
|
-
|
|
313
311
|
"\x0b" => "\n", # Hard line breaks
|
|
314
312
|
|
|
315
313
|
"\x2d" => "\x2d", # ASIS: Breaking hyphens; U+2010?
|
metadata
CHANGED
|
@@ -1,30 +1,27 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: msworddoc-extractor
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
5
|
-
prerelease:
|
|
4
|
+
version: 0.2.0
|
|
6
5
|
platform: ruby
|
|
7
6
|
authors:
|
|
8
7
|
- ITO Nobuaki
|
|
9
8
|
autorequire:
|
|
10
9
|
bindir: bin
|
|
11
10
|
cert_chain: []
|
|
12
|
-
date:
|
|
11
|
+
date: 2015-10-14 00:00:00.000000000 Z
|
|
13
12
|
dependencies:
|
|
14
13
|
- !ruby/object:Gem::Dependency
|
|
15
14
|
name: ruby-ole
|
|
16
15
|
requirement: !ruby/object:Gem::Requirement
|
|
17
|
-
none: false
|
|
18
16
|
requirements:
|
|
19
|
-
- -
|
|
17
|
+
- - ">="
|
|
20
18
|
- !ruby/object:Gem::Version
|
|
21
19
|
version: '0'
|
|
22
20
|
type: :runtime
|
|
23
21
|
prerelease: false
|
|
24
22
|
version_requirements: !ruby/object:Gem::Requirement
|
|
25
|
-
none: false
|
|
26
23
|
requirements:
|
|
27
|
-
- -
|
|
24
|
+
- - ">="
|
|
28
25
|
- !ruby/object:Gem::Version
|
|
29
26
|
version: '0'
|
|
30
27
|
description: Extract text contents from Microsoft Word Document.
|
|
@@ -38,44 +35,37 @@ files:
|
|
|
38
35
|
- bin/worddoc-extract
|
|
39
36
|
- lib/msworddoc-extractor.rb
|
|
40
37
|
- lib/msworddoc/extractor.rb
|
|
41
|
-
- test/
|
|
38
|
+
- test/fareast.doc
|
|
39
|
+
- test/lorem.doc
|
|
42
40
|
- test/test_fareast.rb
|
|
43
41
|
- test/test_io.rb
|
|
44
|
-
- test/
|
|
45
|
-
- test/fareast.doc
|
|
42
|
+
- test/test_msworddoc.rb
|
|
46
43
|
homepage: ''
|
|
47
44
|
licenses: []
|
|
45
|
+
metadata: {}
|
|
48
46
|
post_install_message:
|
|
49
47
|
rdoc_options: []
|
|
50
48
|
require_paths:
|
|
51
49
|
- lib
|
|
52
50
|
required_ruby_version: !ruby/object:Gem::Requirement
|
|
53
|
-
none: false
|
|
54
51
|
requirements:
|
|
55
|
-
- -
|
|
52
|
+
- - ">="
|
|
56
53
|
- !ruby/object:Gem::Version
|
|
57
54
|
version: '0'
|
|
58
|
-
segments:
|
|
59
|
-
- 0
|
|
60
|
-
hash: 1216945514845922976
|
|
61
55
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
62
|
-
none: false
|
|
63
56
|
requirements:
|
|
64
|
-
- -
|
|
57
|
+
- - ">="
|
|
65
58
|
- !ruby/object:Gem::Version
|
|
66
59
|
version: '0'
|
|
67
|
-
segments:
|
|
68
|
-
- 0
|
|
69
|
-
hash: 1216945514845922976
|
|
70
60
|
requirements: []
|
|
71
61
|
rubyforge_project:
|
|
72
|
-
rubygems_version:
|
|
62
|
+
rubygems_version: 2.2.2
|
|
73
63
|
signing_key:
|
|
74
64
|
specification_version: 3
|
|
75
65
|
summary: Extract text contents from Microsoft Word Document
|
|
76
66
|
test_files:
|
|
77
|
-
- test/
|
|
67
|
+
- test/fareast.doc
|
|
68
|
+
- test/lorem.doc
|
|
78
69
|
- test/test_fareast.rb
|
|
79
70
|
- test/test_io.rb
|
|
80
|
-
- test/
|
|
81
|
-
- test/fareast.doc
|
|
71
|
+
- test/test_msworddoc.rb
|