chupa-text-decomposer-pdf 1.0.2 → 1.0.3

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.
Files changed (7) hide show
  1. checksums.yaml +4 -4
  2. data/Rakefile +5 -3
  3. data/chupa-text-decomposer-pdf.gemspec +3 -3
  4. data/doc/text/news.md +8 -0
  5. data/lib/chupa-text/decomposers/pdf.rb +2 -3
  6. data/test/test-pdf.rb +9 -4
  7. metadata +31 -32
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 71901aa054dc878f955620473635ee11df436a2b
4
- data.tar.gz: 68bbc514ce94a38865e48a27e1849c1baec7df9e
3
+ metadata.gz: '083dd5ec66cd3d8859092f81abcc0d3e5c6f3929'
4
+ data.tar.gz: 8ec37a765b3402bf97f3f93a5ef5748aa8257499
5
5
  SHA512:
6
- metadata.gz: 66d265273482895c235c053c5cd69ae92a9510288abcc2a72a8a4f686d9942c15fe6ae4d442d13cf95bb21f5696b81aac68e354c7a023b25da1b292aaece0ade
7
- data.tar.gz: 649fa65ae2b74fc051896afc161eb91c8db9ad04626af94d287bf32bf8961a0ce7feb521f635ccf043297172d550ce2bb1c59ea826e211c43eb6a8fa84d1a943
6
+ metadata.gz: 3114a7e40b3c25cca8294337108276b1f204224bf8e815201145ab97959eac8387aacbb2c786860732624e2ec282be98793c00b4a9b8e6546eb60cc122cbc0d1
7
+ data.tar.gz: c68f85e85556afa87c7926c862ab3bb429439048220738b8aeb33798bcb125b9729a175c98ac4f8bf3cb17837734776f6e9a18fb4b86460ff049875183c2e967
data/Rakefile CHANGED
@@ -1,6 +1,6 @@
1
- # -*- mode: ruby; coding: utf-8 -*-
1
+ # -*- ruby -*-
2
2
  #
3
- # Copyright (C) 2013 Kouhei Sutou <kou@clear-code.com>
3
+ # Copyright (C) 2013-2017 Kouhei Sutou <kou@clear-code.com>
4
4
  #
5
5
  # This library is free software; you can redistribute it and/or
6
6
  # modify it under the terms of the GNU Lesser General Public
@@ -34,7 +34,9 @@ end
34
34
  helper.install
35
35
  spec = helper.gemspec
36
36
 
37
- Packnga::DocumentTask.new(spec) do
37
+ Packnga::DocumentTask.new(spec) do |task|
38
+ task.original_language = "en"
39
+ task.translate_language = "ja"
38
40
  end
39
41
 
40
42
  Packnga::ReleaseTask.new(spec) do
data/chupa-text-decomposer-pdf.gemspec CHANGED
@@ -1,6 +1,6 @@
1
1
  # -*- mode: ruby; coding: utf-8 -*-
2
2
  #
3
- # Copyright (C) 2013 Kouhei Sutou <kou@clear-code.com>
3
+ # Copyright (C) 2013-2014 Kouhei Sutou <kou@clear-code.com>
4
4
  #
5
5
  # This library is free software; you can redistribute it and/or
6
6
  # modify it under the terms of the GNU Lesser General Public
@@ -22,7 +22,7 @@ end
22
22
 
23
23
  Gem::Specification.new do |spec|
24
24
  spec.name = "chupa-text-decomposer-pdf"
25
- spec.version = "1.0.2"
25
+ spec.version = "1.0.3"
26
26
  spec.homepage = "https://github.com/ranguba/chupa-text-decomposer-pdf"
27
27
  spec.authors = ["Kouhei Sutou"]
28
28
  spec.email = ["kou@clear-code.com"]
@@ -31,7 +31,7 @@ Gem::Specification.new do |spec|
31
31
  description = clean_white_space.call(entries[entries.index("Description") + 1])
32
32
  spec.summary = description.split(/\n\n+/, 2).first
33
33
  spec.description = description
34
- spec.license = "LGPLv2.1 or later"
34
+ spec.license = "LGPL-2.1+"
35
35
  spec.files = ["#{spec.name}.gemspec"]
36
36
  spec.files += ["README.md", "LICENSE.txt", "Rakefile", "Gemfile"]
37
37
  spec.files += [".yardopts"]
data/doc/text/news.md CHANGED
@@ -1,5 +1,13 @@
1
1
  # News
2
2
 
3
+ ## 1.0.3: 2017-05-02
4
+
5
+ ### Improvements
6
+
7
+ * Improved PDF data detection.
8
+
9
+ * Supported source data attributes.
10
+
3
11
  ## 1.0.2: 2014-02-18
4
12
 
5
13
  ### Improvements
data/lib/chupa-text/decomposers/pdf.rb CHANGED
@@ -24,7 +24,7 @@ module ChupaText
24
24
  registry.register("pdf", self)
25
25
 
26
26
  def target?(data)
27
- data.extension == "pdf" or
27
+ (data.extension == "pdf" and data.body.start_with?("%PDF-1")) or
28
28
  data.mime_type == "application/pdf"
29
29
  end
30
30
 
@@ -37,8 +37,7 @@ module ChupaText
37
37
  text << page_text
38
38
  text << "\n" unless page_text.end_with?("\n")
39
39
  end
40
- text_data = TextData.new(text)
41
- text_data.uri = data.uri
40
+ text_data = TextData.new(text, :source_data => data)
42
41
  add_attribute(text_data, document, :title)
43
42
  add_attribute(text_data, document, :author)
44
43
  add_attribute(text_data, document, :subject)
data/test/test-pdf.rb CHANGED
@@ -1,4 +1,4 @@
1
- # Copyright (C) 2013-2014 Kouhei Sutou <kou@clear-code.com>
1
+ # Copyright (C) 2013-2017 Kouhei Sutou <kou@clear-code.com>
2
2
  #
3
3
  # This library is free software; you can redistribute it and/or
4
4
  # modify it under the terms of the GNU Lesser General Public
@@ -37,15 +37,20 @@ class TestPDF < Test::Unit::TestCase
37
37
  data = ChupaText::Data.new
38
38
  data.body = ""
39
39
  data.uri = uri
40
+ data.mime_type = "application/octet-stream"
40
41
  data
41
42
  end
42
43
 
43
44
  def test_pdf
44
- assert_true(decomposer.target?(create_data("index.pdf")))
45
+ assert do
46
+ decomposer.target?(create_data("index.pdf"))
47
+ end
45
48
  end
46
49
 
47
50
  def test_html
48
- assert_false(decomposer.target?(create_data("index.html")))
51
+ assert do
52
+ not decomposer.target?(create_data("index.html"))
53
+ end
49
54
  end
50
55
  end
51
56
 
@@ -105,7 +110,7 @@ class TestPDF < Test::Unit::TestCase
105
110
  end
106
111
 
107
112
  def test_created_time
108
- assert_equal([Time.parse("2014-01-06T00:52:45+09:00")],
113
+ assert_equal([Time.parse("2014-01-05T06:52:45Z")],
109
114
  decompose("created_time"))
110
115
  end
111
116
 
metadata CHANGED
@@ -1,111 +1,111 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: chupa-text-decomposer-pdf
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.0.2
4
+ version: 1.0.3
5
5
  platform: ruby
6
6
  authors:
7
7
  - Kouhei Sutou
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2014-02-17 00:00:00.000000000 Z
11
+ date: 2017-05-02 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: chupa-text
15
15
  requirement: !ruby/object:Gem::Requirement
16
16
  requirements:
17
- - - '>='
17
+ - - ">="
18
18
  - !ruby/object:Gem::Version
19
19
  version: '0'
20
20
  type: :runtime
21
21
  prerelease: false
22
22
  version_requirements: !ruby/object:Gem::Requirement
23
23
  requirements:
24
- - - '>='
24
+ - - ">="
25
25
  - !ruby/object:Gem::Version
26
26
  version: '0'
27
27
  - !ruby/object:Gem::Dependency
28
28
  name: poppler
29
29
  requirement: !ruby/object:Gem::Requirement
30
30
  requirements:
31
- - - '>='
31
+ - - ">="
32
32
  - !ruby/object:Gem::Version
33
33
  version: '0'
34
34
  type: :runtime
35
35
  prerelease: false
36
36
  version_requirements: !ruby/object:Gem::Requirement
37
37
  requirements:
38
- - - '>='
38
+ - - ">="
39
39
  - !ruby/object:Gem::Version
40
40
  version: '0'
41
41
  - !ruby/object:Gem::Dependency
42
42
  name: bundler
43
43
  requirement: !ruby/object:Gem::Requirement
44
44
  requirements:
45
- - - '>='
45
+ - - ">="
46
46
  - !ruby/object:Gem::Version
47
47
  version: '0'
48
48
  type: :development
49
49
  prerelease: false
50
50
  version_requirements: !ruby/object:Gem::Requirement
51
51
  requirements:
52
- - - '>='
52
+ - - ">="
53
53
  - !ruby/object:Gem::Version
54
54
  version: '0'
55
55
  - !ruby/object:Gem::Dependency
56
56
  name: rake
57
57
  requirement: !ruby/object:Gem::Requirement
58
58
  requirements:
59
- - - '>='
59
+ - - ">="
60
60
  - !ruby/object:Gem::Version
61
61
  version: '0'
62
62
  type: :development
63
63
  prerelease: false
64
64
  version_requirements: !ruby/object:Gem::Requirement
65
65
  requirements:
66
- - - '>='
66
+ - - ">="
67
67
  - !ruby/object:Gem::Version
68
68
  version: '0'
69
69
  - !ruby/object:Gem::Dependency
70
70
  name: test-unit
71
71
  requirement: !ruby/object:Gem::Requirement
72
72
  requirements:
73
- - - '>='
73
+ - - ">="
74
74
  - !ruby/object:Gem::Version
75
75
  version: '0'
76
76
  type: :development
77
77
  prerelease: false
78
78
  version_requirements: !ruby/object:Gem::Requirement
79
79
  requirements:
80
- - - '>='
80
+ - - ">="
81
81
  - !ruby/object:Gem::Version
82
82
  version: '0'
83
83
  - !ruby/object:Gem::Dependency
84
84
  name: packnga
85
85
  requirement: !ruby/object:Gem::Requirement
86
86
  requirements:
87
- - - '>='
87
+ - - ">="
88
88
  - !ruby/object:Gem::Version
89
89
  version: '0'
90
90
  type: :development
91
91
  prerelease: false
92
92
  version_requirements: !ruby/object:Gem::Requirement
93
93
  requirements:
94
- - - '>='
94
+ - - ">="
95
95
  - !ruby/object:Gem::Version
96
96
  version: '0'
97
97
  - !ruby/object:Gem::Dependency
98
98
  name: redcarpet
99
99
  requirement: !ruby/object:Gem::Requirement
100
100
  requirements:
101
- - - '>='
101
+ - - ">="
102
102
  - !ruby/object:Gem::Version
103
103
  version: '0'
104
104
  type: :development
105
105
  prerelease: false
106
106
  version_requirements: !ruby/object:Gem::Requirement
107
107
  requirements:
108
- - - '>='
108
+ - - ">="
109
109
  - !ruby/object:Gem::Version
110
110
  version: '0'
111
111
  description: |
@@ -119,27 +119,27 @@ executables: []
119
119
  extensions: []
120
120
  extra_rdoc_files: []
121
121
  files:
122
- - chupa-text-decomposer-pdf.gemspec
123
- - README.md
122
+ - ".yardopts"
123
+ - Gemfile
124
124
  - LICENSE.txt
125
+ - README.md
125
126
  - Rakefile
126
- - Gemfile
127
- - .yardopts
128
- - lib/chupa-text/decomposers/pdf.rb
127
+ - chupa-text-decomposer-pdf.gemspec
129
128
  - doc/text/news.md
130
- - test/test-pdf.rb
131
- - test/fixture/one-page.pdf
132
- - test/fixture/multi-pages.pdf
133
- - test/fixture/encrypted.pdf
129
+ - lib/chupa-text/decomposers/pdf.rb
130
+ - test/fixture/attributes.odt
134
131
  - test/fixture/attributes.pdf
135
132
  - test/fixture/encrypted.odt
136
- - test/fixture/one-page.odt
133
+ - test/fixture/encrypted.pdf
137
134
  - test/fixture/multi-pages.odt
138
- - test/fixture/attributes.odt
135
+ - test/fixture/multi-pages.pdf
136
+ - test/fixture/one-page.odt
137
+ - test/fixture/one-page.pdf
139
138
  - test/run-test.rb
139
+ - test/test-pdf.rb
140
140
  homepage: https://github.com/ranguba/chupa-text-decomposer-pdf
141
141
  licenses:
142
- - LGPLv2.1 or later
142
+ - LGPL-2.1+
143
143
  metadata: {}
144
144
  post_install_message:
145
145
  rdoc_options: []
@@ -147,20 +147,19 @@ require_paths:
147
147
  - lib
148
148
  required_ruby_version: !ruby/object:Gem::Requirement
149
149
  requirements:
150
- - - '>='
150
+ - - ">="
151
151
  - !ruby/object:Gem::Version
152
152
  version: '0'
153
153
  required_rubygems_version: !ruby/object:Gem::Requirement
154
154
  requirements:
155
- - - '>='
155
+ - - ">="
156
156
  - !ruby/object:Gem::Version
157
157
  version: '0'
158
158
  requirements: []
159
159
  rubyforge_project:
160
- rubygems_version: 2.0.14
160
+ rubygems_version: 2.5.2
161
161
  signing_key:
162
162
  specification_version: 4
163
163
  summary: This is a ChupaText decomposer plugin for to extract text and meta-data from
164
164
  PDF.
165
165
  test_files: []
166
- has_rdoc: