doc2text 0.4.8 → 0.4.10

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 (3) hide show
  1. checksums.yaml +4 -4
  2. data/lib/doc2text/docx/docx.rb +12 -0
  3. metadata +9 -12
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: a1a6da6fcc5e830d2cd0b62fc9626bfd877f44c09b325d50858594560e89056d
4
- data.tar.gz: cebfa6f59a2f32f5b12e9b19081052d16fbcdafd04c5d1f554faab3c1a174a36
3
+ metadata.gz: 74365e7b06103f594f0e2984c520ed24aad2e7b45202eac4a5b0069297e2743c
4
+ data.tar.gz: e53dcb4b5eca2f92d8287e4447b8307978493ae36e4eb4e1c53fb54dd529f9fa
5
5
  SHA512:
6
- metadata.gz: 1ce3300483c041f2080610f28a8f8e11b8c15d32c97759b206723acfd94576561798da14148903761d376d14ae5749aeed49622d4e02ba6dfbb8e095122d2aa1
7
- data.tar.gz: 0273ab4beacbb3b369fbb50d6dd6fe390c1a0bf66a54b8967d9d24ae41425a06bef88da71e28fb7fd151d75580a1301a2ed6599bc8cd7f6e7ee6b392307b336c
6
+ metadata.gz: 430df5a5805e14f4e7348595662415c1c98148d6bab6274cd0db52e92e08fe2be75e3ce88e380412ea3e25966040ff3ed7f4a24a4bbdb9a88fdbaacf3bca710e
7
+ data.tar.gz: f93c232f94dd142c9e1d39afa1db8ba0129ff9fd0901c1417569ba4113ddff7995e2424cfcd033dd52e3197c9515fd22cfece5da6b4e6c30f22ac01b43017bd9
@@ -19,6 +19,18 @@ module Doc2Text
19
19
  end
20
20
  end
21
21
 
22
+ def parse_styles
23
+ styles_parser = Doc2Text::Odt::StylesParser.new
24
+ xml = Nokogiri::XML::SAX::Parser.new(styles_parser)
25
+ xml.parse open File.join('word', 'styles.xml')
26
+ styles_parser.xml_root
27
+ end
28
+
29
+ def parse(markdown)
30
+ parser = Nokogiri::XML::SAX::Parser.new(markdown)
31
+ parser.parse open File.join('word', 'document.xml')
32
+ end
33
+
22
34
  def contains_extracted_files?
23
35
  File.exist? File.join(extract_path, '[Content_Types].xml')
24
36
  end
metadata CHANGED
@@ -1,43 +1,42 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: doc2text
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.4.8
4
+ version: 0.4.10
5
5
  platform: ruby
6
6
  authors:
7
7
  - Valentin A.
8
- autorequire:
9
8
  bindir: bin
10
9
  cert_chain: []
11
- date: 2025-02-25 00:00:00.000000000 Z
10
+ date: 1980-01-02 00:00:00.000000000 Z
12
11
  dependencies:
13
12
  - !ruby/object:Gem::Dependency
14
13
  name: nokogiri
15
14
  requirement: !ruby/object:Gem::Requirement
16
15
  requirements:
17
- - - ">="
16
+ - - "~>"
18
17
  - !ruby/object:Gem::Version
19
- version: 1.18.2
18
+ version: '1.19'
20
19
  type: :runtime
21
20
  prerelease: false
22
21
  version_requirements: !ruby/object:Gem::Requirement
23
22
  requirements:
24
- - - ">="
23
+ - - "~>"
25
24
  - !ruby/object:Gem::Version
26
- version: 1.18.2
25
+ version: '1.19'
27
26
  - !ruby/object:Gem::Dependency
28
27
  name: rubyzip
29
28
  requirement: !ruby/object:Gem::Requirement
30
29
  requirements:
31
30
  - - "~>"
32
31
  - !ruby/object:Gem::Version
33
- version: 2.3.0
32
+ version: '3.2'
34
33
  type: :runtime
35
34
  prerelease: false
36
35
  version_requirements: !ruby/object:Gem::Requirement
37
36
  requirements:
38
37
  - - "~>"
39
38
  - !ruby/object:Gem::Version
40
- version: 2.3.0
39
+ version: '3.2'
41
40
  description: Parses odt to markdown
42
41
  email: valentin@nalisbg.com
43
42
  executables:
@@ -65,7 +64,6 @@ homepage: http://doc2text.com
65
64
  licenses:
66
65
  - Apache-2.0
67
66
  metadata: {}
68
- post_install_message:
69
67
  rdoc_options: []
70
68
  require_paths:
71
69
  - lib
@@ -80,8 +78,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
80
78
  - !ruby/object:Gem::Version
81
79
  version: '0'
82
80
  requirements: []
83
- rubygems_version: 3.4.20
84
- signing_key:
81
+ rubygems_version: 4.0.10
85
82
  specification_version: 4
86
83
  summary: Translates odt to markdown
87
84
  test_files: []