filerary 0.0.1 → 0.0.2
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.
- checksums.yaml +4 -4
- data/lib/filerary/librarian.rb +14 -5
- data/lib/filerary/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 6cb82ae7cf6e47684a98d9fd942ed055f624b9cf
|
|
4
|
+
data.tar.gz: 827a84c3b79c5e50300cc814edcd849b927b047f
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 0822bb86cbe996ef71a856bd54a3ca6fb504527b4fa3e818ccaf4bc79edc04a235da33cb959246ed9961bd341040ccfea7be3c3922f90e62c7061f2fc256d4c1
|
|
7
|
+
data.tar.gz: a7ae84144ba9abda1bfd1ce4c8826aa5f44bd1da9ed8914d7692d7349b46253fbf55b844d889ae1f7fba00ec808dd3db8ec067bd3f125ab2c842390296eb3151
|
data/lib/filerary/librarian.rb
CHANGED
|
@@ -1,6 +1,9 @@
|
|
|
1
1
|
require "fileutils"
|
|
2
|
+
require "uri"
|
|
2
3
|
require "grn_mini"
|
|
3
4
|
require "chupa-text"
|
|
5
|
+
gem "chupa-text-decomposer-pdf"
|
|
6
|
+
gem "chupa-text-decomposer-libreoffice"
|
|
4
7
|
|
|
5
8
|
module Filerary
|
|
6
9
|
class Librarian
|
|
@@ -60,14 +63,20 @@ module Filerary
|
|
|
60
63
|
extractor = ChupaText::Extractor.new
|
|
61
64
|
extractor.apply_configuration(ChupaText::Configuration.default)
|
|
62
65
|
|
|
63
|
-
|
|
64
|
-
|
|
66
|
+
begin
|
|
67
|
+
extractor.extract(URI.encode(path)) do |text_data|
|
|
68
|
+
text = text_data.body
|
|
69
|
+
end
|
|
70
|
+
rescue URI::InvalidURIError
|
|
71
|
+
return path
|
|
65
72
|
end
|
|
66
73
|
|
|
67
|
-
|
|
68
|
-
text.force_encoding(Encoding.default_external || "UTF-8")
|
|
74
|
+
return path unless text
|
|
69
75
|
|
|
70
|
-
|
|
76
|
+
# TODO: I want to specify encoding in ChupaText side.
|
|
77
|
+
text.force_encoding("UTF-8")
|
|
78
|
+
return text if text.valid_encoding?
|
|
79
|
+
text.force_encoding(Encoding.default_external)
|
|
71
80
|
end
|
|
72
81
|
end
|
|
73
82
|
end
|
data/lib/filerary/version.rb
CHANGED