chupa-text 1.2.5 → 1.2.6
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/doc/text/news.md +8 -0
- data/lib/chupa-text/data.rb +3 -0
- data/lib/chupa-text/decomposers/http-server.rb +6 -5
- data/lib/chupa-text/extractor.rb +7 -2
- data/lib/chupa-text/file-content.rb +3 -0
- data/lib/chupa-text/input-data.rb +4 -0
- data/lib/chupa-text/version.rb +1 -1
- data/lib/chupa-text/virtual-content.rb +8 -0
- data/lib/chupa-text/virtual-file-data.rb +4 -0
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 0555d47f2e5bc1f80ed47485190a9db10a7a3996a4f8e43012dff65cc19e4069
|
4
|
+
data.tar.gz: acc1ea064a381f34ded5e9253b93ddefd33308d5b12184f3f2bb018dc98f985a
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 9c3ea10422cd7cf588f07ee97819499c6c33fcbb9bf235b2d49ac3fe69aa29feaae42e94a9fddde48532293f503d8d4f4bb1d75a897d7045e1910d8cea261cac
|
7
|
+
data.tar.gz: e8d8e3e1acfcc6a9a1b4329118652590d3a354cbce043aad821960dcd169a049e9917ae9e4bf13ab3c14e7da2df613cb16f627d138d4c372cc2fbf301ddb1f4d
|
data/doc/text/news.md
CHANGED
data/lib/chupa-text/data.rb
CHANGED
@@ -60,11 +60,11 @@ module ChupaText
|
|
60
60
|
http = Net::HTTP.new(url.host, url.port)
|
61
61
|
http.use_ssl = true if url.is_a?(URI::HTTPS)
|
62
62
|
if data.timeout.is_a?(Numeric)
|
63
|
-
|
64
|
-
http.
|
65
|
-
|
66
|
-
|
67
|
-
|
63
|
+
timeout = data.timeout * 1.5
|
64
|
+
http.open_timeout = timeout
|
65
|
+
http.read_timeout = timeout
|
66
|
+
http.write_timeout = timeout if http.respond_to?(:write_timeout=)
|
67
|
+
http.continue_timeout = timeout
|
68
68
|
end
|
69
69
|
begin
|
70
70
|
http.start do
|
@@ -101,6 +101,7 @@ module ChupaText
|
|
101
101
|
def process_request(url, http, data)
|
102
102
|
request = Net::HTTP::Post.new(url)
|
103
103
|
request["transfer-encoding"] = "chunked"
|
104
|
+
request["expect"] = "100-continue" if http.continue_timeout
|
104
105
|
data.open do |input|
|
105
106
|
request.set_form(build_parameters(data, input),
|
106
107
|
"multipart/form-data")
|
data/lib/chupa-text/extractor.rb
CHANGED
@@ -90,11 +90,15 @@ module ChupaText
|
|
90
90
|
if decomposer.nil?
|
91
91
|
if target.text_plain?
|
92
92
|
debug {"#{log_tag}[extract][text-plain]"}
|
93
|
-
|
93
|
+
utf8_data = target.to_utf8_body_data
|
94
|
+
yield(utf8_data)
|
95
|
+
utf8_data.release unless target == utf8_data
|
94
96
|
else
|
95
97
|
debug {"#{log_tag}[extract][decomposer] not found"}
|
96
98
|
if target.text?
|
97
|
-
|
99
|
+
utf8_data = target.to_utf8_body_data
|
100
|
+
yield(utf8_data)
|
101
|
+
utf8_data.release unless target == utf8_data
|
98
102
|
end
|
99
103
|
end
|
100
104
|
else
|
@@ -107,6 +111,7 @@ module ChupaText
|
|
107
111
|
"<#{target.mime_type}> -> <#{decomposed.mime_type}>"
|
108
112
|
end
|
109
113
|
extract_recursive(decomposed, &block)
|
114
|
+
decomposed.release
|
110
115
|
end
|
111
116
|
end
|
112
117
|
end
|
data/lib/chupa-text/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: chupa-text
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.2.
|
4
|
+
version: 1.2.6
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Kouhei Sutou
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2019-
|
11
|
+
date: 2019-06-10 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: archive-zip
|