henkei 1.18.2 → 1.19.0
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 +5 -5
- data/jar/{tika-app-1.18.jar → tika-app-1.19.jar} +0 -0
- data/lib/henkei.rb +5 -1
- data/lib/henkei/version.rb +1 -1
- metadata +4 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: bd1b40c3aae2a0fe84a43638db85b968a2dafec308c60fba6540b90d8f0f3243
|
4
|
+
data.tar.gz: bc5f3d46118c86c23625775d4cfa33cbe28452e0cb39511b8158d201bd4ed29d
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6242d7e2f56bd84f6037b37833ff8f4f60e5743b4fe9fdcce9caa386182ade357a3b8d64852ebdf10045c9436542ac1f6609fa3dc8234f14eab3b331ccd6a6e7
|
7
|
+
data.tar.gz: b203ee0ad86112e536af9d68a6165074f524ea38f27c4303950a6dfb4a7c7537676912b9007523808f2ec78566a776a8ce75916b8758dd66bc67849c831245c8
|
Binary file
|
data/lib/henkei.rb
CHANGED
@@ -12,7 +12,7 @@ require 'stringio'
|
|
12
12
|
# Read text and metadata from files and documents using Apache Tika toolkit
|
13
13
|
class Henkei # rubocop:disable Metrics/ClassLength
|
14
14
|
GEM_PATH = File.dirname(File.dirname(__FILE__))
|
15
|
-
JAR_PATH = File.join(Henkei::GEM_PATH, 'jar', 'tika-app-1.
|
15
|
+
JAR_PATH = File.join(Henkei::GEM_PATH, 'jar', 'tika-app-1.19.jar')
|
16
16
|
CONFIG_PATH = File.join(Henkei::GEM_PATH, 'jar', 'tika-config.xml')
|
17
17
|
DEFAULT_SERVER_PORT = 9293 # an arbitrary, but perfectly cromulent, port
|
18
18
|
|
@@ -121,6 +121,7 @@ class Henkei # rubocop:disable Metrics/ClassLength
|
|
121
121
|
def creation_date
|
122
122
|
return @creation_date if defined? @creation_date
|
123
123
|
return unless metadata['Creation-Date']
|
124
|
+
|
124
125
|
@creation_date = Time.parse(metadata['Creation-Date'])
|
125
126
|
end
|
126
127
|
|
@@ -238,6 +239,7 @@ class Henkei # rubocop:disable Metrics/ClassLength
|
|
238
239
|
loop do
|
239
240
|
chunk = file.read(65_536)
|
240
241
|
break unless chunk
|
242
|
+
|
241
243
|
s.write(chunk)
|
242
244
|
end
|
243
245
|
|
@@ -248,6 +250,7 @@ class Henkei # rubocop:disable Metrics/ClassLength
|
|
248
250
|
loop do
|
249
251
|
chunk = s.recv(65_536)
|
250
252
|
break if chunk.empty? || !chunk
|
253
|
+
|
251
254
|
resp << chunk
|
252
255
|
end
|
253
256
|
resp
|
@@ -262,6 +265,7 @@ class Henkei # rubocop:disable Metrics/ClassLength
|
|
262
265
|
command << switch_for_type(type)
|
263
266
|
command.join ' '
|
264
267
|
end
|
268
|
+
private_class_method :tika_command
|
265
269
|
|
266
270
|
# Internal helper for building the Java command to call Tika
|
267
271
|
#
|
data/lib/henkei/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: henkei
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.19.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Erol Fornoles
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2018-
|
12
|
+
date: 2018-11-09 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: json
|
@@ -139,7 +139,7 @@ files:
|
|
139
139
|
- README.md
|
140
140
|
- Rakefile
|
141
141
|
- henkei.gemspec
|
142
|
-
- jar/tika-app-1.
|
142
|
+
- jar/tika-app-1.19.jar
|
143
143
|
- jar/tika-config.xml
|
144
144
|
- lib/henkei.rb
|
145
145
|
- lib/henkei/version.rb
|
@@ -170,7 +170,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
170
170
|
version: '0'
|
171
171
|
requirements: []
|
172
172
|
rubyforge_project:
|
173
|
-
rubygems_version: 2.6
|
173
|
+
rubygems_version: 2.7.6
|
174
174
|
signing_key:
|
175
175
|
specification_version: 4
|
176
176
|
summary: Read text and metadata from files and documents (.doc, .docx, .pages, .odt,
|