hocr_reader 0.2.0 → 0.2.1
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/Gemfile.lock +1 -1
- data/lib/hocr_reader/part.rb +11 -3
- data/lib/hocr_reader/reader.rb +2 -1
- data/lib/hocr_reader/version.rb +1 -1
- 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: 54cd8a89c894f8598628089d2e81f254e0fa3fab62e458ee90cda4a00bbd3155
|
4
|
+
data.tar.gz: 4fd76ad523f109b69554375be468c470e487b47dce3b20b5794ee8b2040968da
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8634eafcbf3eefad6117ce4db1b482f2597eb96413914baa8f1b4a00cd510f2d72b77450bcfb438f7b37bce420a6f1b1839d0e9cbfff1aeb925ca7c3c8154708
|
7
|
+
data.tar.gz: 69e2d5ac1fe4c34266046bbc142f121378e81477dd24e5789563397e3f642a11b031042e339649de9926622b112dcc5c4498c8e56efdb41303829d192a465325
|
data/Gemfile.lock
CHANGED
data/lib/hocr_reader/part.rb
CHANGED
@@ -5,9 +5,11 @@ require 'bigdecimal'
|
|
5
5
|
module HocrReader
|
6
6
|
# class Part
|
7
7
|
class Part
|
8
|
-
attr_accessor :
|
8
|
+
attr_accessor :part_name, :text,
|
9
|
+
:x_start, :y_start, :x_end, :y_end, :language, :attributes
|
9
10
|
|
10
|
-
def initialize(phrase, title_attributes, lang)
|
11
|
+
def initialize(part_name, phrase, title_attributes, lang)
|
12
|
+
@part_name = part_name[3..-2]
|
11
13
|
@text = phrase.text
|
12
14
|
@attributes = split_the_attributes title_attributes
|
13
15
|
@x_start = bbox[0].to_i
|
@@ -36,8 +38,10 @@ module HocrReader
|
|
36
38
|
parameters.each do |parameter|
|
37
39
|
value << to_numeric(parameter)
|
38
40
|
end
|
39
|
-
|
41
|
+
elsif numeric?(parameters[0])
|
40
42
|
value = to_numeric(parameters[0])
|
43
|
+
else
|
44
|
+
value = parameters[0]
|
41
45
|
end
|
42
46
|
value
|
43
47
|
end
|
@@ -61,5 +65,9 @@ module HocrReader
|
|
61
65
|
num.to_f
|
62
66
|
end
|
63
67
|
end
|
68
|
+
|
69
|
+
def numeric?(str)
|
70
|
+
Float(str) != nil rescue false
|
71
|
+
end
|
64
72
|
end
|
65
73
|
end
|
data/lib/hocr_reader/reader.rb
CHANGED
@@ -42,9 +42,10 @@ module HocrReader
|
|
42
42
|
title_attributes = part.attributes['title'].value.to_s
|
43
43
|
.split(';')
|
44
44
|
language_attribute = part.attributes['lang'].value.to_s if part.attributes['lang']
|
45
|
-
this_part = Part.new(part, title_attributes, language_attribute)
|
45
|
+
this_part = Part.new(part_name, part, title_attributes, language_attribute)
|
46
46
|
@parts.push this_part
|
47
47
|
end
|
48
|
+
@parts
|
48
49
|
end
|
49
50
|
# rubocop:enable Metrics/MethodLength, Metrics/AbcSize
|
50
51
|
|
data/lib/hocr_reader/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: hocr_reader
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- David Verrier
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-
|
11
|
+
date: 2020-12-26 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: minitest
|