hocr_turtletext 0.1.1 → 0.1.2
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/Gemfile.lock +1 -1
- data/lib/hocr_turtletext.rb +1 -0
- data/lib/hocr_turtletext/reader.rb +3 -1
- data/lib/hocr_turtletext/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: 23ed7d4b8c32b028f82675d42d9a8b2625692276
|
|
4
|
+
data.tar.gz: c0e778642e9c0fe39a72116797ea39223cbf17bb
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: ec2e4c2fc85a3b241afff470cb820c0b907301be78cd4f2d28e67c60509337bf75ba8c7cd1a17c592fb2e3234c96803b0c3db5247d50cbbefd2445fbb6068149
|
|
7
|
+
data.tar.gz: 53dd315bc5c91df9d2da50a18385f64b243bd852c4d77b7cf88d6dc0431f54e3f6a441be71ddf6906d324d76f9e61b13bb551a35fda0a017bcda97a304d97bda
|
data/Gemfile.lock
CHANGED
data/lib/hocr_turtletext.rb
CHANGED
|
@@ -98,7 +98,9 @@ class HocrTurtletext::Reader
|
|
|
98
98
|
end
|
|
99
99
|
|
|
100
100
|
def add_positional_info_to_line(ocr_line)
|
|
101
|
-
ocr_line.css('span.ocrx_word, span.ocr_word')
|
|
101
|
+
ocr_line.css('span.ocrx_word, span.ocr_word')
|
|
102
|
+
.reject { |word| word.text.strip.empty? }
|
|
103
|
+
.map do |word|
|
|
102
104
|
word_attributes = word.attributes['title'].value.to_s
|
|
103
105
|
.delete(';').split(' ')
|
|
104
106
|
info(word, word_attributes)
|