rhocr 0.0.2 → 0.0.3

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.
Files changed (4) hide show
  1. data/Rakefile +1 -1
  2. data/lib/ocr_page.rb +3 -3
  3. data/rhocr.gemspec +1 -1
  4. metadata +1 -1
data/Rakefile CHANGED
@@ -2,7 +2,7 @@ require 'rubygems'
2
2
  require 'rake'
3
3
  require 'echoe'
4
4
 
5
- Echoe.new('rhocr', '0.0.2') do |p|
5
+ Echoe.new('rhocr', '0.0.3') do |p|
6
6
  p.description = "Manipulate and use OCR data encode in HOCR"
7
7
  p.url = "http://github.com/daandi/rhocr"
8
8
  p.author = "Andreas Neumann"
data/lib/ocr_page.rb CHANGED
@@ -10,10 +10,10 @@ class OCRPage < OCRBox
10
10
 
11
11
  def hocr_lines( hocr_contents)
12
12
  hocr_array = []
13
- for line in hocr_contents.split(/<span class="ocr_line"/) do
13
+ for line in hocr_contents.split(/<span class=['"]ocr_line['"]/) do
14
14
  line_array = []
15
- for ocrx_word in line.scan(/<span class="ocrx_word"[^>]+>[^<]+<\/span>/) do
16
- ocrx_word =~ /title="bbox (\d+) (\d+) (\d+) (\d+)">([^<]+)</
15
+ for ocrx_word in line.scan(/<span class=['"]ocrx_word['"][^>]+>[^<]+<\/span>/) do
16
+ ocrx_word =~ /title=['"]bbox (\d+) (\d+) (\d+) (\d+)['"]>([^<]+)</
17
17
  current_word = OCRXWord.new($1,$2,$3,$4,$5)
18
18
  line_array << current_word
19
19
  end
data/rhocr.gemspec CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  Gem::Specification.new do |s|
4
4
  s.name = %q{rhocr}
5
- s.version = "0.0.2"
5
+ s.version = "0.0.3"
6
6
 
7
7
  s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
8
8
  s.authors = ["Andreas Neumann"]
metadata CHANGED
@@ -2,7 +2,7 @@
2
2
  name: rhocr
3
3
  version: !ruby/object:Gem::Version
4
4
  prerelease:
5
- version: 0.0.2
5
+ version: 0.0.3
6
6
  platform: ruby
7
7
  authors:
8
8
  - Andreas Neumann