Class: OCRDocument

Inherits:
Object
  • Object
show all
Defined in:
lib/ocr_document.rb

Direct Known Subclasses

RHOCR

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initializeOCRDocument

Returns a new instance of OCRDocument.



8
9
10
11
# File 'lib/ocr_document.rb', line 8

def initialize
    @pages = Hash.new()
    @page_count = 0
end

Instance Attribute Details

#page_countObject (readonly)

Returns the value of attribute page_count.



6
7
8
# File 'lib/ocr_document.rb', line 6

def page_count
  @page_count
end

#pagesObject (readonly)

Returns the value of attribute pages.



6
7
8
# File 'lib/ocr_document.rb', line 6

def pages
  @pages
end

Instance Method Details

#add_image_to_page(page_number, image_path) ⇒ Object



26
27
28
# File 'lib/ocr_document.rb', line 26

def add_image_to_page(page_number, image_path)
    @pages[page_number].image = image_path
end

#add_page(file) ⇒ Object Also known as: add_file



20
21
22
23
24
# File 'lib/ocr_document.rb', line 20

def add_page( file )
    page = OCRPage.new( file )
    @pages[page.page_number] = page
    @page_count += 1
end

#add_pages(list_o_pages) ⇒ Object Also known as: add_files



13
14
15
16
17
18
# File 'lib/ocr_document.rb', line 13

def add_pages( list_o_pages  )
    raise "no files given" if list_o_pages.empty?
    list_o_pages.each do |file|
        add_page(file)
    end
end

#each_lineObject



41
42
43
44
45
46
47
# File 'lib/ocr_document.rb', line 41

def each_line
    for page in @pages.values do
        page.each_line do |line|
            yield line
        end
    end
end

#each_pageObject



34
35
36
37
38
39
# File 'lib/ocr_document.rb', line 34

def each_page
    sorted_pages = @pages.keys.sort
    sorted_pages.each do |page_key|
        yield @pages[page_key]
    end
end

#each_wordObject



49
50
51
52
53
54
55
56
57
# File 'lib/ocr_document.rb', line 49

def each_word
    for page in @pages.values do
        page.each_line do |line|
            line.each do |word|
                yield word
            end
        end
    end
end

#page(number) ⇒ Object



30
31
32
# File 'lib/ocr_document.rb', line 30

def page( number )
    @pages[number]
end