Class: RTesseract::BoxChar

Inherits:
Box show all
Defined in:
lib/rtesseract/box_char.rb

Overview

Class to read char positions from an image

Constant Summary

Constants inherited from RTesseract

LANGUAGES, OPTIONS

Instance Attribute Summary

Attributes inherited from RTesseract

#image_object, #lang, #options, #options_cmd, #processor, #psm, #source

Instance Method Summary collapse

Methods inherited from Box

#after_convert_hook, #initialize_hook, #to_s, #words

Methods inherited from RTesseract

#after_convert_hook, choose_processor!, #clear_console_output, #command_line_options, #config, #config_file, #convert, #convert_command, #crop!, #default_command, #from_blob, #image, #initialize, #initialize_hook, #read, read, #remove_file, #text_file, #text_file_with_ext, #to_s, #to_s_without_spaces

Constructor Details

This class inherits a constructor from RTesseract

Instance Method Details

#config_hook ⇒ Object 



5
6
7
 
# File 'lib/rtesseract/box_char.rb', line 5

def config_hook
  @options['tessedit_create_boxfile'] = 1 # Split chars
end

#convert_text ⇒ Object 



19
20
21
22
23
24
25
26
 
# File 'lib/rtesseract/box_char.rb', line 19

def convert_text
  text_objects = []
  parse_file.each_line do |line|
    char, x_start, y_start, x_end, y_end, _word = line.split(' ')
    text_objects << { char: char, x_start: x_start.to_i, y_start: y_start.to_i, x_end: x_end.to_i, y_end: y_end.to_i }
  end
  @value = text_objects
end

#file_ext ⇒ Object 



11
12
13
 
# File 'lib/rtesseract/box_char.rb', line 11

def file_ext
  '.box'
end

#parse_file ⇒ Object 



15
16
17
 
# File 'lib/rtesseract/box_char.rb', line 15

def parse_file
  File.read(text_file_with_ext).to_s
end