"""OCR in Python using the Tesseract engine from Google
http://code.google.com/p/pytesser/
by Michael J.T. O'Kelly
V 0.0.1, 3/10/07"""
import Image
import subprocess
import util
import errors
tesseract_exe_name = 'tesseract' # Name of executable to be called at command line
scratch_image_name = "temp.bmp" # This file must be .bmp or other Tesseract-compatible format
scratch_text_name_root = "temp" # Leave out the .txt extension
cleanup_scratch_flag = True # Temporary files cleaned up after OCR operation
def call_tesseract(input_filename, output_filename, language):
 """Calls external tesseract.exe on input file (restrictions on types),
 outputting output_filename+'txt'"""
 args = [tesseract_exe_name, input_filename, output_filename, "-l", language]
 proc = subprocess.Popen(args)
 retcode = proc.wait()
 if retcode!=0:
  errors.check_for_errors()
def image_to_string(im, cleanup = cleanup_scratch_flag, language = "eng"):
 """Converts im to file, applies tesseract, and fetches resulting text.
 If cleanup=True, delete scratch files after operation."""
 try:
  util.image_to_scratch(im, scratch_image_name)
  call_tesseract(scratch_image_name, scratch_text_name_root,language)
  text = util.retrieve_text(scratch_text_name_root)
 finally:
  if cleanup:
   util.perform_cleanup(scratch_image_name, scratch_text_name_root)
 return text
def image_file_to_string(filename, cleanup = cleanup_scratch_flag, graceful_errors=True, language = "eng"):
 """Applies tesseract to filename; or, if image is incompatible and graceful_errors=True,
 converts to compatible format and then applies tesseract. Fetches resulting text.
 If cleanup=True, delete scratch files after operation."""
 try:
  try:
   call_tesseract(filename, scratch_text_name_root, language)
   text = util.retrieve_text(scratch_text_name_root)
  except errors.Tesser_General_Exception:
   if graceful_errors:
    im = Image.open(filename)
    text = image_to_string(im, cleanup)
   else:
    raise
 finally:
  if cleanup:
   util.perform_cleanup(scratch_image_name, scratch_text_name_root)
 return text
if __name__=='__main__':
 im = Image.open('phototest.tif')
 text = image_to_string(im)
 print text
 try:
  text = image_file_to_string('fnord.tif', graceful_errors=False)
 except errors.Tesser_General_Exception, value:
  print "fnord.tif is incompatible filetype. Try graceful_errors=True"
  print value
 text = image_file_to_string('fnord.tif', graceful_errors=True)
 print "fnord.tif contents:", text
 text = image_file_to_string('fonts_test.png', graceful_errors=True)
 print text

def get_hash(self, img):
    #计算图片的hash值
    image = img.convert("L")
    pixels = list(image.getdata())
    avg = sum(pixels) / len(pixels)
    return "".join(map(lambda p : "1" if p > avg else "0", pixels))

#识别出对应位置图像成字符，把字符交给chose处理
  def getWordMeaning(self):
    pic_up = ImageGrab.grab((480,350, 480+300, 350+66))
    pic_aws1 = ImageGrab.grab((463,456, 463+362, 456+45))
    pic_aws2 = ImageGrab.grab((463,530, 463+362, 530+45))
    pic_aws3 = ImageGrab.grab((463,601, 463+362, 601+45))
    pic_aws4 = ImageGrab.grab((463,673, 463+362, 673+45))
    str_up = image_to_string(pic_up).strip().lower()
    #判断当前单词和上次识别单词相同，就不继续识别
    if str_up <> self.lastWord:
      #如果题目单词是英文，选项按中文进行识别
      if str_up.isalpha():
        eng_up = self.dt[str_up].decode('gbk') if self.dt.has_key(str_up) else ''
        chs1 = image_to_string(pic_aws1, language='chi_sim').decode('utf-8').strip()
        chs2 = image_to_string(pic_aws2, language='chi_sim').decode('utf-8').strip()
        chs3 = image_to_string(pic_aws3, language='chi_sim').decode('utf-8').strip()
        chs4 = image_to_string(pic_aws4, language='chi_sim').decode('utf-8').strip()
        print str_up, ':', eng_up
        self.chose(eng_up, (chs1, chs2, chs3, chs4))
      #如果题目单词是中文，选项按英文进行识别
      else:
        chs_up = image_to_string(pic_up, language='chi_sim').decode('utf-8').strip()
        eng1 = image_to_string(pic_aws1).strip()
        eng2 = image_to_string(pic_aws2).strip()
        eng3 = image_to_string(pic_aws3).strip()
        eng4 = image_to_string(pic_aws4).strip()
        
        e2c1 = self.dt[eng1].decode('gbk') if self.dt.has_key(eng1) else ''
        e2c2 = self.dt[eng2].decode('gbk') if self.dt.has_key(eng2) else ''
        e2c3 = self.dt[eng3].decode('gbk') if self.dt.has_key(eng3) else ''
        e2c4 = self.dt[eng4].decode('gbk') if self.dt.has_key(eng4) else ''
        print chs_up
        self.chose(chs_up, (e2c1, e2c2, e2c3, e2c4))
      self.lastWord = str_up
    return str_up

#根据传入的题目和选项进行匹配选择
  def chose(self, g, chs_list):
    j, max_score = -1, 0
    same_list = None
    #替换掉题目里的特殊字符
    re_list = [u'~', u',', u'.', u';', u' ', u'a', u'V', u'v', u'i', u'n', u'【', u')', u'_', u'W', u'd', u'j', u'-', u't']
    for i in re_list:
      g = g.replace(i, '')
    print type(g)
    #判断2个字符串中相同字符，相同字符最多的为最佳答案
    for i, chsWord in enumerate(chs_list):
      print type(chsWord)
      l = [x for x in g if x in chsWord and len(x)>0]
      score = len(l) if l else 0
      
      if score > max_score:
        max_score = score
        j = i
        same_list = l
    #如果没有匹配上默认选最后一个
    if j ==-1:
      print '1. %s; 2. %s; 3. %s; 4. %s; Not found choice.' % (chs_list[0], chs_list[1], chs_list[2], chs_list[3])
    else:
      print '1. %s; 2. %s; 3. %s; 4. %s; choice: %s' % (chs_list[0], chs_list[1], chs_list[2], chs_list[3], chs_list[j])
      for k, v in enumerate(same_list):
        print str(k) + '.' + v,
    order = j + 1
    self.mouseMove(order)
    return order