Python string.count方法代码示例

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def count_words(candidate_text, common_words=frequency.common_words['english'], case_sensitive=True):
   '''
   Count the instances of common words in the expected plaintext
   language, return the total number of characters matched in each
   word 

   candidate_text - (string) Sample to analyze
   common_words - (list) Sequences expected to appear in the text
   case_sensitive - (bool) Whether or not to match case sensitively
   '''
   score = 0

   for word in common_words:
      if not case_sensitive:
         word = word.lower()
      num_found = candidate_text.count(word)
      if num_found > 0:
         score += num_found * len(word)
      
   return score 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def translateDescParams(desc_params):
    desc_params = desc_params.replace(" ", "")
    buff = ""

    for elem in desc_params.split(","):
        if elem != "":
            tab = ""
            if "[" in elem:
                tab = "[" * string.count(elem, "[")

                elem = elem[:tab.find("[") - 2]

            if elem not in BASIC_TYPES:
                if elem in ADVANCED_TYPES:
                    buff += tab + ADVANCED_TYPES[elem] + " "
                else:
                    buff += tab + "L" + elem.replace(".", "/") + "; "
            else:
                buff += tab + BASIC_TYPES[elem] + " "

    buff = buff[:-1]
    return buff 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def translateDescReturn(desc_return):
    buff = ""
    for elem in desc_return.split(" "):
        tab = ""
        if "[" in elem:
            tab = "[" * string.count(elem, "[")
            elem = elem[:tab.find("[") - 2]

        if elem in BASIC_TYPES:
            buff += tab + BASIC_TYPES[elem] + " "
        else:
            if elem in ADVANCED_TYPES:
                buff += tab + ADVANCED_TYPES[elem] + " "
            else:
                if "." in elem:
                    buff += tab + "L" + elem.replace(".", "/") + "; "

    buff = buff[:-1]
    return buff 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def _getFragWord(frags,maxWidth):
    ''' given a fragment list return a list of lists
        [size, spaces, (f00,w00), ..., (f0n,w0n)]
        each pair f,w represents a style and some string
    '''
    W = []
    n = 0
    s = 0
    for f in frags:
        text = f.text[:]
        W.append((f,text))
        cb = getattr(f,'cbDefn',None)
        if cb:
            _w = getattr(cb,'width',0)
            if hasattr(_w,'normalizedValue'):
                _w._normalizer = maxWidth
        n = n + stringWidth(text, f.fontName, f.fontSize)

        #s = s + _countSpaces(text)
        s = s + string.count(text, ' ') # much faster for many blanks

        #del f.text # we can't do this until we sort out splitting
                    # of paragraphs
    return n, s, W 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def ParseCSVLine(line):
    line = line.strip()
    values = []
    while line.__len__() > 0:
        if string.count(line, ',') > 0:
            if line[0] == '"':
                line = line[1:]
                values.append(line[:string.find(line, '"')])
                line = line[string.find(line, '"') + 1:]
                line = line[1:]
                if line.__len__() == 0:
                    values.append("")
            else:
                values.append(line[:string.find(line, ',')])
                line = line[string.find(line, ',') + 1:]
                if line.__len__() == 0:
                    values.append("")
        else:
            values.append(line)
            line = ""
    return values 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def domain_counter(fqdn):
    ''' counter for domains based on the last two zones '''
    fulldata = []
    for each in fqdn:
        a = count((each),".")
        if a >= 2:
            fulldata.append(each[::-1])
    fulldata.sort()
    domain_trunk = []
    for each in fulldata:
        splitdata = each.split('.')
        # treat the first two as one
        TwoZones = str(splitdata[0])+"."+str(splitdata[1])
        #print TwoZones
        domain_trunk.append(TwoZones)        
    fulldata = []
    for each in domain_trunk:
        fulldata.append(each[::-1])
    return (Counter(fulldata)) 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def ip_print(sublist):
    query      = r.hget('IP:'+str(sublist), 'name')
    first      = r.hget('IP:'+str(sublist), 'first')
    date       = r.hget('IP:'+str(sublist), 'date')
    count      = r.hget('IP:'+str(sublist), 'count')
    rr_type    = r.hget('IP:'+str(sublist), 'type')
    ttl        = r.hget('IP:'+str(sublist), 'ttl')
    count      = r.hget('IP:'+str(sublist), 'count')
    #dns_client = r.hget(sublist, 'dns_client')
    #dns_server = r.hget(sublist, 'dns_server')
    #nss        = r.hget(sublist, 'nss')

    if first == None:
        first = '00000000'
    if date == None:
        date = '00000000'
    
    # PRINT FIELDS
    print "{0:18} {1:35} {2:9} {3:9} {4:8} {5:8} {6:6}".format(sublist,query,first[:8],date[:8],record_translate(rr_type),ttl,count)
    pass 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def unique(L):
	noDupli=[]
	[noDupli.append(i) for i in L if not noDupli.count(i)]
	return noDupli 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def parseJavaScriptContent(jsContent):
	global database_url, database_ext, dumb_params
	"""
		Parse the content of a JavaScript file
	"""
	for l in jsContent.readlines():
		for e in allowed:
			if l.count('.'+e) > 0:
				# we found an external a call
				if l.count('http://') > 0 and l.count(root) < 1:
					# External link
					et= '.'+e
					b1 = l.find('http://')
					b2 = l.find(et) + len(et)
					database_ext.append(l[b1:b2])
				else:
					# Internal link
					et= '.'+e
					b2 = l.find(et) + len(et)
					b1 = rfindFirstJSChars(l[:b2])+1
					database_url.append(giveGoodURL(l[b1:b2],root))
		# try to get a parameter
		k = l.find('?')
		if k > 0:
			results = l[k:].split('?')
			plop = []
			for a in results:
				plop.append(cleanListDumbParams(regDumbParam.split(a)))
			dumb_params.append(flatten(plop))
		k = l.find('&')
		if k > 0:
			results = l[k:].split('&')
			plop = []
			for a in results:
				plop.append(cleanListDumbParams(regDumbParam.split(a)))
			plop = flatten(plop)
			dumb_params.append(flatten(plop))
	dumb_params = unique(flatten(dumb_params)) 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def generate_frequency_table(text,charset):
   '''
   Generate a character frequency table for a given text
   and charset as dict with character or string as key and
   frequency of appearance as value expressed as a decimal
   percentage

   text - A sample of plaintext to analyze for frequency data
   charset - (list of strings) The set of items to count in the plaintext
      such as ['a','b','c', ... 'z','aa','ab','ac', ... 'zz']
   '''
   freq_table = {}
   text_len = 0 
   for char in charset:
      freq_table[char] = 0 
   for char in text:
      if char in charset:
         freq_table[char] += 1
         text_len += 1
   for multigraph in filter(lambda x: len(x)>1,charset):
      freq_table[multigraph] = string.count(text, multigraph)
   # Normalize frequencies with length of text
   for key in freq_table.keys():
      if text_len != 0:
         freq_table[key] /= float(text_len)
      else:
         freq_table[key] = 0 
   return freq_table 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def format_error(input, err, scanner):
  """This is a really dumb long function to print error messages nicely."""
  error_message = StringIO.StringIO()
  p = err.pos
  print >> error_message, "error position", p
  # Figure out the line number
  line = count(input[:p], '\n')
  print >> error_message, err.msg, "on line", repr(line+1) + ":"
  # Now try printing part of the line
  text = input[max(p-80, 0):p+80]
  p = p - max(p-80, 0)

  # Strip to the left
  i = rfind(text[:p], '\n')
  j = rfind(text[:p], '\r')
  if i < 0 or (0 <= j < i): i = j
  if 0 <= i < p:
    p = p - i - 1
  text = text[i+1:]

  # Strip to the right
  i = find(text,'\n', p)
  j = find(text,'\r', p)
  if i < 0 or (0 <= j < i):
    i = j
  if i >= 0:
    text = text[:i]

  # Now shorten the text
  while len(text) > 70 and p > 60:
    # Cut off 10 chars
    text = "..." + text[10:]
    p = p - 7

  # Now print the string, along with an indicator
  print >> error_message, '> ', text.replace('\t', ' ').encode(sys.getdefaultencoding())
  print >> error_message, '> ', ' '*p + '^'
  print >> error_message, 'List of nearby tokens:', scanner
  return error_message.getvalue() 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def wrap_error_reporter(parser, rule):
  try:
    return getattr(parser, rule)()
  except SyntaxError, e:
    logging.exception('syntax error')
    input = parser._scanner.input
    try:
      error_msg = format_error(input, e, parser._scanner)
    except ImportError:
      error_msg = 'Syntax Error %s on line\n' % (e.msg, 1 + count(input[:e.pos])) 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def _countSpaces(text):
    return string.count(text, ' ')
##  i = 0
##  s = 0
##  while 1:
##      j = string.find(text,' ',i)
##      if j<0: return s
##      s = s + 1
##      i = j + 1 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def LoadBlocks(path):
    global blocks
    with open(path) as f:
        count = 0
        for line in f:
            count += 1
            if count < 3:
                continue
            blocks.append(ParseCSVLine(line))
    blocks = sorted(blocks, key=lambda it: int(it[0])) 

# 需要导入模块: import string [as 别名]
# 或者: from string import count [as 别名]
def LoadLocations(path):
    global locations
    with open(path) as f:
        count = 0
        for line in f:
            count += 1
            if count < 3:
                continue
            (locId, country, region, city, postalCode, latitude, longitude,
            metroCode, areaCode) = ParseCSVLine(line)
            locations[int(locId)] = {"country": country, "region": region,
                "city": city, "postalCode": postalCode, "latitude": latitude,
                "longitude": longitude, "metroCode": metroCode,
                "areaCode": areaCode}