[Python-checkins] python/nondist/sandbox/csv/util sniffer.py,NONE,1.1

2003年3月12日 10:58:26 -0800

Update of /cvsroot/python/python/nondist/sandbox/csv/util
In directory sc8-pr-cvs1:/tmp/cvs-serv21719
Added Files:
	sniffer.py 
Log Message:
Initial commit of sniffer.py
--- NEW FILE: sniffer.py ---
"""
dialect = Sniffer().sniff(file('csv/easy.csv'))
print "delimiter", dialect.delimiter
print "quotechar", dialect.quotechar
print "skipinitialspace", dialect.skipinitialspace
"""
from csv import csv
import re, string
class Sniffer:
 """
 "Sniffs" the format of a CSV file (i.e. delimiter, quotechar)
 Sniffer.dialect will be either a csv.Dialect object or None
 if the file format couldn't be determined.
 """
 def __init__(self, sample = 16 * 1024):
 # in case there is more than one possible delimiter
 self.preferred = [',', '\t', ';', ' ', ':']
 # amount of data (in bytes) to sample
 self.sample = sample
 def sniff(self, fileobj):
 """
 Takes a file-like object and returns a dialect (or None)
 """
 data = fileobj.read(self.sample)
 quotechar, delimiter, skipinitialspace = self._guessQuoteAndDelimiter(data)
 if delimiter is None:
 delimiter, skipinitialspace = self._guessDelimiter(data)
 print quotechar, delimiter, skipinitialspace
 class Dialect(csv.Dialect):
 _name = "sniffed"
 lineterminator = '\r\n'
 quoting = csv.QUOTE_MINIMAL
 escapechar = ''
 doublequote = False
 Dialect.delimiter = delimiter
 Dialect.quotechar = quotechar
 Dialect.skipinitialspace = skipinitialspace
 return Dialect()
 def _guessQuoteAndDelimiter(self, data):
 """
 Looks for text enclosed between two identical quotes
 (the probable quotechar) which are preceded and followed
 by the same character (the probable delimiter).
 For example:
 ,'some text',
 The quote with the most wins, same with the delimiter.
 If there is no quotechar the delimiter can't be determined
 this way.
 """
 for restr in ('(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)', # ,".*?",
 '(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)', # ".*?",
 '(?P<delim>>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)', # ,".*?"
 '(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\n)'): # ".*?" (no delim, no space)
 regexp = re.compile(restr, re.S | re.M)
 matches = regexp.findall(data)
 if matches:
 print restr
 print matches
 break

 if not matches:
 return ('', None, 0) # (quotechar, delimiter, skipinitialspace)
 quotes = {}
 delims = {}
 spaces = 0
 for m in matches:
 n = regexp.groupindex['quote'] - 1
 key = m[n]
 if key:
 quotes[key] = quotes.get(key, 0) + 1
 try:
 n = regexp.groupindex['delim'] - 1
 key = m[n]
 except KeyError:
 continue
 if key:
 delims[key] = delims.get(key, 0) + 1
 try:
 n = regexp.groupindex['space'] - 1
 except KeyError:
 continue
 if m[n]:
 spaces += 1
 print "QUOTES", quotes
 print "DELIMS", delims
 quotechar = reduce(lambda a, b, quotes = quotes:
 (quotes[a] > quotes[b]) and a or b, quotes.keys())
 if delims:
 delim = reduce(lambda a, b, delims = delims:
 (delims[a] > delims[b]) and a or b, delims.keys())
 skipinitialspace = delims[delim] == spaces
 if delim == '\n': # most likely a file with a single column
 delim = None
 else:
 # there is *no* delimiter, it's a single column of quoted data
 delim = ''
 skipinitialspace = 0

 return (quotechar, delim, skipinitialspace)
 def _guessDelimiter(self, data):
 """
 The delimiter /should/ occur the same number of times on
 each row. However, due to malformed data, it may not. We don't want
 an all or nothing approach, so we allow for small variations in this
 number.
 1) build a table of the frequency of each character on every line.
 2) build a table of freqencies of this frequency (meta-frequency?),
 e.g. "x occurred 5 times in 10 rows, 6 times in 1000 rows,
 7 times in 2 rows"
 3) use the mode of the meta-frequency to determine the /expected/
 frequency for that character 
 4) find out how often the character actually meets that goal 
 5) the character that best meets its goal is the delimiter 
 For performance reasons, the data is evaluated in chunks, so it can
 try and evaluate the smallest portion of the data possible, evaluating
 additional chunks as necessary. 
 """

 data = filter(None, data.split('\n'))
 ascii = [chr(c) for c in range(127)] # 7-bit ASCII
 # build frequency tables
 chunkLength = min(10, len(data))
 iteration = 0
 charFrequency = {}
 modes = {}
 delims = {}
 start, end = 0, min(chunkLength, len(data))
 while start < len(data):
 iteration += 1
 for line in data[start:end]:
 for char in ascii:
 metafrequency = charFrequency.get(char, {})
 freq = line.strip().count(char) # must count even if frequency is 0
 metafrequency[freq] = metafrequency.get(freq, 0) + 1 # value is the mode
 charFrequency[char] = metafrequency
 for char in charFrequency.keys():
 items = charFrequency[char].items()
 if len(items) == 1 and items[0][0] == 0:
 continue
 # get the mode of the frequencies
 if len(items) > 1:
 modes[char] = reduce(lambda a, b: a[1] > b[1] and a or b, items)
 # adjust the mode - subtract the sum of all other frequencies
 items.remove(modes[char])
 modes[char] = (modes[char][0], modes[char][1]
 - reduce(lambda a, b: (0, a[1] + b[1]), items)[1])
 else:
 modes[char] = items[0]
 # build a list of possible delimiters
 modeList = modes.items()
 total = float(chunkLength * iteration)
 consistency = 1.0 # (rows of consistent data) / (number of rows) = 100%
 threshold = 0.9 # minimum consistency threshold
 while len(delims) == 0 and consistency >= threshold:
 for k, v in modeList:
 if v[0] > 0 and v[1] > 0:
 if (v[1]/total) >= consistency:
 delims[k] = v
 consistency -= 0.01
 if len(delims) == 1:
 delim = delims.keys()[0]
 skipinitialspace = data[0].count(delim) == data[0].count("%c " % delim)
 return (delim, skipinitialspace)
 # analyze another chunkLength lines
 start = end
 end += chunkLength
 if not delims:
 return None
 # if there's more than one, fall back to a 'preferred' list
 if len(delims) > 1:
 for d in self.preferred:
 if d in delims.keys():
 skipinitialspace = data[0].count(d) == data[0].count("%c " % d)
 return (d, skipinitialspace)
 # finally, just return the first damn character in the list
 delim = delims.keys()[0]
 skipinitialspace = data[0].count(delim) == data[0].count("%c " % delim)
 return (delim, skipinitialspace)