def __init__( self, key, pattern, decoder=unicode, maxErrors = 0 ):
""" Build a line text analyzer.
key: a label to recognized the type of the line trying to be identified.
pattern: an approximate regular expression pattern to do the identification
decoder: the constructor to the returned value. It takes the matching text as argument
maxErrors: the numbers of errors tolerated in the approximate regular expression
"""
self.are = ARE( pattern, maxErrors )
self.key = key
self.decoder = decoder
class LineAnalyzer( object ):
""" A LineAnalyzer is assumed to recognize substring in a line according to a certain pattern.
"""
def __init__( self, key, pattern, decoder=unicode, maxErrors = 0 ):
""" Build a line text analyzer.
key: a label to recognized the type of the line trying to be identified.
pattern: an approximate regular expression pattern to do the identification
decoder: the constructor to the returned value. It takes the matching text as argument
maxErrors: the numbers of errors tolerated in the approximate regular expression
"""
self.are = ARE( pattern, maxErrors )
self.key = key
self.decoder = decoder
def analyze( self, line ):
""" If line identify a part of the class detected by Line analyzer, return a tuple of a key descriptior, and the matched part of the line.
Else return None.
"""
match = self.are.search( line )
if match == None:
return None
#print '!!!%s!!! %s' %( self.key, match.text )
return self.key, self.decoder( match.text )