Created
February 3, 2012 23:48
-
-
Save laginha/1733811 to your computer and use it in GitHub Desktop.
Unicode csv reader
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from unicodedata import normalize, combining | |
def unicode_( s ): | |
""" | |
Convert string to unicode & Remove accents | |
""" | |
ustr = u''.join( ucharlist( '%s'%s ) ) | |
nkfd = normalize( 'NFKD', ustr ) | |
return u''.join( [ c for c in nkfd if not combining(c) ] ) | |
ucharlist = lambda a: [ unichr( ord(c) ) for c in a ] | |
ulist = lambda a: [ unicode_(i) for i in a ] | |
utuple = lambda a,b: ( unicode_(a), unicode_(b) ) | |
udict = lambda a: dict( [ utuple(*i) for i in a.items() ] ) | |
import csv | |
class CSV: | |
@staticmethod | |
def readlines(filename, delimiter=';'): | |
""" | |
Yield each csv's row at a time | |
""" | |
file_ = open( filename, 'rb' ) | |
rows = csv.reader( file_, delimiter = delimiter ) | |
for row in rows: | |
yield ulist( row ) | |
@staticmethod | |
def readjson(filename, delimiter=';'): | |
""" | |
Yield each csv's row as a dictionary except the first row | |
""" | |
file_ = open( filename, 'rb' ) | |
rows = csv.DictReader( file_, delimiter = delimiter ) | |
for row in rows: | |
yield udict( row ) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment