近期天地图项目处理数据时由于原始数据质量较差,属性字段中多有全角字符,带来后期处理与开发不便,因此做了个属性全角换半角的脚本如下
经验:Unicode处理
# -*- coding: utf-8 -*-
__author__ = 'tanshuai'
import arcpy
from arcpy import env
fullCorner = ['0' , '1' , '2' , '3' , '4' ,
'5' , '6' , '7' , '8' , '9' ,
'A' , 'B' , 'C' , 'D' , 'E' ,
'F' , 'G' , 'H' , 'I' , 'J' ,
'K' , 'L' , 'M' , 'N' , 'O' ,
'P' , 'Q' , 'R' , 'S' , 'T' ,
'U' , 'V' , 'W' , 'X' , 'Y' ,
'Z' , 'a' , 'b' , 'c' , 'd' ,
'e' , 'f' , 'g' , 'h' , 'i' ,
'j' , 'k' , 'l' , 'm' , 'n' ,
'o' , 'p' , 'q' , 'r' , 's' ,
't' , 'u' , 'v' , 'w' , 'x' ,
'y' , 'z' , '-' , ' ' , ':' ,
'.' , ',' , '/' , '%' , '#' ,
'!' , '@' , '&' , '(' , ')' ,
'<' , '>' , '"' , ''' , '?' ,
'[' , ']' , '{' , '}' , '\' ,
'|' , '+' , '=' , '_' , '^' ,
'¥' , ' ̄' , '`']
halfCorner = ['0', '1', '2', '3', '4',
'5', '6', '7', '8', '9',
'A', 'B', 'C', 'D', 'E',
'F', 'G', 'H', 'I', 'J',
'K', 'L', 'M', 'N', 'O',
'P', 'Q', 'R', 'S', 'T',
'U', 'V', 'W', 'X', 'Y',
'Z', 'a', 'b', 'c', 'd',
'e', 'f', 'g', 'h', 'i',
'j', 'k', 'l', 'm', 'n',
'o', 'p', 'q', 'r', 's',
't', 'u', 'v', 'w', 'x',
'y', 'z', '-', ' ', ':',
'.', ',', '/', '%', '#',
'!', '@', '&', '(', ')',
'<', '>', '"', '\'','?',
'[', ']', '{', '}', '\\',
'|', '+', '=', '_', '^',
'¥','~', '`']
def replaceCharacter(fldValueText):
for full in fullCorner:
if fldValueText.find(full) > -1:
index = fullCorner.index(full)
half = halfCorner[index];
fldValueText = fldValueText.replace(full, half)
print fldValueText
return fldValueText
env.workspace = "E:\\test2"
length = len(fullCorner)
cursor = arcpy.UpdateCursor("test3.shp")
try:
for row in cursor:
fieldList = arcpy.ListFields("test3.shp")
for field in fieldList:
if field.type == "String":
value = row.getValue(field.name)
valueTxt = value.encode('utf-8')
if len(valueTxt) > 0:
print valueTxt
resultValue = replaceCharacter(valueTxt)
row.setValue(field.name, resultValue)
cursor.updateRow(row)
print resultValue
else:
continue
except Exception,e:
print("错误"+e)
finally:
del row,cursor
print("complete!")