5章代码

5.3  获得汉字长度和分解

#coding=utf8
import arcpy

import os
import sys
import math
import string
from collections import namedtuple

#判断字符串是否为汉字
def isChineseWord(string):
    if string.isalpha():
        if ord(string) in range(65,91) or ord(string) in range(97,123) :
            print("是字母")
            return  False
        else:
            print("是汉字")
            return True
    print("不是汉字也不是字母")
    return False
#返回汉字和英文数量
def getChinesenum(s):
    s_len = len(s)
    cnum=0
    for c in s:
        if isChineseWord(c):
            cnum+=1
    return cnum,s_len-cnum


def str_count(s):
    '''找出字符串中的中英文、空格、数字、标点符号个数'''

    count_en = count_dg = count_sp = count_zh = count_pu = 0
    s_len = len(s)
    for c in s:
        if c in string.ascii_letters: #英文
            count_en += 1
        elif c.isdigit(): #数字
            count_dg += 1
        elif c.isspace(): #空格
            count_sp += 1
        elif c.isalpha(): #方法检测字符串是否只由字母组成。
            count_zh += 1
        else:
            count_pu += 1 #标点
    total_chars = count_zh + count_en + count_sp + count_dg + count_pu
    if total_chars == s_len:
        return namedtuple('Count', ['total', 'zh', 'en', 'space', 'digit', 'punc'])(s_len, count_zh, count_en, count_sp, count_dg, count_pu)
    else:
        print('Something is wrong!')
        return None
    return None

#汉字长度
def getcharlength(mystr): #在u下一个汉字长度为3
    lenTxt = len(mystr)
    lenTxt_utf8 = len(mystr.decode('utf-8'))
    size = int((lenTxt_utf8 - lenTxt)/2 + lenTxt)
    return size #如果返回为None，就是没有返回值

def getlength():
    ss="我们的gis"
    num=len(ss)
    arcpy.AddMessage(u"{1} length={0}".format(num,ss)) #u加不加都一样 一个汉字为3
    arcpy.AddMessage("{1} length={0}".format(num,ss))
    ss=u"我们的gis" #加u，一个汉字为1
    num=len(ss)
    arcpy.AddMessage(u"ss={1} length={0}".format(num,ss))
    arcpy.AddMessage("ss={1} length={0}".format(num,ss))

    ss=u"我们的gis" #加u，一个汉字为1
    num=getcharlength(ss)
    arcpy.AddMessage("{1} length={0}".format(num,ss))
    ss="我们的gis" #不加u，一个汉字为2
    num=getcharlength(ss)
    arcpy.AddMessage("{1} length={0}".format(num,ss))

    s = u'我们的gis gisoracle 2019.11.07' #一定要加u
    count = str_count(s)
    arcpy.AddMessage(s)
    arcpy.AddMessage('该字符串共有 {} 个字符，其中有 {} 个汉字，{} 个英文，{} 个空格，{} 个数字，{} 个标点符号。'.format(count.total, count.zh, count.en, count.space, count.digit, count.punc))
    cnum,enum=getChinesenum(s)
    arcpy.AddMessage('该字符串共有 {} 汉字字符，非汉字{}'.format(cnum,enum))
    s=u"我们的gis"
    arcpy.AddMessage('该字符串 {} 取左边4个{}'.format(s,s[0:4]))
    s="我们的gis" #下面没有取出来，一定加u
    arcpy.AddMessage('该字符串 {} 取左边4个{}'.format(s,s[0:4]))

def printinfo(): #不能名称为print
    arcpy.AddMessage("====================我们都是Python程序员=============")
    arcpy.AddMessage(u"====================我们都是Python程序员=============") #加不加都一样
    arcpy.AddMessage("{0:<20s}1".format(u"我们都是程序员"))
    arcpy.AddMessage("{0:<20s}12345678901234567890".format("我们都是程序员")) #需要加u
    arcpy.AddMessage("%-20s12345678901234567890"%(u"我们都是程序员"))
    arcpy.AddMessage("%-20s12345678901234567890"%("我们都是程序员")) #需要加u
    arcpy.AddMessage(u"没有对应数据".encode('gbk'))  # 汉字乱码的解决
#把字符串按汉字固定2为截取
def gettrim(s,n):

    num=0
    first=""
    after=""
    for c in s:
        if isChineseWord(c):
            num+=2 #汉字2位
        else:
            num+=1 #其他1位
        if num<=n:
            first=first+c
        else:
            after=after+c
    return first,after
def strtrim():
    s=u"我们1的gis1"
    first,after=gettrim(s,6)
    arcpy.AddMessage('{} 取6位,前{} 后{}'.format(s,first,after))
    s="我们1的gis1" #不加u，一个汉字3位
    first,after=gettrim(s,6)
    arcpy.AddMessage('{} 取6位,前{} 后{}'.format(s,first,after))

def Main():
    getlength()
    strtrim()
    printinfo()
Main()

5.4  表中读写汉字

#coding=utf8
import arcpy
import os
import sys
import math
def readHZ():
    fields = [inField]
    with arcpy.da.SearchCursor(inTable, fields) as cursor:
        i=1
        for row in cursor:
            arcpy.AddMessage(u"序号{0}, 字段={1}, 值={2}".format(i,inField,row[0]))
            i=i+1

def updateHZ():
    fields = [inField]
    with arcpy.da.UpdateCursor(inTable, fields) as cursor:
        i=1
        for row in cursor:
            #mystr=row[0]+u" 长度"+str(i)
            mystr=row[0]+" 长度"+str(i) #加u，不加u都可以
            mystr=mystr[0:50]
            row[0]=mystr
            cursor.updateRow(row)
            i=i+1
def insertHZ():
    fields = (inField)
    cursor = arcpy.da.InsertCursor(inTable, fields)
    for x in xrange(0, 2):
        #cursor.insertRow((str(x*100)+u"我爱你",)) #最后必须加,可以不加u 加u和不加u一样
        cursor.insertRow((str(x*100)+"我爱你",))
    del cursor
def main():
    readHZ()
    updateHZ()
    insertHZ()

inTable=arcpy.GetParameterAsText(0)
inField=arcpy.GetParameterAsText(1)
main()

5.5  读写文本文件中汉字

#coding=utf8
import arcpy

import os
import sys
import math
import codecs
def ReadTXTNEW(txtFile):
    f = codecs.open(txtFile,'r','gbk') #'utf-8'

    lines = f.readlines()
    f.close()
    return lines

def ReadTXT(txtFile):

    f = open(txtFile)
    mystr= f.read()
    f.close()
    return mystr

#返回数组
def ReadTXTList(txtFile):
    sumlist=[]
    f = open(txtFile,"r") #
    try:
        lines = f.readlines()
        for line in lines:
            curline=line.replace('
', '') #删除

            sumlist.append(curline)
    finally:
        f.close()
    return sumlist

def WriteTXT(mylist,txtFile):
    wfiles = open(txtFile,'w')
    num=len(mylist)

    try:
        for i in range(num):
            wfiles.write(mylist[i]+'
')
    finally:
        wfiles.close()
    if wfiles:
        del wfiles

def main(inFile):
    pList=ReadTXTList(inFile)
    num=len(pList)
    for i in range(num):
        arcpy.AddMessage("{0}={1}".format(i,pList[i]))
        #arcpy.AddMessage("u{0}={1}".format(i,pList[i])) #这里不需要加u，加u出错误，因为没有汉字
    txtFile=inFile.lower().replace('.txt', '1.txt')
    mystr=u"我爱你 gisoracle"
    pList.append(mystr.encode("GBK")) ##解决中文乱码问题，直接pList.append(mystr)出来乱码
    #pList.append(mystr) #错误
    WriteTXT(pList,txtFile)
inFile=arcpy.GetParameterAsText(0)
main(inFile)

5.6  元组和列表中汉字使用

#coding=utf8
import arcpy

import os
import sys
import math

##将列表转换为元组。
def usetuple():
    tup1 = ('我爱你 qq', '我爱你 gisorcle', 2019, 2000) #不要加u,否则后面乱码如 u'u6211u7231u4f60 gisorcle'
    num=len(tup1)
    for i in range(num):
        arcpy.AddMessage("{0}={1}".format(i,tup1[i]))
    ss=str(tup1[2:4]) #从2，4，不包括4

    arcpy.AddMessage("{0}".format(ss))
    ss=str(tup1[0:1]) #从0，1，不包括1
    ss = ss.decode('string-escape')# 不加ss = ss.decode('string-escape') 输出 xe6x88x91xe7x88xb1xe4xbdxa0
    arcpy.AddMessage("{0}".format(ss))

#列表
def useList():
    List = ['我爱你 qq', '我爱你 gisorcle'] #不要加u,否则后面乱码入 u'u6211u7231u4f60 gisorcle'
    List.append("我爱")
    num=len(List)
    for i in range(num):
        arcpy.AddMessage("{0}={1}".format(i,List[i]))
    ss=str(List[0:3]) #从0，3，不包括3
    ss = ss.decode('string-escape')# 不加ss = ss.decode('string-escape') 输出 xe6x88x91xe7x88xb1xe4xbdxa0
    arcpy.AddMessage("{0}".format(ss))

def main():
    useList()
    usetuple()
main()

5.7  字典使用

#coding=utf8
import arcpy

import os
import sys
import math
def main():
    d = {}
    fields = arcpy.ListFields(inFeature)
    for field in fields:
        d[field.name] = field.aliasName
    for key in d.keys():
        arcpy.AddMessage("{0}={1}".format(key,d[key]))
    for item in d.items():
        ss = str(item).decode("unicode_escape")
        arcpy.AddMessage("===={0}".format(ss))

inFeature=arcpy.GetParameterAsText(0)
main()