作业20190429

from pathlib import Path,os
import shutil
#定义源文件
p = Path("one/b/text.txt")
if not p.parent.exists():
    p.parent.mkdir(parents=True)
p.write_text("我是源文件")

#定义目标文件
des = Path("one2/b/abc.txt")
if not des.parent.exists():
    des.parent.mkdir(parents=True)

#拷贝源文件到目标文件
# shutil.copy2(p,des)
with open(p,"rb",) as src:
    with open(des,"wb") as f:
        buffer = 16*1024
        while 1:
            temp = src.read(buffer);
            if not temp:
                break
            f.write(temp)
shutil.copystat(p,des)

import pathlib,shutil,random,os,string,re
#检测目录环境是否干净，如果有清空。
trepdir = pathlib.Path("a")
if trepdir.exists():
    shutil.rmtree(trepdir)

#开始
down = pathlib.Path("")
src = pathlib.Path(down,"a/b/c/d")
if not src.exists():
    src.mkdir(parents=True)
arrpath = [] #记录创建文件可能出现的目录
temp = src
while temp!=down:
    arrpath.append(temp)
    temp = temp.parent
# 创建文件
for i in range(50):
    os.close(os.open(str(arrpath[random.randint(0,3)])+"/"+"".join(random.choices(string.ascii_lowercase,k=4)),os.O_CREAT))

# 创建复制文件路径
targe = pathlib.Path(down,"dst/")
# def fun(src,names):
#     rexit = re.compile('^[xyz].*')
#     reset = set()
#     for i in names:
#         if pathlib.Path(src,i).is_dir():
#             continue
#         elif rexit.match(i):
#             continue
#         else:
#             reset.add(i)
#     return reset
#fun =lambda src,names: {*filter(lambda name: not re.compile('^[xyz].*').match(name),(i for i in names if not pathlib.Path(src,i).is_dir()))}
#使用一行解决
fun = lambda src,names:{name for name in names if not pathlib.Path(src,name).is_dir() and not re.compile('^[xyz].*').match(name)}
#检测拷贝目录是否干净，如果存在清空
if targe.exists():
    shutil.rmtree(targe)
#拷贝
shutil.copytree(pathlib.Path("a"),targe,ignore=fun)

#第二种实现
import shutil,random,os,string,re
from pathlib import Path
#检测目录环境是否干净，如果有清空。
trepdir = pathlib.Path("a")
if trepdir.exists():
    shutil.rmtree(trepdir)
    
#定义当前工作目录
down = Path("")
#定义目录结构
src = Path("a/b/c/d")
arrpath = [src] + list(src.parents)[:-1]
#如果目录不存在创建目录。
if not src.exists(): src.mkdir(parents=True)
#生成50个文件
for i in range(50):
    (down / random.choice(arrpath) / "".join(random.choices(string.ascii_lowercase,k=4))).touch()

#定义拷贝目录
targetdir = Path(down,"dst/")

#检测拷贝目录是否干净，如果存在清空
if targe.exists():
    shutil.rmtree(targe)
#定义过滤函数
def fun(src,names,rexit=set("xyz")):
    return {*filter(lambda name: (name[0] not in rexit and not pathlib.Path(src,name).is_dir()),names)}
#拷贝
shutil.copytree(pathlib.Path("a"),targe,ignore=fun)

from pathlib import Path
from collections import OrderedDict
class xdddict:
    def __init__(self):
        self.xdict = OrderedDict()
        self.sortxdict = None
    
    #统计单词
    def countword(self,arr:list):
        for word in arr:
            word = word.lower()
            self.xdict[word] = self.xdict.get(word,0)+1
    
    # 刷新排序列表
    def refreshsortxdict(self):
        self.sortxdict = sorted(self.xdict.items(),key = lambda x:x[1],reverse=True)
    
    #获取top10
    def getTop10(self):
        if not self.sortxdict:
            self.refreshsortxdict()
        return self.sortxdict[:10]

            
fil = Path("sample.txt")
worddict = xdddict()
with fil.open(encoding="utf-8",newline="") as f:
    arr = [",",".","(",")","-","/",".."]
    for line in f:
        line = line.strip()
        for i in arr:
            line = line.replace(i," ")
        worddict.countword(line.split())
print(worddict.getTop10())

from pathlib import Path
from collections import OrderedDict
class xdddict:
    def __init__(self,overlook:set=None):
        self.xdict = OrderedDict()
        self.sortxdict = None
        if overlook==None:
            self.overlook = set()
        else:
            self.overlook = {i.lower() for i in overlook}
    
    #统计单词
    def countword(self,arr:list):
        for word in arr:
            word = word.lower()
            #过滤不需要统计的单词
            if word in self.overlook: continue 
            self.xdict[word] = self.xdict.get(word,0)+1
    
    # 刷新排序列表
    def refreshsortxdict(self):
        self.sortxdict = sorted(self.xdict.items(),key = lambda x:x[1],reverse=True)
    
    #获取top10
    def getTop10(self):
        if not self.sortxdict:
            self.refreshsortxdict()
        return self.sortxdict[:10]

            
fil = Path("sample.txt")
overlook = {"the","is","a","of","and","to","on","return","os","if","in","are","as",
            "for","an","this","or","true","false","not","be","by","that"}
worddict = xdddict(overlook)
with fil.open(encoding="utf-8",newline="") as f:
    arr = [",",".","(",")","-","/","..","`s"]
    for line in f:
        line = line.strip()
        for i in arr:
            line = line.replace(i," ")
        
        worddict.countword(line.split())
print(worddict.getTop10())

from pathlib import Path
class word:
    def __init__(self):
        self.worddict = {} #记录单词数量字典
        pass
    
    #根据行获取单词，过滤不必要字符
    def deallist(self,line:str,outchar = set("""~!@#$/\%^&*()_+-'"\r\n., """)):
        k=0
        leng = len(line)
        for i,one in enumerate(line):
            if one in outchar:
                if k!=i:
                    yield line[k:i].lower()
                k = i + 1
        if k<leng:
            yield line[k:].lower()
    
    #统计单词
    def countword(self,filepath:Path,encoding=None,stopwords=set()):
        with Path(filepath).open("r",encoding=encoding) as f:
            for line in f:
                for word in filter(lambda word: word not in stopwords,self.deallist(line)):
                    self.worddict[word] = self.worddict.get(word,0)+1

    def getTopWord(self,top=10):
        return sorted(self.worddict.items(),key=lambda k: k[1],reverse=True)[:10]
    
if __name__== "__main__":
    wd = word() #创建单词统计类
    stopwords = {"the","is","a","of","and","to","on","return","os","if","in","are","as",
            "for","an","this","or","true","false","not","be","by","that"} #定义停用单词
    wd.countword(Path("sample.txt"),"utf-8",stopwords=stopwords) #开始统计单词
    print(wd.getTopWord()) #获取统计前10名

[DEFAULT]
a = test

[mysql]
default-character-set=utf8
a=1000

[mysqld]
datadir = /dbserver/data
port = 33060
character-set-server=utf8
sql_mode=NO_ENGINE_SUBSTITUTION,STRICT_TRANS_TABLES

import json,configparser
from pathlib import Path
initxt = """\
[DEFAULT]
a = test

[mysql]
default-character-set=utf8
a=1000

[mysqld]
datadir = /dbserver/data
port = 33060
character-set-server=utf8
sql_mode=NO_ENGINE_SUBSTITUTION,STRICT_TRANS_TABLES
"""  
#配置作业环境(创建文件)
with open("mysql.ini","wb") as f:
    f.write(initxt.encode(encoding="utf-8"))
    
#读取文件
cfg = configparser.ConfigParser()
cfg.read("mysql.ini",encoding="utf-8")

#转换json
dt = {}
for i in cfg.items():
    dt[i[0]] = {k:v for k,v in cfg.items(i[0])}
js = json.dumps(dt)
print(js)

import argparse,os,datetime
from pathlib import Path
class ls:
    def __init__(self):
        self.modedict = {0o040000:"d",0o020000:"c",0o060000:"b",0o100000:"f",0o010000:"p",0o120000:"l",0o140000:"s"}
        self.units = ["B","K","M","G","T"]
    def showdir(self,overlook=False,h=False,l=False,*,paths:list=None):
        if not paths:
            paths=[""]
        for i in paths:
            print(i)
            arrname = [*Path(i).iterdir()]
            arrname.sort(key=lambda p: p.name)
            for p in arrname:
                if (not overlook) and p.name.startswith("."):
                    continue
                if l:
                    self.showdir_l(p,h)
                else:
                    print(p.name)
    
    #显示文件详细信息
    def showdir_l(self,p:Path,h):
        stat = p.stat()
        stime = datetime.datetime.fromtimestamp(stat.st_atime).strftime("%Y-%m-%d %H:%M:%S")
        print(self.getstrmode(stat.st_mode),stat.st_nlink,stat.st_gid,stat.st_uid,self.getsize(p,h),stime,p.name,sep="\t")
    
    #获取文件大小
    def getsize(self,p:Path,h):
        size = p.stat().st_size
        if h:
            i = 0
            while size > 1024:
                tempsize = int(size/1024)
                if not tempsize:
                    break
                else:
                    i += 1
                    size = tempsize
            size = str(size)+self.units[i]
        else:
            size = str(size)+"B"
        return size
    
    #获取文件权限
    def getstrmode(self,mode:int):
        strmod = self.modedict.get(mode & 0o170000,"-")
        temp = bin(mode)
        temp = temp[len(temp)-9:]
        i = 2
        while i<len(temp):
            if temp[i-2]=="1": 
                strmod += "r"
            else:
                strmod += "-"
            if temp[i-1]=="1":
                strmod += "w"
            else:
                strmod += "-"
            if temp[i]=="1":
                strmod += "x"
            else:
                strmod += "-"
            i += 3
        return strmod+"."
            

ls = ls()
# ls.showdir()
        
parser = argparse.ArgumentParser(description="ls 显示当前文件信息",add_help=False)
# 注册属性函数
# parser.add_argument(dest="showdir",action="store_const",const =ls.showdir)
# 添加-a,-all参数
parser.add_argument("-a","-all",dest="overlook",action="store_true")
parser.add_argument("-l",action="store_true")
parser.add_argument("-h",action="store_true")
parser.add_argument("paths",nargs="*")

# args = parser.parse_args() #命令行时启动
args = parser.parse_args("-lah a one ./".split())
# print(args.paths)
ls.showdir(overlook=args.overlook,l=args.l,h=args.h,paths=args.paths)

#ls命令进阶
import argparse,datetime,stat
from pathlib import Path
class ls :  
    def listdir(self,overlook=False,h=False,l=False,paths:list=None):
        for i in paths:
            yield (-1,i)
            for p in sorted(Path(i).iterdir(),key=lambda k:k.name): #先排序
                if not overlook and p.name[0]==".": #是否显示点开头的文件
                    continue
                if l: #是否显示详细信息
                    st = p.stat()
                    stime = datetime.datetime.fromtimestamp(st.st_atime).strftime("%Y-%m-%d %H:%M:%S")
                    #mode = stat.filemode(st.st_mode) #调用系统filemode获取对应的字符串权限
                    mode = self.getfiletype(p) + self.getfilemode(st.st_mode)
                    yield (mode,st.st_nlink,st.st_uid,st.st_gid,self.getsize(st.st_size,h),stime,p.name)
                else:
                    yield (p.name,)
    
    #获取文件权限
    def getfilemode(self,mode,arr = "rwxrwxrwx"):
        return "".join(arr[8-i] if mode >> i & 1 else "-" for i in range(8,-1,-1))
    
    def getfiletype(self,p:Path):
        if p.is_dir():
            return "d"
        elif p.is_block_device():
            return "b"
        elif p.is_char_device():
            return "c"
        elif p.is_socket():
            return "s"
        elif p.is_symlink():
            return "l"
        else:
            return "-"
    
    #获取文件大小
    def getsize(self,size,h,unitx = " KMGP"):
        if not h:
            return str(size)
        length = len(unitx)-1
        i = 0
        while size>1024 and i<length:
            size = size//1024
            i +=1
        return str(size)+ ("" if i==0 else unitx[i])
        
        

if __name__ == "__main__":
    parser = argparse.ArgumentParser(prog="ls",description="ls 显示文件",add_help=False)
    parser.add_argument("-a","-all",dest="overlook",action="store_true")
    parser.add_argument("-l",action="store_true")
    parser.add_argument("-h",action="store_true")
    parser.add_argument("paths",nargs="*",default=["."])
    args = parser.parse_args("-lah ./ ../".split())
    lsdir = ls()
    for i in lsdir.listdir(args.overlook,args.h,args.l,args.paths):
        if i[0] == -1:
            print("\n",i[1])
        else:
            if len(i)>1:
                print(*i,sep="\t")
            else:
                print(*i,end="\t",sep="")