需求:在进行hadoop测试时,需要造大量数据,例如某个表存在56列,但实际程序逻辑只适用到某几列,我们造的数据 也只需要某几列
构造几列数据,转化为对应数据表格式
涉及模块:os,getopt,sys
输入:源格式,文本文件
输出:目标格式,文本文件
#!/usr/bin/python # -*- coding: utf-8 -*- #dataformat.py #this script change data from your source to the dest data format #2011-08-05 created version0.1 #2011-10-29 add row-row mapping ,default row value .rebuild all functions. version0.2 #next:add data auto generate by re expression import os,getopt,sys #读入文件,返回所有行 def read_file(path): f = open(path, "r") lines = f.readlines() f.close() return lines #处理一行,转为目标格式,返回目标行 def one_line_proc(parts, total, ft_map, outsp, empty_fill): toindex = 0 outline = "" keys = ft_map.keys() for i in range(1, total+1): if i in keys: fill_index = ft_map[i] if fill_index.startswith("d"): outline += fill_index[1:] else: outline += parts[int(fill_index)-1] else: outline += empty_fill if i !=total: outline += outsp #TODO:加入使用默认值列 若是以d开头,后面是默认,否则取文件对应列 done #TODO:这里根据这个判断长度也需要换掉 done return outline #处理入口,读文件,循环处理每一行,写出 #输入数据分隔符默认\t,输出数据默认分隔符\t def process(inpath, total, to, outpath, insp="\t", outsp="\t", empty_fill=""): #TODO:这里将to转为映射格式 done ft_map = {} in_count = 0 used_row = [] for to_row in to: if r"\:" not in to_row and len(to_row.split(":"))==2: used_row.append(int(to_row.split(":")[1])) if r"\=" not in str(to_row) and len(str(to_row).split("="))==2: pass else: in_count += 1 for to_row in to: if r"\=" not in str(to_row) and len(str(to_row).split("="))==2: ft_map.update({int(to_row.split("=")[0]):"d"+to_row.split("=")[1]}) continue elif r"\:" not in to_row and len(to_row.split(":"))==2: ft_map.update({int(to_row.split(":")[0]):to_row.split(":")[1]}) continue else: to_index = 0 for i in range(1, 100): if i not in used_row: to_index = i break ft_map.update({int(to_row):str(to_index)}) used_row.append(to_index) lines = read_file(inpath) f = open(outpath,"w") result=[] for line in lines: parts = line.strip("\n").split(insp) #TODO:这里判断长度必须换掉 done if len(parts) >= in_count: outline = one_line_proc(parts, total, ft_map, outsp, empty_fill) result.append(outline+"\n") f.writelines(result) f.close() #打印帮助信息 def help_msg(): print("功能:原数据文件转为目标数据格式") print("选项:") print("\t -i inputfilepath [必输,原文件路径]") print("\t -t n [必输,n为数字,目标数据总的域个数]") print("\t -a '1,3,4' [必输,域编号字符串,逗号分隔。指定域用原数据字段填充,未指定用'0'填充]") print("\t -o outputfilepath [可选,默认为 inputfilepath.dist ]") print("\t -F 'FS' [可选,原文件域分隔符,默认为\\t ]") print("\t -P 'OFS' [可选,输出文件的域分隔符,默认为\\t ]") sys.exit(0) #程序入口,读入参数,执行 def main(): try: opts,args = getopt.getopt(sys.argv[1:],"F:P:t:a:i:o:f:h") for op,value in opts: if op in ("-h","-H","--help"): help_msg() if op == "-i": inpath = value elif op == "-o": outpath = value elif op == "-t": total = int(value) elif op == "-a": to = value.split(",") elif op == "-F": insp = value.decode("string_escape") elif op == "-P": outsp = value.decode("string_escape") elif op == "-f": empty_fill = value #考虑下这边放在神马地方合适 if len(opts) < 3: print(sys.argv[0]+" : the amount of params must great equal than 3") sys.exit(1) except getopt.GetoptError: print(sys.argv[0]+" : params are not defined well!") if 'inpath' not in dir(): print(sys.argv[0]+" : -i param is needed,input file path must define!") sys.exit(1) if 'total' not in dir(): print(sys.argv[0]+" : -t param is needed,the fields of result file must define!") sys.exit(1) if 'to' not in dir(): print(sys.argv[0]+" : -a param is needed,must assign the field to put !") sys.exit(1) if not os.path.exists(inpath): print(sys.argv[0]+" file : %s is not exists"%inpath) sys.exit(1) if 'empty_fill' not in dir(): empty_fill = '' tmp=[] for st in to: tmp.append(str(st)) to=tmp if 'outpath' not in dir(): outpath = inpath+".dist" if 'insp' in dir() and 'outsp' in dir(): process(inpath,total,to,outpath,insp,outsp,empty_fill=empty_fill) elif 'insp' in dir(): process(inpath,total,to,outpath,insp,empty_fill=empty_fill) elif 'outsp' in dir(): process(inpath,total,to,outpath,outsp=outsp,empty_fill=empty_fill) else: process(inpath,total,to,outpath,empty_fill=empty_fill) if __name__ =="__main__": main()
使用说明:
功能:可指定输入分隔,输出分隔,无配置字段填充,某列默认值
可按顺序填充,也可乱序映射填充
输入:输入文件路径
选项:
-i “path” |
必设 |
输入文件路径 |
-t n |
必设 |
目标数据表总列数 |
-a “r1,r2” |
必设 |
将要填充的列号列表,可配置默认值,可配置映射 |
-o “path” |
可选 |
输出文件路径,默认为 输入文件路径.dist |
-F “IFS” |
可选 |
输入文件中字段域分隔符,默认\t |
-P ”OFS” |
可选 |
输出文件中字段域分隔符,默认\t |
-f “” |
可选 |
指定未配置列的填充内容,默认为空 |
-h |
单独 |
查看帮助信息 |
列填充的配置示例:
普通用法【最常用】
命令:./dataformat.py –i in_file –t 65 -a “22,39,63” –F “^I” –P “^A” –f “0”
说明:
命令: ./dataformat.py -i in_file –t 30 –a “3=tag_1,9,7,12=0.0” –o out_file
说明:
命令:./dataformat.py –i in_file –t 56 –a “3:2,9,5:3,1=abc,11”
说明: