0
我使用R中的调查包来分析国家犯罪受害调查的数据。 Thomas Lumley的书复杂调查：使用R和他的调查软件包中的帮助文件的分析指南使用正则表达式来表示像这样的复制权重，PERREPWGT[1-160]+。但是，这个表达式并不总是标识所有的重复重量。如果我将+号改为？正则表达式正常工作，并标识所有重复权重。下面显示了一个简短的测试案例。我对正则表达式不太自信。这是对正则表达式的正确更改还是有更可靠的方式来编写模式？复杂调查中重复权重的正则表达式R包
x<-c("V3067", "V3068", "V3069", "V3070", "V3071", "V3072", "V3073", "V3074", "V3075", "V3076", "V3077", "V3078",
"V3079", "V3080", "WGTPERCY", "V3081", "V3082", "PERREPWGT1", "PERREPWGT2", "PERREPWGT3", "PERREPWGT4",
"PERREPWGT5", "PERREPWGT6", "PERREPWGT7", "PERREPWGT8", "PERREPWGT9", "PERREPWGT10", "PERREPWGT11",
"PERREPWGT12", "PERREPWGT13", "PERREPWGT14", "PERREPWGT15", "PERREPWGT16", "PERREPWGT17", "PERREPWGT18",
"PERREPWGT19", "PERREPWGT20", "PERREPWGT21", "PERREPWGT22", "PERREPWGT23", "PERREPWGT24", "PERREPWGT25",
"PERREPWGT26", "PERREPWGT27", "PERREPWGT28", "PERREPWGT29", "PERREPWGT30", "PERREPWGT31", "PERREPWGT32",
"PERREPWGT33", "PERREPWGT34", "PERREPWGT35", "PERREPWGT36", "PERREPWGT37", "PERREPWGT38", "PERREPWGT39",
"PERREPWGT40", "PERREPWGT41", "PERREPWGT42", "PERREPWGT43", "PERREPWGT44", "PERREPWGT45", "PERREPWGT46",
"PERREPWGT47", "PERREPWGT48", "PERREPWGT49", "PERREPWGT50", "PERREPWGT51", "PERREPWGT52", "PERREPWGT53",
"PERREPWGT54", "PERREPWGT55", "PERREPWGT56", "PERREPWGT57", "PERREPWGT58", "PERREPWGT59", "PERREPWGT60",
"PERREPWGT61", "PERREPWGT62", "PERREPWGT63", "PERREPWGT64", "PERREPWGT65", "PERREPWGT66", "PERREPWGT67",
"PERREPWGT68", "PERREPWGT69", "PERREPWGT70", "PERREPWGT71", "PERREPWGT72", "PERREPWGT73", "PERREPWGT74",
"PERREPWGT75", "PERREPWGT76", "PERREPWGT77", "PERREPWGT78", "PERREPWGT79", "PERREPWGT80", "PERREPWGT81",
"PERREPWGT82", "PERREPWGT83", "PERREPWGT84", "PERREPWGT85", "PERREPWGT86", "PERREPWGT87", "PERREPWGT88",
"PERREPWGT89", "PERREPWGT90", "PERREPWGT91", "PERREPWGT92", "PERREPWGT93", "PERREPWGT94", "PERREPWGT95",
"PERREPWGT96", "PERREPWGT97", "PERREPWGT98", "PERREPWGT99", "PERREPWGT100", "PERREPWGT101", "PERREPWGT102",
"PERREPWGT103", "PERREPWGT104", "PERREPWGT105", "PERREPWGT106", "PERREPWGT107", "PERREPWGT108", "PERREPWGT109",
"PERREPWGT110", "PERREPWGT111", "PERREPWGT112", "PERREPWGT113", "PERREPWGT114", "PERREPWGT115", "PERREPWGT116",
"PERREPWGT117", "PERREPWGT118", "PERREPWGT119", "PERREPWGT120", "PERREPWGT121", "PERREPWGT122", "PERREPWGT123",
"PERREPWGT124", "PERREPWGT125", "PERREPWGT126", "PERREPWGT127", "PERREPWGT128", "PERREPWGT129", "PERREPWGT130",
"PERREPWGT131", "PERREPWGT132", "PERREPWGT133", "PERREPWGT134", "PERREPWGT135", "PERREPWGT136", "PERREPWGT137",
"PERREPWGT138", "PERREPWGT139", "PERREPWGT140", "PERREPWGT141", "PERREPWGT142", "PERREPWGT143", "PERREPWGT144",
"PERREPWGT145", "PERREPWGT146", "PERREPWGT147", "PERREPWGT148", "PERREPWGT149", "PERREPWGT150", "PERREPWGT151",
"PERREPWGT152", "PERREPWGT153", "PERREPWGT154", "PERREPWGT155", "PERREPWGT156", "PERREPWGT157", "PERREPWGT158",
"PERREPWGT159", "PERREPWGT160")
#Regular expression consistent with examples in survey package
#Does NOT identify all replicate weight names
grep("PERREPWGT[1-160]+", x)
#Correctly identifies array index 18 through 177
grep("PERREPWGT[1-160]?", x)