R 包学习 - stringr()

stringr: R 语言字符串处理包

• 字符串拼接函数
  str_c: 字符串拼接。
  str_join: 字符串拼接，同str_c。
  str_trim: 去掉字符串的空格和TAB(\t)
  str_pad: 补充字符串的长度
  str_dup: 复制字符串
  str_wrap: 控制字符串输出格式
  str_sub: 截取字符串

• 字符串计算函数

str_count: 字符串计数
str_length: 字符串长度
str_sort: 字符串值排序
str_order: 字符串索引排序，规则同str_sort

• 字符串匹配函数

str_split: 字符串分割
str_split_fixed: 字符串分割，同str_split
str_subset: 返回匹配的字符串
word: 从文本中提取单词
str_detect: 检查匹配字符串的字符
str_match: 从字符串中提取匹配组。
str_match_all: 从字符串中提取匹配组，同str_match
str_replace: 字符串替换
str_replace_all: 字符串替换，同str_replace
str_replace_na:把NA替换为NA字符串
str_locate: 找到匹配的字符串的位置。
str_locate_all: 找到匹配的字符串的位置,同str_locate
str_extract: 从字符串中提取匹配字符
str_extract_all: 从字符串中提取匹配字符，同str_extract

• 字符串变换函数

str_conv: 字符编码转换
str_to_upper: 字符串转成大写
str_to_lower: 字符串转成小写,规则同str_to_upper
str_to_title: 字符串转成首字母大写,规则同str_to_upper

• 参数控制函数，仅用于构造功能的参数，不能独立使用。

boundary: 定义使用边界
coll: 定义字符串标准排序规则。
fixed: 定义用于匹配的字符，包括正则表达式中的转义符
regex: 定义正则表达式

> str_c('a','b')
[1] "ab"
> str_c('a','b',sep='-')
[1] "a-b"
> str_c(c('a','a1'),c('b','b1'),sep='-')
[1] "a-b"   "a1-b1"

> str_c(head(letters), collapse = "")
[1] "abcdef"
> str_c(head(letters), collapse = ", ")
[1] "a, b, c, d, e, f"

> str_c(c('a','a1'),c('b','b1'),collapse='-')
[1] "ab-a1b1"

#只过滤左边的空格
> str_trim("  left space\t\n",side='left') 
[1] "left space\t\n"

#只过滤右边的空格
> str_trim("  left space\t\n",side='right')
[1] "  left space"

#过滤两边的空格
> str_trim("  left space\t\n",side='both')
[1] "left space"

#过滤两边的空格
> str_trim("\nno space\n\t")
[1] "no space"

# 从左边补充空格，直到字符串长度为20
> str_pad("conan", 20, "left")
[1] "               conan"

# 从右边补充空格，直到字符串长度为20
> str_pad("conan", 20, "right")
[1] "conan               "

# 从左右两边各补充空格，直到字符串长度为20
> str_pad("conan", 20, "both")
[1] "       conan        "

# 从左右两边各补充x字符，直到字符串长度为20
> str_pad("conan", 20, "both",'x')
[1] "xxxxxxxconanxxxxxxxx"

> val <- c("abca4", 123, "cba2")

# 复制2次
> str_dup(val, 2)
[1] "abca4abca4" "123123"     "cba2cba2"  

# 按位置复制
> str_dup(val, 1:3)
[1] "abca4"        "123123"       "cba2cba2cba2"

> txt <- "I am Conan."

# 截取1-4的索引位置的字符串
> str_sub(txt, 1, 4)
[1] "I am"

# 截取1-6的索引位置的字符串
> str_sub(txt, end=6)
[1] "I am C"

# 截取6到结束的索引位置的字符串
> str_sub(txt, 6)
[1] "Conan."

# 分2段截取字符串
> str_sub(txt, c(1, 4), c(6, 8))
[1] "I am C" "m Con" 

# 通过负坐标截取字符串
> str_sub(txt, -3)
[1] "an."
> str_sub(txt, end = -3)
[1] "I am Cona"

> x <- "AAABBBCCC"

# 在字符串的1的位置赋值为1
> str_sub(x, 1, 1) <- 1; x
[1] "1AABBBCCC"

# 在字符串从2到-2的位置赋值为2345
> str_sub(x, 2, -2) <- "2345"; x
[1] "12345C"

> str_count('aaa444sssddd', "a")
[1] 3


> fruit <- c("apple", "banana", "pear", "pineapple")
> str_count(fruit, "a")
[1] 1 3 1 1
> str_count(fruit, "p")
[1] 2 0 1 3

# 用fixed匹配字符
> str_count(c("a.", ".", ".a.",NA), fixed("."))
[1]  1  1  2 NA

# 用\\匹配字符
> str_count(c("a.", ".", ".a.",NA), "\\.")
[1]  1  1  2 NA

> str_length(c("I", "am", "张丹", NA))
[1]  1  2  2 NA

> val <- "abc,123,234,iuuu"

# 以,进行分割
> s1<-str_split(val, ",");s1
[[1]]
[1] "abc"  "123"  "234"  "iuuu"

# 以,进行分割，保留2块
> s2<-str_split(val, ",",2);s2
[[1]]
[1] "abc"          "123,234,iuuu"

# 查看str_split()函数操作的结果类型list
> class(s1)
[1] "list"

# 用str_split_fixed()函数分割，结果类型是matrix
> s3<-str_split_fixed(val, ",",2);s3
     [,1]  [,2]          
[1,] "abc" "123,234,iuuu"

> class(s3)
[1] "matrix"

> val <- c("abc", 123, "cba")

# 全文匹配
> str_subset(val, "a")
[1] "abc" "cba"

# 开头匹配
> str_subset(val, "^a")
[1] "abc"

# 结尾匹配
> str_subset(val, "a$")
[1] "cba"

> val <- c("I am Conan.", "http://fens.me, ok")

# 默认以空格分割，取第一个位置的字符串
> word(val, 1)
[1] "I"               "http://fens.me,"
> word(val, -1)
[1] "Conan." "ok"    
> word(val, 2, -1)
[1] "am Conan." "ok"       

# 以,分割，取第一个位置的字符串 
> val<-'111,222,333,444'
> word(val, 1, sep = fixed(','))
[1] "111"
> word(val, 3, sep = fixed(','))
[1] "333"

> val <- c("abca4", 123, "cba2")

# 检查字符串向量，是否包括a
> str_detect(val, "a")
[1]  TRUE FALSE  TRUE

# 检查字符串向量，是否以a为开头
> str_detect(val, "^a")
[1]  TRUE FALSE FALSE

# 检查字符串向量，是否以a为结尾
> str_detect(val, "a$")
[1] FALSE FALSE FALSE

> val <- c("abc", 123, "cba")

# 匹配字符a，并返回对应的字符
> str_match(val, "a")
     [,1]
[1,] "a" 
[2,] NA  
[3,] "a" 

# 匹配字符0-9，限1个，并返回对应的字符
> str_match(val, "[0-9]")
     [,1]
[1,] NA  
[2,] "1" 
[3,] NA  

# 匹配字符0-9，不限数量，并返回对应的字符
> str_match(val, "[0-9]*")
     [,1] 
[1,] ""   
[2,] "123"
[3,] ""  

• str_replace

> val <- c("abc", 123, "cba")

# 把目标字符串第一个出现的a或b，替换为-
> str_replace(val, "[ab]", "-")
[1] "-bc" "123" "c-a"

# 把目标字符串所有出现的a或b，替换为-
> str_replace_all(val, "[ab]", "-")
[1] "--c" "123" "c--"

# 把目标字符串所有出现的a，替换为被转义的字符
> str_replace_all(val, "[a]", "\1\1")
[1] "\001\001bc" "123"        "cb\001\001"

参考：http://blog.fens.me/r-stringr/