[我希望仅能在给定的定界符集合之外使用grepl()和gsub()，例如，我希望能够忽略引号之间的文本。
这是我想要的输出：
grepl2("banana", "'banana' banana \"banana\"", escaped =c('""', "''"))
#> [1] TRUE
grepl2("banana", "'banana' apple \"banana\"", escaped =c('""', "''"))
#> [1] FALSE
grepl2("banana", "{banana} banana {banana}", escaped = "{}")
#> [1] TRUE
grepl2("banana", "{banana} apple {banana}", escaped = "{}")
#> [1] FALSE
gsub2("banana", "potatoe", "'banana' banana \"banana\"")
#> [1] "'banana' potatoe \"banana\""
gsub2("banana", "potatoe", "'banana' apple \"banana\"")
#> [1] "'banana' apple \"banana\""
gsub2("banana", "potatoe", "{banana} banana {banana}", escaped = "{}")
#> [1] "{banana} potatoe {banana}"
gsub2("banana", "potatoe", "{banana} apple {banana}", escaped = "{}")
#> [1] "{banana} apple {banana}"
实际案例中可能引用了不同数量和顺序的子字符串。
我已经编写了以下用于这些情况的函数，但是它们很笨拙，gsub2()根本不健壮，因为它暂时用占位符替换了分隔的内容，并且这些占位符可能会受到后续操作的影响。
regex_escape <-
function(string,n = 1) {
for(i in seq_len(n)){
string <- gsub("([][{}().+*^$|\\?])", "\\\\\\1", string)
}
string
}
grepl2 <-
function(pattern, x, ignore.case = FALSE, perl = FALSE, fixed = FALSE,
useBytes = FALSE, escaped =c('""', "''")){
escaped <- strsplit(escaped,"")
# TODO check that "escaped" delimiters are balanced and don't cross each other
for(i in 1:length(escaped)){
close <- regex_escape(escaped[[i]][[2]])
open <- regex_escape(escaped[[i]][[1]])
pattern_i <- sprintf("%s.*?%s", open, close)
x <- gsub(pattern_i,"",x)
}
grepl(pattern, x, ignore.case, perl, fixed, useBytes)
}
gsub2 <- function(pattern, replacement, x, ignore.case = FALSE, perl = FALSE,
fixed = FALSE, useBytes = FALSE, escaped =c('""', "''")){
escaped <- strsplit(escaped,"")
# TODO check that "escaped" delimiters are balanced and don't cross each other
matches <- character()
for(i in 1:length(escaped)){
close <- regex_escape(escaped[[i]][[2]])
open <- regex_escape(escaped[[i]][[1]])
pattern_i <- sprintf("%s.*?%s", open, close)
ind <- gregexpr(pattern_i,x)
matches_i <- regmatches(x, ind)[[1]]
regmatches(x, ind)[[1]] <- paste0("((",length(matches) + seq_along(matches_i),"))")
matches <- c(matches, matches_i)
}
x <- gsub(pattern, replacement, x, ignore.case, perl, fixed, useBytes)
for(i in seq_along(matches)){
pattern <- sprintf("\\(\\(%s\\)\\)", i)
x <- gsub(pattern, matches[[i]], x)
}
x
}
是否有使用正则表达式且没有占位符的解决方案？请注意，我当前的函数支持多对定界符，但我对仅支持一对定界符的解决方案感到满意，并且不会尝试在简单引号之间匹配子字符串。
也可以使用不同的定界符，例如{和}而不是2 "或2 '，如果有帮助的话。
我也可以强加perl = TRUE
我在grepl2上试过手，但还没有破解gsub2。无论如何，这只会删除提供的escaped字符的最短对之间的所有字符（不包括新行）。它也应该很好地扩展。如果采用此解决方案，则可能需要进行内置检查，以确保escaped字符的pairs不带空格（或改用substr()。希望对您有所帮助！
grepl3 <-
function(pattern, x, ignore.case = FALSE, perl = FALSE, fixed = FALSE,
useBytes = FALSE, escaped =c('""', "''")){
new_esc1 <- gsub("([][{}().+*^$|\\?])", "\\\\\\1", substr(escaped, 1, 1))
new_esc2 <- gsub("([][{}().+*^$|\\?])", "\\\\\\1", substr(escaped, 2, 2))
rm_pat <- paste0(new_esc1, ".*?", new_esc2, collapse = "|")
new_arg <- gsub(rm_pat, "", arg)
grepl(pattern, new_arg)
}
grepl3(pattern = "banana", x = "'banana' apple \"banana\" {banana}", escaped =c("''", '""', "{}"))
[1] FALSE
您可以使用start/end_escape参数来提供匹配的定界符（例如{和}）的LHS和RHS，而不会在错误的位置进行匹配（}作为LHS定界符）
perl = TRUE允许环顾断言。它们评估其中的语句的有效性，没有在模式中捕获它们。 This post覆盖得很好。
您会在perl = FALSE中收到错误，因为R的默认正则表达式引擎TRE不支持它们。
gsub3 <- function(pattern, replacement, x, escape = NULL, start_escape = NULL, end_escape = NULL) {
if (!is.null(escape) || !is.null(start_escape))
left_escape <- paste0("(?<![", paste0(escape, paste0(start_escape, collapse = ""), collapse = ""), "])")
if (!is.null(escape) || !is.null(end_escape))
right_escape <- paste0("(?![", paste0(escape, paste0(end_escape, collapse = ""), collapse = ""), "])")
patt <- paste0(left_escape, "(", pattern, ")", right_escape)
gsub(patt, replacement, x, perl = TRUE)
}
gsub3("banana", "potatoe", "'banana' banana \"banana\"", escape = "'\"")
#> [1] "'banana' potatoe \"banana\""
gsub3("banana", "potatoe", "'banana' apple \"banana\"", escape = '"\'')
#> [1] "'banana' apple \"banana\""
gsub3("banana", "potatoe", "{banana} banana {banana}", escape = "{}")
#> [1] "{banana} potatoe {banana}"
gsub3("banana", "potatoe", "{banana} apple {banana}", escape = "{}")
#> [1] "{banana} apple {banana}"
下面是grepl3-请注意，这不需要perl = TRUE，因为我们不在乎模式所捕获的内容，只要它匹配即可。
grepl3 <- function(pattern, x, escape = "'", start_escape = NULL, end_escape = NULL) {
if (!is.null(escape) || !is.null(start_escape))
start_escape <- paste0("[^", paste0(escape, paste0(start_escape, collapse = ""), collapse = ""), "]")
if (!is.null(escape) || !is.null(end_escape))
end_escape <- paste0("[^", paste0(escape, paste0(end_escape, collapse = ""), collapse = ""), "]")
patt <- paste0(start_escape, pattern, end_escape)
grepl(patt, x)
}
grepl3("banana", "'banana' banana \"banana\"", escape =c('"', "'"))
#> [1] TRUE
grepl3("banana", "'banana' apple \"banana\"", escape =c('""', "''"))
#> [1] FALSE
grepl3("banana", "{banana} banana {banana}", escape = "{}")
#> [1] TRUE
grepl3("banana", "{banana} apple {banana}", escape = "{}")
#> [1] FALSE
编辑：
这可以解决gsub，而不会引起Andrew提到的问题，只要您可以使用一组成对的运算符就可以了。我认为您可以对其进行修改，以允许使用多个定界符。感谢令人着迷的问题，在regmatches中找到了新宝石！
gsub4 <-
function(pattern,
replacement,
x,
left_escape = "{",
right_escape = "}") {
# `regmatches()` takes a character vector and
# output of `gregexpr` and friends and returns
# the matching (or unmatching, as here) substrings
string_pieces <-
regmatches(x,
gregexpr(
paste0(
"\\Q", # Begin quote, regex will treat everything after as fixed.
left_escape,
"\\E(?>[^", # \\ ends quotes.
left_escape,
right_escape,
"]|(?R))*", # Recurses, allowing nested escape characters
"\\Q",
right_escape,
"\\E",
collapse = ""
),
x,
perl = TRUE
), invert =NA) # even indices match pattern (so are escaped),
# odd indices we want to perform replacement on.
for (k in seq_along(string_pieces)) {
n_pieces <- length(string_pieces[[k]])
# Due to the structure of regmatches(invert = NA), we know that it will always
# return unmatched strings at odd values, padding with "" as needed.
to_replace <- seq(from = 1, to = n_pieces, by = 2)
string_pieces[[k]][to_replace] <- gsub(pattern, replacement, string_pieces[[k]][to_replace])
}
sapply(string_pieces, paste0, collapse = "")
}
gsub4('banana', 'apples', "{banana's} potatoes {banana} banana", left_escape = "{", right_escape = "}")
#> [1] "{banana's} potatoes {banana} apples"
gsub4('banana', 'apples', "{banana's} potatoes {banana} banana", left_escape = "{", right_escape = "}")
#> [1] "{banana's} potatoes {banana} apples"
gsub4('banana', 'apples', "banana's potatoes", left_escape = "{", right_escape = "}")
#> [1] "apples's potatoes"
gsub4('banana', 'apples', "{banana's} potatoes", left_escape = "{", right_escape = "}")
#> [1] "{banana's} potatoes"
这是在字符类中使用否定运算符的简单正则表达式解决方案。它仅满足您的简单情况。我无法使其满足配对的多个定界符请求：
grepl2 <- function(patt, escape="'", arg=NULL) {
grepl( patt=paste0("[^",escape,"]",
patt,
"[^",escape,"]"), arg) }
grepl2("banana", "'banana' apple \"banana\"", escape =c( "'"))
#[1] TRUE
grepl2("banana", "'banana' apple ", escape =c( "'"))
[#1] FALSE
我的意见是，您可能需要分开两个大括号才能使代码正常工作。在这里，我正在使用正则表达式环顾功能。 R外部可能无法通用（尤其是回溯？
grepl2 = function(pattern, x, escapes = c(open="\"'{", close="\"'}")){
grepl(paste0("(?<![", escapes[[1]], "])",
pattern,
"(?![", escapes[[2]], "])"),
x, perl=T)
}
grepl2("banana", "'banana' banana \"banana\"")
#> [1] TRUE
grepl2("banana", "'banana' apple \"banana\"")
#> [1] FALSE
grepl2("banana", "{banana} banana {banana}")
#> [1] TRUE
grepl2("banana", "{banana} apple {banana}")
#> [1] FALSE