r - 扩展 gsub 和 grepl 以忽略给定分隔符之间的子字符串

Question

我希望能够仅在给定的定界符集之外使用 grepl() 和 gsub()，例如我希望能够忽略之间的文本引号。

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}"

真实案例可能会以不同的数量和顺序引用子字符串。

我已经编写了以下适用于这些情况的函数，但它们很笨重并且 gsub2() 根本不健壮，因为它暂时用占位符替换了分隔的内容，这些占位符可能是受后续操作影响。

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而不使用占位符的解决方案？请注意，我当前的函数支持多对定界符，但我会对仅支持一对定界符的解决方案感到满意，并且不会尝试匹配简单引号之间的子字符串。

强加不同的分隔符也是可以接受的，例如 { 和 } 而不是 2 " 或 2 ' 如果有帮助。

我也可以强加 perl = TRUE

Answer 1

您可以使用 start/end_escape 参数来提供匹配定界符的 LHS 和 RHS，例如 { 和 } 而无需在错误的地方(} 作为 LHS 分隔符)

perl = TRUE 允许环视断言。这些评估其中陈述的有效性，没有在模式中捕获它们。 This post很好地涵盖了它们。

你会在 perl = FALSE 中得到一个错误，因为 TRE ，R 的默认正则表达式引擎，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 - 注意这不需要 perl = TRUE 因为我们不关心模式捕获什么，只关心它匹配。

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:

这应该可以解决 gsub 而不会出现 Andrew 提到的问题，只要您可以使用一组成对的运算符。我认为您可以修改它以允许使用多个定界符。感谢这个有趣的问题，在 regmatches 中找到了一个新的 gem!

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"