Remove/Replace/Extract Brackets

Usage

rm_bracket(text.var, pattern = "all", trim = TRUE, clean = TRUE, replacement = "", extract = FALSE, include.markers = ifelse(extract, FALSE, TRUE), dictionary = getOption("regex.library"), ...)
rm_round(text.var, pattern = "(", trim = TRUE, clean = TRUE, replacement = "", extract = FALSE, include.markers = ifelse(extract, FALSE, TRUE), dictionary = getOption("regex.library"), ...)
rm_square(text.var, pattern = "[", trim = TRUE, clean = TRUE, replacement = "", extract = FALSE, include.markers = ifelse(extract, FALSE, TRUE), dictionary = getOption("regex.library"), ...)
rm_curly(text.var, pattern = "{", trim = TRUE, clean = TRUE, replacement = "", extract = FALSE, include.markers = ifelse(extract, FALSE, TRUE), dictionary = getOption("regex.library"), ...)
rm_angle(text.var, pattern = "<", trim = TRUE, clean = TRUE, replacement = "", extract = FALSE, include.markers = ifelse(extract, FALSE, TRUE), dictionary = getOption("regex.library"), ...)
rm_bracket_multiple(text.var, trim = TRUE, clean = TRUE, pattern = "all", replacement = "", extract = FALSE, include.markers = FALSE, merge = TRUE)

Arguments

text.var

The text variable.

pattern

The type of bracket (and encased text) to remove. This is one or more of the strings "curly"/"\{", "square"/"[", "round"/"(", "angle"/"<" and "all". These strings correspond to: {, [, (, < or all four types.

trim

logical. If TRUE removes leading and trailing white spaces.

clean

trim logical. If TRUE extra white spaces and escaped character will be removed.

replacement

Replacement for matched pattern.

extract

logical. If TRUE the bracketed text is extracted into a list of vectors.

include.markers

logical. If TRUE and extract = TRUE returns the markers (left/right) and the text between.

dictionary

A dictionary of canned regular expressions to search within if pattern begins with "@rm_".

merge

logical. If TRUE the results of each bracket type will be merged by string. FALSE returns a named list of lists of vectors of bracketed text per bracket type.

...

Other arguments passed to gsub.

Examples

examp <- structure(list(person = structure(c(1L, 2L, 1L, 3L),
    .Label = c("bob", "greg", "sue"), class = "factor"), text =
    c("I love chicken [unintelligible]!",
    "Me too! (laughter) It's so good.[interrupting]",
    "Yep it's awesome {reading}.", "Agreed. {is so much fun}")), .Names =
    c("person", "text"), row.names = c(NA, -4L), class = "data.frame")

examp

  person                                           text
1    bob               I love chicken [unintelligible]!
2   greg Me too! (laughter) It's so good.[interrupting]
3    bob                    Yep it's awesome {reading}.
4    sue                       Agreed. {is so much fun}

rm_bracket(examp$text, pattern = "square")

[1] "I love chicken !"                 "Me too! (laughter) It's so good." "Yep it's awesome {reading}."     
[4] "Agreed. {is so much fun}"        

rm_bracket(examp$text, pattern = "curly")

[1] "I love chicken [unintelligible]!"               "Me too! (laughter) It's so good.[interrupting]"
[3] "Yep it's awesome ."                             "Agreed."                                       

rm_bracket(examp$text, pattern = c("square", "round"))

[1] "I love chicken !"            "Me too! It's so good."       "Yep it's awesome {reading}." "Agreed. {is so much fun}"   

rm_bracket(examp$text)

[1] "I love chicken !"      "Me too! It's so good." "Yep it's awesome ."    "Agreed."              


rm_bracket(examp$text, pattern = "square", extract=TRUE)

[[1]]
[1] "unintelligible"

[[2]]
[1] "interrupting"

[[3]]
[1] NA

[[4]]
[1] NA


rm_bracket(examp$text, pattern = "curly", extract=TRUE)

[[1]]
[1] NA

[[2]]
[1] NA

[[3]]
[1] "reading"

[[4]]
[1] "is so much fun"


rm_bracket(examp$text, pattern = c("square", "round"), extract=TRUE)

[[1]]
[1] "unintelligible"

[[2]]
[1] "laughter"     "interrupting"

[[3]]
[1] NA

[[4]]
[1] NA


rm_bracket(examp$text, pattern = c("square", "round"), merge = FALSE, extract=TRUE)

[[1]]
[1] "unintelligible"

[[2]]
[1] "laughter"     "interrupting"

[[3]]
[1] NA

[[4]]
[1] NA


rm_bracket(examp$text, extract=TRUE)

[[1]]
[1] "unintelligible"

[[2]]
[1] "laughter"     "interrupting"

[[3]]
[1] "reading"

[[4]]
[1] "is so much fun"


rm_bracket(examp$tex, include.markers=TRUE, extract=TRUE)

[[1]]
[1] "[unintelligible]"

[[2]]
[1] "(laughter)"     "[interrupting]"

[[3]]
[1] "{reading}"

[[4]]
[1] "{is so much fun}"



## <strong>Not run</strong>: 
# library(qdap)
# rm_bracket(examp$tex, pattern="curly", extract=TRUE) %>%
#   unlist() %>%
#   na.omit() %>%
#   paste2()
# ## <strong>End(Not run)</strong>

x <- "I like [bots] (not). And <likely> many do not {he he}"

rm_round(x)

[1] "I like [bots] . And <likely> many do not {he he}"

rm_round(x, extract = TRUE)

[[1]]
[1] "not"



rm_round(x, include.marker = FALSE)

[1] "I like [bots] (). And <likely> many do not {he he}"

rm_round(x, extract = TRUE, include.marker = TRUE)

[[1]]
[1] "(not)"



rm_square(x)

[1] "I like (not). And <likely> many do not {he he}"

rm_square(x, extract = TRUE)

[[1]]
[1] "bots"



rm_curly(x)

[1] "I like [bots] (not). And <likely> many do not"

rm_curly(x, extract = TRUE)

[[1]]
[1] "he he"



rm_angle(x)

[1] "I like [bots] (not). And many do not {he he}"

rm_angle(x, extract = TRUE)

[[1]]
[1] "likely"



lapply(rm_between('She said, "I am!" and he responded..."Am what?".',
    left='"', right='"', extract = TRUE), "[", c(TRUE, FALSE))

[[1]]
[1] "I am!"

See also

Author