qdapRegex (version 0.7.5)

rm_white: Remove/Replace/Extract White Space

Description

rm_white - Remove multiple white space (> 1 becomes a single white space), white space before a comma, white space before a single or consecutive combination of a colon, semicolon, or endmark (period, question mark, or exclamation point), white space after a left bracket ("", "(", "[") or before a right bracket ("", ")", "]"), leading or trailing white space.

rm_white_bracket - Remove white space after a left bracket ("", "(", "[") or before a right bracket ("", ")", "]").

rm_white_colon - Remove white space before a single or consecutive combination of a colon, semicolon.

rm_white_comma - Remove white space before a comma.

rm_white_endmark - Remove white space before endmark(s) (".", "?", "!").

rm_white_lead - Remove leading white space.

rm_white_lead_trail - Remove leading or trailing white space.

rm_white_trail - Remove trailing white space.

rm_white_multiple - Remove multiple white space (> 1 becomes a single white space).

rm_white_punctuation - Remove multiple white space before a comma, white space before a single or consecutive combination of a colon, semicolon, or endmark (period, question mark, or exclamation point).

Usage

rm_white(
  text.var,
  trim = FALSE,
  clean = FALSE,
  pattern = "@rm_white",
  replacement = "",
  extract = FALSE,
  dictionary = getOption("regex.library"),
  ...
)
ex_white(
  text.var,
  trim = FALSE,
  clean = FALSE,
  pattern = "@rm_white",
  replacement = "",
  extract = TRUE,
  dictionary = getOption("regex.library"),
  ...
)
rm_white_bracket(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_bracket",
  replacement = "",
  extract = FALSE,
  dictionary = getOption("regex.library"),
  ...
)
ex_white_bracket(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_bracket",
  replacement = "",
  extract = TRUE,
  dictionary = getOption("regex.library"),
  ...
)
rm_white_colon(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_colon",
  replacement = "",
  extract = FALSE,
  dictionary = getOption("regex.library"),
  ...
)
ex_white_colon(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_colon",
  replacement = "",
  extract = TRUE,
  dictionary = getOption("regex.library"),
  ...
)
rm_white_comma(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_comma",
  replacement = "",
  extract = FALSE,
  dictionary = getOption("regex.library"),
  ...
)
ex_white_comma(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_comma",
  replacement = "",
  extract = TRUE,
  dictionary = getOption("regex.library"),
  ...
)
rm_white_endmark(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_endmark",
  replacement = "",
  extract = FALSE,
  dictionary = getOption("regex.library"),
  ...
)
ex_white_endmark(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_endmark",
  replacement = "",
  extract = TRUE,
  dictionary = getOption("regex.library"),
  ...
)
rm_white_lead(
  text.var,
  trim = FALSE,
  clean = FALSE,
  pattern = "@rm_white_lead",
  replacement = "",
  extract = FALSE,
  dictionary = getOption("regex.library"),
  ...
)
ex_white_lead(
  text.var,
  trim = FALSE,
  clean = FALSE,
  pattern = "@rm_white_lead",
  replacement = "",
  extract = TRUE,
  dictionary = getOption("regex.library"),
  ...
)
rm_white_lead_trail(
  text.var,
  trim = FALSE,
  clean = FALSE,
  pattern = "@rm_white_lead_trail",
  replacement = "",
  extract = FALSE,
  dictionary = getOption("regex.library"),
  ...
)
ex_white_lead_trail(
  text.var,
  trim = FALSE,
  clean = FALSE,
  pattern = "@rm_white_lead_trail",
  replacement = "",
  extract = TRUE,
  dictionary = getOption("regex.library"),
  ...
)
rm_white_trail(
  text.var,
  trim = FALSE,
  clean = FALSE,
  pattern = "@rm_white_trail",
  replacement = "",
  extract = FALSE,
  dictionary = getOption("regex.library"),
  ...
)
ex_white_trail(
  text.var,
  trim = FALSE,
  clean = FALSE,
  pattern = "@rm_white_trail",
  replacement = "",
  extract = TRUE,
  dictionary = getOption("regex.library"),
  ...
)
rm_white_multiple(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_multiple",
  replacement = "",
  extract = FALSE,
  dictionary = getOption("regex.library"),
  ...
)
ex_white_multiple(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_multiple",
  replacement = "",
  extract = TRUE,
  dictionary = getOption("regex.library"),
  ...
)
rm_white_punctuation(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_punctuation",
  replacement = "",
  extract = FALSE,
  dictionary = getOption("regex.library"),
  ...
)
ex_white_punctuation(
  text.var,
  trim = !extract,
  clean = TRUE,
  pattern = "@rm_white_punctuation",
  replacement = "",
  extract = TRUE,
  dictionary = getOption("regex.library"),
  ...
)

Value

Returns a character string with extra white space removed.

Arguments

text.var

The text variable.

trim

logical. If TRUE removes leading and trailing white spaces.

clean

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

pattern

A character string containing a regular expression (or character string for fixed = TRUE) to be matched in the given character vector. Default, @rm_dollar uses the rm_dollar regex from the regular expression dictionary from the dictionary argument.

replacement

Replacement for matched pattern.

extract

logical. If TRUE the dollar strings are extracted into a list of vectors.

dictionary

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

...

Other arguments passed to gsub.

Author

rm_white_endmark/rm_white_punctuation - stackoverflow's hwnd and Tyler Rinker <[e-mail]>.

References

The rm_white_endmark/rm_white_punctuation regular expression was taken from: https://stackoverflow.com/a/25464921/1000343

See Also

gsub, stri_extract_all_regex

Other rm_ functions: rm_abbreviation(), rm_between(), rm_bracket(), rm_caps_phrase(), rm_caps(), rm_citation_tex(), rm_citation(), rm_city_state_zip(), rm_city_state(), rm_date(), rm_default(), rm_dollar(), rm_email(), rm_emoticon(), rm_endmark(), rm_hash(), rm_nchar_words(), rm_non_ascii(), rm_non_words(), rm_number(), rm_percent(), rm_phone(), rm_postal_code(), rm_repeated_characters(), rm_repeated_phrases(), rm_repeated_words(), rm_tag(), rm_time(), rm_title_name(), rm_url(), rm_zip()

Examples

x <-  c(" There is ( $5.50 ) for , me . ", " that's [ 45.6% ] of! the pizza !", 
    "     14% is { $26  } or $25.99 ?", "Oh ;  here's colon : Yippee !")

rm_white(x)
rm_white_bracket(x)
rm_white_colon(x)
rm_white_comma(x)
rm_white_endmark(x)
rm_white_lead(x)
rm_white_trail(x)
rm_white_lead_trail(x)
rm_white_multiple(x)
rm_white_punctuation(x)

Run the code above in your browser using DataCamp Workspace