Learn R Programming
Ecfun (version 0.1-2)

subNonStandardNames: sub for nonstandard names

Description

sub(nonEnglishData["nonEnglish"], nonEnglishData["English"], x)

Usage

subNonStandardNames(x,
   standardCharacters=c(letters, LETTERS, ' ','.', ',', 0:9,
      '"', "'", '-', '_', '(', ')', '[', ']', ''),
   replacement='_',
   gsubList=list(list(pattern='\\\\\\\\|\\\\',
      replacement='"')),
   removeSecondLine=TRUE,
   nonStandardNames=Ecdat::nonEnglishNames, ...)
x{
    character vector in which it is desired replace
    nonStandardNames[, 1] in
    subNonStandardCharacters(x, ...) with the corresponding
    element of nonStandardNames[, 2].
  }
  standardCharacters, replacement, gsubList, ...{
    arguments passed to subNonStandardCharacters
  }
  removeSecondLine{
    logical:  If TRUE, delete anything following "\n" and return it as
    an attribute "secondLine"
  }
  nonStandardNames{
    data.frame or character matrix with two columns:  Replace any
    substring of x matching nonStandardNames[, 1] with the
    corresponding elemeng of nonStandardNames[, 2]
  }

1.  removeSecondLine

  2.  x. <- subNonStandardCharacters(x, standardCharacters, replacement,
  ...)

  3.  Loop over all rows of nonStandardNames substituting anything
  matching nonEnglishData[i, 1] with nonEnglishData[i,
    2].

  4.  Eliminate leading and trailing blanks.

a character vector with all nonStandardCharacters replaced first
  by replacement and then by the second column of
  nonStandardNames for any that match the first column.
[object Object]
sub
  nonEnglishNames
  subNonStandardCharactersNames <- c('Raul', 'Ra`l', 'Torres,Raul', 'Torres, Raul',
           "Robert C. \\Bobby\\\\", 'Ed  --Vacancy')
#  confusion in character sets can create
#  names like Names[2]

library(Ecdat)Name2 <- subNonStandardNames(Names)
Name2

Name2. <- c('Raul', 'Raul', Names[3:4],
            'Robert C. "Bobby"', 'Ed')
attr(Name2., 'secondLine') <- c(rep(NA, 5), ' --Vacancy')
Name2.

stopifnot(
all.equal(Name2, Name2.)
)
manip

Arguments