Learn R Programming
Ecfun (version 0.1-3)

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 or matrix or a data.frame of character 
    vectors 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.
  
  NOTE:  On 13 May 2013 Jeff Newmiller at the University of California, 
  Davis, wrote, 'I think it is a fools errand to think that you can 
  automatically "normalize" arbitrary Unicode characters to an ASCII 
  form that everyone will agree on.'  (This was a reply on 
  r-help@r-project.org, subject:  "Re: [R] Matching names with non-
  English characters".)  Doubtless someone has software to do a better 
  job of this than what this function does, but I've so far been unable 
  to find it in R.  If you know of a better solution to this problem, 
  I'd be pleased to hear from you.  Spencer Graves

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.  If a 
  secondLine is found on any elements, it is returned as a "secondLine"
  attribute.
[object Object]
sub
  nonEnglishNames
  subNonStandardCharacters##
## 1.  Example 
##
tstSNSN <- c('Raul', 'Ra`l', 'Torres,Raul', 'Torres, Raul',
           "Robert C. \\Bobby\\\\", 'Ed  \n --Vacancy', '', '  ')#  confusion in character sets can create
#  names like Names[2]
##
## 2.  subNonStandardNames(vector)
##SNS2 <- subNonStandardNames(tstSNSN)
SNS2

# check 
SNS2. <- c('Raul', 'Raul', tstSNSN[3:4],
            'Robert C. "Bobby"', 'Ed', '', '')
attr(SNS2., 'secondLine') <- c(rep(NA, 5), ' --Vacancy', NA, NA)
SNS2.

stopifnot(
all.equal(SNS2, SNS2.)
)
##
## 2.  subNonStandardNames(matrix)
##
tstmat <- parseName(tstSNSN, surnameFirst=TRUE)
submat <- subNonStandardNames(tstmat)

# check 
SNSmat <- parseName(SNS2., surnameFirst=TRUE)
stopifnot(
all.equal(submat, SNSmat)
)

##
## 3.  subNonStandardNames(data.frame)
##
tstdf <- as.data.frame(tstmat)
subdf <- subNonStandardNames(tstdf)

# check 
SNSdf <- as.data.frame(SNSmat)
stopifnot(
all.equal(subdf, SNSdf)
)
manip

Arguments