Thesaurus Readers and Writers

Functions to read and write thesauri and thesaurus sets.

ReadThesaurus(
  file,
  caseSensitive = FALSE,
  accentSensitive = FALSE,
  punctuationSensitive = FALSE
)

ReadThesaurusSet(file)

WriteThesaurus(thesaurus, file)

WriteThesaurusSet(thesaurusSet, file)

Arguments

file

Name of a file.

caseSensitive, accentSensitive, punctuationSensitive

Logical. They set the case, accent, and punctuation sensitivity (FALSE by default) of the thesaurus.

thesaurus

A thesaurus object.

thesaurusSet

A thesaurus set.

Value

WriteThesaurus and WriteThesaurusSet create or overwrite the corresponding files. No value is returned.

ReadThesaurus and ReadThesaurusSet return the read thesaurus or thesaurusSet, respectively.

See also

zoologThesaurus for a description of the thesaurus and thesaurus set structure,

ThesaurusManagement, StandardizeNomenclature

Examples

## Read a thesaurus for taxa:
thesaurusFile <- system.file("extdata", "taxonThesaurus.csv", package="zoolog")
thesaurus <- ReadThesaurus(thesaurusFile)
## The attributes of the thesaurus include the fields 'caseSensitive',
## 'accentSensitive', and 'punctuationSensitive', all FALSE by default.
attributes(thesaurus)
#> $names
#>  [1] "Bos taurus"            "Bos primigenius"       "Bos"                  
#>  [4] "Ovis aries"            "Ovis orientalis"       "Ovis"                 
#>  [7] "Capra hircus"          "Capra aegagrus"        "Capra"                
#> [10] "Caprini"               "Sus domesticus"        "Sus scrofa"           
#> [13] "Sus"                   "Cervus elaphus"        "Cervus"               
#> [16] "Dama mesopotamica"     "Dama"                  "Gazella gazella"      
#> [19] "Gazella"               "Equus asinus"          "Equus caballus"       
#> [22] "Equus"                 "Oryctolagus cuniculus" "Oryctolagus"          
#> [25] "Canis familiaris"      "Canis lupus"           "Canis"                
#> 
#> $class
#> [1] "data.frame"
#> 
#> $row.names
#>  [1]  1  2  3  4  5  6  7  8  9 10 11 12
#> 
#> $caseSensitive
#> [1] FALSE
#> 
#> $accentSensitive
#> [1] FALSE
#> 
#> $punctuationSensitive
#> [1] FALSE
#> 

## Any of them can be set by the user if desired:
thesaurus2 <- ReadThesaurus(thesaurusFile, accentSensitive = TRUE)
attributes(thesaurus2)
#> $names
#>  [1] "Bos taurus"            "Bos primigenius"       "Bos"                  
#>  [4] "Ovis aries"            "Ovis orientalis"       "Ovis"                 
#>  [7] "Capra hircus"          "Capra aegagrus"        "Capra"                
#> [10] "Caprini"               "Sus domesticus"        "Sus scrofa"           
#> [13] "Sus"                   "Cervus elaphus"        "Cervus"               
#> [16] "Dama mesopotamica"     "Dama"                  "Gazella gazella"      
#> [19] "Gazella"               "Equus asinus"          "Equus caballus"       
#> [22] "Equus"                 "Oryctolagus cuniculus" "Oryctolagus"          
#> [25] "Canis familiaris"      "Canis lupus"           "Canis"                
#> 
#> $class
#> [1] "data.frame"
#> 
#> $row.names
#>  [1]  1  2  3  4  5  6  7  8  9 10 11 12
#> 
#> $caseSensitive
#> [1] FALSE
#> 
#> $accentSensitive
#> [1] TRUE
#> 
#> $punctuationSensitive
#> [1] FALSE
#> 

## Write the thesarus to a file:
fileExample <- file.path(tempdir(), "thesaurusExample.csv")
WriteThesaurus(thesaurus, fileExample)
## Replace tempdir() for your preferred local path if you want to easily
## examine the written file.

## Read a thesaurus set:
thesaurusSetFile <- system.file("extdata", "zoologThesaurusSet.csv", package="zoolog")
thesaurusSet <- ReadThesaurusSet(thesaurusSetFile)
## The attributes of the thesaurus set include information of the constituent
## thesauri: names, source file names, and their mode of application on datasets.
attributes(thesaurusSet)
#> $names
#> [1] "identifier" "taxon"      "element"    "measure"   
#> 
#> $applyToColNames
#> [1]  TRUE FALSE FALSE  TRUE
#> 
#> $applyToColValues
#> [1] FALSE  TRUE  TRUE  TRUE
#> 
#> $fileName
#> [1] "identifierThesaurus.csv" "taxonThesaurus.csv"     
#> [3] "elementThesaurus.csv"    "measureThesaurus.csv"   
#> 
## The attributes of each thesaurus are also set by 'ReadThesaurusSet'.
attributes(thesaurusSet$measure)
#> $names
#>  [1] "BatF"     "Bd"       "BFcd"     "BFd"      "BFp"      "BFcr"    
#>  [7] "BG"       "Bp"       "BPacd"    "BPtr"     "BPC"      "BT"      
#> [13] "BTP"      "B.tr.pat" "Davis.3"  "DC"       "Dd"       "DD"      
#> [19] "DEL"      "DEM"      "DHA"      "Dl"       "Dm"       "Dp"      
#> [25] "DPA"      "DVL"      "DVM"      "GB"       "GD"       "GH"      
#> [31] "GL"       "GLC"      "GLF"      "GLl"      "GLm"      "GLP"     
#> [37] "GLpe"     "GLT"      "H"        "HFcr"     "HS"       "HTC"     
#> [43] "L"        "LA"       "LAPa"     "LAR"      "LCDe"     "Ld"      
#> [49] "LeP"      "LFo"      "LFOM"     "LG"       "Ll"       "LO"      
#> [55] "LS"       "LTc"      "LT(lat)"  "PL"       "SB"       "SBV"     
#> [61] "SD"       "SDO"      "SDTc"     "SH"       "SLC"      "SLFp"    
#> [67] "W"        "WA"       "WP"       "WCL"      "WCM"     
#> 
#> $class
#> [1] "data.frame"
#> 
#> $row.names
#> [1] 1 2 3
#> 
#> $caseSensitive
#> [1] TRUE
#> 
#> $accentSensitive
#> [1] FALSE
#> 
#> $punctuationSensitive
#> [1] FALSE
#> 

## Write the thesaurus set to a file:
fileSetExample <- file.path(tempdir(), "thesaurusSetExample.csv")
WriteThesaurusSet(thesaurusSet, fileSetExample)
## It writes the thesaurus-set main data frame and each of the included
## thesaurus files.
## Again, replace tempdir() for your preferred local path if you want to
## easily examine the written files.