1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
|
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/sort.R
\name{stri_duplicated}
\alias{stri_duplicated}
\alias{stri_duplicated_any}
\title{Determine Duplicated Elements}
\usage{
stri_duplicated(
str,
from_last = FALSE,
fromLast = from_last,
...,
opts_collator = NULL
)
stri_duplicated_any(
str,
from_last = FALSE,
fromLast = from_last,
...,
opts_collator = NULL
)
}
\arguments{
\item{str}{a character vector}
\item{from_last}{a single logical value;
indicates whether search should be performed from the last to the
first string}
\item{fromLast}{[DEPRECATED] alias of \code{from_last}}
\item{...}{additional settings for \code{opts_collator}}
\item{opts_collator}{a named list with \pkg{ICU} Collator's options,
see \code{\link{stri_opts_collator}}, \code{NULL}
for default collation options}
}
\value{
\code{stri_duplicated()} returns a logical vector of the same length
as \code{str}. Each of its elements indicates whether a canonically
equivalent string was already found in \code{str}.
\code{stri_duplicated_any()} returns a single non-negative integer.
Value of 0 indicates that all the elements in \code{str} are unique.
Otherwise, it gives the index of the first non-unique element.
}
\description{
\code{stri_duplicated()} determines which strings in a character vector
are duplicates of other elements.
\code{stri_duplicated_any()} determines if there are any duplicated
strings in a character vector.
}
\details{
Missing values are regarded as equal.
Unlike \code{\link{duplicated}} and \code{\link{anyDuplicated}},
these functions test for canonical equivalence of strings
(and not whether the strings are just bytewise equal)
Such operations are locale-dependent.
Hence, \code{stri_duplicated} and \code{stri_duplicated_any}
are significantly slower (but much better suited for natural language
processing) than their base R counterparts.
See also \code{\link{stri_unique}} for extracting unique elements.
}
\examples{
# In the following examples, we have 3 duplicated values,
# 'a' - 2 times, NA - 1 time
stri_duplicated(c('a', 'b', 'a', NA, 'a', NA))
stri_duplicated(c('a', 'b', 'a', NA, 'a', NA), from_last=TRUE)
stri_duplicated_any(c('a', 'b', 'a', NA, 'a', NA))
# compare the results:
stri_duplicated(c('\u0105', stri_trans_nfkd('\u0105')))
duplicated(c('\u0105', stri_trans_nfkd('\u0105')))
stri_duplicated(c('gro\u00df', 'GROSS', 'Gro\u00df', 'Gross'), strength=1)
duplicated(c('gro\u00df', 'GROSS', 'Gro\u00df', 'Gross'))
}
\references{
\emph{Collation} - ICU User Guide,
\url{https://unicode-org.github.io/icu/userguide/collation/}
}
\seealso{
The official online manual of \pkg{stringi} at \url{https://stringi.gagolewski.com/}
Gagolewski M., \pkg{stringi}: Fast and portable character string processing in R, \emph{Journal of Statistical Software} 103(2), 2022, 1-59, \doi{10.18637/jss.v103.i02}
Other locale_sensitive:
\code{\link{\%s<\%}()},
\code{\link{about_locale}},
\code{\link{about_search_boundaries}},
\code{\link{about_search_coll}},
\code{\link{stri_compare}()},
\code{\link{stri_count_boundaries}()},
\code{\link{stri_enc_detect2}()},
\code{\link{stri_extract_all_boundaries}()},
\code{\link{stri_locate_all_boundaries}()},
\code{\link{stri_opts_collator}()},
\code{\link{stri_order}()},
\code{\link{stri_rank}()},
\code{\link{stri_sort_key}()},
\code{\link{stri_sort}()},
\code{\link{stri_split_boundaries}()},
\code{\link{stri_trans_tolower}()},
\code{\link{stri_unique}()},
\code{\link{stri_wrap}()}
}
\concept{locale_sensitive}
\author{
\href{https://www.gagolewski.com/}{Marek Gagolewski} and other contributors
}
|
