.\" Automatically generated by Pod::Man 2.28 (Pod::Simple 3.30) .\" .\" Standard preamble: .\" ======================================================================== .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp .. .de Vb \" Begin verbatim text .ft CW .nf .ne \\$1 .. .de Ve \" End verbatim text .ft R .fi .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left .\" double quote, and \*(R" will give a right double quote. \*(C+ will .\" give a nicer C++. Capital omega is used to do unbreakable dashes and .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff, .\" nothing in troff, for use with C<>. .tr \(*W- .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- . ds PI pi . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch . ds L" "" . ds R" "" . ds C` "" . ds C' "" 'br\} .el\{\ . ds -- \|\(em\| . ds PI \(*p . ds L" `` . ds R" '' . ds C` . ds C' 'br\} .\" .\" Escape single quotes in literal strings from groff's Unicode transform. .ie \n(.g .ds Aq \(aq .el .ds Aq ' .\" .\" If the F register is turned on, we'll generate index entries on stderr for .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. .\" .\" Avoid warning from groff about undefined register 'F'. .de IX .. .nr rF 0 .if \n(.g .if rF .nr rF 1 .if (\n(rF:(\n(.g==0)) \{ . if \nF \{ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . if !\nF==2 \{ . nr % 0 . nr F 2 . \} . \} .\} .rr rF .\" .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). .\" Fear. Run. Save yourself. No user-serviceable parts. . \" fudge factors for nroff and troff .if n \{\ . ds #H 0 . ds #V .8m . ds #F .3m . ds #[ \f1 . ds #] \fP .\} .if t \{\ . ds #H ((1u-(\\\\n(.fu%2u))*.13m) . ds #V .6m . ds #F 0 . ds #[ \& . ds #] \& .\} . \" simple accents for nroff and troff .if n \{\ . ds ' \& . ds ` \& . ds ^ \& . ds , \& . ds ~ ~ . ds / .\} .if t \{\ . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' .\} . \" troff and (daisy-wheel) nroff accents .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' .ds 8 \h'\*(#H'\(*b\h'-\*(#H' .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] .ds ae a\h'-(\w'a'u*4/10)'e .ds Ae A\h'-(\w'A'u*4/10)'E . \" corrections for vroff .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' . \" for low resolution devices (crt and lpr) .if \n(.H>23 .if \n(.V>19 \ \{\ . ds : e . ds 8 ss . ds o a . ds d- d\h'-1'\(ga . ds D- D\h'-1'\(hy . ds th \o'bp' . ds Th \o'LP' . ds ae ae . ds Ae AE .\} .rm #[ #] #H #V #F C .\" ======================================================================== .\" .IX Title "Text::Levenshtein::Damerau 3pm" .TH Text::Levenshtein::Damerau 3pm "2015-07-15" "perl v5.20.2" "User Contributed Perl Documentation" .\" For nroff, turn off justification. Always turn off hyphenation; it makes .\" way too many mistakes in technical documents. .if n .ad l .nh .SH "NAME" Text::Levenshtein::Damerau \- Damerau Levenshtein edit distance. .SH "SYNOPSIS" .IX Header "SYNOPSIS" .Vb 3 \& use Text::Levenshtein::Damerau; \& use warnings; \& use strict; \& \& my @targets = (\*(Aqfuor\*(Aq,\*(Aqxr\*(Aq,\*(Aqfourrrr\*(Aq,\*(Aqfo\*(Aq); \& \& # Initialize Text::Levenshtein::Damerau object with text to compare against \& my $tld = Text::Levenshtein::Damerau\->new(\*(Aqfour\*(Aq); \& \& print $tld\->dld($targets[0]); \& # prints 1 \& \& my $tld = $tld\->dld({ list => \e@targets }); \& print $tld\->{\*(Aqfuor\*(Aq}; \& # prints 1 \& \& print $tld\->dld_best_match({ list => \e@targets }); \& # prints fuor \& \& print $tld\->dld_best_distance({ list => \e@targets }); \& # prints 1 \& \& \& # or even more simply \& use Text::Levenshtein::Damerau qw/edistance/; \& use warnings; \& use strict; \& \& print edistance(\*(AqNeil\*(Aq,\*(AqNiel\*(Aq); \& # prints 1 .Ve .SH "DESCRIPTION" .IX Header "DESCRIPTION" Returns the true Damerau Levenshtein edit distance of strings with adjacent transpositions. Useful for fuzzy matching, \s-1DNA\s0 variation metrics, and fraud detection. .PP Defaults to using Pure Perl Text::Levenshtein::Damerau::PP, but has an \s-1XS\s0 addon Text::Levenshtein::Damerau::XS for massive speed imrovements. Works correctly with utf8 if backend supports it; known to work with \f(CW\*(C`Text::Levenshtein::Damerau::PP\*(C'\fR and \f(CW\*(C`Text::Levenshtein::Damerau::XS\*(C'\fR. .PP .Vb 4 \& use utf8; \& my $tld = Text::Levenshtein::Damerau\->new(\*(AqXXXX\*(Aq); \& print $tld\->dld(\*(AqXXXX\*(Aq); \& # prints 1 .Ve .SH "CONSTRUCTOR" .IX Header "CONSTRUCTOR" .SS "new" .IX Subsection "new" Creates and returns a \f(CW\*(C`Text::Levenshtein::Damerau\*(C'\fR object. Takes a scalar with the text (source) you want to compare against. .PP .Vb 2 \& my $tld = Text::Levenshtein::Damerau\->new(\*(AqNeil\*(Aq); \& # Creates a new Text::Levenshtein::Damerau object $tld .Ve .SH "METHODS" .IX Header "METHODS" .ie n .SS "$tld\->dld" .el .SS "\f(CW$tld\fP\->dld" .IX Subsection "$tld->dld" \&\fBScalar\fR Argument: Takes a string to compare with. .PP Returns: an integer representing the edit distance between the source and the passed argument. .PP \&\fBHashref\fR Argument: Takes a hashref containing: .IP "\(bu" 4 list => \e@array (array ref of strings to compare with) .IP "\(bu" 4 \&\fI\s-1OPTIONAL\s0\fR max_distance => \f(CW$int\fR (only return results with \f(CW$int\fR distance or less). .IP "\(bu" 4 \&\fI\s-1OPTIONAL\s0\fR backend => 'Some::Module::its_function' Any module that will take 2 arguments and returns an int. If the module fails to load, the function doesn't exist, or the function doesn't return a number when passed 2 strings, then \f(CW\*(C`backend\*(C'\fR remains unchanged. .Sp .Vb 2 \& # Override defaults and use Text::Levenshtein::Damerau::PP\*(Aqs pp_edistance() \& $tld\->dld({ list=> \e@list, backend => \*(AqText::Levenshtein::Damerau::PP::pp_edistance\*(Aq); \& \& # Override defaults and use Text::Levenshtein::Damerau::XS\*(Aqs xs_edistance() \& use Text::Levenshtein::Damerau; \& requires Text::Levenshtein::Damerau::XS; \& ... \& $tld\->dld({ list=> \e@list, backend => \*(AqText::Levenshtein::Damerau::XS::xs_edistance\*(Aq); .Ve .PP Returns: hashref with each word from the passed list as keys, and their edit distance (if less than max_distance, which is unlimited by default). .PP .Vb 3 \& my $tld = Text::Levenshtein::Damerau\->new(\*(AqNeil\*(Aq); \& print $tld\->dld( \*(AqNiel\*(Aq ); \& # prints 1 \& \& #or if you want to check the distance of various items in a list \& \& my @names_list = (\*(AqNiel\*(Aq,\*(AqJack\*(Aq); \& my $tld = Text::Levenshtein::Damerau\->new(\*(AqNeil\*(Aq); \& my $d_ref = $tld\->dld({ list=> \e@names_list }); # pass a list, returns a hash ref \& print $d_ref\->{\*(AqNiel\*(Aq}; #prints 1 \& print $d_ref\->{\*(AqJack\*(Aq}; #prints 4 .Ve .ie n .SS "$tld\->dld_best_match" .el .SS "\f(CW$tld\fP\->dld_best_match" .IX Subsection "$tld->dld_best_match" Argument: an array reference of strings. .PP Returns: the string with the smallest edit distance between the source and the array of strings passed. .PP Takes distance of \f(CW$tld\fR source against every item in \f(CW@targets\fR, then returns the string of the best match. .PP .Vb 4 \& my $tld = Text::Levenshtein::Damerau\->new(\*(AqNeil\*(Aq); \& my @name_spellings = (\*(AqNiel\*(Aq,\*(AqNeell\*(Aq,\*(AqKNiel\*(Aq); \& print $tld\->dld_best_match({ list=> \e@name_spellings }); \& # prints Niel .Ve .ie n .SS "$tld\->dld_best_distance" .el .SS "\f(CW$tld\fP\->dld_best_distance" .IX Subsection "$tld->dld_best_distance" Arguments: an array reference of strings. .PP Returns: the smallest edit distance between the source and the array reference of strings passed. .PP Takes distance of \f(CW$tld\fR source against every item in the passed array, then returns the smallest edit distance. .PP .Vb 4 \& my $tld = Text::Levenshtein::Damerau\->new(\*(AqNeil\*(Aq); \& my @name_spellings = (\*(AqNiel\*(Aq,\*(AqNeell\*(Aq,\*(AqKNiel\*(Aq); \& print $tld\->dld_best_distance({ list => \e@name_spellings }); \& # prints 1 .Ve .SH "EXPORTABLE METHODS" .IX Header "EXPORTABLE METHODS" .SS "edistance" .IX Subsection "edistance" Arguments: source string and target string. .IP "\(bu" 4 \&\fI\s-1OPTIONAL\s0 3rd argument\fR int (max distance; only return results with \f(CW$int\fR distance or less). 0 = unlimited. Default = 0. .PP Returns: int that represents the edit distance between the two argument. \-1 if max distance is set and reached. .PP Wrapper function to take the edit distance between a source and target string. It will attempt to use, in order: .IP "\(bu" 4 Text::Levenshtein::Damerau::XS \fBxs_edistance\fR .IP "\(bu" 4 Text::Levenshtein::Damerau::PP \fBpp_edistance\fR .PP .Vb 3 \& use Text::Levenshtein::Damerau qw/edistance/; \& print edistance(\*(AqNeil\*(Aq,\*(AqNiel\*(Aq); \& # prints 1 .Ve .SH "SEE ALSO" .IX Header "SEE ALSO" .IP "\(bu" 4 \fIRepository\fR .IP "\(bu" 4 \fIDamerau levenshtein explanation\fR .IP "\(bu" 4 Text::Fuzzy \fIRegular levenshtein distance\fR .SH "BUGS" .IX Header "BUGS" Please report bugs to: .PP .SH "AUTHOR" .IX Header "AUTHOR" Nick Logan <\fIug@skunkds.com\fR> .SH "LICENSE AND COPYRIGHT" .IX Header "LICENSE AND COPYRIGHT" This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself.