.\" Automatically generated by Pod::Man 4.14 (Pod::Simple 3.40) .\" .\" 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 >0, 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 "KinoSearch1::Analysis::TokenBatch 3pm" .TH KinoSearch1::Analysis::TokenBatch 3pm "2020-11-09" "perl v5.32.0" "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 Add many tokens to the batch, by supplying the string to be tokenized, and arrays of token starts and token ends (specified in bytes). .SH "NAME" KinoSearch1::Analysis::TokenBatch \- a collection of tokens .SH "SYNOPSIS" .IX Header "SYNOPSIS" .Vb 3 \& while ( $batch\->next ) { \& $batch\->set_text( lc( $batch\->get_text ) ); \& } .Ve .SH "EXPERIMENTAL API" .IX Header "EXPERIMENTAL API" TokenBatch's \s-1API\s0 should be considered experimental and is likely to change. .SH "DESCRIPTION" .IX Header "DESCRIPTION" A TokenBatch is a collection of Tokens which you can add to, then iterate over. .SH "METHODS" .IX Header "METHODS" .SS "new" .IX Subsection "new" .Vb 1 \& my $batch = KinoSearch1::Analysis::TokenBatch\->new; .Ve .PP Constructor. .SS "append" .IX Subsection "append" .Vb 1 \& $batch\->append( $text, $start_offset, $end_offset, $pos_inc ); .Ve .PP Add a Token to the end of the batch. Accepts either three or four arguments: text, start_offset, end_offset, and an optional position increment which defaults to 1 if not supplied. For a description of what these arguments mean, see the docs for Token. .SS "next" .IX Subsection "next" .Vb 3 \& while ( $batch\->next ) { \& # ... \& } .Ve .PP Proceed to the next token in the TokenBatch. Returns true if the TokenBatch ends up located at valid token. .SH "ACCESSOR METHODS" .IX Header "ACCESSOR METHODS" All of TokenBatch's accessor methods affect the current Token. Calling any of these methods when the TokenBatch is not located at a valid Token will trigger an exception. .SS "set_text get_text" .IX Subsection "set_text get_text" Set/get the text of the current Token. .SS "set_start_offset get_start_offset" .IX Subsection "set_start_offset get_start_offset" Set/get the start_offset of the current Token. .SS "set_end_offset get_end_offset" .IX Subsection "set_end_offset get_end_offset" Set/get the end_offset of the current Token. .SS "set_pos_inc get_pos_inc" .IX Subsection "set_pos_inc get_pos_inc" Set/get the position increment of the current Token. .SH "COPYRIGHT" .IX Header "COPYRIGHT" Copyright 2005\-2010 Marvin Humphrey .SH "LICENSE, DISCLAIMER, BUGS, etc." .IX Header "LICENSE, DISCLAIMER, BUGS, etc." See KinoSearch1 version 1.01.