.\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.16) .\" .\" 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" '' '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. .ie \nF \{\ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . nr % 0 . rr F .\} .el \{\ . de IX .. .\} .\" .\" 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 "HTML::Copy 3pm" .TH HTML::Copy 3pm "2013-06-21" "perl v5.14.2" "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" HTML::Copy \- copy a HTML file without breaking links. .SH "VERSION" .IX Header "VERSION" Version 1.31 .SH "SYMPOSIS" .IX Header "SYMPOSIS" .Vb 1 \& use HTML::Copy; \& \& HTML::Copy\->htmlcopy($source_path, $destination_path); \& \& # or \& \& $p = HTML::Copy\->new($source_path); \& $p\->copy_to($destination_path); \& \& # or \& \& open my $in, "<", $source_path; \& $p = HTML::Copy\->new($in) \& $p\->source_path($source_path); # can be omitted, \& # when $source_path is in cwd. \& \& $p\->destination_path($destination_path) # can be omitted, \& # when $source_path is in cwd. \& open my $out, ">", $source_path; \& $p\->copy_to($out); .Ve .SH "DESCRIPTION" .IX Header "DESCRIPTION" This module is to copy a \s-1HTML\s0 file without beaking links in the file. This module is a sub class of HTML::Parser. .SH "REQUIRED MODULES" .IX Header "REQUIRED MODULES" .IP "HTML::Parser" 2 .IX Item "HTML::Parser" .SH "CLASS METHODS" .IX Header "CLASS METHODS" .SS "htmlcopy" .IX Subsection "htmlcopy" .Vb 1 \& HTML::Copy\->htmlcopy($source_path, $destination_path); .Ve .PP Parse contents of \f(CW$source_path\fR, change links and write into \f(CW$destination_path\fR. .SS "parse_file" .IX Subsection "parse_file" .Vb 2 \& $html_text = HTML::Copy\->parse_file($source_path, \& $destination_path); .Ve .PP Parse contents of \f(CW$source_path\fR and change links to copy into \f(CW$destination_path\fR. But don't make \f(CW$destination_path\fR. Just return modified \s-1HTML\s0. The encoding of strings is converted into utf8. .SH "CONSTRUCTOR METHODS" .IX Header "CONSTRUCTOR METHODS" .SS "new" .IX Subsection "new" .Vb 1 \& $p = HTML::Copy\->new($source); .Ve .PP Make an instance of this module with specifying a source of \s-1HTML\s0. .PP The argument \f(CW$source\fR can be a file path or a file handle. When a file handle is passed, you may need to indicate a file path of the passed file handle by the method \*(L"source_path\*(R". If calling \*(L"source_path\*(R" is omitted, it is assumed that the location of the file handle is the current working directory. .SH "INSTANCE METHODS" .IX Header "INSTANCE METHODS" .SS "copy_to" .IX Subsection "copy_to" .Vb 1 \& $p\->copy_to($destination) .Ve .PP Parse contents of \f(CW$source\fR given in new method, change links and write into \f(CW$destination\fR. .PP The argument \f(CW$destination\fR can be a file path or a file handle. When \f(CW$destination\fR is a file handle, you may need to indicate the location of the file handle by a method \*(L"destination_path\*(R". \*(L"destination_path\*(R" must be called before calling \*(L"copy_to\*(R". When calling \*(L"destination_path\*(R" is omitted, it is assumed that the locaiton of the file handle is the current working directory. .SS "parse_to" .IX Subsection "parse_to" .Vb 1 \& $p\->parse_to($destination_path) .Ve .PP Parse contents of \f(CW$source_path\fR given in new method, change links and return \s-1HTML\s0 contents to wirte \f(CW$destination_path\fR. Unlike copy_to, \f(CW$destination_path\fR will not created and just return modified \s-1HTML\s0. The encoding of strings is converted into utf8. .SH "ACCESSOR METHODS" .IX Header "ACCESSOR METHODS" .SS "source_path" .IX Subsection "source_path" .Vb 2 \& $p\->source_path \& $p\->source_path($path) .Ve .PP Get and set a source location. Usually source location is specified with the \*(L"new\*(R" method. When a file handle is passed to \*(L"new\*(R" and the location of the file handle is not the current working directory, you need to use this method. .SS "destination_path" .IX Subsection "destination_path" .Vb 2 \& $p\->destination_path \& $p\->destination_path($path) .Ve .PP Get and set a destination location. Usually destination location is specified with the \*(L"copy_to\*(R". When a file handle is passed to \*(L"copy_to\*(R" and the location of the file handle is not the current working directory, you need to use this method before \*(L"copy_to\*(R". .SS "enchoding" .IX Subsection "enchoding" .Vb 1 \& $p\->encoding; .Ve .PP Get an encoding of a source \s-1HTML\s0. .SS "io_layer" .IX Subsection "io_layer" .Vb 2 \& $p\->io_layer; \& $p\->io_layer(\*(Aq:utf8\*(Aq); .Ve .PP Get and set PerlIO layer to read the source path and to write the destination path. Usually it was automatically determined by \f(CW$source_path\fR's charset tag. If charset is not specified, Encode::Guess module will be used. .SS "encode_suspects" .IX Subsection "encode_suspects" .Vb 2 \& @suspects = $p\->encode_sustects; \& $p\->encode_suspects(qw/shiftjis euc\-jp/); .Ve .PP Add suspects of text encoding to guess the text encoding of the source \s-1HTML\s0. If the source \s-1HTML\s0 have charset tag, it is not required to add suspects. .SS "source_html" .IX Subsection "source_html" .Vb 1 \& $p\->source_html; .Ve .PP Obtain source \s-1HTML\s0's contents .SH "NOTE" .IX Header "NOTE" Cleanuped pathes should be given to HTML::Copy and it's instances. For example, a verbose path like '/aa/bb/../cc' may cause converting links wrongly. This is a limitaion of the \s-1URI\s0 module's rel method. To cleanup pathes, Cwd::realpath is useful. .SH "AUTHOR" .IX Header "AUTHOR" Tetsuro \s-1KURITA\s0