.\" Automatically generated by Pod::Man 2.27 (Pod::Simple 3.28) .\" .\" 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 "HTML::Quoted 3pm" .TH HTML::Quoted 3pm "2014-02-08" "perl v5.18.2" "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::Quoted \- extract structure of quoted HTML mail message .SH "SYNOPSIS" .IX Header "SYNOPSIS" .Vb 3 \& use HTML::Quoted; \& my $html = \*(Aq...\*(Aq; \& my $struct = HTML::Quoted\->extract( $html ); .Ve .SH "DESCRIPTION" .IX Header "DESCRIPTION" Parses and extracts quotation structure out of a \s-1HTML\s0 message. Purpose and returned structures are very similar to Text::Quoted. .SH "SUPPORTED FORMATS" .IX Header "SUPPORTED FORMATS" Variouse MUAs use quite different approaches for quoting in mails. .PP Some use \fIblockquote\fR tag and it's quite easy to parse. .PP Some wrap text into \fIp\fR tags and add '>' in the beginning of the paragraphs. .PP Things gettign messier when it's an \s-1HTML\s0 reply on plain text mail thread. .PP If \fByou found format\fR that is not supported then file a bug report via rt.cpan.org with as short as possible example. \fBTest file\fR is even better. Test file with patch is the best. Not obviouse patches without tests suck. .SH "METHODS" .IX Header "METHODS" .SS "extract" .IX Subsection "extract" .Vb 1 \& my $struct = HTML::Quoted\->extract( $html ); .Ve .PP Takes a string with \s-1HTML\s0 and returns array reference. Each element in the array either array or hash. For example: .PP .Vb 11 \& [ \& { \*(Aqraw\*(Aq => \*(AqHi,\*(Aq }, \& { \*(Aqraw\*(Aq => \*(Aq

On date X wrote:
\*(Aq }, \& [ \& { \*(Aqraw\*(Aq => \*(Aq
\*(Aq }, \& { \*(Aqraw\*(Aq => \*(AqHello,\*(Aq }, \& { \*(Aqraw\*(Aq => \*(Aq
How are you?
\*(Aq }, \& { \*(Aqraw\*(Aq => \*(Aq
\*(Aq } \& ], \& ... \& ] .Ve .PP Hashes represent a part of the html. The following keys are meaningful at the moment: .IP "\(bu" 4 raw \- raw \s-1HTML\s0 .IP "\(bu" 4 quoter_raw, quoter \- raw and decoded (entities are converted) quoter if block is prefixed with quoting characters .SS "combine_hunks" .IX Subsection "combine_hunks" .Vb 1 \& my $html = HTML::Quoted\->combine_hunks( $arrayref_of_hunks ); .Ve .PP Takes the output of \f(CW\*(C`extract\*(C'\fR and turns it back into \s-1HTML.\s0 .SH "AUTHOR" .IX Header "AUTHOR" Ruslan.Zakirov .SH "LICENSE" .IX Header "LICENSE" Under the same terms as perl itself.