[OpenSPARC-T2-DV] / tools / perl-5.8.0 / man / man3 / HTML::Filter.3

.\" Automatically generated by Pod::Man v1.34, Pod::Parser v1.13
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sh \" Subsection heading
.br
.if t .Sp
.ne 5
.PP
\fB\\$1\fR
.PP
..
.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.  | will give a
.\" real vertical bar.  \*(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-|\(bv\*(Tr
.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\}
.\"
.\" If the F register is turned on, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.if \nF \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    nr % 0
.    rr F
.\}
.\"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.hy 0
.if n .na
.\"
.\" 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::Filter 3"
.TH HTML::Filter 3 "1999-12-09" "perl v5.8.0" "User Contributed Perl Documentation"
.SH "NAME"
HTML::Filter \- Filter HTML text through the parser
.SH "NOTE"
.IX Header "NOTE"
This module is deprecated. \f(CW\*(C`HTML::Parser\*(C'\fR now provides the
functionally of \f(CW\*(C`HTML::Filter\*(C'\fR much more efficiently with the the
\&\f(CW\*(C`default\*(C'\fR handler.
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 2
\& require HTML::Filter;
\& $p = HTML::Filter->new->parse_file("index.html");
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
\&\f(CW\*(C`HTML::Filter\*(C'\fR is an \s-1HTML\s0 parser that by default prints the
original text of each \s-1HTML\s0 element (a slow version of \fIcat\fR\|(1) basically).
The callback methods may be overridden to modify the filtering for some
\&\s-1HTML\s0 elements and you can override \fIoutput()\fR method which is called to
print the \s-1HTML\s0 text.
.PP
\&\f(CW\*(C`HTML::Filter\*(C'\fR is a subclass of \f(CW\*(C`HTML::Parser\*(C'\fR. This means that
the document should be given to the parser by calling the \f(CW$p\fR\->\fIparse()\fR
or \f(CW$p\fR\->\fIparse_file()\fR methods.
.SH "EXAMPLES"
.IX Header "EXAMPLES"
The first example is a filter that will remove all comments from an
\&\s-1HTML\s0 file.  This is achieved by simply overriding the comment method
to do nothing.
.PP
.Vb 4
\&  package CommentStripper;
\&  require HTML::Filter;
\&  @ISA=qw(HTML::Filter);
\&  sub comment { }  # ignore comments
.Ve
.PP
The second example shows a filter that will remove any <\s-1TABLE\s0>s
found in the \s-1HTML\s0 file.  We specialize the \fIstart()\fR and \fIend()\fR methods
to count table tags and then make output not happen when inside a
table.
.PP
.Vb 9
\&  package TableStripper;
\&  require HTML::Filter;
\&  @ISA=qw(HTML::Filter);
\&  sub start
\&  {
\&     my $self = shift;
\&     $self->{table_seen}++ if $_[0] eq "table";
\&     $self->SUPER::start(@_);
\&  }
.Ve
.PP
.Vb 6
\&  sub end
\&  {
\&     my $self = shift;
\&     $self->SUPER::end(@_);
\&     $self->{table_seen}-- if $_[0] eq "table";
\&  }
.Ve
.PP
.Vb 7
\&  sub output
\&  {
\&      my $self = shift;
\&      unless ($self->{table_seen}) {
\&          $self->SUPER::output(@_);
\&      }
\&  }
.Ve
.PP
If you want to collect the parsed text internally you might want to do
something like this:
.PP
.Vb 5
\&  package FilterIntoString;
\&  require HTML::Filter;
\&  @ISA=qw(HTML::Filter);
\&  sub output { push(@{$_[0]->{fhtml}}, $_[1]) }
\&  sub filtered_html { join("", @{$_[0]->{fhtml}}) }
.Ve
.SH "SEE ALSO"
.IX Header "SEE ALSO"
HTML::Parser
.SH "COPYRIGHT"
.IX Header "COPYRIGHT"
Copyright 1997\-1999 Gisle Aas.
.PP
This library is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.
Commit	Line	Data
86530b38 AT	1	.\" Automatically generated by Pod::Man v1.34, Pod::Parser v1.13
	2	.\"
	3	.\" Standard preamble:
	4	.\" ========================================================================
	5	.de Sh \" Subsection heading
	6	.br
	7	.if t .Sp
	8	.ne 5
	9	.PP
	10	\fB\\$1\fR
	11	.PP
	12	..
	13	.de Sp \" Vertical space (when we can't use .PP)
	14	.if t .sp .5v
	15	.if n .sp
	16	..
	17	.de Vb \" Begin verbatim text
	18	.ft CW
	19	.nf
	20	.ne \\$1
	21	..
	22	.de Ve \" End verbatim text
	23	.ft R
	24	.fi
	25	..
	26	.\" Set up some character translations and predefined strings. \*(-- will
	27	.\" give an unbreakable dash, \(PI will give pi, \(L" will give a left
	28	.\" double quote, and \*(R" will give a right double quote. \| will give a
	29	.\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to
	30	.\" do unbreakable dashes and therefore won't be available. \(C` and \(C'
	31	.\" expand to `' in nroff, nothing in troff, for use with C<>.
	32	.tr \(W-\|\(bv\(Tr
	33	.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
	34	.ie n \{\
	35	. ds -- \(*W-
	36	. ds PI pi
	37	. if (\n(.H=4u)&(1m=24u) .ds -- \(W\h'-12u'\(W\h'-12u'-\" diablo 10 pitch
	38	. if (\n(.H=4u)&(1m=20u) .ds -- \(W\h'-12u'\(W\h'-8u'-\" diablo 12 pitch
	39	. ds L" ""
	40	. ds R" ""
	41	. ds C` ""
	42	. ds C' ""
	43	'br\}
	44	.el\{\
	45	. ds -- \\|\(em\\|
	46	. ds PI \(*p
	47	. ds L" ``
	48	. ds R" ''
	49	'br\}
	50	.\"
	51	.\" If the F register is turned on, we'll generate index entries on stderr for
	52	.\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index
	53	.\" entries marked with X<> in POD. Of course, you'll have to process the
	54	.\" output yourself in some meaningful fashion.
	55	.if \nF \{\
	56	. de IX
	57	. tm Index:\\$1\t\\n%\t"\\$2"
	58	..
	59	. nr % 0
	60	. rr F
	61	.\}
	62	.\"
	63	.\" For nroff, turn off justification. Always turn off hyphenation; it makes
	64	.\" way too many mistakes in technical documents.
65	.hy 0
66	.if n .na
67	.\"
68	.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
69	.\" Fear. Run. Save yourself. No user-serviceable parts.
70	. \" fudge factors for nroff and troff
71	.if n \{\
72	. ds #H 0
73	. ds #V .8m
74	. ds #F .3m
75	. ds #[ \f1
76	. ds #] \fP
77	.\}
78	.if t \{\
79	. ds #H ((1u-(\\\\n(.fu%2u))*.13m)
80	. ds #V .6m
81	. ds #F 0
82	. ds #[ \&
83	. ds #] \&
84	.\}
85	. \" simple accents for nroff and troff
86	.if n \{\
87	. ds ' \&
88	. ds ` \&
89	. ds ^ \&
90	. ds , \&
91	. ds ~ ~
92	. ds /
93	.\}
94	.if t \{\
95	. ds ' \\k:\h'-(\\n(.wu8/10-\(#H)'\'\h"\|\\n:u"
96	. ds ` \\k:\h'-(\\n(.wu8/10-\(#H)'\`\h'\|\\n:u'
97	. ds ^ \\k:\h'-(\\n(.wu10/11-\(#H)'^\h'\|\\n:u'
98	. ds , \\k:\h'-(\\n(.wu*8/10)',\h'\|\\n:u'
99	. ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'\|\\n:u'
100	. ds / \\k:\h'-(\\n(.wu8/10-\(#H)'\z\(sl\h'\|\\n:u'
101	.\}
102	. \" troff and (daisy-wheel) nroff accents
103	.ds : \\k:\h'-(\\n(.wu8/10-\(#H+.1m+\(#F)'\v'-\(#V'\z.\h'.2m+\(#F'.\h'\|\\n:u'\v'\(#V'
104	.ds 8 \h'\(#H'\(b\h'-\*(#H'
105	.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\(#H)/2u'\v'-.3n'\(#[\z\(de\v'.3n'\h'\|\\n:u'\*(#]
106	.ds d- \h'\(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\(#H'
107	.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'\|\\n:u'
108	.ds th \(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u2/3)'\s-1o\s+1\*(#]
109	.ds Th \(#[\s+2I\s-2\h'-\w'I'u3/5'\v'-.3m'o\v'.3m'\*(#]
110	.ds ae a\h'-(\w'a'u*4/10)'e
111	.ds Ae A\h'-(\w'A'u*4/10)'E
112	. \" corrections for vroff
113	.if v .ds ~ \\k:\h'-(\\n(.wu9/10-\(#H)'\s-2\u~\d\s+2\h'\|\\n:u'
114	.if v .ds ^ \\k:\h'-(\\n(.wu10/11-\(#H)'\v'-.4m'^\v'.4m'\h'\|\\n:u'
115	. \" for low resolution devices (crt and lpr)
116	.if \n(.H>23 .if \n(.V>19 \
117	\{\
118	. ds : e
119	. ds 8 ss
120	. ds o a
121	. ds d- d\h'-1'\(ga
122	. ds D- D\h'-1'\(hy
123	. ds th \o'bp'
124	. ds Th \o'LP'
125	. ds ae ae
126	. ds Ae AE
127	.\}
128	.rm #[ #] #H #V #F C
129	.\" ========================================================================
130	.\"
131	.IX Title "HTML::Filter 3"
132	.TH HTML::Filter 3 "1999-12-09" "perl v5.8.0" "User Contributed Perl Documentation"
133	.SH "NAME"
134	HTML::Filter \- Filter HTML text through the parser
135	.SH "NOTE"
136	.IX Header "NOTE"
137	This module is deprecated. \f(CW\(C`HTML::Parser\(C'\fR now provides the
138	functionally of \f(CW\(C`HTML::Filter\(C'\fR much more efficiently with the the
139	\&\f(CW\(C`default\(C'\fR handler.
140	.SH "SYNOPSIS"
141	.IX Header "SYNOPSIS"
142	.Vb 2
143	\& require HTML::Filter;
144	\& $p = HTML::Filter->new->parse_file("index.html");
145	.Ve
146	.SH "DESCRIPTION"
147	.IX Header "DESCRIPTION"
148	\&\f(CW\(C`HTML::Filter\(C'\fR is an \s-1HTML\s0 parser that by default prints the
149	original text of each \s-1HTML\s0 element (a slow version of \fIcat\fR\\|(1) basically).
150	The callback methods may be overridden to modify the filtering for some
151	\&\s-1HTML\s0 elements and you can override \fIoutput()\fR method which is called to
152	print the \s-1HTML\s0 text.
153	.PP
154	\&\f(CW\(C`HTML::Filter\(C'\fR is a subclass of \f(CW\(C`HTML::Parser\(C'\fR. This means that
155	the document should be given to the parser by calling the \f(CW$p\fR\->\fIparse()\fR
156	or \f(CW$p\fR\->\fIparse_file()\fR methods.
157	.SH "EXAMPLES"
158	.IX Header "EXAMPLES"
159	The first example is a filter that will remove all comments from an
160	\&\s-1HTML\s0 file. This is achieved by simply overriding the comment method
161	to do nothing.
162	.PP
163	.Vb 4
164	\& package CommentStripper;
165	\& require HTML::Filter;
166	\& @ISA=qw(HTML::Filter);
167	\& sub comment { } # ignore comments
168	.Ve
169	.PP
170	The second example shows a filter that will remove any <\s-1TABLE\s0>s
171	found in the \s-1HTML\s0 file. We specialize the \fIstart()\fR and \fIend()\fR methods
172	to count table tags and then make output not happen when inside a
173	table.
174	.PP
175	.Vb 9
176	\& package TableStripper;
177	\& require HTML::Filter;
178	\& @ISA=qw(HTML::Filter);
179	\& sub start
180	\& {
181	\& my $self = shift;
182	\& $self->{table_seen}++ if $_[0] eq "table";
183	\& $self->SUPER::start(@_);
184	\& }
185	.Ve
186	.PP
187	.Vb 6
188	\& sub end
189	\& {
190	\& my $self = shift;
191	\& $self->SUPER::end(@_);
192	\& $self->{table_seen}-- if $_[0] eq "table";
193	\& }
194	.Ve
195	.PP
196	.Vb 7
197	\& sub output
198	\& {
199	\& my $self = shift;
200	\& unless ($self->{table_seen}) {
201	\& $self->SUPER::output(@_);
202	\& }
203	\& }
204	.Ve
205	.PP
206	If you want to collect the parsed text internally you might want to do
207	something like this:
208	.PP
209	.Vb 5
210	\& package FilterIntoString;
211	\& require HTML::Filter;
212	\& @ISA=qw(HTML::Filter);
213	\& sub output { push(@{$_[0]->{fhtml}}, $_[1]) }
214	\& sub filtered_html { join("", @{$_[0]->{fhtml}}) }
215	.Ve
216	.SH "SEE ALSO"
217	.IX Header "SEE ALSO"
218	HTML::Parser
219	.SH "COPYRIGHT"
220	.IX Header "COPYRIGHT"
221	Copyright 1997\-1999 Gisle Aas.
222	.PP
223	This library is free software; you can redistribute it and/or
224	modify it under the same terms as Perl itself.