perlSGML.1997Sep
view release on metacpan or search on metacpan
doc/SGML..Parser.sgml view on Meta::CPAN
<p>SGML::Parser - SGML instance parser</p>
<!-- =================================================================== -->
<hr><h2><a name="Synopsis">Synopsis</a></h2>
<pre>
package MyParser;
use SGML::Parser;
@ISA = qw( SGML::Parser );
sub cdata { ... }
sub char_ref { ... }
sub comment_decl { ... }
sub end_tag { ... }
sub entity_ref { ... }
sub ignored_data { ... }
sub marked_sect_close { ... }
sub marked_sect_open { ... }
sub parm_entity_ref { ... }
sub processing_inst { ... }
sub start_tag { ... }
doc/SGML..Parser.sgml view on Meta::CPAN
</p>
<!-- =================================================================== -->
<hr><h2><a name="Callback_Methods">Callback Methods</a></h2>
<p>The following methods are intended to be redefined by a derived
class to handle the processing events generated by the
<strong>parse_data</strong> method.
</p>
<ul>
<li><a href="#cdata">cdata</a></li>
<li><a href="#char_ref">char_ref</a></li>
<li><a href="#comment_decl">comment_decl</a></li>
<li><a href="#end_tag">end_tag</a></li>
<li><a href="#entity_ref">entity_ref</a></li>
<li><a href="#error">error</a></li>
<li><a href="#ignored_data">ignored_data</a></li>
<li><a href="#marked_sect_close">marked_sect_close</a></li>
<li><a href="#marked_sect_open">marked_sect_open</a></li>
<li><a href="#parm_entity_ref">parm_entity_ref</a></li>
<li><a href="#processing_inst">processing_inst</a></li>
<li><a href="#start_tag">start_tag</a></li>
</ul>
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<hr size=0 width="50%" align=left noshade>
<h3><a name="cdata">cdata</a></h3>
<pre>
$parser-><strong>cdata</strong>(<var>$data</var>);
</pre>
<h4>Arguments:</h4>
<dl>
<dt><var>$data</var>
<dd>Character data.
</dl>
<h4>Return:</h4>
<p>N/A
</p>
<h4>Description:</h4>
<p><strong>cdata</strong> is invoked when character data is encountered.
The character data is passed into the method. Multiple lines of
character data may generate multiple <strong>cdata</strong> calls.
</p>
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<hr size=0 width="50%" align=left noshade>
<h3><a name="char_ref">char_ref</a></h3>
<pre>
$parser-><strong>char_ref</strong>(<var>$value</var>);
</pre>
<h4>Arguments:</h4>
doc/html/SGML..Parser.html view on Meta::CPAN
<p>SGML::Parser - SGML instance parser</p>
<!-- =================================================================== -->
<hr><h2><a name="Synopsis">Synopsis</a></h2>
<pre>
package MyParser;
use SGML::Parser;
@ISA = qw( SGML::Parser );
sub cdata { ... }
sub char_ref { ... }
sub comment_decl { ... }
sub end_tag { ... }
sub entity_ref { ... }
sub ignored_data { ... }
sub marked_sect_close { ... }
sub marked_sect_open { ... }
sub parm_entity_ref { ... }
sub processing_inst { ... }
sub start_tag { ... }
doc/html/SGML..Parser.html view on Meta::CPAN
</p>
<!-- =================================================================== -->
<hr><h2><a name="Callback_Methods">Callback Methods</a></h2>
<p>The following methods are intended to be redefined by a derived
class to handle the processing events generated by the
<strong>parse_data</strong> method.
</p>
<ul>
<li><a href="#cdata">cdata</a></li>
<li><a href="#char_ref">char_ref</a></li>
<li><a href="#comment_decl">comment_decl</a></li>
<li><a href="#end_tag">end_tag</a></li>
<li><a href="#entity_ref">entity_ref</a></li>
<li><a href="#error">error</a></li>
<li><a href="#ignored_data">ignored_data</a></li>
<li><a href="#marked_sect_close">marked_sect_close</a></li>
<li><a href="#marked_sect_open">marked_sect_open</a></li>
<li><a href="#parm_entity_ref">parm_entity_ref</a></li>
<li><a href="#processing_inst">processing_inst</a></li>
<li><a href="#start_tag">start_tag</a></li>
</ul>
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<hr size=0 width="50%" align=left noshade>
<h3><a name="cdata">cdata</a></h3>
<pre>
$parser-><strong>cdata</strong>(<var>$data</var>);
</pre>
<h4>Arguments:</h4>
<dl>
<dt><var>$data</var>
<dd>Character data.
</dl>
<h4>Return:</h4>
<p>N/A
</p>
<h4>Description:</h4>
<p><strong>cdata</strong> is invoked when character data is encountered.
The character data is passed into the method. Multiple lines of
character data may generate multiple <strong>cdata</strong> calls.
</p>
<!-- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -->
<hr size=0 width="50%" align=left noshade>
<h3><a name="char_ref">char_ref</a></h3>
<pre>
$parser-><strong>char_ref</strong>(<var>$value</var>);
</pre>
<h4>Arguments:</h4>
doc/html/sgml.pl.html view on Meta::CPAN
<dl>
<dt>An open tag</dt>
<dd><code>&$sgml'OpenTagFunc($gi, $attribute_list);</code></dd>
<dt>An end tag</dt>
<dd><code>&$sgml'EndTagFunc($gi);</code></dd>
<dt>A comment</dt>
<dd><code>&$sgml'CommentFunc(*comment_text);</code></dd>
<dt>Processing instruction</dt>
<dd><code>&$sgml'ProcInsFunc(*pi_text);</code></dd>
<dt>Character data</dt>
<dd><code>&$sgml'CdataFunc(*cdata);</code></dd>
</dl>
<h4>Notes</h4>
<ul>
<li><p><code>SGMLread_sgml</code> is not intended to parse a DTD, or an
SGML declaration statement, '<code><!SGML ...></code>'. It is
designed to parse SGML instances. If a "<code><!</code>" sequence
is encountered (and not part of a comment declaration,
<code>SGMLread_sgml</code> tries to ignore the declaration.
</p></li>
doc/sgml.pl.sgml view on Meta::CPAN
<dl>
<dt>An open tag</dt>
<dd><code>&$sgml'OpenTagFunc($gi, $attribute_list);</code></dd>
<dt>An end tag</dt>
<dd><code>&$sgml'EndTagFunc($gi);</code></dd>
<dt>A comment</dt>
<dd><code>&$sgml'CommentFunc(*comment_text);</code></dd>
<dt>Processing instruction</dt>
<dd><code>&$sgml'ProcInsFunc(*pi_text);</code></dd>
<dt>Character data</dt>
<dd><code>&$sgml'CdataFunc(*cdata);</code></dd>
</dl>
<h4>Notes</h4>
<ul>
<li><p><code>SGMLread_sgml</code> is not intended to parse a DTD, or an
SGML declaration statement, '<code><!SGML ...></code>'. It is
designed to parse SGML instances. If a "<code><!</code>" sequence
is encountered (and not part of a comment declaration,
<code>SGMLread_sgml</code> tries to ignore the declaration.
</p></li>
lib/SGML/DTD.pm view on Meta::CPAN
##---------------------------------------------------------------------------
## reset() initializes all instance variables.
##
sub reset {
my $this = shift;
$this->{ParEntity} = {}; # Int parameter entities
$this->{PubParEntity} = {}; # Ext public parameter entities
$this->{SysParEntity} = {}; # Ext system parameter entities
$this->{GenEntity} = {}; # (pcdata) general entities
$this->{StartTagEntity} = {}; # Start tag entities (STARTTAG)
$this->{EndTagEntity} = {}; # End tag entities (ENDTAG)
$this->{MSEntity} = {}; # Marked section ents (MS)
$this->{MDEntity} = {}; # Markup declaration ents (MD)
$this->{PIEntity} = {}; # Processing instructions ents (PI)
$this->{CDataEntity} = {}; # Character data entities (CDATA)
$this->{SDataEntity} = {}; # System data ents (SDATA)
## Following ent structures currently not used.
$this->{PubEntity} = {}; # External public ents (PUBLIC)
$this->{SysEntity} = {}; # External system ents (SYSTEM)
$this->{SysCDEntity} = {}; # Ext cdata ents (SYSTEM CDATA)
$this->{SysNDEntity} = {}; # Ext non-SGML ents (SYSTEM NDATA)
$this->{SysSDEntity} = {}; # Ext sdata ents (SYSTEM SDATA)
$this->{SysSubDEntity} = {}; # Ext sub doc ents (SYSTEM SUBDOC)
$this->{SysNotation} = {}; # Notations w/SYSTEM ids
$this->{PubNotation} = {}; # Notations w/PUBLIC ids
$this->{ShortRef} = {}; # Short ref mappings
$this->{UseMap} = {}; # Maps in use (<!USEMAP ...)
lib/SGML/DTD.pm view on Meta::CPAN
$this->do_ge_starttag($name, $line), last GENSW
if $tmp =~ /^\s*$STARTTAG\s*$/io;
$this->do_ge_endtag($name, $line), last GENSW
if $tmp =~ /^\s*$ENDTAG\s*$/io;
$this->do_ge_ms($name, $line), last GENSW
if $tmp =~ /^\s*$MS\s*$/io;
$this->do_ge_md($name, $line), last GENSW
if $tmp =~ /^\s*$MD\s*$/io;
$this->do_ge_pi($name, $line), last GENSW
if $tmp =~ /^\s*$PI\s*$/io;
$this->do_ge_cdata($name, $line), last GENSW
if $tmp =~ /^\s*$CDATA\s*$/io;
$this->do_ge_sdata($name, $line), last GENSW
if $tmp =~ /^\s*$SDATA\s*$/io;
$this->do_ge_public($name, $line), last GENSW
if $tmp =~ /^\s*$PUBLIC\s*$/io;
$this->do_ge_system($name, $line), last GENSW
if $tmp =~ /^\s*$SYSTEM\s*$/io;
$this->{_AGE}{$name} = $this->{GenEntity}{$name} = $tmp;
}
push(@{$this->{GenEntities}}, $name);
lib/SGML/DTD.pm view on Meta::CPAN
sub do_ge_pi {
my $this = shift;
my($name, $line) = @_;
my($tmp);
$tmp = &get_next_group($line);
$this->{PIEntity}{$name} = $tmp;
$this->{_AGE}{$name} = $pio_ . $tmp . $pic_;
}
sub do_ge_cdata {
my $this = shift;
my($name, $line) = @_;
my($tmp);
$tmp = &get_next_group($line);
$this->{CDataEntity}{$name} = $tmp;
}
sub do_ge_sdata {
my $this = shift;
lib/SGML/Parser.pm view on Meta::CPAN
## $line_no_start);
##
## Only the first argument is required. The other are optional.
##
## The routine calls callback methods for the various events
## that can occur. It is up to the methods to make sense of
## the data.
##
## The following lists the various methods invoked during parsing:
##
## $this->cdata($cdata);
## $this->char_ref($funcname_or_charnum);
## $this->comment_decl(\@comments);
## $this->end_tag($gi);
## $txt = $this->entity_ref($entname);
## $this->ignored_data($data);
## $this->marked_sect_close();
## $this->marked_sect_open($status_keyword, $status_spec);
## $txt = $this->parm_entity_ref($entname);
## $this->processing_inst($pidata);
## $this->start_tag($gi, $attr_spec);
lib/SGML/Parser.pm view on Meta::CPAN
last LOOP unless defined($buf = $this->_get_line());
}
#--------------------------------------------------------------
# Check for markup. Choose match that occurs earliest in
# string.
#--------------------------------------------------------------
($before, $after, $type, $m1) = (undef,'','','');
# Pcdata mode checks
if ($this->{'mode'} == $ModePCData) {
if ($buf =~ m@<([!?/>$namestart])@o) {
$before = $`; $m1 = $1; $after = $';
BLK: {
if ($m1 eq '!') { $type = $TypeMDO; last BLK; }
if ($m1 eq '?') { $type = $TypePIO; last BLK; }
if ($m1 eq '/') { $type = $TypeETagO; last BLK; }
if ($m1 eq '>') { $type = $TypeSTagO; last BLK; }
$type = $TypeSTagO;
}
lib/SGML/Parser.pm view on Meta::CPAN
$this->{'mode'} == $ModeMSRCData) {
if ($buf =~ m@\&([#$namestart])@o) {
if (!defined($before) or length($before) > length($`)) {
$before = $`; $m1 = $1; $after = $';
$type = $TypeERO;
}
}
}
# Check for cdata mode
if ($this->{'mode'} == $ModeCData) {
if ($buf =~ m|<(/)|) {
if (!defined($before) or length($before) > length($`)) {
$before = $`; $m1 = $1; $after = $';
$type = $TypeETagO;
}
}
}
# Check for marked section close
lib/SGML/Parser.pm view on Meta::CPAN
if ($type == $TypeMSC and length($before) > length($`)) {
$this->{'_open_ms_ign'}++;
}
}
}
#--------------------------------------------------------------
# Now, check what the type is and process accordingly.
#--------------------------------------------------------------
## Invoke cdata callback if any before text -------------------
if ($before ne '') {
$this->{'mode'} == $ModeIgnore ?
$this->ignored_data($before) : $this->cdata($before);
}
## Entity reference -------------------------------------------
if ($type == $TypeERO) {
$buf = $after;
$name = $m1;
if ($name eq '#') { # Character reference
if ($buf =~ s/^([$namechars]+);?//o) {
$name = $1;
lib/SGML/Parser.pm view on Meta::CPAN
"Comment declaration " .
"not closed");
last COMDCL;
}
}
if ($buf =~ s/^\s*--//o) {
next COMDCL;
} elsif ($buf =~ s/^\s*>//o) {
last COMDCL;
} else { # punt
$this->error("Invalid cdata outside of comment");
next COMDCL;
}
}
$this->comment_decl(\@comms);
next LOOP;
} # end comment
$buf = "<!" . $buf;
} # end markup declaration
## If not markup, invoke cdata callback -----------------------
$this->{'mode'} == $ModeIgnore ?
$this->ignored_data($buf) :
$this->cdata($buf);
$buf = '';
}
}; # End eval
$this->{'_input'} = pop(@{$this->{'_input_stack'}});
# Return buffer. May contain data if parsing was aborted, otherwise
# should be undef.
$buf;
lib/SGML/Parser.pm view on Meta::CPAN
##########################################################################
##**********************************************************************##
## CALLBACK METHODS
##**********************************************************************##
## Subclasses are to redefine callback methods to perform
## whatever actions are desired.
##**********************************************************************##
sub cdata { }
sub char_ref { }
sub comment_decl { }
sub end_tag { }
sub entity_ref { undef }
sub ignored_data { }
sub marked_sect_close { }
sub marked_sect_open { }
sub parm_entity_ref { undef }
sub processing_inst { }
sub start_tag { }
lib/SGML/StripParser.pm view on Meta::CPAN
sub set_ign_parm_ents {
my $this = shift;
$this->{'_stripout'}{_ignents}{@_} = ('IGNORE') x scalar(@_);
}
##**********************************************************************##
## Redefined SGML::Parser Callback Methods
##**********************************************************************##
sub cdata {
my $this = shift;
print { $this->{'_stripout'}{'_fh'} } $_[0];
}
sub char_ref {
my $this = shift;
my $val = shift;
my $str = '';
if ($this->{'_stripout'}{'_charset'}) {
&do_ge_starttag($name, *line), last GENSW
if $tmp =~ /^\s*$STARTTAG\s*$/io;
&do_ge_endtag($name, *line), last GENSW
if $tmp =~ /^\s*$ENDTAG\s*$/io;
&do_ge_ms($name, *line), last GENSW
if $tmp =~ /^\s*$MS\s*$/io;
&do_ge_md($name, *line), last GENSW
if $tmp =~ /^\s*$MD\s*$/io;
&do_ge_pi($name, *line), last GENSW
if $tmp =~ /^\s*$PI\s*$/io;
&do_ge_cdata($name, *line), last GENSW
if $tmp =~ /^\s*$CDATA\s*$/io;
&do_ge_sdata($name, *line), last GENSW
if $tmp =~ /^\s*$SDATA\s*$/io;
&do_ge_public($name, *line), last GENSW
if $tmp =~ /^\s*$PUBLIC\s*$/io;
&do_ge_system($name, *line), last GENSW
if $tmp =~ /^\s*$SYSTEM\s*$/io;
$_AGE{$name} = $GenEntity{$name} = $tmp;
}
push(@GenEntities, $name);
sub do_ge_pi {
local($name, *line) = @_;
local($tmp);
$tmp = &get_next_group(*line);
$PIEntity{$name} = $tmp;
$_AGE{$name} = $pio_ . $tmp . $pic_;
}
sub do_ge_cdata {
local($name, *line) = @_;
local($tmp);
$tmp = &get_next_group(*line);
$CDataEntity{$name} = $tmp;
}
sub do_ge_sdata {
local($name, *line) = @_;
local($tmp);
lib/sgml.pl view on Meta::CPAN
##---------------------------------------------------------------------------
## SGMLread_sgml() reads SGML markup. A callback is called when
## the following occurs:
##
## o An open tag: &$OpenTagFunc($gi, $attribute_list)
## o An end tag: &$EndTagFunc($gi)
## o A comment: &$CommentFunc(*comment_text);
## o Processing instruction:
## &$ProcInsFunc(*pi_text);
## o Character data: &$CdataFunc(*cdata);
##
## Argument descriptions:
## $handle : Filehandle containing the SGML instance.
##
## Notes:
## o read_sgml() is not intended to parse a DTD, or an
## SGML declaration statement, '<!SGML ...>'. It is
## designed to parse SGML instances. If a "<!" sequence
## is encountered (and not part of a comment declaration,
## read_sgml() tries to ignore the declaration.
old/stripsgml view on Meta::CPAN
);
##---------------------------------------------------------------------------##
## Globals
##---------------------------------------------------------------------------##
## Variable to hold current URL
$Url = '';
## Register callbacks to sgml.pl
$sgml'CdataFunc = "main'cdata_cb";
$sgml'OpenTagFunc = "main'open_tag_cb";
$sgml'EndTagFunc = "main'close_tag_cb";
##---------------------------------------------------------------------------##
##------------##
## Begin MAIN ##
##------------##
{
&get_cli_opts();
old/stripsgml view on Meta::CPAN
&Usage() unless
&NGetOpt(
"html", # Generate compact listing
"help" # Help message
);
&Usage() if defined($opt_help);
$HTML = 1 if defined($opt_html);
}
sub cdata_cb {
local(*data) = shift;
$data =~ s/\&([#\w-._]+);/&expand_ent($1)/ge;
print STDOUT $data;
}
sub open_tag_cb {
local($gi, $attr) = ($_[0], $_[1]);
if ($HTML && ($gi =~ /^A$/i)) {
sgm/IBMIDDoc.dtd view on Meta::CPAN
<!ELEMENT FragmentRef - O (Title) -- Fragment Reference -->
<!ATTLIST FragmentRef
FragID NAME #CONREF -- Must be Fragment ID --
Repeat CDATA #IMPLIED -- Default is NO --
RepID NAME #IMPLIED -- Must be REPSEP ID --
RepSep CDATA #IMPLIED -- Repeat separator chars --
OptReq (Opt | Req| Def) Req
%Common.Atts.NoLexMdl.NoRefType;
LexModel CDATA #FIXED
"REPEAT ('YES' | 'NO' | number | rcdata)
&Common.LexModel;"
RefType CDATA #FIXED
"RepID RepSep FragID Fragment &Common.RefType;"
TargetType CDATA #FIXED "Fragment"
InfoMaster NAME #FIXED "SymbolicReference"
>
<!ELEMENT Range - O (Title, RangeStart?, RangeEnd?) >
<!ATTLIST Range
Repeat CDATA #IMPLIED
RepID NAME #IMPLIED -- Must be REPSEP ID --
SetID NAME #IMPLIED -- Must be SET ID --
RepSep CDATA #IMPLIED -- Repeat separator chars --
OptReq (Opt | Req| Def) Req
%Common.Atts.NoLexMdl.NoRefType;
LexModel CDATA #FIXED
"REPEAT ('YES' | 'NO' | number | rcdata)
&Common.LexModel;"
RefType CDATA #FIXED
"REPID REPSEP SETID SET &Common.RefType;"
>
<!ELEMENT (RangeStart | RangeEnd)
- O (%DataPool;)* >
<!ATTLIST (RangeStart | RangeEnd)
%Common.Atts;
>
( run in 0.356 second using v1.01-cache-2.11-cpan-454fe037f31 )