NG4R3P

Linux 4gvps.4gvps.com 3.10.0-1127.18.2.vz7.163.46 #1 SMP Fri Nov 20 21:47:55 MSK 2020 x86_64
SOFT : Apache PHP : 7.4.33
/lib64/perl5/vendor_perl/HTML/

38.135.39.45

[ NAME ]	[ SIZE ]	[ PERM ]	[ DATE ]	[ ACT ]
+FILE +DIR
Entities.pm	14.644 KB	-rw-r--r--	2013-03-25 22:32	R E G D
Filter.pm	2.622 KB	-rw-r--r--	2013-03-25 22:32	R E G D
HeadParser.pm	8.326 KB	-rw-r--r--	2013-05-08 22:19	R E G D
LinkExtor.pm	4.399 KB	-rw-r--r--	2013-03-25 22:32	R E G D
Parser.pm	38.856 KB	-rw-r--r--	2013-05-08 22:19	R E G D
PullParser.pm	5.548 KB	-rw-r--r--	2013-03-25 22:32	R E G D
TokeParser.pm	9.867 KB	-rw-r--r--	2013-03-25 22:32	R E G D
REQUEST EXIT

package HTML::Parser; # Copyright 1996-2009, Gisle Aas. # Copyright 1999-2000, Michael A. Chase. # # This library is free software; you can redistribute it and/or # modify it under the same terms as Perl itself. use strict; use vars qw($VERSION @ISA); $VERSION = "3.71"; require HTML::Entities; require XSLoader; XSLoader::load('HTML::Parser', $VERSION); sub new { my $class = shift; my $self = bless {}, $class; return $self->init(@_); } sub init { my $self = shift; $self->_alloc_pstate; my %arg = @_; my $api_version = delete $arg{api_version} || (@_ ? 3 : 2); if ($api_version >= 4) { require Carp; Carp::croak("API version $api_version not supported " . "by HTML::Parser $VERSION"); } if ($api_version < 3) { # Set up method callbacks compatible with HTML-Parser-2.xx $self->handler(text => "text", "self,text,is_cdata"); $self->handler(end => "end", "self,tagname,text"); $self->handler(process => "process", "self,token0,text"); $self->handler(start => "start", "self,tagname,attr,attrseq,text"); $self->handler(comment => sub { my($self, $tokens) = @_; for (@$tokens) { $self->comment($_); } }, "self,tokens"); $self->handler(declaration => sub { my $self = shift; $self->declaration(substr($_[0], 2, -1)); }, "self,text"); } if (my $h = delete $arg{handlers}) { $h = {@$h} if ref($h) eq "ARRAY"; while (my($event, $cb) = each %$h) { $self->handler($event => @$cb); } } # In the end we try to assume plain attribute or handler while (my($option, $val) = each %arg) { if ($option =~ /^(\w+)_h$/) { $self->handler($1 => @$val); } elsif ($option =~ /^(text|start|end|process|declaration|comment)$/) { require Carp; Carp::croak("Bad constructor option '$option'"); } else { $self->$option($val); } } return $self; } sub parse_file { my($self, $file) = @_; my $opened; if (!ref($file) && ref(\$file) ne "GLOB") { # Assume $file is a filename local(*F); open(F, "<", $file) || return undef; binmode(F); # should we? good for byte counts $opened++; $file = *F; } my $chunk = ''; while (read($file, $chunk, 512)) { $self->parse($chunk) || last; } close($file) if $opened; $self->eof; } sub netscape_buggy_comment # legacy { my $self = shift; require Carp; Carp::carp("netscape_buggy_comment() is deprecated. " . "Please use the strict_comment() method instead"); my $old = !$self->strict_comment; $self->strict_comment(!shift) if @_; return $old; } # set up method stubs sub text { } *start = \&text; *end = \&text; *comment = \&text; *declaration = \&text; *process = \&text; 1; __END__ =head1 NAME HTML::Parser - HTML parser class =head1 SYNOPSIS use HTML::Parser (); # Create parser object $p = HTML::Parser->new( api_version => 3, start_h => [\&start, "tagname, attr"], end_h => [\&end, "tagname"], marked_sections => 1, ); # Parse document text chunk by chunk $p->parse($chunk1); $p->parse($chunk2); #... $p->eof; # signal end of document # Parse directly from file $p->parse_file("foo.html"); # or open(my $fh, "<:utf8", "foo.html") || die; $p->parse_file($fh); =head1 DESCRIPTION Objects of the C class will recognize markup and separate it from plain text (alias data content) in HTML documents. As different kinds of markup and text are recognized, the corresponding event handlers are invoked. C is not a generic SGML parser. We have tried to make it able to deal with the HTML that is actually "out there", and it normally parses as closely as possible to the way the popular web browsers do it instead of strictly following one of the many HTML specifications from W3C. Where there is disagreement, there is often an option that you can enable to get the official behaviour. The document to be parsed may be supplied in arbitrary chunks. This makes on-the-fly parsing as documents are received from the network possible. If event driven parsing does not feel right for your application, you might want to use C. This is an C subclass that allows a more conventional program structure. =head1 METHODS The following method is used to construct a new C object: =over =item $p = HTML::Parser->new( %options_and_handlers ) This class method creates a new C object and returns it. Key/value argument pairs may be provided to assign event handlers or initialize parser options. The handlers and parser options can also be set or modified later by the method calls described below. If a top level key is in the form "_h" (e.g., "text_h") then it assigns a handler to that event, otherwise it initializes a parser option. The event handler specification value must be an array reference. Multiple handlers may also be assigned with the 'handlers => [%handlers]' option. See examples below. If new() is called without any arguments, it will create a parser that uses callback methods compatible with version 2 of C. See the section on "version 2 compatibility" below for details. The special constructor option 'api_version => 2' can be used to initialize version 2 callbacks while still setting other options and handlers. The 'api_version => 3' option can be used if you don't want to set any options and don't want to fall back to v2 compatible mode. Examples: $p = HTML::Parser->new(api_version => 3, text_h => [ sub {...}, "dtext" ]); This creates a new parser object with a text event handler subroutine that receives the original text with general entities decoded. $p = HTML::Parser->new(api_version => 3, start_h => [ 'my_start', "self,tokens" ]); This creates a new parser object with a start event handler method that receives the $p and the tokens array. $p = HTML::Parser->new(api_version => 3, handlers => { text => [\@array, "event,text"], comment => [\@array, "event,text"], }); This creates a new parser object that stores the event type and the original text in @array for text and comment events. =back The following methods feed the HTML document to the C object: =over =item $p->parse( $string ) Parse $string as the next chunk of the HTML document. Handlers invoked should not attempt to modify the $string in-place until $p->parse returns. If an invoked event handler aborts parsing by calling $p->eof, then $p->parse() will return a FALSE value. Otherwise the return value is a reference to the parser object ($p). =item $p->parse( $code_ref ) If a code reference is passed as the argument to be parsed, then the chunks to be parsed are obtained by invoking this function repeatedly. Parsing continues until the function returns an empty (or undefined) result. When this happens $p->eof is automatically signaled. Parsing will also abort if one of the event handlers calls $p->eof. The effect of this is the same as: while (1) { my $chunk = &$code_ref(); if (!defined($chunk) || !length($chunk)) { $p->eof; return $p; } $p->parse($chunk) || return undef; } But it is more efficient as this loop runs internally in XS code. =item $p->parse_file( $file ) Parse text directly from a file. The $file argument can be a filename, an open file handle, or a reference to an open file handle. If $file contains a filename and the file can't be opened, then the method returns an undefined value and $! tells why it failed. Otherwise the return value is a reference to the parser object. If a file handle is passed as the $file argument, then the file will normally be read until EOF, but not closed. If an invoked event handler aborts parsing by calling $p->eof, then $p->parse_file() may not have read the entire file. On systems with multi-byte line terminators, the values passed for the offset and length argspecs may be too low if parse_file() is called on a file handle that is not in binary mode. If a filename is passed in, then parse_file() will open the file in binary mode. =item $p->eof Signals the end of the HTML document. Calling the $p->eof method outside a handler callback will flush any remaining buffered text (which triggers the C event if there is any remaining text). Calling $p->eof inside a handler will terminate parsing at that point and cause $p->parse to return a FALSE value. This also terminates parsing by $p->parse_file(). After $p->eof has been called, the parse() and parse_file() methods can be invoked to feed new documents with the parser object. The return value from eof() is a reference to the parser object. =back Most parser options are controlled by boolean attributes. Each boolean attribute is enabled by calling the corresponding method with a TRUE argument and disabled with a FALSE argument. The attribute value is left unchanged if no argument is given. The return value from each method is the old attribute value. Methods that can be used to get and/or set parser options are: =over =item $p->attr_encoded =item $p->attr_encoded( $bool ) By default, the C and C<@attr> argspecs will have general entities for attribute values decoded. Enabling this attribute leaves entities alone. =item $p->backquote =item $p->backquote( $bool ) By default, only ' and " are recognized as quote characters around attribute values. MSIE also recognizes backquotes for some reason. Enabling this attribute provides compatibility with this behaviour. =item $p->boolean_attribute_value( $val ) This method sets the value reported for boolean attributes inside HTML start tags. By default, the name of the attribute is also used as its value. This affects the values reported for C and C argspecs. =item $p->case_sensitive =item $p->case_sensitive( $bool ) By default, tagnames and attribute names are down-cased. Enabling this attribute leaves them as found in the HTML source document. =item $p->closing_plaintext =item $p->closing_plaintext( $bool ) By default, "plaintext" element can never be closed. Everything up to the end of the document is parsed in CDATA mode. This historical behaviour is what at least MSIE does. Enabling this attribute makes closing "" tag effective and the parsing process will resume after seeing this tag. This emulates early gecko-based browsers. =item $p->empty_element_tags =item $p->empty_element_tags( $bool ) By default, empty element tags are not recognized as such and the "/" before ">" is just treated like a normal name character (unless C is enabled). Enabling this attribute make C recognize these tags. Empty element tags look like start tags, but end with the character sequence "/>" instead of ">". When recognized by C they cause an artificial end event in addition to the start event. The C for the artificial end event will be empty and the C array will be undefined even though the the token array will have one element containing the tag name. =item $p->marked_sections =item $p->marked_sections( $bool ) By default, section markings like are treated like ordinary text. When this attribute is enabled section markings are honoured. There are currently no events associated with the marked section markup, but the text can be returned as C. =item $p->strict_comment =item $p->strict_comment( $bool ) By default, comments are terminated by the first occurrence of "-->". This is the behaviour of most popular browsers (like Mozilla, Opera and MSIE), but it is not correct according to the official HTML standard. Officially, you need an even number of "--" tokens before the closing ">" is recognized and there may not be anything but whitespace between an even and an odd "--". The official behaviour is enabled by enabling this attribute. Enabling of 'strict_comment' also disables recognizing these forms as comments: =item $p->strict_end =item $p->strict_end( $bool ) By default, attributes and other junk are allowed to be present on end tags in a manner that emulates MSIE's behaviour. The official behaviour is enabled with this attribute. If enabled, only whitespace is allowed between the tagname and the final ">". =item $p->strict_names =item $p->strict_names( $bool ) By default, almost anything is allowed in tag and attribute names. This is the behaviour of most popular browsers and allows us to parse some broken tags with invalid attribute values like: [PREV

By default, "LIST]" is parsed as a boolean attribute, not as part of the ALT value as was clearly intended. This is also what Mozilla sees. The official behaviour is enabled by enabling this attribute. If enabled, it will cause the tag above to be reported as text since "LIST]" is not a legal attribute name. =item $p->unbroken_text =item $p->unbroken_text( $bool ) By default, blocks of text are given to the text handler as soon as possible (but the parser takes care always to break text at a boundary between whitespace and non-whitespace so single words and entities can always be decoded safely). This might create breaks that make it hard to do transformations on the text. When this attribute is enabled, blocks of text are always reported in one piece. This will delay the text event until the following (non-text) event has been recognized by the parser. Note that the C argspec will give you the offset of the first segment of text and C is the combined length of the segments. Since there might be ignored tags in between, these numbers can't be used to directly index in the original document file. =item $p->utf8_mode =item $p->utf8_mode( $bool ) Enable this option when parsing raw undecoded UTF-8. This tells the parser that the entities expanded for strings reported by C, C<@attr> and C should be expanded as decoded UTF-8 so they end up compatible with the surrounding text. If C is enabled then it is an error to pass strings containing characters with code above 255 to the parse() method, and the parse() method will croak if you try. Example: The Unicode character "\x{2665}" is "\xE2\x99\xA5" when UTF-8 encoded. The character can also be represented by the entity "♥" or "♥". If we feed the parser: $p->parse("\xE2\x99\xA5♥"); then C will be reported as "\xE2\x99\xA5\x{2665}" without C enabled, but as "\xE2\x99\xA5\xE2\x99\xA5" when enabled. The later string is what you want. This option is only available with perl-5.8 or better. =item $p->xml_mode =item $p->xml_mode( $bool ) Enabling this attribute changes the parser to allow some XML constructs. This enables the behaviour controlled by individually by the C, C, C and C attributes and also suppresses special treatment of elements that are parsed as CDATA for HTML. =item $p->xml_pic =item $p->xml_pic( $bool ) By default, I are terminated by ">". When this attribute is enabled, processing instructions are terminated by "?>" instead. =back As markup and text is recognized, handlers are invoked. The following method is used to set up handlers for different events: =over =item $p->handler( event => \&subroutine, $argspec ) =item $p->handler( event => $method_name, $argspec ) =item $p->handler( event => \@accum, $argspec ) =item $p->handler( event => "" ); =item $p->handler( event => undef ); =item $p->handler( event ); This method assigns a subroutine, method, or array to handle an event. Event is one of C, C, C, C, C, C, C, C or C. The C<\&subroutine> is a reference to a subroutine which is called to handle the event. The C<$method_name> is the name of a method of $p which is called to handle the event. The C<@accum> is an array that will hold the event information as sub-arrays. If the second argument is "", the event is ignored. If it is undef, the default handler is invoked for the event. The C<$argspec> is a string that describes the information to be reported for the event. Any requested information that does not apply to a specific event is passed as C. If argspec is omitted, then it is left unchanged. The return value from $p->handler is the old callback routine or a reference to the accumulator array. Any return values from handler callback routines/methods are always ignored. A handler callback can request parsing to be aborted by invoking the $p->eof method. A handler callback is not allowed to invoke the $p->parse() or $p->parse_file() method. An exception will be raised if it tries. Examples: $p->handler(start => "start", 'self, attr, attrseq, text' ); This causes the "start" method of object $p to be called for 'start' events. The callback signature is $p->start(\%attr, \@attr_seq, $text). $p->handler(start => \&start, 'attr, attrseq, text' ); This causes subroutine start() to be called for 'start' events. The callback signature is start(\%attr, \@attr_seq, $text). $p->handler(start => \@accum, '"S", attr, attrseq, text' ); This causes 'start' event information to be saved in @accum. The array elements will be ['S', \%attr, \@attr_seq, $text]. $p->handler(start => ""); This causes 'start' events to be ignored. It also suppresses invocations of any default handler for start events. It is in most cases equivalent to $p->handler(start => sub {}), but is more efficient. It is different from the empty-sub-handler in that C is not reset by it. $p->handler(start => undef); This causes no handler to be associated with start events. If there is a default handler it will be invoked. =back Filters based on tags can be set up to limit the number of events reported. The main bottleneck during parsing is often the huge number of callbacks made from the parser. Applying filters can improve performance significantly. The following methods control filters: =over =item $p->ignore_elements( @tags ) Both the C event and the C event as well as any events that would be reported in between are suppressed. The ignored elements can contain nested occurrences of itself. Example: $p->ignore_elements(qw(script style)); The C