Parent Directory
|
Revision Log
|
Patch
| revision 1.2 by wakaba, Tue May 1 10:47:37 2007 UTC | revision 1.215 by wakaba, Thu Jul 2 22:11:51 2009 UTC | |
|---|---|---|
| # | Line 1 | Line 1 |
| 1 | package Whatpm::HTML; | package Whatpm::HTML; |
| 2 | use strict; | use strict; |
| 3 | our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; | our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
| 4 | use Error qw(:try); | |
| 5 | ||
| 6 | ## This is an early version of an HTML parser. | use Whatpm::HTML::Tokenizer; |
| 7 | ||
| 8 | my $permitted_slash_tag_name = { | ## NOTE: This module don't check all HTML5 parse errors; character |
| 9 | base => 1, | ## encoding related parse errors are expected to be handled by relevant |
| 10 | link => 1, | ## modules. |
| 11 | meta => 1, | ## Parse errors for control characters that are not allowed in HTML5 |
| 12 | hr => 1, | ## documents, for surrogate code points, and for noncharacter code |
| 13 | br => 1, | ## points, as well as U+FFFD substitions for characters whose code points |
| 14 | img=> 1, | ## is higher than U+10FFFF may be detected by combining the parser with |
| 15 | embed => 1, | ## the checker implemented by Whatpm::Charset::UnicodeChecker (for its |
| 16 | param => 1, | ## usage example, see |t/HTML-tree.t| in the Whatpm package or the |
| 17 | area => 1, | ## WebHACC::Language::HTML module in the WebHACC package). |
| 18 | col => 1, | |
| 19 | input => 1, | ## ISSUE: |
| 20 | ## var doc = implementation.createDocument (null, null, null); | |
| 21 | ## doc.write (''); | |
| 22 | ## alert (doc.compatMode); | |
| 23 | ||
| 24 | require IO::Handle; | |
| 25 | ||
| 26 | ## Namespace URLs | |
| 27 | ||
| 28 | my $HTML_NS = q<http://www.w3.org/1999/xhtml>; | |
| 29 | my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; | |
| 30 | my $SVG_NS = q<http://www.w3.org/2000/svg>; | |
| 31 | my $XLINK_NS = q<http://www.w3.org/1999/xlink>; | |
| 32 | my $XML_NS = q<http://www.w3.org/XML/1998/namespace>; | |
| 33 | my $XMLNS_NS = q<http://www.w3.org/2000/xmlns/>; | |
| 34 | ||
| 35 | ## Element categories | |
| 36 | ||
| 37 | ## Bits 12-15 | |
| 38 | sub SPECIAL_EL () { 0b1_000000000000000 } | |
| 39 | sub SCOPING_EL () { 0b1_00000000000000 } | |
| 40 | sub FORMATTING_EL () { 0b1_0000000000000 } | |
| 41 | sub PHRASING_EL () { 0b1_000000000000 } | |
| 42 | ||
| 43 | ## Bits 10-11 | |
| 44 | #sub FOREIGN_EL () { 0b1_00000000000 } # see Whatpm::HTML::Tokenizer | |
| 45 | sub FOREIGN_FLOW_CONTENT_EL () { 0b1_0000000000 } | |
| 46 | ||
| 47 | ## Bits 6-9 | |
| 48 | sub TABLE_SCOPING_EL () { 0b1_000000000 } | |
| 49 | sub TABLE_ROWS_SCOPING_EL () { 0b1_00000000 } | |
| 50 | sub TABLE_ROW_SCOPING_EL () { 0b1_0000000 } | |
| 51 | sub TABLE_ROWS_EL () { 0b1_000000 } | |
| 52 | ||
| 53 | ## Bit 5 | |
| 54 | sub ADDRESS_DIV_P_EL () { 0b1_00000 } | |
| 55 | ||
| 56 | ## NOTE: Used in </body> and EOF algorithms. | |
| 57 | ## Bit 4 | |
| 58 | sub ALL_END_TAG_OPTIONAL_EL () { 0b1_0000 } | |
| 59 | ||
| 60 | ## NOTE: Used in "generate implied end tags" algorithm. | |
| 61 | ## NOTE: There is a code where a modified version of | |
| 62 | ## END_TAG_OPTIONAL_EL is used in "generate implied end tags" | |
| 63 | ## implementation (search for the algorithm name). | |
| 64 | ## Bit 3 | |
| 65 | sub END_TAG_OPTIONAL_EL () { 0b1_000 } | |
| 66 | ||
| 67 | ## Bits 0-2 | |
| 68 | ||
| 69 | sub MISC_SPECIAL_EL () { SPECIAL_EL | 0b000 } | |
| 70 | sub FORM_EL () { SPECIAL_EL | 0b001 } | |
| 71 | sub FRAMESET_EL () { SPECIAL_EL | 0b010 } | |
| 72 | sub HEADING_EL () { SPECIAL_EL | 0b011 } | |
| 73 | sub SELECT_EL () { SPECIAL_EL | 0b100 } | |
| 74 | sub SCRIPT_EL () { SPECIAL_EL | 0b101 } | |
| 75 | ||
| 76 | sub ADDRESS_DIV_EL () { SPECIAL_EL | ADDRESS_DIV_P_EL | 0b001 } | |
| 77 | sub BODY_EL () { SPECIAL_EL | ALL_END_TAG_OPTIONAL_EL | 0b001 } | |
| 78 | ||
| 79 | sub DTDD_EL () { | |
| 80 | SPECIAL_EL | | |
| 81 | END_TAG_OPTIONAL_EL | | |
| 82 | ALL_END_TAG_OPTIONAL_EL | | |
| 83 | 0b010 | |
| 84 | } | |
| 85 | sub LI_EL () { | |
| 86 | SPECIAL_EL | | |
| 87 | END_TAG_OPTIONAL_EL | | |
| 88 | ALL_END_TAG_OPTIONAL_EL | | |
| 89 | 0b100 | |
| 90 | } | |
| 91 | sub P_EL () { | |
| 92 | SPECIAL_EL | | |
| 93 | ADDRESS_DIV_P_EL | | |
| 94 | END_TAG_OPTIONAL_EL | | |
| 95 | ALL_END_TAG_OPTIONAL_EL | | |
| 96 | 0b001 | |
| 97 | } | |
| 98 | ||
| 99 | sub TABLE_ROW_EL () { | |
| 100 | SPECIAL_EL | | |
| 101 | TABLE_ROWS_EL | | |
| 102 | TABLE_ROW_SCOPING_EL | | |
| 103 | ALL_END_TAG_OPTIONAL_EL | | |
| 104 | 0b001 | |
| 105 | } | |
| 106 | sub TABLE_ROW_GROUP_EL () { | |
| 107 | SPECIAL_EL | | |
| 108 | TABLE_ROWS_EL | | |
| 109 | TABLE_ROWS_SCOPING_EL | | |
| 110 | ALL_END_TAG_OPTIONAL_EL | | |
| 111 | 0b001 | |
| 112 | } | |
| 113 | ||
| 114 | sub MISC_SCOPING_EL () { SCOPING_EL | 0b000 } | |
| 115 | sub BUTTON_EL () { SCOPING_EL | 0b001 } | |
| 116 | sub CAPTION_EL () { SCOPING_EL | 0b010 } | |
| 117 | sub HTML_EL () { | |
| 118 | SCOPING_EL | | |
| 119 | TABLE_SCOPING_EL | | |
| 120 | TABLE_ROWS_SCOPING_EL | | |
| 121 | TABLE_ROW_SCOPING_EL | | |
| 122 | ALL_END_TAG_OPTIONAL_EL | | |
| 123 | 0b001 | |
| 124 | } | |
| 125 | sub TABLE_EL () { | |
| 126 | SCOPING_EL | | |
| 127 | TABLE_ROWS_EL | | |
| 128 | TABLE_SCOPING_EL | | |
| 129 | 0b001 | |
| 130 | } | |
| 131 | sub TABLE_CELL_EL () { | |
| 132 | SCOPING_EL | | |
| 133 | TABLE_ROW_SCOPING_EL | | |
| 134 | ALL_END_TAG_OPTIONAL_EL | | |
| 135 | 0b001 | |
| 136 | } | |
| 137 | ||
| 138 | sub MISC_FORMATTING_EL () { FORMATTING_EL | 0b000 } | |
| 139 | sub A_EL () { FORMATTING_EL | 0b001 } | |
| 140 | sub NOBR_EL () { FORMATTING_EL | 0b010 } | |
| 141 | ||
| 142 | sub RUBY_EL () { PHRASING_EL | 0b001 } | |
| 143 | ||
| 144 | ## ISSUE: ALL_END_TAG_OPTIONAL_EL? | |
| 145 | sub OPTGROUP_EL () { PHRASING_EL | END_TAG_OPTIONAL_EL | 0b001 } | |
| 146 | sub OPTION_EL () { PHRASING_EL | END_TAG_OPTIONAL_EL | 0b010 } | |
| 147 | sub RUBY_COMPONENT_EL () { PHRASING_EL | END_TAG_OPTIONAL_EL | 0b100 } | |
| 148 | ||
| 149 | sub MML_AXML_EL () { PHRASING_EL | FOREIGN_EL | 0b001 } | |
| 150 | ||
| 151 | my $el_category = { | |
| 152 | a => A_EL, | |
| 153 | address => ADDRESS_DIV_EL, | |
| 154 | applet => MISC_SCOPING_EL, | |
| 155 | area => MISC_SPECIAL_EL, | |
| 156 | article => MISC_SPECIAL_EL, | |
| 157 | aside => MISC_SPECIAL_EL, | |
| 158 | b => FORMATTING_EL, | |
| 159 | base => MISC_SPECIAL_EL, | |
| 160 | basefont => MISC_SPECIAL_EL, | |
| 161 | bgsound => MISC_SPECIAL_EL, | |
| 162 |