/usr/share/ada/adainclude/opentoken/html_lexer.adb is in libopentoken5-dev 6.0b-4.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 | -------------------------------------------------------------------------------
--
-- Copyright (C) 2009, 2010 Stephen Leake
-- Copyright (C) 1999, 2000 Christoph Karl Walter Grein
--
-- This file is part of the OpenToken package.
--
-- The OpenToken package is free software; you can redistribute it and/or
-- modify it under the terms of the GNU General Public License as published
-- by the Free Software Foundation; either version 3, or (at your option)
-- any later version. The OpenToken package is distributed in the hope that
-- it will be useful, but WITHOUT ANY WARRANTY; without even the implied
-- warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-- GNU General Public License for more details. You should have received
-- a copy of the GNU General Public License distributed with the OpenToken
-- package; see file GPL.txt. If not, write to the Free Software Foundation,
-- 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
--
-- As a special exception, if other files instantiate generics from
-- this unit, or you link this unit with other files to produce an
-- executable, this unit does not by itself cause the resulting
-- executable to be covered by the GNU General Public License. This
-- exception does not however invalidate any other reasons why the
-- executable file might be covered by the GNU Public License.
-------------------------------------------------------------------------------
with Ada.Characters.Latin_1;
with Ada.Strings.Maps.Constants;
with OpenToken.Recognizer.Bracketed_Comment;
with OpenToken.Recognizer.Character_Set;
with OpenToken.Recognizer.End_Of_File;
with OpenToken.Recognizer.HTML_Entity;
with OpenToken.Recognizer.Keyword;
with OpenToken.Recognizer.Nothing;
with OpenToken.Recognizer.Separator;
with OpenToken.Recognizer.String;
package body HTML_Lexer is
function Name (Token : HTML_Token) return Token_Name is
begin
return Token.Name;
end Name;
function Lexeme (Token : HTML_Token) return Standard.String is
begin
return Ada.Strings.Unbounded.To_String (Token.Lexeme);
end Lexeme;
function Line (Token : in HTML_Token) return Natural
is begin
return Token.Line;
end Line;
function Column (Token : in HTML_Token) return Natural
is begin
return Token.Column;
end Column;
use type Ada.Strings.Maps.Character_Set;
HTML_Whitespace : constant Ada.Strings.Maps.Character_Set := Ada.Strings.Maps.To_Set
(Ada.Characters.Latin_1.HT &
Ada.Characters.Latin_1.CR &
Ada.Characters.Latin_1.LF &
Ada.Characters.Latin_1.Space);
function Text_Syntax return Tokenizer.Syntax
is begin
return
(Document_Type => Tokenizer.Get
(OpenToken.Recognizer.Bracketed_Comment.Get
(Comment_Opener => "<!",
Comment_Closer => ">",
Reportable => True)),
Start_Tag_Opener => Tokenizer.Get (OpenToken.Recognizer.Separator.Get ("<")),
End_Tag_Opener => Tokenizer.Get (OpenToken.Recognizer.Separator.Get ("</")),
Text => Tokenizer.Get
(OpenToken.Recognizer.Character_Set.Get
(Ada.Strings.Maps.Constants.Graphic_Set - Ada.Strings.Maps.To_Set ("<&"),
Reportable => True)),
Entity => Tokenizer.Get (OpenToken.Recognizer.HTML_Entity.Get),
-- See HTML definition section 3.2.4 Comments; HTML syntax
-- actually allows whitespace in the comment closer: "-- >"
-- is a closer. That also means that "<! foo -- bar>" is
-- invalid syntax. But we don't have a recognizer that can
-- deal with that, and this is good enough for common usage.
Comment => Tokenizer.Get
(OpenToken.Recognizer.Bracketed_Comment.Get
(Comment_Opener => "<!--",
Comment_Closer => "-->",
Reportable => True)),
Whitespace => Tokenizer.Get (OpenToken.Recognizer.Character_Set.Get (HTML_Whitespace)),
Bad_Token => Tokenizer.Get (OpenToken.Recognizer.Nothing.Get),
End_Of_File => Tokenizer.Get (OpenToken.Recognizer.End_Of_File.Get),
Pre => Tokenizer.Get
(OpenToken.Recognizer.Bracketed_Comment.Get
(Comment_Opener => "<pre>",
Comment_Closer => "</pre>",
Reportable => True)),
others => Tokenizer.Get (OpenToken.Recognizer.Nothing.Get));
end Text_Syntax;
function Tag_Syntax return Tokenizer.Syntax
is begin
return
(Tag_Closer => Tokenizer.Get (OpenToken.Recognizer.Separator.Get (">")),
HTML => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("HTML")),
Head => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("Head")),
Meta => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("Meta")),
HTML_Body => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("Body")),
Heading_1 => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("H1")),
Anchor => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("A")),
Image => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("IMG")),
Content => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("CONTENT")),
Hyper_Reference => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("HREF")),
Link_Type => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("TYPE")),
Name => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("NAME")),
Source => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("SRC")),
Title => Tokenizer.Get (OpenToken.Recognizer.Keyword.Get ("TITLE")),
Assignment => Tokenizer.Get (OpenToken.Recognizer.Separator.Get ("=")),
Value => Tokenizer.Get
(OpenToken.Recognizer.Character_Set.Get
(Ada.Strings.Maps.Constants.Letter_Set or
Ada.Strings.Maps.Constants.Decimal_Digit_Set or
Ada.Strings.Maps.To_Set (".-_/:#?',*%"), -- unquoted URIs, framesets
Reportable => True)),
String => Tokenizer.Get (OpenToken.Recognizer.String.Get (Double_Delimiter => False)),
Whitespace => Tokenizer.Get (OpenToken.Recognizer.Character_Set.Get (HTML_Whitespace)),
Bad_Token => Tokenizer.Get (OpenToken.Recognizer.Nothing.Get),
End_Of_File => Tokenizer.Get (OpenToken.Recognizer.End_Of_File.Get),
others => Tokenizer.Get (OpenToken.Recognizer.Nothing.Get));
end Tag_Syntax;
end HTML_Lexer;
|