core
/
oga
6
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Cleaned up lexer rules a bit. 

There's no benefit to adding variables for angle brackets and such, it's much
easier to grok to just use them directly.
This commit is contained in:
Yorick Peterse 2014-02-28 20:09:13 +01:00
parent 2294bf19f4
commit 3c825afee0
1 changed files with 16 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
lib/oga/lexer.rl
View File

@ -77,29 +77,9 @@ module Oga
# Use instance variables for `ts` and friends. # Use instance variables for `ts` and friends.
access @; access @;
newline = '\n'; newline = '\n' | '\r\n';
whitespace = [ \t]; whitespace = [ \t];
any_escaped = /\\./;
smaller = '<';
greater = '>';
slash = '/';
bang = '!';
equals = '=';
colon = ':';
dash = '-';
lbracket = '[';
rbracket = ']';
s_quote = "'";
d_quote = '"';
# FIXME: there really should be a better way of doing this.
text = (any - s_quote - d_quote - equals - bang - slash -
greater - smaller - whitespace - newline - colon - dash -
lbracket - rbracket)+;
# DOCTYPES # DOCTYPES
# #
# http://www.w3.org/TR/html-markup/syntax.html#doctype-syntax # http://www.w3.org/TR/html-markup/syntax.html#doctype-syntax
@ -114,8 +94,8 @@ module Oga
# different rules. Because Oga doesn't really use the doctype for # different rules. Because Oga doesn't really use the doctype for
# anything we'll just slap all the formats into a single rule. Easy # anything we'll just slap all the formats into a single rule. Easy
# enough. # enough.
doctype = smaller whitespace* bang whitespace* 'DOCTYPE'i whitespace* doctype = '<' whitespace* '!' whitespace* 'DOCTYPE'i whitespace*
'HTML'i whitespace* any* greater; 'HTML'i whitespace* any* '>';
# CDATA # CDATA
# #
@ -127,8 +107,8 @@ module Oga
# In HTML CDATA tags have no meaning/are not supported. Oga does # In HTML CDATA tags have no meaning/are not supported. Oga does
# support them but treats their contents as plain text. # support them but treats their contents as plain text.
# #
cdata_start = smaller bang lbracket 'CDATA' lbracket; cdata_start = '<![CDATA[';
cdata_end = rbracket rbracket greater; cdata_end = ']]>';
cdata := |* cdata := |*
cdata_start => { cdata_start => {
@ -161,18 +141,17 @@ module Oga
cdata_start >{ fhold; fgoto cdata; }; cdata_start >{ fhold; fgoto cdata; };
# General rules and actions. # General rules and actions.
smaller => { t(:T_SMALLER) }; '<' => { t(:T_SMALLER) };
greater => { t(:T_GREATER) }; '>' => { t(:T_GREATER) };
slash => { t(:T_SLASH) }; '/' => { t(:T_SLASH) };
d_quote => { t(:T_DQUOTE) }; '"' => { t(:T_DQUOTE) };
s_quote => { t(:T_SQUOTE) }; "'" => { t(:T_SQUOTE) };
dash => { t(:T_DASH) }; '-' => { t(:T_DASH) };
rbracket => { t(:T_RBRACKET) }; ']' => { t(:T_RBRACKET) };
lbracket => { t(:T_LBRACKET) }; '[' => { t(:T_LBRACKET) };
colon => { t(:T_COLON) }; ':' => { t(:T_COLON) };
bang => { t(:T_BANG) }; '!' => { t(:T_BANG) };
equals => { t(:T_EQUALS) }; '=' => { t(:T_EQUALS) };
text => { t(:T_TEXT) };
*|; *|;
}%% }%%
end # Lexer end # Lexer