core
/
oga
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Cleaned up the XML lexer documentation.

This commit is contained in:
Yorick Peterse 2014-05-19 09:39:35 +02:00
parent cd0f3380c4
commit 93b9718406
1 changed files with 21 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
ext/ragel/base_lexer.rl
View File

@ -33,6 +33,12 @@
identifier = [a-zA-Z0-9\-_]+; identifier = [a-zA-Z0-9\-_]+;
attribute = [a-zA-Z0-9\-_:]+; attribute = [a-zA-Z0-9\-_:]+;
cdata_start = '<![CDATA[';
cdata_end = ']]>';
comment_start = '<!--';
comment_end = '-->';
# Strings # Strings
# #
# Strings in HTML can either be single or double quoted. If a string # Strings in HTML can either be single or double quoted. If a string
@ -107,33 +113,6 @@
}; };
*|; *|;
# CDATA
#
# http://www.w3.org/TR/html-markup/syntax.html#cdata-sections
#
# CDATA tags are broken up into 3 parts: the start, the content and the
# end tag.
#
# In HTML CDATA tags have no meaning/are not supported. Oga does
# support them but treats their contents as plain text.
#
cdata_start = '<![CDATA[';
cdata_end = ']]>';
# Comments
#
# http://www.w3.org/TR/html-markup/syntax.html#comments
#
# Comments are lexed into 3 parts: the start tag, the content and the
# end tag.
#
# Unlike the W3 specification these rules *do* allow character
# sequences such as `--` and `->`. Putting extra checks in for these
# sequences would actually make the rules/actions more complex.
#
comment_start = '<!--';
comment_end = '-->';
# XML declaration tags # XML declaration tags
# #
# http://www.w3.org/TR/REC-xml/#sec-prolog-dtd # http://www.w3.org/TR/REC-xml/#sec-prolog-dtd
@ -226,13 +205,27 @@
main := |* main := |*
'<' => start_element; '<' => start_element;
doctype_start => start_doctype; doctype_start => start_doctype;
cdata_start => start_cdata;
xml_decl_start => start_xml_decl; xml_decl_start => start_xml_decl;
# Comments
#
# http://www.w3.org/TR/html-markup/syntax.html#comments
#
# Unlike the W3 specification these rules *do* allow character
# sequences such as `--` and `->`. Putting extra checks in for these
# sequences would actually make the rules/actions more complex.
#
comment_start any* comment_end => { comment_start any* comment_end => {
callback("on_comment", data, encoding, ts + 4, te - 3); callback("on_comment", data, encoding, ts + 4, te - 3);
}; };
# CDATA
#
# http://www.w3.org/TR/html-markup/syntax.html#cdata-sections
#
# In HTML CDATA tags have no meaning/are not supported. Oga does
# support them but treats their contents as plain text.
#
cdata_start any* cdata_end => { cdata_start any* cdata_end => {
callback("on_cdata", data, encoding, ts + 9, te - 3); callback("on_cdata", data, encoding, ts + 9, te - 3);
}; };