#
#  Bounded stack language for HTML
#
BSL type recursive trans-line

typefaces
r----	HTML-Text-Roman
i----	HTML-Text-Italic
rb---	HTML-Text-Bold
lb---	HTML-Text-Heading
t----	HTML-Text-Typewriter
r-uB-	HTML-Text-HREF
#
t--B-	HTML-Comment
t--R-	HTML-Element
t----	HTML-Element-Attr
t--B-	HTML-Entity
#
t--G-	HTML-String
t--R-	HTML-String-Escape
#
t----	HTML-Script-Plain
tb---	HTML-Script-Keyword
tb-l-	HTML-Script-Variable
t--G-	HTML-Script-Number

state set
R	HTML-Text-Roman
I	HTML-Text-Italic
B	HTML-Text-Bold
H	HTML-Text-Heading
T	HTML-Text-Typewriter
A	HTML-Text-HREF
#
D	HTML-Element-Attr
C	HTML-Comment
S	HTML-String
#
j	HTML-Script-Plain
s	HTML-String
h	HTML-String
c	HTML-Comment
d	HTML-Comment

demo string <em>Click <a href="here.html">here</a></em>

word range a-zA-Z0-9_

rules
#
########################################################################
#
#  PART 1 - Regular HTML
#
#  Scan  sequences of non-special characters first (for speed).
#
RIBHTA	[^<>"&]+	nop
RIBHTA	\{HTML-Entity}\&[#0-9a-zA-Z]+;	nop
#
#  Commands
#
RIBHTA	\{HTML-Element}<I>:<i>:<IT>:<it>:<EM>:<em>	push I
RIBHTA	\{HTML-Element}<B>:<b>	push B
RIBHTA	\{HTML-Element}<[hH][0-9]>:<TITLE>:<title>	push H
RIBHTA	\{HTML-Element}<TT>:<tt>:<PRE>:<pre>:<CODE>:<code>	push T
RIBHTA	\{HTML-Element}<[aA]\{HTML-Element-Attr}[ ]*[hH][rR][eE][fF]\>	push A, push D
RIBHTA	\{HTML-Element}</i>:</it>:</em>:</b>:</h[0-9]>:</title>:</tt>:</pre>:</code>:</a>	pop
RIBHTA	\{HTML-Element}</I>:</IT>:</EM>:</B>:</H[0-9]>:</TITLE>:</TT>:</PRE>:</CODE>:</A>	pop
RIBHTAC	\{HTML-Element}<SCRIPT\>:<script\>:<STYLE\>:<style\>	push j, push D
RIBHTACDjsh	\{HTML-Element}<\?	push j
RIBHTA	\{HTML-Element}<[ \t]*[/!?]?[a-zA-Z0-9]*	push D
#
#  Command trailers
#
D	\{HTML-Element}--	goto C
D	\{HTML-Element}>	pop
D	[a-zA-Z]+	nop
D	"\{HTML-String}	push S
#
#  Strings inside elements
#
S	[^"<]+	nop
S	\{HTML-Element}<\?	push j
S	\{HTML-Element-Attr}"	pop
#
#  Comments
#
C	\{HTML-Element}--	goto D
#
########################################################################
#
#  PART 2 - Scripts and PHP (try to cover this in one system)
#
j	\{HTML-Element}\?>:</SCRIPT>:</script>:</STYLE>:</style>	pop
#
#  Standard C control keywords
#
j	\{HTML-Script-Keyword}\<break\>:\<case\>:\<continue\>:\<default\>:\<do\>:\<else\>:\<for\>:\<if\>:\<return\>:\<static\>:\<switch\>:\<while\>	nop
#
#  Object oriented and ecma/php specific keywords
#
j	\{HTML-Script-Keyword}\<function\>:\<class\>:\<extends\>:\<new\>:\<global\>:\<var\>	nop
j	\{HTML-Script-Keyword}\<include\>:\<require\>:\<require_once\>	nop
j	\{HTML-Script-Keyword}\<foreach\>:\<in\>:\<as\>	nop
#
#  Strings, numbers and comments
#
j	"	push s
j	'	push h
j	\{HTML-Script-Number}0[xX][0-9a-fA-F]+:-0[xX][0-9a-fA-F]+:[\-0-9]*.[0-9]+[eE][0-9]+:[\-0-9]+.[0-9]*[eE][0-9]+:[\-0-9]+.[0-9]*:[\-0-9]*.[0-9]+:[0-9]+:-[0-9]+	nop
js	\{HTML-Script-Plain}\$\{HTML-Script-Variable}[a-zA-Z0-9_]+	nop
js	\{HTML-Script-Plain}\${\{HTML-Script-Variable}[a-zA-Z0-9_]+\{HTML-Script-Plain}}	nop
js	\{HTML-Script-Plain}{\$\{HTML-Script-Variable}[\-a-zA-Z0-9_$>'\[\]]+\{HTML-Script-Plain}}	nop
j	\{HTML-Comment}/\*	push c
j	\{HTML-Comment}//	push d
#
#  Inside comments
#
cd	[^/*?]+	nop
c	\*/	pop
d	\?>	pop
d	$	pop
#
#  Inside strings
#
sh	[^"'\\${]+	nop
s	\{HTML-Script-Plain}"	pop
h	\{HTML-Script-Plain}'	pop
sh	\{HTML-String-Escape}\\[0-9][0-9][0-9]:\\x[0-9A-Fa-f][0-9A-Fa-f]:\\a:\\b:\\e:\\f:\\n:\\r:\\t:\\v:\\0	nop
sh	\{HTML-String-Escape}\\\{HTML-String}?	nop
#sh	$	pop