Hi Alex,
> So please take your time, and send it to me when ready.
here is the XML parser:
# expects well formed XML
# encoding by picolisp (utf8 "only", no utf16 etc.)
# trim whitespace except in cdata
# ignore <? <!-- <!DOCTYPE
# non-builtin entities as normal text: &ent; => ent
(de _xml (In Char)
(unless Char
(skip)
(unless (= "<" (char))
(quit "Bad XML") ) )
(case (peek)
("?"
(from "?>")
(unless In (_xml2 In)))
("!"
(char)
(case (peek)
("-"
(ifn (= '`(chop "--") (list (char) (char)))
(quit "XML comment expected")
(from "-->")
(unless In (_xml2 In))))
("D"
(ifn (= '`(chop "DOCTYPE")
(list (char) (char) (char) (char) (char) (char) (char)))
(quit "XML DOCTYPE expected")
(when (= "[" (from "[" ">"))
(use X
(loop
(T (= "]" (setq X (from "]" "\"" "'" "<!--"))))
(case X
("\"" (from "\""))
("'" (from "'"))
("<!--" (from "-->")))))
(from ">"))
(unless In (_xml2 In))))
("["
(ifn (= '`(chop "[CDATA[")
(list (char) (char) (char) (char) (char) (char) (char)))
(quit "XML CDATA expected")
(prog1 # ??? echo to string?
(pipe (echo "]]>") (till NIL T))
(from "]]>"))))
(T (quit "Unhandled XML tag"))))
(T
(let Tok (till " ^I^M^J/>" T)
(use X
(make
(link (intern (pack Tok)))
(let L
(make
(loop
(NIL (skip) (quit "Unexpected end of XML" Tok))
(T (member @ '("/" ">")))
(NIL (setq X (intern (pack (trim (till "="))))))
(char)
(skip)
(let C (char)
(unless (member C '("\"" "'"))
(quit "XML attribute quote expected" X) )
(link (cons X (pack (xmlEsc (till C))))))
(char) ) )
(if (= "/" (char))
(prog (char) (and L (link L)))
(link L)
(loop
(NIL (skip) (quit "Unexpected end of XML" Tok))
(T (and (= "<" (setq X (char))) (= "/" (peek)))
(char)
(unless (= Tok (till " ^I^M^J/>" T))
(quit "Unbalanced XML" Tok) )
(skip)
(char) )
(if (= "<" X)
(when (_xml2 T "<")
(link @))
(link
(pack (xmlEsc (trim (cons X (till
"^M^J<"))))))))))))))))
_xml should be called from xml function as (_xml), like the previous
_xml2 code.
I found a few XML files where the above code fails but this is due to:
1) utf-8 byte order mark is not understood. The UTF-8 representation
of the BOM is the byte sequence EF BB BF. I am not sure how others
handle this but it should not be part of the parser probably.
2) some "unusual" utf-8 characters. Not sure why I get these
failures. However, this is quite minor problem and might be a bug
in picolisp utf-8 fandling code?
Example file:
00000000: 3c64 6f63 3ef0 9080 80f4 8fbf bd3c 2f64 <doc>........</d
00000010: 6f63 3e oc>
Any ideas?
Also, I think that a better way of checking whether a file is an XML
file is:
(de xml! (F)
(call "sh" "-c" (pack "xmlstarlet val -w -q " F " 1>/dev/null 2>/dev/null")))
or something like that, using a specialized validation program.
Another check might be encoding check like:
(in (list "enca" "-L" "none" F)
(not (from "UCS-2" "Unrecognized" "non-text")))
I hope people will find this useful.
Thanks,
Tomas
--
UNSUBSCRIBE: mailto:[EMAIL PROTECTED]
