X-Git-Url: http://matita.cs.unibo.it/gitweb/?a=blobdiff_plain;f=helm%2FDEVEL%2Fpxp%2Fnetstring%2Fnethtml_scanner.mll;fp=helm%2FDEVEL%2Fpxp%2Fnetstring%2Fnethtml_scanner.mll;h=03e6dea0e2cf31f196785c5bfd7e31bb96c4d677;hb=c03d2c1fdab8d228cb88aaba5ca0f556318bebc5;hp=0000000000000000000000000000000000000000;hpb=758057e85325f94cd88583feb1fdf6b038e35055;p=helm.git

diff --git a/helm/DEVEL/pxp/netstring/nethtml_scanner.mll b/helm/DEVEL/pxp/netstring/nethtml_scanner.mll
new file mode 100644
index 000000000..03e6dea0e
--- /dev/null
+++ b/helm/DEVEL/pxp/netstring/nethtml_scanner.mll
@@ -0,0 +1,128 @@
+(* $Id$
+ * ----------------------------------------------------------------------
+ *
+ *)
+
+{
+  type token =
+      Lcomment
+    | Rcomment
+    | Mcomment
+    | Ldoctype
+    | Rdoctype
+    | Mdoctype
+    | Lelement of string
+    | Lelementend of string
+    | Relement
+    | Cdata of string 
+    | Space of int
+    | Name of string
+    | Is
+    | Literal of string
+    | Other
+    | Eof
+}
+
+(* Simplified rules: Only Latin-1 is recognized as character set *)
+
+let letter = ['A'-'Z' 'a'-'z' '\192'-'\214' '\216'-'\246' '\248'-'\255']
+let extender = '\183'
+let digit = ['0'-'9']
+let hexdigit = ['0'-'9' 'A'-'F' 'a'-'f']
+let namechar = letter | digit | '.' | ':' | '-' | '_' | extender
+let name = ( letter | '_' | ':' ) namechar*
+let nmtoken = namechar+
+let ws = [ ' ' '\t' '\r' '\n' ]
+let string_literal1 = '"' [^ '"' '>' '<' '\n']* '"'
+let string_literal2 = "'" [^ '\'' '>' '<' '\n']* "'"
+
+
+(* This following rules reflect HTML as it is used, not the SGML
+ * rules.
+ *)
+
+rule scan_document = parse
+  | "<!--"
+      { Lcomment }
+  | "<!"
+      { Ldoctype }
+  | "<" name
+      { let s = Lexing.lexeme lexbuf in
+	Lelement (String.sub s 1 (String.length s - 1))
+      }
+  | "</" name
+      { let s = Lexing.lexeme lexbuf in
+	Lelementend (String.sub s 2 (String.length s - 2))
+      }
+  | "<"                (* misplaced "<" *)
+      { Cdata "<" }
+  | eof
+      { Eof }
+  | [^ '<' ]+
+      { Cdata (Lexing.lexeme lexbuf)}
+
+and scan_special = parse
+  | "</" name 
+      { let s = Lexing.lexeme lexbuf in
+	Lelementend (String.sub s 2 (String.length s - 2))
+      }
+  | "<"
+      { Cdata "<" }
+  | eof
+      { Eof }
+  | [^ '<' ]+
+      { Cdata (Lexing.lexeme lexbuf)}
+
+
+and scan_comment = parse
+  | "-->"
+      { Rcomment }
+  | "-"
+      { Mcomment }
+  | eof
+      { Eof }
+  | [^ '-']+
+      { Mcomment }
+
+and scan_doctype = parse
+  | ">"                   (* Occurence in strings, and [ ] brackets ignored *)
+      { Rdoctype }
+  | eof
+      { Eof }
+  | [^ '>' ] +
+      { Mdoctype }
+
+and scan_element = parse
+  | ">"
+      { Relement }
+  | ws+
+      { Space (String.length (Lexing.lexeme lexbuf)) }
+  | name
+      { Name (Lexing.lexeme lexbuf) }
+  | "="
+      { Is }
+  | string_literal1
+      { let s = Lexing.lexeme lexbuf in
+	Literal (String.sub s 1 (String.length s - 2)) 
+      }
+  | string_literal2
+      { let s = Lexing.lexeme lexbuf in
+	Literal (String.sub s 1 (String.length s - 2)) 
+      }
+  | eof
+      { Eof }
+  | _
+      { Other }
+
+(* ======================================================================
+ * History:
+ * 
+ * $Log$
+ * Revision 1.1  2000/11/17 09:57:28  lpadovan
+ * Initial revision
+ *
+ * Revision 1.1  2000/03/03 01:07:25  gerd
+ * 	Initial revision.
+ *
+ * 
+ *)