[r2005-03-08 15:27:12 by afrisch] utf-8 BOM

Original author: afrisch
Date: 2005-03-08 15:27:12+00:00

runtime/cduce_pxp.ml

@@ -18,6 +18,21 @@ let pxp_config =
       drop_ignorable_whitespace = true
   }
 
+let utf8_bom = "\239\187\191"
+
+let of_string s =
+  let enc,s =
+    if (String.length s >= 3) && (String.sub s 0 3 = utf8_bom)
+    then Some `Enc_utf8, (String.sub s 3 (String.length s - 3))
+    else None,s in
+  enc, new Netchannels.input_string s
+
+let of_file fn =
+  let ic = open_in_bin fn in
+  let buf = String.create 3 in
+  really_input ic buf 0 3;
+  let e = if buf = utf8_bom then Some `Enc_utf8 else (seek_in ic 0; None) in
+  e, new Netchannels.input_channel ic
 
 let channel_of_id rid =
   let url =
@@ -26,31 +41,25 @@ let channel_of_id rid =
       | _, Some rel -> rel
       | _ -> raise Not_competent
   in
-  let ch = 
+  let enc,ch = 
     if Url.is_url url 
-    then new Netchannels.input_string (!Url.load_url url)
-    else new Netchannels.input_channel (open_in_bin url) 
+    then of_string (!Url.load_url url)
+    else of_file url
   in
-  ch, None, Some { rid with rid_system = Some url }
+  ch, enc, Some { rid with rid_system = Some url }
 
 let alt = new resolve_to_any_obj_channel ~channel_of_id ()
 
+let src_of_uri uri = XExtID (System uri,None,alt)
+
 let load_pxp uri =
   try
-    let src =  XExtID (System uri,None,alt) in
-    let mgr = create_entity_manager pxp_config src in
+    let mgr = create_entity_manager pxp_config (src_of_uri uri) in
     process_entity pxp_config 
       (`Entry_document[`Extend_dtd_fully]) mgr pxp_handle_event;
   with exn ->
     raise (Location.Generic (Pxp_types.string_of_exn exn))
 
-(*
-let channel_or_url id url =
-  let data = !Url.load_url (Neturl.string_of_url url) in
-  let ch = new Netchannels.input_string data in
-  (data, None, None)
-*)
-
 let use () = Load_xml.xml_parser := load_pxp
 
 let () = 
@@ -59,3 +68,4 @@ let () =
     "PXP XML parser"
     use
 
+let () = Schema_xml.src_of_uri := src_of_uri

schema/schema_xml.ml

@@ -4,6 +4,8 @@ open Schema_pcre
 exception Error of string
 let error s = raise (Error s)
 
+let src_of_uri = ref (fun _ -> failwith "PXP support required to load XML Schema")
+
 type node =
   ('a Pxp_document.node Pxp_document.extension as 'a) Pxp_document.node
 
@@ -41,27 +43,8 @@ let new_xsd_config () =
 let node_of src =
   (Pxp_tree_parser.parse_wfdocument_entity (new_xsd_config ()) src spec) # root
 
-open Pxp_types
-open Pxp_reader
-
-let channel_of_id rid =
-  let url =
-    match rid.rid_system_base, rid.rid_system with
-      | Some base, Some rel -> Url.local base rel
-      | _, Some rel -> rel
-      | _ -> raise Not_competent
-  in
-  let ch = 
-    if Url.is_url url 
-    then new Netchannels.input_string (!Url.load_url url)
-    else new Netchannels.input_channel (open_in_bin url) 
-  in
-  ch, None, Some { rid with rid_system = Some url }
-
-let alt = new resolve_to_any_obj_channel ~channel_of_id ()
-
 let node_of_uri uri =
-  try node_of (XExtID (System uri,None,alt))
+  try node_of (!src_of_uri uri)
   with exn -> raise (Location.Generic (Pxp_types.string_of_exn exn))
 
 let _may_attr name n =

schema/schema_xml.mli

@@ -4,6 +4,8 @@ exception Error of string
 module Node: Set.OrderedType
 type node = Node.t
 
+val src_of_uri: (string -> Pxp_types.source) ref
+
 val node_of_uri: string -> node
 
 val _may_attr: string -> node -> Utf8.t option

web/manual/expressions.xml

@@ -731,16 +731,27 @@ of type <code>%%T%%</code>.  The reference is actually a value of type
 </p>
 
 <p>
-Three syntactic sugar constructions are provided to facilitate
+Two syntactic sugar constructions are provided to facilitate
 the use of references:
 </p>
 
 <sample>
 !%%e%%        ===  %%e%%.get []           {{ Dereferencing }}
 %%e1%% := %%e2%%  ===  %%e1%%.set %%e2%%          {{ Assignment }}
+</sample>
+
+<p>
+An expression of type <code>[]</code> is often considered
+as a command and followed by another expression. The sequencing
+operator gives a syntax for that:
+</p>
+
+<sample>
 %%e1%% ; %%e2%%   ===  let [] = %%e1%% in %%e2%%   {{Sequencing}}
 </sample>
 
+
+
 </box>
 
 
@@ -756,11 +767,11 @@ select %%e%% from
    %%p2%% in %%e2%%,
        :
    %%pn%% in %%en%%
-where %%b%%
+where %%c1%% and ... and %%cn%%
 ]]></sample>
 <p>
-where <code>%%e%%</code> is an expression <code>%%b%%</code> a boolean
-expression, the <code>%%pi%%</code>'s are patterns, and the
+where <code>%%e%%</code> is an expression, the <code>%%ci%%</code>
+are boolean expressions, the <code>%%pi%%</code>'s are patterns, and the
 <code>%%ei%%</code>'s are sequence expressions.
 </p>
 <p>
@@ -770,5 +781,11 @@ transform is that queries are automatically optimized by applying classical
 logic SQL optimization techniques (this automatic optimization can be
 disabled).
 </p>
+<p>
+The built-in optimizer is free to move boolean conditions around to
+ evaluate them as soon as possible. As warning is issued if a
+ condition does not depend on any of the variables captured by the
+ patterns.
+</p>
 </box>
 </page>

web/manual/schema.xml

@@ -633,4 +633,33 @@ val xml : Any = <ignored_tag From="fake@microsoft.com">[
   </p>
 </box>
 
+<box title="Unsupported XML Schema features" link="nonsupp">
+<p>
+The support for XML Schema embedded in CDuce does not attempt
+to cover the full XML Schema specification. In particular,
+imported schemas are not checked to be valid. You can use
+for instance this <a href="http://apps.gotdotnet.com/xmltools/xsdvalidator/">
+on-line validator</a> to check validity of a schema.
+</p>
+
+<p>
+Also, some features from the XML Schema specification are not or
+only partially supported. Here is a non-exhaustive list of limitations:
+</p>
+<ul>
+<li>
+  Substitution groups.
+</li>
+<li>
+  Some facets (pattern, totalDigits, fractionDigits).
+</li>
+<li>
+  <tt>&lt;redefine></tt> (inclusion of an XML Schema with modifications).
+</li>
+<li>
+  <tt>xsi:type</tt>.
+</li>
+</ul>
+</box>
+
 </page>

web/manual/types_patterns.xml

@@ -258,10 +258,8 @@ E.g.: <code>[ 1 2 3 ] @ [ 4 5 6 ]</code> evaluates to
 It is possible to specify a terminator different from <code>`nil</code>;
 for instance 
 <code>[ 1 2 3 4 ; %%q%% ]</code> denotes <code>(1,(2,(3,(4,%%q%%))))</code>, 
-and is equivalent to (but more efficient than):
+and is equivalent to 
 <code>[ 1 2 3 4 ] @ %%q%%</code>.
-Consequently, a pair <code>(%%e1%%,%%e2%%)</code> can also
-be written <code>[ %%e1%%; %%e2%% ]</code>.
 </p>
 
 <p>
@@ -344,6 +342,18 @@ in a pattern, e.g.: <code>[ x::Int* ; _ ]</code>, which
 is equivalent to <code>[ x::Int* _* ]</code>.
 </p>
 
+<p>
+If it possible in some circumstances to use the <code>@</code>
+operator (sequence concatenation) on types, including in recursive 
+definitions. E.g.:
+</p>
+
+<sample><![CDATA[
+type t = [ <a>(t @ t) ? ]    (* [s?] where s=<a>[ s? s? ] *)
+type x = [ Int* ]
+type y = x @ [ Char* ]       (* [ Int* Char* ] *)
+]]></sample>
+
 </section>
 
 </box>
@@ -444,6 +454,20 @@ it is possible to omit it. E.g.: <code>{ x; y = b; z }</code>
 is equivalent to <code>{ x = x; y = b; z = z }</code>.
 </p>
 
+<p>
+The <code>+</code> operator (record concatenation, with priority given
+to the right argument in case of overlapping) is available on record
+types and patterns. This operator can be used to make a close
+record type/pattern open, or to add fields:
+</p>
+
+<sample>
+type t = { a=Int b=Char }
+type s = t + {..}               (* { a=Int b=Char .. }
+type u = s + { c=Float }        (* { a=Int b=Char c=Float .. } *)
+type v = t + { c=Float }        (* { a=Int b=Char c=Float } *)
+</sample>
+
 </box>
 
 <box title="XML elements" link="xml">