*add comment on another mistake in RFC 2616 (query part of

Request-URIs only allowed for absoluteURIs)
*add copy of Appendix A of RFC 2396 for convenience

scheme/lib/url.scm

@@ -1,6 +1,6 @@
 ;;; HTTP 1.1 Request-URI parsing and unparsing -*- Scheme -*-
 
-;;; Copyright (c) 1995 by Olin Shivers.
+;;; Copyright (c) 2005 by Viola Brunner.
 ;;; For copyright information, see the file COPYING which comes with
 ;;; the distribution.
 
@@ -8,9 +8,13 @@
 ;;; RFC 2616 Hypertext Transfer Protocol -- HTTP/1.1
 ;;; RFC 2396 Uniform Resource Identifiers (URI): Generic Syntax
 ;;;
-;;; RFC 2616 adopts definitions of regexps from RFC 2396.
+;;; RFC 2616 adopts definitions of regexps from RFC 2396
+;;; (see copy of Appendix A of RFC 2396 below)
 
 
+;;; Note: there are 2 Problems in RFC 2616 concerning URIS:
+
+;;; Problem 1:
 ;;; RFC 2616 is ambiguous in defining Request_URIS:
 ;;;
 ;;; section 5.1.2 states:
@@ -19,24 +23,39 @@
 ;;;
 ;;; whilst section 3.2.2 defines the 'http_URL'
 ;;; http_URL = "http://" host [ ":" port ] [ abs_path [ "?" query ]]
-
-
-;;; Since allowing for general absoluteURIs doesn't make too much sense
-;;; we implement only Request_URIs as follows:
-;;; Request-URI    = ( http_URL | abs_path) ["#" fragment]
 ;;;
-;;; where http_URL is a subset of absoluteURI
+;;; Solution to Problem 1:
+;;; Since allowing for general absoluteURIs doesn't make too much sense
+;;; we implement Request_URIs of the form
+;;; Request-URI    = ( http_URL | abs_path) ["#" fragment]
+;;; where http_URL is a only a subset of absoluteURI
 
-;;; [ "#" fragment ] is allowed even though 
-;;; RFC 2616 disallowes the #fragment part 
-;;; (while RFC 1945 for HTTP/1.0 allowed it).
-;;; (This is for compatibility with buggy clients).
 
+;;; Problem 2: 
+;;; according to RFC 2616, section 5.1.2, the Request-URI may only
+;;; have a [? query] part if it's an absoluteURI; on the other hand
+;;; only requests being made to proxies are supposed to use
+;;; absoluteURIs; abs_path is the normal case. So this must be a mistake.
+;;; See also http://skrb.org/ietf/http_errata.html#uriquery
+;;;
+;;; Solution to Problem 2:
+;;, we implement Request_URIs of the form
+;;; Request-URI    = ( http_URL | abs_path ["?" query] ) ["#" fragment]
+
+
+;;; Here we depart from the RFCs:
+;;; RFC 2616 and 1945 disallow a #fragment-suffix of the Request-URI.
+;;; For compatibility with buggy clients we _do_ allow for it.
+;;; (Apache does so, too).
 
 
 
 ;;; RexExps for Request-URIs as scsh SREs
 ;;; stick to RFC terminology throughout
+;;; (see copy of Appendix A of RFC 2396 below)
+;;;
+;;; we implement Request_URIs of the form
+;;; Request-URI    = ( http_URL | abs_path) ["#" fragment]
 
 (define digit (rx numeric))
 
@@ -276,3 +295,60 @@
 (define (escape-query query)
   (escape query query-reserved-and-excluded))
 
+;; Appendix A of RFC 2396
+;;
+;A. Collected BNF for URI
+
+;      URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
+;      absoluteURI   = scheme ":" ( hier_part | opaque_part )
+;      relativeURI   = ( net_path | abs_path | rel_path ) [ "?" query ]
+;      hier_part     = ( net_path | abs_path ) [ "?" query ]
+;      opaque_part   = uric_no_slash *uric
+;      uric_no_slash = unreserved | escaped | ";" | "?" | ":" | "@" |
+;                      "&" | "=" | "+" | "$" | ","
+;      net_path      = "//" authority [ abs_path ]
+;      abs_path      = "/"  path_segments
+;      rel_path      = rel_segment [ abs_path ]
+;      rel_segment   = 1*( unreserved | escaped |
+;                          ";" | "@" | "&" | "=" | "+" | "$" | "," )
+;      scheme        = alpha *( alpha | digit | "+" | "-" | "." )
+;      authority     = server | reg_name
+;      reg_name      = 1*( unreserved | escaped | "$" | "," |
+;                          ";" | ":" | "@" | "&" | "=" | "+" )
+;      server        = [ [ userinfo "@" ] hostport ]
+;      userinfo      = *( unreserved | escaped |
+;                         ";" | ":" | "&" | "=" | "+" | "$" | "," )
+;      hostport      = host [ ":" port ]
+;      host          = hostname | IPv4address
+;      hostname      = *( domainlabel "." ) toplabel [ "." ]
+;      domainlabel   = alphanum | alphanum *( alphanum | "-" ) alphanum
+;      toplabel      = alpha | alpha *( alphanum | "-" ) alphanum
+;      IPv4address   = 1*digit "." 1*digit "." 1*digit "." 1*digit
+;      port          = *digit
+;      path          = [ abs_path | opaque_part ]
+;      path_segments = segment *( "/" segment )
+;      segment       = *pchar *( ";" param )
+;      param         = *pchar
+;      pchar         = unreserved | escaped |
+;                      ":" | "@" | "&" | "=" | "+" | "$" | ","
+;      query         = *uric
+;      fragment      = *uric
+;      uric          = reserved | unreserved | escaped
+;      reserved      = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
+;                      "$" | ","
+;      unreserved    = alphanum | mark
+;      mark          = "-" | "_" | "." | "!" | "~" | "*" | "'" |
+;                      "(" | ")"
+;      escaped       = "%" hex hex
+;      hex           = digit | "A" | "B" | "C" | "D" | "E" | "F" |
+;                              "a" | "b" | "c" | "d" | "e" | "f"
+;      alphanum      = alpha | digit
+;      alpha         = lowalpha | upalpha
+;      lowalpha = "a" | "b" | "c" | "d" | "e" | "f" | "g" | "h" | "i" |
+;                 "j" | "k" | "l" | "m" | "n" | "o" | "p" | "q" | "r" |
+;                 "s" | "t" | "u" | "v" | "w" | "x" | "y" | "z"
+;      upalpha  = "A" | "B" | "C" | "D" | "E" | "F" | "G" | "H" | "I" |
+;                 "J" | "K" | "L" | "M" | "N" | "O" | "P" | "Q" | "R" |
+;                 "S" | "T" | "U" | "V" | "W" | "X" | "Y" | "Z"
+;      digit    = "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" |
+;                 "8" | "9"