Re: [xml] patch: Functions to parse and create URI query strings

["Richard W.M. Jones" <rjones redhat com>]

The attached patch just adds query_raw, and uses it in preference to 
query if it is set.

Rich.

--
Emerging Technologies, Red Hat  http://et.redhat.com/~rjones/
64 Baker Street, London, W1U 7DF     Mobile: +44 7866 314 421

Registered Address: Red Hat UK Ltd, Amberley Place, 107-111 Peascod
Street, Windsor, Berkshire, SL4 1TE, United Kingdom.
Registered in England and Wales under Company Registration No. 3798903
Directors: Michael Cunningham (USA), Charlie Peters (USA) and David
Owens (Ireland)

Index: uri.c
===================================================================
--- uri.c       (revision 3606)
+++ uri.c       (working copy)
@@ -446,7 +446,33 @@
                }
            }
        }
-       if (uri->query != NULL) {
+       if (uri->query_raw != NULL) {
+           if (len + 1 >= max) {
+               max *= 2;
+               ret = (xmlChar *) xmlRealloc(ret,
+                       (max + 1) * sizeof(xmlChar));
+               if (ret == NULL) {
+                   xmlGenericError(xmlGenericErrorContext,
+                           "xmlSaveUri: out of memory\n");
+                   return(NULL);
+               }
+           }
+           ret[len++] = '?';
+           p = uri->query_raw;
+           while (*p != 0) {
+               if (len + 1 >= max) {
+                   max *= 2;
+                   ret = (xmlChar *) xmlRealloc(ret,
+                           (max + 1) * sizeof(xmlChar));
+                   if (ret == NULL) {
+                       xmlGenericError(xmlGenericErrorContext,
+                               "xmlSaveUri: out of memory\n");
+                       return(NULL);
+                   }
+               }
+               ret[len++] = *p++;
+           }
+       } else if (uri->query != NULL) {
            if (len + 3 >= max) {
                max *= 2;
                ret = (xmlChar *) xmlRealloc(ret,
@@ -574,6 +600,8 @@
     uri->authority = NULL;
     if (uri->query != NULL) xmlFree(uri->query);
     uri->query = NULL;
+    if (uri->query_raw != NULL) xmlFree(uri->query_raw);
+    uri->query_raw = NULL;
 }
 
 /**
@@ -594,6 +622,7 @@
     if (uri->opaque != NULL) xmlFree(uri->opaque);
     if (uri->authority != NULL) xmlFree(uri->authority);
     if (uri->query != NULL) xmlFree(uri->query);
+    if (uri->query_raw != NULL) xmlFree(uri->query_raw);
     xmlFree(uri);
 }
 
@@ -1030,7 +1059,11 @@
         xmlFree(segment);
     }
 
-    if (uri->query) {
+    if (uri->query_raw) {
+        ret = xmlStrcat(ret, BAD_CAST "?");
+        ret = xmlStrcat(ret, BAD_CAST uri->query_raw);
+    }
+    else if (uri->query) {
         segment =
             xmlURIEscapeStr(BAD_CAST uri->query, BAD_CAST ";/?:@&=+,$");
         NULLCHK(segment)
@@ -1133,6 +1166,13 @@
            uri->query = STRNDUP(*str, cur - *str);
        else
            uri->query = xmlURIUnescapeString(*str, cur - *str, NULL);
+
+       /* Save the raw bytes of the query as well.
+        * See: http://mail.gnome.org/archives/xml/2007-April/thread.html#00114
+        */
+       if (uri->query_raw != NULL)
+           xmlFree (uri->query_raw);
+       uri->query_raw = STRNDUP (*str, cur - *str);
     }
     *str = cur;
     return (0);
@@ -1946,8 +1986,12 @@
        }
        if (bas->path != NULL)
            res->path = xmlMemStrdup(bas->path);
-       if (ref->query != NULL)
+       if (ref->query_raw != NULL)
+           res->query_raw = xmlMemStrdup (ref->query_raw);
+       else if (ref->query != NULL)
            res->query = xmlMemStrdup(ref->query);
+       else if (bas->query_raw != NULL)
+           res->query_raw = xmlMemStrdup(bas->query_raw);
        else if (bas->query != NULL)
            res->query = xmlMemStrdup(bas->query);
        if (ref->fragment != NULL)
@@ -1968,7 +2012,9 @@
     if (bas->scheme != NULL)
        res->scheme = xmlMemStrdup(bas->scheme);
  
-    if (ref->query != NULL)
+    if (ref->query_raw != NULL)
+       res->query_raw = xmlMemStrdup(ref->query_raw);
+    else if (ref->query != NULL)
        res->query = xmlMemStrdup(ref->query);
     if (ref->fragment != NULL)
        res->fragment = xmlMemStrdup(ref->fragment);
Index: include/libxml/uri.h
===================================================================
--- include/libxml/uri.h        (revision 3606)
+++ include/libxml/uri.h        (working copy)
@@ -23,6 +23,10 @@
  *
  * A parsed URI reference. This is a struct containing the various fields
  * as described in RFC 2396 but separated for further processing.
+ *
+ * Note: query is a deprecated field which is incorrectly unescaped.
+ * query_raw takes precedence over query if the former is set.
+ * See: http://mail.gnome.org/archives/xml/2007-April/thread.html#00127
  */
 typedef struct _xmlURI xmlURI;
 typedef xmlURI *xmlURIPtr;
@@ -34,9 +38,10 @@
     char *user;                /* the user part */
     int port;          /* the port number */
     char *path;                /* the path string */
-    char *query;       /* the query string */
+    char *query;       /* the query string (deprecated - use with caution) */
     char *fragment;    /* the fragment identifier */
     int  cleanup;      /* parsing potentially unclean URI */
+    char *query_raw;   /* the query string (as it appears in the URI) */
 };
 
 /*

Attachment: smime.p7s
Description: S/MIME Cryptographic Signature