http redirects: %-encode bytes outside of ascii range

Apparently there are sites out there that do redirects to URLs they
provide in plain UTF-8 or similar. Browsers and wget %-encode such
headers when doing a subsequent request. Now libcurl does too.

Added test 1138 to verify.

Closes #473

3 files changed, 98 insertions, 19 deletions

diff --git a/lib/transfer.c b/lib/transfer.c
index dda235cc7..91777d6f5 100644
--- a/lib/transfer.c
+++ b/lib/transfer.c
@@ -1396,16 +1396,18 @@ CURLcode Curl_posttransfer(struct SessionHandle *data)
  */
 static size_t strlen_url(const char *url)
 {
-  const char *ptr;
+  const unsigned char *ptr;
   size_t newlen=0;
   bool left=TRUE; /* left side of the ? */
 
-  for(ptr=url; *ptr; ptr++) {
+  for(ptr=(unsigned char *)url; *ptr; ptr++) {
     switch(*ptr) {
     case '?':
       left=FALSE;
       /* fall through */
     default:
+      if(*ptr >= 0x80)
+        newlen += 2;
       newlen++;
       break;
     case ' ':
@@ -1426,9 +1428,9 @@ static void strcpy_url(char *output, const char *url)
 {
   /* we must add this with whitespace-replacing */
   bool left=TRUE;
-  const char *iptr;
+  const unsigned char *iptr;
   char *optr = output;
-  for(iptr = url;    /* read from here */
+  for(iptr = (unsigned char *)url;    /* read from here */
       *iptr;         /* until zero byte */
       iptr++) {
     switch(*iptr) {
@@ -1436,7 +1438,12 @@ static void strcpy_url(char *output, const char *url)
       left=FALSE;
       /* fall through */
     default:
-      *optr++=*iptr;
+      if(*iptr >= 0x80) {
+        snprintf(optr, 4, "%%%02x", *iptr);
+        optr += 3;
+      }
+      else
+        *optr++=*iptr;
       break;
     case ' ':
       if(left) {
@@ -1684,23 +1691,21 @@ CURLcode Curl_follow(struct SessionHandle *data,
     newurl = absolute;
   }
   else {
+    /* The new URL MAY contain space or high byte values, that means a mighty
+       stupid redirect URL but we still make an effort to do "right". */
+    char *newest;
+    size_t newlen = strlen_url(newurl);
+
     /* This is an absolute URL, don't allow the custom port number */
     disallowport = TRUE;
 
-    if(strchr(newurl, ' ')) {
-      /* This new URL contains at least one space, this is a mighty stupid
-         redirect but we still make an effort to do "right". */
-      char *newest;
-      size_t newlen = strlen_url(newurl);
-
-      newest = malloc(newlen+1); /* get memory for this */
-      if(!newest)
-        return CURLE_OUT_OF_MEMORY;
-      strcpy_url(newest, newurl); /* create a space-free URL */
+    newest = malloc(newlen+1); /* get memory for this */
+    if(!newest)
+      return CURLE_OUT_OF_MEMORY;
+    strcpy_url(newest, newurl); /* create a space-free URL */
 
-      free(newurl); /* that was no good */
-      newurl = newest; /* use this instead now */
-    }
+    free(newurl); /* that was no good */
+    newurl = newest; /* use this instead now */
 
   }
 
diff --git a/tests/data/Makefile.inc b/tests/data/Makefile.inc
index 79214dbfa..3cf8c3e22 100644
--- a/tests/data/Makefile.inc
+++ b/tests/data/Makefile.inc
@@ -118,7 +118,7 @@ test1104 test1105 test1106 test1107 test1108 test1109 test1110 test1111 \
 test1112 test1113 test1114 test1115 test1116 test1117 test1118 test1119 \
 test1120 test1121 test1122 test1123 test1124 test1125 test1126 test1127 \
 test1128 test1129 test1130 test1131 test1132 test1133 test1134 test1135 \
-test1136 test1137 \
+test1136 test1137 test1138 \
 \
 test1200 test1201 test1202 test1203 test1204 test1205 test1206 test1207 \
 test1208 test1209 test1210 test1211 test1212 test1213 test1214 test1215 \
diff --git a/tests/data/test1138 b/tests/data/test1138
new file mode 100644
index 000000000..0c91d204d
--- /dev/null
+++ b/tests/data/test1138
@@ -0,0 +1,74 @@
+<testcase>
+<info>
+<keywords>
+HTTP
+HTTP GET
+followlocation
+</keywords>
+</info>
+#
+# Server-side
+<reply>
+<data>
+HTTP/1.1 302 OK swsclose

+Location: ../moo.html/?name=آغاز-سم-زدایی-از-بازار-پول&testcase=/11380002    

+Date: Thu, 09 Nov 2010 14:49:00 GMT

+Connection: close

+

+</data>
+<data2>
+HTTP/1.1 200 OK swsclose

+Location: this should be ignored

+Date: Thu, 09 Nov 2010 14:49:00 GMT

+Connection: close

+

+body
+</data2>
+<datacheck>
+HTTP/1.1 302 OK swsclose

+Location: ../moo.html/?name=آغاز-سم-زدایی-از-بازار-پول&testcase=/11380002    

+Date: Thu, 09 Nov 2010 14:49:00 GMT

+Connection: close

+

+HTTP/1.1 200 OK swsclose

+Location: this should be ignored

+Date: Thu, 09 Nov 2010 14:49:00 GMT

+Connection: close

+

+body
+</datacheck>
+</reply>
+
+#
+# Client-side
+<client>
+<server>
+http
+</server>
+ <name>
+HTTP redirect with UTF-8 characters
+ </name>
+ <command>
+http://%HOSTIP:%HTTPPORT/we/are/all/twits/1138 -L
+</command>
+</client>
+
+#
+# Verify data after the test has been "shot"
+<verify>
+<strip>
+^User-Agent:.*
+</strip>
+<protocol>
+GET /we/are/all/twits/1138 HTTP/1.1

+Host: %HOSTIP:%HTTPPORT

+Accept: */*

+

+GET /we/are/all/moo.html/?name=%d8%a2%d8%ba%d8%a7%d8%b2-%d8%b3%d9%85-%d8%b2%d8%af%d8%a7%db%8c%db%8c-%d8%a7%d8%b2-%d8%a8%d8%a7%d8%b2%d8%a7%d8%b1-%d9%be%d9%88%d9%84&testcase=/11380002 HTTP/1.1

+User-Agent: curl/7.10 (i686-pc-linux-gnu) libcurl/7.10 OpenSSL/0.9.6c ipv6 zlib/1.1.3

+Host: %HOSTIP:%HTTPPORT

+Accept: */*

+

+</protocol>
+</verify>
+</testcase>