Do not unquote + into ' ' in URLs

Since 9d2e942 (decode file:// and ssh:// URLs, 2010-05-23) the URL
logic unquotes escaped URLs.  For the %2B type of escape, this is
conformant with RFC 2396.  However, it also unquotes + into a space
character, which is only appropriate for the query strings in HTTP.
This notably broke fetching from the gtk+ repository.

We cannot just remove the corresponding code since the same
url_decode_internal() is also used by the HTTP backend to decode query
parameters.  Introduce a new argument that controls whether the +
decoding happens, and use it only in the (client-side) url_decode().

Reported-by: Jasper St. Pierre <jstpierre@mecheye.net>
Signed-off-by: Thomas Rast <trast@student.ethz.ch>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/t/t5601-clone.sh b/t/t5601-clone.sh
index 8abb71afcd4d7389260baa6f82ecb9b53bb9524c..4431dfd02b59710b8e7fc48928dd846615a8c000 100755 (executable)
--- a/t/t5601-clone.sh
+++ b/t/t5601-clone.sh
@@ -178,8 +178,14 @@ test_expect_success 'clone respects global branch.autosetuprebase' '
 
 test_expect_success 'respect url-encoding of file://' '
        git init x+y &&
-       test_must_fail git clone "file://$PWD/x+y" xy-url &&
-       git clone "file://$PWD/x%2By" xy-url
+       git clone "file://$PWD/x+y" xy-url-1 &&
+       git clone "file://$PWD/x%2By" xy-url-2
+'
+
+test_expect_success 'do not query-string-decode + in URLs' '
+       rm -rf x+y &&
+       git init "x y" &&
+       test_must_fail git clone "file://$PWD/x+y" xy-no-plus
 '
 
 test_expect_success 'do not respect url-encoding of non-url path' '

diff --git a/url.c b/url.c
index 230623657a0e06975c4721a9fddb117ba84883b1..cd8f74f00c345294f94cb25e4e00849a0618168b 100644 (file)
--- a/url.c
+++ b/url.c
@@ -67,7 +67,8 @@ static int url_decode_char(const char *q)
        return val;
 }
 
-static char *url_decode_internal(const char **query, const char *stop_at, struct strbuf *out)
+static char *url_decode_internal(const char **query, const char *stop_at,
+                                struct strbuf *out, int decode_plus)
 {
        const char *q = *query;
 
@@ -90,7 +91,7 @@ static char *url_decode_internal(const char **query, const char *stop_at, struct
                        }
                }
 
-               if (c == '+')
+               if (decode_plus && c == '+')
                        strbuf_addch(out, ' ');
                else
                        strbuf_addch(out, c);
@@ -110,17 +111,17 @@ char *url_decode(const char *url)
                strbuf_add(&out, url, colon - url);
                url = colon;
        }
-       return url_decode_internal(&url, NULL, &out);
+       return url_decode_internal(&url, NULL, &out, 0);
 }
 
 char *url_decode_parameter_name(const char **query)
 {
        struct strbuf out = STRBUF_INIT;
-       return url_decode_internal(query, "&=", &out);
+       return url_decode_internal(query, "&=", &out, 1);
 }
 
 char *url_decode_parameter_value(const char **query)
 {
        struct strbuf out = STRBUF_INIT;
-       return url_decode_internal(query, "&", &out);
+       return url_decode_internal(query, "&", &out, 1);
 }