curl/get_url_file_name: use libcurl URL parser

To avoid URL tricks, use the URL parser for this.

This update changes curl's behavior slightly in that it will ignore the
possible query part from the URL and only use the file name from the
actual path from the URL. I consider it a bugfix.

"curl -O localhost/name?giveme-giveme" will now save the output in the
local file named 'name'

Updated test 1210 to verify

Assisted-by: Jay Satiro
Closes #9684

diff --git a/src/tool_operhlp.c b/src/tool_operhlp.c
index d311e8d9daa4f72069d2712b0da9ea1d31b67a2b..f41406f3ce42058e118a2795d589ca8a338c2704 100644 (file)
--- a/src/tool_operhlp.c
+++ b/src/tool_operhlp.c
@@ -149,61 +149,65 @@ CURLcode add_file_name_to_url(CURL *curl, char **inurlp, const char *filename)
 CURLcode get_url_file_name(char **filename, const char *url)
 {
   const char *pc, *pc2;
+  CURLU *uh = curl_url();
+  char *path = NULL;
+
+  if(!uh)
+    return CURLE_OUT_OF_MEMORY;
 
   *filename = NULL;
 
-  /* Find and get the remote file name */
-  pc = strstr(url, "://");
-  if(pc)
-    pc += 3;
-  else
-    pc = url;
-
-  pc2 = strrchr(pc, '\\');
-  pc = strrchr(pc, '/');
-  if(pc2 && (!pc || pc < pc2))
-    pc = pc2;
-
-  if(pc)
-    /* duplicate the string beyond the slash */
-    pc++;
-  else
-    /* no slash => empty string */
-    pc = "";
-
-  *filename = strdup(pc);
-  if(!*filename)
-    return CURLE_OUT_OF_MEMORY;
+  if(!curl_url_set(uh, CURLUPART_URL, url, CURLU_GUESS_SCHEME) &&
+     !curl_url_get(uh, CURLUPART_PATH, &path, 0)) {
+    curl_url_cleanup(uh);
+
+    pc = strrchr(path, '/');
+    pc2 = strrchr(pc ? pc + 1 : path, '\\');
+    if(pc2)
+      pc = pc2;
+
+    if(pc)
+      /* duplicate the string beyond the slash */
+      pc++;
+    else
+      /* no slash => empty string */
+      pc = "";
+
+    *filename = strdup(pc);
+    curl_free(path);
+    if(!*filename)
+      return CURLE_OUT_OF_MEMORY;
 
 #if defined(MSDOS) || defined(WIN32)
-  {
-    char *sanitized;
-    SANITIZEcode sc = sanitize_file_name(&sanitized, *filename, 0);
-    Curl_safefree(*filename);
-    if(sc)
-      return CURLE_URL_MALFORMAT;
-    *filename = sanitized;
-  }
+    {
+      char *sanitized;
+      SANITIZEcode sc = sanitize_file_name(&sanitized, *filename, 0);
+      Curl_safefree(*filename);
+      if(sc)
+        return CURLE_URL_MALFORMAT;
+      *filename = sanitized;
+    }
 #endif /* MSDOS || WIN32 */
 
-  /* in case we built debug enabled, we allow an environment variable
-   * named CURL_TESTDIR to prefix the given file name to put it into a
-   * specific directory
-   */
+    /* in case we built debug enabled, we allow an environment variable
+     * named CURL_TESTDIR to prefix the given file name to put it into a
+     * specific directory
+     */
 #ifdef DEBUGBUILD
-  {
-    char *tdir = curlx_getenv("CURL_TESTDIR");
-    if(tdir) {
-      char buffer[512]; /* suitably large */
-      msnprintf(buffer, sizeof(buffer), "%s/%s", tdir, *filename);
-      Curl_safefree(*filename);
-      *filename = strdup(buffer); /* clone the buffer */
-      curl_free(tdir);
-      if(!*filename)
-        return CURLE_OUT_OF_MEMORY;
+    {
+      char *tdir = curlx_getenv("CURL_TESTDIR");
+      if(tdir) {
+        char *alt = aprintf("%s/%s", tdir, *filename);
+        Curl_safefree(*filename);
+        *filename = alt;
+        curl_free(tdir);
+        if(!*filename)
+          return CURLE_OUT_OF_MEMORY;
+      }
     }
-  }
 #endif
-
-  return CURLE_OK;
+    return CURLE_OK;
+  }
+  curl_url_cleanup(uh);
+  return CURLE_URL_MALFORMAT;
 }

diff --git a/tests/data/test1210 b/tests/data/test1210
index 037eb16d8e3ebecef0ac3fa40eead7b5aec3af89..89cfe61eaf48bb50575d4c1cd64399c7fd111afa 100644 (file)
--- a/tests/data/test1210
+++ b/tests/data/test1210
@@ -39,7 +39,7 @@ HTTP GET with -J without Content-Disposition
 CURL_TESTDIR=%PWD/log
 </setenv>
 <command option="no-output,no-include">
-http://%HOSTIP:%HTTPPORT/%TESTNUMBER -J -O
+http://%HOSTIP:%HTTPPORT/%TESTNUMBER?junk -J -O
 </command>
 </client>
 
@@ -47,7 +47,7 @@ http://%HOSTIP:%HTTPPORT/%TESTNUMBER -J -O
 # Verify data after the test has been "shot"
 <verify>
 <protocol>
-GET /%TESTNUMBER HTTP/1.1\r
+GET /%TESTNUMBER?junk HTTP/1.1\r
 Host: %HOSTIP:%HTTPPORT\r
 User-Agent: curl/%VERSION\r
 Accept: */*\r