http: extract type/subtype portion of content-type

diff --git a/http.c b/http.c
index 94e1afdee7890825dfda0946b999f524265603fc..6bfd0934b3cc977436f5955992918d8991270dec 100644 (file)
--- a/http.c
+++ b/http.c
@@ -906,6 +906,35 @@ static CURLcode curlinfo_strbuf(CURL *curl, CURLINFO info, struct strbuf *buf)
        return ret;
 }
 
+/*
+ * Extract a normalized version of the content type, with any
+ * spaces suppressed, all letters lowercased, and no trailing ";"
+ * or parameters.
+ *
+ * Note that we will silently remove even invalid whitespace. For
+ * example, "text / plain" is specifically forbidden by RFC 2616,
+ * but "text/plain" is the only reasonable output, and this keeps
+ * our code simple.
+ *
+ * Example:
+ *   "TEXT/PLAIN; charset=utf-8" -> "text/plain"
+ *   "text / plain" -> "text/plain"
+ */
+static void extract_content_type(struct strbuf *raw, struct strbuf *type)
+{
+       const char *p;
+
+       strbuf_reset(type);
+       strbuf_grow(type, raw->len);
+       for (p = raw->buf; *p; p++) {
+               if (isspace(*p))
+                       continue;
+               if (*p == ';')
+                       break;
+               strbuf_addch(type, tolower(*p));
+       }
+}
+
 /* http_request() targets */
 #define HTTP_REQUEST_STRBUF    0
 #define HTTP_REQUEST_FILE      1
@@ -957,9 +986,12 @@ static int http_request(const char *url,
 
        ret = run_one_slot(slot, &results);
 
-       if (options && options->content_type)
-               curlinfo_strbuf(slot->curl, CURLINFO_CONTENT_TYPE,
-                               options->content_type);
+       if (options && options->content_type) {
+               struct strbuf raw = STRBUF_INIT;
+               curlinfo_strbuf(slot->curl, CURLINFO_CONTENT_TYPE, &raw);
+               extract_content_type(&raw, options->content_type);
+               strbuf_release(&raw);
+       }
 
        if (options && options->effective_url)
                curlinfo_strbuf(slot->curl, CURLINFO_EFFECTIVE_URL,