http: optionally extract charset parameter from content-type

Since the previous commit, we now give a sanitized,
shortened version of the content-type header to any callers
who ask for it.

This patch adds back a way for them to cleanly access
specific parameters to the type. We could easily extract all
parameters and make them available via a string_list, but:

  1. That complicates the interface and memory management.

  2. In practice, no planned callers care about anything
     except the charset.

This patch therefore goes with the simplest thing, and we
can expand or change the interface later if it becomes
necessary.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 57 insertions, 4 deletions

diff --git a/http.c b/http.c
index 6bfd0934b3..84463dff3d 100644
--- a/http.c
+++ b/http.c
@@ -907,6 +907,32 @@ static CURLcode curlinfo_strbuf(CURL *curl, CURLINFO info, struct strbuf *buf)
 }
 
 /*
+ * Check for and extract a content-type parameter. "raw"
+ * should be positioned at the start of the potential
+ * parameter, with any whitespace already removed.
+ *
+ * "name" is the name of the parameter. The value is appended
+ * to "out".
+ */
+static int extract_param(const char *raw, const char *name,
+			 struct strbuf *out)
+{
+	size_t len = strlen(name);
+
+	if (strncasecmp(raw, name, len))
+		return -1;
+	raw += len;
+
+	if (*raw != '=')
+		return -1;
+	raw++;
+
+	while (*raw && !isspace(*raw))
+		strbuf_addch(out, *raw++);
+	return 0;
+}
+
+/*
  * Extract a normalized version of the content type, with any
  * spaces suppressed, all letters lowercased, and no trailing ";"
  * or parameters.
@@ -916,11 +942,15 @@ static CURLcode curlinfo_strbuf(CURL *curl, CURLINFO info, struct strbuf *buf)
  * but "text/plain" is the only reasonable output, and this keeps
  * our code simple.
  *
+ * If the "charset" argument is not NULL, store the value of any
+ * charset parameter there.
+ *
  * Example:
- *   "TEXT/PLAIN; charset=utf-8" -> "text/plain"
+ *   "TEXT/PLAIN; charset=utf-8" -> "text/plain", "utf-8"
  *   "text / plain" -> "text/plain"
  */
-static void extract_content_type(struct strbuf *raw, struct strbuf *type)
+static void extract_content_type(struct strbuf *raw, struct strbuf *type,
+				 struct strbuf *charset)
 {
 	const char *p;
 
@@ -929,10 +959,25 @@ static void extract_content_type(struct strbuf *raw, struct strbuf *type)
 	for (p = raw->buf; *p; p++) {
 		if (isspace(*p))
 			continue;
-		if (*p == ';')
+		if (*p == ';') {
+			p++;
 			break;
+		}
 		strbuf_addch(type, tolower(*p));
 	}
+
+	if (!charset)
+		return;
+
+	strbuf_reset(charset);
+	while (*p) {
+		while (isspace(*p))
+			p++;
+		if (!extract_param(p, "charset", charset))
+			return;
+		while (*p && !isspace(*p))
+			p++;
+	}
 }
 
 /* http_request() targets */
@@ -989,7 +1034,8 @@ static int http_request(const char *url,
 	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);
+		extract_content_type(&raw, options->content_type,
+				     options->charset);
 		strbuf_release(&raw);
 	}
 
diff --git a/http.h b/http.h
index e64084fe6d..473179b14d 100644
--- a/http.h
+++ b/http.h
@@ -144,6 +144,13 @@ struct http_get_options {
 	struct strbuf *content_type;
 
 	/*
+	 * If non-NULL, and content_type above is non-NULL, returns
+	 * the charset parameter from the content-type. If none is
+	 * present, returns an empty string.
+	 */
+	struct strbuf *charset;
+
+	/*
 	 * If non-NULL, returns the URL we ended up at, including any
 	 * redirects we followed.
 	 */