[PATCH v3] notmuch/emacs: Observe the charset of text/html parts, where known.

[David Edmondson]

Add the charset of text/html parts to the JSON output of 'notmuch
-show' when it is known. Observe the encoding when rendering such
parts in emacs.
---

Commentary added.

 emacs/notmuch-show.el |    3 ++-
 notmuch-show.c        |   28 +++++++++++++++++++++++-----
 2 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/emacs/notmuch-show.el b/emacs/notmuch-show.el
index 5502efd..0354a8e 100644
--- a/emacs/notmuch-show.el
+++ b/emacs/notmuch-show.el
@@ -328,7 +328,8 @@ message at DEPTH in the current thread."
 current buffer, if possible."
   (let ((display-buffer (current-buffer)))
     (with-temp-buffer
-      (let ((handle (mm-make-handle (current-buffer) (list content-type))))
+      (let* ((charset (plist-get part :content-charset))
+	     (handle (mm-make-handle (current-buffer) `(,content-type (charset . ,charset)))))
 	(if (and (mm-inlinable-p handle)
 		 (mm-inlined-p handle))
 	    (let ((content (notmuch-show-get-bodypart-content msg part nth)))
diff --git a/notmuch-show.c b/notmuch-show.c
index 0200b9c..87a1c90 100644
--- a/notmuch-show.c
+++ b/notmuch-show.c
@@ -675,13 +675,31 @@ format_part_content_json (GMimeObject *part)
 	    printf (", \"filename\": %s", json_quote_str (ctx, filename));
     }
 
-    if (g_mime_content_type_is_type (content_type, "text", "*") &&
-	!g_mime_content_type_is_type (content_type, "text", "html"))
+    if (g_mime_content_type_is_type (content_type, "text", "*"))
     {
-	show_text_part_content (part, stream_memory);
-	part_content = g_mime_stream_mem_get_byte_array (GMIME_STREAM_MEM (stream_memory));
+	/* For non-HTML text/* parts, we include the content in the
+	 * JSON. Since JSON must be Unicode, we handle charset
+	 * decoding here and do not report a charset to the caller.
+	 * For text/html parts, we do not include the content. If a
+	 * caller is interested in text/html parts, it should retrieve
+	 * them separately and they will not be decoded. Since this
+	 * makes charset decoding the responsibility on the caller, we
+	 * report the charset for text/html parts.
+	 */
+	if (g_mime_content_type_is_type (content_type, "text", "html"))
+	{
+	    const char *content_charset = g_mime_object_get_content_type_parameter (GMIME_OBJECT (part), "charset");
+
+	    if (content_charset != NULL)
+		printf (", \"content-charset\": %s", json_quote_str (ctx, content_charset));
+	}
+	else
+	{
+	    show_text_part_content (part, stream_memory);
+	    part_content = g_mime_stream_mem_get_byte_array (GMIME_STREAM_MEM (stream_memory));
 
-	printf (", \"content\": %s", json_quote_chararray (ctx, (char *) part_content->data, part_content->len));
+	    printf (", \"content\": %s", json_quote_chararray (ctx, (char *) part_content->data, part_content->len));
+	}
     }
     else if (g_mime_content_type_is_type (content_type, "multipart", "*"))
     {
-- 
1.7.7.3