X-Git-Url: https://git.notmuchmail.org/git?a=blobdiff_plain;f=lib%2Findex.cc;h=e5ae2ba73d568027f1c661994e073aff8852a942;hb=fc12f6f07b5ee6cbcf54a30116fe0a37f8f557cd;hp=19ddc39c25050873829196e6c8876be46751bbd0;hpb=4a085a51376d888185e6719c397832173a4ba159;p=notmuch

diff --git a/lib/index.cc b/lib/index.cc
index 19ddc39c..e5ae2ba7 100644
--- a/lib/index.cc
+++ b/lib/index.cc
@@ -58,6 +58,33 @@ static const scanner_state_t uuencode_states[] = {
     {12, ' ',  '`',  12, 11}
 };
 
+/* The following table is intended to implement this DFA (in 'dot'
+   format). Note that 2 and 3 are "hidden" states used to step through
+   the possible out edges of state 1.
+
+digraph html_filter {
+       0 -> 1  [label="<"];
+       0 -> 0;
+       1 -> 4 [label="'"];
+       1 -> 5 [label="\""];
+       1 -> 0 [label=">"];
+       1 -> 1;
+       4 -> 1 [label="'"];
+       4 -> 4;
+       5 -> 1 [label="\""];
+       5 -> 5;
+}
+*/
+static const int first_html_skipping_state = 1;
+static const scanner_state_t html_states[] = {
+    {0,  '<',  '<',  1,  0},
+    {1,  '\'', '\'', 4,  2},  /* scanning for quote or > */
+    {1,  '"',  '"',  5,  3},
+    {1,  '>',  '>',  0,  1},
+    {4,  '\'', '\'', 1,  4},  /* inside single quotes */
+    {5,  '"', '"',   1,  5},  /* inside double quotes */
+};
+
 /* Oh, how I wish that gobject didn't require so much noisy boilerplate!
  * (Though I have at least eliminated some of the stock set...) */
 typedef struct _NotmuchFilterDiscardNonTerm NotmuchFilterDiscardNonTerm;
@@ -90,6 +117,7 @@ typedef struct _NotmuchFilterDiscardNonTermClass NotmuchFilterDiscardNonTermClas
  **/
 struct _NotmuchFilterDiscardNonTerm {
     GMimeFilter parent_object;
+    GMimeContentType *content_type;
     int state;
     int first_skipping_state;
     const scanner_state_t *states;
@@ -99,7 +127,7 @@ struct _NotmuchFilterDiscardNonTermClass {
     GMimeFilterClass parent_class;
 };
 
-static GMimeFilter *notmuch_filter_discard_non_term_new (void);
+static GMimeFilter *notmuch_filter_discard_non_term_new (GMimeContentType *content);
 
 static void notmuch_filter_discard_non_term_finalize (GObject *object);
 
@@ -138,8 +166,8 @@ notmuch_filter_discard_non_term_finalize (GObject *object)
 static GMimeFilter *
 filter_copy (GMimeFilter *gmime_filter)
 {
-    (void) gmime_filter;
-    return notmuch_filter_discard_non_term_new ();
+    NotmuchFilterDiscardNonTerm *filter = (NotmuchFilterDiscardNonTerm *) gmime_filter;
+    return notmuch_filter_discard_non_term_new (filter->content_type);
 }
 
 static void
@@ -156,19 +184,26 @@ filter_filter (GMimeFilter *gmime_filter, char *inbuf, size_t inlen, size_t pres
 
     int next;
 
-    g_mime_filter_set_size (gmime_filter, inlen, FALSE);
+    g_mime_filter_set_size (gmime_filter, inlen, false);
     outptr = gmime_filter->outbuf;
 
+    next = filter->state;
     while (inptr < inend) {
-	if (*inptr >= states[filter->state].a &&
-	    *inptr <= states[filter->state].b)
-	{
-	    next = states[filter->state].next_if_match;
-	}
-	else
-	{
-	    next = states[filter->state].next_if_not_match;
-	}
+	 /* Each state is defined by a contiguous set of rows of the
+	 * state table marked by a common value for '.state'. The
+	 * state numbers must be equal to the index of the first row
+	 * in a given state; thus the loop condition here looks for a
+	 * jump to a first row of a state, which is a real transition
+	 * in the underlying DFA.
+	 */
+	do {
+	    if (*inptr >= states[next].a && *inptr <= states[next].b)  {
+		next = states[next].next_if_match;
+	    } else  {
+		next = states[next].next_if_not_match;
+	    }
+
+	} while (next != states[next].state);
 
 	if (filter->state < filter->first_skipping_state)
 	    *outptr++ = *inptr;
@@ -204,7 +239,7 @@ filter_reset (GMimeFilter *gmime_filter)
  * Returns: a new #NotmuchFilterDiscardNonTerm filter.
  **/
 static GMimeFilter *
-notmuch_filter_discard_non_term_new (void)
+notmuch_filter_discard_non_term_new (GMimeContentType *content_type)
 {
     static GType type = 0;
     NotmuchFilterDiscardNonTerm *filter;
@@ -226,10 +261,16 @@ notmuch_filter_discard_non_term_new (void)
 	type = g_type_register_static (GMIME_TYPE_FILTER, "NotmuchFilterDiscardNonTerm", &info, (GTypeFlags) 0);
     }
 
-    filter = (NotmuchFilterDiscardNonTerm *) g_object_newv (type, 0, NULL);
+    filter = (NotmuchFilterDiscardNonTerm *) g_object_new (type, NULL);
+    filter->content_type = content_type;
     filter->state = 0;
-    filter->states = uuencode_states;
-    filter->first_skipping_state = first_uuencode_skipping_state;
+    if (g_mime_content_type_is_type (content_type, "text", "html")) {
+      filter->states = html_states;
+      filter->first_skipping_state = first_html_skipping_state;
+    } else {
+      filter->states = uuencode_states;
+      filter->first_skipping_state = first_uuencode_skipping_state;
+    }
 
     return (GMimeFilter *) filter;
 }
@@ -310,6 +351,19 @@ _index_address_list (notmuch_message_t *message,
     }
 }
 
+static void
+_index_content_type (notmuch_message_t *message, GMimeObject *part)
+{
+    GMimeContentType *content_type = g_mime_object_get_content_type (part);
+    if (content_type) {
+	char *mime_string = g_mime_content_type_to_string (content_type);
+	if (mime_string) {
+	    _notmuch_message_gen_terms (message, "mimetype", mime_string);
+	    g_free (mime_string);
+	}
+    }
+}
+
 /* Callback to generate terms for each mime part of a message. */
 static void
 _index_mime_part (notmuch_message_t *message,
@@ -320,6 +374,7 @@ _index_mime_part (notmuch_message_t *message,
     GMimeDataWrapper *wrapper;
     GByteArray *byte_array;
     GMimeContentDisposition *disposition;
+    GMimeContentType *content_type;
     char *body;
     const char *charset;
 
@@ -329,15 +384,7 @@ _index_mime_part (notmuch_message_t *message,
 	return;
     }
 
-    GMimeContentType *content_type = g_mime_object_get_content_type(part);
-    if (content_type) {
-	char *mime_string = g_mime_content_type_to_string(content_type);
-	if (mime_string)
-	{
-	    _notmuch_message_gen_terms (message, "mimetype", mime_string);
-	    g_free(mime_string);
-	}
-    }
+    _index_content_type (message, part);
 
     if (GMIME_IS_MULTIPART (part)) {
 	GMimeMultipart *multipart = GMIME_MULTIPART (part);
@@ -351,15 +398,25 @@ _index_mime_part (notmuch_message_t *message,
 
 	for (i = 0; i < g_mime_multipart_get_count (multipart); i++) {
 	    if (GMIME_IS_MULTIPART_SIGNED (multipart)) {
-		/* Don't index the signature. */
-		if (i == 1)
+		/* Don't index the signature, but index its content type. */
+		if (i == GMIME_MULTIPART_SIGNED_SIGNATURE) {
+		    _index_content_type (message,
+					 g_mime_multipart_get_part (multipart, i));
 		    continue;
-		if (i > 1)
+		} else if (i != GMIME_MULTIPART_SIGNED_CONTENT) {
 		    _notmuch_database_log (_notmuch_message_database (message),
-					  "Warning: Unexpected extra parts of multipart/signed. Indexing anyway.\n");
+					   "Warning: Unexpected extra parts of multipart/signed. Indexing anyway.\n");
+		}
 	    }
 	    if (GMIME_IS_MULTIPART_ENCRYPTED (multipart)) {
-		/* Don't index encrypted parts. */
+		/* Don't index encrypted parts, but index their content type. */
+		_index_content_type (message,
+				     g_mime_multipart_get_part (multipart, i));
+		if ((i != GMIME_MULTIPART_ENCRYPTED_VERSION) &&
+		    (i != GMIME_MULTIPART_ENCRYPTED_CONTENT)) {
+		    _notmuch_database_log (_notmuch_message_database (message),
+					   "Warning: Unexpected extra parts of multipart/encrypted.\n");
+		}
 		continue;
 	    }
 	    _index_mime_part (message,
@@ -403,10 +460,12 @@ _index_mime_part (notmuch_message_t *message,
     byte_array = g_byte_array_new ();
 
     stream = g_mime_stream_mem_new_with_byte_array (byte_array);
-    g_mime_stream_mem_set_owner (GMIME_STREAM_MEM (stream), FALSE);
+    g_mime_stream_mem_set_owner (GMIME_STREAM_MEM (stream), false);
 
     filter = g_mime_stream_filter_new (stream);
-    discard_non_term_filter = notmuch_filter_discard_non_term_new ();
+
+    content_type = g_mime_object_get_content_type (part);
+    discard_non_term_filter = notmuch_filter_discard_non_term_new (content_type);
 
     g_mime_stream_filter_add (GMIME_STREAM_FILTER (filter),
 			      discard_non_term_filter);
@@ -434,7 +493,7 @@ _index_mime_part (notmuch_message_t *message,
     g_object_unref (discard_non_term_filter);
 
     g_byte_array_append (byte_array, (guint8 *) "\0", 1);
-    body = (char *) g_byte_array_free (byte_array, FALSE);
+    body = (char *) g_byte_array_free (byte_array, false);
 
     if (body) {
 	_notmuch_message_gen_terms (message, NULL, body);
@@ -449,7 +508,7 @@ _notmuch_message_index_file (notmuch_message_t *message,
 {
     GMimeMessage *mime_message;
     InternetAddressList *addresses;
-    const char *from, *subject;
+    const char *subject;
     notmuch_status_t status;
 
     status = _notmuch_message_file_get_mime_message (message_file,
@@ -457,12 +516,10 @@ _notmuch_message_index_file (notmuch_message_t *message,
     if (status)
 	return status;
 
-    from = g_mime_message_get_sender (mime_message);
-
-    addresses = internet_address_list_parse_string (from);
+    addresses = g_mime_message_get_from (mime_message);
     if (addresses) {
 	_index_address_list (message, "from", addresses);
-	g_object_unref (addresses);
+	g_mime_2_6_unref (addresses);
     }
 
     addresses = g_mime_message_get_all_recipients (mime_message);