* which we discard data. */
static const int first_uuencode_skipping_state = 11;
static const scanner_state_t uuencode_states[] = {
- {0, 'b', 'b', 1, 0},
- {1, 'e', 'e', 2, 0},
- {2, 'g', 'g', 3, 0},
- {3, 'i', 'i', 4, 0},
- {4, 'n', 'n', 5, 0},
- {5, ' ', ' ', 6, 0},
- {6, '0', '7', 7, 0},
- {7, '0', '7', 8, 0},
- {8, '0', '7', 9, 0},
- {9, ' ', ' ', 10, 0},
- {10, '\n', '\n', 11, 10},
- {11, 'M', 'M', 12, 0},
- {12, ' ', '`', 12, 11}
+ { 0, 'b', 'b', 1, 0 },
+ { 1, 'e', 'e', 2, 0 },
+ { 2, 'g', 'g', 3, 0 },
+ { 3, 'i', 'i', 4, 0 },
+ { 4, 'n', 'n', 5, 0 },
+ { 5, ' ', ' ', 6, 0 },
+ { 6, '0', '7', 7, 0 },
+ { 7, '0', '7', 8, 0 },
+ { 8, '0', '7', 9, 0 },
+ { 9, ' ', ' ', 10, 0 },
+ { 10, '\n', '\n', 11, 10 },
+ { 11, 'M', 'M', 12, 0 },
+ { 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!
**/
struct _NotmuchFilterDiscardNonTerm {
GMimeFilter parent_object;
+ GMimeContentType *content_type;
int state;
int first_skipping_state;
const scanner_state_t *states;
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);
static GMimeFilterClass *parent_class = NULL;
static void
-notmuch_filter_discard_non_term_class_init (NotmuchFilterDiscardNonTermClass *klass)
+notmuch_filter_discard_non_term_class_init (NotmuchFilterDiscardNonTermClass *klass,
+ unused (void *class_data))
{
GObjectClass *object_class = G_OBJECT_CLASS (klass);
GMimeFilterClass *filter_class = GMIME_FILTER_CLASS (klass);
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
{
NotmuchFilterDiscardNonTerm *filter = (NotmuchFilterDiscardNonTerm *) gmime_filter;
const scanner_state_t *states = filter->states;
- register const char *inptr = inbuf;
+ const char *inptr = inbuf;
const char *inend = inbuf + inlen;
char *outptr;
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;
* 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;
- if (!type) {
+ if (! type) {
static const GTypeInfo info = {
- sizeof (NotmuchFilterDiscardNonTermClass),
- NULL, /* base_class_init */
- NULL, /* base_class_finalize */
- (GClassInitFunc) notmuch_filter_discard_non_term_class_init,
- NULL, /* class_finalize */
- NULL, /* class_data */
- sizeof (NotmuchFilterDiscardNonTerm),
- 0, /* n_preallocs */
- NULL, /* instance_init */
- NULL /* value_table */
+ .class_size = sizeof (NotmuchFilterDiscardNonTermClass),
+ .base_init = NULL,
+ .base_finalize = NULL,
+ .class_init = (GClassInitFunc) notmuch_filter_discard_non_term_class_init,
+ .class_finalize = NULL,
+ .class_data = NULL,
+ .instance_size = sizeof (NotmuchFilterDiscardNonTerm),
+ .n_preallocs = 0,
+ .instance_init = NULL,
+ .value_table = NULL,
};
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;
}
}
}
+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_get_mime_type (content_type);
+ if (mime_string) {
+ _notmuch_message_gen_terms (message, "mimetype", mime_string);
+ g_free (mime_string);
+ }
+ }
+}
+
+static void
+_index_encrypted_mime_part (notmuch_message_t *message, notmuch_indexopts_t *indexopts,
+ GMimeMultipartEncrypted *part,
+ _notmuch_message_crypto_t *msg_crypto);
+
/* Callback to generate terms for each mime part of a message. */
static void
_index_mime_part (notmuch_message_t *message,
- GMimeObject *part)
+ notmuch_indexopts_t *indexopts,
+ GMimeObject *part,
+ _notmuch_message_crypto_t *msg_crypto)
{
GMimeStream *stream, *filter;
GMimeFilter *discard_non_term_filter;
GMimeDataWrapper *wrapper;
GByteArray *byte_array;
GMimeContentDisposition *disposition;
+ GMimeContentType *content_type;
char *body;
const char *charset;
+ GMimeObject *repaired_part = NULL;
if (! part) {
- _notmuch_database_log (_notmuch_message_database (message),
- "Warning: Not indexing empty mime part.\n");
- return;
+ _notmuch_database_log (notmuch_message_get_database (message),
+ "Warning: Not indexing empty mime part.\n");
+ goto DONE;
}
- 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);
- }
+ repaired_part = _notmuch_repair_mixed_up_mangled (part);
+ if (repaired_part) {
+ /* This was likely "Mixed Up" in transit! We will instead use
+ * the more likely-to-be-correct variant. */
+ notmuch_message_add_property (message, "index.repaired", "mixedup");
+ part = repaired_part;
}
+ _index_content_type (message, part);
+
if (GMIME_IS_MULTIPART (part)) {
GMimeMultipart *multipart = GMIME_MULTIPART (part);
int i;
if (GMIME_IS_MULTIPART_SIGNED (multipart))
- _notmuch_message_add_term (message, "tag", "signed");
+ _notmuch_message_add_term (message, "tag", "signed");
if (GMIME_IS_MULTIPART_ENCRYPTED (multipart))
- _notmuch_message_add_term (message, "tag", "encrypted");
+ _notmuch_message_add_term (message, "tag", "encrypted");
for (i = 0; i < g_mime_multipart_get_count (multipart); i++) {
+ GMimeObject *child;
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)
- _notmuch_database_log (_notmuch_message_database (message),
- "Warning: Unexpected extra parts of multipart/signed. Indexing anyway.\n");
+ } else if (i != GMIME_MULTIPART_SIGNED_CONTENT) {
+ _notmuch_database_log (notmuch_message_get_database (message),
+ "Warning: Unexpected extra parts of multipart/signed. Indexing anyway.\n");
+ }
}
if (GMIME_IS_MULTIPART_ENCRYPTED (multipart)) {
- /* Don't index encrypted parts. */
+ _index_content_type (message,
+ g_mime_multipart_get_part (multipart, i));
+ if (i == GMIME_MULTIPART_ENCRYPTED_CONTENT) {
+ _index_encrypted_mime_part (message, indexopts,
+ GMIME_MULTIPART_ENCRYPTED (part),
+ msg_crypto);
+ } else {
+ if (i != GMIME_MULTIPART_ENCRYPTED_VERSION) {
+ _notmuch_database_log (notmuch_message_get_database (message),
+ "Warning: Unexpected extra parts of multipart/encrypted.\n");
+ }
+ }
continue;
}
- _index_mime_part (message,
- g_mime_multipart_get_part (multipart, i));
+ child = g_mime_multipart_get_part (multipart, i);
+ GMimeObject *toindex = child;
+ if (_notmuch_message_crypto_potential_payload (msg_crypto, child, part, i) &&
+ msg_crypto->decryption_status == NOTMUCH_MESSAGE_DECRYPTED_FULL) {
+ toindex = _notmuch_repair_crypto_payload_skip_legacy_display (child);
+ if (toindex != child)
+ notmuch_message_add_property (message, "index.repaired", "skip-protected-headers-legacy-display");
+ }
+ _index_mime_part (message, indexopts, toindex, msg_crypto);
}
- return;
+ goto DONE;
}
if (GMIME_IS_MESSAGE_PART (part)) {
mime_message = g_mime_message_part_get_message (GMIME_MESSAGE_PART (part));
- _index_mime_part (message, g_mime_message_get_mime_part (mime_message));
+ _index_mime_part (message, indexopts, g_mime_message_get_mime_part (mime_message), msg_crypto);
- return;
+ goto DONE;
}
if (! (GMIME_IS_PART (part))) {
- _notmuch_database_log (_notmuch_message_database (message),
- "Warning: Not indexing unknown mime part: %s.\n",
- g_type_name (G_OBJECT_TYPE (part)));
- return;
+ _notmuch_database_log (notmuch_message_get_database (message),
+ "Warning: Not indexing unknown mime part: %s.\n",
+ g_type_name (G_OBJECT_TYPE (part)));
+ goto DONE;
}
disposition = g_mime_object_get_content_disposition (part);
if (disposition &&
strcasecmp (g_mime_content_disposition_get_disposition (disposition),
- GMIME_DISPOSITION_ATTACHMENT) == 0)
- {
+ GMIME_DISPOSITION_ATTACHMENT) == 0) {
const char *filename = g_mime_part_get_filename (GMIME_PART (part));
_notmuch_message_add_term (message, "tag", "attachment");
/* XXX: Would be nice to call out to something here to parse
* the attachment into text and then index that. */
- return;
+ goto DONE;
}
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);
}
}
- wrapper = g_mime_part_get_content_object (GMIME_PART (part));
+ wrapper = g_mime_part_get_content (GMIME_PART (part));
if (wrapper)
g_mime_data_wrapper_write_to_stream (wrapper, filter);
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);
free (body);
}
+ DONE:
+ if (repaired_part)
+ g_object_unref (repaired_part);
+}
+
+/* descend (if desired) into the cleartext part of an encrypted MIME
+ * part while indexing. */
+static void
+_index_encrypted_mime_part (notmuch_message_t *message,
+ notmuch_indexopts_t *indexopts,
+ GMimeMultipartEncrypted *encrypted_data,
+ _notmuch_message_crypto_t *msg_crypto)
+{
+ notmuch_status_t status;
+ GError *err = NULL;
+ notmuch_database_t *notmuch = NULL;
+ GMimeObject *clear = NULL;
+
+ if (! indexopts || (notmuch_indexopts_get_decrypt_policy (indexopts) == NOTMUCH_DECRYPT_FALSE))
+ return;
+
+ notmuch = notmuch_message_get_database (message);
+
+ bool attempted = false;
+ GMimeDecryptResult *decrypt_result = NULL;
+ bool get_sk = (notmuch_indexopts_get_decrypt_policy (indexopts) == NOTMUCH_DECRYPT_TRUE);
+ clear = _notmuch_crypto_decrypt (&attempted, notmuch_indexopts_get_decrypt_policy (indexopts),
+ message, encrypted_data, get_sk ? &decrypt_result : NULL, &err);
+ if (! attempted)
+ return;
+ if (err || ! clear) {
+ if (decrypt_result)
+ g_object_unref (decrypt_result);
+ if (err) {
+ _notmuch_database_log (notmuch, "Failed to decrypt during indexing. (%d:%d) [%s]\n",
+ err->domain, err->code, err->message);
+ g_error_free (err);
+ } else {
+ _notmuch_database_log (notmuch, "Failed to decrypt during indexing. (unknown error)\n");
+ }
+ /* Indicate that we failed to decrypt during indexing */
+ status = notmuch_message_add_property (message, "index.decryption", "failure");
+ if (status)
+ _notmuch_database_log_append (notmuch, "failed to add index.decryption "
+ "property (%d)\n", status);
+ return;
+ }
+ if (decrypt_result) {
+ status = _notmuch_message_crypto_successful_decryption (msg_crypto);
+ if (status)
+ _notmuch_database_log_append (notmuch, "failed to mark the message as decrypted (%s)\n",
+ notmuch_status_to_string (status));
+ if (get_sk) {
+ status = notmuch_message_add_property (message, "session-key",
+ g_mime_decrypt_result_get_session_key (decrypt_result));
+ if (status)
+ _notmuch_database_log (notmuch, "failed to add session-key "
+ "property (%d)\n", status);
+ }
+ g_object_unref (decrypt_result);
+ }
+ GMimeObject *toindex = clear;
+ if (_notmuch_message_crypto_potential_payload (msg_crypto, clear, GMIME_OBJECT (encrypted_data), GMIME_MULTIPART_ENCRYPTED_CONTENT) &&
+ msg_crypto->decryption_status == NOTMUCH_MESSAGE_DECRYPTED_FULL) {
+ toindex = _notmuch_repair_crypto_payload_skip_legacy_display (clear);
+ if (toindex != clear)
+ notmuch_message_add_property (message, "index.repaired", "skip-protected-headers-legacy-display");
+ }
+ _index_mime_part (message, indexopts, toindex, msg_crypto);
+ g_object_unref (clear);
+
+ status = notmuch_message_add_property (message, "index.decryption", "success");
+ if (status)
+ _notmuch_database_log (notmuch, "failed to add index.decryption "
+ "property (%d)\n", status);
+
+}
+
+static notmuch_status_t
+_notmuch_message_index_user_headers (notmuch_message_t *message, GMimeMessage *mime_message)
+{
+
+ notmuch_database_t *notmuch = notmuch_message_get_database (message);
+ notmuch_string_map_iterator_t *iter = _notmuch_database_user_headers (notmuch);
+
+ for (; _notmuch_string_map_iterator_valid (iter);
+ _notmuch_string_map_iterator_move_to_next (iter)) {
+
+ const char *prefix_name = _notmuch_string_map_iterator_key (iter);
+
+ const char *header_name = _notmuch_string_map_iterator_value (iter);
+
+ const char *header = g_mime_object_get_header (GMIME_OBJECT (mime_message), header_name);
+ if (header)
+ _notmuch_message_gen_terms (message, prefix_name, header);
+ }
+
+ if (iter)
+ _notmuch_string_map_iterator_destroy (iter);
+ return NOTMUCH_STATUS_SUCCESS;
+
}
notmuch_status_t
_notmuch_message_index_file (notmuch_message_t *message,
+ notmuch_indexopts_t *indexopts,
notmuch_message_file_t *message_file)
{
GMimeMessage *mime_message;
InternetAddressList *addresses;
- const char *from, *subject;
+ const char *subject;
notmuch_status_t status;
+ _notmuch_message_crypto_t *msg_crypto;
status = _notmuch_message_file_get_mime_message (message_file,
&mime_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);
}
addresses = g_mime_message_get_all_recipients (mime_message);
subject = g_mime_message_get_subject (mime_message);
_notmuch_message_gen_terms (message, "subject", subject);
- _index_mime_part (message, g_mime_message_get_mime_part (mime_message));
+ status = _notmuch_message_index_user_headers (message, mime_message);
+
+ msg_crypto = _notmuch_message_crypto_new (NULL);
+ _index_mime_part (message, indexopts, g_mime_message_get_mime_part (mime_message), msg_crypto);
+ if (msg_crypto && msg_crypto->payload_subject) {
+ _notmuch_message_gen_terms (message, "subject", msg_crypto->payload_subject);
+ _notmuch_message_update_subject (message, msg_crypto->payload_subject);
+ }
+
+ talloc_free (msg_crypto);
return NOTMUCH_STATUS_SUCCESS;
}