X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Findex.cc;h=0c4e232924ce1e139066c02c9f03bb5336f4167d;hp=da0e6cebd7c327ee3fdb35ffdf15110f89ce2fc0;hb=6dd00d64863dfc0563877ca7899231b8c3058c49;hpb=610f0e09929a5f351f7c1c3850ac7e0d83ffe388 diff --git a/lib/index.cc b/lib/index.cc index da0e6ceb..0c4e2329 100644 --- a/lib/index.cc +++ b/lib/index.cc @@ -12,7 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program. If not, see http://www.gnu.org/licenses/ . + * along with this program. If not, see https://www.gnu.org/licenses/ . * * Author: Carl Worth */ @@ -24,13 +24,74 @@ #include + +typedef struct { + int state; + int a; + int b; + int next_if_match; + int next_if_not_match; +} scanner_state_t; + +/* Simple, linear state-transition diagram for the uuencode filter. + * + * If the character being processed is within the range of [a, b] + * for the current state then we transition next_if_match + * state. If not, we transition to the next_if_not_match state. + * + * The final two states are special in that they are the states in + * 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} +}; + +/* 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 _NotmuchFilterDiscardUuencode NotmuchFilterDiscardUuencode; -typedef struct _NotmuchFilterDiscardUuencodeClass NotmuchFilterDiscardUuencodeClass; +typedef struct _NotmuchFilterDiscardNonTerm NotmuchFilterDiscardNonTerm; +typedef struct _NotmuchFilterDiscardNonTermClass NotmuchFilterDiscardNonTermClass; /** - * NotmuchFilterDiscardUuencode: + * NotmuchFilterDiscardNonTerm: * * @parent_object: parent #GMimeFilter * @encode: encoding vs decoding @@ -54,18 +115,21 @@ typedef struct _NotmuchFilterDiscardUuencodeClass NotmuchFilterDiscardUuencodeCl * final line of encoded data (the line not starting with M) will be * indexed. **/ -struct _NotmuchFilterDiscardUuencode { +struct _NotmuchFilterDiscardNonTerm { GMimeFilter parent_object; + GMimeContentType *content_type; int state; + int first_skipping_state; + const scanner_state_t *states; }; -struct _NotmuchFilterDiscardUuencodeClass { +struct _NotmuchFilterDiscardNonTermClass { GMimeFilterClass parent_class; }; -static GMimeFilter *notmuch_filter_discard_uuencode_new (void); +static GMimeFilter *notmuch_filter_discard_non_term_new (GMimeContentType *content); -static void notmuch_filter_discard_uuencode_finalize (GObject *object); +static void notmuch_filter_discard_non_term_finalize (GObject *object); static GMimeFilter *filter_copy (GMimeFilter *filter); static void filter_filter (GMimeFilter *filter, char *in, size_t len, size_t prespace, @@ -78,14 +142,14 @@ static void filter_reset (GMimeFilter *filter); static GMimeFilterClass *parent_class = NULL; static void -notmuch_filter_discard_uuencode_class_init (NotmuchFilterDiscardUuencodeClass *klass) +notmuch_filter_discard_non_term_class_init (NotmuchFilterDiscardNonTermClass *klass) { GObjectClass *object_class = G_OBJECT_CLASS (klass); GMimeFilterClass *filter_class = GMIME_FILTER_CLASS (klass); parent_class = (GMimeFilterClass *) g_type_class_ref (GMIME_TYPE_FILTER); - object_class->finalize = notmuch_filter_discard_uuencode_finalize; + object_class->finalize = notmuch_filter_discard_non_term_finalize; filter_class->copy = filter_copy; filter_class->filter = filter_filter; @@ -94,7 +158,7 @@ notmuch_filter_discard_uuencode_class_init (NotmuchFilterDiscardUuencodeClass *k } static void -notmuch_filter_discard_uuencode_finalize (GObject *object) +notmuch_filter_discard_non_term_finalize (GObject *object) { G_OBJECT_CLASS (parent_class)->finalize (object); } @@ -102,67 +166,46 @@ notmuch_filter_discard_uuencode_finalize (GObject *object) static GMimeFilter * filter_copy (GMimeFilter *gmime_filter) { - (void) gmime_filter; - return notmuch_filter_discard_uuencode_new (); + NotmuchFilterDiscardNonTerm *filter = (NotmuchFilterDiscardNonTerm *) gmime_filter; + return notmuch_filter_discard_non_term_new (filter->content_type); } static void filter_filter (GMimeFilter *gmime_filter, char *inbuf, size_t inlen, size_t prespace, char **outbuf, size_t *outlen, size_t *outprespace) { - NotmuchFilterDiscardUuencode *filter = (NotmuchFilterDiscardUuencode *) gmime_filter; + NotmuchFilterDiscardNonTerm *filter = (NotmuchFilterDiscardNonTerm *) gmime_filter; + const scanner_state_t *states = filter->states; register const char *inptr = inbuf; const char *inend = inbuf + inlen; char *outptr; (void) prespace; - /* Simple, linear state-transition diagram for our filter. - * - * If the character being processed is within the range of [a, b] - * for the current state then we transition next_if_match - * state. If not, we transition to the next_if_not_match state. - * - * The final two states are special in that they are the states in - * which we discard data. */ - static const struct { - int state; - int a; - int b; - int next_if_match; - int next_if_not_match; - } 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} - }; int next; 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; + } - if (filter->state < 11) + } while (next != states[next].state); + + if (filter->state < filter->first_skipping_state) *outptr++ = *inptr; filter->state = next; @@ -185,41 +228,49 @@ filter_complete (GMimeFilter *filter, char *inbuf, size_t inlen, size_t prespace static void filter_reset (GMimeFilter *gmime_filter) { - NotmuchFilterDiscardUuencode *filter = (NotmuchFilterDiscardUuencode *) gmime_filter; + NotmuchFilterDiscardNonTerm *filter = (NotmuchFilterDiscardNonTerm *) gmime_filter; filter->state = 0; } /** - * notmuch_filter_discard_uuencode_new: + * notmuch_filter_discard_non_term_new: * - * Returns: a new #NotmuchFilterDiscardUuencode filter. + * Returns: a new #NotmuchFilterDiscardNonTerm filter. **/ static GMimeFilter * -notmuch_filter_discard_uuencode_new (void) +notmuch_filter_discard_non_term_new (GMimeContentType *content_type) { static GType type = 0; - NotmuchFilterDiscardUuencode *filter; + NotmuchFilterDiscardNonTerm *filter; if (!type) { static const GTypeInfo info = { - sizeof (NotmuchFilterDiscardUuencodeClass), + sizeof (NotmuchFilterDiscardNonTermClass), NULL, /* base_class_init */ NULL, /* base_class_finalize */ - (GClassInitFunc) notmuch_filter_discard_uuencode_class_init, + (GClassInitFunc) notmuch_filter_discard_non_term_class_init, NULL, /* class_finalize */ NULL, /* class_data */ - sizeof (NotmuchFilterDiscardUuencode), + sizeof (NotmuchFilterDiscardNonTerm), 0, /* n_preallocs */ NULL, /* instance_init */ NULL /* value_table */ }; - type = g_type_register_static (GMIME_TYPE_FILTER, "NotmuchFilterDiscardUuencode", &info, (GTypeFlags) 0); + type = g_type_register_static (GMIME_TYPE_FILTER, "NotmuchFilterDiscardNonTerm", &info, (GTypeFlags) 0); } - filter = (NotmuchFilterDiscardUuencode *) g_object_newv (type, 0, NULL); + filter = (NotmuchFilterDiscardNonTerm *) g_object_newv (type, 0, NULL); + filter->content_type = content_type; filter->state = 0; + 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; } @@ -231,26 +282,22 @@ _index_address_mailbox (notmuch_message_t *message, InternetAddress *address) { InternetAddressMailbox *mailbox = INTERNET_ADDRESS_MAILBOX (address); - const char *name, *addr; + const char *name, *addr, *combined; void *local = talloc_new (message); name = internet_address_get_name (address); addr = internet_address_mailbox_get_addr (mailbox); - /* In the absence of a name, we'll strip the part before the @ - * from the address. */ - if (! name) { - const char *at; + /* Combine the name and address and index them as a phrase. */ + if (name && addr) + combined = talloc_asprintf (local, "%s %s", name, addr); + else if (name) + combined = name; + else + combined = addr; - at = strchr (addr, '@'); - if (at) - name = talloc_strndup (local, addr, at - addr); - } - - if (name) - _notmuch_message_gen_terms (message, prefix_name, name); - if (addr) - _notmuch_message_gen_terms (message, prefix_name, addr); + if (combined) + _notmuch_message_gen_terms (message, prefix_name, combined); talloc_free (local); } @@ -310,7 +357,7 @@ _index_mime_part (notmuch_message_t *message, GMimeObject *part) { GMimeStream *stream, *filter; - GMimeFilter *discard_uuencode_filter; + GMimeFilter *discard_non_term_filter; GMimeDataWrapper *wrapper; GByteArray *byte_array; GMimeContentDisposition *disposition; @@ -318,10 +365,21 @@ _index_mime_part (notmuch_message_t *message, const char *charset; if (! part) { - fprintf (stderr, "Warning: Not indexing empty mime part.\n"); + _notmuch_database_log (_notmuch_message_database (message), + "Warning: Not indexing empty mime part.\n"); 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); + } + } + if (GMIME_IS_MULTIPART (part)) { GMimeMultipart *multipart = GMIME_MULTIPART (part); int i; @@ -338,7 +396,8 @@ _index_mime_part (notmuch_message_t *message, if (i == 1) continue; if (i > 1) - fprintf (stderr, "Warning: Unexpected extra parts of multipart/signed. Indexing anyway.\n"); + _notmuch_database_log (_notmuch_message_database (message), + "Warning: Unexpected extra parts of multipart/signed. Indexing anyway.\n"); } if (GMIME_IS_MULTIPART_ENCRYPTED (multipart)) { /* Don't index encrypted parts. */ @@ -361,14 +420,16 @@ _index_mime_part (notmuch_message_t *message, } if (! (GMIME_IS_PART (part))) { - fprintf (stderr, "Warning: Not indexing unknown mime part: %s.\n", - g_type_name (G_OBJECT_TYPE (part))); + _notmuch_database_log (_notmuch_message_database (message), + "Warning: Not indexing unknown mime part: %s.\n", + g_type_name (G_OBJECT_TYPE (part))); return; } disposition = g_mime_object_get_content_disposition (part); if (disposition && - strcmp (disposition->disposition, GMIME_DISPOSITION_ATTACHMENT) == 0) + strcasecmp (g_mime_content_disposition_get_disposition (disposition), + GMIME_DISPOSITION_ATTACHMENT) == 0) { const char *filename = g_mime_part_get_filename (GMIME_PART (part)); @@ -386,10 +447,10 @@ _index_mime_part (notmuch_message_t *message, g_mime_stream_mem_set_owner (GMIME_STREAM_MEM (stream), FALSE); filter = g_mime_stream_filter_new (stream); - discard_uuencode_filter = notmuch_filter_discard_uuencode_new (); + discard_non_term_filter = notmuch_filter_discard_non_term_new (content_type); g_mime_stream_filter_add (GMIME_STREAM_FILTER (filter), - discard_uuencode_filter); + discard_non_term_filter); charset = g_mime_object_get_content_type_parameter (part, "charset"); if (charset) { @@ -411,7 +472,7 @@ _index_mime_part (notmuch_message_t *message, g_object_unref (stream); g_object_unref (filter); - g_object_unref (discard_uuencode_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); @@ -425,86 +486,36 @@ _index_mime_part (notmuch_message_t *message, notmuch_status_t _notmuch_message_index_file (notmuch_message_t *message, - const char *filename) + notmuch_message_file_t *message_file) { - GMimeStream *stream = NULL; - GMimeParser *parser = NULL; - GMimeMessage *mime_message = NULL; + GMimeMessage *mime_message; InternetAddressList *addresses; - FILE *file = NULL; const char *from, *subject; - notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS; - static int initialized = 0; - char from_buf[5]; - bool is_mbox = false; - static bool mbox_warning = false; - - if (! initialized) { - g_mime_init (0); - initialized = 1; - } - - file = fopen (filename, "r"); - if (! file) { - fprintf (stderr, "Error opening %s: %s\n", filename, strerror (errno)); - ret = NOTMUCH_STATUS_FILE_ERROR; - goto DONE; - } - - /* Is this mbox? */ - if (fread (from_buf, sizeof (from_buf), 1, file) == 1 && - strncmp (from_buf, "From ", 5) == 0) - is_mbox = true; - rewind (file); - - /* Evil GMime steals my FILE* here so I won't fclose it. */ - stream = g_mime_stream_file_new (file); - - parser = g_mime_parser_new_with_stream (stream); - g_mime_parser_set_scan_from (parser, is_mbox); - - mime_message = g_mime_parser_construct_message (parser); + notmuch_status_t status; - if (is_mbox) { - if (!g_mime_parser_eos (parser)) { - /* This is a multi-message mbox. */ - ret = NOTMUCH_STATUS_FILE_NOT_EMAIL; - goto DONE; - } - /* For historical reasons, we support single-message mboxes, - * but this behavior is likely to change in the future, so - * warn. */ - if (!mbox_warning) { - mbox_warning = true; - fprintf (stderr, "\ -Warning: %s is an mbox containing a single message,\n\ -likely caused by misconfigured mail delivery. Support for single-message\n\ -mboxes is deprecated and may be removed in the future.\n", filename); - } - } + 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); - _index_address_list (message, "from", addresses); + addresses = internet_address_list_parse_string (from); + if (addresses) { + _index_address_list (message, "from", addresses); + g_object_unref (addresses); + } addresses = g_mime_message_get_all_recipients (mime_message); - _index_address_list (message, "to", addresses); + if (addresses) { + _index_address_list (message, "to", addresses); + g_object_unref (addresses); + } 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)); - DONE: - if (mime_message) - g_object_unref (mime_message); - - if (parser) - g_object_unref (parser); - - if (stream) - g_object_unref (stream); - - return ret; + return NOTMUCH_STATUS_SUCCESS; }