X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Findex.cc;h=10420d84426ca165659cba5118def218d6020cc3;hp=d9612e031101e3f96d1c975bbe161e9b933be95f;hb=4ce7591610444a1c5ef6f56b57af8e180437fa62;hpb=20c15bc820bee78cee62060a4f8cd027aa374f42 diff --git a/lib/index.cc b/lib/index.cc index d9612e03..10420d84 100644 --- a/lib/index.cc +++ b/lib/index.cc @@ -24,6 +24,67 @@ #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 _NotmuchFilterDiscardNonTerm NotmuchFilterDiscardNonTerm; @@ -56,14 +117,17 @@ typedef struct _NotmuchFilterDiscardNonTermClass NotmuchFilterDiscardNonTermClas **/ struct _NotmuchFilterDiscardNonTerm { GMimeFilter parent_object; + GMimeContentType *content_type; int state; + int first_skipping_state; + const scanner_state_t *states; }; 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); @@ -102,8 +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 @@ -111,58 +175,37 @@ filter_filter (GMimeFilter *gmime_filter, char *inbuf, size_t inlen, size_t pres char **outbuf, size_t *outlen, size_t *outprespace) { 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; + } + + } while (next != states[next].state); - if (filter->state < 11) + if (filter->state < filter->first_skipping_state) *outptr++ = *inptr; filter->state = next; @@ -196,7 +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; @@ -219,7 +262,15 @@ notmuch_filter_discard_non_term_new (void) } 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; } @@ -396,7 +447,7 @@ _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_non_term_filter = notmuch_filter_discard_non_term_new (); + 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); @@ -439,7 +490,7 @@ _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, @@ -447,12 +498,10 @@ _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);