+
+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;
+typedef struct _NotmuchFilterDiscardNonTermClass NotmuchFilterDiscardNonTermClass;
+
+/**
+ * NotmuchFilterDiscardNonTerm:
+ *
+ * @parent_object: parent #GMimeFilter
+ * @encode: encoding vs decoding
+ * @state: State of the parser
+ *
+ * A filter to discard uuencoded portions of an email.
+ *
+ * A uuencoded portion is identified as beginning with a line
+ * matching:
+ *
+ * begin [0-7][0-7][0-7] .*
+ *
+ * After that detection, and beginning with the following line,
+ * characters will be discarded as long as the first character of each
+ * line begins with M and subsequent characters on the line are within
+ * the range of ASCII characters from ' ' to '`'.
+ *
+ * This is not a perfect UUencode filter. It's possible to have a
+ * message that will legitimately match that pattern, (so that some
+ * legitimate content is discarded). And for most UUencoded files, the
+ * final line of encoded data (the line not starting with M) will be
+ * indexed.
+ **/
+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 (GMimeContentType *content);
+
+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,
+ char **out, size_t *outlen, size_t *outprespace);
+static void filter_complete (GMimeFilter *filter, char *in, size_t len, size_t prespace,
+ char **out, size_t *outlen, size_t *outprespace);
+static void filter_reset (GMimeFilter *filter);
+
+
+static GMimeFilterClass *parent_class = NULL;
+
+static void
+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);
+
+ object_class->finalize = notmuch_filter_discard_non_term_finalize;
+
+ filter_class->copy = filter_copy;
+ filter_class->filter = filter_filter;
+ filter_class->complete = filter_complete;
+ filter_class->reset = filter_reset;
+}
+
+static void
+notmuch_filter_discard_non_term_finalize (GObject *object)
+{
+ G_OBJECT_CLASS (parent_class)->finalize (object);
+}
+
+static GMimeFilter *
+filter_copy (GMimeFilter *gmime_filter)
+{
+ 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)
+{
+ NotmuchFilterDiscardNonTerm *filter = (NotmuchFilterDiscardNonTerm *) gmime_filter;
+ const scanner_state_t *states = filter->states;
+ const char *inptr = inbuf;
+ const char *inend = inbuf + inlen;
+ char *outptr;
+
+ (void) prespace;
+
+ int next;
+
+ g_mime_filter_set_size (gmime_filter, inlen, false);
+ outptr = gmime_filter->outbuf;
+
+ next = filter->state;
+ while (inptr < inend) {
+ /* 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;
+
+ filter->state = next;
+ inptr++;
+ }
+
+ *outlen = outptr - gmime_filter->outbuf;
+ *outprespace = gmime_filter->outpre;
+ *outbuf = gmime_filter->outbuf;
+}
+
+static void
+filter_complete (GMimeFilter *filter, char *inbuf, size_t inlen, size_t prespace,
+ char **outbuf, size_t *outlen, size_t *outprespace)
+{
+ if (inbuf && inlen)
+ filter_filter (filter, inbuf, inlen, prespace, outbuf, outlen, outprespace);
+}
+
+static void
+filter_reset (GMimeFilter *gmime_filter)
+{
+ NotmuchFilterDiscardNonTerm *filter = (NotmuchFilterDiscardNonTerm *) gmime_filter;
+
+ filter->state = 0;
+}
+
+/**
+ * notmuch_filter_discard_non_term_new:
+ *
+ * Returns: a new #NotmuchFilterDiscardNonTerm filter.
+ **/
+static GType type = 0;
+
+static const GTypeInfo info = {
+ .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,
+};
+
+void
+_notmuch_filter_init () {
+ type = g_type_register_static (GMIME_TYPE_FILTER, "NotmuchFilterDiscardNonTerm", &info,
+ (GTypeFlags) 0);
+ parent_class = (GMimeFilterClass *) g_type_class_ref (GMIME_TYPE_FILTER);
+}
+
+static GMimeFilter *
+notmuch_filter_discard_non_term_new (GMimeContentType *content_type)
+{
+ NotmuchFilterDiscardNonTerm *filter;
+
+ filter = (NotmuchFilterDiscardNonTerm *) g_object_new (type, 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;
+}
+