X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Findex.cc;h=cf930251c8c7be4c34bb53dab6930cca940d0302;hp=125fa6c94f2b6612f6aac3e36dfe518753eaddaf;hb=2bc0af15aa4cc5b4963e9ff2c2b615ea9ce4ffca;hpb=e5316b320a51915fc1dbdd8724643931cd03327f diff --git a/lib/index.cc b/lib/index.cc index 125fa6c9..cf930251 100644 --- a/lib/index.cc +++ b/lib/index.cc @@ -20,9 +20,210 @@ #include "notmuch-private.h" #include +#include #include +/* 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; + +/** + * NotmuchFilterDiscardUuencode: + * + * @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 _NotmuchFilterDiscardUuencode { + GMimeFilter parent_object; + int state; +}; + +struct _NotmuchFilterDiscardUuencodeClass { + GMimeFilterClass parent_class; +}; + +GMimeFilter *notmuch_filter_discard_uuencode_new (void); + +static void notmuch_filter_discard_uuencode_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_uuencode_class_init (NotmuchFilterDiscardUuencodeClass *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; + + 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_uuencode_finalize (GObject *object) +{ + G_OBJECT_CLASS (parent_class)->finalize (object); +} + +static GMimeFilter * +filter_copy (GMimeFilter *gmime_filter) +{ + (void) gmime_filter; + return notmuch_filter_discard_uuencode_new (); +} + +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; + 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; + + 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; + } + + if (filter->state < 11) + *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) +{ + NotmuchFilterDiscardUuencode *filter = (NotmuchFilterDiscardUuencode *) gmime_filter; + + filter->state = 0; +} + +/** + * notmuch_filter_discard_uuencode_new: + * + * Returns: a new #NotmuchFilterDiscardUuencode filter. + **/ +GMimeFilter * +notmuch_filter_discard_uuencode_new (void) +{ + static GType type = 0; + NotmuchFilterDiscardUuencode *filter; + + if (!type) { + static const GTypeInfo info = { + sizeof (NotmuchFilterDiscardUuencodeClass), + NULL, /* base_class_init */ + NULL, /* base_class_finalize */ + (GClassInitFunc) notmuch_filter_discard_uuencode_class_init, + NULL, /* class_finalize */ + NULL, /* class_data */ + sizeof (NotmuchFilterDiscardUuencode), + 0, /* n_preallocs */ + NULL, /* instance_init */ + NULL /* value_table */ + }; + + type = g_type_register_static (GMIME_TYPE_FILTER, "NotmuchFilterDiscardUuencode", &info, (GTypeFlags) 0); + } + + filter = (NotmuchFilterDiscardUuencode *) g_object_newv (type, 0, NULL); + filter->state = 0; + + return (GMimeFilter *) filter; +} + /* We're finally down to a single (NAME + address) email "mailbox". */ static void _index_address_mailbox (notmuch_message_t *message, @@ -31,7 +232,7 @@ _index_address_mailbox (notmuch_message_t *message, { InternetAddressMailbox *mailbox = INTERNET_ADDRESS_MAILBOX (address); const char *name, *addr; - void *local = talloc_new (NULL); + void *local = talloc_new (message); name = internet_address_get_name (address); addr = internet_address_mailbox_get_addr (mailbox); @@ -123,66 +324,13 @@ skip_re_in_subject (const char *subject) return s; } -/* Given a string representing the body of a message, generate terms - * for it, (skipping quoted portions and signatures). - * - * This function is evil in that it modifies the string passed to it, - * (changing some newlines into '\0'). - */ -static void -_index_body_text (notmuch_message_t *message, char *body) -{ - char *line, *line_end, *next_line; - - if (body == NULL) - return; - - next_line = body; - - while (1) { - line = next_line; - if (*line == '\0') - break; - - next_line = strchr (line, '\n'); - if (next_line == NULL) { - next_line = line + strlen (line); - } - line_end = next_line - 1; - - /* Get to the next non-blank line. */ - while (*next_line == '\n') - next_line++; - - /* Skip blank lines. */ - if (line_end < line) - continue; - - /* Skip lines that are quotes. */ - if (*line == '>') - continue; - - /* Also skip lines introducing a quote on the next line. */ - if (*line_end == ':' && *next_line == '>') - continue; - - /* Finally, bail as soon as we see a signature. */ - /* XXX: Should only do this if "near" the end of the message. */ - if (strncmp (line, "-- ", 3) == 0) - break; - - *(line_end + 1) = '\0'; - - _notmuch_message_gen_terms (message, NULL, line); - } -} - /* Callback to generate terms for each mime part of a message. */ static void _index_mime_part (notmuch_message_t *message, GMimeObject *part) { - GMimeStream *stream; + GMimeStream *stream, *filter; + GMimeFilter *discard_uuencode_filter; GMimeDataWrapper *wrapper; GByteArray *byte_array; GMimeContentDisposition *disposition; @@ -240,18 +388,29 @@ _index_mime_part (notmuch_message_t *message, stream = g_mime_stream_mem_new_with_byte_array (byte_array); 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 (); + + g_mime_stream_filter_add (GMIME_STREAM_FILTER (filter), + discard_uuencode_filter); + wrapper = g_mime_part_get_content_object (GMIME_PART (part)); if (wrapper) - g_mime_data_wrapper_write_to_stream (wrapper, stream); + g_mime_data_wrapper_write_to_stream (wrapper, filter); g_object_unref (stream); + g_object_unref (filter); + g_object_unref (discard_uuencode_filter); g_byte_array_append (byte_array, (guint8 *) "\0", 1); body = (char *) g_byte_array_free (byte_array, FALSE); - _index_body_text (message, body); + if (body) { + _notmuch_message_gen_terms (message, NULL, body); - free (body); + free (body); + } } notmuch_status_t