X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Findex.cc;h=0ad683fac51b7704b1f15ee0c6c24b331dcfd02f;hp=125fa6c94f2b6612f6aac3e36dfe518753eaddaf;hb=29648a137c5807135ab168917b4a51d5e19e51c2;hpb=e5316b320a51915fc1dbdd8724643931cd03327f diff --git a/lib/index.cc b/lib/index.cc index 125fa6c9..0ad683fa 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 */ @@ -20,9 +20,261 @@ #include "notmuch-private.h" #include +#include #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; +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) +{ + 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_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; + register 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 GMimeFilter * +notmuch_filter_discard_non_term_new (GMimeContentType *content_type) +{ + static GType type = 0; + NotmuchFilterDiscardNonTerm *filter; + + 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 */ + }; + + type = g_type_register_static (GMIME_TYPE_FILTER, "NotmuchFilterDiscardNonTerm", &info, (GTypeFlags) 0); + } + + 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; +} + /* We're finally down to a single (NAME + address) email "mailbox". */ static void _index_address_mailbox (notmuch_message_t *message, @@ -30,26 +282,22 @@ _index_address_mailbox (notmuch_message_t *message, InternetAddress *address) { InternetAddressMailbox *mailbox = INTERNET_ADDRESS_MAILBOX (address); - const char *name, *addr; - void *local = talloc_new (NULL); + 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); } @@ -103,104 +351,86 @@ _index_address_list (notmuch_message_t *message, } } -static const char * -skip_re_in_subject (const char *subject) -{ - const char *s = subject; - - if (subject == NULL) - return NULL; - - while (*s) { - while (*s && isspace (*s)) - s++; - if (strncasecmp (s, "re:", 3) == 0) - s += 3; - else - break; - } - - 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) +_index_content_type (notmuch_message_t *message, GMimeObject *part) { - 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); + 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); } - 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); } } +static void +_index_encrypted_mime_part (notmuch_message_t *message, notmuch_indexopts_t *indexopts, + GMimeContentType *content_type, + GMimeMultipartEncrypted *part); + /* Callback to generate terms for each mime part of a message. */ static void _index_mime_part (notmuch_message_t *message, + notmuch_indexopts_t *indexopts, GMimeObject *part) { - GMimeStream *stream; + GMimeStream *stream, *filter; + GMimeFilter *discard_non_term_filter; GMimeDataWrapper *wrapper; GByteArray *byte_array; GMimeContentDisposition *disposition; + GMimeContentType *content_type; char *body; + const char *charset; + + if (! part) { + _notmuch_database_log (_notmuch_message_database (message), + "Warning: Not indexing empty mime part.\n"); + return; + } + + _index_content_type (message, part); + content_type = g_mime_object_get_content_type (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"); + + if (GMIME_IS_MULTIPART_ENCRYPTED (multipart)) + _notmuch_message_add_term (message, "tag", "encrypted"); + for (i = 0; i < g_mime_multipart_get_count (multipart); i++) { 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) - fprintf (stderr, "Warning: Unexpected extra parts of multipart/signed. Indexing anyway.\n"); + } else if (i != GMIME_MULTIPART_SIGNED_CONTENT) { + _notmuch_database_log (_notmuch_message_database (message), + "Warning: Unexpected extra parts of multipart/signed. Indexing anyway.\n"); + } + } + if (GMIME_IS_MULTIPART_ENCRYPTED (multipart)) { + _index_content_type (message, + g_mime_multipart_get_part (multipart, i)); + if (i == GMIME_MULTIPART_ENCRYPTED_CONTENT) { + _index_encrypted_mime_part(message, indexopts, + content_type, + GMIME_MULTIPART_ENCRYPTED (part)); + } else { + if (i != GMIME_MULTIPART_ENCRYPTED_VERSION) { + _notmuch_database_log (_notmuch_message_database (message), + "Warning: Unexpected extra parts of multipart/encrypted.\n"); + } + } + continue; } - _index_mime_part (message, + _index_mime_part (message, indexopts, g_mime_multipart_get_part (multipart, i)); } return; @@ -211,20 +441,22 @@ _index_mime_part (notmuch_message_t *message, 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)); return; } 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)); @@ -239,76 +471,160 @@ _index_mime_part (notmuch_message_t *message, 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_stream_filter_add (GMIME_STREAM_FILTER (filter), + discard_non_term_filter); + + charset = g_mime_object_get_content_type_parameter (part, "charset"); + if (charset) { + GMimeFilter *charset_filter; + charset_filter = g_mime_filter_charset_new (charset, "UTF-8"); + /* This result can be NULL for things like "unknown-8bit". + * Don't set a NULL filter as that makes GMime print + * annoying assertion-failure messages on stderr. */ + if (charset_filter) { + g_mime_stream_filter_add (GMIME_STREAM_FILTER (filter), + charset_filter); + g_object_unref (charset_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_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); - _index_body_text (message, body); + if (body) { + _notmuch_message_gen_terms (message, NULL, body); - free (body); + free (body); + } } -notmuch_status_t -_notmuch_message_index_file (notmuch_message_t *message, - const char *filename) +/* 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, + g_mime_3_unused(GMimeContentType *content_type), + GMimeMultipartEncrypted *encrypted_data) { - GMimeStream *stream = NULL; - GMimeParser *parser = NULL; - GMimeMessage *mime_message = NULL; - InternetAddressList *addresses; - FILE *file = NULL; - const char *from, *subject; - notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS; - static int initialized = 0; - - if (! initialized) { - g_mime_init (0); - initialized = 1; - } + notmuch_status_t status; + GError *err = NULL; + notmuch_database_t * notmuch = NULL; + GMimeObject *clear = NULL; - file = fopen (filename, "r"); - if (! file) { - fprintf (stderr, "Error opening %s: %s\n", filename, strerror (errno)); - ret = NOTMUCH_STATUS_FILE_ERROR; - goto DONE; - } + if (!indexopts || (notmuch_indexopts_get_decrypt_policy (indexopts) == NOTMUCH_DECRYPT_FALSE)) + return; - /* Evil GMime steals my FILE* here so I won't fclose it. */ - stream = g_mime_stream_file_new (file); + notmuch = _notmuch_message_database (message); - parser = g_mime_parser_new_with_stream (stream); + GMimeCryptoContext* crypto_ctx = NULL; +#if (GMIME_MAJOR_VERSION < 3) + { + const char *protocol = NULL; + protocol = g_mime_content_type_get_parameter (content_type, "protocol"); + status = _notmuch_crypto_get_gmime_ctx_for_protocol (&(indexopts->crypto), + protocol, &crypto_ctx); + if (status) { + _notmuch_database_log (notmuch, "Warning: setup failed for decrypting " + "during indexing. (%d)\n", status); + 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; + } + } +#endif + bool attempted = false; + GMimeDecryptResult *decrypt_result = NULL; + bool get_sk = (HAVE_GMIME_SESSION_KEYS && notmuch_indexopts_get_decrypt_policy (indexopts) == NOTMUCH_DECRYPT_TRUE); + clear = _notmuch_crypto_decrypt (&attempted, notmuch_indexopts_get_decrypt_policy (indexopts), + message, crypto_ctx, 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) { +#if HAVE_GMIME_SESSION_KEYS + 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); + } +#endif + g_object_unref (decrypt_result); + } + _index_mime_part (message, indexopts, clear); + g_object_unref (clear); - mime_message = g_mime_parser_construct_message (parser); + status = notmuch_message_add_property (message, "index.decryption", "success"); + if (status) + _notmuch_database_log (notmuch, "failed to add index.decryption " + "property (%d)\n", status); - from = g_mime_message_get_sender (mime_message); - addresses = internet_address_list_parse_string (from); +} - _index_address_list (message, "from", addresses); +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 *subject; + notmuch_status_t status; + + status = _notmuch_message_file_get_mime_message (message_file, + &mime_message); + if (status) + return status; + + addresses = g_mime_message_get_from (mime_message); + if (addresses) { + _index_address_list (message, "from", addresses); + g_mime_2_6_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); - subject = skip_re_in_subject (subject); _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); + _index_mime_part (message, indexopts, g_mime_message_get_mime_part (mime_message)); - return ret; + return NOTMUCH_STATUS_SUCCESS; }