X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Findex.cc;h=78c18cf36d10898a8ea3aebcb1c8fe84fcff3df3;hp=80df64bfb73a3edbf2ff9819e99c473c3d41f81b;hb=71521f06b00a01c5b0eaea5f5f624fe57ed7f426;hpb=2ce25b93a72b4a8d6daa5321f9ef7df0772a789f diff --git a/lib/index.cc b/lib/index.cc index 80df64bf..78c18cf3 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; +}; + +static 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. + **/ +static 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; - int own_name = 0; + void *local = talloc_new (message); name = internet_address_get_name (address); addr = internet_address_mailbox_get_addr (mailbox); @@ -42,16 +243,16 @@ _index_address_mailbox (notmuch_message_t *message, const char *at; at = strchr (addr, '@'); - if (at) { - name = strndup (addr, at - addr); - own_name = 1; - } + 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); + + talloc_free (local); } static void @@ -103,95 +304,34 @@ _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) -{ - 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; char *body; + const char *charset; + + if (! part) { + fprintf (stderr, "Warning: Not indexing empty mime part.\n"); + return; + } 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. */ @@ -200,6 +340,10 @@ _index_mime_part (notmuch_message_t *message, if (i > 1) fprintf (stderr, "Warning: Unexpected extra parts of multipart/signed. Indexing anyway.\n"); } + if (GMIME_IS_MULTIPART_ENCRYPTED (multipart)) { + /* Don't index encrypted parts. */ + continue; + } _index_mime_part (message, g_mime_multipart_get_part (multipart, i)); } @@ -240,18 +384,43 @@ _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); + + 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_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 @@ -266,9 +435,12 @@ _notmuch_message_index_file (notmuch_message_t *message, 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); + g_mime_init (GMIME_ENABLE_RFC2047_WORKAROUNDS); initialized = 1; } @@ -279,23 +451,53 @@ _notmuch_message_index_file (notmuch_message_t *message, 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); + 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); + } + } + 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); - 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));