debian/notmuch
1
0
Fork 0
mirror of https://git.notmuchmail.org/git/notmuch synced 2024-11-25 04:18:08 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

notmuch-index-message: Correctly parse and index encoded mime parts.

Browse source 
This cleans up some old code that was very ugly, (separately opening
the mail file and seeking to the end of the headers to parse the
body). I knew gmime must have had support for transparently decoding
mime content, but I just couldn't find it previously.

Note: Multipart and MultipartSigned parts are not handled yet.

Things are quite happy now. The few differences I see with sup are:

1. sup forces email address domains to lowercase, (I don't think I care)

2. sup and notmuch disagree on ordering of multiple thread_id values
   (another thing that's of no concern)

We are still doing one thing wrong when a message belongs to multiple
threads. We've got a nice comma-separated thread-value just like sup,
but then we're also putting in a comma-separated thread-term where
sup does multiple thread terms. That should be an easy fix.

Beyond that, sup and notmuch are still disagreeing on the term lists
for some messages, (I think attachment vs. inline content-disposition
is at least one piece of this). But there are likley still differences
in the heuristics for which chunks of the message body to index. I'll
be looking into this more.
This commit is contained in:
Carl Worth 2009-10-14 12:48:58 -07:00
parent 9ab2447e89
commit 1c63ec7031
1 changed files with 67 additions and 67 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

134
notmuch-index-message.cc
View file

@ -333,89 +333,90 @@ parse_references (GPtrArray *array,
} }
} }
/* Generate terms for the body of a message, given the filename of the /* Given a string representing the body of a message, generate terms
* message and the offset at which the headers of the message end, * for it, (skipping quoted portions and signatures). */
* (and hence the body begins). */
static void static void
gen_terms_body (Xapian::TermGenerator term_gen, gen_terms_body_str (Xapian::TermGenerator term_gen,
const char * filename, char *body)
gint64 body_offset)
{ {
GIOChannel *channel; char *line, *line_end, *next_line;
GIOStatus gio_status;
GError *error = NULL;
char *p, *body_line = NULL, *prev_line = NULL;
channel = g_io_channel_new_file (filename, "r", &error); if (body == NULL)
if (channel == NULL) { return;
fprintf (stderr, "Error: %s\n", error->message);
exit (1);
}
gio_status = g_io_channel_seek_position (channel, body_offset, next_line = body;
G_SEEK_SET, &error);
if (gio_status != G_IO_STATUS_NORMAL) {
fprintf (stderr, "Error: %s\n", error->message);
exit (1);
}
while (1) { while (1) {
if (body_line) line = next_line;
g_free (body_line); if (*line == '\0')
gio_status = g_io_channel_read_line (channel, &body_line,
NULL, NULL, &error);
if (gio_status == G_IO_STATUS_EOF)
break; break;
if (gio_status != G_IO_STATUS_NORMAL) {
fprintf (stderr, "Error: %s\n", error->message);
exit (1);
}
if (strlen (body_line) == 0) next_line = strchr (line, '\n');
if (next_line == NULL) {
next_line = line + strlen (line);
}
line_end = next_line - 1;
/* Trim whitespace. */
while (*next_line && isspace (*next_line))
next_line++;
/* Skip lines that are quotes. */
if (*line == '>')
continue; continue;
/* If the line looks like it might be introducing a quote, /* Also skip lines introducing a quote on the next line. */
* save it until we see if the next line begins a quote. */ while (line_end > line && isspace (*line_end))
p = body_line + strlen (body_line) - 1; line_end--;
while (p > body_line and isspace (*p))
p--; if (*line_end == ':' && *next_line == '>')
if (*p == ':') {
prev_line = body_line;
body_line = NULL;
continue; continue;
}
/* Skip quoted lines, (and previous lines that introduced them) */ /* Finally, bail as soon as we see a signature. */
if (body_line[0] == '>') {
if (prev_line) {
g_free (prev_line);
prev_line = NULL;
}
continue;
}
/* Now that we're not looking at a quote we can add the prev_line */
if (prev_line) {
gen_terms (term_gen, "body", prev_line);
g_free (prev_line);
prev_line = NULL;
}
/* Skip signatures */
/* XXX: Should only do this if "near" the end of the message. */ /* XXX: Should only do this if "near" the end of the message. */
if (strncmp (body_line, "-- ", 3) == 0 || if (strncmp (line, "-- ", 3) == 0 ||
strncmp (body_line, "----------", 10) == 0 || strncmp (line, "----------", 10) == 0 ||
strncmp (body_line, "__________", 10) == 0) strncmp (line, "__________", 10) == 0)
break; break;
gen_terms (term_gen, "body", body_line); *(line_end + 1) = '\0';
gen_terms (term_gen, "body", line);
}
}
/* Callback to generate terms for each mime part of a message. */
static void
gen_terms_part (GMimeObject *parent,
GMimeObject *part,
gpointer user_data)
{
Xapian::TermGenerator *term_gen = (Xapian::TermGenerator *) user_data;
GMimeStream *stream;
GMimeDataWrapper *wrapper;
GByteArray *byte_array;
char *body;
if (! GMIME_IS_PART (part)) {
fprintf (stderr, "Warning: Not indexing unknown mime part: %s.\n",
g_type_name (G_OBJECT_TYPE (part)));
return;
} }
if (body_line) byte_array = g_byte_array_new ();
g_free (body_line);
g_io_channel_close (channel); stream = g_mime_stream_mem_new_with_byte_array (byte_array);
g_mime_stream_mem_set_owner (GMIME_STREAM_MEM (stream), FALSE);
wrapper = g_mime_part_get_content_object (GMIME_PART (part));
g_mime_data_wrapper_write_to_stream (wrapper, stream);
g_object_unref (stream);
body = (char *) g_byte_array_free (byte_array, FALSE);
gen_terms_body_str (*term_gen, body);
free (body);
} }
static void static void
@ -474,8 +475,7 @@ index_file (Xapian::WritableDatabase db,
gen_terms (term_gen, "subject", subject); gen_terms (term_gen, "subject", subject);
gen_terms (term_gen, "body", subject); gen_terms (term_gen, "body", subject);
gen_terms_body (term_gen, filename, g_mime_message_foreach (message, gen_terms_part, &term_gen);
g_mime_parser_get_headers_end (parser));
parents = g_ptr_array_new (); parents = g_ptr_array_new ();