char *subject;
GHashTable *authors_hash;
char *authors;
+ char *nonmatched_authors;
GHashTable *tags;
notmuch_message_list_t *message_list;
thread->authors = talloc_strdup (thread, author);
}
+/*
+ * move authors of matched messages in the thread to
+ * the front of the authors list, but keep them in
+ * existing order within their group
+ */
+static void
+_thread_move_matched_author (notmuch_thread_t *thread,
+ const char *author)
+{
+ char *authors_copy;
+ char *current_author;
+ char *last_pipe,*next_pipe;
+ int idx,nm_start,author_len,authors_len;
+
+ if (thread->authors == NULL || author == NULL)
+ return;
+ if (thread->nonmatched_authors == NULL)
+ thread->nonmatched_authors = thread->authors;
+ author_len = strlen(author);
+ authors_len = strlen(thread->authors);
+ if (author_len == authors_len) {
+ /* just one author */
+ thread->nonmatched_authors += author_len;
+ return;
+ }
+ current_author = strcasestr(thread->authors, author);
+ if (current_author == NULL)
+ return;
+ /* how far inside the nonmatched authors is our author? */
+ idx = current_author - thread->nonmatched_authors;
+ if (idx < 0) {
+ /* already among matched authors */
+ return;
+ }
+ /* are there any authors in the list after our author? */
+ if (thread->nonmatched_authors + author_len < thread->authors + authors_len) {
+ /* we have to make changes, so let's get a temp copy */
+ authors_copy = talloc_strdup(thread,thread->authors);
+ /* nm_start is the offset into where the non-matched authors start */
+ nm_start = thread->nonmatched_authors - thread->authors;
+ /* copy this author and add the "| " - the if clause above tells us there's more */
+ strncpy(thread->nonmatched_authors,author,author_len);
+ strncpy(thread->nonmatched_authors+author_len,"| ",2);
+ thread->nonmatched_authors += author_len+2;
+ if (idx > 0) {
+ /* we are actually moving authors around, not just changing the separator
+ * first copy the authors that came BEFORE our author */
+ strncpy(thread->nonmatched_authors, authors_copy+nm_start, idx-2);
+ /* finally, if there are authors AFTER our author, copy those */
+ if(author_len+nm_start+idx < authors_len) {
+ strncpy(thread->nonmatched_authors + idx - 2,", ",2);
+ strncpy(thread->nonmatched_authors + idx, authors_copy+nm_start + idx + author_len + 2,
+ authors_len - (nm_start + idx + author_len + 2));
+ }
+ }
+ /* finally let's make sure there's just one '|' in the authors string */
+ last_pipe = strchr(thread->authors,'|');
+ while (last_pipe) {
+ next_pipe = strchr(last_pipe+1,'|');
+ if (next_pipe)
+ *last_pipe = ',';
+ last_pipe = next_pipe;
+ }
+ } else {
+ thread->nonmatched_authors += author_len;
+ /* so now all authors are matched - let's remove the '|' */
+ last_pipe = strchr(thread->authors,'|');
+ if (last_pipe)
+ *last_pipe = ',';
+ }
+ return;
+}
+
+/* clean up the uggly "Lastname, Firstname" format that some mail systems
+ * (most notably, Exchange) are creating to be "Firstname Lastname"
+ * To make sure that we don't change other potential situations where a
+ * comma is in the name, we check that we match one of these patterns
+ * "Last, First" <first.last@company.com>
+ * "Last, First MI" <first.mi.last@company.com>
+ */
+char *
+_thread_cleanup_author (notmuch_thread_t *thread,
+ const char *author, const char *from)
+{
+ char *clean_author,*test_author;
+ const char *comma;
+ char *blank;
+ int fname,lname;
+
+ clean_author = talloc_strdup(thread, author);
+ if (clean_author == NULL)
+ return NULL;
+ comma = strchr(author,',');
+ if (comma) {
+ /* let's assemble what we think is the correct name */
+ lname = comma - author;
+ fname = strlen(author) - lname - 2;
+ strncpy(clean_author, comma + 2, fname);
+ *(clean_author+fname) = ' ';
+ strncpy(clean_author + fname + 1, author, lname);
+ *(clean_author+fname+1+lname) = '\0';
+ /* make a temporary copy and see if it matches the email */
+ test_author = talloc_strdup(thread,clean_author);
+
+ blank=strchr(test_author,' ');
+ while (blank != NULL) {
+ *blank = '.';
+ blank=strchr(test_author,' ');
+ }
+ if (strcasestr(from, test_author) == NULL)
+ /* we didn't identify this as part of the email address
+ * so let's punt and return the original author */
+ strcpy (clean_author, author);
+
+ }
+ return clean_author;
+}
+
/* Add 'message' as a message that belongs to 'thread'.
*
* The 'thread' will talloc_steal the 'message' and hold onto a
{
notmuch_tags_t *tags;
const char *tag;
- InternetAddressList *list;
+ InternetAddressList *list = NULL;
InternetAddress *address;
const char *from, *author;
+ char *clean_author;
_notmuch_message_list_add_message (thread->message_list,
talloc_steal (thread, message));
message);
from = notmuch_message_get_header (message, "from");
- list = internet_address_list_parse_string (from);
+ if (from)
+ list = internet_address_list_parse_string (from);
+
if (list) {
address = internet_address_list_get_address (list, 0);
if (address) {
mailbox = INTERNET_ADDRESS_MAILBOX (address);
author = internet_address_mailbox_get_addr (mailbox);
}
- _thread_add_author (thread, author);
+ clean_author = _thread_cleanup_author (thread, author, from);
+ _thread_add_author (thread, clean_author);
+ notmuch_message_set_author (message, clean_author);
}
g_object_unref (G_OBJECT (list));
}
if (! thread->subject) {
const char *subject;
subject = notmuch_message_get_header (message, "subject");
- thread->subject = talloc_strdup (thread, subject);
+ thread->subject = talloc_strdup (thread, subject ? subject : "");
}
for (tags = notmuch_message_get_tags (message);
- notmuch_tags_has_more (tags);
- notmuch_tags_advance (tags))
+ notmuch_tags_valid (tags);
+ notmuch_tags_move_to_next (tags))
{
tag = notmuch_tags_get (tags);
g_hash_table_insert (thread->tags, xstrdup (tag), NULL);
}
}
+static void
+_thread_set_subject_from_message (notmuch_thread_t *thread,
+ notmuch_message_t *message)
+{
+ const char *subject;
+ const char *cleaned_subject;
+
+ subject = notmuch_message_get_header (message, "subject");
+ if (! subject)
+ return;
+
+ if ((strncasecmp (subject, "Re: ", 4) == 0) ||
+ (strncasecmp (subject, "Aw: ", 4) == 0) ||
+ (strncasecmp (subject, "Vs: ", 4) == 0) ||
+ (strncasecmp (subject, "Sv: ", 4) == 0)) {
+
+ cleaned_subject = talloc_strndup (thread,
+ subject + 4,
+ strlen(subject) - 4);
+ } else {
+ cleaned_subject = talloc_strdup (thread, subject);
+ }
+
+ if (thread->subject)
+ talloc_free (thread->subject);
+
+ thread->subject = talloc_strdup (thread, cleaned_subject);
+}
+
static void
_thread_add_matched_message (notmuch_thread_t *thread,
- notmuch_message_t *message)
+ notmuch_message_t *message,
+ notmuch_sort_t sort)
{
time_t date;
+ notmuch_message_t *hashed_message;
date = notmuch_message_get_date (message);
thread->newest = date;
thread->matched_messages++;
+
+ if (g_hash_table_lookup_extended (thread->message_hash,
+ notmuch_message_get_message_id (message), NULL,
+ (void **) &hashed_message)) {
+ notmuch_message_set_flag (hashed_message,
+ NOTMUCH_MESSAGE_FLAG_MATCH, 1);
+ }
+ _thread_move_matched_author (thread,notmuch_message_get_author(hashed_message));
+
+ if ((sort == NOTMUCH_SORT_OLDEST_FIRST && date <= thread->newest) ||
+ (sort != NOTMUCH_SORT_OLDEST_FIRST && date == thread->newest))
+ {
+ _thread_set_subject_from_message (thread, message);
+ }
}
static void
_notmuch_thread_create (void *ctx,
notmuch_database_t *notmuch,
const char *thread_id,
- const char *query_string)
+ const char *query_string,
+ notmuch_sort_t sort)
{
notmuch_thread_t *thread;
- const char *thread_id_query_string, *matched_query_string;
- notmuch_query_t *thread_id_query, *matched_query;
+ const char *thread_id_query_string;
+ notmuch_query_t *thread_id_query;
+
notmuch_messages_t *messages;
notmuch_message_t *message;
+ notmuch_bool_t matched_is_subset_of_thread;
thread_id_query_string = talloc_asprintf (ctx, "thread:%s", thread_id);
if (unlikely (query_string == NULL))
return NULL;
- /* XXX: We could be a bit more efficient here if
- * thread_id_query_string is identical to query_string, (then we
- * could get by with just one database search instead of two). */
-
- matched_query_string = talloc_asprintf (ctx, "%s AND (%s)",
- thread_id_query_string,
- query_string);
- if (unlikely (matched_query_string == NULL))
- return NULL;
+ /* Under normal circumstances we need to do two database
+ * queries. One is for the thread itself (thread_id_query_string)
+ * and the second is to determine which messages in that thread
+ * match the original query (matched_query_string).
+ *
+ * But under two circumstances, we use only the
+ * thread_id_query_string:
+ *
+ * 1. If the original query_string *is* just the thread
+ * specification.
+ *
+ * 2. If the original query_string matches all messages ("" or
+ * "*").
+ *
+ * In either of these cases, we can be more efficient by running
+ * just the thread_id query (since we know all messages in the
+ * thread will match the query_string).
+ *
+ * Beyond the performance advantage, in the second case, it's
+ * important to not try to create a concatenated query because our
+ * parser handles "" and "*" as special cases and will not do the
+ * right thing with a query string of "* and thread:<foo>".
+ **/
+ matched_is_subset_of_thread = 1;
+ if (strcmp (query_string, thread_id_query_string) == 0 ||
+ strcmp (query_string, "") == 0 ||
+ strcmp (query_string, "*") == 0)
+ {
+ matched_is_subset_of_thread = 0;
+ }
thread_id_query = notmuch_query_create (notmuch, thread_id_query_string);
if (unlikely (thread_id_query == NULL))
return NULL;
- matched_query = notmuch_query_create (notmuch, matched_query_string);
- if (unlikely (thread_id_query == NULL))
- return NULL;
-
thread = talloc (ctx, notmuch_thread_t);
if (unlikely (thread == NULL))
return NULL;
thread->authors_hash = g_hash_table_new_full (g_str_hash, g_str_equal,
free, NULL);
thread->authors = NULL;
+ thread->nonmatched_authors = NULL;
thread->tags = g_hash_table_new_full (g_str_hash, g_str_equal,
free, NULL);
notmuch_query_set_sort (thread_id_query, NOTMUCH_SORT_OLDEST_FIRST);
for (messages = notmuch_query_search_messages (thread_id_query);
- notmuch_messages_has_more (messages);
- notmuch_messages_advance (messages))
+ notmuch_messages_valid (messages);
+ notmuch_messages_move_to_next (messages))
{
message = notmuch_messages_get (messages);
+
_thread_add_message (thread, message);
+
+ if (! matched_is_subset_of_thread)
+ _thread_add_matched_message (thread, message, sort);
+
_notmuch_message_close (message);
}
notmuch_query_destroy (thread_id_query);
- for (messages = notmuch_query_search_messages (matched_query);
- notmuch_messages_has_more (messages);
- notmuch_messages_advance (messages))
+ if (matched_is_subset_of_thread)
{
- message = notmuch_messages_get (messages);
- _thread_add_matched_message (thread, message);
- _notmuch_message_close (message);
- }
+ const char *matched_query_string;
+ notmuch_query_t *matched_query;
+
+ matched_query_string = talloc_asprintf (ctx, "%s AND (%s)",
+ thread_id_query_string,
+ query_string);
+ if (unlikely (matched_query_string == NULL))
+ return NULL;
+
+ matched_query = notmuch_query_create (notmuch, matched_query_string);
+ if (unlikely (matched_query == NULL))
+ return NULL;
+
+ for (messages = notmuch_query_search_messages (matched_query);
+ notmuch_messages_valid (messages);
+ notmuch_messages_move_to_next (messages))
+ {
+ message = notmuch_messages_get (messages);
+ _thread_add_matched_message (thread, message, sort);
+ _notmuch_message_close (message);
+ }
- notmuch_query_destroy (matched_query);
+ notmuch_query_destroy (matched_query);
+ }
_resolve_thread_relationships (thread);