X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Fthread.cc;h=3738baa90978563dcfacc2b62f820402f8790fa1;hp=58d88c2d1597145276a83807165d6939ab340bd2;hb=a4ce6cfbc63c53934c4c06f1b00ffef1c560b3b5;hpb=c1e16435cfe4471c3415d9f625f7230d59c8afb4 diff --git a/lib/thread.cc b/lib/thread.cc index 58d88c2d..3738baa9 100644 --- a/lib/thread.cc +++ b/lib/thread.cc @@ -21,8 +21,6 @@ #include "notmuch-private.h" #include "database-private.h" -#include - #include #include /* GHashTable */ @@ -31,6 +29,9 @@ struct _notmuch_thread { char *thread_id; char *subject; GHashTable *authors_hash; + GPtrArray *authors_array; + GHashTable *matched_authors_hash; + int has_non_matched_authors; char *authors; GHashTable *tags; @@ -46,16 +47,26 @@ static int _notmuch_thread_destructor (notmuch_thread_t *thread) { g_hash_table_unref (thread->authors_hash); + g_hash_table_unref (thread->matched_authors_hash); g_hash_table_unref (thread->tags); g_hash_table_unref (thread->message_hash); + if (thread->authors_array) { + g_ptr_array_free (thread->authors_array, TRUE); + thread->authors_array = NULL; + } + return 0; } +/* Add each author of the thread to the thread's authors_hash and the + * thread's authors_array. */ static void _thread_add_author (notmuch_thread_t *thread, const char *author) { + char *author_copy; + if (author == NULL) return; @@ -63,14 +74,120 @@ _thread_add_author (notmuch_thread_t *thread, author, NULL, NULL)) return; - g_hash_table_insert (thread->authors_hash, xstrdup (author), NULL); + author_copy = talloc_strdup (thread, author); + + g_hash_table_insert (thread->authors_hash, author_copy, NULL); + + g_ptr_array_add (thread->authors_array, author_copy); +} + +/* Add each matched author of the thread to the thread's + * matched_authors_hash and to the thread's authors string. */ +static void +_thread_add_matched_author (notmuch_thread_t *thread, + const char *author) +{ + char *author_copy; + + if (author == NULL) + return; + + if (g_hash_table_lookup_extended (thread->matched_authors_hash, + author, NULL, NULL)) + return; + + author_copy = talloc_strdup (thread, author); + + g_hash_table_insert (thread->matched_authors_hash, author_copy, NULL); if (thread->authors) thread->authors = talloc_asprintf (thread, "%s, %s", thread->authors, author); else - thread->authors = talloc_strdup (thread, author); + thread->authors = author_copy; +} + +/* Copy any authors from the authors array that were not also matched + * authors onto the end of the thread's authors string. + * We use a '|' to separate matched and unmatched authors. */ +static void +_complete_thread_authors (notmuch_thread_t *thread) +{ + unsigned int i; + char *author; + + for (i = 0; i < thread->authors_array->len; i++) { + author = (char *) g_ptr_array_index (thread->authors_array, i); + if (g_hash_table_lookup_extended (thread->matched_authors_hash, + author, NULL, NULL)) + continue; + if (thread->has_non_matched_authors) { + thread->authors = talloc_asprintf (thread, "%s, %s", + thread->authors, + author); + } else { + thread->authors = talloc_asprintf (thread, "%s| %s", + thread->authors, + author); + thread->has_non_matched_authors = 1; + } + } + + g_ptr_array_free (thread->authors_array, TRUE); + thread->authors_array = NULL; +} + +/* clean up the ugly "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" + * "Last, First MI" + */ +static 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; + + if (author == NULL) + return NULL; + clean_author = talloc_strdup(thread, author); + if (clean_author == NULL) + return NULL; + /* check if there's a comma in the name and that there's a + * component of the name behind it (so the name doesn't end with + * the comma - in which case the string that strchr finds is just + * one character long ",\0"). + * Otherwise just return the copy of the original author name that + * we just made*/ + comma = strchr(author,','); + if (comma && strlen(comma) > 1) { + /* 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'. @@ -84,9 +201,10 @@ _thread_add_message (notmuch_thread_t *thread, { 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)); @@ -97,7 +215,9 @@ _thread_add_message (notmuch_thread_t *thread, 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) { @@ -107,7 +227,9 @@ _thread_add_message (notmuch_thread_t *thread, 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)); } @@ -115,33 +237,79 @@ _thread_add_message (notmuch_thread_t *thread, 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); - if (date < thread->oldest || ! thread->matched_messages) + if (date < thread->oldest || ! thread->matched_messages) { thread->oldest = date; + if (sort == NOTMUCH_SORT_OLDEST_FIRST) + _thread_set_subject_from_message (thread, message); + } - if (date > thread->newest || ! thread->matched_messages) + if (date > thread->newest || ! thread->matched_messages) { thread->newest = date; + if (sort != NOTMUCH_SORT_OLDEST_FIRST) + _thread_set_subject_from_message (thread, message); + } 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_add_matched_author (thread, notmuch_message_get_author (hashed_message)); } static void @@ -201,36 +369,56 @@ notmuch_thread_t * _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:". + **/ + 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; @@ -241,8 +429,13 @@ _notmuch_thread_create (void *ctx, thread->thread_id = talloc_strdup (thread, thread_id); thread->subject = NULL; thread->authors_hash = g_hash_table_new_full (g_str_hash, g_str_equal, - free, NULL); + NULL, NULL); + thread->authors_array = g_ptr_array_new (); + thread->matched_authors_hash = g_hash_table_new_full (g_str_hash, + g_str_equal, + NULL, NULL); thread->authors = NULL; + thread->has_non_matched_authors = 0; thread->tags = g_hash_table_new_full (g_str_hash, g_str_equal, free, NULL); @@ -261,26 +454,49 @@ _notmuch_thread_create (void *ctx, 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); + _complete_thread_authors (thread); _resolve_thread_relationships (thread);