lib: make folder: prefix literal

In xapian terms, convert folder: prefix from probabilistic to boolean
prefix, matching the paths, relative from the maildir root, of the
message files, ignoring the maildir new and cur leaf directories.

folder:foo matches all message files in foo, foo/new, and foo/cur.

folder:foo/new does *not* match message files in foo/new.

folder:"" matches all message files in the top level maildir and its
new and cur subdirectories.

This change constitutes a database change: bump the database version
and add database upgrade support for folder: terms. The upgrade also
adds path: terms.

Finally, fix the folder search test for literal folder: search, as
some of the folder: matching capabilities are lost in the
probabilistic to boolean prefix change.

3 files changed, 114 insertions, 13 deletions

diff --git a/lib/database.cc b/lib/database.cc
index 93cc7f57..aef748f7 100644
--- a/lib/database.cc
+++ b/lib/database.cc
@@ -42,7 +42,7 @@ typedef struct {
     const char *prefix;
 } prefix_t;
 
-#define NOTMUCH_DATABASE_VERSION 1
+#define NOTMUCH_DATABASE_VERSION 2
 
 #define STRINGIFY(s) _SUB_STRINGIFY(s)
 #define _SUB_STRINGIFY(s) #s
@@ -210,6 +210,13 @@ static prefix_t BOOLEAN_PREFIX_EXTERNAL[] = {
     { "is",			"K" },
     { "id",			"Q" },
     { "path",			"P" },
+    /*
+     * Without the ":", since this is a multi-letter prefix, Xapian
+     * will add a colon itself if the first letter of the path is
+     * upper-case ASCII. Including the ":" forces there to always be a
+     * colon, which keeps our own logic simpler.
+     */
+    { "folder",			"XFOLDER:" },
 };
 
 static prefix_t PROBABILISTIC_PREFIX[]= {
@@ -217,7 +224,6 @@ static prefix_t PROBABILISTIC_PREFIX[]= {
     { "to",			"XTO" },
     { "attachment",		"XATTACHMENT" },
     { "subject",		"XSUBJECT"},
-    { "folder",			"XFOLDER"}
 };
 
 const char *
@@ -1168,6 +1174,40 @@ notmuch_database_upgrade (notmuch_database_t *notmuch,
 	}
     }
 
+    /*
+     * Prior to version 2, the "folder:" prefix was probabilistic and
+     * stemmed. Change it to the current boolean prefix. Add "path:"
+     * prefixes while at it.
+     */
+    if (version < 2) {
+	notmuch_query_t *query = notmuch_query_create (notmuch, "");
+	notmuch_messages_t *messages;
+	notmuch_message_t *message;
+
+	count = 0;
+	total = notmuch_query_count_messages (query);
+
+	for (messages = notmuch_query_search_messages (query);
+	     notmuch_messages_valid (messages);
+	     notmuch_messages_move_to_next (messages)) {
+	    if (do_progress_notify) {
+		progress_notify (closure, (double) count / total);
+		do_progress_notify = 0;
+	    }
+
+	    message = notmuch_messages_get (messages);
+
+	    _notmuch_message_upgrade_folder (message);
+	    _notmuch_message_sync (message);
+
+	    notmuch_message_destroy (message);
+
+	    count++;
+	}
+
+	notmuch_query_destroy (query);
+    }
+
     db->set_metadata ("version", STRINGIFY (NOTMUCH_DATABASE_VERSION));
     db->flush ();
 
diff --git a/lib/message.cc b/lib/message.cc
index 21abe8e1..9243b769 100644
--- a/lib/message.cc
+++ b/lib/message.cc
@@ -504,6 +504,56 @@ _notmuch_message_remove_terms (notmuch_message_t *message, const char *prefix)
     }
 }
 
+/* Return true if p points at "new" or "cur". */
+static bool is_maildir (const char *p)
+{
+    return strcmp (p, "cur") == 0 || strcmp (p, "new") == 0;
+}
+
+/* Add "folder:" term for directory. */
+static notmuch_status_t
+_notmuch_message_add_folder_terms (notmuch_message_t *message,
+				   const char *directory)
+{
+    char *folder, *last;
+
+    folder = talloc_strdup (NULL, directory);
+    if (! folder)
+	return NOTMUCH_STATUS_OUT_OF_MEMORY;
+
+    /*
+     * If the message file is in a leaf directory named "new" or
+     * "cur", presume maildir and index the parent directory. Thus a
+     * "folder:" prefix search matches messages in the specified
+     * maildir folder, i.e. in the specified directory and its "new"
+     * and "cur" subdirectories.
+     *
+     * Note that this means the "folder:" prefix can't be used for
+     * distinguishing between message files in "new" or "cur". The
+     * "path:" prefix needs to be used for that.
+     *
+     * Note the deliberate difference to _filename_is_in_maildir(). We
+     * don't want to index different things depending on the existence
+     * or non-existence of all maildir sibling directories "new",
+     * "cur", and "tmp". Doing so would be surprising, and difficult
+     * for the user to fix in case all subdirectories were not in
+     * place during indexing.
+     */
+    last = strrchr (folder, '/');
+    if (last) {
+	if (is_maildir (last + 1))
+	    *last = '\0';
+    } else if (is_maildir (folder)) {
+	*folder = '\0';
+    }
+
+    _notmuch_message_add_term (message, "folder", folder);
+
+    talloc_free (folder);
+
+    return NOTMUCH_STATUS_SUCCESS;
+}
+
 #define RECURSIVE_SUFFIX "/**"
 
 /* Add "path:" terms for directory. */
@@ -570,9 +620,8 @@ _notmuch_message_add_directory_terms (void *ctx, notmuch_message_t *message)
 	directory = _notmuch_database_get_directory_path (ctx,
 							  message->notmuch,
 							  directory_id);
-	if (strlen (directory))
-	    _notmuch_message_gen_terms (message, "folder", directory);
 
+	_notmuch_message_add_folder_terms (message, directory);
 	_notmuch_message_add_path_terms (message, directory);
     }
 
@@ -610,9 +659,7 @@ _notmuch_message_add_filename (notmuch_message_t *message,
      * notmuch_directory_get_child_files() . */
     _notmuch_message_add_term (message, "file-direntry", direntry);
 
-    /* New terms allow user to search with folder: specification. */
-    _notmuch_message_gen_terms (message, "folder", directory);
-
+    _notmuch_message_add_folder_terms (message, directory);
     _notmuch_message_add_path_terms (message, directory);
 
     talloc_free (local);
@@ -637,8 +684,6 @@ _notmuch_message_remove_filename (notmuch_message_t *message,
 				  const char *filename)
 {
     void *local = talloc_new (message);
-    const char *folder_prefix = _find_prefix ("folder");
-    char *zfolder_prefix = talloc_asprintf(local, "Z%s", folder_prefix);
     char *direntry;
     notmuch_private_status_t private_status;
     notmuch_status_t status;
@@ -659,10 +704,7 @@ _notmuch_message_remove_filename (notmuch_message_t *message,
     /* Re-synchronize "folder:" and "path:" terms for this message. */
 
     /* Remove all "folder:" terms. */
-    _notmuch_message_remove_terms (message, folder_prefix);
-
-    /* Remove all "folder:" stemmed terms. */
-    _notmuch_message_remove_terms (message, zfolder_prefix);
+    _notmuch_message_remove_terms (message, _find_prefix ("folder"));
 
     /* Remove all "path:" terms. */
     _notmuch_message_remove_terms (message, _find_prefix ("path"));
@@ -675,6 +717,22 @@ _notmuch_message_remove_filename (notmuch_message_t *message,
     return status;
 }
 
+/* Upgrade the "folder:" prefix from V1 to V2. */
+#define FOLDER_PREFIX_V1       "XFOLDER"
+#define ZFOLDER_PREFIX_V1      "Z" FOLDER_PREFIX_V1
+void
+_notmuch_message_upgrade_folder (notmuch_message_t *message)
+{
+    /* Remove all old "folder:" terms. */
+    _notmuch_message_remove_terms (message, FOLDER_PREFIX_V1);
+
+    /* Remove all old "folder:" stemmed terms. */
+    _notmuch_message_remove_terms (message, ZFOLDER_PREFIX_V1);
+
+    /* Add new boolean "folder:" and "path:" terms. */
+    _notmuch_message_add_directory_terms (message, message);
+}
+
 char *
 _notmuch_message_talloc_copy_data (notmuch_message_t *message)
 {
diff --git a/lib/notmuch-private.h b/lib/notmuch-private.h
index af185c7c..59eb2bc2 100644
--- a/lib/notmuch-private.h
+++ b/lib/notmuch-private.h
@@ -263,6 +263,9 @@ _notmuch_message_gen_terms (notmuch_message_t *message,
 void
 _notmuch_message_upgrade_filename_storage (notmuch_message_t *message);
 
+void
+_notmuch_message_upgrade_folder (notmuch_message_t *message);
+
 notmuch_status_t
 _notmuch_message_add_filename (notmuch_message_t *message,
 			       const char *filename);