[PATCH 1/5] lib: make folder: prefix literal

[Jani Nikula <jani@nikula.org>]

In xapian terms, convert folder: prefix from probabilistic to boolean
prefix. This change constitutes a database change: bump the database
version and add database upgrade support.
---
 lib/database.cc       |  39 ++++++++++++-
 lib/message.cc        | 154 +++++++++++++++++++++++++-------------------------
 lib/notmuch-private.h |   3 +
 3 files changed, 117 insertions(+), 79 deletions(-)

diff --git a/lib/database.cc b/lib/database.cc
index f395061..145fd66 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
@@ -208,7 +208,8 @@ static prefix_t BOOLEAN_PREFIX_EXTERNAL[] = {
     { "thread",			"G" },
     { "tag",			"K" },
     { "is",			"K" },
-    { "id",			"Q" }
+    { "id",			"Q" },
+    { "folder",			"P" },
 };
 
 static prefix_t PROBABILISTIC_PREFIX[]= {
@@ -216,7 +217,6 @@ static prefix_t PROBABILISTIC_PREFIX[]= {
     { "to",			"XTO" },
     { "attachment",		"XATTACHMENT" },
     { "subject",		"XSUBJECT"},
-    { "folder",			"XFOLDER"}
 };
 
 const char *
@@ -1167,6 +1167,39 @@ 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.
+     */
+    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 1b46379..500aa26 100644
--- a/lib/message.cc
+++ b/lib/message.cc
@@ -505,89 +505,27 @@ _notmuch_message_add_filename (notmuch_message_t *message,
     _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_term (message, "folder", directory);
 
     talloc_free (local);
 
     return NOTMUCH_STATUS_SUCCESS;
 }
 
-/* Remove a particular 'filename' from 'message'.
- *
- * This change will not be reflected in the database until the next
- * call to _notmuch_message_sync.
- *
- * If this message still has other filenames, returns
- * NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID.
- *
- * Note: This function does not remove a document from the database,
- * even if the specified filename is the only filename for this
- * message. For that functionality, see
- * _notmuch_database_remove_message. */
-notmuch_status_t
-_notmuch_message_remove_filename (notmuch_message_t *message,
-				  const char *filename)
+static void
+_notmuch_message_remove_terms (notmuch_message_t *message, const char *prefix)
 {
-    const char *direntry_prefix = _find_prefix ("file-direntry");
-    int direntry_prefix_len = strlen (direntry_prefix);
-    const char *folder_prefix = _find_prefix ("folder");
-    int folder_prefix_len = strlen (folder_prefix);
-    void *local = talloc_new (message);
-    char *zfolder_prefix = talloc_asprintf(local, "Z%s", folder_prefix);
-    int zfolder_prefix_len = strlen (zfolder_prefix);
-    char *direntry;
-    notmuch_private_status_t private_status;
-    notmuch_status_t status;
-    Xapian::TermIterator i, last;
-
-    status = _notmuch_database_filename_to_direntry (
-	local, message->notmuch, filename, NOTMUCH_FIND_LOOKUP, &direntry);
-    if (status || !direntry)
-	return status;
+    Xapian::TermIterator i;
+    size_t prefix_len = strlen (prefix);
 
-    /* Unlink this file from its parent directory. */
-    private_status = _notmuch_message_remove_term (message,
-						   "file-direntry", direntry);
-    status = COERCE_STATUS (private_status,
-			    "Unexpected error from _notmuch_message_remove_term");
-    if (status)
-	return status;
-
-    /* Re-synchronize "folder:" terms for this message. This requires:
-     *  1. removing all "folder:" terms
-     *  2. removing all "folder:" stemmed terms
-     *  3. adding back terms for all remaining filenames of the message. */
-
-    /* 1. removing all "folder:" terms */
     while (1) {
 	i = message->doc.termlist_begin ();
-	i.skip_to (folder_prefix);
+	i.skip_to (prefix);
 
 	/* Terminate loop when no terms remain with desired prefix. */
 	if (i == message->doc.termlist_end () ||
-	    strncmp ((*i).c_str (), folder_prefix, folder_prefix_len))
-	{
+	    strncmp ((*i).c_str (), prefix, prefix_len))
 	    break;
-	}
-
-	try {
-	    message->doc.remove_term ((*i));
-	} catch (const Xapian::InvalidArgumentError) {
-	    /* Ignore failure to remove non-existent term. */
-	}
-    }
-
-    /* 2. removing all "folder:" stemmed terms */
-    while (1) {
-	i = message->doc.termlist_begin ();
-	i.skip_to (zfolder_prefix);
-
-	/* Terminate loop when no terms remain with desired prefix. */
-	if (i == message->doc.termlist_end () ||
-	    strncmp ((*i).c_str (), zfolder_prefix, zfolder_prefix_len))
-	{
-	    break;
-	}
 
 	try {
 	    message->doc.remove_term ((*i));
@@ -595,12 +533,18 @@ _notmuch_message_remove_filename (notmuch_message_t *message,
 	    /* Ignore failure to remove non-existent term. */
 	}
     }
+}
 
-    /* 3. adding back terms for all remaining filenames of the message. */
-    i = message->doc.termlist_begin ();
-    i.skip_to (direntry_prefix);
+/* Add "folder:" terms for all filenames of the message. */
+static notmuch_status_t
+_notmuch_message_add_folder_terms (void *ctx, notmuch_message_t *message)
+{
+    const char *direntry_prefix = _find_prefix ("file-direntry");
+    int direntry_prefix_len = strlen (direntry_prefix);
+    Xapian::TermIterator i = message->doc.termlist_begin ();
+    notmuch_status_t status = NOTMUCH_STATUS_SUCCESS;
 
-    for (; i != message->doc.termlist_end (); i++) {
+    for (i.skip_to (direntry_prefix); i != message->doc.termlist_end (); i++) {
 	unsigned int directory_id;
 	const char *direntry, *directory;
 	char *colon;
@@ -620,18 +564,76 @@ _notmuch_message_remove_filename (notmuch_message_t *message,
 	if (colon == NULL || *colon != ':')
 	    INTERNAL_ERROR ("malformed direntry");
 
-	directory = _notmuch_database_get_directory_path (local,
+	directory = _notmuch_database_get_directory_path (ctx,
 							  message->notmuch,
 							  directory_id);
-	if (strlen (directory))
-	    _notmuch_message_gen_terms (message, "folder", directory);
+	_notmuch_message_add_term (message, "folder", directory);
     }
 
+    return status;
+}
+
+/* Remove a particular 'filename' from 'message'.
+ *
+ * This change will not be reflected in the database until the next
+ * call to _notmuch_message_sync.
+ *
+ * If this message still has other filenames, returns
+ * NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID.
+ *
+ * Note: This function does not remove a document from the database,
+ * even if the specified filename is the only filename for this
+ * message. For that functionality, see
+ * _notmuch_database_remove_message. */
+notmuch_status_t
+_notmuch_message_remove_filename (notmuch_message_t *message,
+				  const char *filename)
+{
+    void *local = talloc_new (message);
+    char *direntry;
+    notmuch_private_status_t private_status;
+    notmuch_status_t status;
+
+    status = _notmuch_database_filename_to_direntry (
+	local, message->notmuch, filename, NOTMUCH_FIND_LOOKUP, &direntry);
+    if (status || !direntry)
+	return status;
+
+    /* Unlink this file from its parent directory. */
+    private_status = _notmuch_message_remove_term (message,
+						   "file-direntry", direntry);
+    status = COERCE_STATUS (private_status,
+			    "Unexpected error from _notmuch_message_remove_term");
+    if (status)
+	return status;
+
+    /* Remove all "folder:" terms from the message. */
+    _notmuch_message_remove_terms (message, _find_prefix ("folder"));
+
+    /* Add back "folder:" terms for all remaining filenames of the message. */
+    status = _notmuch_message_add_folder_terms (local, message);
+
     talloc_free (local);
 
     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:" terms. */
+    _notmuch_message_add_folder_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 af185c7..59eb2bc 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);
-- 
1.8.5.2