[notmuch] [PATCH 2/2] Preserve folder information when indexing

[Michal Sojka]

This patch was originally sent by Andreas Klöckner. This is a slightly
reworked version (only coding style changes) which was manually rebased
to the current HEAD.

There are still things to fix (see the previous Carl's email)
- Redundant trailing directory name traversal
- Supporting hierarchical folders
---
 lib/database.cc |   13 +++++++++----
 lib/notmuch.h   |    1 +
 notmuch-new.c   |   38 +++++++++++++++++++++++++++++++++++++-
 3 files changed, 47 insertions(+), 5 deletions(-)

diff --git a/lib/database.cc b/lib/database.cc
index cce7847..5f2f35d 100644
--- a/lib/database.cc
+++ b/lib/database.cc
@@ -84,9 +84,9 @@ typedef struct {
  *	MESSAGE_ID:	The unique ID of the mail mess (see "id" above)
  *
  * In addition, terms from the content of the message are added with
- * "from", "to", "attachment", and "subject" prefixes for use by the
- * user in searching. But the database doesn't really care itself
- * about any of these.
+ * "from", "to", "attachment", "subject" and "folder" prefixes for use
+ * by the user in searching. But the database doesn't really care
+ * itself about any of these.
  *
  * The data portion of a mail document is empty.
  *
@@ -154,7 +154,8 @@ prefix_t PROBABILISTIC_PREFIX[]= {
     { "from",			"XFROM" },
     { "to",			"XTO" },
     { "attachment",		"XATTACHMENT" },
-    { "subject",		"XSUBJECT"}
+    { "subject",		"XSUBJECT"},
+    { "folder", 		"XFOLDER"}
 };
 
 int
@@ -1317,6 +1318,7 @@ _notmuch_database_link_message (notmuch_database_t *notmuch,
 notmuch_status_t
 notmuch_database_add_message (notmuch_database_t *notmuch,
 			      const char *filename,
+			      const char *folder_name,
 			      notmuch_message_t **message_ret)
 {
     notmuch_message_file_t *message_file;
@@ -1432,6 +1434,9 @@ notmuch_database_add_message (notmuch_database_t *notmuch,
 	    date = notmuch_message_file_get_header (message_file, "date");
 	    _notmuch_message_set_date (message, date);
 
+	    if (folder_name != NULL)
+		_notmuch_message_gen_terms (message, "folder", folder_name);
+
 	    _notmuch_message_index_file (message, filename);
 	} else {
 	    ret = NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID;
diff --git a/lib/notmuch.h b/lib/notmuch.h
index 15c9db4..3a5ab78 100644
--- a/lib/notmuch.h
+++ b/lib/notmuch.h
@@ -263,6 +263,7 @@ notmuch_database_get_directory (notmuch_database_t *database,
 notmuch_status_t
 notmuch_database_add_message (notmuch_database_t *database,
 			      const char *filename,
+			      const char *folder_name,
 			      notmuch_message_t **message);
 
 /* Remove a message from the given notmuch database.
diff --git a/notmuch-new.c b/notmuch-new.c
index f25c71f..b7c65db 100644
--- a/notmuch-new.c
+++ b/notmuch-new.c
@@ -21,6 +21,7 @@
 #include "notmuch-client.h"
 
 #include <unistd.h>
+#include <glib.h>
 
 typedef struct _filename_node {
     char *filename;
@@ -169,6 +170,35 @@ _entries_resemble_maildir (struct dirent **entries, int count)
     return 0;
 }
 
+static char*
+_get_folder_base_name(const char *path)
+{
+    gchar *full_folder_name = NULL;
+    gchar *folder_base_name = NULL;
+
+    /* Find name of "folder" containing the email. */
+    full_folder_name = g_strdup(path);
+    while (1) {
+	folder_base_name = g_path_get_basename(full_folder_name);
+
+	if (strcmp(folder_base_name, "cur") == 0
+	    || strcmp(folder_base_name, "new") == 0) {
+	    gchar *parent_name = g_path_get_dirname(full_folder_name);
+	    g_free(full_folder_name);
+	    full_folder_name = parent_name;
+	} else
+	    break;
+    }
+
+    g_free(full_folder_name);
+
+    if (strcmp(folder_base_name, ".") == 0) {
+	g_free(folder_base_name);
+	folder_base_name = NULL;
+    }
+    return folder_base_name;
+}
+
 /* Examine 'path' recursively as follows:
  *
  *   o Ask the filesystem for the mtime of 'path' (fs_mtime)
@@ -222,6 +252,7 @@ add_files_recursive (notmuch_database_t *notmuch,
     notmuch_filenames_t *db_subdirs = NULL;
     struct stat st;
     notmuch_bool_t is_maildir, new_directory;
+    char *folder_base_name = NULL;
 
     if (stat (path, &st)) {
 	fprintf (stderr, "Error reading directory %s: %s\n",
@@ -407,7 +438,10 @@ add_files_recursive (notmuch_database_t *notmuch,
 	    fflush (stdout);
 	}
 
-	status = notmuch_database_add_message (notmuch, next, &message);
+	folder_base_name = _get_folder_base_name(path);
+	status = notmuch_database_add_message (notmuch, next,
+					       folder_base_name,
+					       &message);
 	switch (status) {
 	/* success */
 	case NOTMUCH_STATUS_SUCCESS:
@@ -499,6 +533,8 @@ add_files_recursive (notmuch_database_t *notmuch,
 	notmuch_filenames_destroy (db_files);
     if (directory)
 	notmuch_directory_destroy (directory);
+    if (folder_base_name)
+	g_free(folder_base_name);
 
     return ret;
 }
-- 
1.6.6