From: david@tethera.net
To: notmuch@notmuchmail.org
Date: Mon,  7 Dec 2009 23:14:48 -0400
Message-Id: <1260242088-15680-1-git-send-email-david@tethera.net>
In-Reply-To: <1260124225-10830-1-git-send-email-david@tethera.net>
References: <1260124225-10830-1-git-send-email-david@tethera.net>
Cc: David Bremner <bremner@unb.ca>
Subject: [notmuch] [PATCH] notmuch-restore.c: only update tags for messages
	that differ from dump file.
Precedence: list

From: David Bremner <bremner@unb.ca>

The main feature of this patch is that it compares the list of current
tags on a message with those read by restore. Only if the two lists
differ is the tag list in the message replaced.  In my experiments this leads to
a large performance improvement.

Since I had to rewrite the parsing of tags from the dump file anyway
to keep a list of tags (in case they should be written to the
database), I decided to make it a bit more robust. It sorts the
incoming tags (it is critical for the comparison of the two tag lists
that they are both sorted), and allows arbitrary whitespace (as
determined by "isspace") between tags.

The patch allocates a temporary array to keep track of the current
list of tags using calloc and grows it as neccesary using realloc.
---

This is the second version of the patch, the only difference is in the test 
on line 144 (used to be 142), and the comment before explaining it.

 notmuch-restore.c |   75 ++++++++++++++++++++++++++++++++++++++++++++--------
 1 files changed, 63 insertions(+), 12 deletions(-)

diff --git a/notmuch-restore.c b/notmuch-restore.c
index 1b9598d..9d7bd17 100644
--- a/notmuch-restore.c
+++ b/notmuch-restore.c
@@ -18,8 +18,17 @@
  * Author: Carl Worth <cworth@cworth.org>
  */
 
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
 #include "notmuch-client.h"
 
+#define DEFAULT_TAG_ARRAY_SIZE 2
+/* for qsort */
+static int scmp( const void *sp1, const void *sp2 )
+{
+    return( strcmp(*(const char **)sp1, *(const char **)sp2) );
+}
 int
 notmuch_restore_command (unused (void *ctx), int argc, char *argv[])
 {
@@ -31,6 +40,9 @@ notmuch_restore_command (unused (void *ctx), int argc, char *argv[])
     ssize_t line_len;
     regex_t regex;
     int rerr;
+    char **tag_array=NULL;
+    int tag_array_size=DEFAULT_TAG_ARRAY_SIZE;
+
 
     config = notmuch_config_open (ctx, NULL, NULL);
     if (config == NULL)
@@ -61,11 +73,18 @@ notmuch_restore_command (unused (void *ctx), int argc, char *argv[])
 	      "^([^ ]+) \\(([^)]*)\\)$",
 	      REG_EXTENDED);
 
+    /* Make an array of pointers to point to individual tokens */
+    tag_array=calloc(tag_array_size,sizeof(char*));
+
     while ((line_len = getline (&line, &line_size, input)) != -1) {
 	regmatch_t match[3];
-	char *message_id, *tags, *tag, *next;
+	char *message_id, *tags,  *next;
 	notmuch_message_t *message;
 	notmuch_status_t status;
+	int tag_count;
+
+	notmuch_tags_t *tag_list;
+	int i;
 
 	chomp_newline (line);
 
@@ -89,26 +108,55 @@ notmuch_restore_command (unused (void *ctx), int argc, char *argv[])
 	    goto NEXT_LINE;
 	}
 
-	notmuch_message_freeze (message);
+	next=tags;
+	tag_count=0;
+	while(*next){
+	  while(*next && isspace(*next))
+	    next++;
+	  if (*next) {
+	    while (tag_count>= tag_array_size){
+	      tag_array_size*=2;
+	      tag_array=realloc(tag_array,tag_array_size*sizeof(char *));
+	    }
+	    tag_array[tag_count]=next;
+	    tag_count++;
+	  }
+	  while (*next && !isspace(*next))
+	    next++;
+	  if (*next){
+	    *next='\0';
+	    next++;
+	  }
+	}
+
+	qsort(tag_array,tag_count,sizeof(char*),scmp);
+	
+	tag_list = notmuch_message_get_tags (message);
+	i=0;
+	while (notmuch_tags_has_more (tag_list) && i<tag_count &&
+	       (strcmp(notmuch_tags_get (tag_list),tag_array[i])==0)){
+	  notmuch_tags_advance (tag_list);
+	  i++;
+	}
 
-	notmuch_message_remove_all_tags (message);
+	/* the only success condition is for the tag list comparison is to run
+	   off the end of both lists at the same time */
+	if (notmuch_tags_has_more (tag_list) || i<tag_count ){
+	  notmuch_message_freeze (message);
+	  notmuch_message_remove_all_tags (message);
 
-	next = tags;
-	while (next) {
-	    tag = strsep (&next, " ");
-	    if (*tag == '\0')
-		continue;
-	    status = notmuch_message_add_tag (message, tag);
+	  for (i=0; i<tag_count; i++) {
+	    status = notmuch_message_add_tag (message, tag_array[i]);
 	    if (status) {
 		fprintf (stderr,
 			 "Error applying tag %s to message %s:\n",
-			 tag, message_id);
+			 tag_array[i], message_id);
 		fprintf (stderr, "%s\n",
 			 notmuch_status_to_string (status));
 	    }
+	  }
+	  notmuch_message_thaw (message);
 	}
-
-	notmuch_message_thaw (message);
 	notmuch_message_destroy (message);
       NEXT_LINE:
 	free (message_id);
@@ -120,6 +168,9 @@ notmuch_restore_command (unused (void *ctx), int argc, char *argv[])
     if (line)
 	free (line);
 
+    if (tag_array)
+      free (tag_array);
+
     notmuch_database_close (notmuch);
     if (input != stdin)
 	fclose (input);
-- 
1.6.5.3