From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eigenstate.org ([206.124.132.107]) by ewsd; Fri Nov 22 13:39:29 EST 2019
Received: from eigenstate.org (localhost [127.0.0.1])
	by eigenstate.org (OpenSMTPD) with ESMTP id 87154cc4;
	Fri, 22 Nov 2019 10:39:26 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha1; c=relaxed; d=eigenstate.org; h=
	message-id:to:subject:date:from:in-reply-to:mime-version
	:content-type:content-transfer-encoding; s=mail; bh=UcQ57rvG5vSQ
	GGJF0wA5zrs0op4=; b=D2StgP8326DTf6eNQIMlYRouEKomItilGeMOlhOzaZfA
	cRrTmasGgEH5VruOoJXC8pyACcGQImsCxwRPrbb3UFDqpdNfi1tuYEb3+0IQPv40
	s/KeEK1Ncvl3ieGDgxOH/rkxDUFFX6+jrelmqkrlfERX02mqczStci4W2VDFw3k=
DomainKey-Signature: a=rsa-sha1; c=nofws; d=eigenstate.org; h=message-id
	:to:subject:date:from:in-reply-to:mime-version:content-type
	:content-transfer-encoding; q=dns; s=mail; b=bewqexej+wdHeSaDWv6
	FsCIB6jubLGdWtFcDDkuxM3mXvBqDienYEgxBdy9KQENr0pm5ANtJcfo5ymi7jYM
	TVRuK6pmQg+IFsleXZPb+DUMLEgfPizTrqXzql+7ppWcWhelKPhHUk9jXurZoVer
	v8X7W7A5YXpHBSma9ZjrB4fs=
Received: from abbatoir.hsd1.ca.comcast.net (c-76-21-119-139.hsd1.ca.comcast.net [76.21.119.139])
	by eigenstate.org (OpenSMTPD) with ESMTPSA id e1659b60 (TLSv1.2:ECDHE-RSA-AES256-SHA:256:NO);
	Fri, 22 Nov 2019 10:39:26 -0800 (PST)
Message-ID: <663176CA83C9DF3BA009A5067FE7C47A@eigenstate.org>
To: cinap_lenrek@felloff.net, 9front@9front.org
Subject: Re: [9front] fix ref822
Date: Fri, 22 Nov 2019 10:39:25 -0800
From: ori@eigenstate.org
In-Reply-To: 4F2E28EFD56B89BE598EA209856361F5@felloff.net
MIME-Version: 1.0
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit
List-ID: <9front.9front.org>
List-Help: <http://lists.9front.org>
X-Glyph: ➈
X-Bullshit: encrypted open-source extension-scale ACPI over SVG cloud storage injection generator 

> i think this is also wrong:
> 
> +	if(i + n > Nref){
> +		for(i = 0; i < n; i++)
> +			free(a[i]);
> +		for(i = n; i < Nref; i++)
> +			a[i - n] = a[i];
>  	}
> 
> i is number of entries in a[], n is number of entries in f[]. if we got
> like i = 1 and n = Nref, we'd want to remove 1 item from a because:
> 
> i + n - Nref == 1 + Nref - Nref == 1
> 
> also, i think the uniqarray() approach is wrong. we probably want to
> deduplicate while we insert into a. we should never populate m->references
> with duplicate items in the first place.
> 
> delete uniquearray() and instead just do it like this:
> 
> a = m->references;
> n = tokenize(f, ....);
> 
> for(i=0; i<n; i++){
> 	for(j=0; j<Nref; j++){
> 		if(a[j] == nil || strcmp(a[j], f[i]) == 0)
> 			break;
> 	}
> 	if(j == Nref){
> 		// handle full case, shift a by one
> 	}
> 
> 	// now a[j] can be: nil = slot free, 
> 	a[j] = f[i];	// put into array
> }
> 
> --
> cinap

Actually, ignore that last message.  Yeah, this is better, though it
has produces marginally different results.

Updated patch:

diff -r 8b2040ba4785 sys/src/cmd/upas/fs/mbox.c
--- a/sys/src/cmd/upas/fs/mbox.c	Fri Nov 22 17:29:35 2019 +1030
+++ b/sys/src/cmd/upas/fs/mbox.c	Fri Nov 22 10:38:48 2019 -0800
@@ -857,25 +857,6 @@
 	return rtrim(strdup(skipwhite(p + h->len)));
 }
 
-/*
- * firefox, e.g. doesn't keep references unique
- */
-static int
-uniqarray(char **a, int n, int allocd)
-{
-	int i, j;
-
-	for(i = 0; i < n; i++)
-		for(j = i + 1; j < n; j++)
-			if(strcmp(a[i], a[j]) == 0){
-				if(allocd)
-					free(a[j]);
-				memmove(a + j, a + j + 1, sizeof *a*(n - (j + 1)));
-				a[--n] = 0;
-			}
-	return n;
-}
-
 static char*
 ref822(Message *m, Header *h, char*, char *p)
 {
@@ -886,26 +867,26 @@
 	n = getfields(s, f, nelem(f), 1, "<> \n\t\r,");
 	if(n > Nref)
 		n = Nref;
-	n = uniqarray(f, n, 0);
 	a = m->references;
 	for(i = 0; i < Nref; i++)
 		if(a[i] == nil)
 			break;
 	/*
 	 * if there are too many references, drop from the beginning
-	 * of the list.
+	 * of the list. If someone else has a duplicate, we keep the
+	 * old duplicate.
 	 */
-	if(i + n > Nref){
-		for(i = 0; i < n; i++)
-			free(a[i]);
-		for(i = n; i < Nref; i++)
-			a[i - n] = a[i];
+	for(i = 0; i < n; i++){
+		for(j = 0; j < Nref; j++)
+			if(a[j] == nil || strcmp(a[j], f[i]) == 0)
+				break;
+		if(j == Nref){
+			free(a[0]);
+			memmove(&a[0], &a[1], (Nref - 1) * sizeof(a[0]));
+			j--;
+		}
+		a[j] = strdup(f[i]);
 	}
-	for(j = 0; j < n;)
-		a[i++] = strdup(f[j++]);
-	n = uniqarray(a, i, 1);
-	if(n < Nref)
-		a[n] = nil;
 	free(s);
 	return (char*)~0;
 }