little util to scan mailboxes for any and every address they contain.

	* tests/data/getaddr.pl: little util to scan mailboxes for any and
	every address they contain.

	* tests/message/test2.c (main): Added a bunch of stuff to test
	decoding/reencoding/etc of internationalised addresses.

	* tests/message/lib/address-data.h: Copy of some unicode/other
	testing data.  **Beware** of editing this file in emacs, it'll
	probably try and convert all the characters to something
	unusable.

	* tests/lib/camel-test.c (camel_test_break): Add a debugger hook
	point.

	* camel-mime-utils.c (quoted_encode): Check for space and convert
	to _ separately.
	(header_decode_mailbox): Fixed the 'check comments for realname'
	code, problem was the domain getting code was skipping all
	whitespace/comments before we could get a look-in.  This is
	approximate but fairly robust.
	(header_decode_text): Dont use the c-type isspace func here, we
	want a specific whitespace only.
	(header_decode_text): If we have decoded words next to each other,
	do not insert whitespaces between them, which is what rfc2047 requires.
	(header_decode_text): Make c unsigned too.

svn path=/trunk/; revision=6658

7 files changed, 243 insertions, 66 deletions

diff --git a/camel/ChangeLog b/camel/ChangeLog
index b4b3ca8015..8107aa8247 100644
--- a/camel/ChangeLog
+++ b/camel/ChangeLog
@@ -1,5 +1,31 @@
 2000-11-24  Not Zed  <NotZed@HelixCode.com>
 
+	* tests/data/getaddr.pl: little util to scan mailboxes for any and
+	every address they contain.
+
+	* tests/message/test2.c (main): Added a bunch of stuff to test
+	decoding/reencoding/etc of internationalised addresses.
+
+	* tests/message/lib/address-data.h: Copy of some unicode/other
+	testing data.  **Beware** of editing this file in emacs, it'll
+	probably try and convert all the characters to something
+	unusable.
+
+	* tests/lib/camel-test.c (camel_test_break): Add a debugger hook
+	point.
+
+	* camel-mime-utils.c (quoted_encode): Check for space and convert
+	to _ separately.
+	(header_decode_mailbox): Fixed the 'check comments for realname'
+	code, problem was the domain getting code was skipping all
+	whitespace/comments before we could get a look-in.  This is
+	approximate but fairly robust.
+	(header_decode_text): Dont use the c-type isspace func here, we
+	want a specific whitespace only.
+	(header_decode_text): If we have decoded words next to each other,
+	do not insert whitespaces between them, which is what rfc2047 requires.
+	(header_decode_text): Make c unsigned too.
+
 	* tests/README: Added at least some explanation of all this stuff.
 
 	* tests/lib/camel-test.h (check_msg): Added a non-gcc version of
diff --git a/camel/camel-mime-utils.c b/camel/camel-mime-utils.c
index 238b34156e..f1f08e25a0 100644
--- a/camel/camel-mime-utils.c
+++ b/camel/camel-mime-utils.c
@@ -809,9 +809,9 @@ quoted_encode(const unsigned char *in, int len, unsigned char *out, unsigned sho
 	outptr = out;
 	while (inptr < inend) {
 		c = *inptr++;
-		if (camel_mime_special_table[c] & safemask) {
-			if (c==' ')
-				c = '_';
+		if (c==' ') {
+			*outptr++ = '_';
+		} else if (camel_mime_special_table[c] & safemask) {
 			*outptr++ = c;
 		} else {
 			*outptr++ = '=';
@@ -983,15 +983,17 @@ header_decode_text (const char *in, int inlen)
 	GString *out;
 	char *inptr, *inend, *start;
 	char *decoded;
-	
+	unsigned char lastc = 0;
+	int wasdword = FALSE;
+
 	out = g_string_new ("");
 	start = inptr = (char *) in;
 	inend = inptr + inlen;
 	
 	while (inptr && inptr < inend) {
-		char c = *inptr++;
+		unsigned char c = *inptr++;
 		
-		if (isspace (c)) {
+		if (is_lwsp(c)) {
 			char *word, *dword;
 			guint len;
 			
@@ -999,16 +1001,23 @@ header_decode_text (const char *in, int inlen)
 			word = start;
 			
 			dword = rfc2047_decode_word (word, len);
-			
+
 			if (dword) {
+				if (!wasdword && lastc)
+					g_string_append_c(out, lastc);
+					
 				g_string_append (out, dword);
 				g_free (dword);
+				lastc = c;
+				wasdword = TRUE;
 			} else {
+				if (lastc)
+					g_string_append_c(out, lastc);
 				out = append_latin1 (out, word, len);
+				lastc = c;
+				wasdword = FALSE;
 			}
-			
-			g_string_append_c (out, c);
-			
+						
 			start = inptr;
 		}
 	}
@@ -1023,9 +1032,13 @@ header_decode_text (const char *in, int inlen)
 		dword = rfc2047_decode_word (word, len);
 		
 		if (dword) {
+			if (!wasdword && lastc)
+				g_string_append_c(out, lastc);
 			g_string_append (out, dword);
 			g_free (dword);
 		} else {
+			if (lastc)
+				g_string_append_c(out, lastc);
 			out = g_string_append_len (out, word, len);
 		}
 	}
@@ -1797,6 +1810,7 @@ header_decode_mailbox(const char **in)
 	GString *addr;
 	GString *name = NULL;
 	struct _header_address *address = NULL;
+	const char *comment = NULL;
 
 	addr = g_string_new("");
 
@@ -1862,6 +1876,7 @@ header_decode_mailbox(const char **in)
 			addr = g_string_append_c(addr, '.');
 			addr = g_string_append(addr, pre);
 		}
+		comment = inptr;
 		header_decode_lwsp(&inptr);
 	}
 	g_free(pre);
@@ -1872,6 +1887,7 @@ header_decode_mailbox(const char **in)
 
 		inptr++;
 		addr = g_string_append_c(addr, '@');
+		comment = inptr;
 		dom = header_decode_domain(&inptr);
 		addr = g_string_append(addr, dom);
 		g_free(dom);
@@ -1886,17 +1902,33 @@ header_decode_mailbox(const char **in)
 		} else {
 			w(g_warning("invalid route address, no closing '>': %s", *in));
 		} 
-	} else if (name == NULL) { /* check for comment after address */
+	} else if (name == NULL && comment != NULL && inptr>comment) { /* check for comment after address */
 		char *text, *tmp;
-		const char *comment = inptr;
+		const char *comstart, *comend;
 
-		header_decode_lwsp(&inptr);
-		if (inptr-comment > 3) { /* just guess ... */
-			tmp = g_strndup(comment, inptr-comment);
-			text = header_decode_string(tmp);
-			name = g_string_new(text);
-			g_free(tmp);
-			g_free(text);
+		/* this is a bit messy, we go from the last known position, because
+		   decode_domain/etc skip over any comments on the way */
+		/* FIXME: This wont detect comments inside the domain itself,
+		   but nobody seems to use that feature anyway ... */
+
+		d(printf("checking for comment from '%s'\n", comment));
+
+		comstart = strchr(comment, '(');
+		if (comstart) {
+			comstart++;
+			header_decode_lwsp(&inptr);
+			comend = inptr-1;
+			while (comend > comstart && comend[0] != ')')
+				comend--;
+			
+			if (comend > comstart) {
+				d(printf("  looking at subset '%.*s'\n", comend-comstart, comstart));
+				tmp = g_strndup(comstart, comend-comstart);
+				text = header_decode_string(tmp);
+				name = g_string_new(text);
+				g_free(tmp);
+				g_free(text);
+			}
 		}
 	}
 
diff --git a/camel/tests/README b/camel/tests/README
index e9262541b4..2ffcc2dbcc 100644
--- a/camel/tests/README
+++ b/camel/tests/README
@@ -33,6 +33,8 @@ code has known limitations currently that stop it passing, but
 otherwise works for nominal input.
 
 To debug tests, set a breakpoint on camel_test_fail, which will be
-called for any failure, even a non-fatal one.
+called for any failure, even a non-fatal one.  Or set it to
+camel_test_break, which will only be called for fatal errors which are
+to print to the screen.
 
  Michael <notzed@helixcode.com>
diff --git a/camel/tests/data/getaddr.pl b/camel/tests/data/getaddr.pl
new file mode 100755
index 0000000000..74a8a81f74
--- /dev/null
+++ b/camel/tests/data/getaddr.pl
@@ -0,0 +1,32 @@
+#!/usr/bin/perl
+
+# get addresses out of messages
+
+if ($#ARGV < 0) {
+    print "Usage: $0 message(s) mbox(es)\n";
+    exit 1;
+}
+
+foreach $name (@ARGV) {
+    open IN,"<$name";
+    while (<IN>) {
+	if (/^From: (.*)/i
+	    || /^To: (.*)/i
+	    || /^Cc: (.*)/i) {
+	    $base = $1;
+	    while (<IN>) {
+		if (/^\s+(.*)/) {
+		    $base .= " ".$1;
+		} else {
+		    last;
+		}
+	    }
+	    $uniq{$base} = 1;
+	}
+    }
+    close IN;
+}
+
+foreach $key (sort keys %uniq) {
+    print $key."\n";
+}
diff --git a/camel/tests/lib/address-data.h b/camel/tests/lib/address-data.h
new file mode 100644
index 0000000000..acecac596a
--- /dev/null
+++ b/camel/tests/lib/address-data.h
@@ -0,0 +1,93 @@
+/* BE WARY of editing this file with emacs.
+	Otherwise it might be smart and try to re-encode everything, which
+	you really do not want
+*/
+
+static struct _a {
+	int count;
+	char *addr;
+	char *utf8;		/* the utf8 in this table was generated by camel itself.  As a result i'm making the assumption it
+				   was right when it was created.  It also depends on the format of ::format(),. which is likely to
+				   change, to handle other bugs ! */
+} test_address[] = {
+	{ 1, "\"=?ISO-8859-1?Q?David_Guti=E9rrez_Magallanes?=\" <david@iiia.csic.es>", "David Gutiérrez Magallanes <david@iiia.csic.es>" },
+	{ 1, "\"=?iso-8859-1?Q?Jos=E9?= Antonio Milke G.\" <gerencia@ovoplus.com>", "José Antonio Milke G. <gerencia@ovoplus.com>" },
+	{ 1, "\"=?iso-8859-2?Q?Hi-Fi_Internert_market_=3D_1.Virtu=E1ln=ED_Internetov=E9_H?= =?iso-8859-2?Q?i-Fi_Studio?=\" <hifimarket@atlas.cz>", "Hi-Fi Internert market = 1.Virtuální Internetové Hi-Fi Studio <hifimarket@atlas.cz>" },
+	{ 3, "\"James M. Cape\" <jcape@jcinteractive.com>, =?iso-8859-1?Q?Joaqu=EDn_Cuenca_Abela?= <cuenca@ie2.u-psud.fr>, gnome-hackers@nuclecu.unam.mx", "James M. Cape <jcape@jcinteractive.com>, Joaquín Cuenca Abela <cuenca@ie2.u-psud.fr>, gnome-hackers@nuclecu.unam.mx" },
+	{ 1, "=?ISO-8859-1?Q?David_Guti=E9rrez_Magallanes?= <david@iiia.csic.es>", "David Gutiérrez Magallanes <david@iiia.csic.es>" },
+	{ 1, "=?ISO-8859-2?Q?Tomasz_K=B3oczko?= <kloczek@rudy.mif.pg.gda.pl>", "Tomasz Kłoczko <kloczek@rudy.mif.pg.gda.pl>" },
+	{ 1, "=?ISO-8859-2?Q?Vladim=EDr_Solnick=FD?= <vs@utia.cas.cz>", "Vladimír Solnický <vs@utia.cas.cz>" },
+	{ 1, "=?iso-8859-1?Q?=22S=F6rensen=2C_Daniel=22?= <dasar@wmdata.com>", "\"Sörensen, Daniel\" <dasar@wmdata.com>" },
+	{ 1, "=?iso-8859-1?Q?=C1=C2=AAQ=A7=CA?= <dennys@iim.nctu.edu.tw>", "ÁªQ§Ê <dennys@iim.nctu.edu.tw>" },
+	{ 1, "=?iso-8859-1?Q?=C1=C2=AAQ=A7=CA?= <dennys@news.iim.nctu.edu.tw>", "ÁªQ§Ê <dennys@news.iim.nctu.edu.tw>" },
+	{ 1, "=?iso-8859-1?Q?=C1kos?= Valentinyi <A.Valentinyi@soton.ac.uk>", "Ákos Valentinyi <A.Valentinyi@soton.ac.uk>" },
+	{ 1, "=?iso-8859-1?Q?Joaqu=EDn?= Cuenca Abela <cuenca@ie2.u-psud.fr>", "Joaquín Cuenca Abela <cuenca@ie2.u-psud.fr>" },
+	{ 2, "=?iso-8859-1?Q?Joaqu=EDn?= Cuenca Abela <cuenca@ie2.u-psud.fr>, gnome-hackers@nuclecu.unam.mx", "Joaquín Cuenca Abela <cuenca@ie2.u-psud.fr>, gnome-hackers@nuclecu.unam.mx" },
+	{ 1, "=?iso-8859-1?Q?Joaqu=EDn_Cuenca_Abela?= <cuenca@celium.net>", "Joaquín Cuenca Abela <cuenca@celium.net>" },
+	{ 1, "=?iso-8859-1?Q?Juantom=E1s=20Garc=EDa?= <juantomas@lared.es>", "Juantomás García <juantomas@lared.es>" },
+	{ 1, "=?iso-8859-1?Q?Kenneth_ll=E9phaane_Christiansen?= <kenneth@ripen.dk>", "Kenneth lléphaane Christiansen <kenneth@ripen.dk>" },
+	{ 1, "=?iso-8859-1?Q?Kjell_Tage_=D8hman?= <tage@ohman.no>", "Kjell Tage Øhman <tage@ohman.no>" },
+	{ 1, "=?iso-8859-1?Q?Martin_Norb=E4ck?= <d95mback@dtek.chalmers.se>", "Martin Norbäck <d95mback@dtek.chalmers.se>" },
+	{ 1, "=?iso-8859-1?Q?P=E5llen?= <pollen@astrakan.hig.se>", "Pållen <pollen@astrakan.hig.se>" },
+	{ 1, "=?iso-8859-1?Q?Ville_P=E4tsi?= <drc@gnu.org>", "Ville Pätsi <drc@gnu.org>" },
+	{ 1, "=?iso-8859-1?q?Joaqu=EDn?= Cuenca Abela <cuenca@celium.net>", "Joaquín Cuenca Abela <cuenca@celium.net>" },
+	{ 1, "=?iso-8859-2?Q?Dra=BEen_Ka=E8ar?= <dave@srce.hr>", "Dražen Kačar <dave@srce.hr>" },
+        /* yep this is right, this isn't valid so doesn't decode at all */
+	{ 1, "=?windows-1250?Q? \"Jaka Mo=E8nik\" ?= <jaka.mocnik@kiss.uni-lj.si>", "=?windows-1250?Q? Jaka Mo=E8nik ?= <jaka.mocnik@kiss.uni-lj.si>" },
+	{ 3, "George <jirka@5z.com>, Juantomas =?ISO-8859-1?Q?Garc=C3=83=C2=ADa?= <juantomas@lared.es>, gnome-hackers@gnome.org", "George <jirka@5z.com>, Juantomas García <juantomas@lared.es>, gnome-hackers@gnome.org" },
+	{ 7, "Jon Trowbridge <trow@emccta.com>, gnome-1.4-list@gnome.org, gnome-devel-list@gnome.org, gnome-hackers@gnome.org, Dom Lachowicz <cinamod@hotmail.com>, =?iso-8859-1?Q?Joaqu=EDn_Cuenca_Abela?= <cuenca@celium.net>, sam th <sam@uchicago.edu>", "Jon Trowbridge <trow@emccta.com>, gnome-1.4-list@gnome.org, gnome-devel-list@gnome.org, gnome-hackers@gnome.org, Dom Lachowicz <cinamod@hotmail.com>, Joaquín Cuenca Abela <cuenca@celium.net>, sam th <sam@uchicago.edu>" },
+	{ 6, "Jon Trowbridge <trow@emccta.com>, gnome-1.4-list@gnome.org, gnome-devel-list@gnome.org, gnome-hackers@gnome.org, Dom Lachowicz <cinamod@hotmail.com>, =?iso-8859-1?Q?Joaqu=EDn_Cuenca_Abela?= <cuenca@ie2.u-psud.fr>", "Jon Trowbridge <trow@emccta.com>, gnome-1.4-list@gnome.org, gnome-devel-list@gnome.org, gnome-hackers@gnome.org, Dom Lachowicz <cinamod@hotmail.com>, Joaquín Cuenca Abela <cuenca@ie2.u-psud.fr>" },
+	{ 1, "Kai =?iso-8859-1?Q?Gro=DFjohann?= <Kai.Grossjohann@CS.Uni-Dortmund.DE>", "Kai Großjohann <Kai.Grossjohann@CS.Uni-Dortmund.DE>" },
+	{ 1, "Kai.Grossjohann@CS.Uni-Dortmund.DE (Kai =?iso-8859-1?q?Gro=DFjohann?=)", "Kai Großjohann <Kai.Grossjohann@CS.Uni-Dortmund.DE>" },
+	{ 1, "Rickard =?iso-8859-1?Q?Nordstr=F6m?= <rzi@ebox.tninet.se>", "Rickard Nordström <rzi@ebox.tninet.se>" },
+	{ 1, "Tomasz =?iso-8859-2?q?K=B3oczko?= <kloczek@rudy.mif.pg.gda.pl>", "Tomasz Kłoczko <kloczek@rudy.mif.pg.gda.pl>" },
+	{ 1, "VALCKE =?iso-8859-1?Q?C=E9dric?= <cvalcke@freesurf.fr>", "VALCKE Cédric <cvalcke@freesurf.fr>" },
+	{ 1, "Ville =?iso-8859-1?q?P=E4tsi?= <drc@gnu.org>", "Ville Pätsi <drc@gnu.org>" },
+	{ 1, "david@iiia.csic.es (=?ISO-8859-1?Q?David_Guti=E9rrez_Magallanes?=)", "David Gutiérrez Magallanes <david@iiia.csic.es>" },
+	{ 1, "kloczek@rudy.mif.pg.gda.pl (=?ISO-8859-2?Q?Tomasz_K=B3oczko?=)", "Tomasz Kłoczko <kloczek@rudy.mif.pg.gda.pl>" },
+	{ 1, "lassehp@imv.aau.dk (Lasse =?ISO-8859-1?Q?Hiller=F8e?= Petersen)", "Lasse Hillerøe Petersen <lassehp@imv.aau.dk>" },
+	{ 1, "ysato@etl.go.jp (Yutaka Sato =?ISO-2022-JP?B?GyRAOjRGI0stGyhK?=)", "Yutaka Sato 佐藤豊 <ysato@etl.go.jp>" },
+};
+
+static struct _l {
+    char *type;
+    char *line;
+} test_lines[] = {
+	/* commented out unsupported charsets - FIXME: camel should somehow handle this, although it can't really of course */
+	/*{ "windows-1251", "���� ����� �� �������� �� ������ �� �����.\n�� �� �������� �� ��� �� �������?" },*/
+	{ "iso-8859-1", "Omple les miniatures de la finestra amb contingut de la pantalla" },
+	{ "ISO-8859-2", "Spr�vce oken h�be s okrajem okna\n(AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
+	{ "ISO-8859-1", "Vinduesh�ndtering flytter dekorationsvindue istedet\n(AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
+	{ "ISO-8859-1", "Vorschaubilder der Fenster mit dem Bildschirminhalt ausf�llen" },
+	{ "iso-8859-7", "�������� �������� ��� �� ��������� ��� ����� ��������� (���������-��������������)" },
+	{ "iso-8859-1", "You've chosen to disable the startup hint.\nTo re-enable it, choose \"Startup Hint\"\nin the GNOME Control Centre" },
+	{ "iso-8859-1", "El aplique de reloj muestra en su panel la fecha y la hora de forma simple \ny ligero " },
+	{ "iso-8859-1", "Applet ei vasta salvestusk�sule.\nKas peaks ta niisama sulgema, v�i veel ootama?" },
+	{ "iso-8859-1", "Lehio kudeatzaileak lehioaren dekorazaioa mugiarazten\n(AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
+	{ "iso-8859-15", "N�yt� sovellukset, joiden ikkunoista on n�kyvill� vain otsikkopalkki" },
+	{ "ISO-8859-1", "Afficher les t�ches qui ne sont pas dans la liste des fen�tres" },
+	{ "iso-8859-1", "N�l applet ag tabhair freagra ar iarratas s�bh�il.\nBain amach an applet n� lean ar f�nacht?" },
+	{ "iso-8859-1", "Amosa-las tarefas agochadas da lista de fiestras (SKIP-WINLIST)" },
+	{ "iso-8859-2", "Az ablakkezel� a dekor�ci�t mozgassa az ablak helyett\n(AfterStep, Enlightenment, FVWM, IceWM, SawMill)" },
+	{ "iso-8859-1", "Riempi la finestra delle anteprime con il contenuto dello schermo" },
+	{ "euc-jp", "������ɥ��ޥ͡�����Ͼ��ꥦ����ɥ���ư����\n(AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
+	{ "euc-kr", "â �����ڰ� �ٹ� â ��� �̵�\n(AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
+	{ "iso-8859-13", "Priedas neatsakin�ja � pra�ym� i�sisaugoti.\nPa�alinti pried� ar laukti toliau?" },
+	{ "iso-8859-1", "Window manager verplaatst dekoratie\n(AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
+	{ "iso-8859-1", "Vindush�ndtereren flytter dekorasjonsvinduet i stedet\n(AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
+	{ "iso-8859-2", "Przemieszczanie dekoracji zamiast okna\n(AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
+	{ "iso-8859-1", "Este programa � respons�vel por executar outras aplica��es, embeber pequenos applets, a paz no mundo e crashes aleat�rios do X." },
+	{ "iso-8859-1", "Mostrar tarefas que se escondem da lista de janelas (SKIP-WINLIST)" },
+	{ "koi8-r", "������ �������� ����� � ������������� ��������� � ������� ������" },
+	{ "iso-8859-2", "Spr�vca okien pres�va okraje okien\n(AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
+	{ "iso-8859-2", "Ka�i posle, ki se skrivajo pred upravljalnik oken (SKIP-WINLIST)" },
+	{ "iso-8859-5", "Window ��������� ������ ����������� ������ ������ ���a\n(AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
+	{ "iso-8859-2", "Window menadzeri pomera dekoracioni prozor umesto toga\n(AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
+	{ "iso-8859-1", "F�nsterhanteraren flyttar dekorationsf�nstret ist�llet\n(AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
+	/*{ "TSCII", "���츼�-���� ���� ��¡� ���츼���� ���� (���츼�-���-�Ţ�)" },*/
+	{ "iso-8859-9", "Kaydetme iste�ine bir uygulak cevap vermiyor .\nUygula�� sileyim mi , yoksa bekleyeyim mi ?" },
+	{ "koi8-u", "����ͦ����� ������æ� ��ͦ��� צ���\n(AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
+	{ "iso-8859-1", "Cwand on scrift�r est bodj� fo�, li scrift�r �t totes\nles apliketes � dvins sont pierdowes. Bodj� ci scrift�r chal?" },
+	{ "gb2312", "Ǩ�Ƶ�װ�δ��ڹ�������(AfterStep, Enlightenment, FVWM, IceWM, SawMill)" },
+	{ "big5", "�����޲z�̥u���ʸ˹�����\n(AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
+};
diff --git a/camel/tests/lib/camel-test.c b/camel/tests/lib/camel-test.c
index a913ad78a4..6a1e00addb 100644
--- a/camel/tests/lib/camel-test.c
+++ b/camel/tests/lib/camel-test.c
@@ -116,6 +116,11 @@ void camel_test_pull(void)
 	g_free(node);
 }
 
+/* where to set breakpoints */
+void camel_test_break(void)
+{
+}
+
 void camel_test_fail(const char *why, ...)
 {
 	va_list ap;
@@ -135,6 +140,7 @@ void camel_test_failv(const char *why, va_list ap)
 	if ((nonfatal == NULL && camel_test_verbose > 0)
 	    || (nonfatal && camel_test_verbose > 1)) {
 		printf("Failed.\n%s\n", text);
+		camel_test_break();
 	}
 
 	g_free(text);
diff --git a/camel/tests/message/test2.c b/camel/tests/message/test2.c
index 8a3fe3c250..00bd6aabf2 100644
--- a/camel/tests/message/test2.c
+++ b/camel/tests/message/test2.c
@@ -11,51 +11,7 @@
 #include <camel/camel-internet-address.h>
 #include <camel/camel-address.h>
 
-/* a bunch of test strings in different encodings, just taken from gnome-core po files */
-/* see data/genline.pl */
-struct _l {
-    char *type;
-    char *line;
-} test_lines[] = {
-	/* FIXME: for now, remove the types libunicode doesn't know about, this is tricky to fix */
-	/* And at best, all we could do is translate it to X-Unknown, or something */
-	/*{ "windows-1251", "���� ����� �� �������� �� ������ �� �����.\n�� �� �������� �� ��� �� �������?" },*/
-	{ "iso-8859-1", "Omple les miniatures de la finestra amb contingut de la pantalla" },
-	{ "ISO-8859-2", "Spr�vce oken h�be s okrajem okna (AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
-	{ "ISO-8859-1", "Vinduesh�ndtering flytter dekorationsvindue istedet (AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
-	{ "ISO-8859-1", "Vorschaubilder der Fenster mit dem Bildschirminhalt ausf�llen" },
-	{ "iso-8859-7", "�������� �������� ��� �� ��������� ��� ����� ��������� (���������-��������������)" },
-	{ "iso-8859-1", "You've chosen to disable the startup hint. To re-enable it, choose \"Startup Hint\" in the GNOME Control Centre" },
-	{ "iso-8859-1", "El aplique de reloj muestra en su panel la fecha y la hora de forma simple y ligero " },
-	{ "iso-8859-1", "Applet ei vasta salvestusk�sule. Kas peaks ta niisama sulgema, v�i veel ootama?" },
-	{ "iso-8859-1", "Lehio kudeatzaileak lehioaren dekorazaioa mugiarazten (AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
-	{ "iso-8859-15", "N�yt� sovellukset, joiden ikkunoista on n�kyvill� vain otsikkopalkki" },
-	{ "ISO-8859-1", "Afficher les t�ches qui ne sont pas dans la liste des fen�tres" },
-	{ "iso-8859-1", "N�l applet ag tabhair freagra ar iarratas s�bh�il. Bain amach an applet n� lean ar f�nacht?" },
-	{ "iso-8859-1", "Amosa-las tarefas agochadas da lista de fiestras (SKIP-WINLIST)" },
-	{ "iso-8859-2", "Az ablakkezel� a dekor�ci�t mozgassa az ablak helyett (AfterStep, Enlightenment, FVWM, IceWM, SawMill)" },
-	{ "iso-8859-1", "Riempi la finestra delle anteprime con il contenuto dello schermo" },
-	{ "euc-jp", "������ɥ��ޥ͡�����Ͼ��ꥦ����ɥ���ư���� (AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
-	{ "euc-kr", "â �����ڰ� �ٹ� â ��� �̵� (AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
-	{ "iso-8859-13", "Priedas neatsakin�ja � pra�ym� i�sisaugoti. Pa�alinti pried� ar laukti toliau?" },
-	{ "iso-8859-1", "Window manager verplaatst dekoratie (AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
-	{ "iso-8859-1", "Vindush�ndtereren flytter dekorasjonsvinduet i stedet (AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
-	{ "iso-8859-2", "Przemieszczanie dekoracji zamiast okna (AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
-	{ "iso-8859-1", "Este programa � respons�vel por executar outras aplica��es, embeber pequenos applets, a paz no mundo e crashes aleat�rios do X." },
-	{ "iso-8859-1", "Mostrar tarefas que se escondem da lista de janelas (SKIP-WINLIST)" },
-	{ "koi8-r", "������ �������� ����� � ������������� ��������� � ������� ������" },
-	{ "iso-8859-2", "Spr�vca okien pres�va okraje okien (AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
-	{ "iso-8859-2", "Ka�i posle, ki se skrivajo pred upravljalnik oken (SKIP-WINLIST)" },
-	{ "iso-8859-5", "Window ��������� ������ ����������� ������ ������ ���a (AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
-	{ "iso-8859-2", "Window menadzeri pomera dekoracioni prozor umesto toga (AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
-	{ "iso-8859-1", "F�nsterhanteraren flyttar dekorationsf�nstret ist�llet (AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
-	/*{ "TSCII", "���츼�-���� ���� ��¡� ���츼���� ���� (���츼�-���-�Ţ�)" },*/
-	{ "iso-8859-9", "Kaydetme iste�ine bir uygulak cevap vermiyor . Uygula�� sileyim mi , yoksa bekleyeyim mi ?" },
-	{ "koi8-u", "����ͦ����� ������æ� ��ͦ��� צ��� (AfterStep, Enlightenment, FVWM, IceWM, Sawfish)" },
-	{ "iso-8859-1", "Cwand on scrift�r est bodj� fo�, li scrift�r �t totes les apliketes � dvins sont pierdowes. Bodj� ci scrift�r chal?" },
-	{ "gb2312", "Ǩ�Ƶ�װ�δ��ڹ�������(AfterStep, Enlightenment, FVWM, IceWM, SawMill)" },
-	{ "big5", "�����޲z�̥u���ʸ˹����� (AfterStep, Enlightenment, FVWM, IceWM, Sawmill)" },
-};
+#include "address-data.h"
 
 static char *convert(const char *in, const char *from, const char *to)
 {
@@ -330,8 +286,38 @@ int main(int argc, char **argv)
 
 	camel_test_end();
 
-	/* FIXME: Add test of decoding of externally defined addresses */
+	camel_test_start("CamelInternetAddress, I18N decode");
+
+	for (i=0;i<ARRAY_LEN(test_address);i++) {
+		push("Testing address line %d '%s'", i, test_address[i].addr);
+
+		addr = camel_internet_address_new();
+		push("checking decoded");
+		check(camel_address_decode(CAMEL_ADDRESS(addr), test_address[i].addr) == test_address[i].count);
+		format = camel_address_format(CAMEL_ADDRESS(addr));
+		check(strcmp(format, test_address[i].utf8) == 0);
+		test_free(format);
+		pull();
+		
+		push("Comparing re-encoded output");
+		addr2 = CAMEL_INTERNET_ADDRESS(camel_internet_address_new());
+		enc = camel_address_encode(CAMEL_ADDRESS(addr));
+		check_msg(camel_address_decode(CAMEL_ADDRESS(addr2), enc) == test_address[i].count, "enc = '%s'", enc);
+		test_free(enc);
+		test_address_compare(addr, addr2);
+		check_unref(addr2, 1);
+		pull();
+
+		check_unref(addr, 1);
+
+		pull();
+	}
+
+	camel_test_end();
+
 	/* FIXME: Add test of decoding of broken addresses */
 
 	return 0;
 }
+
+