Merge branch 'ew/svn-test-and-old-i18n'

* ew/svn-test-and-old-i18n: t8005: fix typo, it's ISO-8859-5, not KOI8-R t8005: convert CP1251 character set to ISO8859-5 t8005: use more portable character encoding names t5100: use ancient encoding syntax for backwards compatibility t9301: use ISO8859-1 rather than ISO-8859-1 t3901: Use ISO8859-1 instead of ISO-8859-1 for backward compatibility t3901: avoid negation on right hand side of '|' builtin-mailinfo.c: use "ISO8859-1" instead of "latin1" as fallback encoding builtin-mailinfo.c: compare character encodings case insensitively Use 'UTF-8' rather than 'utf-8' everywhere for backward compatibility t3900: use ancient iconv names for backward compatibility
git-mirror · May 31, 2009 · 22cdab5 · 22cdab5
2 parents 0667621 + 1886431
commit 22cdab5
Show file tree

Hide file tree

Showing 17 changed files with 91 additions and 93 deletions.
diff --git a/builtin-log.c b/builtin-log.c
@@ -619,7 +619,7 @@ static void make_cover_letter(struct rev_info *rev, int use_stdout,
 	struct shortlog log;
 	struct strbuf sb = STRBUF_INIT;
 	int i;
-	const char *encoding = "utf-8";
+	const char *encoding = "UTF-8";
 	struct diff_options opts;
 	int need_8bit_cte = 0;
 	struct commit *commit = NULL;

diff --git a/builtin-mailinfo.c b/builtin-mailinfo.c
@@ -193,8 +193,7 @@ static void handle_content_type(struct strbuf *line)
 		*content_top = boundary;
 		boundary = NULL;
 	}
-	if (slurp_attr(line->buf, "charset=", &charset))
-		strbuf_tolower(&charset);
+	slurp_attr(line->buf, "charset=", &charset);
 
 	if (boundary) {
 		strbuf_release(boundary);
@@ -481,7 +480,7 @@ static const char *guess_charset(const struct strbuf *line, const char *target_c
 		if (is_utf8(line->buf))
 			return NULL;
 	}
-	return "latin1";
+	return "ISO8859-1";
 }
 
 static void convert_to_utf8(struct strbuf *line, const char *charset)
@@ -494,7 +493,7 @@ static void convert_to_utf8(struct strbuf *line, const char *charset)
 			return;
 	}
 
-	if (!strcmp(metainfo_charset, charset))
+	if (!strcasecmp(metainfo_charset, charset))
 		return;
 	out = reencode_string(line->buf, metainfo_charset, charset);
 	if (!out)
@@ -550,7 +549,6 @@ static int decode_header_bq(struct strbuf *it)
 		if (cp + 3 - it->buf > it->len)
 			goto decode_header_bq_out;
 		strbuf_add(&charset_q, ep, cp - ep);
-		strbuf_tolower(&charset_q);
 
 		encoding = cp[1];
 		if (!encoding || cp[2] != '?')
@@ -944,7 +942,7 @@ int cmd_mailinfo(int argc, const char **argv, const char *prefix)
 	 */
 	git_config(git_default_config, NULL);
 
-	def_charset = (git_commit_encoding ? git_commit_encoding : "utf-8");
+	def_charset = (git_commit_encoding ? git_commit_encoding : "UTF-8");
 	metainfo_charset = def_charset;
 
 	while (1 < argc && argv[1][0] == '-') {

diff --git a/builtin-revert.c b/builtin-revert.c
@@ -323,9 +323,9 @@ static int revert_or_cherry_pick(int argc, const char **argv)
 
 	encoding = get_encoding(message);
 	if (!encoding)
-		encoding = "utf-8";
+		encoding = "UTF-8";
 	if (!git_commit_encoding)
-		git_commit_encoding = "utf-8";
+		git_commit_encoding = "UTF-8";
 	if ((reencoded_message = reencode_string(message,
 					git_commit_encoding, encoding)))
 		message = reencoded_message;

diff --git a/pretty.c b/pretty.c
@@ -284,7 +284,7 @@ static char *replace_encoding_header(char *buf, const char *encoding)
 static char *logmsg_reencode(const struct commit *commit,
 			     const char *output_encoding)
 {
-	static const char *utf8 = "utf-8";
+	static const char *utf8 = "UTF-8";
 	const char *use_encoding;
 	char *encoding;
 	char *out;
@@ -881,7 +881,7 @@ char *reencode_commit_message(const struct commit *commit, const char **encoding
 		    ? git_log_output_encoding
 		    : git_commit_encoding);
 	if (!encoding)
-		encoding = "utf-8";
+		encoding = "UTF-8";
 	if (encoding_p)
 		*encoding_p = encoding;
 	return logmsg_reencode(commit, encoding);

diff --git a/t/t3900-i18n-commit.sh b/t/t3900-i18n-commit.sh
@@ -34,7 +34,7 @@ test_expect_success 'no encoding header for base case' '
 	test z = "z$E"
 '
 
-for H in ISO-8859-1 EUCJP ISO-2022-JP
+for H in ISO8859-1 eucJP ISO-2022-JP
 do
 	test_expect_success "$H setup" '
 		git config i18n.commitencoding $H &&
@@ -44,7 +44,7 @@ do
 	'
 done
 
-for H in ISO-8859-1 EUCJP ISO-2022-JP
+for H in ISO8859-1 eucJP ISO-2022-JP
 do
 	test_expect_success "check encoding header for $H" '
 		E=$(git cat-file commit '$H' | sed -ne "s/^encoding //p") &&
@@ -61,14 +61,14 @@ test_expect_success 'config to remove customization' '
 	else
 		test z = "z$Z"
 	fi &&
-	git config i18n.commitencoding utf-8
+	git config i18n.commitencoding UTF-8
 '
 
-test_expect_success 'ISO-8859-1 should be shown in UTF-8 now' '
-	compare_with ISO-8859-1 "$TEST_DIRECTORY"/t3900/1-UTF-8.txt
+test_expect_success 'ISO8859-1 should be shown in UTF-8 now' '
+	compare_with ISO8859-1 "$TEST_DIRECTORY"/t3900/1-UTF-8.txt
 '
 
-for H in EUCJP ISO-2022-JP
+for H in eucJP ISO-2022-JP
 do
 	test_expect_success "$H should be shown in UTF-8 now" '
 		compare_with '$H' "$TEST_DIRECTORY"/t3900/2-UTF-8.txt
@@ -86,7 +86,7 @@ test_expect_success 'config to add customization' '
 	fi
 '
 
-for H in ISO-8859-1 EUCJP ISO-2022-JP
+for H in ISO8859-1 eucJP ISO-2022-JP
 do
 	test_expect_success "$H should be shown in itself now" '
 		git config i18n.commitencoding '$H' &&
@@ -95,21 +95,21 @@ do
 done
 
 test_expect_success 'config to tweak customization' '
-	git config i18n.logoutputencoding utf-8
+	git config i18n.logoutputencoding UTF-8
 '
 
-test_expect_success 'ISO-8859-1 should be shown in UTF-8 now' '
-	compare_with ISO-8859-1 "$TEST_DIRECTORY"/t3900/1-UTF-8.txt
+test_expect_success 'ISO8859-1 should be shown in UTF-8 now' '
+	compare_with ISO8859-1 "$TEST_DIRECTORY"/t3900/1-UTF-8.txt
 '
 
-for H in EUCJP ISO-2022-JP
+for H in eucJP ISO-2022-JP
 do
 	test_expect_success "$H should be shown in UTF-8 now" '
 		compare_with '$H' "$TEST_DIRECTORY"/t3900/2-UTF-8.txt
 	'
 done
 
-for J in EUCJP ISO-2022-JP
+for J in eucJP ISO-2022-JP
 do
 	if test "$J" = ISO-2022-JP
 	then
@@ -118,15 +118,15 @@ do
 		ICONV=
 	fi
 	git config i18n.logoutputencoding $J
-	for H in EUCJP ISO-2022-JP
+	for H in eucJP ISO-2022-JP
 	do
 		test_expect_success "$H should be shown in $J now" '
 			compare_with '$H' "$TEST_DIRECTORY"/t3900/'$J'.txt $ICONV
 		'
 	done
 done
 
-for H in ISO-8859-1 EUCJP ISO-2022-JP
+for H in ISO8859-1 eucJP ISO-2022-JP
 do
 	test_expect_success "No conversion with $H" '
 		compare_with "--encoding=none '$H'" "$TEST_DIRECTORY"/t3900/'$H'.txt

diff --git a/t/t3900/ISO-8859-1.txt → t/t3900/ISO8859-1.txt b/t/t3900/ISO-8859-1.txt → t/t3900/ISO8859-1.txt
diff --git a/t/t3900/EUCJP.txt → t/t3900/eucJP.txt b/t/t3900/EUCJP.txt → t/t3900/eucJP.txt
diff --git a/t/t3901-i18n-patch.sh b/t/t3901-i18n-patch.sh
@@ -17,9 +17,9 @@ check_encoding () {
 		git cat-file commit HEAD~$j |
 		case "$header" in
 		8859)
-			grep "^encoding ISO-8859-1" ;;
+			grep "^encoding ISO8859-1" ;;
 		*)
-			! grep "^encoding ISO-8859-1" ;;
+			grep "^encoding ISO8859-1"; test "$?" != 0 ;;
 		esac || {
 			bad=1
 			break
@@ -55,7 +55,7 @@ test_expect_success setup '
 	git commit -s -m "Second on side" &&
 
 	# the second one on the side branch is ISO-8859-1
-	git config i18n.commitencoding ISO-8859-1 &&
+	git config i18n.commitencoding ISO8859-1 &&
 	# use author and committer name in ISO-8859-1 to match it.
 	. "$TEST_DIRECTORY"/t3901-8859-1.txt &&
 	test_tick &&
@@ -68,14 +68,14 @@ test_expect_success setup '
 '
 
 test_expect_success 'format-patch output (ISO-8859-1)' '
-	git config i18n.logoutputencoding ISO-8859-1 &&
+	git config i18n.logoutputencoding ISO8859-1 &&
 
 	git format-patch --stdout master..HEAD^ >out-l1 &&
 	git format-patch --stdout HEAD^ >out-l2 &&
-	grep "^Content-Type: text/plain; charset=ISO-8859-1" out-l1 &&
-	grep "^From: =?ISO-8859-1?q?=C1=E9=ED=20=F3=FA?=" out-l1 &&
-	grep "^Content-Type: text/plain; charset=ISO-8859-1" out-l2 &&
-	grep "^From: =?ISO-8859-1?q?=C1=E9=ED=20=F3=FA?=" out-l2
+	grep "^Content-Type: text/plain; charset=ISO8859-1" out-l1 &&
+	grep "^From: =?ISO8859-1?q?=C1=E9=ED=20=F3=FA?=" out-l1 &&
+	grep "^Content-Type: text/plain; charset=ISO8859-1" out-l2 &&
+	grep "^From: =?ISO8859-1?q?=C1=E9=ED=20=F3=FA?=" out-l2
 '
 
 test_expect_success 'format-patch output (UTF-8)' '
@@ -110,7 +110,7 @@ test_expect_success 'rebase (U/U)' '
 
 test_expect_success 'rebase (U/L)' '
 	git config i18n.commitencoding UTF-8 &&
-	git config i18n.logoutputencoding ISO-8859-1 &&
+	git config i18n.logoutputencoding ISO8859-1 &&
 	. "$TEST_DIRECTORY"/t3901-utf8.txt &&
 
 	git reset --hard side &&
@@ -121,8 +121,8 @@ test_expect_success 'rebase (U/L)' '
 
 test_expect_success 'rebase (L/L)' '
 	# In this test we want ISO-8859-1 encoded commits as the result
-	git config i18n.commitencoding ISO-8859-1 &&
-	git config i18n.logoutputencoding ISO-8859-1 &&
+	git config i18n.commitencoding ISO8859-1 &&
+	git config i18n.logoutputencoding ISO8859-1 &&
 	. "$TEST_DIRECTORY"/t3901-8859-1.txt &&
 
 	git reset --hard side &&
@@ -134,7 +134,7 @@ test_expect_success 'rebase (L/L)' '
 test_expect_success 'rebase (L/U)' '
 	# This is pathological -- use UTF-8 as intermediate form
 	# to get ISO-8859-1 results.
-	git config i18n.commitencoding ISO-8859-1 &&
+	git config i18n.commitencoding ISO8859-1 &&
 	git config i18n.logoutputencoding UTF-8 &&
 	. "$TEST_DIRECTORY"/t3901-8859-1.txt &&
 
@@ -162,8 +162,8 @@ test_expect_success 'cherry-pick(U/U)' '
 test_expect_success 'cherry-pick(L/L)' '
 	# Both the commitencoding and logoutputencoding is set to ISO-8859-1
 
-	git config i18n.commitencoding ISO-8859-1 &&
-	git config i18n.logoutputencoding ISO-8859-1 &&
+	git config i18n.commitencoding ISO8859-1 &&
+	git config i18n.logoutputencoding ISO8859-1 &&
 	. "$TEST_DIRECTORY"/t3901-8859-1.txt &&
 
 	git reset --hard master &&
@@ -178,7 +178,7 @@ test_expect_success 'cherry-pick(U/L)' '
 	# Commitencoding is set to UTF-8 but logoutputencoding is ISO-8859-1
 
 	git config i18n.commitencoding UTF-8 &&
-	git config i18n.logoutputencoding ISO-8859-1 &&
+	git config i18n.logoutputencoding ISO8859-1 &&
 	. "$TEST_DIRECTORY"/t3901-utf8.txt &&
 
 	git reset --hard master &&
@@ -193,7 +193,7 @@ test_expect_success 'cherry-pick(L/U)' '
 	# Again, the commitencoding is set to ISO-8859-1 but
 	# logoutputencoding is set to UTF-8.
 
-	git config i18n.commitencoding ISO-8859-1 &&
+	git config i18n.commitencoding ISO8859-1 &&
 	git config i18n.logoutputencoding UTF-8 &&
 	. "$TEST_DIRECTORY"/t3901-8859-1.txt &&
 
@@ -218,7 +218,7 @@ test_expect_success 'rebase --merge (U/U)' '
 
 test_expect_success 'rebase --merge (U/L)' '
 	git config i18n.commitencoding UTF-8 &&
-	git config i18n.logoutputencoding ISO-8859-1 &&
+	git config i18n.logoutputencoding ISO8859-1 &&
 	. "$TEST_DIRECTORY"/t3901-utf8.txt &&
 
 	git reset --hard side &&
@@ -229,8 +229,8 @@ test_expect_success 'rebase --merge (U/L)' '
 
 test_expect_success 'rebase --merge (L/L)' '
 	# In this test we want ISO-8859-1 encoded commits as the result
-	git config i18n.commitencoding ISO-8859-1 &&
-	git config i18n.logoutputencoding ISO-8859-1 &&
+	git config i18n.commitencoding ISO8859-1 &&
+	git config i18n.logoutputencoding ISO8859-1 &&
 	. "$TEST_DIRECTORY"/t3901-8859-1.txt &&
 
 	git reset --hard side &&
@@ -242,7 +242,7 @@ test_expect_success 'rebase --merge (L/L)' '
 test_expect_success 'rebase --merge (L/U)' '
 	# This is pathological -- use UTF-8 as intermediate form
 	# to get ISO-8859-1 results.
-	git config i18n.commitencoding ISO-8859-1 &&
+	git config i18n.commitencoding ISO8859-1 &&
 	git config i18n.logoutputencoding UTF-8 &&
 	. "$TEST_DIRECTORY"/t3901-8859-1.txt &&
 

diff --git a/t/t5100/rfc2047-samples.mbox b/t/t5100/rfc2047-samples.mbox
@@ -1,48 +1,48 @@
 From nobody Mon Sep 17 00:00:00 2001
 From: =?US-ASCII?Q?Keith_Moore?= <moore@cs.utk.edu>
-To: =?ISO-8859-1?Q?Keld_J=F8rn_Simonsen?= <keld@dkuug.dk>
-CC: =?ISO-8859-1?Q?Andr=E9?= Pirard <PIRARD@vm1.ulg.ac.be>
-Subject: =?ISO-8859-1?B?SWYgeW91IGNhbiByZWFkIHRoaXMgeW8=?=
- =?ISO-8859-2?B?dSB1bmRlcnN0YW5kIHRoZSBleGFtcGxlLg==?=
+To: =?ISO8859-1?Q?Keld_J=F8rn_Simonsen?= <keld@dkuug.dk>
+CC: =?ISO8859-1?Q?Andr=E9?= Pirard <PIRARD@vm1.ulg.ac.be>
+Subject: =?ISO8859-1?B?SWYgeW91IGNhbiByZWFkIHRoaXMgeW8=?=
+ =?ISO8859-2?B?dSB1bmRlcnN0YW5kIHRoZSBleGFtcGxlLg==?=
 
 From nobody Mon Sep 17 00:00:00 2001
-From: =?ISO-8859-1?Q?Olle_J=E4rnefors?= <ojarnef@admin.kth.se>
+From: =?ISO8859-1?Q?Olle_J=E4rnefors?= <ojarnef@admin.kth.se>
 To: ietf-822@dimacs.rutgers.edu, ojarnef@admin.kth.se
 Subject: Time for ISO 10646?
 
 From nobody Mon Sep 17 00:00:00 2001
 To: Dave Crocker <dcrocker@mordor.stanford.edu>
 Cc: ietf-822@dimacs.rutgers.edu, paf@comsol.se
-From: =?ISO-8859-1?Q?Patrik_F=E4ltstr=F6m?= <paf@nada.kth.se>
+From: =?ISO8859-1?Q?Patrik_F=E4ltstr=F6m?= <paf@nada.kth.se>
 Subject: Re: RFC-HDR care and feeding
 
 From nobody Mon Sep 17 00:00:00 2001
 From: Nathaniel Borenstein <nsb@thumper.bellcore.com>
-      (=?iso-8859-8?b?7eXs+SDv4SDp7Oj08A==?=)
+      (=?ISO8859-8?b?7eXs+SDv4SDp7Oj08A==?=)
 To: Greg Vaudreuil <gvaudre@NRI.Reston.VA.US>, Ned Freed
    <ned@innosoft.com>, Keith Moore <moore@cs.utk.edu>
 Subject: Test of new header generator
 MIME-Version: 1.0
-Content-type: text/plain; charset=ISO-8859-1
+Content-type: text/plain; charset=ISO8859-1
 
 From nobody Mon Sep 17 00:00:00 2001
-Subject: (=?ISO-8859-1?Q?a?=)
+Subject: (=?ISO8859-1?Q?a?=)
 
 From nobody Mon Sep 17 00:00:00 2001
-Subject: (=?ISO-8859-1?Q?a?= b)
+Subject: (=?ISO8859-1?Q?a?= b)
 
 From nobody Mon Sep 17 00:00:00 2001
-Subject: (=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=)
+Subject: (=?ISO8859-1?Q?a?= =?ISO8859-1?Q?b?=)
 
 From nobody Mon Sep 17 00:00:00 2001
-Subject: (=?ISO-8859-1?Q?a?=  =?ISO-8859-1?Q?b?=)
+Subject: (=?ISO8859-1?Q?a?=  =?ISO8859-1?Q?b?=)
 
 From nobody Mon Sep 17 00:00:00 2001
-Subject: (=?ISO-8859-1?Q?a?=
-    =?ISO-8859-1?Q?b?=)
+Subject: (=?ISO8859-1?Q?a?=
+    =?ISO8859-1?Q?b?=)
 
 From nobody Mon Sep 17 00:00:00 2001
-Subject: (=?ISO-8859-1?Q?a_b?=)
+Subject: (=?ISO8859-1?Q?a_b?=)
 
 From nobody Mon Sep 17 00:00:00 2001
-Subject: (=?ISO-8859-1?Q?a?= =?ISO-8859-2?Q?_b?=)
+Subject: (=?ISO8859-1?Q?a?= =?ISO8859-2?Q?_b?=)