[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20190416194433.8664-1-krisman@collabora.com>
Date: Tue, 16 Apr 2019 15:44:32 -0400
From: Gabriel Krisman Bertazi <krisman@...labora.com>
To: tytso@....edu
Cc: linux-ext4@...r.kernel.org,
Gabriel Krisman Bertazi <krisman@...labora.com>
Subject: [PATCH 1/2] unicode: Update unicode database unicode version 12.1.0
Unicode 12.1.0 adds the character U+32FF (SQUARE ERA NAME REIWA),
only. It's decomposition in NFD is identity, so there isn't much change
here. In fact, the only behavior alteration would be strict mode
allowing a file with this character.
Feel free to squash these two into the respective patches of the previous seriessubmitted it separately to make review easier.
Signed-off-by: Gabriel Krisman Bertazi <krisman@...labora.com>
---
fs/unicode/README.utf8data | 49 +++++++++++++++++++-------------------
fs/unicode/utf8-selftest.c | 4 ++--
fs/unicode/utf8data.h | 17 +++++++------
3 files changed, 37 insertions(+), 33 deletions(-)
diff --git a/fs/unicode/README.utf8data b/fs/unicode/README.utf8data
index cbcdb56832ed..eeb7561526d9 100644
--- a/fs/unicode/README.utf8data
+++ b/fs/unicode/README.utf8data
@@ -1,39 +1,40 @@
The utf8data.h file in this directory is generated from the Unicode
-Character Database for version 12.0.0 of the Unicode standard.
+Character Database for version 12.1.0 of the Unicode standard.
The full set of files can be found here:
- http://www.unicode.org/Public/12.0.0/ucd/
+ http://www.unicode.org/Public/12.1.0/ucd/
Individual source links:
- http://www.unicode.org/Public/12.0.0/ucd/CaseFolding.txt
- http://www.unicode.org/Public/12.0.0/ucd/DerivedAge.txt
- http://www.unicode.org/Public/12.0.0/ucd/extracted/DerivedCombiningClass.txt
- http://www.unicode.org/Public/12.0.0/ucd/DerivedCoreProperties.txt
- http://www.unicode.org/Public/12.0.0/ucd/NormalizationCorrections.txt
- http://www.unicode.org/Public/12.0.0/ucd/NormalizationTest.txt
- http://www.unicode.org/Public/12.0.0/ucd/UnicodeData.txt
+ https://www.unicode.org/Public/12.1.0/ucd/CaseFolding-12.1.0d2.txt
+ https://www.unicode.org/Public/12.1.0/ucd/DerivedAge-12.1.0d3.txt
+ https://www.unicode.org/Public/12.1.0/ucd/extracted/DerivedCombiningClass-12.1.0d2.txt
+ https://www.unicode.org/Public/12.1.0/ucd/DerivedCoreProperties-12.1.0d2.txt
+ https://www.unicode.org/Public/12.1.0/ucd/NormalizationCorrections-12.1.0d1.txt
+ https://www.unicode.org/Public/12.1.0/ucd/NormalizationTest-12.1.0d3.txt
+ https://www.unicode.org/Public/12.1.0/ucd/UnicodeData-12.1.0d2.txt
md5sums (verify by running "md5sum -c README.utf8data"):
- a794be08c28f90853003c9bdf8826509 CaseFolding.txt
- 6b4750a2ff1a19ce7f28b6a6528457e8 DerivedAge.txt
- fae28c468eb7017785ecf21fdc6c5835 DerivedCombiningClass.txt
- efb8b829abd2a0aaa617e3d66211440d DerivedCoreProperties.txt
- 4c662a8f228506aea5e8a6e2e06e15d8 NormalizationCorrections.txt
- 35866dad08e10d658c344808b48ac01d NormalizationTest.txt
- 6221effa1dd15524745a467f7366233d UnicodeData.txt
+ 900e76da1d822a160fd6b8c0b1d70094 CaseFolding-12.1.0d2.txt
+ 131256380bff4fea8ad4a851616f2f10 DerivedAge-12.1.0d3.txt
+ e731a4089b30002144e107e3d6f8d1fa DerivedCombiningClass-12.1.0d2.txt
+ a47c9fbd7ff92a9b261ba9831e68778a DerivedCoreProperties-12.1.0d2.txt
+ fcab6dad15e440879d92f315978f93d3 NormalizationCorrections-12.1.0d1.txt
+ f9ff1c55a60decf436100f791b44aa98 NormalizationTest-12.1.0d3.txt
+ 755f6af699f8c8d2d958da411f78f6c6 UnicodeData-12.1.0d2.txt
sha1sums (verify by running "sha1sum -c README.utf8data"):
- 404fc6a0a80a64ecece059fa9a1e342152d58db3 CaseFolding.txt
- cb18ee0677d6054b7e1b87946f6d566a8c0feebe DerivedAge.txt
- 79226de6bf7d8fde525120634a9177d9b2a55e13 DerivedCombiningClass.txt
- 8cc194267f90d5c4ba4118236f9d6df28b4db425 DerivedCoreProperties.txt
- 48104614d353e9962fe5b074e4348cd0f95104df NormalizationCorrections.txt
- 7e7806e4579f0a481b3677969675f63aec08feba NormalizationTest.txt
- 0a309cf58fe2a5d0d904c9bf2c1a89b2666c413a UnicodeData.txt
+ dc9245f6803c4ac99555c361f5052e0b13eb779b CaseFolding-12.1.0d2.txt
+ 3281104f237184cdb5d869e86eb8573678ada7da DerivedAge-12.1.0d3.txt
+ 2f5f995ccb96e0fa84b15151b35d5e2681535175 DerivedCombiningClass-12.1.0d2.txt
+ 5b8698a3fcd5018e1987f296b02e2c17e696415e DerivedCoreProperties-12.1.0d2.txt
+ cd83935fbc012345d8792d2c704f69497e753835 NormalizationCorrections-12.1.0d1.txt
+ ea419aae505b337b0d99a83fa83fe58ddff7c19f NormalizationTest-12.1.0d3.txt
+ dc973c0fc93d6f09d9ab9f70d1c9f89c447f0526 UnicodeData-12.1.0d2.txt
+
To update to the newer version of the Unicode standard, the latest
released version of the UCD can be found here:
@@ -46,7 +47,7 @@ cd to this directory (fs/unicode) and run this command:
make C=../.. objdir=../.. utf8data.h.new
After sanity checking the newly generated utf8data.h.new file (the
-version generated from the 12.0.0 UCD should be 4,106 lines long, and
+version generated from the 12.1.0 UCD should be 4,109 lines long, and
have a total size of 324k) and/or comparing it with the older version
of utf8data.h, rename it to utf8data.h.
diff --git a/fs/unicode/utf8-selftest.c b/fs/unicode/utf8-selftest.c
index 6964553c0132..80752013fce0 100644
--- a/fs/unicode/utf8-selftest.c
+++ b/fs/unicode/utf8-selftest.c
@@ -27,7 +27,7 @@ unsigned int total_tests;
/* Tests will be based on this version. */
#define latest_maj 12
-#define latest_min 0
+#define latest_min 1
#define latest_rev 0
#define _test(cond, func, line, fmt, ...) do { \
@@ -243,7 +243,7 @@ static void check_utf8_nfdicf(void)
static void check_utf8_comparisons(void)
{
int i;
- struct unicode_map *table = utf8_load("11.0.0");
+ struct unicode_map *table = utf8_load("12.1.0");
if (IS_ERR(table)) {
pr_err("%s: Unable to load utf8 %d.%d.%d. Skipping.\n",
diff --git a/fs/unicode/utf8data.h b/fs/unicode/utf8data.h
index 4d65c04e0786..76e4f0e1b089 100644
--- a/fs/unicode/utf8data.h
+++ b/fs/unicode/utf8data.h
@@ -3,7 +3,7 @@
#error Only nls_utf8-norm.c should include this file.
#endif
-static const unsigned int utf8vers = 0xc0000;
+static const unsigned int utf8vers = 0xc0100;
static const unsigned int utf8agetab[] = {
0,
@@ -27,7 +27,8 @@ static const unsigned int utf8agetab[] = {
0x90000,
0xa0000,
0xb0000,
- 0xc0000
+ 0xc0000,
+ 0xc0100
};
static const struct utf8data utf8nfdicfdata[] = {
@@ -52,7 +53,8 @@ static const struct utf8data utf8nfdicfdata[] = {
{ 0x90000, 3200 },
{ 0xa0000, 3200 },
{ 0xb0000, 3200 },
- { 0xc0000, 3200 }
+ { 0xc0000, 3200 },
+ { 0xc0100, 3200 }
};
static const struct utf8data utf8nfdidata[] = {
@@ -77,7 +79,8 @@ static const struct utf8data utf8nfdidata[] = {
{ 0x90000, 20736 },
{ 0xa0000, 20736 },
{ 0xb0000, 20736 },
- { 0xc0000, 20736 }
+ { 0xc0000, 20736 },
+ { 0xc0100, 20736 }
};
static const unsigned char utf8data[64256] = {
@@ -285,7 +288,7 @@ static const unsigned char utf8data[64256] = {
0xe8,0x9a,0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,
0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8,0x9e,
0x86,0x00,0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- /* nfdicf_c0000 */
+ /* nfdicf_c0100 */
0xd7,0xb0,0x56,0x04,0x01,0x00,0x95,0xa8,0xd4,0x5e,0xd3,0x2e,0xd2,0x16,0xd1,0x0a,
0x10,0x04,0x01,0x00,0x01,0xff,0x61,0x00,0x10,0x06,0x01,0xff,0x62,0x00,0x01,0xff,
0x63,0x00,0xd1,0x0c,0x10,0x06,0x01,0xff,0x64,0x00,0x01,0xff,0x65,0x00,0x10,0x06,
@@ -1382,7 +1385,7 @@ static const unsigned char utf8data[64256] = {
0x00,0x12,0x00,0x12,0x00,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
- /* nfdi_c0000 */
+ /* nfdi_c0100 */
0x57,0x04,0x01,0x00,0xc6,0xe5,0xac,0x13,0xe4,0x41,0x0c,0xe3,0x7a,0x07,0xe2,0xf3,
0x01,0xc1,0xd0,0x1f,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x15,0x53,0x04,0x01,0x00,
0x52,0x04,0x01,0x00,0x91,0x09,0x10,0x04,0x01,0x00,0x01,0xff,0x00,0x01,0x00,0x01,
@@ -2698,7 +2701,7 @@ static const unsigned char utf8data[64256] = {
0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,
0x00,0x06,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0xcf,0x86,0xd5,0x10,0x94,0x0c,0x53,
0x04,0x01,0x00,0x12,0x04,0x01,0x00,0x07,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0x53,
- 0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,
+ 0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x16,
0x00,0xd1,0x30,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,
0x04,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,
0x00,0x07,0x00,0x92,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x01,0x00,0x01,
--
2.20.1
Powered by blists - more mailing lists