Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

support gbk charset #808

Open
wants to merge 10 commits into
base: master
Choose a base branch
from
Open

support gbk charset #808

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
bb23b5d
1. Support charset gbk in parser; 2. fix description for charsetlatin…
spongedu Apr 13, 2020
72cf9d6
Update charset/charset.go
spongedu Apr 13, 2020
2b6c2eb
Merge branch 'master' into 200413
spongedu Apr 13, 2020
396c043
Merge branch 'master' into 200413
spongedu Apr 16, 2020
824320b
Update charset/charset.go
spongedu Apr 21, 2020
5076d4d
Merge branch 'master' into 200413
spongedu Apr 21, 2020
5ea592c
Merge remote-tracking branch 'origin/master' into 200413
spongedu May 30, 2020
f0a9ee9
Merge remote-tracking branch 'origin/master' into 200413
spongedu Jun 4, 2020
143ed26
Merge branch 'master' into 200413
spongedu Jun 11, 2020
73b534d
Merge branch 'master' into 200413
AilinKid Jun 19, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 13 additions & 7 deletions charset/charset.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,17 +56,19 @@ var charsetInfos = []*Charset{
{CharsetUTF8, CollationUTF8, make(map[string]*Collation), "UTF-8 Unicode", 3},
{CharsetUTF8MB4, CollationUTF8MB4, make(map[string]*Collation), "UTF-8 Unicode", 4},
{CharsetASCII, CollationASCII, make(map[string]*Collation), "US ASCII", 1},
{CharsetLatin1, CollationLatin1, make(map[string]*Collation), "Latin1", 1},
{CharsetBin, CollationBin, make(map[string]*Collation), "binary", 1},
{CharsetLatin1, CollationLatin1, make(map[string]*Collation), "cp1252 West European", 1},
{CharsetBin, CollationBin, make(map[string]*Collation), "Binary pseudo charset", 1},
{CharsetGBK, CollationGBKChineseCi, make(map[string]*Collation), "GBK Simplified Chinese", 2},
}

// All the names supported collations should be in the following table.
var supportedCollationNames = map[string]struct{}{
CollationUTF8: {},
CollationUTF8MB4: {},
CollationASCII: {},
CollationLatin1: {},
CollationBin: {},
CollationUTF8: {},
CollationUTF8MB4: {},
CollationASCII: {},
CollationLatin1: {},
CollationBin: {},
CollationGBKChineseCi: {},
}

// Desc is a charset description.
Expand Down Expand Up @@ -186,6 +188,10 @@ const (
CharsetUTF8 = "utf8"
// CollationUTF8 is the default collation for CharsetUTF8.
CollationUTF8 = "utf8_bin"
// CharsetGBK is an extension of the GB2312 character set for simplified Chinese characters.
CharsetGBK = "gbk"
// CollationGBKChineseCi is the default collation for CharsetGBK.
CollationGBKChineseCi = "gbk_chinese_ci"
// CharsetUTF8MB4 represents 4 bytes utf8, which works the same way as utf8 in Go.
CharsetUTF8MB4 = "utf8mb4"
// CollationUTF8MB4 is the default collation for CharsetUTF8MB4.
Expand Down
56 changes: 56 additions & 0 deletions parser_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,6 +210,62 @@ func (s *testParserSuite) TestSimple(c *C) {
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE t38 (c1 CHAR(20) CHARACTER SET gbk);"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE t39 (c1 CHAR(20) CHARACTER SET gbk COLLATE gbk_bin);"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE t219 (c1 TEXT CHARACTER SET gbk COLLATE gbk_chinese_ci)DEFAULT CHARACTER SET=utf8 COLLATE=utf8_general_ci;"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE t218 (c1 TEXT CHARACTER SET gbk)DEFAULT CHARACTER SET=utf8 COLLATE=utf8_general_ci;"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE t211 (c1 TINYTEXT CHARACTER SET gbk COLLATE gbk_chinese_ci)DEFAULT CHARACTER SET=utf8 COLLATE=utf8_general_ci;"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE t210 (c1 TINYTEXT CHARACTER SET gbk)DEFAULT CHARACTER SET=utf8 COLLATE=utf8_general_ci;"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE t203 (c1 VARCHAR(20) CHARACTER SET gbk COLLATE gbk_chinese_ci)DEFAULT CHARACTER SET=utf8 COLLATE=utf8_general_ci;"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE t197 (c1 CHAR(20) CHARACTER SET gbk COLLATE gbk_bin) DEFAULT CHARACTER SET=utf8 COLLATE=utf8_general_ci;"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE t196 (c1 CHAR(20) CHARACTER SET gbk) DEFAULT CHARACTER SET=utf8 COLLATE=utf8_general_ci;"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE `c_s*s.` (a INT, v VARCHAR(255));"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE `\"$c_s*s.` (a INT, v VARCHAR(255));"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE `'<$c_s*s.` (a INT, v VARCHAR(255));"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE `'c_s*s.` (a INT, v VARCHAR(255));"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

src = "CREATE TABLE `@.` (a INT, v VARCHAR(255));"
_, err = parser.ParseOneStmt(src, "", "")
c.Assert(err, IsNil)

// for #7371, support NATIONAL CHARACTER
// reference link: https://dev.mysql.com/doc/refman/5.7/en/charset-national.html
src = "CREATE TABLE t(c1 NATIONAL CHARACTER(10));"
Expand Down