support #114 add heuristic rule KWR.004

dc6d2b3c · martianzhang · 147ee2d0 · dc6d2b3c · dc6d2b3c · dc6d2b3c
7 changed file
--- a/advisor/heuristic.go
+++ b/advisor/heuristic.go
@@ -22,6 +22,7 @@ import (
 	"regexp"
 	"strconv"
 	"strings"
+	"unicode/utf8"

 	"github.com/XiaoMi/soar/ast"
 	"github.com/XiaoMi/soar/common"
@@ -1393,6 +1394,22 @@ func (q *Query4Audit) RulePluralWord() Rule {
 	return rule
 }

+// RuleMultiBytesWord KWR.004
+func (q *Query4Audit) RuleMultiBytesWord() Rule {
+	// TODO: 目前使用 utf8 字符集检查，其他字符集输入可能会有问题
+	var rule = q.RuleOK()
+	for _, tk := range ast.Tokenize(q.Query) {
+		switch tk.Type {
+		case ast.TokenTypeBacktickQuote, ast.TokenTypeWord:
+			if utf8.RuneCountInString(tk.Val) != len(tk.Val) {
+				rule = HeuristicRules["KWR.004"]
+			}
+		default:
+		}
+	}
+	return rule
+}
+
 // RuleInsertSelect LCK.001
 func (q *Query4Audit) RuleInsertSelect() Rule {
 	var rule = q.RuleOK()
@@ -3177,7 +3194,7 @@ func (q *Query4Audit) RuleStandardName() Rule {
 				rule = HeuristicRules["STA.004"]
 			}
 		case ast.TokenTypeWord:
-			// TOKEN_TYPE_WORD中处理连续下划线的情况，其他情况容易误伤
+			// TOKEN_TYPE_WORD 中处理连续下划线的情况，其他情况容易误伤
 			if strings.Contains(tk.Val, "__") {
 				rule = HeuristicRules["STA.004"]
 			}

--- a/advisor/heuristic_test.go
+++ b/advisor/heuristic_test.go
@@ -1035,6 +1035,44 @@ func TestRulePluralWord(t *testing.T) {
 	common.Log.Debug("Exiting function: %s", common.GetFunctionName())
 }

+// KWR.004
+func TestRuleMultiBytesWord(t *testing.T) {
+	common.Log.Debug("Entering function: %s", common.GetFunctionName())
+	sqls := [][]string{
+		{
+			"select col as 列 from tb",
+			"select col as `列` from tb",
+		},
+		{
+			"select col as c from tb",
+			"select '列'",
+		},
+	}
+	for _, sql := range sqls[0] {
+		q, err := NewQuery4Audit(sql)
+		if err == nil {
+			rule := q.RuleMultiBytesWord()
+			if rule.Item != "KWR.004" {
+				t.Error("Rule not match:", rule.Item, "Expect : KWR.004")
+			}
+		} else {
+			t.Error("sqlparser.Parse Error:", err)
+		}
+	}
+	for _, sql := range sqls[1] {
+		q, err := NewQuery4Audit(sql)
+		if err == nil {
+			rule := q.RuleMultiBytesWord()
+			if rule.Item != "OK" {
+				t.Error("Rule not match:", rule.Item, "Expect : OK")
+			}
+		} else {
+			t.Error("sqlparser.Parse Error:", err)
+		}
+	}
+	common.Log.Debug("Exiting function: %s", common.GetFunctionName())
+}
+
 // LCK.001
 func TestRuleInsertSelect(t *testing.T) {
 	common.Log.Debug("Entering function: %s", common.GetFunctionName())

--- a/advisor/rules.go
+++ b/advisor/rules.go
@@ -797,6 +797,14 @@ func init() {
 			Case:     "CREATE TABLE tbl ( `books` int )",
 			Func:     (*Query4Audit).RulePluralWord,
 		},
+		"KWR.004": {
+			Item:     "KWR.004",
+			Severity: "L1",
+			Summary:  "不建议使用使用多字节编码字符(中文)命名",
+			Content:  `为库、表、列、别名命名时建议使用英文，数字，下划线等字符，不建议使用中文或其他多字节编码字符。`,
+			Case:     "select col as 列 from tb",
+			Func:     (*Query4Audit).RuleMultiBytesWord,
+		},
 		"LCK.001": {
 			Item:     "LCK.001",
 			Severity: "L3",

--- a/advisor/testdata/TestListHeuristicRules.golden
+++ b/advisor/testdata/TestListHeuristicRules.golden
@@ -812,6 +812,16 @@ CREATE TABLE tbl ( `select` int )
 ```sql
 CREATE TABLE tbl ( `books` int )
 ```
+## 不建议使用使用多字节编码字符(中文)命名
+
+* **Item**:KWR.004
+* **Severity**:L1
+* **Content**:为库、表、列、别名命名时建议使用英文，数字，下划线等字符，不建议使用中文或其他多字节编码字符。
+* **Case**:
+
+```sql
+select col as 列 from tb
+```
 ## INSERT INTO xx SELECT 加锁粒度较大请谨慎

 * **Item**:LCK.001

--- a/advisor/testdata/TestMergeConflictHeuristicRules.golden
+++ b/advisor/testdata/TestMergeConflictHeuristicRules.golden
@@ -75,6 +75,7 @@ advisor.Rule{Item:"KEY.009", Severity:"L0", Summary:"添加唯一索引前请注
 advisor.Rule{Item:"KWR.001", Severity:"L2", Summary:"SQL_CALC_FOUND_ROWS 效率低下", Content:"因为 SQL_CALC_FOUND_ROWS 不能很好地扩展，所以可能导致性能问题; 建议业务使用其他策略来替代 SQL_CALC_FOUND_ROWS 提供的计数功能，比如：分页结果展示等。", Case:"select SQL_CALC_FOUND_ROWS col from tbl where id>1000", Position:0, Func:func(*advisor.Query4Audit) advisor.Rule {...}}
 advisor.Rule{Item:"KWR.002", Severity:"L2", Summary:"不建议使用 MySQL 关键字做列名或表名", Content:"当使用关键字做为列名或表名时程序需要对列名和表名进行转义，如果疏忽被将导致请求无法执行。", Case:"CREATE TABLE tbl ( `select` int )", Position:0, Func:func(*advisor.Query4Audit) advisor.Rule {...}}
 advisor.Rule{Item:"KWR.003", Severity:"L1", Summary:"不建议使用复数做列名或表名", Content:"表名应该仅仅表示表里面的实体内容，不应该表示实体数量，对应于 DO 类名也是单数形式，符合表达习惯。", Case:"CREATE TABLE tbl ( `books` int )", Position:0, Func:func(*advisor.Query4Audit) advisor.Rule {...}}
+advisor.Rule{Item:"KWR.004", Severity:"L1", Summary:"不建议使用使用多字节编码字符(中文)命名", Content:"为库、表、列、别名命名时建议使用英文，数字，下划线等字符，不建议使用中文或其他多字节编码字符。", Case:"select col as 列 from tb", Position:0, Func:func(*advisor.Query4Audit) advisor.Rule {...}}
 advisor.Rule{Item:"LCK.001", Severity:"L3", Summary:"INSERT INTO xx SELECT 加锁粒度较大请谨慎", Content:"INSERT INTO xx SELECT 加锁粒度较大请谨慎", Case:"INSERT INTO tbl SELECT * FROM tbl2;", Position:0, Func:func(*advisor.Query4Audit) advisor.Rule {...}}
 advisor.Rule{Item:"LCK.002", Severity:"L3", Summary:"请慎用 INSERT ON DUPLICATE KEY UPDATE", Content:"当主键为自增键时使用 INSERT ON DUPLICATE KEY UPDATE 可能会导致主键出现大量不连续快速增长，导致主键快速溢出无法继续写入。极端情况下还有可能导致主从数据不一致。", Case:"INSERT INTO t1(a,b,c) VALUES (1,2,3) ON DUPLICATE KEY UPDATE c=c+1;", Position:0, Func:func(*advisor.Query4Audit) advisor.Rule {...}}
 advisor.Rule{Item:"LIT.001", Severity:"L2", Summary:"用字符类型存储IP地址", Content:"字符串字面上看起来像IP地址，但不是 INET_ATON() 的参数，表示数据被存储为字符而不是整数。将IP地址存储为整数更为有效。", Case:"insert into tbl (IP,name) values('10.20.306.122','test')", Position:0, Func:func(*advisor.Query4Audit) advisor.Rule {...}}

--- a/doc/heuristic.md
+++ b/doc/heuristic.md
@@ -812,6 +812,16 @@ CREATE TABLE tbl ( `select` int )
 ```sql
 CREATE TABLE tbl ( `books` int )
 ```
+## 不建议使用使用多字节编码字符(中文)命名
+
+* **Item**:KWR.004
+* **Severity**:L1
+* **Content**:为库、表、列、别名命名时建议使用英文，数字，下划线等字符，不建议使用中文或其他多字节编码字符。
+* **Case**:
+
+```sql
+select col as 列 from tb
+```
 ## INSERT INTO xx SELECT 加锁粒度较大请谨慎

 * **Item**:LCK.001

--- a/vendor/vendor.json
+++ b/vendor/vendor.json
@@ -1034,68 +1034,68 @@
 		{
 			"checksumSHA1": "q7Bd5YJHsxvzEpiOBaYn+wEpqyU=",
 			"path": "vitess.io/vitess",
-			"revision": "b0d2eee6a26cd87bbc748e2bd07fefaa44ef59be",
-			"revisionTime": "2018-11-19T18:27:10Z"
+			"revision": "32dd398dd5459e5cf15904db35aba7460519b612",
+			"revisionTime": "2018-11-22T02:19:16Z"
 		},
 		{
 			"checksumSHA1": "aKn1oKcY74N8TRLm3Ayt7Q4bbI4=",
 			"path": "vitess.io/vitess/go/bytes2",
-			"revision": "b0d2eee6a26cd87bbc748e2bd07fefaa44ef59be",
-			"revisionTime": "2018-11-19T18:27:10Z"
+			"revision": "32dd398dd5459e5cf15904db35aba7460519b612",
+			"revisionTime": "2018-11-22T02:19:16Z"
 		},
 		{
 			"checksumSHA1": "JVCEN4UGRmg3TofIBdzZMZ3G0Ww=",
 			"path": "vitess.io/vitess/go/hack",
-			"revision": "b0d2eee6a26cd87bbc748e2bd07fefaa44ef59be",
-			"revisionTime": "2018-11-19T18:27:10Z"
+			"revision": "32dd398dd5459e5cf15904db35aba7460519b612",
+			"revisionTime": "2018-11-22T02:19:16Z"
 		},
 		{
 			"checksumSHA1": "e1WJ7vCnVrlQQQlc6n/FewCDMso=",
 			"path": "vitess.io/vitess/go/sqltypes",
-			"revision": "b0d2eee6a26cd87bbc748e2bd07fefaa44ef59be",
-			"revisionTime": "2018-11-19T18:27:10Z"
+			"revision": "32dd398dd5459e5cf15904db35aba7460519b612",
+			"revisionTime": "2018-11-22T02:19:16Z"
 		},
 		{
 			"checksumSHA1": "ntFIQYkBS51G6y+FEkjFW40+HOU=",
 			"path": "vitess.io/vitess/go/vt/log",
-			"revision": "b0d2eee6a26cd87bbc748e2bd07fefaa44ef59be",
-			"revisionTime": "2018-11-19T18:27:10Z"
+			"revision": "32dd398dd5459e5cf15904db35aba7460519b612",
+			"revisionTime": "2018-11-22T02:19:16Z"
 		},
 		{
 			"checksumSHA1": "XozR8bmeSR5KTe/nlUJkpJY2HKI=",
 			"path": "vitess.io/vitess/go/vt/proto/query",
-			"revision": "b0d2eee6a26cd87bbc748e2bd07fefaa44ef59be",
-			"revisionTime": "2018-11-19T18:27:10Z"
+			"revision": "32dd398dd5459e5cf15904db35aba7460519b612",
+			"revisionTime": "2018-11-22T02:19:16Z"
 		},
 		{
 			"checksumSHA1": "OnWsUHLDKcO3spwH0jD55SvKD24=",
 			"path": "vitess.io/vitess/go/vt/proto/topodata",
-			"revision": "b0d2eee6a26cd87bbc748e2bd07fefaa44ef59be",
-			"revisionTime": "2018-11-19T18:27:10Z"
+			"revision": "32dd398dd5459e5cf15904db35aba7460519b612",
+			"revisionTime": "2018-11-22T02:19:16Z"
 		},
 		{
 			"checksumSHA1": "sBAuZ/itMR8U8qbK4yLHxkP6Cpc=",
 			"path": "vitess.io/vitess/go/vt/proto/vtgate",
-			"revision": "b0d2eee6a26cd87bbc748e2bd07fefaa44ef59be",
-			"revisionTime": "2018-11-19T18:27:10Z"
+			"revision": "32dd398dd5459e5cf15904db35aba7460519b612",
+			"revisionTime": "2018-11-22T02:19:16Z"
 		},
 		{
 			"checksumSHA1": "pLWM+SPGZs3k+IhjktE/cGUlpM0=",
 			"path": "vitess.io/vitess/go/vt/proto/vtrpc",
-			"revision": "b0d2eee6a26cd87bbc748e2bd07fefaa44ef59be",
-			"revisionTime": "2018-11-19T18:27:10Z"
+			"revision": "32dd398dd5459e5cf15904db35aba7460519b612",
+			"revisionTime": "2018-11-22T02:19:16Z"
 		},
 		{
 			"checksumSHA1": "2ZBC/pPjs13cocUf8PoMSvAO5u4=",
 			"path": "vitess.io/vitess/go/vt/sqlparser",
-			"revision": "b0d2eee6a26cd87bbc748e2bd07fefaa44ef59be",
-			"revisionTime": "2018-11-19T18:27:10Z"
+			"revision": "32dd398dd5459e5cf15904db35aba7460519b612",
+			"revisionTime": "2018-11-22T02:19:16Z"
 		},
 		{
 			"checksumSHA1": "oF4XzuOzwvj1iduX/lYqNSyY/HM=",
 			"path": "vitess.io/vitess/go/vt/vterrors",
-			"revision": "b0d2eee6a26cd87bbc748e2bd07fefaa44ef59be",
-			"revisionTime": "2018-11-19T18:27:10Z"
+			"revision": "32dd398dd5459e5cf15904db35aba7460519b612",
+			"revisionTime": "2018-11-22T02:19:16Z"
 		}
 	],
 	"rootPath": "github.com/XiaoMi/soar"