Skip to content

[Feature] Support KeepUnicodeEscape feature to fix Hive regex parsing… #6578

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

Open
aoeiuvb wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[Feature] Support KeepUnicodeEscape feature to fix Hive regex parsing… #6578

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
42 changes: 7 additions & 35 deletions core/src/main/java/com/alibaba/druid/sql/dialect/hive/parser/HiveLexer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,7 @@ public class HiveLexer extends Lexer {
PrimaryBangBangSupport
)
);

static {
Map<String, Token> map = new HashMap<>();

Expand Down Expand Up @@ -180,43 +181,13 @@ protected void scanString() {
arraycopy(mark + 1, buf, 0, bufPos);
hasSpecial = true;
}

switch (ch) {
case '0':
putChar('\0');
break;
case '\'':
putChar('\'');
break;
case '"':
putChar('"');
break;
case 'b':
putChar('\b');
break;
case 'n':
putChar('\n');
break;
case 'r':
putChar('\r');
break;
case 't':
putChar('\t');
break;
case '\\':
putChar('\\');
break;
case 'Z':
putChar((char) 0x1A); // ctrl + Z
break;
case '%':
putChar('%');
break;
case '_':
putChar('_');
break;
// only deal with unicode other remains the same
case 'u':
if ((features & SQLParserFeature.SupportUnicodeCodePoint.mask) != 0) {
if ((features & SQLParserFeature.KeepUnicodeEscape.mask) != 0) {
putChar('\\');
putChar('u');
} else if ((features & SQLParserFeature.SupportUnicodeCodePoint.mask) != 0) {
int codePointSize = 0;
for (int i = 0; i < 4; i++, codePointSize++) {
char c = charAt(pos + 1 + i);
Expand All @@ -234,6 +205,7 @@ protected void scanString() {
}
break;
default:
putChar('\\');
putChar(ch);
break;
}
Expand Down
3 changes: 2 additions & 1 deletion core/src/main/java/com/alibaba/druid/sql/dialect/hive/visitor/HiveOutputVisitor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -463,7 +463,7 @@ public boolean visit(SQLCharExpr x, boolean parameterized) {
char ch = text.charAt(i);
switch (ch) {
case '\\':
buf.append("\\\\");
buf.append("\\");
break;
case '\'':
buf.append("\\'");
Expand Down Expand Up @@ -521,6 +521,7 @@ protected void printTableOptionsPrefix(SQLCreateTableStatement x) {
public boolean visit(HiveCreateTableStatement x) {
return visit((SQLCreateTableStatement) x);
}

@Override
public boolean visit(SQLCreateTableStatement x) {
printCreateTable(x, true, true);
Expand Down
3 changes: 2 additions & 1 deletion core/src/main/java/com/alibaba/druid/sql/parser/SQLParserFeature.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,8 @@ public enum SQLParserFeature {
Presto,
MySQLSupportStandardComment,

Template;
Template,
KeepUnicodeEscape;

SQLParserFeature() {
mask = (1 << ordinal());
Expand Down
70 changes: 70 additions & 0 deletions core/src/test/java/com/alibaba/druid/bvt/sql/hive/HiveRegContainUnicodeTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
package com.alibaba.druid.bvt.sql.hive;

import com.alibaba.druid.DbType;
import com.alibaba.druid.sql.SQLUtils;
import com.alibaba.druid.sql.ast.SQLStatement;
import com.alibaba.druid.sql.parser.SQLParserFeature;
import com.alibaba.druid.sql.parser.SQLParserUtils;
import com.alibaba.druid.sql.parser.SQLStatementParser;
import com.alibaba.druid.sql.visitor.SchemaStatVisitor;
import com.alibaba.druid.util.JdbcConstants;
import junit.framework.TestCase;

import java.util.List;

public class HiveRegContainUnicodeTest extends TestCase {
public void test_select() throws Exception {
String sql = "SELECT page_views.* " +
"FROM page_views " +
"WHERE page_views.name REGEXP '[\\u4e00-\\u9fa5]{2,}' and page_views.date >= '2008-03-01'";
{
SQLStatementParser parser = SQLParserUtils.createSQLStatementParser(sql, DbType.hive);
List<SQLStatement> statementList = parser.parseStatementList();
String sqlString = SQLUtils.toSQLString(statementList, DbType.hive);
assertEquals("SELECT page_views.*\n" +
"FROM page_views\n" +
"WHERE page_views.name REGEXP '[一-龥]{2,}'\n" +
"\tAND page_views.date >= '2008-03-01'", sqlString);
}

{
SQLStatementParser parser = SQLParserUtils.createSQLStatementParser(sql, DbType.hive);
parser.config(SQLParserFeature.KeepUnicodeEscape, true);
List<SQLStatement> statementList = parser.parseStatementList();
String sqlString = SQLUtils.toSQLString(statementList, DbType.hive);

assertEquals("SELECT page_views.*\n" +
"FROM page_views\n" +
"WHERE page_views.name REGEXP '[\\u4e00-\\u9fa5]{2,}'\n" +
"\tAND page_views.date >= '2008-03-01'", sqlString);
}

{
String fotmat = SQLUtils.format(sql, DbType.hive, null, null, new SQLParserFeature[]{SQLParserFeature.KeepUnicodeEscape});

assertEquals("SELECT page_views.*\n" +
"FROM page_views\n" +
"WHERE page_views.name REGEXP '[\\u4e00-\\u9fa5]{2,}'\n" +
"\tAND page_views.date >= '2008-03-01'", fotmat);
}

{
String origin = "select 'asd' regexp '[\\u4e00-\\u9fa5]{2,}[\\\\s|\\.]'";
SQLStatementParser parser = SQLParserUtils.createSQLStatementParser(origin, DbType.hive);
parser.config(SQLParserFeature.KeepUnicodeEscape, true);
List<SQLStatement> statementList = parser.parseStatementList();
String format = SQLUtils.toSQLString(statementList, DbType.hive);
assertEquals("SELECT 'asd' REGEXP '[\\u4e00-\\u9fa5]{2,}[\\\\s|\\.]'", format);
}

{
String origin = "select 'asd' regexp '[\\u4e00-\\u9fa5]{2,}[\\\\s|\\.]'";
SQLStatementParser parser = SQLParserUtils.createSQLStatementParser(origin, DbType.hive);
List<SQLStatement> statementList = parser.parseStatementList();
String format = SQLUtils.toSQLString(statementList, DbType.hive);
assertEquals("SELECT 'asd' REGEXP '[一-龥]{2,}[\\\\s|\\.]'", format);
}


}
}