Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
22 changes: 20 additions & 2 deletions parser/lexer.go
Original file line number Diff line number Diff line change
Expand Up @@ -249,10 +249,28 @@ func (l *Lexer) consumeMultiLineComment() {
func (l *Lexer) consumeString() error {
i := 1
endChar := byte('\'')
for l.peekOk(i) && l.peekN(i) != endChar {
for l.peekOk(i) {
c := l.peekN(i)
// backslash escape
if c == '\\' {
i++
if l.peekOk(i) {
i++
}
continue
}
// single quote
if c == endChar {
// double single quote ''
if l.peekOk(i+1) && l.peekN(i+1) == endChar {
i += 2
continue
}
break
}
i++
}
if !l.peekOk(i) {
if !l.peekOk(i) || l.peekN(i) != endChar {
return errors.New("invalid string")
}
l.lastToken = &Token{
Expand Down
82 changes: 70 additions & 12 deletions parser/lexer_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -32,18 +32,76 @@ func TestConsumeComment(t *testing.T) {
}

func TestConsumeString(t *testing.T) {
strs := []string{
"'hello world'",
"'123'",
}
for _, s := range strs {
lexer := NewLexer(s)
err := lexer.consumeToken()
require.NoError(t, err)
require.Equal(t, TokenKindString, lexer.lastToken.Kind)
require.Equal(t, strings.Trim(s, "'"), lexer.lastToken.String)
require.True(t, lexer.isEOF())
}
t.Run("Simple strings", func(t *testing.T) {
strs := []string{
"'hello world'",
"'123'",
}
for _, s := range strs {
lexer := NewLexer(s)
err := lexer.consumeToken()
require.NoError(t, err)
require.Equal(t, TokenKindString, lexer.lastToken.Kind)
require.Equal(t, strings.Trim(s, "'"), lexer.lastToken.String)
require.True(t, lexer.isEOF())
}
})

t.Run("Strings with backslash-escaped quotes", func(t *testing.T) {
testCases := []struct {
input string
expected string
}{
{`'hello\'world'`, `hello\'world`},
{`'test\''`, `test\'`},
{`'\'abc\''`, `\'abc\'`},
}
for _, tc := range testCases {
lexer := NewLexer(tc.input)
err := lexer.consumeToken()
require.NoError(t, err, "Failed to parse: %s", tc.input)
require.Equal(t, TokenKindString, lexer.lastToken.Kind)
require.Equal(t, tc.expected, lexer.lastToken.String)
require.True(t, lexer.isEOF())
}
})

t.Run("Strings with double single quotes", func(t *testing.T) {
testCases := []struct {
input string
expected string
}{
{`'hello''world'`, `hello''world`},
{`'test''123'`, `test''123`},
{`'abc''def''ghi'`, `abc''def''ghi`},
}
for _, tc := range testCases {
lexer := NewLexer(tc.input)
err := lexer.consumeToken()
require.NoError(t, err, "Failed to parse: %s", tc.input)
require.Equal(t, TokenKindString, lexer.lastToken.Kind)
require.Equal(t, tc.expected, lexer.lastToken.String)
require.True(t, lexer.isEOF())
}
})

t.Run("Strings with backslash-escaped backslashes", func(t *testing.T) {
testCases := []struct {
input string
expected string
}{
{`'a\\b'`, `a\\b`},
{`'test\\123'`, `test\\123`},
}
for _, tc := range testCases {
lexer := NewLexer(tc.input)
err := lexer.consumeToken()
require.NoError(t, err, "Failed to parse: %s", tc.input)
require.Equal(t, TokenKindString, lexer.lastToken.Kind)
require.Equal(t, tc.expected, lexer.lastToken.String)
require.True(t, lexer.isEOF())
}
})
}

func TestConsumeNumber(t *testing.T) {
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
-- Origin SQL:
SELECT * FROM test_table SETTINGS additional_table_filters={'test_table': 'status = 1'};

SELECT * FROM test_table SETTINGS additional_table_filters={'test_table': 'value = \'test\''};

SELECT * FROM test_table SETTINGS additional_table_filters={'test_table': 'value = ''test'''};

SELECT * FROM test_table
SETTINGS additional_table_filters={'test_table': 'id IN (\'a\', \'b\') AND status = \'active\''}
FORMAT JSON;

SELECT number, x, y FROM (SELECT number FROM system.numbers LIMIT 5) f
ANY LEFT JOIN (SELECT x, y FROM table_1) s ON f.number = s.x
SETTINGS additional_table_filters={'system.numbers':'number != 3', 'table_1':'x != 2'};


-- Format SQL:
SELECT * FROM test_table SETTINGS additional_table_filters={'test_table': 'status = 1'};
SELECT * FROM test_table SETTINGS additional_table_filters={'test_table': 'value = \'test\''};
SELECT * FROM test_table SETTINGS additional_table_filters={'test_table': 'value = ''test'''};
SELECT * FROM test_table SETTINGS additional_table_filters={'test_table': 'id IN (\'a\', \'b\') AND status = \'active\''} FORMAT JSON;
SELECT number, x, y FROM (SELECT number FROM system.numbers LIMIT 5) AS f ANY LEFT JOIN (SELECT x, y FROM table_1) AS s ON f.number = s.x SETTINGS additional_table_filters={'system.numbers': 'number != 3', 'table_1': 'x != 2'};
Loading