github-actions[bot] commented on code in PR #68873:
URL: https://github.com/apache/doris/pull/68873#discussion_r4239783790
##########
fe/fe-core/src/main/java/org/apache/doris/datasource/jdbc/source/JdbcScanNode.java:
##########
@@ -213,13 +233,178 @@ private String getTvfQuery() {
if (!projectsTimestamps) {
return query;
}
- String source = query.trim();
- if (source.endsWith(";")) {
- source = source.substring(0, source.length() - 1);
+ boolean mysql = jdbcType == TOdbcTableType.MYSQL || jdbcType ==
TOdbcTableType.OCEANBASE;
+ String source = stripTerminalDelimiter(query.trim(),
+ mysql && mysqlSqlMode.contains("NO_BACKSLASH_ESCAPES"), mysql
&& mysqlSqlMode.contains("ANSI_QUOTES"),
+ mysql && mysqlSqlMode.contains("MSSQL"));
+ // WITH SESSION must stay outside the derived table; terminate
trailing line comments with a newline.
+ int start = jdbcType == TOdbcTableType.TRINO ?
trinoSessionQueryStart(source) : 0;
+ return source.substring(0, start) + "SELECT " + Joiner.on(",
").join(columns)
+ + " FROM (" + source.substring(start) + "\n)
doris_jdbc_source";
+ }
+
+ private String stripTerminalDelimiter(String sql, boolean
noBackslashEscapes, boolean ansiQuotes, boolean mssql) {
+ boolean mysql = jdbcType == TOdbcTableType.MYSQL || jdbcType ==
TOdbcTableType.OCEANBASE;
+ List<Integer> delimiters = new java.util.ArrayList<>();
+ for (int i = 0; i < sql.length();) {
+ char c = sql.charAt(i);
+ if (Character.isWhitespace(c)) {
+ i++;
+ } else if (jdbcType == TOdbcTableType.CLICKHOUSE
+ && (sql.startsWith("//", i) || sql.startsWith("#!", i) ||
sql.startsWith("# ", i))) {
+ // ClickHouse comments may contain unmatched quotes; their
contents end only at LF.
+ int newline = sql.indexOf('\n', i + 2);
+ i = newline < 0 ? sql.length() : newline + 1;
+ // MySQL's second dash needs a following whitespace/control
character; --1 is arithmetic.
+ } else if ((sql.startsWith("--", i) && (!mysql || (i + 2 <
sql.length()
+ && (Character.isWhitespace(sql.charAt(i + 2)) ||
Character.isISOControl(sql.charAt(i + 2))))))
+ || (c == '#'
+ && (jdbcType == TOdbcTableType.MYSQL || jdbcType ==
TOdbcTableType.OCEANBASE))) {
+ while (i < sql.length() && sql.charAt(i) != '\n' &&
sql.charAt(i) != '\r') {
+ i++;
+ }
+ } else if (sql.startsWith("/*", i)) {
+ i = skipBlockComment(sql, i, jdbcType ==
TOdbcTableType.CLICKHOUSE);
Review Comment:
[P2] Scan ClickHouse Unicode-quoted tokens before ASCII quotes. ClickHouse
v25.8 accepts `“a'b”` as a quoted identifier. For a TIMESTAMPTZ TVF source
`SELECT ts, 1 AS “a'b” FROM t;`, this scanner treats the apostrophe inside the
identifier as an opening string quote and leaves the terminal `;`, generating
`FROM (SELECT ts, 1 AS “a'b” FROM t;\n)`, which is invalid. The previous
wrapper removed the final delimiter. Recognize ClickHouse's Unicode quote pairs
as whole tokens and add a TVF case. This is a distinct lexical form from the
reported bracket, heredoc, comment, and backtick cases. See the [ClickHouse
lexer](https://raw.githubusercontent.com/ClickHouse/ClickHouse/v25.8.1.5101-lts/src/Parsers/Lexer.cpp).
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
