Merge pull request #50216 from azat/fix-asts

Fix UB for INTO OUTFILE extensions (APPEND / AND STDOUT) and WATCH EVENTS

src/Parsers/ASTColumnDeclaration.h

@@ -16,7 +16,7 @@ public:
     std::optional<bool> null_modifier;
     String default_specifier;
     ASTPtr default_expression;
-    bool ephemeral_default;
+    bool ephemeral_default = false;
     ASTPtr comment;
     ASTPtr codec;
     ASTPtr ttl;

src/Parsers/ASTDictionaryAttributeDeclaration.h

@@ -19,13 +19,13 @@ public:
     /// Attribute expression
     ASTPtr expression;
     /// Is attribute mirrored to the parent identifier
-    bool hierarchical;
+    bool hierarchical = false;
     /// Is hierarchical attribute bidirectional
-    bool bidirectional;
+    bool bidirectional = false;
     /// Flag that shows whether the id->attribute image is injective
-    bool injective;
+    bool injective = false;
     /// MongoDB object ID
-    bool is_object_id;
+    bool is_object_id = false;
 
     String getID(char delim) const override { return "DictionaryAttributeDeclaration" + (delim + name); }
 

src/Parsers/ASTOrderByElement.h

@@ -11,14 +11,14 @@ namespace DB
 class ASTOrderByElement : public IAST
 {
 public:
-    int direction; /// 1 for ASC, -1 for DESC
-    int nulls_direction; /// Same as direction for NULLS LAST, opposite for NULLS FIRST.
-    bool nulls_direction_was_explicitly_specified;
+    int direction = 0; /// 1 for ASC, -1 for DESC
+    int nulls_direction = 0; /// Same as direction for NULLS LAST, opposite for NULLS FIRST.
+    bool nulls_direction_was_explicitly_specified = false;
 
     /** Collation for locale-specific string comparison. If empty, then sorting done by bytes. */
     ASTPtr collation;
 
-    bool with_fill;
+    bool with_fill = false;
     ASTPtr fill_from;
     ASTPtr fill_to;
     ASTPtr fill_step;

src/Parsers/ASTQueryWithOutput.cpp

@@ -35,6 +35,13 @@ void ASTQueryWithOutput::formatImpl(const FormatSettings & s, FormatState & stat
     {
         s.ostr << (s.hilite ? hilite_keyword : "") << s.nl_or_ws << indent_str << "INTO OUTFILE " << (s.hilite ? hilite_none : "");
         out_file->formatImpl(s, state, frame);
+
+        s.ostr << (s.hilite ? hilite_keyword : "");
+        if (is_outfile_append)
+            s.ostr << " APPEND";
+        if (is_into_outfile_with_stdout)
+            s.ostr << " AND STDOUT";
+        s.ostr << (s.hilite ? hilite_none : "");
     }
 
     if (format)

src/Parsers/ASTQueryWithOutput.h

@@ -15,8 +15,8 @@ class ASTQueryWithOutput : public IAST
 {
 public:
     ASTPtr out_file;
-    bool is_into_outfile_with_stdout;
-    bool is_outfile_append;
+    bool is_into_outfile_with_stdout = false;
+    bool is_outfile_append = false;
     ASTPtr format;
     ASTPtr settings_ast;
     ASTPtr compression;

src/Parsers/ASTWatchQuery.h

@@ -23,7 +23,7 @@ class ASTWatchQuery : public ASTQueryWithTableAndOutput
 
 public:
     ASTPtr limit_length;
-    bool is_watch_events;
+    bool is_watch_events = false;
 
     ASTWatchQuery() = default;
     String getID(char) const override { return "WatchQuery_" + getDatabase() + "_" + getTable(); }

tests/queries/0_stateless/02767_into_outfile_extensions_msan.reference

@@ -0,0 +1,2 @@
+Expression ((Projection + Before ORDER BY))
+  ReadFromStorage (SystemNumbers)

tests/queries/0_stateless/02767_into_outfile_extensions_msan.sh

@@ -0,0 +1,11 @@
+#!/usr/bin/env bash
+
+CUR_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+# shellcheck source=../shell_config.sh
+. "$CUR_DIR"/../shell_config.sh
+
+out="explain1.$CLICKHOUSE_TEST_UNIQUE_NAME.out"
+# only EXPLAIN triggers the problem under MSan
+$CLICKHOUSE_CLIENT -q "explain select * from numbers(1) into outfile '$out'"
+cat "$out"
+rm -f "$out"

tests/queries/0_stateless/02768_into_outfile_extensions_format.reference

@@ -0,0 +1,20 @@
+SELECT *
+FROM numbers(1)
+INTO OUTFILE '/dev/null'
+;
+
+SELECT *
+FROM numbers(1)
+INTO OUTFILE '/dev/null' AND STDOUT
+;
+
+SELECT *
+FROM numbers(1)
+INTO OUTFILE '/dev/null' APPEND
+;
+
+SELECT *
+FROM numbers(1)
+INTO OUTFILE '/dev/null' APPEND AND STDOUT
+;
+

tests/queries/0_stateless/02768_into_outfile_extensions_format.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+
+CUR_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+# shellcheck source=../shell_config.sh
+. "$CUR_DIR"/../shell_config.sh
+
+echo "
+select * from numbers(1) into outfile '/dev/null';
+select * from numbers(1) into outfile '/dev/null' and stdout;
+select * from numbers(1) into outfile '/dev/null' append;
+select * from numbers(1) into outfile '/dev/null' append and stdout;
+" | clickhouse-format -n