Merge pull request #52635 from hendrik-m/table-names-as-string-literal

Allow writing table name as a string literal

docs/en/operations/utilities/clickhouse-local.md

@@ -34,7 +34,13 @@ The binary you just downloaded can run all sorts of ClickHouse tools and utiliti
 
 A common use of `clickhouse-local` is to run ad-hoc queries on files: where you don't have to insert the data into a table. `clickhouse-local` can stream the data from a file into a temporary table and execute your SQL.
 
-If the file is sitting on the same machine as `clickhouse-local`, use the `file` table engine. The following `reviews.tsv` file contains a sampling of Amazon product reviews:
+If the file is sitting on the same machine as `clickhouse-local`, you can simple specify the file to load. The following `reviews.tsv` file contains a sampling of Amazon product reviews:
+
+```bash
+./clickhouse local -q "SELECT * FROM 'reviews.tsv'"
+```
+
+This command is a shortcut of:
 
 ```bash
 ./clickhouse local -q "SELECT * FROM file('reviews.tsv')"

src/Parsers/ExpressionElementParsers.cpp

@@ -243,6 +243,38 @@ bool ParserIdentifier::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
 }
 
 
+bool ParserTableAsStringLiteralIdentifier::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
+{
+    if (pos->type != TokenType::StringLiteral)
+        return false;
+
+    ReadBufferFromMemory in(pos->begin, pos->size());
+    String s;
+
+    if (!tryReadQuotedStringInto(s, in))
+    {
+        expected.add(pos, "string literal");
+        return false;
+    }
+
+    if (in.count() != pos->size())
+    {
+        expected.add(pos, "string literal");
+        return false;
+    }
+
+    if (s.empty())
+    {
+        expected.add(pos, "non-empty string literal");
+        return false;
+    }
+
+    node = std::make_shared<ASTTableIdentifier>(s);
+    ++pos;
+    return true;
+}
+
+
 bool ParserCompoundIdentifier::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
 {
     ASTPtr id_list;

src/Parsers/ExpressionElementParsers.h

@@ -34,6 +34,19 @@ protected:
 };
 
 
+/** An identifier for tables written as string literal, for example, 'mytable.avro'
+  */
+class ParserTableAsStringLiteralIdentifier : public IParserBase
+{
+public:
+    explicit ParserTableAsStringLiteralIdentifier() {}
+
+protected:
+    const char * getName() const override { return "string literal table identifier"; }
+    bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override;
+};
+
+
 /** An identifier, possibly containing a dot, for example, x_yz123 or `something special` or Hits.EventTime,
  *  possibly with UUID clause like `db name`.`table name` UUID 'xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx'
   */

src/Parsers/ParserTablesInSelectQuery.cpp

@@ -24,6 +24,8 @@ bool ParserTableExpression::parseImpl(Pos & pos, ASTPtr & node, Expected & expec
     if (!ParserWithOptionalAlias(std::make_unique<ParserSubquery>(), allow_alias_without_as_keyword).parse(pos, res->subquery, expected)
         && !ParserWithOptionalAlias(std::make_unique<ParserFunction>(false, true), allow_alias_without_as_keyword).parse(pos, res->table_function, expected)
         && !ParserWithOptionalAlias(std::make_unique<ParserCompoundIdentifier>(true, true), allow_alias_without_as_keyword)
+                .parse(pos, res->database_and_table_name, expected)
+        && !ParserWithOptionalAlias(std::make_unique<ParserTableAsStringLiteralIdentifier>(), allow_alias_without_as_keyword)
                 .parse(pos, res->database_and_table_name, expected))
         return false;
 

tests/queries/0_stateless/02816_clickhouse_local_table_name_expressions.reference

@@ -0,0 +1,27 @@
+Test 1: check double quotes
+1	abc	123	abacaba
+2	def	456	bacabaa
+3	story	78912	acabaab
+4	history	21321321	cabaaba
+Test 1a: check double quotes no parsing overflow
+1
+Test 1b: check double quotes empty
+1
+Test 2: check back quotes
+1	abc	123	abacaba
+2	def	456	bacabaa
+3	story	78912	acabaab
+4	history	21321321	cabaaba
+Test 2a: check back quotes no parsing overflow
+1
+Test 2b: check back quotes empty
+1
+Test 3: check literal
+1	abc	123	abacaba
+2	def	456	bacabaa
+3	story	78912	acabaab
+4	history	21321321	cabaaba
+Test 3a: check literal no parsing overflow
+1
+Test 3b: check literal empty
+1

tests/queries/0_stateless/02816_clickhouse_local_table_name_expressions.sh

@@ -0,0 +1,56 @@
+#!/usr/bin/env bash
+
+CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+# shellcheck source=../shell_config.sh
+. "$CURDIR"/../shell_config.sh
+
+dir=${CLICKHOUSE_TEST_UNIQUE_NAME}
+[[ -d $dir ]] && rm -rd $dir
+mkdir $dir
+
+# Create temporary csv file for tests
+echo '"id","str","int","text"' > $dir/tmp.csv
+echo '1,"abc",123,"abacaba"' >> $dir/tmp.csv
+echo '2,"def",456,"bacabaa"' >> $dir/tmp.csv
+echo '3,"story",78912,"acabaab"' >> $dir/tmp.csv
+echo '4,"history",21321321,"cabaaba"' >> $dir/tmp.csv
+
+#################
+echo "Test 1: check double quotes"
+
+$CLICKHOUSE_LOCAL -q "SELECT * FROM \"${dir}/tmp.csv\""
+#################
+echo "Test 1a: check double quotes no parsing overflow"
+
+$CLICKHOUSE_LOCAL -q "SELECT * FROM \"${dir}/tmp.csv\"\"bad\"" 2>&1 | grep -c "UNKNOWN_TABLE"
+#################
+echo "Test 1b: check double quotes empty"
+
+$CLICKHOUSE_LOCAL -q "SELECT * FROM \"\"" 2>&1 | grep -c "SYNTAX_ERROR"
+#################
+echo "Test 2: check back quotes"
+
+$CLICKHOUSE_LOCAL -q "SELECT * FROM \`${dir}/tmp.csv\`"
+#################
+echo "Test 2a: check back quotes no parsing overflow"
+
+$CLICKHOUSE_LOCAL -q "SELECT * FROM \`${dir}/tmp.csv\`\`bad\`" 2>&1 | grep -c "UNKNOWN_TABLE"
+#################
+echo "Test 2b: check back quotes empty"
+
+$CLICKHOUSE_LOCAL -q "SELECT * FROM \`\`" 2>&1 | grep -c "SYNTAX_ERROR"
+#################
+echo "Test 3: check literal"
+
+$CLICKHOUSE_LOCAL -q "SELECT * FROM '${dir}/tmp.csv'"
+#################
+echo "Test 3a: check literal no parsing overflow"
+
+$CLICKHOUSE_LOCAL -q "SELECT * FROM '${dir}/tmp.csv''bad'" 2>&1 | grep -c "SYNTAX_ERROR"
+#################
+echo "Test 3b: check literal empty"
+
+$CLICKHOUSE_LOCAL -q "SELECT * FROM ''" 2>&1 | grep -c "SYNTAX_ERROR"
+
+# Remove temporary dir with files
+rm -rd $dir