Add documentation for data-modifying statements in WITH clauses.

[postgresql] / doc / src / sgml / ref / select.sgml

<!--
doc/src/sgml/ref/select.sgml
PostgreSQL documentation
-->

<refentry id="SQL-SELECT">
 <refmeta>
  <refentrytitle>SELECT</refentrytitle>
  <manvolnum>7</manvolnum>
  <refmiscinfo>SQL - Language Statements</refmiscinfo>
 </refmeta>

 <refnamediv>
  <refname>SELECT</refname>
  <refname>TABLE</refname>
  <refname>WITH</refname>
  <refpurpose>retrieve rows from a table or view</refpurpose>
 </refnamediv>

 <indexterm zone="sql-select">
  <primary>SELECT</primary>
 </indexterm>

 <indexterm zone="sql-select">
  <primary>TABLE command</primary>
 </indexterm>

 <indexterm zone="sql-select">
  <primary>WITH</primary>
  <secondary>in SELECT</secondary>
 </indexterm>

 <refsynopsisdiv>
<synopsis>
[ WITH [ RECURSIVE ] <replaceable class="parameter">with_query</replaceable> [, ...] ]
SELECT [ ALL | DISTINCT [ ON ( <replaceable class="parameter">expression</replaceable> [, ...] ) ] ]
    * | <replaceable class="parameter">expression</replaceable> [ [ AS ] <replaceable class="parameter">output_name</replaceable> ] [, ...]
    [ FROM <replaceable class="parameter">from_item</replaceable> [, ...] ]
    [ WHERE <replaceable class="parameter">condition</replaceable> ]
    [ GROUP BY <replaceable class="parameter">expression</replaceable> [, ...] ]
    [ HAVING <replaceable class="parameter">condition</replaceable> [, ...] ]
    [ WINDOW <replaceable class="parameter">window_name</replaceable> AS ( <replaceable class="parameter">window_definition</replaceable> ) [, ...] ]
    [ { UNION | INTERSECT | EXCEPT } [ ALL | DISTINCT ] <replaceable class="parameter">select</replaceable> ]
    [ ORDER BY <replaceable class="parameter">expression</replaceable> [ ASC | DESC | USING <replaceable class="parameter">operator</replaceable> ] [ NULLS { FIRST | LAST } ] [, ...] ]
    [ LIMIT { <replaceable class="parameter">count</replaceable> | ALL } ]
    [ OFFSET <replaceable class="parameter">start</replaceable> [ ROW | ROWS ] ]
    [ FETCH { FIRST | NEXT } [ <replaceable class="parameter">count</replaceable> ] { ROW | ROWS } ONLY ]
    [ FOR { UPDATE | SHARE } [ OF <replaceable class="parameter">table_name</replaceable> [, ...] ] [ NOWAIT ] [...] ]

<phrase>where <replaceable class="parameter">from_item</replaceable> can be one of:</phrase>

    [ ONLY ] <replaceable class="parameter">table_name</replaceable> [ * ] [ [ AS ] <replaceable class="parameter">alias</replaceable> [ ( <replaceable class="parameter">column_alias</replaceable> [, ...] ) ] ]
    ( <replaceable class="parameter">select</replaceable> ) [ AS ] <replaceable class="parameter">alias</replaceable> [ ( <replaceable class="parameter">column_alias</replaceable> [, ...] ) ]
    <replaceable class="parameter">with_query_name</replaceable> [ [ AS ] <replaceable class="parameter">alias</replaceable> [ ( <replaceable class="parameter">column_alias</replaceable> [, ...] ) ] ]
    <replaceable class="parameter">function_name</replaceable> ( [ <replaceable class="parameter">argument</replaceable> [, ...] ] ) [ AS ] <replaceable class="parameter">alias</replaceable> [ ( <replaceable class="parameter">column_alias</replaceable> [, ...] | <replaceable class="parameter">column_definition</replaceable> [, ...] ) ]
    <replaceable class="parameter">function_name</replaceable> ( [ <replaceable class="parameter">argument</replaceable> [, ...] ] ) AS ( <replaceable class="parameter">column_definition</replaceable> [, ...] )
    <replaceable class="parameter">from_item</replaceable> [ NATURAL ] <replaceable class="parameter">join_type</replaceable> <replaceable class="parameter">from_item</replaceable> [ ON <replaceable class="parameter">join_condition</replaceable> | USING ( <replaceable class="parameter">join_column</replaceable> [, ...] ) ]

<phrase>and <replaceable class="parameter">with_query</replaceable> is:</phrase>

    <replaceable class="parameter">with_query_name</replaceable> [ ( <replaceable class="parameter">column_name</replaceable> [, ...] ) ] AS ( <replaceable class="parameter">select</replaceable> | <replaceable class="parameter">insert</replaceable> | <replaceable class="parameter">update</replaceable> | <replaceable class="parameter">delete</replaceable> )

TABLE [ ONLY ] <replaceable class="parameter">table_name</replaceable> [ * ]
</synopsis>

 </refsynopsisdiv>

 <refsect1>
  <title>Description</title>

  <para>
   <command>SELECT</command> retrieves rows from zero or more tables.
   The general processing of <command>SELECT</command> is as follows:

   <orderedlist>
    <listitem>
     <para>
      All queries in the <literal>WITH</literal> list are computed.
      These effectively serve as temporary tables that can be referenced
      in the <literal>FROM</literal> list.  A <literal>WITH</literal> query
      that is referenced more than once in <literal>FROM</literal> is
      computed only once.
      (See <xref linkend="sql-with" endterm="sql-with-title"> below.)
     </para>
    </listitem>

    <listitem>
     <para>
      All elements in the <literal>FROM</literal> list are computed.
      (Each element in the <literal>FROM</literal> list is a real or
      virtual table.)  If more than one element is specified in the
      <literal>FROM</literal> list, they are cross-joined together.
      (See <xref linkend="sql-from" endterm="sql-from-title"> below.)
     </para>
    </listitem>

    <listitem>
     <para>
      If the <literal>WHERE</literal> clause is specified, all rows
      that do not satisfy the condition are eliminated from the
      output.  (See <xref linkend="sql-where"
      endterm="sql-where-title"> below.)
     </para>
    </listitem>

    <listitem>
     <para>
      If the <literal>GROUP BY</literal> clause is specified, the
      output is combined into groups of rows that match on one or more
      values.  If the <literal>HAVING</literal> clause is present, it
      eliminates groups that do not satisfy the given condition.  (See
      <xref linkend="sql-groupby" endterm="sql-groupby-title"> and
      <xref linkend="sql-having" endterm="sql-having-title"> below.)
     </para>
    </listitem>

    <listitem>
     <para>
      The actual output rows are computed using the
      <command>SELECT</command> output expressions for each selected
      row or row group.  (See
      <xref linkend="sql-select-list" endterm="sql-select-list-title">
      below.)
     </para>
    </listitem>

    <listitem>
     <para>
      <literal>SELECT DISTINCT</literal> eliminates duplicate rows from the
      result.  <literal>SELECT DISTINCT ON</literal> eliminates rows that
      match on all the specified expressions.  <literal>SELECT ALL</literal>
      (the default) will return all candidate rows, including
      duplicates.  (See <xref linkend="sql-distinct"
      endterm="sql-distinct-title"> below.)
     </para>
    </listitem>

    <listitem>
     <para>
      Using the operators <literal>UNION</literal>,
      <literal>INTERSECT</literal>, and <literal>EXCEPT</literal>, the
      output of more than one <command>SELECT</command> statement can
      be combined to form a single result set.  The
      <literal>UNION</literal> operator returns all rows that are in
      one or both of the result sets.  The
      <literal>INTERSECT</literal> operator returns all rows that are
      strictly in both result sets.  The <literal>EXCEPT</literal>
      operator returns the rows that are in the first result set but
      not in the second.  In all three cases, duplicate rows are
      eliminated unless <literal>ALL</literal> is specified.  The noise
      word <literal>DISTINCT</> can be added to explicitly specify
      eliminating duplicate rows.  Notice that <literal>DISTINCT</> is
      the default behavior here, even though <literal>ALL</literal> is
      the default for <command>SELECT</> itself.  (See
      <xref linkend="sql-union" endterm="sql-union-title">, <xref
      linkend="sql-intersect" endterm="sql-intersect-title">, and
      <xref linkend="sql-except" endterm="sql-except-title"> below.)
     </para>
    </listitem>

    <listitem>
     <para>
      If the <literal>ORDER BY</literal> clause is specified, the
      returned rows are sorted in the specified order.  If
      <literal>ORDER BY</literal> is not given, the rows are returned
      in whatever order the system finds fastest to produce.  (See
      <xref linkend="sql-orderby" endterm="sql-orderby-title"> below.)
     </para>
    </listitem>

    <listitem>
     <para>
      If the <literal>LIMIT</literal> (or <literal>FETCH FIRST</literal>) or <literal>OFFSET</literal>
      clause is specified, the <command>SELECT</command> statement
      only returns a subset of the result rows. (See <xref
      linkend="sql-limit" endterm="sql-limit-title"> below.)
     </para>
    </listitem>

    <listitem>
     <para>
      If <literal>FOR UPDATE</literal> or <literal>FOR SHARE</literal>
      is specified, the
      <command>SELECT</command> statement locks the selected rows
      against concurrent updates.  (See <xref linkend="sql-for-update-share"
      endterm="sql-for-update-share-title"> below.)
     </para>
    </listitem>
   </orderedlist>
  </para>

  <para>
   You must have <literal>SELECT</literal> privilege on each column used
   in a <command>SELECT</> command.  The use of <literal>FOR UPDATE</literal>
   or <literal>FOR SHARE</literal> requires
   <literal>UPDATE</literal> privilege as well (for at least one column
   of each table so selected).
  </para>
 </refsect1>

 <refsect1>
  <title>Parameters</title>

  <refsect2 id="SQL-WITH">
   <title id="sql-with-title"><literal>WITH</literal> Clause</title>

   <para>
    The <literal>WITH</literal> clause allows you to specify one or more
    subqueries that can be referenced by name in the primary query.
    The subqueries effectively act as temporary tables or views
    for the duration of the primary query.
    Each subquery can be a <command>SELECT</command>,
    <command>INSERT</command>, <command>UPDATE</command> or
    <command>DELETE</command> statement.
    When writing a data-modifying statement (<command>INSERT</command>,
    <command>UPDATE</command> or <command>DELETE</command>) in
    <literal>WITH</>, it is usual to include a <literal>RETURNING</> clause.
    It is the output of <literal>RETURNING</>, <emphasis>not</> the underlying
    table that the statement modifies, that forms the temporary table that is
    read by the primary query.  If <literal>RETURNING</> is omitted, the
    statement is still executed, but it produces no output so it cannot be
    referenced as a table by the primary query.
   </para>

   <para>
    A name (without schema qualification) must be specified for each
    <literal>WITH</literal> query.  Optionally, a list of column names
    can be specified; if this is omitted,
    the column names are inferred from the subquery.
   </para>

   <para>
    If <literal>RECURSIVE</literal> is specified, it allows a
    <command>SELECT</command> subquery to reference itself by name.  Such a
    subquery must have the form
<synopsis>
<replaceable class="parameter">non_recursive_term</replaceable> UNION [ ALL | DISTINCT ] <replaceable class="parameter">recursive_term</replaceable>
</synopsis>
    where the recursive self-reference must appear on the right-hand
    side of the <literal>UNION</>.  Only one recursive self-reference
    is permitted per query.  Recursive data-modifying statements are not
    supported, but you can use the results of a recursive
    <command>SELECT</command> query in
    a data-modifying statement.  See <xref linkend="queries-with"> for
    an example.
   </para>

   <para>
    Another effect of <literal>RECURSIVE</literal> is that
    <literal>WITH</literal> queries need not be ordered: a query
    can reference another one that is later in the list.  (However,
    circular references, or mutual recursion, are not implemented.)
    Without <literal>RECURSIVE</literal>, <literal>WITH</literal> queries
    can only reference sibling <literal>WITH</literal> queries
    that are earlier in the <literal>WITH</literal> list.
   </para>

   <para>
    A key property of <literal>WITH</literal> queries is that they
    are evaluated only once per execution of the primary query,
    even if the primary query refers to them more than once.
    In particular, data-modifying statements are guaranteed to be
    executed once and only once, regardless of whether the primary query
    reads all or any of their output.
   </para>

   <para>
    The primary query and the <literal>WITH</literal> queries are all
    (notionally) executed at the same time.  This implies that the effects of
    a data-modifying statement in <literal>WITH</literal> cannot be seen from
    other parts of the query, other than by reading its <literal>RETURNING</>
    output.  If two such data-modifying statements attempt to modify the same
    row, the results are unspecified.
   </para>

   <para>
    See <xref linkend="queries-with"> for additional information.
   </para>
  </refsect2>

  <refsect2 id="SQL-FROM">
   <title id="sql-from-title"><literal>FROM</literal> Clause</title>

   <para>
    The <literal>FROM</literal> clause specifies one or more source
    tables for the <command>SELECT</command>.  If multiple sources are
    specified, the result is the Cartesian product (cross join) of all
    the sources.  But usually qualification conditions
    are added to restrict the returned rows to a small subset of the
    Cartesian product.
   </para>

   <para>
    The <literal>FROM</literal> clause can contain the following
    elements:

    <variablelist>
     <varlistentry>
      <term><replaceable class="parameter">table_name</replaceable></term>
      <listitem>
       <para>
        The name (optionally schema-qualified) of an existing table or
        view.  If <literal>ONLY</> is specified, only that table is
        scanned.  If <literal>ONLY</> is not specified, the table and
        any descendant tables are scanned.
       </para>
      </listitem>
     </varlistentry>

     <varlistentry>
      <term><replaceable class="parameter">alias</replaceable></term>
      <listitem>
       <para>
        A substitute name for the <literal>FROM</> item containing the
        alias.  An alias is used for brevity or to eliminate ambiguity
        for self-joins (where the same table is scanned multiple
        times).  When an alias is provided, it completely hides the
        actual name of the table or function; for example given
        <literal>FROM foo AS f</>, the remainder of the
        <command>SELECT</command> must refer to this <literal>FROM</>
        item as <literal>f</> not <literal>foo</>.  If an alias is
        written, a column alias list can also be written to provide
        substitute names for one or more columns of the table.
       </para>
      </listitem>
     </varlistentry>

     <varlistentry>
      <term><replaceable class="parameter">select</replaceable></term>
      <listitem>
       <para>
        A sub-<command>SELECT</command> can appear in the
        <literal>FROM</literal> clause.  This acts as though its
        output were created as a temporary table for the duration of
        this single <command>SELECT</command> command.  Note that the
        sub-<command>SELECT</command> must be surrounded by
        parentheses, and an alias <emphasis>must</emphasis> be
        provided for it.  A
        <xref linkend="sql-values"> command
        can also be used here.
       </para>
      </listitem>
     </varlistentry>

     <varlistentry>
      <term><replaceable class="parameter">with_query_name</replaceable></term>
      <listitem>
       <para>
        A <literal>WITH</> query is referenced by writing its name,
        just as though the query's name were a table name.  (In fact,
        the <literal>WITH</> query hides any real table of the same name
        for the purposes of the primary query.  If necessary, you can
        refer to a real table of the same name by schema-qualifying
        the table's name.)
        An alias can be provided in the same way as for a table.
       </para>
      </listitem>
     </varlistentry>

     <varlistentry>
      <term><replaceable class="parameter">function_name</replaceable></term>
      <listitem>
       <para>
        Function calls can appear in the <literal>FROM</literal>
        clause.  (This is especially useful for functions that return
        result sets, but any function can be used.)  This acts as
        though its output were created as a temporary table for the
        duration of this single <command>SELECT</command> command. An
        alias can also be used. If an alias is written, a column alias
        list can also be written to provide substitute names for one
        or more attributes of the function's composite return type. If
        the function has been defined as returning the <type>record</>
        data type, then an alias or the key word <literal>AS</> must
        be present, followed by a column definition list in the form
        <literal>( <replaceable
        class="parameter">column_name</replaceable> <replaceable
        class="parameter">data_type</replaceable> <optional>, ... </>
        )</literal>.  The column definition list must match the actual
        number and types of columns returned by the function.
       </para>
      </listitem>
     </varlistentry>

     <varlistentry>
      <term><replaceable class="parameter">join_type</replaceable></term>
      <listitem>
       <para>
        One of
        <itemizedlist>
         <listitem>
          <para><literal>[ INNER ] JOIN</literal></para>
         </listitem>
         <listitem>
          <para><literal>LEFT [ OUTER ] JOIN</literal></para>
         </listitem>
         <listitem>
          <para><literal>RIGHT [ OUTER ] JOIN</literal></para>
         </listitem>
         <listitem>
          <para><literal>FULL [ OUTER ] JOIN</literal></para>
         </listitem>
         <listitem>
          <para><literal>CROSS JOIN</literal></para>
         </listitem>
        </itemizedlist>

        For the <literal>INNER</> and <literal>OUTER</> join types, a
        join condition must be specified, namely exactly one of
        <literal>NATURAL</>, <literal>ON <replaceable
        class="parameter">join_condition</replaceable></literal>, or
        <literal>USING (<replaceable
        class="parameter">join_column</replaceable> [, ...])</literal>.
        See below for the meaning.  For <literal>CROSS JOIN</literal>,
        none of these clauses can appear.
       </para>

       <para>
        A <literal>JOIN</literal> clause combines two
        <literal>FROM</> items.  Use parentheses if necessary to
        determine the order of nesting.  In the absence of parentheses,
        <literal>JOIN</literal>s nest left-to-right.  In any case
        <literal>JOIN</literal> binds more tightly than the commas
        separating <literal>FROM</> items.
       </para>

       <para>
        <literal>CROSS JOIN</> and <literal>INNER JOIN</literal>
        produce a simple Cartesian product, the same result as you get from
        listing the two items at the top level of <literal>FROM</>,
        but restricted by the join condition (if any).
        <literal>CROSS JOIN</> is equivalent to <literal>INNER JOIN ON
        (TRUE)</>, that is, no rows are removed by qualification.
        These join types are just a notational convenience, since they
        do nothing you couldn't do with plain <literal>FROM</> and
        <literal>WHERE</>.
       </para>

       <para>
        <literal>LEFT OUTER JOIN</> returns all rows in the qualified
        Cartesian product (i.e., all combined rows that pass its join
        condition), plus one copy of each row in the left-hand table
        for which there was no right-hand row that passed the join
        condition.  This left-hand row is extended to the full width
        of the joined table by inserting null values for the
        right-hand columns.  Note that only the <literal>JOIN</>
        clause's own condition is considered while deciding which rows
        have matches.  Outer conditions are applied afterwards.
       </para>

       <para>
        Conversely, <literal>RIGHT OUTER JOIN</> returns all the
        joined rows, plus one row for each unmatched right-hand row
        (extended with nulls on the left).  This is just a notational
        convenience, since you could convert it to a <literal>LEFT
        OUTER JOIN</> by switching the left and right inputs.
       </para>

       <para>
        <literal>FULL OUTER JOIN</> returns all the joined rows, plus
        one row for each unmatched left-hand row (extended with nulls
        on the right), plus one row for each unmatched right-hand row
        (extended with nulls on the left).
       </para>
      </listitem>
     </varlistentry>

     <varlistentry>
      <term><literal>ON <replaceable class="parameter">join_condition</replaceable></literal></term>
      <listitem>
       <para>
        <replaceable class="parameter">join_condition</replaceable> is
        an expression resulting in a value of type
        <type>boolean</type> (similar to a <literal>WHERE</literal>
        clause) that specifies which rows in a join are considered to
        match.
       </para>
      </listitem>
     </varlistentry>

     <varlistentry>
      <term><literal>USING ( <replaceable class="parameter">join_column</replaceable> [, ...] )</literal></term>
      <listitem>
       <para>
        A clause of the form <literal>USING ( a, b, ... )</literal> is
        shorthand for <literal>ON left_table.a = right_table.a AND
        left_table.b = right_table.b ...</literal>.  Also,
        <literal>USING</> implies that only one of each pair of
        equivalent columns will be included in the join output, not
        both.
       </para>
      </listitem>
     </varlistentry>

     <varlistentry>
      <term><literal>NATURAL</literal></term>
      <listitem>
       <para>
        <literal>NATURAL</literal> is shorthand for a
        <literal>USING</> list that mentions all columns in the two
        tables that have the same names.
       </para>
      </listitem>
     </varlistentry>
    </variablelist>
   </para>
  </refsect2>

  <refsect2 id="SQL-WHERE">
   <title id="sql-where-title"><literal>WHERE</literal> Clause</title>

   <para>
    The optional <literal>WHERE</literal> clause has the general form
<synopsis>
WHERE <replaceable class="parameter">condition</replaceable>
</synopsis>
    where <replaceable class="parameter">condition</replaceable> is
    any expression that evaluates to a result of type
    <type>boolean</type>.  Any row that does not satisfy this
    condition will be eliminated from the output.  A row satisfies the
    condition if it returns true when the actual row values are
    substituted for any variable references.
   </para>
  </refsect2>

  <refsect2 id="SQL-GROUPBY">
   <title id="sql-groupby-title"><literal>GROUP BY</literal> Clause</title>

   <para>
    The optional <literal>GROUP BY</literal> clause has the general form
<synopsis>
GROUP BY <replaceable class="parameter">expression</replaceable> [, ...]
</synopsis>
   </para>

   <para>
    <literal>GROUP BY</literal> will condense into a single row all
    selected rows that share the same values for the grouped
    expressions.  <replaceable
    class="parameter">expression</replaceable> can be an input column
    name, or the name or ordinal number of an output column
    (<command>SELECT</command> list item), or an arbitrary
    expression formed from input-column values.  In case of ambiguity,
    a <literal>GROUP BY</literal> name will be interpreted as an
    input-column name rather than an output column name.
   </para>

   <para>
    Aggregate functions, if any are used, are computed across all rows
    making up each group, producing a separate value for each group
    (whereas without <literal>GROUP BY</literal>, an aggregate
    produces a single value computed across all the selected rows).
    When <literal>GROUP BY</literal> is present, it is not valid for
    the <command>SELECT</command> list expressions to refer to
    ungrouped columns except within aggregate functions or if the
    ungrouped column is functionally dependent on the grouped columns,
    since there would otherwise be more than one possible value to
    return for an ungrouped column.  A functional dependency exists if
    the grouped columns (or a subset thereof) are the primary key of
    the table containing the ungrouped column.
   </para>
  </refsect2>

  <refsect2 id="SQL-HAVING">
   <title id="sql-having-title"><literal>HAVING</literal> Clause</title>

   <para>
    The optional <literal>HAVING</literal> clause has the general form
<synopsis>
HAVING <replaceable class="parameter">condition</replaceable>
</synopsis>
    where <replaceable class="parameter">condition</replaceable> is
    the same as specified for the <literal>WHERE</literal> clause.
   </para>

   <para>
    <literal>HAVING</literal> eliminates group rows that do not
    satisfy the condition.  <literal>HAVING</literal> is different
    from <literal>WHERE</literal>: <literal>WHERE</literal> filters
    individual rows before the application of <literal>GROUP
    BY</literal>, while <literal>HAVING</literal> filters group rows
    created by <literal>GROUP BY</literal>.  Each column referenced in
    <replaceable class="parameter">condition</replaceable> must
    unambiguously reference a grouping column, unless the reference
    appears within an aggregate function.
   </para>

   <para>
    The presence of <literal>HAVING</literal> turns a query into a grouped
    query even if there is no <literal>GROUP BY</> clause.  This is the
    same as what happens when the query contains aggregate functions but
    no <literal>GROUP BY</> clause.  All the selected rows are considered to
    form a single group, and the <command>SELECT</command> list and
    <literal>HAVING</literal> clause can only reference table columns from
    within aggregate functions.  Such a query will emit a single row if the
    <literal>HAVING</literal> condition is true, zero rows if it is not true.
   </para>
  </refsect2>

  <refsect2 id="SQL-WINDOW">
   <title id="sql-window-title"><literal>WINDOW</literal> Clause</title>

   <para>
    The optional <literal>WINDOW</literal> clause has the general form
<synopsis>
WINDOW <replaceable class="parameter">window_name</replaceable> AS ( <replaceable class="parameter">window_definition</replaceable> ) [, ...]
</synopsis>
    where <replaceable class="parameter">window_name</replaceable> is
    a name that can be referenced from subsequent window definitions or
    <literal>OVER</> clauses, and
    <replaceable class="parameter">window_definition</replaceable> is
<synopsis>
[ <replaceable class="parameter">existing_window_name</replaceable> ]
[ PARTITION BY <replaceable class="parameter">expression</replaceable> [, ...] ]
[ ORDER BY <replaceable class="parameter">expression</replaceable> [ ASC | DESC | USING <replaceable class="parameter">operator</replaceable> ] [ NULLS { FIRST | LAST } ] [, ...] ]
[ <replaceable class="parameter">frame_clause</replaceable> ]
</synopsis>
   </para>

   <para>
    If an <replaceable class="parameter">existing_window_name</replaceable>
    is specified it must refer to an earlier entry in the <literal>WINDOW</>
    list; the new window copies its partitioning clause from that entry,
    as well as its ordering clause if any.  In this case the new window cannot
    specify its own <literal>PARTITION BY</> clause, and it can specify
    <literal>ORDER BY</> only if the copied window does not have one.
    The new window always uses its own frame clause; the copied window
    must not specify a frame clause.
   </para>

   <para>
    The elements of the <literal>PARTITION BY</> list are interpreted in
    much the same fashion as elements of a
    <xref linkend="sql-groupby" endterm="sql-groupby-title">, except that
    they are always simple expressions and never the name or number of an
    output column.
    Another difference is that these expressions can contain aggregate
    function calls, which are not allowed in a regular <literal>GROUP BY</>
    clause.  They are allowed here because windowing occurs after grouping
    and aggregation.
   </para>

   <para>
    Similarly, the elements of the <literal>ORDER BY</> list are interpreted
    in much the same fashion as elements of an
    <xref linkend="sql-orderby" endterm="sql-orderby-title">, except that
    the expressions are always taken as simple expressions and never the name
    or number of an output column.
   </para>

   <para>
    The optional <replaceable class="parameter">frame_clause</> defines
    the <firstterm>window frame</> for window functions that depend on the
    frame (not all do).  The window frame is a set of related rows for
    each row of the query (called the <firstterm>current row</>).
    The <replaceable class="parameter">frame_clause</> can be one of

<synopsis>
[ RANGE | ROWS ] <replaceable>frame_start</>
[ RANGE | ROWS ] BETWEEN <replaceable>frame_start</> AND <replaceable>frame_end</>
</synopsis>

    where <replaceable>frame_start</> and <replaceable>frame_end</> can be
    one of

<synopsis>
UNBOUNDED PRECEDING
<replaceable>value</replaceable> PRECEDING
CURRENT ROW
<replaceable>value</replaceable> FOLLOWING
UNBOUNDED FOLLOWING
</synopsis>

    If <replaceable>frame_end</> is omitted it defaults to <literal>CURRENT
    ROW</>.  Restrictions are that
    <replaceable>frame_start</> cannot be <literal>UNBOUNDED FOLLOWING</>,
    <replaceable>frame_end</> cannot be <literal>UNBOUNDED PRECEDING</>,
    and the <replaceable>frame_end</> choice cannot appear earlier in the
    above list than the <replaceable>frame_start</> choice &mdash; for example
    <literal>RANGE BETWEEN CURRENT ROW AND <replaceable>value</>
    PRECEDING</literal> is not allowed.
   </para>

   <para>
    The default framing option is <literal>RANGE UNBOUNDED PRECEDING</>,
    which is the same as <literal>RANGE BETWEEN UNBOUNDED PRECEDING AND
    CURRENT ROW</>; it sets the frame to be all rows from the partition start
    up through the current row's last peer in the <literal>ORDER BY</>
    ordering (which means all rows if there is no <literal>ORDER BY</>).
    In general, <literal>UNBOUNDED PRECEDING</> means that the frame
    starts with the first row of the partition, and similarly
    <literal>UNBOUNDED FOLLOWING</> means that the frame ends with the last
    row of the partition (regardless of <literal>RANGE</> or <literal>ROWS</>
    mode).  In <literal>ROWS</> mode, <literal>CURRENT ROW</>
    means that the frame starts or ends with the current row; but in
    <literal>RANGE</> mode it means that the frame starts or ends with
    the current row's first or last peer in the <literal>ORDER BY</> ordering.
    The <replaceable>value</> <literal>PRECEDING</> and
    <replaceable>value</> <literal>FOLLOWING</> cases are currently only
    allowed in <literal>ROWS</> mode.  They indicate that the frame starts
    or ends with the row that many rows before or after the current row.
    <replaceable>value</replaceable> must be an integer expression not
    containing any variables, aggregate functions, or window functions.
    The value must not be null or negative; but it can be zero, which
    selects the current row itself.
   </para>

   <para>
    Beware that the <literal>ROWS</> options can produce unpredictable
    results if the <literal>ORDER BY</> ordering does not order the rows
    uniquely.  The <literal>RANGE</> options are designed to ensure that
    rows that are peers in the <literal>ORDER BY</> ordering are treated
    alike; any two peer rows will be both in or both not in the frame.
   </para>

   <para>
    The purpose of a <literal>WINDOW</literal> clause is to specify the
    behavior of <firstterm>window functions</> appearing in the query's
    <xref linkend="sql-select-list" endterm="sql-select-list-title"> or
    <xref linkend="sql-orderby" endterm="sql-orderby-title">.  These functions
    can reference the <literal>WINDOW</literal> clause entries by name
    in their <literal>OVER</> clauses.  A <literal>WINDOW</literal> clause
    entry does not have to be referenced anywhere, however; if it is not
    used in the query it is simply ignored.  It is possible to use window
    functions without any <literal>WINDOW</literal> clause at all, since
    a window function call can specify its window definition directly in
    its <literal>OVER</> clause.  However, the <literal>WINDOW</literal>
    clause saves typing when the same window definition is needed for more
    than one window function.
   </para>

   <para>
    Window functions are described in detail in
    <xref linkend="tutorial-window">,
    <xref linkend="syntax-window-functions">, and
    <xref linkend="queries-window">.
   </para>
  </refsect2>

  <refsect2 id="sql-select-list">
   <title id="sql-select-list-title"><command>SELECT</command> List</title>

   <para>
    The <command>SELECT</command> list (between the key words
    <literal>SELECT</> and <literal>FROM</>) specifies expressions
    that form the output rows of the <command>SELECT</command>
    statement.  The expressions can (and usually do) refer to columns
    computed in the <literal>FROM</> clause.
   </para>

   <para>
    Just as in a table, every output column of a <command>SELECT</command>
    has a name.  In a simple <command>SELECT</command> this name is just
    used to label the column for display, but when the <command>SELECT</>
    is a sub-query of a larger query, the name is seen by the larger query
    as the column name of the virtual table produced by the sub-query.
    To specify the name to use for an output column, write
    <literal>AS</> <replaceable class="parameter">output_name</replaceable>
    after the column's expression.  (You can omit <literal>AS</literal>,
    but only if the desired output name does not match any
    <productname>PostgreSQL</productname> keyword (see <xref
    linkend="sql-keywords-appendix">).  For protection against possible
    future keyword additions, it is recommended that you always either
    write <literal>AS</literal> or double-quote the output name.)
    If you do not specify a column name, a name is chosen automatically
    by <productname>PostgreSQL</productname>.  If the column's expression
    is a simple column reference then the chosen name is the same as that
    column's name; in more complex cases a generated name looking like
    <literal>?column<replaceable>N</>?</literal> is usually chosen.
   </para>

   <para>
    An output column's name can be used to refer to the column's value in
    <literal>ORDER BY</> and <literal>GROUP BY</> clauses, but not in the
    <literal>WHERE</> or <literal>HAVING</> clauses; there you must write
    out the expression instead.
   </para>

   <para>
    Instead of an expression, <literal>*</literal> can be written in
    the output list as a shorthand for all the columns of the selected
    rows.  Also, you can write <literal><replaceable
    class="parameter">table_name</replaceable>.*</literal> as a
    shorthand for the columns coming from just that table.  In these
    cases it is not possible to specify new names with <literal>AS</>;
    the output column names will be the same as the table columns' names.
   </para>
  </refsect2>

  <refsect2 id="sql-distinct">
   <title id="sql-distinct-title"><literal>DISTINCT</literal> Clause</title>

   <para>
    If <literal>SELECT DISTINCT</> is specified, all duplicate rows are
    removed from the result set (one row is kept from each group of
    duplicates).  <literal>SELECT ALL</> specifies the opposite: all rows are
    kept; that is the default.
   </para>

   <para>
    <literal>SELECT DISTINCT ON ( <replaceable
    class="parameter">expression</replaceable> [, ...] )</literal>
    keeps only the first row of each set of rows where the given
    expressions evaluate to equal.  The <literal>DISTINCT ON</literal>
    expressions are interpreted using the same rules as for
    <literal>ORDER BY</> (see above).  Note that the <quote>first
    row</quote> of each set is unpredictable unless <literal>ORDER
    BY</> is used to ensure that the desired row appears first.  For
    example:
<programlisting>
SELECT DISTINCT ON (location) location, time, report
    FROM weather_reports
    ORDER BY location, time DESC;
</programlisting>
    retrieves the most recent weather report for each location.  But
    if we had not used <literal>ORDER BY</> to force descending order
    of time values for each location, we'd have gotten a report from
    an unpredictable time for each location.
   </para>

   <para>
    The <literal>DISTINCT ON</> expression(s) must match the leftmost
    <literal>ORDER BY</> expression(s).  The <literal>ORDER BY</> clause
    will normally contain additional expression(s) that determine the
    desired precedence of rows within each <literal>DISTINCT ON</> group.
   </para>
  </refsect2>

  <refsect2 id="SQL-UNION">
   <title id="sql-union-title"><literal>UNION</literal> Clause</title>

   <para>
    The <literal>UNION</literal> clause has this general form:
<synopsis>
<replaceable class="parameter">select_statement</replaceable> UNION [ ALL | DISTINCT ] <replaceable class="parameter">select_statement</replaceable>
</synopsis>
    <replaceable class="parameter">select_statement</replaceable> is
    any <command>SELECT</command> statement without an <literal>ORDER
    BY</>, <literal>LIMIT</>, <literal>FOR UPDATE</literal>, or
    <literal>FOR SHARE</literal> clause.
    (<literal>ORDER BY</> and <literal>LIMIT</> can be attached to a
    subexpression if it is enclosed in parentheses.  Without
    parentheses, these clauses will be taken to apply to the result of
    the <literal>UNION</literal>, not to its right-hand input
    expression.)
   </para>

   <para>
    The <literal>UNION</literal> operator computes the set union of
    the rows returned by the involved <command>SELECT</command>
    statements.  A row is in the set union of two result sets if it
    appears in at least one of the result sets.  The two
    <command>SELECT</command> statements that represent the direct
    operands of the <literal>UNION</literal> must produce the same
    number of columns, and corresponding columns must be of compatible
    data types.
   </para>

   <para>
    The result of <literal>UNION</> does not contain any duplicate
    rows unless the <literal>ALL</> option is specified.
    <literal>ALL</> prevents elimination of duplicates.  (Therefore,
    <literal>UNION ALL</> is usually significantly quicker than
    <literal>UNION</>; use <literal>ALL</> when you can.)
    <literal>DISTINCT</> can be written to explicitly specify the
    default behavior of eliminating duplicate rows.
   </para>

   <para>
    Multiple <literal>UNION</> operators in the same
    <command>SELECT</command> statement are evaluated left to right,
    unless otherwise indicated by parentheses.
   </para>

   <para>
    Currently, <literal>FOR UPDATE</> and <literal>FOR SHARE</> cannot be
    specified either for a <literal>UNION</> result or for any input of a
    <literal>UNION</>.
   </para>
  </refsect2>

  <refsect2 id="SQL-INTERSECT">
   <title id="sql-intersect-title"><literal>INTERSECT</literal> Clause</title>

   <para>
    The <literal>INTERSECT</literal> clause has this general form:
<synopsis>
<replaceable class="parameter">select_statement</replaceable> INTERSECT [ ALL | DISTINCT ] <replaceable class="parameter">select_statement</replaceable>
</synopsis>
    <replaceable class="parameter">select_statement</replaceable> is
    any <command>SELECT</command> statement without an <literal>ORDER
    BY</>, <literal>LIMIT</>, <literal>FOR UPDATE</literal>, or
    <literal>FOR SHARE</literal> clause.
   </para>

   <para>
    The <literal>INTERSECT</literal> operator computes the set
    intersection of the rows returned by the involved
    <command>SELECT</command> statements.  A row is in the
    intersection of two result sets if it appears in both result sets.
   </para>

   <para>
    The result of <literal>INTERSECT</literal> does not contain any
    duplicate rows unless the <literal>ALL</> option is specified.
    With <literal>ALL</>, a row that has <replaceable>m</> duplicates in the
    left table and <replaceable>n</> duplicates in the right table will appear
    min(<replaceable>m</>,<replaceable>n</>) times in the result set.
    <literal>DISTINCT</> can be written to explicitly specify the
    default behavior of eliminating duplicate rows.
   </para>

   <para>
    Multiple <literal>INTERSECT</literal> operators in the same
    <command>SELECT</command> statement are evaluated left to right,
    unless parentheses dictate otherwise.
    <literal>INTERSECT</literal> binds more tightly than
    <literal>UNION</literal>.  That is, <literal>A UNION B INTERSECT
    C</literal> will be read as <literal>A UNION (B INTERSECT
    C)</literal>.
   </para>

   <para>
    Currently, <literal>FOR UPDATE</> and <literal>FOR SHARE</> cannot be
    specified either for an <literal>INTERSECT</> result or for any input of
    an <literal>INTERSECT</>.
   </para>
  </refsect2>

  <refsect2 id="SQL-EXCEPT">
   <title id="sql-except-title"><literal>EXCEPT</literal> Clause</title>

   <para>
    The <literal>EXCEPT</literal> clause has this general form:
<synopsis>
<replaceable class="parameter">select_statement</replaceable> EXCEPT [ ALL | DISTINCT ] <replaceable class="parameter">select_statement</replaceable>
</synopsis>
    <replaceable class="parameter">select_statement</replaceable> is
    any <command>SELECT</command> statement without an <literal>ORDER
    BY</>, <literal>LIMIT</>, <literal>FOR UPDATE</literal>, or
    <literal>FOR SHARE</literal> clause.
   </para>

   <para>
    The <literal>EXCEPT</literal> operator computes the set of rows
    that are in the result of the left <command>SELECT</command>
    statement but not in the result of the right one.
   </para>

   <para>
    The result of <literal>EXCEPT</literal> does not contain any
    duplicate rows unless the <literal>ALL</> option is specified.
    With <literal>ALL</>, a row that has <replaceable>m</> duplicates in the
    left table and <replaceable>n</> duplicates in the right table will appear
    max(<replaceable>m</>-<replaceable>n</>,0) times in the result set.
    <literal>DISTINCT</> can be written to explicitly specify the
    default behavior of eliminating duplicate rows.
   </para>

   <para>
    Multiple <literal>EXCEPT</literal> operators in the same
    <command>SELECT</command> statement are evaluated left to right,
    unless parentheses dictate otherwise.  <literal>EXCEPT</> binds at
    the same level as <literal>UNION</>.
   </para>

   <para>
    Currently, <literal>FOR UPDATE</> and <literal>FOR SHARE</> cannot be
    specified either for an <literal>EXCEPT</> result or for any input of
    an <literal>EXCEPT</>.
   </para>
  </refsect2>

  <refsect2 id="SQL-ORDERBY">
   <title id="sql-orderby-title"><literal>ORDER BY</literal> Clause</title>

   <para>
    The optional <literal>ORDER BY</literal> clause has this general form:
<synopsis>
ORDER BY <replaceable class="parameter">expression</replaceable> [ ASC | DESC | USING <replaceable class="parameter">operator</replaceable> ] [ NULLS { FIRST | LAST } ] [, ...]
</synopsis>
    The <literal>ORDER BY</literal> clause causes the result rows to
    be sorted according to the specified expression(s).  If two rows are
    equal according to the leftmost expression, they are compared
    according to the next expression and so on.  If they are equal
    according to all specified expressions, they are returned in
    an implementation-dependent order.
   </para>

   <para>
    Each <replaceable class="parameter">expression</replaceable> can be the
    name or ordinal number of an output column
    (<command>SELECT</command> list item), or it can be an arbitrary
    expression formed from input-column values.
   </para>

   <para>
    The ordinal number refers to the ordinal (left-to-right) position
    of the output column. This feature makes it possible to define an
    ordering on the basis of a column that does not have a unique
    name.  This is never absolutely necessary because it is always
    possible to assign a name to an output column using the
    <literal>AS</> clause.
   </para>

   <para>
    It is also possible to use arbitrary expressions in the
    <literal>ORDER BY</literal> clause, including columns that do not
    appear in the <command>SELECT</command> output list.  Thus the
    following statement is valid:
<programlisting>
SELECT name FROM distributors ORDER BY code;
</programlisting>
    A limitation of this feature is that an <literal>ORDER BY</>
    clause applying to the result of a <literal>UNION</>,
    <literal>INTERSECT</>, or <literal>EXCEPT</> clause can only
    specify an output column name or number, not an expression.
   </para>

   <para>
    If an <literal>ORDER BY</> expression is a simple name that
    matches both an output column name and an input column name,
    <literal>ORDER BY</> will interpret it as the output column name.
    This is the opposite of the choice that <literal>GROUP BY</> will
    make in the same situation.  This inconsistency is made to be
    compatible with the SQL standard.
   </para>

   <para>
    Optionally one can add the key word <literal>ASC</> (ascending) or
    <literal>DESC</> (descending) after any expression in the
    <literal>ORDER BY</> clause.  If not specified, <literal>ASC</> is
    assumed by default.  Alternatively, a specific ordering operator
    name can be specified in the <literal>USING</> clause.
    An ordering operator must be a less-than or greater-than
    member of some B-tree operator family.
    <literal>ASC</> is usually equivalent to <literal>USING &lt;</> and
    <literal>DESC</> is usually equivalent to <literal>USING &gt;</>.
    (But the creator of a user-defined data type can define exactly what the
    default sort ordering is, and it might correspond to operators with other
    names.)
   </para>

   <para>
    If <literal>NULLS LAST</> is specified, null values sort after all
    non-null values; if <literal>NULLS FIRST</> is specified, null values
    sort before all non-null values.  If neither is specified, the default
    behavior is <literal>NULLS LAST</> when <literal>ASC</> is specified
    or implied, and <literal>NULLS FIRST</> when <literal>DESC</> is specified
    (thus, the default is to act as though nulls are larger than non-nulls).
    When <literal>USING</> is specified, the default nulls ordering depends
    on whether the operator is a less-than or greater-than operator.
   </para>

   <para>
    Note that ordering options apply only to the expression they follow;
    for example <literal>ORDER BY x, y DESC</> does not mean
    the same thing as <literal>ORDER BY x DESC, y DESC</>.
   </para>

   <para>
    Character-string data is sorted according to the locale-specific
    collation order that was established when the database was created.
   </para>
  </refsect2>

  <refsect2 id="SQL-LIMIT">
   <title id="sql-limit-title"><literal>LIMIT</literal> Clause</title>

   <para>
    The <literal>LIMIT</literal> clause consists of two independent
    sub-clauses:
<synopsis>
LIMIT { <replaceable class="parameter">count</replaceable> | ALL }
OFFSET <replaceable class="parameter">start</replaceable>
</synopsis>
    <replaceable class="parameter">count</replaceable> specifies the
    maximum number of rows to return, while <replaceable
    class="parameter">start</replaceable> specifies the number of rows
    to skip before starting to return rows.  When both are specified,
    <replaceable class="parameter">start</replaceable> rows are skipped
    before starting to count the <replaceable
    class="parameter">count</replaceable> rows to be returned.
   </para>

   <para>
    If the <replaceable class="parameter">count</replaceable> expression
    evaluates to NULL, it is treated as <literal>LIMIT ALL</>, i.e., no
    limit.  If <replaceable class="parameter">start</replaceable> evaluates
    to NULL, it is treated the same as <literal>OFFSET 0</>.
   </para>

   <para>
    SQL:2008 introduced a different syntax to achieve the same thing,
    which <productname>PostgreSQL</> also supports.  It is:
<synopsis>
OFFSET <replaceable class="parameter">start</replaceable> { ROW | ROWS }
FETCH { FIRST | NEXT } [ <replaceable class="parameter">count</replaceable> ] { ROW | ROWS } ONLY
</synopsis>
    According to the standard, the <literal>OFFSET</literal> clause must come
    before the <literal>FETCH</literal> clause if both are present; but
    <productname>PostgreSQL</> is laxer and allows either order.
    <literal>ROW</literal>
    and <literal>ROWS</literal> as well as <literal>FIRST</literal>
    and <literal>NEXT</literal> are noise words that don't influence
    the effects of these clauses.  In this syntax, when using expressions
    other than simple constants for <replaceable class="parameter">start</>
    or <replaceable class="parameter">count</replaceable>, parentheses will be
    necessary in most cases.  If <replaceable class="parameter">count</> is
    omitted in <literal>FETCH</>, it defaults to 1.
   </para>

   <para>
    When using <literal>LIMIT</>, it is a good idea to use an
    <literal>ORDER BY</> clause that constrains the result rows into a
    unique order.  Otherwise you will get an unpredictable subset of
    the query's rows &mdash; you might be asking for the tenth through
    twentieth rows, but tenth through twentieth in what ordering?  You
    don't know what ordering unless you specify <literal>ORDER BY</>.
   </para>

   <para>
    The query planner takes <literal>LIMIT</> into account when
    generating a query plan, so you are very likely to get different
    plans (yielding different row orders) depending on what you use
    for <literal>LIMIT</> and <literal>OFFSET</>.  Thus, using
    different <literal>LIMIT</>/<literal>OFFSET</> values to select
    different subsets of a query result <emphasis>will give
    inconsistent results</emphasis> unless you enforce a predictable
    result ordering with <literal>ORDER BY</>.  This is not a bug; it
    is an inherent consequence of the fact that SQL does not promise
    to deliver the results of a query in any particular order unless
    <literal>ORDER BY</> is used to constrain the order.
   </para>

   <para>
    It is even possible for repeated executions of the same <literal>LIMIT</>
    query to return different subsets of the rows of a table, if there
    is not an <literal>ORDER BY</> to enforce selection of a deterministic
    subset.  Again, this is not a bug; determinism of the results is
    simply not guaranteed in such a case.
   </para>
  </refsect2>

  <refsect2 id="SQL-FOR-UPDATE-SHARE">
   <title id="sql-for-update-share-title"><literal>FOR UPDATE</literal>/<literal>FOR SHARE</literal> Clause</title>

   <para>
    The <literal>FOR UPDATE</literal> clause has this form:
<synopsis>
FOR UPDATE [ OF <replaceable class="parameter">table_name</replaceable> [, ...] ] [ NOWAIT ]
</synopsis>
   </para>

   <para>
    The closely related <literal>FOR SHARE</literal> clause has this form:
<synopsis>
FOR SHARE [ OF <replaceable class="parameter">table_name</replaceable> [, ...] ] [ NOWAIT ]
</synopsis>
   </para>

   <para>
    <literal>FOR UPDATE</literal> causes the rows retrieved by the
    <command>SELECT</command> statement to be locked as though for
    update.  This prevents them from being modified or deleted by
    other transactions until the current transaction ends.  That is,
    other transactions that attempt <command>UPDATE</command>,
    <command>DELETE</command>, or <command>SELECT FOR UPDATE</command>
    of these rows will be blocked until the current transaction ends.
    Also, if an <command>UPDATE</command>, <command>DELETE</command>,
    or <command>SELECT FOR UPDATE</command> from another transaction
    has already locked a selected row or rows, <command>SELECT FOR
    UPDATE</command> will wait for the other transaction to complete,
    and will then lock and return the updated row (or no row, if the
    row was deleted).  Within a <literal>REPEATABLE READ</> or <literal>SERIALIZABLE</> transaction,
    however, an error will be thrown if a row to be locked has changed
    since the transaction started.  For further discussion see <xref
    linkend="mvcc">.
   </para>

   <para>
    <literal>FOR SHARE</literal> behaves similarly, except that it
    acquires a shared rather than exclusive lock on each retrieved
    row.  A shared lock blocks other transactions from performing
    <command>UPDATE</command>, <command>DELETE</command>, or <command>SELECT
    FOR UPDATE</command> on these rows, but it does not prevent them
    from performing <command>SELECT FOR SHARE</command>.
   </para>

   <para>
    To prevent the operation from waiting for other transactions to commit,
    use the <literal>NOWAIT</> option.  With <literal>NOWAIT</>, the statement
    reports an error, rather than waiting, if a selected row
    cannot be locked immediately.  Note that <literal>NOWAIT</> applies only
    to the row-level lock(s) &mdash; the required <literal>ROW SHARE</literal>
    table-level lock is still taken in the ordinary way (see
    <xref linkend="mvcc">).  You can use
    <xref linkend="sql-lock">
    with the <literal>NOWAIT</> option first,
    if you need to acquire the table-level lock without waiting.
   </para>

   <para>
    If specific tables are named in <literal>FOR UPDATE</literal>
    or <literal>FOR SHARE</literal>,
    then only rows coming from those tables are locked; any other
    tables used in the <command>SELECT</command> are simply read as
    usual.  A <literal>FOR UPDATE</literal> or <literal>FOR SHARE</literal>
    clause without a table list affects all tables used in the statement.
    If <literal>FOR UPDATE</literal> or <literal>FOR SHARE</literal> is
    applied to a view or sub-query, it affects all tables used in
    the view or sub-query.
    However, <literal>FOR UPDATE</literal>/<literal>FOR SHARE</literal>
    do not apply to <literal>WITH</> queries referenced by the primary query.
    If you want row locking to occur within a <literal>WITH</> query, specify
    <literal>FOR UPDATE</literal> or <literal>FOR SHARE</literal> within the
    <literal>WITH</> query.
   </para>

   <para>
    Multiple <literal>FOR UPDATE</literal> and <literal>FOR SHARE</literal>
    clauses can be written if it is necessary to specify different locking
    behavior for different tables.  If the same table is mentioned (or
    implicitly affected) by both <literal>FOR UPDATE</literal> and
    <literal>FOR SHARE</literal> clauses, then it is processed as
    <literal>FOR UPDATE</literal>.  Similarly, a table is processed
    as <literal>NOWAIT</> if that is specified in any of the clauses
    affecting it.
   </para>

   <para>
    <literal>FOR UPDATE</literal> and <literal>FOR SHARE</literal> cannot be
    used in contexts where returned rows cannot be clearly identified with
    individual table rows; for example they cannot be used with aggregation.
   </para>

   <para>
    When <literal>FOR UPDATE</literal> or <literal>FOR SHARE</literal>
    appears at the top level of a <command>SELECT</> query, the rows that
    are locked are exactly those that are returned by the query; in the
    case of a join query, the rows locked are those that contribute to
    returned join rows.  In addition, rows that satisfied the query
    conditions as of the query snapshot will be locked, although they
    will not be returned if they were updated after the snapshot
    and no longer satisfy the query conditions.  If a
    <literal>LIMIT</> is used, locking stops
    once enough rows have been returned to satisfy the limit (but note that
    rows skipped over by <literal>OFFSET</> will get locked).  Similarly,
    if <literal>FOR UPDATE</literal> or <literal>FOR SHARE</literal>
    is used in a cursor's query, only rows actually fetched or stepped past
    by the cursor will be locked.
   </para>

   <para>
    When <literal>FOR UPDATE</literal> or <literal>FOR SHARE</literal>
    appears in a sub-<command>SELECT</>, the rows locked are those
    returned to the outer query by the sub-query.  This might involve
    fewer rows than inspection of the sub-query alone would suggest,
    since conditions from the outer query might be used to optimize
    execution of the sub-query.  For example,
<programlisting>
SELECT * FROM (SELECT * FROM mytable FOR UPDATE) ss WHERE col1 = 5;
</programlisting>
    will lock only rows having <literal>col1 = 5</>, even though that
    condition is not textually within the sub-query.
   </para>

  <caution>
   <para>
    Avoid locking a row and then modifying it within a later savepoint or
    <application>PL/pgSQL</application> exception block.  A subsequent
    rollback would cause the lock to be lost.  For example:
<programlisting>
BEGIN;
SELECT * FROM mytable WHERE key = 1 FOR UPDATE;
SAVEPOINT s;
UPDATE mytable SET ... WHERE key = 1;
ROLLBACK TO s;
</programlisting>
    After the <command>ROLLBACK</>, the row is effectively unlocked, rather
    than returned to its pre-savepoint state of being locked but not modified.
    This hazard occurs if a row locked in the current transaction is updated
    or deleted, or if a shared lock is upgraded to exclusive: in all these
    cases, the former lock state is forgotten.  If the transaction is then
    rolled back to a state between the original locking command and the
    subsequent change, the row will appear not to be locked at all.  This is
    an implementation deficiency which will be addressed in a future release
    of <productname>PostgreSQL</productname>.
   </para>
  </caution>

  <caution>
   <para>
    It is possible for a <command>SELECT</> command using <literal>ORDER
    BY</literal> and <literal>FOR UPDATE/SHARE</literal> to return rows out of
    order.  This is because <literal>ORDER BY</> is applied first.
    The command sorts the result, but might then block trying to obtain a lock
    on one or more of the rows.  Once the <literal>SELECT</> unblocks, some
    of the ordering column values might have been modified, leading to those
    rows appearing to be out of order (though they are in order in terms
    of the original column values).  This can be worked around at need by
    placing the <literal>FOR UPDATE/SHARE</literal> clause in a sub-query,
    for example
<programlisting>
SELECT * FROM (SELECT * FROM mytable FOR UPDATE) ss ORDER BY column1;
</programlisting>
    Note that this will result in locking all rows of <structname>mytable</>,
    whereas <literal>FOR UPDATE</> at the top level would lock only the
    actually returned rows.  This can make for a significant performance
    difference, particularly if the <literal>ORDER BY</> is combined with
    <literal>LIMIT</> or other restrictions.  So this technique is recommended
    only if concurrent updates of the ordering columns are expected and a
    strictly sorted result is required.
   </para>
  </caution>
  </refsect2>

  <refsect2 id="SQL-TABLE">
   <title><literal>TABLE</literal> Command</title>

   <para>
    The command
<programlisting>
TABLE <replaceable class="parameter">name</replaceable>
</programlisting>
    is completely equivalent to
<programlisting>
SELECT * FROM <replaceable class="parameter">name</replaceable>
</programlisting>
    It can be used as a top-level command or as a space-saving syntax
    variant in parts of complex queries.
   </para>
  </refsect2>
 </refsect1>

 <refsect1>
  <title>Examples</title>

  <para>
   To join the table <literal>films</literal> with the table
   <literal>distributors</literal>:

<programlisting>
SELECT f.title, f.did, d.name, f.date_prod, f.kind
    FROM distributors d, films f
    WHERE f.did = d.did

       title       | did |     name     | date_prod  |   kind
-------------------+-----+--------------+------------+----------
 The Third Man     | 101 | British Lion | 1949-12-23 | Drama
 The African Queen | 101 | British Lion | 1951-08-11 | Romantic
 ...
</programlisting>
  </para>

  <para>
   To sum the column <literal>len</literal> of all films and group
   the results by <literal>kind</literal>:

<programlisting>
SELECT kind, sum(len) AS total FROM films GROUP BY kind;

   kind   | total
----------+-------
 Action   | 07:34
 Comedy   | 02:58
 Drama    | 14:28
 Musical  | 06:42
 Romantic | 04:38
</programlisting>
  </para>

  <para>
   To sum the column <literal>len</literal> of all films, group
   the results by <literal>kind</literal> and show those group totals
   that are less than 5 hours:

<programlisting>
SELECT kind, sum(len) AS total
    FROM films
    GROUP BY kind
    HAVING sum(len) &lt; interval '5 hours';

   kind   | total
----------+-------
 Comedy   | 02:58
 Romantic | 04:38
</programlisting>
  </para>

  <para>
   The following two examples are identical ways of sorting the individual
   results according to the contents of the second column
   (<literal>name</literal>):

<programlisting>
SELECT * FROM distributors ORDER BY name;
SELECT * FROM distributors ORDER BY 2;

 did |       name
-----+------------------
 109 | 20th Century Fox
 110 | Bavaria Atelier
 101 | British Lion
 107 | Columbia
 102 | Jean Luc Godard
 113 | Luso films
 104 | Mosfilm
 103 | Paramount
 106 | Toho
 105 | United Artists
 111 | Walt Disney
 112 | Warner Bros.
 108 | Westward
</programlisting>
  </para>

  <para>
   The next example shows how to obtain the union of the tables
   <literal>distributors</literal> and
   <literal>actors</literal>, restricting the results to those that begin
   with the letter W in each table.  Only distinct rows are wanted, so the
   key word <literal>ALL</literal> is omitted.

<programlisting>
distributors:               actors:
 did |     name              id |     name
-----+--------------        ----+----------------
 108 | Westward               1 | Woody Allen
 111 | Walt Disney            2 | Warren Beatty
 112 | Warner Bros.           3 | Walter Matthau
 ...                         ...

SELECT distributors.name
    FROM distributors
    WHERE distributors.name LIKE 'W%'
UNION
SELECT actors.name
    FROM actors
    WHERE actors.name LIKE 'W%';

      name
----------------
 Walt Disney
 Walter Matthau
 Warner Bros.
 Warren Beatty
 Westward
 Woody Allen
</programlisting>
  </para>

  <para>
   This example shows how to use a function in the <literal>FROM</>
   clause, both with and without a column definition list:

<programlisting>
CREATE FUNCTION distributors(int) RETURNS SETOF distributors AS $$
    SELECT * FROM distributors WHERE did = $1;
$$ LANGUAGE SQL;

SELECT * FROM distributors(111);
 did |    name
-----+-------------
 111 | Walt Disney

CREATE FUNCTION distributors_2(int) RETURNS SETOF record AS $$
    SELECT * FROM distributors WHERE did = $1;
$$ LANGUAGE SQL;

SELECT * FROM distributors_2(111) AS (f1 int, f2 text);
 f1  |     f2
-----+-------------
 111 | Walt Disney
</programlisting>
  </para>

  <para>
   This example shows how to use a simple <literal>WITH</> clause:

<programlisting>
WITH t AS (
    SELECT random() as x FROM generate_series(1, 3)
  )
SELECT * FROM t
UNION ALL
SELECT * FROM t

         x          
--------------------
  0.534150459803641
  0.520092216785997
 0.0735620250925422
  0.534150459803641
  0.520092216785997
 0.0735620250925422
</programlisting>

   Notice that the <literal>WITH</> query was evaluated only once,
   so that we got two sets of the same three random values.
  </para>

  <para>
   This example uses <literal>WITH RECURSIVE</literal> to find all
   subordinates (direct or indirect) of the employee Mary, and their
   level of indirectness, from a table that shows only direct
   subordinates:

<programlisting>
WITH RECURSIVE employee_recursive(distance, employee_name, manager_name) AS (
    SELECT 1, employee_name, manager_name
    FROM employee
    WHERE manager_name = 'Mary'
  UNION ALL
    SELECT er.distance + 1, e.employee_name, e.manager_name
    FROM employee_recursive er, employee e
    WHERE er.employee_name = e.manager_name
  )
SELECT distance, employee_name FROM employee_recursive;
</programlisting>

   Notice the typical form of recursive queries:
   an initial condition, followed by <literal>UNION</literal>,
   followed by the recursive part of the query. Be sure that the
   recursive part of the query will eventually return no tuples, or
   else the query will loop indefinitely.  (See <xref linkend="queries-with">
   for more examples.)
  </para>
 </refsect1>

 <refsect1>
  <title>Compatibility</title>

  <para>
   Of course, the <command>SELECT</command> statement is compatible
   with the SQL standard.  But there are some extensions and some
   missing features.
  </para>

  <refsect2>
   <title>Omitted <literal>FROM</literal> Clauses</title>

   <para>
    <productname>PostgreSQL</productname> allows one to omit the
    <literal>FROM</literal> clause.  It has a straightforward use to
    compute the results of simple expressions:
<programlisting>
SELECT 2+2;

 ?column?
----------
        4
</programlisting>
    Some other <acronym>SQL</acronym> databases cannot do this except
    by introducing a dummy one-row table from which to do the
    <command>SELECT</command>.
   </para>

   <para>
    Note that if a <literal>FROM</literal> clause is not specified,
    the query cannot reference any database tables. For example, the
    following query is invalid:
<programlisting>
SELECT distributors.* WHERE distributors.name = 'Westward';
</programlisting>
    <productname>PostgreSQL</productname> releases prior to
    8.1 would accept queries of this form, and add an implicit entry
    to the query's <literal>FROM</literal> clause for each table
    referenced by the query. This is no longer allowed.
   </para>
  </refsect2>

  <refsect2>
   <title>Omitting the <literal>AS</literal> Key Word</title>

   <para>
    In the SQL standard, the optional key word <literal>AS</> can be
    omitted before an output column name whenever the new column name
    is a valid column name (that is, not the same as any reserved
    keyword).  <productname>PostgreSQL</productname> is slightly more
    restrictive: <literal>AS</> is required if the new column name
    matches any keyword at all, reserved or not.  Recommended practice is
    to use <literal>AS</> or double-quote output column names, to prevent
    any possible conflict against future keyword additions.
   </para>

   <para>
    In <literal>FROM</literal> items, both the standard and
    <productname>PostgreSQL</productname> allow <literal>AS</> to
    be omitted before an alias that is an unreserved keyword.  But
    this is impractical for output column names, because of syntactic
    ambiguities.
   </para>
  </refsect2>

  <refsect2>
   <title><literal>ONLY</literal> and Parentheses</title>

   <para>
    The SQL standard requires parentheses around the table name
    after <literal>ONLY</literal>, as in <literal>SELECT * FROM ONLY
    (tab1), ONLY (tab2) WHERE ...</literal>.  PostgreSQL supports that
    as well, but the parentheses are optional.  (This point applies
    equally to all SQL commands supporting the <literal>ONLY</literal>
    option.)
   </para>
  </refsect2>

  <refsect2>
   <title>Namespace Available to <literal>GROUP BY</literal> and <literal>ORDER BY</literal></title>

   <para>
    In the SQL-92 standard, an <literal>ORDER BY</literal> clause can
    only use output column names or numbers, while a <literal>GROUP
    BY</literal> clause can only use expressions based on input column
    names.  <productname>PostgreSQL</productname> extends each of
    these clauses to allow the other choice as well (but it uses the
    standard's interpretation if there is ambiguity).
    <productname>PostgreSQL</productname> also allows both clauses to
    specify arbitrary expressions.  Note that names appearing in an
    expression will always be taken as input-column names, not as
    output-column names.
   </para>

   <para>
    SQL:1999 and later use a slightly different definition which is not
    entirely upward compatible with SQL-92.
    In most cases, however, <productname>PostgreSQL</productname>
    will interpret an <literal>ORDER BY</literal> or <literal>GROUP
    BY</literal> expression the same way SQL:1999 does.
   </para>
  </refsect2>

  <refsect2>
   <title>Functional Dependencies</title>

   <para>
    <productname>PostgreSQL</productname> recognizes functional dependency
    (allowing columns to be omitted from <literal>GROUP BY</>) only when
    a table's primary key is included in the <literal>GROUP BY</> list.
    The SQL standard specifies additional conditions that should be
    recognized.
   </para>
  </refsect2>

  <refsect2>
   <title><literal>WINDOW</literal> Clause Restrictions</title>

   <para>
    The SQL standard provides additional options for the window
    <replaceable class="parameter">frame_clause</>.
    <productname>PostgreSQL</productname> currently supports only the
    options listed above.
   </para>
  </refsect2>

  <refsect2>
   <title><literal>LIMIT</literal> and <literal>OFFSET</literal></title>

   <para>
    The clauses <literal>LIMIT</literal> and <literal>OFFSET</literal>
    are <productname>PostgreSQL</productname>-specific syntax, also
    used by <productname>MySQL</productname>.  The SQL:2008 standard
    has introduced the clauses <literal>OFFSET ... FETCH {FIRST|NEXT}
    ...</literal> for the same functionality, as shown above
    in <xref linkend="sql-limit" endterm="sql-limit-title">.  This
    syntax is also used by <productname>IBM DB2</productname>.
    (Applications written for <productname>Oracle</productname>
    frequently use a workaround involving the automatically
    generated <literal>rownum</literal> column, which is not available in
    PostgreSQL, to implement the effects of these clauses.)
   </para>
  </refsect2>

  <refsect2>
   <title><literal>FOR UPDATE</> and <literal>FOR SHARE</></title>

   <para>
    Although <literal>FOR UPDATE</> appears in the SQL standard, the
    standard allows it only as an option of <command>DECLARE CURSOR</>.
    <productname>PostgreSQL</productname> allows it in any <command>SELECT</>
    query as well as in sub-<command>SELECT</>s, but this is an extension.
    The <literal>FOR SHARE</> variant, and the <literal>NOWAIT</> option,
    do not appear in the standard.
   </para>
  </refsect2>

  <refsect2>
   <title>Data-Modifying Statements in <literal>WITH</></title>

   <para>
    <productname>PostgreSQL</productname> allows <command>INSERT</>,
    <command>UPDATE</>, and <command>DELETE</> to be used as <literal>WITH</>
    queries.  This is not found in the SQL standard.
   </para>
  </refsect2>

  <refsect2>
   <title>Nonstandard Clauses</title>

   <para>
    The clause <literal>DISTINCT ON</literal> is not defined in the
    SQL standard.
   </para>
  </refsect2>
 </refsect1>
</refentry>