1、SelectStmt
/* ----------------------
* Select Statement
*
* A "simple" SELECT is represented in the output of gram.y by a single
* SelectStmt node; so is a VALUES construct. A query containing set
* operators (UNION, INTERSECT, EXCEPT) is represented by a tree of SelectStmt
* nodes, in which the leaf nodes are component SELECTs and the internal nodes
* represent UNION, INTERSECT, or EXCEPT operators. Using the same node
* type for both leaf and internal nodes allows gram.y to stick ORDER BY,
* LIMIT, etc, clause values into a SELECT statement without worrying
* whether it is a simple or compound SELECT.
* ----------------------
*/
typedef enum SetOperation
{
SETOP_NONE = 0,
SETOP_UNION,
SETOP_INTERSECT,
SETOP_EXCEPT
} SetOperation;
typedef struct SelectStmt
{
NodeTag type;
/*
* These fields are used only in "leaf" SelectStmts.
*/
List *distinctClause; /* NULL, list of DISTINCT ON exprs, or
* lcons(NIL,NIL) for all (SELECT DISTINCT) */
IntoClause *intoClause; /* target for SELECT INTO */
List *targetList; /* the target list (of ResTarget) */
List *fromClause; /* the FROM clause */
Node *whereClause; /* WHERE qualification */
List *groupClause; /* GROUP BY clauses */
Node *havingClause; /* HAVING conditional-expression */
List *windowClause; /* WINDOW window_name AS (...), ... */
/*
* In a "leaf" node representing a VALUES list, the above fields are all
* null, and instead this field is set. Note that the elements of the
* sublists are just expressions, without ResTarget decoration. Also note
* that a list element can be DEFAULT (represented as a SetToDefault
* node), regardless of the context of the VALUES list. It's up to parse
* analysis to reject that where not valid.
*/
List *valuesLists; /* untransformed list of expression lists */
/*
* These fields are used in both "leaf" SelectStmts and upper-level
* SelectStmts.
*/
List *sortClause; /* sort clause (a list of SortBy's) */
Node *limitOffset; /* # of result tuples to skip */
Node *limitCount; /* # of result tuples to return */
List *lockingClause; /* FOR UPDATE (list of LockingClause's) */
WithClause *withClause; /* WITH clause */
/*
* These fields are used only in upper-level SelectStmts.
*/
SetOperation op; /* type of set op */
bool all; /* ALL specified? */
struct SelectStmt *larg; /* left child */
struct SelectStmt *rarg; /* right child */
/* Eventually add fields for CORRESPONDING spec here */
} SelectStmt;
2、RangeSubselect
/*
* RangeSubselect - subquery appearing in a FROM clause
*/
typedef struct RangeSubselect
{
NodeTag type;
bool lateral; /* does it have LATERAL prefix? */
Node *subquery; /* the untransformed sub-select clause */
Alias *alias; /* table alias & optional column aliases */
} RangeSubselect;
3、Alias
/*
* Alias -
* specifies an alias for a range variable; the alias might also
* specify renaming of columns within the table.
*
* Note: colnames is a list of Value nodes (always strings). In Alias structs
* associated with RTEs, there may be entries corresponding to dropped
* columns; these are normally empty strings (""). See parsenodes.h for info.
*/
typedef struct Alias
{
NodeTag type;
char *aliasname; /* aliased rel name (never qualified) */
List *colnames; /* optional list of column aliases */
} Alias;
4、ResTarget
/*
* ResTarget -
* result target (used in target list of pre-transformed parse trees)
*
* In a SELECT target list, 'name' is the column label from an
* 'AS ColumnLabel' clause, or NULL if there was none, and 'val' is the
* value expression itself. The 'indirection' field is not used.
*
* INSERT uses ResTarget in its target-column-names list. Here, 'name' is
* the name of the destination column, 'indirection' stores any subscripts
* attached to the destination, and 'val' is not used.
*
* In an UPDATE target list, 'name' is the name of the destination column,
* 'indirection' stores any subscripts attached to the destination, and
* 'val' is the expression to assign.
*
* See A_Indirection for more info about what can appear in 'indirection'.
*/
typedef struct ResTarget
{
NodeTag type;
char *name; /* column name or NULL */
List *indirection; /* subscripts, field names, and '*', or NIL */
Node *val; /* the value expression to compute or assign */
int location; /* token location, or -1 if unknown */
} ResTarget;
5、FromExpr
/*----------
* FromExpr - represents a FROM ... WHERE ... construct
*
* This is both more flexible than a JoinExpr (it can have any number of
* children, including zero) and less so --- we don't need to deal with
* aliases and so on. The output column set is implicitly just the union
* of the outputs of the children.
*----------
*/
typedef struct FromExpr
{
NodeTag type;
List *fromlist; /* List of join subtrees */
Node *quals; /* qualifiers on join, if any */
} FromExpr;
6、JoinExpr
/*----------
* JoinExpr - for SQL JOIN expressions
*
* isNatural, usingClause, and quals are interdependent. The user can write
* only one of NATURAL, USING(), or ON() (this is enforced by the grammar).
* If he writes NATURAL then parse analysis generates the equivalent USING()
* list, and from that fills in "quals" with the right equality comparisons.
* If he writes USING() then "quals" is filled with equality comparisons.
* If he writes ON() then only "quals" is set. Note that NATURAL/USING
* are not equivalent to ON() since they also affect the output column list.
*
* alias is an Alias node representing the AS alias-clause attached to the
* join expression, or NULL if no clause. NB: presence or absence of the
* alias has a critical impact on semantics, because a join with an alias
* restricts visibility of the tables/columns inside it.
*
* During parse analysis, an RTE is created for the Join, and its index
* is filled into rtindex. This RTE is present mainly so that Vars can
* be created that refer to the outputs of the join. The planner sometimes
* generates JoinExprs internally; these can have rtindex = 0 if there are
* no join alias variables referencing such joins.
*----------
*/
typedef struct JoinExpr
{
NodeTag type;
JoinType jointype; /* type of join */
bool isNatural; /* Natural join? Will need to shape table */
Node *larg; /* left subtree */
Node *rarg; /* right subtree */
List *usingClause; /* USING clause, if any (list of String) */
Node *quals; /* qualifiers on join, if any */
Alias *alias; /* user-written alias clause, if any */
int rtindex; /* RT index assigned for join, or 0 */
} JoinExpr;
7、RangeVar
/*
* RangeVar - range variable, used in FROM clauses
*
* Also used to represent table names in utility statements; there, the alias
* field is not used, and inh tells whether to apply the operation
* recursively to child tables. In some contexts it is also useful to carry
* a TEMP table indication here.
*/
typedef struct RangeVar
{
NodeTag type;
char *catalogname; /* the catalog (database) name, or NULL */
char *schemaname; /* the schema name, or NULL */
char *relname; /* the relation/sequence name */
bool inh; /* expand rel by inheritance? recursively act
* on children? */
char relpersistence; /* see RELPERSISTENCE_* in pg_class.h */
Alias *alias; /* table alias & optional column aliases */
int location; /* token location, or -1 if unknown */
} RangeVar;
8、ColumnRef
/*
* ColumnRef - specifies a reference to a column, or possibly a whole tuple
*
* The "fields" list must be nonempty. It can contain string Value nodes
* (representing names) and A_Star nodes (representing occurrence of a '*').
* Currently, A_Star must appear only as the last list element --- the grammar
* is responsible for enforcing this!
*
* Note: any array subscripting or selection of fields from composite columns
* is represented by an A_Indirection node above the ColumnRef. However,
* for simplicity in the normal case, initial field selection from a table
* name is represented within ColumnRef and not by adding A_Indirection.
*/
typedef struct ColumnRef
{
NodeTag type;
List *fields; /* field names (Value strings) or A_Star */
int location; /* token location, or -1 if unknown */
} ColumnRef;
1、解析树：通过跟踪分析源码，分析解析树Parsetree的结构；
2、其他数据结构：SelectSmt、RangeSubselect、JoinExpr等数据结构。
