Function transformDistinctOnClause

src/backend/parser/parse_clause.c:3207–3301

* transformDistinctOnClause - * transform a DISTINCT ON clause * * Since we may need to add items to the query's targetlist, that list * is passed by reference. * * As with GROUP BY, we absorb the sorting semantics of ORDER BY as much as * possible into the distinctClause. This avoids a possible need to re-sort, * and allows the user to choose the equality semantics used by DISTINCT, *

 * operator.
 */
List *
transformDistinctOnClause(ParseState *pstate, List *distinctlist,
						  List **targetlist, List *sortClause)
{
	List	   *result = NIL;
	List	   *sortgrouprefs = NIL;
	bool		skipped_sortitem;
	ListCell   *lc;
	ListCell   *lc2;

	/*
	 * Add all the DISTINCT ON expressions to the tlist (if not already
	 * present, they are added as resjunk items).  Assign sortgroupref numbers
	 * to them, and make a list of these numbers.  (NB: we rely below on the
	 * sortgrouprefs list being one-for-one with the original distinctlist.
	 * Also notice that we could have duplicate DISTINCT ON expressions and
	 * hence duplicate entries in sortgrouprefs.)
	 */
	foreach(lc, distinctlist)
	{
		Node	   *dexpr = (Node *) lfirst(lc);
		int			sortgroupref;
		TargetEntry *tle;

		tle = findTargetlistEntrySQL92(pstate, dexpr, targetlist,
									   EXPR_KIND_DISTINCT_ON);
		sortgroupref = assignSortGroupRef(tle, *targetlist);
		sortgrouprefs = lappend_int(sortgrouprefs, sortgroupref);
	}

	/*
	 * If the user writes both DISTINCT ON and ORDER BY, adopt the sorting
	 * semantics from ORDER BY items that match DISTINCT ON items, and also
	 * adopt their column sort order.  We insist that the distinctClause and
	 * sortClause match, so throw error if we find the need to add any more
	 * distinctClause items after we've skipped an ORDER BY item that wasn't
	 * in DISTINCT ON.
	 */
	skipped_sortitem = false;
	foreach(lc, sortClause)
	{
		SortGroupClause *scl = (SortGroupClause *) lfirst(lc);

		if (list_member_int(sortgrouprefs, scl->tleSortGroupRef))
		{
			if (skipped_sortitem)
				ereport(ERROR,
						(errcode(ERRCODE_INVALID_COLUMN_REFERENCE),
						 errmsg("SELECT DISTINCT ON expressions must match initial ORDER BY expressions"),
						 parser_errposition(pstate,
											get_matching_location(scl->tleSortGroupRef,
																  sortgrouprefs,
																  distinctlist))));
			else
				result = lappend(result, copyObject(scl));
		}
		else
			skipped_sortitem = true;