• Tom Lane's avatar
    Extend the parser location infrastructure to include a location field in · a2794623
    Tom Lane authored
    most node types used in expression trees (both before and after parse
    analysis).  This allows us to place an error cursor in many situations
    where we formerly could not, because the information wasn't available
    beyond the very first level of parse analysis.  There's a fair amount
    of work still to be done to persuade individual ereport() calls to actually
    include an error location, but this gets the initdb-forcing part of the
    work out of the way; and the situation is already markedly better than
    before for complaints about unimplementable implicit casts, such as
    CASE and UNION constructs with incompatible alternative data types.
    Per my proposal of a few days ago.
    a2794623
parse_node.c 12.2 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454
/*-------------------------------------------------------------------------
 *
 * parse_node.c
 *	  various routines that make nodes for querytrees
 *
 * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/parser/parse_node.c,v 1.102 2008/08/28 23:09:47 tgl Exp $
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include "access/heapam.h"
#include "catalog/pg_type.h"
#include "mb/pg_wchar.h"
#include "nodes/makefuncs.h"
#include "nodes/nodeFuncs.h"
#include "parser/parsetree.h"
#include "parser/parse_coerce.h"
#include "parser/parse_expr.h"
#include "parser/parse_relation.h"
#include "utils/builtins.h"
#include "utils/int8.h"
#include "utils/syscache.h"
#include "utils/varbit.h"


/*
 * make_parsestate
 *		Allocate and initialize a new ParseState.
 *
 * Caller should eventually release the ParseState via free_parsestate().
 */
ParseState *
make_parsestate(ParseState *parentParseState)
{
	ParseState *pstate;

	pstate = palloc0(sizeof(ParseState));

	pstate->parentParseState = parentParseState;

	/* Fill in fields that don't start at null/false/zero */
	pstate->p_next_resno = 1;

	if (parentParseState)
	{
		pstate->p_sourcetext = parentParseState->p_sourcetext;
		pstate->p_variableparams = parentParseState->p_variableparams;
	}

	return pstate;
}

/*
 * free_parsestate
 *		Release a ParseState and any subsidiary resources.
 */
void
free_parsestate(ParseState *pstate)
{
	/*
	 * Check that we did not produce too many resnos; at the very least we
	 * cannot allow more than 2^16, since that would exceed the range of a
	 * AttrNumber. It seems safest to use MaxTupleAttributeNumber.
	 */
	if (pstate->p_next_resno - 1 > MaxTupleAttributeNumber)
		ereport(ERROR,
				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
				 errmsg("target lists can have at most %d entries",
						MaxTupleAttributeNumber)));

	if (pstate->p_target_relation != NULL)
		heap_close(pstate->p_target_relation, NoLock);

	pfree(pstate);
}


/*
 * parser_errposition
 *		Report a parse-analysis-time cursor position, if possible.
 *
 * This is expected to be used within an ereport() call.  The return value
 * is a dummy (always 0, in fact).
 *
 * The locations stored in raw parsetrees are byte offsets into the source
 * string.	We have to convert them to 1-based character indexes for reporting
 * to clients.	(We do things this way to avoid unnecessary overhead in the
 * normal non-error case: computing character indexes would be much more
 * expensive than storing token offsets.)
 */
int
parser_errposition(ParseState *pstate, int location)
{
	int			pos;

	/* No-op if location was not provided */
	if (location < 0)
		return 0;
	/* Can't do anything if source text is not available */
	if (pstate == NULL || pstate->p_sourcetext == NULL)
		return 0;
	/* Convert offset to character number */
	pos = pg_mbstrlen_with_len(pstate->p_sourcetext, location) + 1;
	/* And pass it to the ereport mechanism */
	return errposition(pos);
}


/*
 * make_var
 *		Build a Var node for an attribute identified by RTE and attrno
 */
Var *
make_var(ParseState *pstate, RangeTblEntry *rte, int attrno, int location)
{
	Var		   *result;
	int			vnum,
				sublevels_up;
	Oid			vartypeid;
	int32		type_mod;

	vnum = RTERangeTablePosn(pstate, rte, &sublevels_up);
	get_rte_attribute_type(rte, attrno, &vartypeid, &type_mod);
	result = makeVar(vnum, attrno, vartypeid, type_mod, sublevels_up);
	result->location = location;
	return result;
}

/*
 * transformArrayType()
 *		Get the element type of an array type in preparation for subscripting
 */
Oid
transformArrayType(Oid arrayType)
{
	Oid			elementType;
	HeapTuple	type_tuple_array;
	Form_pg_type type_struct_array;

	/* Get the type tuple for the array */
	type_tuple_array = SearchSysCache(TYPEOID,
									  ObjectIdGetDatum(arrayType),
									  0, 0, 0);
	if (!HeapTupleIsValid(type_tuple_array))
		elog(ERROR, "cache lookup failed for type %u", arrayType);
	type_struct_array = (Form_pg_type) GETSTRUCT(type_tuple_array);

	/* needn't check typisdefined since this will fail anyway */

	elementType = type_struct_array->typelem;
	if (elementType == InvalidOid)
		ereport(ERROR,
				(errcode(ERRCODE_DATATYPE_MISMATCH),
				 errmsg("cannot subscript type %s because it is not an array",
						format_type_be(arrayType))));

	ReleaseSysCache(type_tuple_array);

	return elementType;
}

/*
 * transformArraySubscripts()
 *		Transform array subscripting.  This is used for both
 *		array fetch and array assignment.
 *
 * In an array fetch, we are given a source array value and we produce an
 * expression that represents the result of extracting a single array element
 * or an array slice.
 *
 * In an array assignment, we are given a destination array value plus a
 * source value that is to be assigned to a single element or a slice of
 * that array.	We produce an expression that represents the new array value
 * with the source data inserted into the right part of the array.
 *
 * pstate		Parse state
 * arrayBase	Already-transformed expression for the array as a whole
 * arrayType	OID of array's datatype (should match type of arrayBase)
 * elementType	OID of array's element type (fetch with transformArrayType,
 *				or pass InvalidOid to do it here)
 * elementTypMod typmod to be applied to array elements (if storing) or of
 *				the source array (if fetching)
 * indirection	Untransformed list of subscripts (must not be NIL)
 * assignFrom	NULL for array fetch, else transformed expression for source.
 */
ArrayRef *
transformArraySubscripts(ParseState *pstate,
						 Node *arrayBase,
						 Oid arrayType,
						 Oid elementType,
						 int32 elementTypMod,
						 List *indirection,
						 Node *assignFrom)
{
	bool		isSlice = false;
	List	   *upperIndexpr = NIL;
	List	   *lowerIndexpr = NIL;
	ListCell   *idx;
	ArrayRef   *aref;

	/* Caller may or may not have bothered to determine elementType */
	if (!OidIsValid(elementType))
		elementType = transformArrayType(arrayType);

	/*
	 * A list containing only single subscripts refers to a single array
	 * element.  If any of the items are double subscripts (lower:upper), then
	 * the subscript expression means an array slice operation. In this case,
	 * we supply a default lower bound of 1 for any items that contain only a
	 * single subscript.  We have to prescan the indirection list to see if
	 * there are any double subscripts.
	 */
	foreach(idx, indirection)
	{
		A_Indices  *ai = (A_Indices *) lfirst(idx);

		if (ai->lidx != NULL)
		{
			isSlice = true;
			break;
		}
	}

	/*
	 * Transform the subscript expressions.
	 */
	foreach(idx, indirection)
	{
		A_Indices  *ai = (A_Indices *) lfirst(idx);
		Node	   *subexpr;

		Assert(IsA(ai, A_Indices));
		if (isSlice)
		{
			if (ai->lidx)
			{
				subexpr = transformExpr(pstate, ai->lidx);
				/* If it's not int4 already, try to coerce */
				subexpr = coerce_to_target_type(pstate,
												subexpr, exprType(subexpr),
												INT4OID, -1,
												COERCION_ASSIGNMENT,
												COERCE_IMPLICIT_CAST,
												-1);
				if (subexpr == NULL)
					ereport(ERROR,
							(errcode(ERRCODE_DATATYPE_MISMATCH),
							 errmsg("array subscript must have type integer"),
							 parser_errposition(pstate, exprLocation(ai->lidx))));
			}
			else
			{
				/* Make a constant 1 */
				subexpr = (Node *) makeConst(INT4OID,
											 -1,
											 sizeof(int32),
											 Int32GetDatum(1),
											 false,
											 true);		/* pass by value */
			}
			lowerIndexpr = lappend(lowerIndexpr, subexpr);
		}
		subexpr = transformExpr(pstate, ai->uidx);
		/* If it's not int4 already, try to coerce */
		subexpr = coerce_to_target_type(pstate,
										subexpr, exprType(subexpr),
										INT4OID, -1,
										COERCION_ASSIGNMENT,
										COERCE_IMPLICIT_CAST,
										-1);
		if (subexpr == NULL)
			ereport(ERROR,
					(errcode(ERRCODE_DATATYPE_MISMATCH),
					 errmsg("array subscript must have type integer"),
					 parser_errposition(pstate, exprLocation(ai->uidx))));
		upperIndexpr = lappend(upperIndexpr, subexpr);
	}

	/*
	 * If doing an array store, coerce the source value to the right type.
	 * (This should agree with the coercion done by transformAssignedExpr.)
	 */
	if (assignFrom != NULL)
	{
		Oid			typesource = exprType(assignFrom);
		Oid			typeneeded = isSlice ? arrayType : elementType;
		Node	   *newFrom;

		newFrom = coerce_to_target_type(pstate,
										assignFrom, typesource,
										typeneeded, elementTypMod,
										COERCION_ASSIGNMENT,
										COERCE_IMPLICIT_CAST,
										-1);
		if (newFrom == NULL)
			ereport(ERROR,
					(errcode(ERRCODE_DATATYPE_MISMATCH),
					 errmsg("array assignment requires type %s"
							" but expression is of type %s",
							format_type_be(typeneeded),
							format_type_be(typesource)),
			   errhint("You will need to rewrite or cast the expression."),
					 parser_errposition(pstate, exprLocation(assignFrom))));
		assignFrom = newFrom;
	}

	/*
	 * Ready to build the ArrayRef node.
	 */
	aref = makeNode(ArrayRef);
	aref->refarraytype = arrayType;
	aref->refelemtype = elementType;
	aref->reftypmod = elementTypMod;
	aref->refupperindexpr = upperIndexpr;
	aref->reflowerindexpr = lowerIndexpr;
	aref->refexpr = (Expr *) arrayBase;
	aref->refassgnexpr = (Expr *) assignFrom;

	return aref;
}

/*
 * make_const
 *
 *	Convert a Value node (as returned by the grammar) to a Const node
 *	of the "natural" type for the constant.  Note that this routine is
 *	only used when there is no explicit cast for the constant, so we
 *	have to guess what type is wanted.
 *
 *	For string literals we produce a constant of type UNKNOWN ---- whose
 *	representation is the same as cstring, but it indicates to later type
 *	resolution that we're not sure yet what type it should be considered.
 *	Explicit "NULL" constants are also typed as UNKNOWN.
 *
 *	For integers and floats we produce int4, int8, or numeric depending
 *	on the value of the number.  XXX We should produce int2 as well,
 *	but additional cleanup is needed before we can do that; there are
 *	too many examples that fail if we try.
 */
Const *
make_const(Value *value, int location)
{
	Datum		val;
	int64		val64;
	Oid			typeid;
	int			typelen;
	bool		typebyval;
	Const	   *con;

	switch (nodeTag(value))
	{
		case T_Integer:
			val = Int32GetDatum(intVal(value));

			typeid = INT4OID;
			typelen = sizeof(int32);
			typebyval = true;
			break;

		case T_Float:
			/* could be an oversize integer as well as a float ... */
			if (scanint8(strVal(value), true, &val64))
			{
				/*
				 * It might actually fit in int32. Probably only INT_MIN can
				 * occur, but we'll code the test generally just to be sure.
				 */
				int32		val32 = (int32) val64;

				if (val64 == (int64) val32)
				{
					val = Int32GetDatum(val32);

					typeid = INT4OID;
					typelen = sizeof(int32);
					typebyval = true;
				}
				else
				{
					val = Int64GetDatum(val64);

					typeid = INT8OID;
					typelen = sizeof(int64);
					typebyval = FLOAT8PASSBYVAL;	/* int8 and float8 alike */
				}
			}
			else
			{
				val = DirectFunctionCall3(numeric_in,
										  CStringGetDatum(strVal(value)),
										  ObjectIdGetDatum(InvalidOid),
										  Int32GetDatum(-1));

				typeid = NUMERICOID;
				typelen = -1;	/* variable len */
				typebyval = false;
			}
			break;

		case T_String:

			/*
			 * We assume here that UNKNOWN's internal representation is the
			 * same as CSTRING
			 */
			val = CStringGetDatum(strVal(value));

			typeid = UNKNOWNOID;	/* will be coerced later */
			typelen = -2;		/* cstring-style varwidth type */
			typebyval = false;
			break;

		case T_BitString:
			val = DirectFunctionCall3(bit_in,
									  CStringGetDatum(strVal(value)),
									  ObjectIdGetDatum(InvalidOid),
									  Int32GetDatum(-1));
			typeid = BITOID;
			typelen = -1;
			typebyval = false;
			break;

		case T_Null:
			/* return a null const */
			con = makeConst(UNKNOWNOID,
							-1,
							-2,
							(Datum) 0,
							true,
							false);
			con->location = location;
			return con;

		default:
			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(value));
			return NULL;		/* keep compiler quiet */
	}

	con = makeConst(typeid,
					-1,			/* typmod -1 is OK for all cases */
					typelen,
					val,
					false,
					typebyval);
	con->location = location;

	return con;
}