pg_query 4.2.1 → 5.1.0

data/ext/pg_query/src_backend_utils_adt_numutils.c

@@ -0,0 +1,489 @@
+/*--------------------------------------------------------------------
+ * Symbols referenced in this file:
+ * - pg_strtoint32_safe
+ * - hexlookup
+ *--------------------------------------------------------------------
+ */
+
+/*-------------------------------------------------------------------------
+ *
+ * numutils.c
+ *	  utility functions for I/O of built-in numeric types.
+ *
+ * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/adt/numutils.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include <math.h>
+#include <limits.h>
+#include <ctype.h>
+
+#include "common/int.h"
+#include "utils/builtins.h"
+#include "port/pg_bitutils.h"
+
+/*
+ * A table of all two-digit numbers. This is used to speed up decimal digit
+ * generation by copying pairs of digits into the final output.
+ */
+
+
+/*
+ * Adapted from http://graphics.stanford.edu/~seander/bithacks.html#IntegerLog10
+ */
+
+
+
+
+static const int8 hexlookup[128] = {
+	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+	0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -1, -1, -1, -1, -1, -1,
+	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+};
+
+/*
+ * Convert input string to a signed 16 bit integer.  Input strings may be
+ * expressed in base-10, hexadecimal, octal, or binary format, all of which
+ * can be prefixed by an optional sign character, either '+' (the default) or
+ * '-' for negative numbers.  Hex strings are recognized by the digits being
+ * prefixed by 0x or 0X while octal strings are recognized by the 0o or 0O
+ * prefix.  The binary representation is recognized by the 0b or 0B prefix.
+ *
+ * Allows any number of leading or trailing whitespace characters.  Digits may
+ * optionally be separated by a single underscore character.  These can only
+ * come between digits and not before or after the digits.  Underscores have
+ * no effect on the return value and are supported only to assist in improving
+ * the human readability of the input strings.
+ *
+ * pg_strtoint16() will throw ereport() upon bad input format or overflow;
+ * while pg_strtoint16_safe() instead returns such complaints in *escontext,
+ * if it's an ErrorSaveContext.
+*
+ * NB: Accumulate input as an unsigned number, to deal with two's complement
+ * representation of the most negative number, which can't be represented as a
+ * signed positive number.
+ */
+
+
+
+
+/*
+ * Convert input string to a signed 32 bit integer.  Input strings may be
+ * expressed in base-10, hexadecimal, octal, or binary format, all of which
+ * can be prefixed by an optional sign character, either '+' (the default) or
+ * '-' for negative numbers.  Hex strings are recognized by the digits being
+ * prefixed by 0x or 0X while octal strings are recognized by the 0o or 0O
+ * prefix.  The binary representation is recognized by the 0b or 0B prefix.
+ *
+ * Allows any number of leading or trailing whitespace characters.  Digits may
+ * optionally be separated by a single underscore character.  These can only
+ * come between digits and not before or after the digits.  Underscores have
+ * no effect on the return value and are supported only to assist in improving
+ * the human readability of the input strings.
+ *
+ * pg_strtoint32() will throw ereport() upon bad input format or overflow;
+ * while pg_strtoint32_safe() instead returns such complaints in *escontext,
+ * if it's an ErrorSaveContext.
+ *
+ * NB: Accumulate input as an unsigned number, to deal with two's complement
+ * representation of the most negative number, which can't be represented as a
+ * signed positive number.
+ */
+
+
+int32
+pg_strtoint32_safe(const char *s, Node *escontext)
+{
+	const char *ptr = s;
+	const char *firstdigit;
+	uint32		tmp = 0;
+	bool		neg = false;
+	unsigned char digit;
+
+	/*
+	 * The majority of cases are likely to be base-10 digits without any
+	 * underscore separator characters.  We'll first try to parse the string
+	 * with the assumption that's the case and only fallback on a slower
+	 * implementation which handles hex, octal and binary strings and
+	 * underscores if the fastpath version cannot parse the string.
+	 */
+
+	/* leave it up to the slow path to look for leading spaces */
+
+	if (*ptr == '-')
+	{
+		ptr++;
+		neg = true;
+	}
+
+	/* a leading '+' is uncommon so leave that for the slow path */
+
+	/* process the first digit */
+	digit = (*ptr - '0');
+
+	/*
+	 * Exploit unsigned arithmetic to save having to check both the upper and
+	 * lower bounds of the digit.
+	 */
+	if (likely(digit < 10))
+	{
+		ptr++;
+		tmp = digit;
+	}
+	else
+	{
+		/* we need at least one digit */
+		goto slow;
+	}
+
+	/* process remaining digits */
+	for (;;)
+	{
+		digit = (*ptr - '0');
+
+		if (digit >= 10)
+			break;
+
+		ptr++;
+
+		if (unlikely(tmp > -(PG_INT32_MIN / 10)))
+			goto out_of_range;
+
+		tmp = tmp * 10 + digit;
+	}
+
+	/* when the string does not end in a digit, let the slow path handle it */
+	if (unlikely(*ptr != '\0'))
+		goto slow;
+
+	if (neg)
+	{
+		/* check the negative equivalent will fit without overflowing */
+		if (unlikely(tmp > (uint32) (-(PG_INT32_MIN + 1)) + 1))
+			goto out_of_range;
+		return -((int32) tmp);
+	}
+
+	if (unlikely(tmp > PG_INT32_MAX))
+		goto out_of_range;
+
+	return (int32) tmp;
+
+slow:
+	tmp = 0;
+	ptr = s;
+	/* no need to reset neg */
+
+	/* skip leading spaces */
+	while (isspace((unsigned char) *ptr))
+		ptr++;
+
+	/* handle sign */
+	if (*ptr == '-')
+	{
+		ptr++;
+		neg = true;
+	}
+	else if (*ptr == '+')
+		ptr++;
+
+	/* process digits */
+	if (ptr[0] == '0' && (ptr[1] == 'x' || ptr[1] == 'X'))
+	{
+		firstdigit = ptr += 2;
+
+		for (;;)
+		{
+			if (isxdigit((unsigned char) *ptr))
+			{
+				if (unlikely(tmp > -(PG_INT32_MIN / 16)))
+					goto out_of_range;
+
+				tmp = tmp * 16 + hexlookup[(unsigned char) *ptr++];
+			}
+			else if (*ptr == '_')
+			{
+				/* underscore must be followed by more digits */
+				ptr++;
+				if (*ptr == '\0' || !isxdigit((unsigned char) *ptr))
+					goto invalid_syntax;
+			}
+			else
+				break;
+		}
+	}
+	else if (ptr[0] == '0' && (ptr[1] == 'o' || ptr[1] == 'O'))
+	{
+		firstdigit = ptr += 2;
+
+		for (;;)
+		{
+			if (*ptr >= '0' && *ptr <= '7')
+			{
+				if (unlikely(tmp > -(PG_INT32_MIN / 8)))
+					goto out_of_range;
+
+				tmp = tmp * 8 + (*ptr++ - '0');
+			}
+			else if (*ptr == '_')
+			{
+				/* underscore must be followed by more digits */
+				ptr++;
+				if (*ptr == '\0' || *ptr < '0' || *ptr > '7')
+					goto invalid_syntax;
+			}
+			else
+				break;
+		}
+	}
+	else if (ptr[0] == '0' && (ptr[1] == 'b' || ptr[1] == 'B'))
+	{
+		firstdigit = ptr += 2;
+
+		for (;;)
+		{
+			if (*ptr >= '0' && *ptr <= '1')
+			{
+				if (unlikely(tmp > -(PG_INT32_MIN / 2)))
+					goto out_of_range;
+
+				tmp = tmp * 2 + (*ptr++ - '0');
+			}
+			else if (*ptr == '_')
+			{
+				/* underscore must be followed by more digits */
+				ptr++;
+				if (*ptr == '\0' || *ptr < '0' || *ptr > '1')
+					goto invalid_syntax;
+			}
+			else
+				break;
+		}
+	}
+	else
+	{
+		firstdigit = ptr;
+
+		for (;;)
+		{
+			if (*ptr >= '0' && *ptr <= '9')
+			{
+				if (unlikely(tmp > -(PG_INT32_MIN / 10)))
+					goto out_of_range;
+
+				tmp = tmp * 10 + (*ptr++ - '0');
+			}
+			else if (*ptr == '_')
+			{
+				/* underscore may not be first */
+				if (unlikely(ptr == firstdigit))
+					goto invalid_syntax;
+				/* and it must be followed by more digits */
+				ptr++;
+				if (*ptr == '\0' || !isdigit((unsigned char) *ptr))
+					goto invalid_syntax;
+			}
+			else
+				break;
+		}
+	}
+
+	/* require at least one digit */
+	if (unlikely(ptr == firstdigit))
+		goto invalid_syntax;
+
+	/* allow trailing whitespace, but not other trailing chars */
+	while (isspace((unsigned char) *ptr))
+		ptr++;
+
+	if (unlikely(*ptr != '\0'))
+		goto invalid_syntax;
+
+	if (neg)
+	{
+		/* check the negative equivalent will fit without overflowing */
+		if (tmp > (uint32) (-(PG_INT32_MIN + 1)) + 1)
+			goto out_of_range;
+		return -((int32) tmp);
+	}
+
+	if (tmp > PG_INT32_MAX)
+		goto out_of_range;
+
+	return (int32) tmp;
+
+out_of_range:
+	ereturn(escontext, 0,
+			(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
+			 errmsg("value \"%s\" is out of range for type %s",
+					s, "integer")));
+
+invalid_syntax:
+	ereturn(escontext, 0,
+			(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+			 errmsg("invalid input syntax for type %s: \"%s\"",
+					"integer", s)));
+}
+
+/*
+ * Convert input string to a signed 64 bit integer.  Input strings may be
+ * expressed in base-10, hexadecimal, octal, or binary format, all of which
+ * can be prefixed by an optional sign character, either '+' (the default) or
+ * '-' for negative numbers.  Hex strings are recognized by the digits being
+ * prefixed by 0x or 0X while octal strings are recognized by the 0o or 0O
+ * prefix.  The binary representation is recognized by the 0b or 0B prefix.
+ *
+ * Allows any number of leading or trailing whitespace characters.  Digits may
+ * optionally be separated by a single underscore character.  These can only
+ * come between digits and not before or after the digits.  Underscores have
+ * no effect on the return value and are supported only to assist in improving
+ * the human readability of the input strings.
+ *
+ * pg_strtoint64() will throw ereport() upon bad input format or overflow;
+ * while pg_strtoint64_safe() instead returns such complaints in *escontext,
+ * if it's an ErrorSaveContext.
+ *
+ * NB: Accumulate input as an unsigned number, to deal with two's complement
+ * representation of the most negative number, which can't be represented as a
+ * signed positive number.
+ */
+
+
+
+
+/*
+ * Convert input string to an unsigned 32 bit integer.
+ *
+ * Allows any number of leading or trailing whitespace characters.
+ *
+ * If endloc isn't NULL, store a pointer to the rest of the string there,
+ * so that caller can parse the rest.  Otherwise, it's an error if anything
+ * but whitespace follows.
+ *
+ * typname is what is reported in error messges.
+ *
+ * If escontext points to an ErrorSaveContext node, that is filled instead
+ * of throwing an error; the caller must check SOFT_ERROR_OCCURRED()
+ * to detect errors.
+ */
+#if PG_UINT32_MAX != ULONG_MAX
+#endif
+
+/*
+ * Convert input string to an unsigned 64 bit integer.
+ *
+ * Allows any number of leading or trailing whitespace characters.
+ *
+ * If endloc isn't NULL, store a pointer to the rest of the string there,
+ * so that caller can parse the rest.  Otherwise, it's an error if anything
+ * but whitespace follows.
+ *
+ * typname is what is reported in error messges.
+ *
+ * If escontext points to an ErrorSaveContext node, that is filled instead
+ * of throwing an error; the caller must check SOFT_ERROR_OCCURRED()
+ * to detect errors.
+ */
+
+
+/*
+ * pg_itoa: converts a signed 16-bit integer to its string representation
+ * and returns strlen(a).
+ *
+ * Caller must ensure that 'a' points to enough memory to hold the result
+ * (at least 7 bytes, counting a leading sign and trailing NUL).
+ *
+ * It doesn't seem worth implementing this separately.
+ */
+
+
+/*
+ * pg_ultoa_n: converts an unsigned 32-bit integer to its string representation,
+ * not NUL-terminated, and returns the length of that string representation
+ *
+ * Caller must ensure that 'a' points to enough memory to hold the result (at
+ * least 10 bytes)
+ */
+
+
+/*
+ * pg_ltoa: converts a signed 32-bit integer to its string representation and
+ * returns strlen(a).
+ *
+ * It is the caller's responsibility to ensure that a is at least 12 bytes long,
+ * which is enough room to hold a minus sign, a maximally long int32, and the
+ * above terminating NUL.
+ */
+
+
+/*
+ * Get the decimal representation, not NUL-terminated, and return the length of
+ * same.  Caller must ensure that a points to at least MAXINT8LEN bytes.
+ */
+
+
+/*
+ * pg_lltoa: converts a signed 64-bit integer to its string representation and
+ * returns strlen(a).
+ *
+ * Caller must ensure that 'a' points to enough memory to hold the result
+ * (at least MAXINT8LEN + 1 bytes, counting a leading sign and trailing NUL).
+ */
+
+
+
+/*
+ * pg_ultostr_zeropad
+ *		Converts 'value' into a decimal string representation stored at 'str'.
+ *		'minwidth' specifies the minimum width of the result; any extra space
+ *		is filled up by prefixing the number with zeros.
+ *
+ * Returns the ending address of the string result (the last character written
+ * plus 1).  Note that no NUL terminator is written.
+ *
+ * The intended use-case for this function is to build strings that contain
+ * multiple individual numbers, for example:
+ *
+ *	str = pg_ultostr_zeropad(str, hours, 2);
+ *	*str++ = ':';
+ *	str = pg_ultostr_zeropad(str, mins, 2);
+ *	*str++ = ':';
+ *	str = pg_ultostr_zeropad(str, secs, 2);
+ *	*str = '\0';
+ *
+ * Note: Caller must ensure that 'str' points to enough memory to hold the
+ * result.
+ */
+
+
+/*
+ * pg_ultostr
+ *		Converts 'value' into a decimal string representation stored at 'str'.
+ *
+ * Returns the ending address of the string result (the last character written
+ * plus 1).  Note that no NUL terminator is written.
+ *
+ * The intended use-case for this function is to build strings that contain
+ * multiple individual numbers, for example:
+ *
+ *	str = pg_ultostr(str, a);
+ *	*str++ = ' ';
+ *	str = pg_ultostr(str, b);
+ *	*str = '\0';
+ *
+ * Note: Caller must ensure that 'str' points to enough memory to hold the
+ * result.
+ */
+

data/ext/pg_query/src_backend_utils_adt_ruleutils.c

@@ -11,7 +11,7 @@
  *	  Functions to convert stored expressions/querytrees back to
  *	  source text
  *
- * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  *
@@ -419,6 +419,8 @@ static void get_update_query_targetlist_def(Query *query, List *targetList,
 											RangeTblEntry *rte);
 static void get_delete_query_def(Query *query, deparse_context *context,
 								 bool colNamesVisible);
+static void get_merge_query_def(Query *query, deparse_context *context,
+								bool colNamesVisible);
 static void get_utility_query_def(Query *query, deparse_context *context);
 static void get_basic_select_query(Query *query, deparse_context *context,
 								   TupleDesc resultDesc, bool colNamesVisible);
@@ -465,9 +467,15 @@ static void get_func_expr(FuncExpr *expr, deparse_context *context,
 						  bool showimplicit);
 static void get_agg_expr(Aggref *aggref, deparse_context *context,
 						 Aggref *original_aggref);
+static void get_agg_expr_helper(Aggref *aggref, deparse_context *context,
+								Aggref *original_aggref, const char *funcname,
+								const char *options, bool is_json_objectagg);
 static void get_agg_combine_expr(Node *node, deparse_context *context,
 								 void *callback_arg);
 static void get_windowfunc_expr(WindowFunc *wfunc, deparse_context *context);
+static void get_windowfunc_expr_helper(WindowFunc *wfunc, deparse_context *context,
+									   const char *funcname, const char *options,
+									   bool is_json_objectagg);
 static bool get_func_sql_syntax(FuncExpr *expr, deparse_context *context);
 static void get_coercion_expr(Node *arg, deparse_context *context,
 							  Oid resulttype, int32 resulttypmod,
@@ -475,6 +483,15 @@ static void get_coercion_expr(Node *arg, deparse_context *context,
 static void get_const_expr(Const *constval, deparse_context *context,
 						   int showtype);
 static void get_const_collation(Const *constval, deparse_context *context);
+static void get_json_format(JsonFormat *format, StringInfo buf);
+static void get_json_constructor(JsonConstructorExpr *ctor,
+								 deparse_context *context, bool showimplicit);
+static void get_json_constructor_options(JsonConstructorExpr *ctor,
+										 StringInfo buf);
+static void get_json_agg_constructor(JsonConstructorExpr *ctor,
+									 deparse_context *context,
+									 const char *funcname,
+									 bool is_json_objectagg);
 static void simple_quote_literal(StringInfo buf, const char *val);
 static void get_sublink_expr(SubLink *sublink, deparse_context *context);
 static void get_tablefunc(TableFunc *tf, deparse_context *context,
@@ -483,6 +500,8 @@ static void get_from_clause(Query *query, const char *prefix,
 							deparse_context *context);
 static void get_from_clause_item(Node *jtnode, Query *query,
 								 deparse_context *context);
+static void get_rte_alias(RangeTblEntry *rte, int varno, bool use_as,
+						  deparse_context *context);
 static void get_column_alias_list(deparse_columns *colinfo,
 								  deparse_context *context);
 static void get_from_clause_coldeflist(RangeTblFunction *rtfunc,
@@ -584,6 +603,9 @@ static void get_reloptions(StringInfo buf, Datum reloptions);
 /* Internal version that just reports the key-column definitions */
 
 
+/* Internal version, extensible with flags to control its behavior */
+
+
 /*
  * Internal workhorse to decompile an index definition.
  *
@@ -637,7 +659,7 @@ static void get_reloptions(StringInfo buf, Datum reloptions);
  *
  * Returns the partition key specification, ie, the following:
  *
- * PARTITION BY { RANGE | LIST | HASH } (column opt_collation opt_opclass [, ...])
+ * { RANGE | LIST | HASH } (column opt_collation opt_opclass [, ...])
  */
 
 
@@ -744,8 +766,8 @@ static void get_reloptions(StringInfo buf, Datum reloptions);
  *
  * Note: if you change the output format of this function, be careful not
  * to break psql's rules (in \ef and \sf) for identifying the start of the
- * function body.  To wit: the function body starts on a line that begins
- * with "AS ", and no preceding line will look like that.
+ * function body.  To wit: the function body starts on a line that begins with
+ * "AS ", "BEGIN ", or "RETURN ", and no preceding line will look like that.
  */
 
 
@@ -1214,6 +1236,13 @@ static void get_reloptions(StringInfo buf, Datum reloptions);
 
 
 
+/* ----------
+ * get_merge_query_def				- Parse back a MERGE parsetree
+ * ----------
+ */
+
+
+
 /* ----------
  * get_utility_query_def			- Parse back a UTILITY parsetree
  * ----------
@@ -1413,6 +1442,12 @@ static void get_reloptions(StringInfo buf, Datum reloptions);
  */
 
 
+/*
+ * get_agg_expr_helper		- subroutine for get_agg_expr and
+ *							get_json_agg_constructor
+ */
+
+
 /*
  * This is a helper function for get_agg_expr().  It's used when we deparse
  * a combining Aggref; resolve_special_varno locates the corresponding partial
@@ -1425,6 +1460,13 @@ static void get_reloptions(StringInfo buf, Datum reloptions);
  */
 
 
+
+/*
+ * get_windowfunc_expr_helper	- subroutine for get_windowfunc_expr and
+ *								get_json_agg_constructor
+ */
+
+
 /*
  * get_func_sql_syntax		- Parse back a SQL-syntax function call
  *
@@ -1463,6 +1505,31 @@ static void get_reloptions(StringInfo buf, Datum reloptions);
  */
 
 
+/*
+ * get_json_format			- Parse back a JsonFormat node
+ */
+
+
+/*
+ * get_json_returning		- Parse back a JsonReturning structure
+ */
+
+
+/*
+ * get_json_constructor		- Parse back a JsonConstructorExpr node
+ */
+
+
+/*
+ * Append options, if any, to the JSON constructor being deparsed
+ */
+
+
+/*
+ * get_json_agg_constructor - Parse back an aggregate JsonConstructorExpr node
+ */
+
+
 /*
  * simple_quote_literal - Format a string as a SQL literal, append to buf
  */
@@ -1494,6 +1561,13 @@ static void get_reloptions(StringInfo buf, Datum reloptions);
 
 
 
+/*
+ * get_rte_alias - print the relation's alias, if needed
+ *
+ * If printed, the alias is preceded by a space, or by " AS " if use_as is true.
+ */
+
+
 /*
  * get_column_alias_list - print column alias list for an RTE
  *
@@ -1533,7 +1607,7 @@ static void get_reloptions(StringInfo buf, Datum reloptions);
 
 /*
  * generate_opclass_name
- *		Compute the name to display for a opclass specified by OID
+ *		Compute the name to display for an opclass specified by OID
  *
  * The result includes all necessary quoting and schema-prefixing.
  */

data/ext/pg_query/src_backend_utils_error_assert.c

@@ -9,7 +9,7 @@
  * assert.c
  *	  Assert support code.
  *
- * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  *
@@ -34,20 +34,17 @@
  */
 void
 ExceptionalCondition(const char *conditionName,
-					 const char *errorType,
 					 const char *fileName,
 					 int lineNumber)
 {
 	/* Report the failure on stderr (or local equivalent) */
 	if (!PointerIsValid(conditionName)
-		|| !PointerIsValid(fileName)
-		|| !PointerIsValid(errorType))
+		|| !PointerIsValid(fileName))
 		write_stderr("TRAP: ExceptionalCondition: bad arguments in PID %d\n",
 					 (int) getpid());
 	else
-		write_stderr("TRAP: %s(\"%s\", File: \"%s\", Line: %d, PID: %d)\n",
-					 errorType, conditionName,
-					 fileName, lineNumber, (int) getpid());
+		write_stderr("TRAP: failed Assert(\"%s\"), File: \"%s\", Line: %d, PID: %d\n",
+					 conditionName, fileName, lineNumber, (int) getpid());
 
 	/* Usually this shouldn't be needed, but make sure the msg went out */
 	fflush(stderr);