pg_query 5.0.0 → 6.0.0

data/ext/pg_query/include/postgres/port/pg_bitutils.h

@@ -0,0 +1,421 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_bitutils.h
+ *	  Miscellaneous functions for bit-wise operations.
+ *
+ *
+ * Copyright (c) 2019-2024, PostgreSQL Global Development Group
+ *
+ * src/include/port/pg_bitutils.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_BITUTILS_H
+#define PG_BITUTILS_H
+
+#ifdef _MSC_VER
+#include <intrin.h>
+#define HAVE_BITSCAN_FORWARD
+#define HAVE_BITSCAN_REVERSE
+
+#else
+#if defined(HAVE__BUILTIN_CTZ)
+#define HAVE_BITSCAN_FORWARD
+#endif
+
+#if defined(HAVE__BUILTIN_CLZ)
+#define HAVE_BITSCAN_REVERSE
+#endif
+#endif							/* _MSC_VER */
+
+extern PGDLLIMPORT const uint8 pg_leftmost_one_pos[256];
+extern PGDLLIMPORT const uint8 pg_rightmost_one_pos[256];
+extern PGDLLIMPORT const uint8 pg_number_of_ones[256];
+
+/*
+ * pg_leftmost_one_pos32
+ *		Returns the position of the most significant set bit in "word",
+ *		measured from the least significant bit.  word must not be 0.
+ */
+static inline int
+pg_leftmost_one_pos32(uint32 word)
+{
+#ifdef HAVE__BUILTIN_CLZ
+	Assert(word != 0);
+
+	return 31 - __builtin_clz(word);
+#elif defined(_MSC_VER)
+	unsigned long result;
+	bool		non_zero;
+
+	Assert(word != 0);
+
+	non_zero = _BitScanReverse(&result, word);
+	return (int) result;
+#else
+	int			shift = 32 - 8;
+
+	Assert(word != 0);
+
+	while ((word >> shift) == 0)
+		shift -= 8;
+
+	return shift + pg_leftmost_one_pos[(word >> shift) & 255];
+#endif							/* HAVE__BUILTIN_CLZ */
+}
+
+/*
+ * pg_leftmost_one_pos64
+ *		As above, but for a 64-bit word.
+ */
+static inline int
+pg_leftmost_one_pos64(uint64 word)
+{
+#ifdef HAVE__BUILTIN_CLZ
+	Assert(word != 0);
+
+#if defined(HAVE_LONG_INT_64)
+	return 63 - __builtin_clzl(word);
+#elif defined(HAVE_LONG_LONG_INT_64)
+	return 63 - __builtin_clzll(word);
+#else
+#error must have a working 64-bit integer datatype
+#endif							/* HAVE_LONG_INT_64 */
+
+#elif defined(_MSC_VER) && (defined(_M_AMD64) || defined(_M_ARM64))
+	unsigned long result;
+	bool		non_zero;
+
+	Assert(word != 0);
+
+	non_zero = _BitScanReverse64(&result, word);
+	return (int) result;
+#else
+	int			shift = 64 - 8;
+
+	Assert(word != 0);
+
+	while ((word >> shift) == 0)
+		shift -= 8;
+
+	return shift + pg_leftmost_one_pos[(word >> shift) & 255];
+#endif							/* HAVE__BUILTIN_CLZ */
+}
+
+/*
+ * pg_rightmost_one_pos32
+ *		Returns the position of the least significant set bit in "word",
+ *		measured from the least significant bit.  word must not be 0.
+ */
+static inline int
+pg_rightmost_one_pos32(uint32 word)
+{
+#ifdef HAVE__BUILTIN_CTZ
+	Assert(word != 0);
+
+	return __builtin_ctz(word);
+#elif defined(_MSC_VER)
+	unsigned long result;
+	bool		non_zero;
+
+	Assert(word != 0);
+
+	non_zero = _BitScanForward(&result, word);
+	return (int) result;
+#else
+	int			result = 0;
+
+	Assert(word != 0);
+
+	while ((word & 255) == 0)
+	{
+		word >>= 8;
+		result += 8;
+	}
+	result += pg_rightmost_one_pos[word & 255];
+	return result;
+#endif							/* HAVE__BUILTIN_CTZ */
+}
+
+/*
+ * pg_rightmost_one_pos64
+ *		As above, but for a 64-bit word.
+ */
+static inline int
+pg_rightmost_one_pos64(uint64 word)
+{
+#ifdef HAVE__BUILTIN_CTZ
+	Assert(word != 0);
+
+#if defined(HAVE_LONG_INT_64)
+	return __builtin_ctzl(word);
+#elif defined(HAVE_LONG_LONG_INT_64)
+	return __builtin_ctzll(word);
+#else
+#error must have a working 64-bit integer datatype
+#endif							/* HAVE_LONG_INT_64 */
+
+#elif defined(_MSC_VER) && (defined(_M_AMD64) || defined(_M_ARM64))
+	unsigned long result;
+	bool		non_zero;
+
+	Assert(word != 0);
+
+	non_zero = _BitScanForward64(&result, word);
+	return (int) result;
+#else
+	int			result = 0;
+
+	Assert(word != 0);
+
+	while ((word & 255) == 0)
+	{
+		word >>= 8;
+		result += 8;
+	}
+	result += pg_rightmost_one_pos[word & 255];
+	return result;
+#endif							/* HAVE__BUILTIN_CTZ */
+}
+
+/*
+ * pg_nextpower2_32
+ *		Returns the next higher power of 2 above 'num', or 'num' if it's
+ *		already a power of 2.
+ *
+ * 'num' mustn't be 0 or be above PG_UINT32_MAX / 2 + 1.
+ */
+static inline uint32
+pg_nextpower2_32(uint32 num)
+{
+	Assert(num > 0 && num <= PG_UINT32_MAX / 2 + 1);
+
+	/*
+	 * A power 2 number has only 1 bit set.  Subtracting 1 from such a number
+	 * will turn on all previous bits resulting in no common bits being set
+	 * between num and num-1.
+	 */
+	if ((num & (num - 1)) == 0)
+		return num;				/* already power 2 */
+
+	return ((uint32) 1) << (pg_leftmost_one_pos32(num) + 1);
+}
+
+/*
+ * pg_nextpower2_64
+ *		Returns the next higher power of 2 above 'num', or 'num' if it's
+ *		already a power of 2.
+ *
+ * 'num' mustn't be 0 or be above PG_UINT64_MAX / 2  + 1.
+ */
+static inline uint64
+pg_nextpower2_64(uint64 num)
+{
+	Assert(num > 0 && num <= PG_UINT64_MAX / 2 + 1);
+
+	/*
+	 * A power 2 number has only 1 bit set.  Subtracting 1 from such a number
+	 * will turn on all previous bits resulting in no common bits being set
+	 * between num and num-1.
+	 */
+	if ((num & (num - 1)) == 0)
+		return num;				/* already power 2 */
+
+	return ((uint64) 1) << (pg_leftmost_one_pos64(num) + 1);
+}
+
+/*
+ * pg_prevpower2_32
+ *		Returns the next lower power of 2 below 'num', or 'num' if it's
+ *		already a power of 2.
+ *
+ * 'num' mustn't be 0.
+ */
+static inline uint32
+pg_prevpower2_32(uint32 num)
+{
+	return ((uint32) 1) << pg_leftmost_one_pos32(num);
+}
+
+/*
+ * pg_prevpower2_64
+ *		Returns the next lower power of 2 below 'num', or 'num' if it's
+ *		already a power of 2.
+ *
+ * 'num' mustn't be 0.
+ */
+static inline uint64
+pg_prevpower2_64(uint64 num)
+{
+	return ((uint64) 1) << pg_leftmost_one_pos64(num);
+}
+
+/*
+ * pg_ceil_log2_32
+ *		Returns equivalent of ceil(log2(num))
+ */
+static inline uint32
+pg_ceil_log2_32(uint32 num)
+{
+	if (num < 2)
+		return 0;
+	else
+		return pg_leftmost_one_pos32(num - 1) + 1;
+}
+
+/*
+ * pg_ceil_log2_64
+ *		Returns equivalent of ceil(log2(num))
+ */
+static inline uint64
+pg_ceil_log2_64(uint64 num)
+{
+	if (num < 2)
+		return 0;
+	else
+		return pg_leftmost_one_pos64(num - 1) + 1;
+}
+
+/*
+ * With MSVC on x86_64 builds, try using native popcnt instructions via the
+ * __popcnt and __popcnt64 intrinsics.  These don't work the same as GCC's
+ * __builtin_popcount* intrinsic functions as they always emit popcnt
+ * instructions.
+ */
+#if defined(_MSC_VER) && defined(_M_AMD64)
+#define HAVE_X86_64_POPCNTQ
+#endif
+
+/*
+ * On x86_64, we can use the hardware popcount instruction, but only if
+ * we can verify that the CPU supports it via the cpuid instruction.
+ *
+ * Otherwise, we fall back to a hand-rolled implementation.
+ */
+#ifdef HAVE_X86_64_POPCNTQ
+#if defined(HAVE__GET_CPUID) || defined(HAVE__CPUID)
+#define TRY_POPCNT_FAST 1
+#endif
+#endif
+
+#ifdef TRY_POPCNT_FAST
+/* Attempt to use the POPCNT instruction, but perform a runtime check first */
+extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
+extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
+extern PGDLLIMPORT uint64 (*pg_popcount_optimized) (const char *buf, int bytes);
+extern PGDLLIMPORT uint64 (*pg_popcount_masked_optimized) (const char *buf, int bytes, bits8 mask);
+
+/*
+ * We can also try to use the AVX-512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+extern uint64 pg_popcount_masked_avx512(const char *buf, int bytes, bits8 mask);
+#endif
+
+#else
+/* Use a portable implementation -- no need for a function pointer. */
+extern int	pg_popcount32(uint32 word);
+extern int	pg_popcount64(uint64 word);
+extern uint64 pg_popcount_optimized(const char *buf, int bytes);
+extern uint64 pg_popcount_masked_optimized(const char *buf, int bytes, bits8 mask);
+
+#endif							/* TRY_POPCNT_FAST */
+
+/*
+ * Returns the number of 1-bits in buf.
+ *
+ * If there aren't many bytes to process, the function call overhead of the
+ * optimized versions isn't worth taking, so we inline a loop that consults
+ * pg_number_of_ones in that case.  If there are many bytes to process, we
+ * accept the function call overhead because the optimized versions are likely
+ * to be faster.
+ */
+static inline uint64
+pg_popcount(const char *buf, int bytes)
+{
+	/*
+	 * We set the threshold to the point at which we'll first use special
+	 * instructions in the optimized version.
+	 */
+#if SIZEOF_VOID_P >= 8
+	int			threshold = 8;
+#else
+	int			threshold = 4;
+#endif
+
+	if (bytes < threshold)
+	{
+		uint64		popcnt = 0;
+
+		while (bytes--)
+			popcnt += pg_number_of_ones[(unsigned char) *buf++];
+		return popcnt;
+	}
+
+	return pg_popcount_optimized(buf, bytes);
+}
+
+/*
+ * Returns the number of 1-bits in buf after applying the mask to each byte.
+ *
+ * Similar to pg_popcount(), we only take on the function pointer overhead when
+ * it's likely to be faster.
+ */
+static inline uint64
+pg_popcount_masked(const char *buf, int bytes, bits8 mask)
+{
+	/*
+	 * We set the threshold to the point at which we'll first use special
+	 * instructions in the optimized version.
+	 */
+#if SIZEOF_VOID_P >= 8
+	int			threshold = 8;
+#else
+	int			threshold = 4;
+#endif
+
+	if (bytes < threshold)
+	{
+		uint64		popcnt = 0;
+
+		while (bytes--)
+			popcnt += pg_number_of_ones[(unsigned char) *buf++ & mask];
+		return popcnt;
+	}
+
+	return pg_popcount_masked_optimized(buf, bytes, mask);
+}
+
+/*
+ * Rotate the bits of "word" to the right/left by n bits.
+ */
+static inline uint32
+pg_rotate_right32(uint32 word, int n)
+{
+	return (word >> n) | (word << (32 - n));
+}
+
+static inline uint32
+pg_rotate_left32(uint32 word, int n)
+{
+	return (word << n) | (word >> (32 - n));
+}
+
+/* size_t variants of the above, as required */
+
+#if SIZEOF_SIZE_T == 4
+#define pg_leftmost_one_pos_size_t pg_leftmost_one_pos32
+#define pg_nextpower2_size_t pg_nextpower2_32
+#define pg_prevpower2_size_t pg_prevpower2_32
+#else
+#define pg_leftmost_one_pos_size_t pg_leftmost_one_pos64
+#define pg_nextpower2_size_t pg_nextpower2_64
+#define pg_prevpower2_size_t pg_prevpower2_64
+#endif
+
+#endif							/* PG_BITUTILS_H */

data/ext/pg_query/include/postgres/port/pg_bswap.h

@@ -0,0 +1,161 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_bswap.h
+ *	  Byte swapping.
+ *
+ * Macros for reversing the byte order of 16, 32 and 64-bit unsigned integers.
+ * For example, 0xAABBCCDD becomes 0xDDCCBBAA.  These are just wrappers for
+ * built-in functions provided by the compiler where support exists.
+ *
+ * Note that all of these functions accept unsigned integers as arguments and
+ * return the same.  Use caution when using these wrapper macros with signed
+ * integers.
+ *
+ * Copyright (c) 2015-2024, PostgreSQL Global Development Group
+ *
+ * src/include/port/pg_bswap.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_BSWAP_H
+#define PG_BSWAP_H
+
+
+/*
+ * In all supported versions msvc provides _byteswap_* functions in stdlib.h,
+ * already included by c.h.
+ */
+
+
+/* implementation of uint16 pg_bswap16(uint16) */
+#if defined(HAVE__BUILTIN_BSWAP16)
+
+#define pg_bswap16(x) __builtin_bswap16(x)
+
+#elif defined(_MSC_VER)
+
+#define pg_bswap16(x) _byteswap_ushort(x)
+
+#else
+
+static inline uint16
+pg_bswap16(uint16 x)
+{
+	return
+		((x << 8) & 0xff00) |
+		((x >> 8) & 0x00ff);
+}
+
+#endif							/* HAVE__BUILTIN_BSWAP16 */
+
+
+/* implementation of uint32 pg_bswap32(uint32) */
+#if defined(HAVE__BUILTIN_BSWAP32)
+
+#define pg_bswap32(x) __builtin_bswap32(x)
+
+#elif defined(_MSC_VER)
+
+#define pg_bswap32(x) _byteswap_ulong(x)
+
+#else
+
+static inline uint32
+pg_bswap32(uint32 x)
+{
+	return
+		((x << 24) & 0xff000000) |
+		((x << 8) & 0x00ff0000) |
+		((x >> 8) & 0x0000ff00) |
+		((x >> 24) & 0x000000ff);
+}
+
+#endif							/* HAVE__BUILTIN_BSWAP32 */
+
+
+/* implementation of uint64 pg_bswap64(uint64) */
+#if defined(HAVE__BUILTIN_BSWAP64)
+
+#define pg_bswap64(x) __builtin_bswap64(x)
+
+
+#elif defined(_MSC_VER)
+
+#define pg_bswap64(x) _byteswap_uint64(x)
+
+#else
+
+static inline uint64
+pg_bswap64(uint64 x)
+{
+	return
+		((x << 56) & UINT64CONST(0xff00000000000000)) |
+		((x << 40) & UINT64CONST(0x00ff000000000000)) |
+		((x << 24) & UINT64CONST(0x0000ff0000000000)) |
+		((x << 8) & UINT64CONST(0x000000ff00000000)) |
+		((x >> 8) & UINT64CONST(0x00000000ff000000)) |
+		((x >> 24) & UINT64CONST(0x0000000000ff0000)) |
+		((x >> 40) & UINT64CONST(0x000000000000ff00)) |
+		((x >> 56) & UINT64CONST(0x00000000000000ff));
+}
+#endif							/* HAVE__BUILTIN_BSWAP64 */
+
+
+/*
+ * Portable and fast equivalents for ntohs, ntohl, htons, htonl,
+ * additionally extended to 64 bits.
+ */
+#ifdef WORDS_BIGENDIAN
+
+#define pg_hton16(x)		(x)
+#define pg_hton32(x)		(x)
+#define pg_hton64(x)		(x)
+
+#define pg_ntoh16(x)		(x)
+#define pg_ntoh32(x)		(x)
+#define pg_ntoh64(x)		(x)
+
+#else
+
+#define pg_hton16(x)		pg_bswap16(x)
+#define pg_hton32(x)		pg_bswap32(x)
+#define pg_hton64(x)		pg_bswap64(x)
+
+#define pg_ntoh16(x)		pg_bswap16(x)
+#define pg_ntoh32(x)		pg_bswap32(x)
+#define pg_ntoh64(x)		pg_bswap64(x)
+
+#endif							/* WORDS_BIGENDIAN */
+
+
+/*
+ * Rearrange the bytes of a Datum from big-endian order into the native byte
+ * order.  On big-endian machines, this does nothing at all.  Note that the C
+ * type Datum is an unsigned integer type on all platforms.
+ *
+ * One possible application of the DatumBigEndianToNative() macro is to make
+ * bitwise comparisons cheaper.  A simple 3-way comparison of Datums
+ * transformed by the macro (based on native, unsigned comparisons) will return
+ * the same result as a memcmp() of the corresponding original Datums, but can
+ * be much cheaper.  It's generally safe to do this on big-endian systems
+ * without any special transformation occurring first.
+ *
+ * If SIZEOF_DATUM is not defined, then postgres.h wasn't included and these
+ * macros probably shouldn't be used, so we define nothing.  Note that
+ * SIZEOF_DATUM == 8 would evaluate as 0 == 8 in that case, potentially
+ * leading to the wrong implementation being selected and confusing errors, so
+ * defining nothing is safest.
+ */
+#ifdef SIZEOF_DATUM
+#ifdef WORDS_BIGENDIAN
+#define		DatumBigEndianToNative(x)	(x)
+#else							/* !WORDS_BIGENDIAN */
+#if SIZEOF_DATUM == 8
+#define		DatumBigEndianToNative(x)	pg_bswap64(x)
+#else							/* SIZEOF_DATUM != 8 */
+#define		DatumBigEndianToNative(x)	pg_bswap32(x)
+#endif							/* SIZEOF_DATUM == 8 */
+#endif							/* WORDS_BIGENDIAN */
+#endif							/* SIZEOF_DATUM */
+
+#endif							/* PG_BSWAP_H */

data/ext/pg_query/include/postgres/port/pg_crc32c.h

@@ -0,0 +1,110 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_crc32c.h
+ *	  Routines for computing CRC-32C checksums.
+ *
+ * The speed of CRC-32C calculation has a big impact on performance, so we
+ * jump through some hoops to get the best implementation for each
+ * platform. Some CPU architectures have special instructions for speeding
+ * up CRC calculations (e.g. Intel SSE 4.2), on other platforms we use the
+ * Slicing-by-8 algorithm which uses lookup tables.
+ *
+ * The public interface consists of four macros:
+ *
+ * INIT_CRC32C(crc)
+ *		Initialize a CRC accumulator
+ *
+ * COMP_CRC32C(crc, data, len)
+ *		Accumulate some (more) bytes into a CRC
+ *
+ * FIN_CRC32C(crc)
+ *		Finish a CRC calculation
+ *
+ * EQ_CRC32C(c1, c2)
+ *		Check for equality of two CRCs.
+ *
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/port/pg_crc32c.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_CRC32C_H
+#define PG_CRC32C_H
+
+#include "port/pg_bswap.h"
+
+typedef uint32 pg_crc32c;
+
+/* The INIT and EQ macros are the same for all implementations. */
+#define INIT_CRC32C(crc) ((crc) = 0xFFFFFFFF)
+#define EQ_CRC32C(c1, c2) ((c1) == (c2))
+
+#if defined(USE_SSE42_CRC32C)
+/* Use Intel SSE4.2 instructions. */
+#define COMP_CRC32C(crc, data, len) \
+	((crc) = pg_comp_crc32c_sse42((crc), (data), (len)))
+#define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
+
+extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+
+#elif defined(USE_ARMV8_CRC32C)
+/* Use ARMv8 CRC Extension instructions. */
+
+#define COMP_CRC32C(crc, data, len)							\
+	((crc) = pg_comp_crc32c_armv8((crc), (data), (len)))
+#define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
+
+extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+
+#elif defined(USE_LOONGARCH_CRC32C)
+/* Use LoongArch CRCC instructions. */
+
+#define COMP_CRC32C(crc, data, len)							\
+	((crc) = pg_comp_crc32c_loongarch((crc), (data), (len)))
+#define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
+
+extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
+
+#elif defined(USE_SSE42_CRC32C_WITH_RUNTIME_CHECK) || defined(USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK)
+
+/*
+ * Use Intel SSE 4.2 or ARMv8 instructions, but perform a runtime check first
+ * to check that they are available.
+ */
+#define COMP_CRC32C(crc, data, len) \
+	((crc) = pg_comp_crc32c((crc), (data), (len)))
+#define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
+
+extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
+
+#ifdef USE_SSE42_CRC32C_WITH_RUNTIME_CHECK
+extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+#endif
+#ifdef USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK
+extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+#endif
+
+#else
+/*
+ * Use slicing-by-8 algorithm.
+ *
+ * On big-endian systems, the intermediate value is kept in reverse byte
+ * order, to avoid byte-swapping during the calculation. FIN_CRC32C reverses
+ * the bytes to the final order.
+ */
+#define COMP_CRC32C(crc, data, len) \
+	((crc) = pg_comp_crc32c_sb8((crc), (data), (len)))
+#ifdef WORDS_BIGENDIAN
+#define FIN_CRC32C(crc) ((crc) = pg_bswap32(crc) ^ 0xFFFFFFFF)
+#else
+#define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
+#endif
+
+extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+
+#endif
+
+#endif							/* PG_CRC32C_H */