pg_query 2.2.0 → 6.1.0

data/ext/pg_query/src_port_pg_bitutils.c

@@ -2,6 +2,11 @@
  * Symbols referenced in this file:
  * - pg_popcount64
  * - pg_popcount64_slow
+ * - pg_popcount32
+ * - pg_popcount32_slow
+ * - pg_leftmost_one_pos
+ * - pg_rightmost_one_pos
+ * - pg_number_of_ones
  *--------------------------------------------------------------------
  */
 
@@ -10,7 +15,7 @@
  * pg_bitutils.c
  *	  Miscellaneous functions for bit-wise operations.
  *
- * Copyright (c) 2019-2020, PostgreSQL Global Development Group
+ * Copyright (c) 2019-2024, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
  *	  src/port/pg_bitutils.c
@@ -38,7 +43,24 @@
  * HAVE__BUILTIN_CLZ is defined, but we provide it anyway, so that
  * extensions possibly compiled with a different compiler can use it.
  */
-
+const uint8 pg_leftmost_one_pos[256] = {
+	0, 0, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3,
+	4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+	5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
+	5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
+	6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
+	6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
+	6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
+	6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
+};
 
 /*
  * Array giving the position of the right-most set bit for each possible
@@ -49,7 +71,24 @@
  * HAVE__BUILTIN_CTZ is defined, but we provide it anyway, so that
  * extensions possibly compiled with a different compiler can use it.
  */
-
+const uint8 pg_rightmost_one_pos[256] = {
+	0, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	6, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	7, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	6, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+	4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0
+};
 
 /*
  * Array giving the number of 1-bits in each possible byte value.
@@ -57,39 +96,48 @@
  * Note: we export this for use by functions in which explicit use
  * of the popcount functions seems unlikely to be a win.
  */
-
-
-/*
- * 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 __builtin_popcount if the compiler has that,
- * or a hand-rolled implementation if not.
- */
-#ifdef HAVE_X86_64_POPCNTQ
-#if defined(HAVE__GET_CPUID) || defined(HAVE__CPUID)
-#define USE_POPCNT_ASM 1
-#endif
-#endif
-
-static int	pg_popcount32_slow(uint32 word);
-static int	pg_popcount64_slow(uint64 word);
-
-#ifdef USE_POPCNT_ASM
+const uint8 pg_number_of_ones[256] = {
+	0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4,
+	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
+	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
+	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
+	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
+	4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8
+};
+
+static inline int pg_popcount32_slow(uint32 word);
+static inline int pg_popcount64_slow(uint64 word);
+static uint64 pg_popcount_slow(const char *buf, int bytes);
+static uint64 pg_popcount_masked_slow(const char *buf, int bytes, bits8 mask);
+
+#ifdef TRY_POPCNT_FAST
 static bool pg_popcount_available(void);
 static int	pg_popcount32_choose(uint32 word);
 static int	pg_popcount64_choose(uint64 word);
-static int	pg_popcount32_asm(uint32 word);
-static int	pg_popcount64_asm(uint64 word);
+static uint64 pg_popcount_choose(const char *buf, int bytes);
+static uint64 pg_popcount_masked_choose(const char *buf, int bytes, bits8 mask);
+static inline int pg_popcount32_fast(uint32 word);
+static inline int pg_popcount64_fast(uint64 word);
+static uint64 pg_popcount_fast(const char *buf, int bytes);
+static uint64 pg_popcount_masked_fast(const char *buf, int bytes, bits8 mask);
 
 int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
 int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
-#else
+uint64		(*pg_popcount_optimized) (const char *buf, int bytes) = pg_popcount_choose;
+uint64		(*pg_popcount_masked_optimized) (const char *buf, int bytes, bits8 mask) = pg_popcount_masked_choose;
+#endif							/* TRY_POPCNT_FAST */
 
-int			(*pg_popcount64) (uint64 word) = pg_popcount64_slow;
-#endif							/* USE_POPCNT_ASM */
-
-#ifdef USE_POPCNT_ASM
+#ifdef TRY_POPCNT_FAST
 
 /*
  * Return true if CPUID indicates that the POPCNT instruction is available.
@@ -116,82 +164,221 @@ pg_popcount_available(void)
  * the function pointers so that subsequent calls are routed directly to
  * the chosen implementation.
  */
-static int
-pg_popcount32_choose(uint32 word)
+static inline void
+choose_popcount_functions(void)
 {
 	if (pg_popcount_available())
 	{
-		pg_popcount32 = pg_popcount32_asm;
-		pg_popcount64 = pg_popcount64_asm;
+		pg_popcount32 = pg_popcount32_fast;
+		pg_popcount64 = pg_popcount64_fast;
+		pg_popcount_optimized = pg_popcount_fast;
+		pg_popcount_masked_optimized = pg_popcount_masked_fast;
 	}
 	else
 	{
 		pg_popcount32 = pg_popcount32_slow;
 		pg_popcount64 = pg_popcount64_slow;
+		pg_popcount_optimized = pg_popcount_slow;
+		pg_popcount_masked_optimized = pg_popcount_masked_slow;
 	}
 
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+	if (pg_popcount_avx512_available())
+	{
+		pg_popcount_optimized = pg_popcount_avx512;
+		pg_popcount_masked_optimized = pg_popcount_masked_avx512;
+	}
+#endif
+}
+
+static int
+pg_popcount32_choose(uint32 word)
+{
+	choose_popcount_functions();
 	return pg_popcount32(word);
 }
 
 static int
 pg_popcount64_choose(uint64 word)
 {
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_asm;
-		pg_popcount64 = pg_popcount64_asm;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-	}
-
+	choose_popcount_functions();
 	return pg_popcount64(word);
 }
 
+static uint64
+pg_popcount_choose(const char *buf, int bytes)
+{
+	choose_popcount_functions();
+	return pg_popcount_optimized(buf, bytes);
+}
+
+static uint64
+pg_popcount_masked_choose(const char *buf, int bytes, bits8 mask)
+{
+	choose_popcount_functions();
+	return pg_popcount_masked(buf, bytes, mask);
+}
+
 /*
- * pg_popcount32_asm
+ * pg_popcount32_fast
  *		Return the number of 1 bits set in word
  */
-static int
-pg_popcount32_asm(uint32 word)
+static inline int
+pg_popcount32_fast(uint32 word)
 {
+#ifdef _MSC_VER
+	return __popcnt(word);
+#else
 	uint32		res;
 
 __asm__ __volatile__(" popcntl %1,%0\n":"=q"(res):"rm"(word):"cc");
 	return (int) res;
+#endif
 }
 
 /*
- * pg_popcount64_asm
+ * pg_popcount64_fast
  *		Return the number of 1 bits set in word
  */
-static int
-pg_popcount64_asm(uint64 word)
+static inline int
+pg_popcount64_fast(uint64 word)
 {
+#ifdef _MSC_VER
+	return __popcnt64(word);
+#else
 	uint64		res;
 
 __asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
 	return (int) res;
+#endif
 }
 
-#endif							/* USE_POPCNT_ASM */
+/*
+ * pg_popcount_fast
+ *		Returns the number of 1-bits in buf
+ */
+static uint64
+pg_popcount_fast(const char *buf, int bytes)
+{
+	uint64		popcnt = 0;
+
+#if SIZEOF_VOID_P >= 8
+	/* Process in 64-bit chunks if the buffer is aligned. */
+	if (buf == (const char *) TYPEALIGN(8, buf))
+	{
+		const uint64 *words = (const uint64 *) buf;
+
+		while (bytes >= 8)
+		{
+			popcnt += pg_popcount64_fast(*words++);
+			bytes -= 8;
+		}
+
+		buf = (const char *) words;
+	}
+#else
+	/* Process in 32-bit chunks if the buffer is aligned. */
+	if (buf == (const char *) TYPEALIGN(4, buf))
+	{
+		const uint32 *words = (const uint32 *) buf;
+
+		while (bytes >= 4)
+		{
+			popcnt += pg_popcount32_fast(*words++);
+			bytes -= 4;
+		}
+
+		buf = (const char *) words;
+	}
+#endif
+
+	/* Process any remaining bytes */
+	while (bytes--)
+		popcnt += pg_number_of_ones[(unsigned char) *buf++];
+
+	return popcnt;
+}
+
+/*
+ * pg_popcount_masked_fast
+ *		Returns the number of 1-bits in buf after applying the mask to each byte
+ */
+static uint64
+pg_popcount_masked_fast(const char *buf, int bytes, bits8 mask)
+{
+	uint64		popcnt = 0;
+
+#if SIZEOF_VOID_P >= 8
+	/* Process in 64-bit chunks if the buffer is aligned */
+	uint64		maskv = ~UINT64CONST(0) / 0xFF * mask;
+
+	if (buf == (const char *) TYPEALIGN(8, buf))
+	{
+		const uint64 *words = (const uint64 *) buf;
+
+		while (bytes >= 8)
+		{
+			popcnt += pg_popcount64_fast(*words++ & maskv);
+			bytes -= 8;
+		}
+
+		buf = (const char *) words;
+	}
+#else
+	/* Process in 32-bit chunks if the buffer is aligned. */
+	uint32		maskv = ~((uint32) 0) / 0xFF * mask;
+
+	if (buf == (const char *) TYPEALIGN(4, buf))
+	{
+		const uint32 *words = (const uint32 *) buf;
+
+		while (bytes >= 4)
+		{
+			popcnt += pg_popcount32_fast(*words++ & maskv);
+			bytes -= 4;
+		}
+
+		buf = (const char *) words;
+	}
+#endif
+
+	/* Process any remaining bytes */
+	while (bytes--)
+		popcnt += pg_number_of_ones[(unsigned char) *buf++ & mask];
+
+	return popcnt;
+}
+
+#endif							/* TRY_POPCNT_FAST */
 
 
 /*
  * pg_popcount32_slow
  *		Return the number of 1 bits set in word
  */
+static inline int
+pg_popcount32_slow(uint32 word)
+{
 #ifdef HAVE__BUILTIN_POPCOUNT
+	return __builtin_popcount(word);
 #else							/* !HAVE__BUILTIN_POPCOUNT */
+	int			result = 0;
+
+	while (word != 0)
+	{
+		result += pg_number_of_ones[word & 255];
+		word >>= 8;
+	}
+
+	return result;
 #endif							/* HAVE__BUILTIN_POPCOUNT */
+}
 
 /*
  * pg_popcount64_slow
  *		Return the number of 1 bits set in word
  */
-static int
+static inline int
 pg_popcount64_slow(uint64 word)
 {
 #ifdef HAVE__BUILTIN_POPCOUNT
@@ -215,11 +402,53 @@ pg_popcount64_slow(uint64 word)
 #endif							/* HAVE__BUILTIN_POPCOUNT */
 }
 
-
 /*
- * pg_popcount
+ * pg_popcount_slow
  *		Returns the number of 1-bits in buf
  */
 #if SIZEOF_VOID_P >= 8
 #else
 #endif
+
+/*
+ * pg_popcount_masked_slow
+ *		Returns the number of 1-bits in buf after applying the mask to each byte
+ */
+#if SIZEOF_VOID_P >= 8
+#else
+#endif
+
+#ifndef TRY_POPCNT_FAST
+
+/*
+ * When the POPCNT instruction is not available, there's no point in using
+ * function pointers to vary the implementation between the fast and slow
+ * method.  We instead just make these actual external functions when
+ * TRY_POPCNT_FAST is not defined.  The compiler should be able to inline
+ * the slow versions here.
+ */
+int
+pg_popcount32(uint32 word)
+{
+	return pg_popcount32_slow(word);
+}
+
+int
+pg_popcount64(uint64 word)
+{
+	return pg_popcount64_slow(word);
+}
+
+/*
+ * pg_popcount_optimized
+ *		Returns the number of 1-bits in buf
+ */
+
+
+/*
+ * pg_popcount_masked_optimized
+ *		Returns the number of 1-bits in buf after applying the mask to each byte
+ */
+
+
+#endif							/* !TRY_POPCNT_FAST */

data/ext/pg_query/src_port_pgstrcasecmp.c

@@ -1,6 +1,8 @@
 /*--------------------------------------------------------------------
  * Symbols referenced in this file:
+ * - pg_strcasecmp
  * - pg_toupper
+ * - pg_strncasecmp
  *--------------------------------------------------------------------
  */
 
@@ -24,7 +26,7 @@
  * C library thinks the locale is.
  *
  *
- * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
  *
  * src/port/pgstrcasecmp.c
  *
@@ -38,13 +40,67 @@
 /*
  * Case-independent comparison of two null-terminated strings.
  */
+int
+pg_strcasecmp(const char *s1, const char *s2)
+{
+	for (;;)
+	{
+		unsigned char ch1 = (unsigned char) *s1++;
+		unsigned char ch2 = (unsigned char) *s2++;
+
+		if (ch1 != ch2)
+		{
+			if (ch1 >= 'A' && ch1 <= 'Z')
+				ch1 += 'a' - 'A';
+			else if (IS_HIGHBIT_SET(ch1) && isupper(ch1))
+				ch1 = tolower(ch1);
 
+			if (ch2 >= 'A' && ch2 <= 'Z')
+				ch2 += 'a' - 'A';
+			else if (IS_HIGHBIT_SET(ch2) && isupper(ch2))
+				ch2 = tolower(ch2);
+
+			if (ch1 != ch2)
+				return (int) ch1 - (int) ch2;
+		}
+		if (ch1 == 0)
+			break;
+	}
+	return 0;
+}
 
 /*
  * Case-independent comparison of two not-necessarily-null-terminated strings.
  * At most n bytes will be examined from each string.
  */
+int
+pg_strncasecmp(const char *s1, const char *s2, size_t n)
+{
+	while (n-- > 0)
+	{
+		unsigned char ch1 = (unsigned char) *s1++;
+		unsigned char ch2 = (unsigned char) *s2++;
+
+		if (ch1 != ch2)
+		{
+			if (ch1 >= 'A' && ch1 <= 'Z')
+				ch1 += 'a' - 'A';
+			else if (IS_HIGHBIT_SET(ch1) && isupper(ch1))
+				ch1 = tolower(ch1);
 
+			if (ch2 >= 'A' && ch2 <= 'Z')
+				ch2 += 'a' - 'A';
+			else if (IS_HIGHBIT_SET(ch2) && isupper(ch2))
+				ch2 = tolower(ch2);
+
+			if (ch1 != ch2)
+				return (int) ch1 - (int) ch2;
+		}
+		if (ch1 == 0)
+			break;
+	}
+	return 0;
+}
 
 /*
  * Fold a character to upper case.