pg_query 4.2.1 → 6.1.0

data/ext/pg_query/src_common_kwlookup.c

@@ -10,7 +10,7 @@
  *	  Key word lookup for PostgreSQL
  *
  *
- * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  *

data/ext/pg_query/src_common_psprintf.c

@@ -11,7 +11,7 @@
  *		sprintf into an allocated-on-demand buffer
  *
  *
- * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  *
@@ -122,8 +122,8 @@ pvsnprintf(char *buf, size_t len, const char *fmt, va_list args)
 #ifndef FRONTEND
 		elog(ERROR, "vsnprintf failed: %m with format string \"%s\"", fmt);
 #else
-		fprintf(stderr, "vsnprintf failed: %s with format string \"%s\"\n",
-				strerror(errno), fmt);
+		fprintf(stderr, "vsnprintf failed: %m with format string \"%s\"\n",
+				fmt);
 		exit(EXIT_FAILURE);
 #endif
 	}

data/ext/pg_query/src_common_stringinfo.c

@@ -21,7 +21,7 @@
  * (null-terminated text) or arbitrary binary data.  All storage is allocated
  * with palloc() (falling back to malloc in frontend code).
  *
- * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  *	  src/common/stringinfo.c
@@ -74,10 +74,16 @@ initStringInfo(StringInfo str)
  *
  * Reset the StringInfo: the data buffer remains valid, but its
  * previous content, if any, is cleared.
+ *
+ * Read-only StringInfos as initialized by initReadOnlyStringInfo cannot be
+ * reset.
  */
 void
 resetStringInfo(StringInfo str)
 {
+	/* don't allow resets of read-only StringInfos */
+	Assert(str->maxlen != 0);
+
 	str->data[0] = '\0';
 	str->len = 0;
 	str->cursor = 0;
@@ -215,8 +221,8 @@ appendStringInfoSpaces(StringInfo str, int count)
 		enlargeStringInfo(str, count);
 
 		/* OK, append the spaces */
-		while (--count >= 0)
-			str->data[str->len++] = ' ';
+		memset(&str->data[str->len], ' ', count);
+		str->len += count;
 		str->data[str->len] = '\0';
 	}
 }
@@ -228,7 +234,7 @@ appendStringInfoSpaces(StringInfo str, int count)
  * if necessary. Ensures that a trailing null byte is present.
  */
 void
-appendBinaryStringInfo(StringInfo str, const char *data, int datalen)
+appendBinaryStringInfo(StringInfo str, const void *data, int datalen)
 {
 	Assert(str != NULL);
 
@@ -277,6 +283,9 @@ enlargeStringInfo(StringInfo str, int needed)
 {
 	int			newlen;
 
+	/* validate this is not a read-only StringInfo */
+	Assert(str->maxlen != 0);
+
 	/*
 	 * Guard against out-of-range "needed" values.  Without this, we can get
 	 * an overflow or infinite loop in the following.
@@ -334,3 +343,11 @@ enlargeStringInfo(StringInfo str, int needed)
 
 	str->maxlen = newlen;
 }
+
+/*
+ * destroyStringInfo
+ *
+ * Frees a StringInfo and its buffer (opposite of makeStringInfo()).
+ * This must only be called on palloc'd StringInfos.
+ */
+

data/ext/pg_query/src_common_wchar.c

@@ -2,7 +2,7 @@
  * Symbols referenced in this file:
  * - pg_encoding_max_length
  * - pg_wchar_table
- * - pg_utf_mblen
+ * - pg_utf_mblen_private
  * - pg_mule_mblen
  * - pg_ascii2wchar_with_len
  * - pg_wchar2single_with_len
@@ -34,9 +34,7 @@
  * - pg_euctw_verifystr
  * - pg_utf2wchar_with_len
  * - pg_wchar2utf_with_len
- * - unicode_to_utf8
  * - pg_utf_dsplen
- * - utf8_to_unicode
  * - ucs_wcwidth
  * - mbbisearch
  * - pg_utf8_verifychar
@@ -87,7 +85,7 @@
  * wchar.c
  *	  Functions for working with multibyte characters in various encodings.
  *
- * Portions Copyright (c) 1998-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1998-2024, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
  *	  src/common/wchar.c
@@ -97,6 +95,26 @@
 #include "c.h"
 
 #include "mb/pg_wchar.h"
+#include "utils/ascii.h"
+
+
+/*
+ * In today's multibyte encodings other than UTF8, this two-byte sequence
+ * ensures pg_encoding_mblen() == 2 && pg_encoding_verifymbstr() == 0.
+ *
+ * For historical reasons, several verifychar implementations opt to reject
+ * this pair specifically.  Byte pair range constraints, in encoding
+ * originator documentation, always excluded this pair.  No core conversion
+ * could translate it.  However, longstanding verifychar implementations
+ * accepted any non-NUL byte.  big5_to_euc_tw and big5_to_mic even translate
+ * pairs not valid per encoding originator documentation.  To avoid tightening
+ * core or non-core conversions in a security patch, we sought this one pair.
+ *
+ * PQescapeString() historically used spaces for BYTE1; many other values
+ * could suffice for BYTE1.
+ */
+#define NONUTF8_INVALID_BYTE0 (0x8d)
+#define NONUTF8_INVALID_BYTE1 (' ')
 
 
 /*
@@ -559,39 +577,6 @@ pg_utf2wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
 }
 
 
-/*
- * Map a Unicode code point to UTF-8.  utf8string must have 4 bytes of
- * space allocated.
- */
-unsigned char *
-unicode_to_utf8(pg_wchar c, unsigned char *utf8string)
-{
-	if (c <= 0x7F)
-	{
-		utf8string[0] = c;
-	}
-	else if (c <= 0x7FF)
-	{
-		utf8string[0] = 0xC0 | ((c >> 6) & 0x1F);
-		utf8string[1] = 0x80 | (c & 0x3F);
-	}
-	else if (c <= 0xFFFF)
-	{
-		utf8string[0] = 0xE0 | ((c >> 12) & 0x0F);
-		utf8string[1] = 0x80 | ((c >> 6) & 0x3F);
-		utf8string[2] = 0x80 | (c & 0x3F);
-	}
-	else
-	{
-		utf8string[0] = 0xF0 | ((c >> 18) & 0x07);
-		utf8string[1] = 0x80 | ((c >> 12) & 0x3F);
-		utf8string[2] = 0x80 | ((c >> 6) & 0x3F);
-		utf8string[3] = 0x80 | (c & 0x3F);
-	}
-
-	return utf8string;
-}
-
 /*
  * Trivial conversion from pg_wchar to UTF-8.
  * caller should allocate enough space for "to"
@@ -704,7 +689,7 @@ mbbisearch(pg_wchar ucs, const struct mbinterval *table, int max)
  *		value of -1.
  *
  *	  - Non-spacing and enclosing combining characters (general
- *		category code Mn or Me in the Unicode database) have a
+ *		category code Mn, Me or Cf in the Unicode database) have a
  *		column width of 0.
  *
  *	  - Spacing characters in the East Asian Wide (W) or East Asian
@@ -722,7 +707,7 @@ mbbisearch(pg_wchar ucs, const struct mbinterval *table, int max)
 static int
 ucs_wcwidth(pg_wchar ucs)
 {
-#include "common/unicode_combining_table.h"
+#include "common/unicode_nonspacing_table.h"
 #include "common/unicode_east_asian_fw_table.h"
 
 	/* test for 8-bit control characters */
@@ -741,8 +726,8 @@ ucs_wcwidth(pg_wchar ucs)
 	 * factor for display width leads to the correct behavior, so do that
 	 * search first.
 	 */
-	if (mbbisearch(ucs, combining,
-				   sizeof(combining) / sizeof(struct mbinterval) - 1))
+	if (mbbisearch(ucs, nonspacing,
+				   sizeof(nonspacing) / sizeof(struct mbinterval) - 1))
 		return 0;
 
 	/* binary search in table of wide characters */
@@ -753,34 +738,6 @@ ucs_wcwidth(pg_wchar ucs)
 	return 1;
 }
 
-/*
- * Convert a UTF-8 character to a Unicode code point.
- * This is a one-character version of pg_utf2wchar_with_len.
- *
- * No error checks here, c must point to a long-enough string.
- */
-pg_wchar
-utf8_to_unicode(const unsigned char *c)
-{
-	if ((*c & 0x80) == 0)
-		return (pg_wchar) c[0];
-	else if ((*c & 0xe0) == 0xc0)
-		return (pg_wchar) (((c[0] & 0x1f) << 6) |
-						   (c[1] & 0x3f));
-	else if ((*c & 0xf0) == 0xe0)
-		return (pg_wchar) (((c[0] & 0x0f) << 12) |
-						   ((c[1] & 0x3f) << 6) |
-						   (c[2] & 0x3f));
-	else if ((*c & 0xf8) == 0xf0)
-		return (pg_wchar) (((c[0] & 0x07) << 18) |
-						   ((c[1] & 0x3f) << 12) |
-						   ((c[2] & 0x3f) << 6) |
-						   (c[3] & 0x3f));
-	else
-		/* that is an invalid code on purpose */
-		return 0xffffffff;
-}
-
 static int
 pg_utf_dsplen(const unsigned char *s)
 {
@@ -1609,6 +1566,11 @@ pg_big5_verifychar(const unsigned char *s, int len)
 	if (len < l)
 		return -1;
 
+	if (l == 2 &&
+		s[0] == NONUTF8_INVALID_BYTE0 &&
+		s[1] == NONUTF8_INVALID_BYTE1)
+		return -1;
+
 	while (--l > 0)
 	{
 		if (*++s == '\0')
@@ -1658,6 +1620,11 @@ pg_gbk_verifychar(const unsigned char *s, int len)
 	if (len < l)
 		return -1;
 
+	if (l == 2 &&
+		s[0] == NONUTF8_INVALID_BYTE0 &&
+		s[1] == NONUTF8_INVALID_BYTE1)
+		return -1;
+
 	while (--l > 0)
 	{
 		if (*++s == '\0')
@@ -1707,6 +1674,11 @@ pg_uhc_verifychar(const unsigned char *s, int len)
 	if (len < l)
 		return -1;
 
+	if (l == 2 &&
+		s[0] == NONUTF8_INVALID_BYTE0 &&
+		s[1] == NONUTF8_INVALID_BYTE1)
+		return -1;
+
 	while (--l > 0)
 	{
 		if (*++s == '\0')
@@ -2003,10 +1975,11 @@ pg_utf8_verifystr(const unsigned char *s, int len)
 	uint32		state = BGN;
 
 /*
- * Sixteen seems to give the best balance of performance across different
- * byte distributions.
+ * With a stride of two vector widths, gcc will unroll the loop. Even if
+ * the compiler can unroll a longer loop, it's not worth it because we
+ * must fall back to the byte-wise algorithm if we find any non-ASCII.
  */
-#define STRIDE_LENGTH 16
+#define STRIDE_LENGTH (2 * sizeof(Vector8))
 
 	if (len >= STRIDE_LENGTH)
 	{
@@ -2150,55 +2123,60 @@ pg_utf8_islegal(const unsigned char *source, int length)
 }
 
 
+/*
+ * Fills the provided buffer with two bytes such that:
+ *   pg_encoding_mblen(dst) == 2 && pg_encoding_verifymbstr(dst) == 0
+ */
+
+
 /*
  *-------------------------------------------------------------------
  * encoding info table
- * XXX must be sorted by the same order as enum pg_enc (in mb/pg_wchar.h)
  *-------------------------------------------------------------------
  */
 const pg_wchar_tbl pg_wchar_table[] = {
-	{pg_ascii2wchar_with_len, pg_wchar2single_with_len, pg_ascii_mblen, pg_ascii_dsplen, pg_ascii_verifychar, pg_ascii_verifystr, 1},	/* PG_SQL_ASCII */
-	{pg_eucjp2wchar_with_len, pg_wchar2euc_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifychar, pg_eucjp_verifystr, 3},	/* PG_EUC_JP */
-	{pg_euccn2wchar_with_len, pg_wchar2euc_with_len, pg_euccn_mblen, pg_euccn_dsplen, pg_euccn_verifychar, pg_euccn_verifystr, 2},	/* PG_EUC_CN */
-	{pg_euckr2wchar_with_len, pg_wchar2euc_with_len, pg_euckr_mblen, pg_euckr_dsplen, pg_euckr_verifychar, pg_euckr_verifystr, 3},	/* PG_EUC_KR */
-	{pg_euctw2wchar_with_len, pg_wchar2euc_with_len, pg_euctw_mblen, pg_euctw_dsplen, pg_euctw_verifychar, pg_euctw_verifystr, 4},	/* PG_EUC_TW */
-	{pg_eucjp2wchar_with_len, pg_wchar2euc_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifychar, pg_eucjp_verifystr, 3},	/* PG_EUC_JIS_2004 */
-	{pg_utf2wchar_with_len, pg_wchar2utf_with_len, pg_utf_mblen, pg_utf_dsplen, pg_utf8_verifychar, pg_utf8_verifystr, 4},	/* PG_UTF8 */
-	{pg_mule2wchar_with_len, pg_wchar2mule_with_len, pg_mule_mblen, pg_mule_dsplen, pg_mule_verifychar, pg_mule_verifystr, 4},	/* PG_MULE_INTERNAL */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_LATIN1 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_LATIN2 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_LATIN3 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_LATIN4 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_LATIN5 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_LATIN6 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_LATIN7 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_LATIN8 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_LATIN9 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_LATIN10 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_WIN1256 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_WIN1258 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_WIN866 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_WIN874 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_KOI8R */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_WIN1251 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_WIN1252 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* ISO-8859-5 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* ISO-8859-6 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* ISO-8859-7 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* ISO-8859-8 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_WIN1250 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_WIN1253 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_WIN1254 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_WIN1255 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_WIN1257 */
-	{pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},	/* PG_KOI8U */
-	{0, 0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifychar, pg_sjis_verifystr, 2},	/* PG_SJIS */
-	{0, 0, pg_big5_mblen, pg_big5_dsplen, pg_big5_verifychar, pg_big5_verifystr, 2},	/* PG_BIG5 */
-	{0, 0, pg_gbk_mblen, pg_gbk_dsplen, pg_gbk_verifychar, pg_gbk_verifystr, 2},	/* PG_GBK */
-	{0, 0, pg_uhc_mblen, pg_uhc_dsplen, pg_uhc_verifychar, pg_uhc_verifystr, 2},	/* PG_UHC */
-	{0, 0, pg_gb18030_mblen, pg_gb18030_dsplen, pg_gb18030_verifychar, pg_gb18030_verifystr, 4},	/* PG_GB18030 */
-	{0, 0, pg_johab_mblen, pg_johab_dsplen, pg_johab_verifychar, pg_johab_verifystr, 3},	/* PG_JOHAB */
-	{0, 0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifychar, pg_sjis_verifystr, 2} /* PG_SHIFT_JIS_2004 */
+	[PG_SQL_ASCII] = {pg_ascii2wchar_with_len, pg_wchar2single_with_len, pg_ascii_mblen, pg_ascii_dsplen, pg_ascii_verifychar, pg_ascii_verifystr, 1},
+	[PG_EUC_JP] = {pg_eucjp2wchar_with_len, pg_wchar2euc_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifychar, pg_eucjp_verifystr, 3},
+	[PG_EUC_CN] = {pg_euccn2wchar_with_len, pg_wchar2euc_with_len, pg_euccn_mblen, pg_euccn_dsplen, pg_euccn_verifychar, pg_euccn_verifystr, 2},
+	[PG_EUC_KR] = {pg_euckr2wchar_with_len, pg_wchar2euc_with_len, pg_euckr_mblen, pg_euckr_dsplen, pg_euckr_verifychar, pg_euckr_verifystr, 3},
+	[PG_EUC_TW] = {pg_euctw2wchar_with_len, pg_wchar2euc_with_len, pg_euctw_mblen, pg_euctw_dsplen, pg_euctw_verifychar, pg_euctw_verifystr, 4},
+	[PG_EUC_JIS_2004] = {pg_eucjp2wchar_with_len, pg_wchar2euc_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifychar, pg_eucjp_verifystr, 3},
+	[PG_UTF8] = {pg_utf2wchar_with_len, pg_wchar2utf_with_len, pg_utf_mblen, pg_utf_dsplen, pg_utf8_verifychar, pg_utf8_verifystr, 4},
+	[PG_MULE_INTERNAL] = {pg_mule2wchar_with_len, pg_wchar2mule_with_len, pg_mule_mblen, pg_mule_dsplen, pg_mule_verifychar, pg_mule_verifystr, 4},
+	[PG_LATIN1] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_LATIN2] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_LATIN3] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_LATIN4] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_LATIN5] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_LATIN6] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_LATIN7] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_LATIN8] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_LATIN9] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_LATIN10] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_WIN1256] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_WIN1258] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_WIN866] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_WIN874] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_KOI8R] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_WIN1251] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_WIN1252] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_ISO_8859_5] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_ISO_8859_6] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_ISO_8859_7] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_ISO_8859_8] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_WIN1250] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_WIN1253] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_WIN1254] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_WIN1255] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_WIN1257] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_KOI8U] = {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1},
+	[PG_SJIS] = {0, 0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifychar, pg_sjis_verifystr, 2},
+	[PG_BIG5] = {0, 0, pg_big5_mblen, pg_big5_dsplen, pg_big5_verifychar, pg_big5_verifystr, 2},
+	[PG_GBK] = {0, 0, pg_gbk_mblen, pg_gbk_dsplen, pg_gbk_verifychar, pg_gbk_verifystr, 2},
+	[PG_UHC] = {0, 0, pg_uhc_mblen, pg_uhc_dsplen, pg_uhc_verifychar, pg_uhc_verifystr, 2},
+	[PG_GB18030] = {0, 0, pg_gb18030_mblen, pg_gb18030_dsplen, pg_gb18030_verifychar, pg_gb18030_verifystr, 4},
+	[PG_JOHAB] = {0, 0, pg_johab_mblen, pg_johab_dsplen, pg_johab_verifychar, pg_johab_verifystr, 3},
+	[PG_SHIFT_JIS_2004] = {0, 0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifychar, pg_sjis_verifystr, 2},
 };
 
 /*
@@ -2250,5 +2228,11 @@ pg_encoding_max_length(int encoding)
 {
 	Assert(PG_VALID_ENCODING(encoding));
 
-	return pg_wchar_table[encoding].maxmblen;
+	/*
+	 * Check for the encoding despite the assert, due to some mingw versions
+	 * otherwise issuing bogus warnings.
+	 */
+	return PG_VALID_ENCODING(encoding) ?
+		pg_wchar_table[encoding].maxmblen :
+		pg_wchar_table[PG_SQL_ASCII].maxmblen;
 }

data/ext/pg_query/src_pl_plpgsql_src_pl_comp.c

@@ -27,6 +27,7 @@
  * - plpgsql_parse_wordrowtype
  * - plpgsql_parse_cwordtype
  * - plpgsql_parse_cwordrowtype
+ * - plpgsql_build_datatype_arrayof
  * - plpgsql_parse_result
  * - plpgsql_finish_datums
  * - plpgsql_compile_error_callback
@@ -39,7 +40,7 @@
  * pl_comp.c		- Compiler part of the PL/pgSQL
  *			  procedural language
  *
- * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  *
@@ -693,10 +694,10 @@ plpgsql_parse_tripword(char *word1, char *word2, char *word3,
 
 
 /* ----------
- * plpgsql_parse_wordtype	The scanner found word%TYPE. word can be
- *				a variable name or a basetype.
+ * plpgsql_parse_wordtype	The scanner found word%TYPE. word should be
+ *				a pre-existing variable name.
  *
- * Returns datatype struct, or NULL if no match found for word.
+ * Returns datatype struct.  Throws error if no match found for word.
  * ----------
  */
 PLpgSQL_type * plpgsql_parse_wordtype(char *ident) { return NULL; }
@@ -705,6 +706,10 @@ PLpgSQL_type * plpgsql_parse_wordtype(char *ident) { return NULL; }
 
 /* ----------
  * plpgsql_parse_cwordtype		Same lookup for compositeword%TYPE
+ *
+ * Here, we allow either a block-qualified variable name, or a reference
+ * to a column of some table.  (If we must throw error, we assume that the
+ * latter case was intended.)
  * ----------
  */
 PLpgSQL_type * plpgsql_parse_cwordtype(List *idents) { return NULL; }
@@ -879,7 +884,53 @@ plpgsql_build_recfield(PLpgSQL_rec *rec, const char *fldname)
  * It can be NULL if the type could not be a composite type, or if it was
  * identified by OID to begin with (e.g., it's a function argument type).
  */
-PLpgSQL_type * plpgsql_build_datatype(Oid typeOid, int32 typmod, Oid collation, TypeName *origtypname) { PLpgSQL_type *typ; typ = (PLpgSQL_type *) palloc0(sizeof(PLpgSQL_type)); typ->typname = pstrdup("UNKNOWN"); typ->ttype = PLPGSQL_TTYPE_SCALAR; return typ; }
+
+PLpgSQL_type * plpgsql_build_datatype(Oid typeOid, int32 typmod, Oid collation, TypeName *origtypname)
+{
+	PLpgSQL_type *typ;
+	char *ident = NULL, *ns = NULL;
+	typ = (PLpgSQL_type *) palloc0(sizeof(PLpgSQL_type));
+
+	typ->ttype = PLPGSQL_TTYPE_SCALAR;
+	typ->atttypmod = typmod;
+	typ->collation = collation;
+
+	if (origtypname) {
+		typ->typoid = origtypname->typeOid;
+
+		if (list_length(origtypname->names) == 1) {
+			ident = linitial_node(String, origtypname->names)->sval;
+		} else if (list_length(origtypname->names) == 2) {
+			ns = linitial_node(String, origtypname->names)->sval;
+			ident = lsecond_node(String, origtypname->names)->sval;
+			if (strcmp(ns, "pg_catalog") != 0)
+				typ->ttype = PLPGSQL_TTYPE_REC;
+		}
+	} else {
+		typ->typoid = typeOid;
+		ns = "pg_catalog";
+		switch(typeOid)
+		{
+			case BOOLOID:
+				ident = "boolean";
+				break;
+			case INT4OID:
+				ident = "integer";
+				break;
+			case TEXTOID:
+				ident = "text";
+				break;
+			case REFCURSOROID:
+				ident = "refcursor";
+				break;
+		}
+	}
+	if (ident) {
+		typ->typname = quote_qualified_identifier(ns, ident);
+	}
+	return typ;
+}
+
 
 
 /*
@@ -888,6 +939,49 @@ PLpgSQL_type * plpgsql_build_datatype(Oid typeOid, int32 typmod, Oid collation,
  */
 
 
+/*
+ * Build an array type for the element type specified as argument.
+ */
+
+PLpgSQL_type * plpgsql_build_datatype_arrayof(PLpgSQL_type *dtype)
+{
+	if (dtype->typisarray)
+		return dtype;
+
+	PLpgSQL_type *array_type;
+	array_type = (PLpgSQL_type *) palloc0(sizeof(PLpgSQL_type));
+
+	array_type->ttype = PLPGSQL_TTYPE_REC;
+	array_type->atttypmod = dtype->atttypmod;
+	array_type->collation = dtype->collation;
+
+	array_type->typisarray = true;
+
+	switch(dtype->typoid)
+	{
+		case BOOLOID:
+			array_type->typoid = BOOLARRAYOID;
+			array_type->typname = pstrdup("boolean[]");
+			break;
+		case INT4OID:
+			array_type->typoid = INT4ARRAYOID;
+			array_type->typname = pstrdup("integer[]");
+			break;
+		case TEXTOID:
+			array_type->typoid = TEXTARRAYOID;
+			array_type->typname = pstrdup("text[]");
+			break;
+		default:
+			array_type->typname = pstrdup("UNKNOWN");
+			break;
+	}
+	array_type->typoid = dtype->typoid;
+
+	return array_type;
+}
+
+
+
 /*
  *	plpgsql_recognize_err_condition
  *		Check condition name and translate it to SQLSTATE.

data/ext/pg_query/src_pl_plpgsql_src_pl_funcs.c

@@ -49,7 +49,7 @@
  * pl_funcs.c		- Misc functions for the PL/pgSQL
  *			  procedural language
  *
- * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  *
@@ -287,6 +287,8 @@ plpgsql_getdiag_kindname(PLpgSQL_getdiag_kind kind)
 	{
 		case PLPGSQL_GETDIAG_ROW_COUNT:
 			return "ROW_COUNT";
+		case PLPGSQL_GETDIAG_ROUTINE_OID:
+			return "PG_ROUTINE_OID";
 		case PLPGSQL_GETDIAG_CONTEXT:
 			return "PG_CONTEXT";
 		case PLPGSQL_GETDIAG_ERROR_CONTEXT: