Reduce size of backend scanner's tables.

Previously, the core scanner's yy_transition[] array had 37045 elements.
Since that number is larger than INT16_MAX, Flex generated the array to
contain 32-bit integers.  By reimplementing some of the bulkier scanner
rules, this patch reduces the array to 20495 elements.  The much smaller
total length, combined with the consequent use of 16-bit integers for
the array elements reduces the binary size by over 200kB.  This was
accomplished in two ways:

1. Consolidate handling of quote continuations into a new start condition,
rather than duplicating that logic for five different string types.

2. Treat Unicode strings and identifiers followed by a UESCAPE sequence
as three separate tokens, rather than one.  The logic to de-escape
Unicode strings is moved to the filter code in parser.c, which already
had the ability to provide special processing for token sequences.
While we could have implemented the conversion in the grammar, that
approach was rejected for performance and maintainability reasons.

Performance in microbenchmarks of raw parsing seems equal or slightly
faster in most cases, and it's reasonable to expect that in real-world
usage (with more competition for the CPU cache) there will be a larger
win.  The exception is UESCAPE sequences; lexing those is about 10%
slower, primarily because the scanner now has to be called three times
rather than one.  This seems acceptable since that feature is very
rarely used.

The psql and epcg lexers are likewise modified, primarily because we
want to keep them all in sync.  Since those lexers don't use the
space-hogging -CF option, the space savings is much less, but it's
still good for perhaps 10kB apiece.

While at it, merge the ecpg lexer's handling of C-style comments used
in SQL and in C.  Those have different rules regarding nested comments,
but since we already have the ability to keep track of the previous
start condition, we can use that to handle both cases within a single
start condition.  This matches the core scanner more closely.

John Naylor

Discussion: https://postgr.es/m/CACPNZCvaoa3EgVWm5yZhcSTX6RAtaLgniCPcBVOCwm8h3xpWkw@mail.gmail.com

src/backend/parser/gram.y

@@ -598,10 +598,13 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
  * the set of keywords.  PL/pgSQL depends on this so that it can share the
  * same lexer.  If you add/change tokens here, fix PL/pgSQL to match!
  *
+ * UIDENT and USCONST are reduced to IDENT and SCONST in parser.c, so that
+ * they need no productions here; but we must assign token codes to them.
+ *
  * DOT_DOT is unused in the core SQL grammar, and so will always provoke
  * parse errors.  It is needed by PL/pgSQL.
  */
-%token <str>	IDENT FCONST SCONST BCONST XCONST Op
+%token <str>	IDENT UIDENT FCONST SCONST USCONST BCONST XCONST Op
 %token <ival>	ICONST PARAM
 %token			TYPECAST DOT_DOT COLON_EQUALS EQUALS_GREATER
 %token			LESS_EQUALS GREATER_EQUALS NOT_EQUALS
@@ -691,8 +694,8 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	TREAT TRIGGER TRIM TRUE_P
 	TRUNCATE TRUSTED TYPE_P TYPES_P
 
-	UNBOUNDED UNCOMMITTED UNENCRYPTED UNION UNIQUE UNKNOWN UNLISTEN UNLOGGED
-	UNTIL UPDATE USER USING
+	UESCAPE UNBOUNDED UNCOMMITTED UNENCRYPTED UNION UNIQUE UNKNOWN
+	UNLISTEN UNLOGGED UNTIL UPDATE USER USING
 
 	VACUUM VALID VALIDATE VALIDATOR VALUE_P VALUES VARCHAR VARIADIC VARYING
 	VERBOSE VERSION_P VIEW VIEWS VOLATILE
@@ -15374,6 +15377,7 @@ unreserved_keyword:
 			| TRUSTED
 			| TYPE_P
 			| TYPES_P
+			| UESCAPE
 			| UNBOUNDED
 			| UNCOMMITTED
 			| UNENCRYPTED

src/backend/parser/parser.c

@@ -21,8 +21,14 @@
 
 #include "postgres.h"
 
+#include "mb/pg_wchar.h"
 #include "parser/gramparse.h"
 #include "parser/parser.h"
+#include "parser/scansup.h"
+
+static bool check_uescapechar(unsigned char escape);
+static char *str_udeescape(const char *str, char escape,
+						   int position, core_yyscan_t yyscanner);
 
 
 /*
@@ -75,6 +81,10 @@ raw_parser(const char *str)
  * scanner backtrack, which would cost more performance than this filter
  * layer does.
  *
+ * We also use this filter to convert UIDENT and USCONST sequences into
+ * plain IDENT and SCONST tokens.  While that could be handled by additional
+ * productions in the main grammar, it's more efficient to do it like this.
+ *
  * The filter also provides a convenient place to translate between
  * the core_YYSTYPE and YYSTYPE representations (which are really the
  * same thing anyway, but notationally they're different).
@@ -104,7 +114,7 @@ base_yylex(YYSTYPE *lvalp, YYLTYPE *llocp, core_yyscan_t yyscanner)
 	 * If this token isn't one that requires lookahead, just return it.  If it
 	 * does, determine the token length.  (We could get that via strlen(), but
 	 * since we have such a small set of possibilities, hardwiring seems
-	 * feasible and more efficient.)
+	 * feasible and more efficient --- at least for the fixed-length cases.)
 	 */
 	switch (cur_token)
 	{
@@ -117,6 +127,10 @@ base_yylex(YYSTYPE *lvalp, YYLTYPE *llocp, core_yyscan_t yyscanner)
 		case WITH:
 			cur_token_length = 4;
 			break;
+		case UIDENT:
+		case USCONST:
+			cur_token_length = strlen(yyextra->core_yy_extra.scanbuf + *llocp);
+			break;
 		default:
 			return cur_token;
 	}
@@ -190,7 +204,273 @@ base_yylex(YYSTYPE *lvalp, YYLTYPE *llocp, core_yyscan_t yyscanner)
 					break;
 			}
 			break;
+
+		case UIDENT:
+		case USCONST:
+			/* Look ahead for UESCAPE */
+			if (next_token == UESCAPE)
+			{
+				/* Yup, so get third token, which had better be SCONST */
+				const char *escstr;
+
+				/* Again save and restore *llocp */
+				cur_yylloc = *llocp;
+
+				/* Un-truncate current token so errors point to third token */
+				*(yyextra->lookahead_end) = yyextra->lookahead_hold_char;
+
+				/* Get third token */
+				next_token = core_yylex(&(yyextra->lookahead_yylval),
+										llocp, yyscanner);
+
+				/* If we throw error here, it will point to third token */
+				if (next_token != SCONST)
+					scanner_yyerror("UESCAPE must be followed by a simple string literal",
+									yyscanner);
+
+				escstr = yyextra->lookahead_yylval.str;
+				if (strlen(escstr) != 1 || !check_uescapechar(escstr[0]))
+					scanner_yyerror("invalid Unicode escape character",
+									yyscanner);
+
+				/* Now restore *llocp; errors will point to first token */
+				*llocp = cur_yylloc;
+
+				/* Apply Unicode conversion */
+				lvalp->core_yystype.str =
+					str_udeescape(lvalp->core_yystype.str,
+								  escstr[0],
+								  *llocp,
+								  yyscanner);
+
+				/*
+				 * We don't need to revert the un-truncation of UESCAPE.  What
+				 * we do want to do is clear have_lookahead, thereby consuming
+				 * all three tokens.
+				 */
+				yyextra->have_lookahead = false;
+			}
+			else
+			{
+				/* No UESCAPE, so convert using default escape character */
+				lvalp->core_yystype.str =
+					str_udeescape(lvalp->core_yystype.str,
+								  '\\',
+								  *llocp,
+								  yyscanner);
+			}
+
+			if (cur_token == UIDENT)
+			{
+				/* It's an identifier, so truncate as appropriate */
+				truncate_identifier(lvalp->core_yystype.str,
+									strlen(lvalp->core_yystype.str),
+									true);
+				cur_token = IDENT;
+			}
+			else if (cur_token == USCONST)
+			{
+				cur_token = SCONST;
+			}
+			break;
 	}
 
 	return cur_token;
 }
+
+/* convert hex digit (caller should have verified that) to value */
+static unsigned int
+hexval(unsigned char c)
+{
+	if (c >= '0' && c <= '9')
+		return c - '0';
+	if (c >= 'a' && c <= 'f')
+		return c - 'a' + 0xA;
+	if (c >= 'A' && c <= 'F')
+		return c - 'A' + 0xA;
+	elog(ERROR, "invalid hexadecimal digit");
+	return 0;					/* not reached */
+}
+
+/* is Unicode code point acceptable in database's encoding? */
+static void
+check_unicode_value(pg_wchar c, int pos, core_yyscan_t yyscanner)
+{
+	/* See also addunicode() in scan.l */
+	if (c == 0 || c > 0x10FFFF)
+		ereport(ERROR,
+				(errcode(ERRCODE_SYNTAX_ERROR),
+				 errmsg("invalid Unicode escape value"),
+				 scanner_errposition(pos, yyscanner)));
+
+	if (c > 0x7F && GetDatabaseEncoding() != PG_UTF8)
+		ereport(ERROR,
+				(errcode(ERRCODE_SYNTAX_ERROR),
+				 errmsg("Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8"),
+				 scanner_errposition(pos, yyscanner)));
+}
+
+/* is 'escape' acceptable as Unicode escape character (UESCAPE syntax) ? */
+static bool
+check_uescapechar(unsigned char escape)
+{
+	if (isxdigit(escape)
+		|| escape == '+'
+		|| escape == '\''
+		|| escape == '"'
+		|| scanner_isspace(escape))
+		return false;
+	else
+		return true;
+}
+
+/*
+ * Process Unicode escapes in "str", producing a palloc'd plain string
+ *
+ * escape: the escape character to use
+ * position: start position of U&'' or U&"" string token
+ * yyscanner: context information needed for error reports
+ */
+static char *
+str_udeescape(const char *str, char escape,
+			  int position, core_yyscan_t yyscanner)
+{
+	const char *in;
+	char	   *new,
+			   *out;
+	pg_wchar	pair_first = 0;
+
+	/*
+	 * This relies on the subtle assumption that a UTF-8 expansion cannot be
+	 * longer than its escaped representation.
+	 */
+	new = palloc(strlen(str) + 1);
+
+	in = str;
+	out = new;
+	while (*in)
+	{
+		if (in[0] == escape)
+		{
+			if (in[1] == escape)
+			{
+				if (pair_first)
+					goto invalid_pair;
+				*out++ = escape;
+				in += 2;
+			}
+			else if (isxdigit((unsigned char) in[1]) &&
+					 isxdigit((unsigned char) in[2]) &&
+					 isxdigit((unsigned char) in[3]) &&
+					 isxdigit((unsigned char) in[4]))
+			{
+				pg_wchar	unicode;
+
+				unicode = (hexval(in[1]) << 12) +
+					(hexval(in[2]) << 8) +
+					(hexval(in[3]) << 4) +
+					hexval(in[4]);
+				check_unicode_value(unicode,
+									in - str + position + 3,	/* 3 for U&" */
+									yyscanner);
+				if (pair_first)
+				{
+					if (is_utf16_surrogate_second(unicode))
+					{
+						unicode = surrogate_pair_to_codepoint(pair_first, unicode);
+						pair_first = 0;
+					}
+					else
+						goto invalid_pair;
+				}
+				else if (is_utf16_surrogate_second(unicode))
+					goto invalid_pair;
+
+				if (is_utf16_surrogate_first(unicode))
+					pair_first = unicode;
+				else
+				{
+					unicode_to_utf8(unicode, (unsigned char *) out);
+					out += pg_mblen(out);
+				}
+				in += 5;
+			}
+			else if (in[1] == '+' &&
+					 isxdigit((unsigned char) in[2]) &&
+					 isxdigit((unsigned char) in[3]) &&
+					 isxdigit((unsigned char) in[4]) &&
+					 isxdigit((unsigned char) in[5]) &&
+					 isxdigit((unsigned char) in[6]) &&
+					 isxdigit((unsigned char) in[7]))
+			{
+				pg_wchar	unicode;
+
+				unicode = (hexval(in[2]) << 20) +
+					(hexval(in[3]) << 16) +
+					(hexval(in[4]) << 12) +
+					(hexval(in[5]) << 8) +
+					(hexval(in[6]) << 4) +
+					hexval(in[7]);
+				check_unicode_value(unicode,
+									in - str + position + 3,	/* 3 for U&" */
+									yyscanner);
+				if (pair_first)
+				{
+					if (is_utf16_surrogate_second(unicode))
+					{
+						unicode = surrogate_pair_to_codepoint(pair_first, unicode);
+						pair_first = 0;
+					}
+					else
+						goto invalid_pair;
+				}
+				else if (is_utf16_surrogate_second(unicode))
+					goto invalid_pair;
+
+				if (is_utf16_surrogate_first(unicode))
+					pair_first = unicode;
+				else
+				{
+					unicode_to_utf8(unicode, (unsigned char *) out);
+					out += pg_mblen(out);
+				}
+				in += 8;
+			}
+			else
+				ereport(ERROR,
+						(errcode(ERRCODE_SYNTAX_ERROR),
+						 errmsg("invalid Unicode escape value"),
+						 scanner_errposition(in - str + position + 3,	/* 3 for U&" */
+											 yyscanner)));
+		}
+		else
+		{
+			if (pair_first)
+				goto invalid_pair;
+
+			*out++ = *in++;
+		}
+	}
+
+	/* unfinished surrogate pair? */
+	if (pair_first)
+		goto invalid_pair;
+
+	*out = '\0';
+
+	/*
+	 * We could skip pg_verifymbstr if we didn't process any non-7-bit-ASCII
+	 * codes; but it's probably not worth the trouble, since this isn't likely
+	 * to be a performance-critical path.
+	 */
+	pg_verifymbstr(new, out - new, false);
+	return new;
+
+invalid_pair:
+	ereport(ERROR,
+			(errcode(ERRCODE_SYNTAX_ERROR),
+			 errmsg("invalid Unicode surrogate pair"),
+			 scanner_errposition(in - str + position + 3,	/* 3 for U&" */
+								 yyscanner)));
+	return NULL;				/* keep compiler quiet */
+}

src/fe_utils/psqlscan.l

@@ -114,12 +114,11 @@ extern void psql_yyset_column(int column_no, yyscan_t yyscanner);
  *  <xd> delimited identifiers (double-quoted identifiers)
  *  <xh> hexadecimal numeric string
  *  <xq> standard quoted strings
+ *  <xqs> quote stop (detect continued strings)
  *  <xe> extended quoted strings (support backslash escape sequences)
  *  <xdolq> $foo$ quoted strings
  *  <xui> quoted identifier with Unicode escapes
- *  <xuiend> end of a quoted identifier with Unicode escapes, UESCAPE can follow
  *  <xus> quoted string with Unicode escapes
- *  <xusend> end of a quoted string with Unicode escapes, UESCAPE can follow
  *
  * Note: we intentionally don't mimic the backend's <xeu> state; we have
  * no need to distinguish it from <xe> state, and no good way to get out
@@ -132,12 +131,11 @@ extern void psql_yyset_column(int column_no, yyscan_t yyscanner);
 %x xd
 %x xh
 %x xq
+%x xqs
 %x xe
 %x xdolq
 %x xui
-%x xuiend
 %x xus
-%x xusend
 
 /*
  * In order to make the world safe for Windows and Mac clients as well as
@@ -177,19 +175,18 @@ special_whitespace		({space}+|{comment}{newline})
 horiz_whitespace		({horiz_space}|{comment})
 whitespace_with_newline	({horiz_whitespace}*{newline}{special_whitespace}*)
 
+quote			'
+/* If we see {quote} then {quotecontinue}, the quoted string continues */
+quotecontinue	{whitespace_with_newline}{quote}
+
 /*
- * To ensure that {quotecontinue} can be scanned without having to back up
- * if the full pattern isn't matched, we include trailing whitespace in
- * {quotestop}.  This matches all cases where {quotecontinue} fails to match,
- * except for {quote} followed by whitespace and just one "-" (not two,
- * which would start a {comment}).  To cover that we have {quotefail}.
- * The actions for {quotestop} and {quotefail} must throw back characters
- * beyond the quote proper.
+ * {quotecontinuefail} is needed to avoid lexer backup when we fail to match
+ * {quotecontinue}.  It might seem that this could just be {whitespace}*,
+ * but if there's a dash after {whitespace_with_newline}, it must be consumed
+ * to see if there's another dash --- which would start a {comment} and thus
+ * allow continuation of the {quotecontinue} token.
  */
-quote			'
-quotestop		{quote}{whitespace}*
-quotecontinue	{quote}{whitespace_with_newline}{quote}
-quotefail		{quote}{whitespace}*"-"
+quotecontinuefail	{whitespace}*"-"?
 
 /* Bit string
  * It is tempting to scan the string for only those characters
@@ -250,21 +247,12 @@ xdstop			{dquote}
 xddouble		{dquote}{dquote}
 xdinside		[^"]+
 
-/* Unicode escapes */
-uescape			[uU][eE][sS][cC][aA][pP][eE]{whitespace}*{quote}[^']{quote}
-/* error rule to avoid backup */
-uescapefail		[uU][eE][sS][cC][aA][pP][eE]{whitespace}*"-"|[uU][eE][sS][cC][aA][pP][eE]{whitespace}*{quote}[^']|[uU][eE][sS][cC][aA][pP][eE]{whitespace}*{quote}|[uU][eE][sS][cC][aA][pP][eE]{whitespace}*|[uU][eE][sS][cC][aA][pP]|[uU][eE][sS][cC][aA]|[uU][eE][sS][cC]|[uU][eE][sS]|[uU][eE]|[uU]
-
 /* Quoted identifier with Unicode escapes */
 xuistart		[uU]&{dquote}
 
 /* Quoted string with Unicode escapes */
 xusstart		[uU]&{quote}
 
-/* Optional UESCAPE after a quoted string or identifier with Unicode escapes. */
-xustop1		{uescapefail}?
-xustop2		{uescape}
-
 /* error rule to avoid backup */
 xufailed		[uU]&
 
@@ -438,20 +426,10 @@ other			.
 					BEGIN(xb);
 					ECHO;
 				}
-<xb>{quotestop}	|
-<xb>{quotefail} {
-					yyless(1);
-					BEGIN(INITIAL);
-					ECHO;
-				}
 <xh>{xhinside}	|
 <xb>{xbinside}	{
 					ECHO;
 				}
-<xh>{quotecontinue}	|
-<xb>{quotecontinue}	{
-					ECHO;
-				}
 
 {xhstart}		{
 					/* Hexadecimal bit type.
@@ -463,12 +441,6 @@ other			.
 					BEGIN(xh);
 					ECHO;
 				}
-<xh>{quotestop}	|
-<xh>{quotefail} {
-					yyless(1);
-					BEGIN(INITIAL);
-					ECHO;
-				}
 
 {xnstart}		{
 					yyless(1);	/* eat only 'n' this time */
@@ -490,32 +462,41 @@ other			.
 					BEGIN(xus);
 					ECHO;
 				}
-<xq,xe>{quotestop}	|
-<xq,xe>{quotefail} {
-					yyless(1);
-					BEGIN(INITIAL);
-					ECHO;
-				}
-<xus>{quotestop} |
-<xus>{quotefail} {
-					/* throw back all but the quote */
-					yyless(1);
-					BEGIN(xusend);
+
+<xb,xh,xq,xe,xus>{quote} {
+					/*
+					 * When we are scanning a quoted string and see an end
+					 * quote, we must look ahead for a possible continuation.
+					 * If we don't see one, we know the end quote was in fact
+					 * the end of the string.  To reduce the lexer table size,
+					 * we use a single "xqs" state to do the lookahead for all
+					 * types of strings.
+					 */
+					cur_state->state_before_str_stop = YYSTATE;
+					BEGIN(xqs);
 					ECHO;
 				}
-<xusend>{whitespace} {
+<xqs>{quotecontinue} {
+					/*
+					 * Found a quote continuation, so return to the in-quote
+					 * state and continue scanning the literal.  Nothing is
+					 * added to the literal's contents.
+					 */
+					BEGIN(cur_state->state_before_str_stop);
 					ECHO;
 				}
-<xusend>{other} |
-<xusend>{xustop1} {
+<xqs>{quotecontinuefail} |
+<xqs>{other}	{
+					/*
+					 * Failed to see a quote continuation.  Throw back
+					 * everything after the end quote, and handle the string
+					 * according to the state we were in previously.
+					 */
 					yyless(0);
 					BEGIN(INITIAL);
-					ECHO;
-				}
-<xusend>{xustop2} {
-					BEGIN(INITIAL);
-					ECHO;
+					/* There's nothing to echo ... */
 				}
+
 <xq,xe,xus>{xqdouble} {
 					ECHO;
 				}
@@ -540,9 +521,6 @@ other			.
 <xe>{xehexesc}  {
 					ECHO;
 				}
-<xq,xe,xus>{quotecontinue} {
-					ECHO;
-				}
 <xe>.			{
 					/* This is only needed for \ just before EOF */
 					ECHO;
@@ -599,21 +577,7 @@ other			.
 					BEGIN(INITIAL);
 					ECHO;
 				}
-<xui>{dquote} {
-					yyless(1);
-					BEGIN(xuiend);
-					ECHO;
-				}
-<xuiend>{whitespace} {
-					ECHO;
-				}
-<xuiend>{other} |
-<xuiend>{xustop1} {
-					yyless(0);
-					BEGIN(INITIAL);
-					ECHO;
-				}
-<xuiend>{xustop2}	{
+<xui>{dquote}	{
 					BEGIN(INITIAL);
 					ECHO;
 				}
@@ -1084,8 +1048,7 @@ psql_scan(PsqlScanState state,
 			switch (state->start_state)
 			{
 				case INITIAL:
-				case xuiend:	/* we treat these like INITIAL */
-				case xusend:
+				case xqs:		/* we treat this like INITIAL */
 					if (state->paren_depth > 0)
 					{
 						result = PSCAN_INCOMPLETE;
@@ -1240,7 +1203,8 @@ psql_scan_reselect_sql_lexer(PsqlScanState state)
 bool
 psql_scan_in_quote(PsqlScanState state)
 {
-	return state->start_state != INITIAL;
+	return state->start_state != INITIAL &&
+			state->start_state != xqs;
 }
 
 /*

src/include/fe_utils/psqlscan_int.h

@@ -110,6 +110,7 @@ typedef struct PsqlScanStateData
 	 * and updated with its finishing state on exit.
 	 */
 	int			start_state;	/* yylex's starting/finishing state */
+	int			state_before_str_stop;	/* start cond. before end quote */
 	int			paren_depth;	/* depth of nesting in parentheses */
 	int			xcdepth;		/* depth of nesting in slash-star comments */
 	char	   *dolqstart;		/* current $foo$ quote start string */

src/include/mb/pg_wchar.h

@@ -508,6 +508,28 @@ typedef uint32 (*utf_local_conversion_func) (uint32 code);
 								   (destencoding))
 
 
+/*
+ * Some handy functions for Unicode-specific tests.
+ */
+static inline bool
+is_utf16_surrogate_first(pg_wchar c)
+{
+	return (c >= 0xD800 && c <= 0xDBFF);
+}
+
+static inline bool
+is_utf16_surrogate_second(pg_wchar c)
+{
+	return (c >= 0xDC00 && c <= 0xDFFF);
+}
+
+static inline pg_wchar
+surrogate_pair_to_codepoint(pg_wchar first, pg_wchar second)
+{
+	return ((first & 0x3FF) << 10) + 0x10000 + (second & 0x3FF);
+}
+
+
 /*
  * These functions are considered part of libpq's exported API and
  * are also declared in libpq-fe.h.

src/include/parser/kwlist.h

@@ -416,6 +416,7 @@ PG_KEYWORD("truncate", TRUNCATE, UNRESERVED_KEYWORD)
 PG_KEYWORD("trusted", TRUSTED, UNRESERVED_KEYWORD)
 PG_KEYWORD("type", TYPE_P, UNRESERVED_KEYWORD)
 PG_KEYWORD("types", TYPES_P, UNRESERVED_KEYWORD)
+PG_KEYWORD("uescape", UESCAPE, UNRESERVED_KEYWORD)
 PG_KEYWORD("unbounded", UNBOUNDED, UNRESERVED_KEYWORD)
 PG_KEYWORD("uncommitted", UNCOMMITTED, UNRESERVED_KEYWORD)
 PG_KEYWORD("unencrypted", UNENCRYPTED, UNRESERVED_KEYWORD)

src/include/parser/scanner.h

@@ -48,7 +48,7 @@ typedef union core_YYSTYPE
  * However, those are not defined in this file, because bison insists on
  * defining them for itself.  The token codes used by the core scanner are
  * the ASCII characters plus these:
- *	%token <str>	IDENT FCONST SCONST BCONST XCONST Op
+ *	%token <str>	IDENT UIDENT FCONST SCONST USCONST BCONST XCONST Op
  *	%token <ival>	ICONST PARAM
  *	%token			TYPECAST DOT_DOT COLON_EQUALS EQUALS_GREATER
  *	%token			LESS_EQUALS GREATER_EQUALS NOT_EQUALS
@@ -99,6 +99,7 @@ typedef struct core_yy_extra_type
 	int			literallen;		/* actual current string length */
 	int			literalalloc;	/* current allocated buffer size */
 
+	int			state_before_str_stop;	/* start cond. before end quote */
 	int			xcdepth;		/* depth of nesting in slash-star comments */
 	char	   *dolqstart;		/* current $foo$ quote start string */
 

src/interfaces/ecpg/preproc/ecpg.tokens

@@ -24,4 +24,3 @@
                 S_TYPEDEF
 
 %token CSTRING CVARIABLE CPP_LINE IP
-%token DOLCONST ECONST NCONST UCONST UIDENT

src/interfaces/ecpg/preproc/ecpg.trailer

@@ -1719,46 +1719,12 @@ ecpg_bconst:	BCONST		{ $$ = make_name(); } ;
 
 ecpg_fconst:	FCONST		{ $$ = make_name(); } ;
 
-ecpg_sconst:
-		SCONST
-		{
-			/* could have been input as '' or $$ */
-			$$ = (char *)mm_alloc(strlen($1) + 3);
-			$$[0]='\'';
-			strcpy($$+1, $1);
-			$$[strlen($1)+1]='\'';
-			$$[strlen($1)+2]='\0';
-			free($1);
-		}
-		| ECONST
-		{
-			$$ = (char *)mm_alloc(strlen($1) + 4);
-			$$[0]='E';
-			$$[1]='\'';
-			strcpy($$+2, $1);
-			$$[strlen($1)+2]='\'';
-			$$[strlen($1)+3]='\0';
-			free($1);
-		}
-		| NCONST
-		{
-			$$ = (char *)mm_alloc(strlen($1) + 4);
-			$$[0]='N';
-			$$[1]='\'';
-			strcpy($$+2, $1);
-			$$[strlen($1)+2]='\'';
-			$$[strlen($1)+3]='\0';
-			free($1);
-		}
-		| UCONST	{ $$ = $1; }
-		| DOLCONST	{ $$ = $1; }
-		;
+ecpg_sconst:	SCONST		{ $$ = $1; } ;
 
 ecpg_xconst:	XCONST		{ $$ = make_name(); } ;
 
-ecpg_ident:	IDENT		{ $$ = make_name(); }
+ecpg_ident:	IDENT		{ $$ = $1; }
 		| CSTRING	{ $$ = make3_str(mm_strdup("\""), $1, mm_strdup("\"")); }
-		| UIDENT	{ $$ = $1; }
 		;
 
 quoted_ident_stringvar: name

src/interfaces/ecpg/preproc/ecpg.type

@@ -122,12 +122,8 @@
 %type <str> CSTRING
 %type <str> CPP_LINE
 %type <str> CVARIABLE
-%type <str> DOLCONST
-%type <str> ECONST
-%type <str> NCONST
 %type <str> SCONST
-%type <str> UCONST
-%type <str> UIDENT
+%type <str> IDENT
 
 %type  <struct_union> s_struct_union_symbol
 

src/interfaces/ecpg/preproc/parse.pl

@@ -218,8 +218,8 @@ sub main
 				if ($a eq 'IDENT' && $prior eq '%nonassoc')
 				{
 
-					# add two more tokens to the list
-					$str = $str . "\n%nonassoc CSTRING\n%nonassoc UIDENT";
+					# add more tokens to the list
+					$str = $str . "\n%nonassoc CSTRING";
 				}
 				$prior = $a;
 			}

src/interfaces/ecpg/preproc/parser.c

@@ -6,6 +6,9 @@
  * This should match src/backend/parser/parser.c, except that we do not
  * need to bother with re-entrant interfaces.
  *
+ * Note: ECPG doesn't report error location like the backend does.
+ * This file will need work if we ever want it to.
+ *
  *
  * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -27,8 +30,9 @@ static int	lookahead_token;	/* one-token lookahead */
 static YYSTYPE lookahead_yylval;	/* yylval for lookahead token */
 static YYLTYPE lookahead_yylloc;	/* yylloc for lookahead token */
 static char *lookahead_yytext;	/* start current token */
-static char *lookahead_end;		/* end of current token */
-static char lookahead_hold_char;	/* to be put back at *lookahead_end */
+
+static bool check_uescapechar(unsigned char escape);
+static bool ecpg_isspace(char ch);
 
 
 /*
@@ -43,13 +47,16 @@ static char lookahead_hold_char;	/* to be put back at *lookahead_end */
  * words.  Furthermore it's not clear how to do that without re-introducing
  * scanner backtrack, which would cost more performance than this filter
  * layer does.
+ *
+ * We also use this filter to convert UIDENT and USCONST sequences into
+ * plain IDENT and SCONST tokens.  While that could be handled by additional
+ * productions in the main grammar, it's more efficient to do it like this.
  */
 int
 filtered_base_yylex(void)
 {
 	int			cur_token;
 	int			next_token;
-	int			cur_token_length;
 	YYSTYPE		cur_yylval;
 	YYLTYPE		cur_yylloc;
 	char	   *cur_yytext;
@@ -61,41 +68,26 @@ filtered_base_yylex(void)
 		base_yylval = lookahead_yylval;
 		base_yylloc = lookahead_yylloc;
 		base_yytext = lookahead_yytext;
-		*lookahead_end = lookahead_hold_char;
 		have_lookahead = false;
 	}
 	else
 		cur_token = base_yylex();
 
 	/*
-	 * If this token isn't one that requires lookahead, just return it.  If it
-	 * does, determine the token length.  (We could get that via strlen(), but
-	 * since we have such a small set of possibilities, hardwiring seems
-	 * feasible and more efficient.)
+	 * If this token isn't one that requires lookahead, just return it.
 	 */
 	switch (cur_token)
 	{
 		case NOT:
-			cur_token_length = 3;
-			break;
 		case NULLS_P:
-			cur_token_length = 5;
-			break;
 		case WITH:
-			cur_token_length = 4;
+		case UIDENT:
+		case USCONST:
 			break;
 		default:
 			return cur_token;
 	}
 
-	/*
-	 * Identify end+1 of current token.  base_yylex() has temporarily stored a
-	 * '\0' here, and will undo that when we call it again.  We need to redo
-	 * it to fully revert the lookahead call for error reporting purposes.
-	 */
-	lookahead_end = base_yytext + cur_token_length;
-	Assert(*lookahead_end == '\0');
-
 	/* Save and restore lexer output variables around the call */
 	cur_yylval = base_yylval;
 	cur_yylloc = base_yylloc;
@@ -113,10 +105,6 @@ filtered_base_yylex(void)
 	base_yylloc = cur_yylloc;
 	base_yytext = cur_yytext;
 
-	/* Now revert the un-truncation of the current token */
-	lookahead_hold_char = *lookahead_end;
-	*lookahead_end = '\0';
-
 	have_lookahead = true;
 
 	/* Replace cur_token if needed, based on lookahead */
@@ -157,7 +145,87 @@ filtered_base_yylex(void)
 					break;
 			}
 			break;
+		case UIDENT:
+		case USCONST:
+			/* Look ahead for UESCAPE */
+			if (next_token == UESCAPE)
+			{
+				/* Yup, so get third token, which had better be SCONST */
+				const char *escstr;
+
+				/*
+				 * Again save and restore lexer output variables around the
+				 * call
+				 */
+				cur_yylval = base_yylval;
+				cur_yylloc = base_yylloc;
+				cur_yytext = base_yytext;
+
+				/* Get third token */
+				next_token = base_yylex();
+
+				if (next_token != SCONST)
+					mmerror(PARSE_ERROR, ET_ERROR, "UESCAPE must be followed by a simple string literal");
+
+				/*
+				 * Save and check escape string, which the scanner returns
+				 * with quotes
+				 */
+				escstr = base_yylval.str;
+				if (strlen(escstr) != 3 || !check_uescapechar(escstr[1]))
+					mmerror(PARSE_ERROR, ET_ERROR, "invalid Unicode escape character");
+
+				base_yylval = cur_yylval;
+				base_yylloc = cur_yylloc;
+				base_yytext = cur_yytext;
+
+				/* Combine 3 tokens into 1 */
+				base_yylval.str = psprintf("%s UESCAPE %s", base_yylval.str, escstr);
+
+				/* Clear have_lookahead, thereby consuming all three tokens */
+				have_lookahead = false;
+			}
+
+			if (cur_token == UIDENT)
+				cur_token = IDENT;
+			else if (cur_token == USCONST)
+				cur_token = SCONST;
+			break;
 	}
 
 	return cur_token;
 }
+
+/*
+ * check_uescapechar() and ecpg_isspace() should match their equivalents
+ * in pgc.l.
+ */
+
+/* is 'escape' acceptable as Unicode escape character (UESCAPE syntax) ? */
+static bool
+check_uescapechar(unsigned char escape)
+{
+	if (isxdigit(escape)
+		|| escape == '+'
+		|| escape == '\''
+		|| escape == '"'
+		|| ecpg_isspace(escape))
+		return false;
+	else
+		return true;
+}
+
+/*
+ * ecpg_isspace() --- return true if flex scanner considers char whitespace
+ */
+static bool
+ecpg_isspace(char ch)
+{
+	if (ch == ' ' ||
+		ch == '\t' ||
+		ch == '\n' ||
+		ch == '\r' ||
+		ch == '\f')
+		return true;
+	return false;
+}

src/interfaces/ecpg/test/expected/preproc-strings.c

@@ -45,7 +45,7 @@ int main(void)
 #line 13 "strings.pgc"
 
 
-  { ECPGdo(__LINE__, 0, 1, NULL, 0, ECPGst_normal, "select 'abcdef' , N'abcdef' as foo , E'abc\\bdef' as \"foo\" , U&'d\\0061t\\0061' as U&\"foo\" , U&'d!+000061t!+000061' uescape '!' , $foo$abc$def$foo$", ECPGt_EOIT, 
+  { ECPGdo(__LINE__, 0, 1, NULL, 0, ECPGst_normal, "select 'abcdef' , N'abcdef' as foo , E'abc\\bdef' as \"foo\" , U&'d\\0061t\\0061' as U&\"foo\" , U&'d!+000061t!+000061' UESCAPE '!' , $foo$abc$def$foo$", ECPGt_EOIT, 
 	ECPGt_char,&(s1),(long)0,(long)1,(1)*sizeof(char), 
 	ECPGt_NO_INDICATOR, NULL , 0L, 0L, 0L, 
 	ECPGt_char,&(s2),(long)0,(long)1,(1)*sizeof(char), 

src/interfaces/ecpg/test/expected/preproc-strings.stderr

@@ -8,7 +8,7 @@
 [NO_PID]: sqlca: code: 0, state: 00000
 [NO_PID]: ecpg_process_output on line 13: OK: SET
 [NO_PID]: sqlca: code: 0, state: 00000
-[NO_PID]: ecpg_execute on line 15: query: select 'abcdef' , N'abcdef' as foo , E'abc\bdef' as "foo" , U&'d\0061t\0061' as U&"foo" , U&'d!+000061t!+000061' uescape '!' , $foo$abc$def$foo$; with 0 parameter(s) on connection ecpg1_regression
+[NO_PID]: ecpg_execute on line 15: query: select 'abcdef' , N'abcdef' as foo , E'abc\bdef' as "foo" , U&'d\0061t\0061' as U&"foo" , U&'d!+000061t!+000061' UESCAPE '!' , $foo$abc$def$foo$; with 0 parameter(s) on connection ecpg1_regression
 [NO_PID]: sqlca: code: 0, state: 00000
 [NO_PID]: ecpg_execute on line 15: using PQexec
 [NO_PID]: sqlca: code: 0, state: 00000

src/pl/plpgsql/src/pl_gram.y

@@ -232,7 +232,7 @@ static	void			check_raise_parameters(PLpgSQL_stmt_raise *stmt);
  * Some of these are not directly referenced in this file, but they must be
  * here anyway.
  */
-%token <str>	IDENT FCONST SCONST BCONST XCONST Op
+%token <str>	IDENT UIDENT FCONST SCONST USCONST BCONST XCONST Op
 %token <ival>	ICONST PARAM
 %token			TYPECAST DOT_DOT COLON_EQUALS EQUALS_GREATER
 %token			LESS_EQUALS GREATER_EQUALS NOT_EQUALS

src/test/regress/expected/strings.out

@@ -48,17 +48,21 @@ SELECT 'tricky' AS U&"\" UESCAPE '!';
 (1 row)
 
 SELECT U&'wrong: \061';
-ERROR:  invalid Unicode escape value at or near "\061'"
+ERROR:  invalid Unicode escape value
 LINE 1: SELECT U&'wrong: \061';
                          ^
 SELECT U&'wrong: \+0061';
-ERROR:  invalid Unicode escape value at or near "\+0061'"
+ERROR:  invalid Unicode escape value
 LINE 1: SELECT U&'wrong: \+0061';
                          ^
+SELECT U&'wrong: +0061' UESCAPE +;
+ERROR:  UESCAPE must be followed by a simple string literal at or near "+"
+LINE 1: SELECT U&'wrong: +0061' UESCAPE +;
+                                        ^
 SELECT U&'wrong: +0061' UESCAPE '+';
-ERROR:  invalid Unicode escape character at or near "+'"
+ERROR:  invalid Unicode escape character at or near "'+'"
 LINE 1: SELECT U&'wrong: +0061' UESCAPE '+';
-                                         ^
+                                        ^
 SET standard_conforming_strings TO off;
 SELECT U&'d\0061t\+000061' AS U&"d\0061t\+000061";
 ERROR:  unsafe use of string constant with Unicode escapes

src/test/regress/sql/strings.sql

@@ -27,6 +27,7 @@ SELECT 'tricky' AS U&"\" UESCAPE '!';
 
 SELECT U&'wrong: \061';
 SELECT U&'wrong: \+0061';
+SELECT U&'wrong: +0061' UESCAPE +;
 SELECT U&'wrong: +0061' UESCAPE '+';
 
 SET standard_conforming_strings TO off;