Improve some comments in scanner files

Reviewed-by: John Naylor <john.naylor@enterprisedb.com>
Discussion: https://www.postgresql.org/message-id/flat/b239564c-cad0-b23e-c57e-166d883cb97d@enterprisedb.com

3 files changed, 25 insertions, 19 deletions

diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
index 6e6824faebd..76fd6996eda 100644
--- a/src/backend/parser/scan.l
+++ b/src/backend/parser/scan.l
@@ -174,7 +174,7 @@ extern void core_yyset_column(int column_no, yyscan_t yyscanner);
  *  <xb> bit string literal
  *  <xc> extended C-style comments
  *  <xd> delimited identifiers (double-quoted identifiers)
- *  <xh> hexadecimal numeric string
+ *  <xh> hexadecimal byte string
  *  <xq> standard quoted strings
  *  <xqs> quote stop (detect continued strings)
  *  <xe> extended quoted strings (support backslash escape sequences)
@@ -262,7 +262,7 @@ quotecontinuefail	{whitespace}*"-"?
 xbstart			[bB]{quote}
 xbinside		[^']*
 
-/* Hexadecimal number */
+/* Hexadecimal byte string */
 xhstart			[xX]{quote}
 xhinside		[^']*
 
@@ -341,7 +341,6 @@ xcstart			\/\*{op_chars}*
 xcstop			\*+\/
 xcinside		[^*/]+
 
-digit			[0-9]
 ident_start		[A-Za-z\200-\377_]
 ident_cont		[A-Za-z\200-\377_0-9\$]
 
@@ -380,15 +379,18 @@ self			[,()\[\].;\:\+\-\*\/\%\^\<\>\=]
 op_chars		[\~\!\@\#\^\&\|\`\?\+\-\*\/\%\<\>\=]
 operator		{op_chars}+
 
-/* we no longer allow unary minus in numbers.
- * instead we pass it separately to parser. there it gets
- * coerced via doNegate() -- Leon aug 20 1999
+/*
+ * Numbers
+ *
+ * Unary minus is not part of a number here.  Instead we pass it separately to
+ * the parser, and there it gets coerced via doNegate().
  *
  * {decimalfail} is used because we would like "1..10" to lex as 1, dot_dot, 10.
  *
  * {realfail1} and {realfail2} are added to prevent the need for scanner
  * backup when the {real} rule fails to match completely.
  */
+digit			[0-9]
 
 integer			{digit}+
 decimal			(({digit}*\.{digit}+)|({digit}+\.{digit}*))
diff --git a/src/fe_utils/psqlscan.l b/src/fe_utils/psqlscan.l
index 0fab48a3825..b0fd4394ec6 100644
--- a/src/fe_utils/psqlscan.l
+++ b/src/fe_utils/psqlscan.l
@@ -112,7 +112,7 @@ extern void psql_yyset_column(int column_no, yyscan_t yyscanner);
  *  <xb> bit string literal
  *  <xc> extended C-style comments
  *  <xd> delimited identifiers (double-quoted identifiers)
- *  <xh> hexadecimal numeric string
+ *  <xh> hexadecimal byte string
  *  <xq> standard quoted strings
  *  <xqs> quote stop (detect continued strings)
  *  <xe> extended quoted strings (support backslash escape sequences)
@@ -200,7 +200,7 @@ quotecontinuefail	{whitespace}*"-"?
 xbstart			[bB]{quote}
 xbinside		[^']*
 
-/* Hexadecimal number */
+/* Hexadecimal byte string */
 xhstart			[xX]{quote}
 xhinside		[^']*
 
@@ -279,7 +279,6 @@ xcstart			\/\*{op_chars}*
 xcstop			\*+\/
 xcinside		[^*/]+
 
-digit			[0-9]
 ident_start		[A-Za-z\200-\377_]
 ident_cont		[A-Za-z\200-\377_0-9\$]
 
@@ -318,15 +317,18 @@ self			[,()\[\].;\:\+\-\*\/\%\^\<\>\=]
 op_chars		[\~\!\@\#\^\&\|\`\?\+\-\*\/\%\<\>\=]
 operator		{op_chars}+
 
-/* we no longer allow unary minus in numbers.
- * instead we pass it separately to parser. there it gets
- * coerced via doNegate() -- Leon aug 20 1999
+/*
+ * Numbers
+ *
+ * Unary minus is not part of a number here.  Instead we pass it separately to
+ * the parser, and there it gets coerced via doNegate().
  *
  * {decimalfail} is used because we would like "1..10" to lex as 1, dot_dot, 10.
  *
  * {realfail1} and {realfail2} are added to prevent the need for scanner
  * backup when the {real} rule fails to match completely.
  */
+digit			[0-9]
 
 integer			{digit}+
 decimal			(({digit}*\.{digit}+)|({digit}+\.{digit}*))
diff --git a/src/interfaces/ecpg/preproc/pgc.l b/src/interfaces/ecpg/preproc/pgc.l
index 7a0356638d7..a2f8c7f3d88 100644
--- a/src/interfaces/ecpg/preproc/pgc.l
+++ b/src/interfaces/ecpg/preproc/pgc.l
@@ -130,7 +130,7 @@ static struct _if_value
  *  <xc> extended C-style comments
  *  <xd> delimited identifiers (double-quoted identifiers)
  *  <xdc> double-quoted strings in C
- *  <xh> hexadecimal numeric string
+ *  <xh> hexadecimal byte string
  *  <xn> national character quoted strings
  *  <xq> standard quoted strings
  *  <xqs> quote stop (detect continued strings)
@@ -223,7 +223,7 @@ quotecontinuefail	{whitespace}*"-"?
 xbstart			[bB]{quote}
 xbinside		[^']*
 
-/* Hexadecimal number */
+/* Hexadecimal byte string */
 xhstart			[xX]{quote}
 xhinside		[^']*
 
@@ -305,7 +305,6 @@ xcstart			\/\*{op_chars}*
 xcstop			\*+\/
 xcinside		[^*/]+
 
-digit			[0-9]
 ident_start		[A-Za-z\200-\377_]
 ident_cont		[A-Za-z\200-\377_0-9\$]
 
@@ -346,15 +345,18 @@ self			[,()\[\].;\:\+\-\*\/\%\^\<\>\=]
 op_chars		[\~\!\@\#\^\&\|\`\?\+\-\*\/\%\<\>\=]
 operator		{op_chars}+
 
-/* we no longer allow unary minus in numbers.
- * instead we pass it separately to parser. there it gets
- * coerced via doNegate() -- Leon aug 20 1999
+/*
+ * Numbers
+ *
+ * Unary minus is not part of a number here.  Instead we pass it separately to
+ * the parser, and there it gets coerced via doNegate().
  *
  * {decimalfail} is used because we would like "1..10" to lex as 1, dot_dot, 10.
  *
  * {realfail1} and {realfail2} are added to prevent the need for scanner
  * backup when the {real} rule fails to match completely.
  */
+digit			[0-9]
 
 integer			{digit}+
 decimal			(({digit}*\.{digit}+)|({digit}+\.{digit}*))
@@ -603,7 +605,7 @@ cppline			{space}*#([^i][A-Za-z]*|{if}|{ifdef}|{ifndef}|{import})((\/\*[^*/]*\*+
 							return BCONST;
 						case xh:
 							if (literalbuf[strspn(literalbuf, "0123456789abcdefABCDEF")] != '\0')
-								mmerror(PARSE_ERROR, ET_ERROR, "invalid hex string literal");
+								mmerror(PARSE_ERROR, ET_ERROR, "invalid hexadecimal string literal");
 							base_yylval.str = psprintf("x'%s'", literalbuf);
 							return XCONST;
 						case xq: