Fix lexing of U& sequences just before EOF.

tglsfdc · tglsfdc · commit 0c2338abbb17 · 2014-02-03T19:47:57.000-05:00
Commit a5ff502 was a brick shy of a load in the backend lexer too, not just psql. Per further testing of bug #9068. In passing, improve related comments.
diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
@@ -155,6 +155,9 @@ extern void core_yyset_column(int column_no, yyscan_t yyscanner);
  *  <xus> quoted string with Unicode escapes
  *  <xusend> end of a quoted string with Unicode escapes, UESCAPE can follow
  *  <xeu> Unicode surrogate pair in extended quoted string
+ *
+ * Remember to add an <<EOF>> case whenever you add a new exclusive state!
+ * The default one is probably not the right thing.
  */
 
 %x xb
@@ -545,12 +548,13 @@ other			.
 <xus>{quotefail} {
 					/* throw back all but the quote */
 					yyless(1);
-					/* handle possible UESCAPE in xusend mode */
+					/* xusend state looks for possible UESCAPE */
 					BEGIN(xusend);
 				}
-<xusend>{whitespace}
+<xusend>{whitespace} { /* stay in xusend state over whitespace */ }
 <xusend>{other} |
-<xusend>{xustop1} {
+<xusend>{xustop1} |
+<xusend><<EOF>>	{
 					/* no UESCAPE after the quote, throw back everything */
 					yyless(0);
 					BEGIN(INITIAL);
@@ -725,12 +729,13 @@ other			.
 				}
 <xui>{dquote} {
 					yyless(1);
-					/* handle possible UESCAPE in xuiend mode */
+					/* xuiend state looks for possible UESCAPE */
 					BEGIN(xuiend);
 				}
-<xuiend>{whitespace} { }
+<xuiend>{whitespace} { /* stay in xuiend state over whitespace */ }
 <xuiend>{other} |
-<xuiend>{xustop1} {
+<xuiend>{xustop1} |
+<xuiend><<EOF>>	{
 					/* no UESCAPE after the quote, throw back everything */
 					char		   *ident;
 
diff --git a/src/bin/psql/psqlscan.l b/src/bin/psql/psqlscan.l
@@ -166,7 +166,8 @@ static void escape_variable(bool as_ident);
  *  <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
+ *  <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
