Fix ecpg bugs caused by missing semicolons in the backend grammar.

tglsfdc · tglsfdc · commit 53c2bb78db9f · 2019-02-24T12:51:51.000-05:00
The Bison documentation clearly states that a semicolon is required after every grammar rule, and our scripts that generate ecpg's grammar from the backend's implicitly assumed this is true. But it turns out that only ancient versions of Bison actually enforce that. There have been a couple of rules without trailing semicolons in gram.y for some time, and as a consequence, ecpg's grammar was faulty and produced wrong output for the affected statements. To fix, add the missing semis, and add some cross-checks to ecpg's scripts so that they'll bleat if we mess this up again. The cases that were broken were: * "SET variable = DEFAULT" (but not "SET variable TO DEFAULT"), as well as allied syntaxes such as ALTER SYSTEM SET ... DEFAULT. These produced syntactically invalid output that the server would reject. * Multiple type names in DROP TYPE/DOMAIN commands. Only the first type name would be listed in the emitted command. Per report from Daisuke Higuchi. Back-patch to all supported versions. Discussion: https://postgr.es/m/1803D792815FC24D871C00D17AE95905DB51CE@g01jpexmbkw24
diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
@@ -1377,6 +1377,7 @@ generic_set:
 					n->name = $1;
 					$$ = n;
 				}
+		;
 
 set_rest_more:	/* Generic SET syntaxes: */
 			generic_set 						{$$ = $1;}
diff --git a/src/interfaces/ecpg/preproc/check_rules.pl b/src/interfaces/ecpg/preproc/check_rules.pl
@@ -1,7 +1,7 @@
 #!/usr/bin/perl
 # src/interfaces/ecpg/preproc/check_rules.pl
-# test parser generater for ecpg
-# call with backend parser as stdin
+# test parser generator for ecpg
+# call with backend grammar as stdin
 #
 # Copyright (c) 2009-2014, PostgreSQL Global Development Group
 #
@@ -47,6 +47,7 @@
 
 my $block        = '';
 my $yaccmode     = 0;
+my $in_rule      = 0;
 my $brace_indent = 0;
 my (@arr, %found);
 my $comment     = 0;
@@ -131,10 +132,14 @@
 			$found{$block} = 1;
 			$cc++;
 			$block = '';
+			$in_rule = 0 if $arr[$fieldIndexer] eq ';';
 		}
 		elsif (($arr[$fieldIndexer] =~ '[A-Za-z0-9]+:')
 			|| $arr[ $fieldIndexer + 1 ] eq ':')
 		{
+			die "unterminated rule at grammar line $.\n"
+			  if $in_rule;
+			$in_rule     = 1;
 			$non_term_id = $arr[$fieldIndexer];
 			$non_term_id =~ tr/://d;
 		}
@@ -145,6 +150,9 @@
 	}
 }
 
+die "unterminated rule at end of grammar\n"
+  if $in_rule;
+
 close GRAM;
 if ($verbose)
 {
diff --git a/src/interfaces/ecpg/preproc/parse.pl b/src/interfaces/ecpg/preproc/parse.pl
@@ -22,6 +22,7 @@
 my $copymode              = 0;
 my $brace_indent          = 0;
 my $yaccmode              = 0;
+my $in_rule               = 0;
 my $header_included       = 0;
 my $feature_not_supported = 0;
 my $tokenmode             = 0;
@@ -285,6 +286,7 @@ sub main
 				@fields  = ();
 				$infield = 0;
 				$line    = '';
+				$in_rule = 0;
 				next;
 			}
 
@@ -362,6 +364,9 @@ sub main
 				$line    = '';
 				@fields  = ();
 				$infield = 1;
+				die "unterminated rule at grammar line $.\n"
+				  if $in_rule;
+				$in_rule = 1;
 				next;
 			}
 			elsif ($copymode)
@@ -412,6 +417,9 @@ sub main
 			}
 		}
 	}
+	die "unterminated rule at end of grammar\n"
+	  if $in_rule;
+	return;
 }
 
 

Original file line number	Diff line number	Diff line change
`@@ -1377,6 +1377,7 @@ generic_set:`
`1377`	`1377`	`n->name = $1;`
`1378`	`1378`	`$$ = n;`
`1379`	`1379`	`}`
	`1380`	`+ ;`
`1380`	`1381`
`1381`	`1382`	`set_rest_more: /* Generic SET syntaxes: */`
`1382`	`1383`	`generic_set {$$ = $1;}`
Original file line number	Diff line number	Diff line change
`@@ -1,7 +1,7 @@`
`1`	`1`	`#!/usr/bin/perl`
`2`	`2`	`# src/interfaces/ecpg/preproc/check_rules.pl`
`3`		`-# test parser generater for ecpg`
`4`		`-# call with backend parser as stdin`
	`3`	`+# test parser generator for ecpg`
	`4`	`+# call with backend grammar as stdin`
`5`	`5`	`#`
`6`	`6`	`# Copyright (c) 2009-2014, PostgreSQL Global Development Group`
`7`	`7`	`#`
`@@ -47,6 +47,7 @@`
`47`	`47`
`48`	`48`	`my $block = '';`
`49`	`49`	`my $yaccmode = 0;`
	`50`	`+my $in_rule = 0;`
`50`	`51`	`my $brace_indent = 0;`
`51`	`52`	`my (@arr, %found);`
`52`	`53`	`my $comment = 0;`
`@@ -131,10 +132,14 @@`
`131`	`132`	`$found{$block} = 1;`
`132`	`133`	`$cc++;`
`133`	`134`	`$block = '';`
	`135`	`+ $in_rule = 0 if $arr[$fieldIndexer] eq ';';`
`134`	`136`	`}`
`135`	`137`	`elsif (($arr[$fieldIndexer] =~ '[A-Za-z0-9]+:')`
`136`	`138`	`\|\| $arr[ $fieldIndexer + 1 ] eq ':')`
`137`	`139`	`{`
	`140`	`+ die "unterminated rule at grammar line $.\n"`
	`141`	`+ if $in_rule;`
	`142`	`+ $in_rule = 1;`
`138`	`143`	`$non_term_id = $arr[$fieldIndexer];`
`139`	`144`	`$non_term_id =~ tr/://d;`
`140`	`145`	`}`
`@@ -145,6 +150,9 @@`
`145`	`150`	`}`
`146`	`151`	`}`
`147`	`152`
	`153`	`+die "unterminated rule at end of grammar\n"`
	`154`	`+ if $in_rule;`
	`155`	`+`
`148`	`156`	`close GRAM;`
`149`	`157`	`if ($verbose)`
`150`	`158`	`{`
Original file line number	Diff line number	Diff line change
`@@ -22,6 +22,7 @@`
`22`	`22`	`my $copymode = 0;`
`23`	`23`	`my $brace_indent = 0;`
`24`	`24`	`my $yaccmode = 0;`
	`25`	`+my $in_rule = 0;`
`25`	`26`	`my $header_included = 0;`
`26`	`27`	`my $feature_not_supported = 0;`
`27`	`28`	`my $tokenmode = 0;`
`@@ -285,6 +286,7 @@ sub main`
`285`	`286`	`@fields = ();`
`286`	`287`	`$infield = 0;`
`287`	`288`	`$line = '';`
	`289`	`+ $in_rule = 0;`
`288`	`290`	`next;`
`289`	`291`	`}`
`290`	`292`
`@@ -362,6 +364,9 @@ sub main`
`362`	`364`	`$line = '';`
`363`	`365`	`@fields = ();`
`364`	`366`	`$infield = 1;`
	`367`	`+ die "unterminated rule at grammar line $.\n"`
	`368`	`+ if $in_rule;`
	`369`	`+ $in_rule = 1;`
`365`	`370`	`next;`
`366`	`371`	`}`
`367`	`372`	`elsif ($copymode)`
`@@ -412,6 +417,9 @@ sub main`
`412`	`417`	`}`
`413`	`418`	`}`
`414`	`419`	`}`
	`420`	`+ die "unterminated rule at end of grammar\n"`
	`421`	`+ if $in_rule;`
	`422`	`+ return;`
`415`	`423`	`}`
`416`	`424`
`417`	`425`