From 68ac70bc7bf365fa17bd6d7ea597fa0a05488b8d Mon Sep 17 00:00:00 2001
From: Akim Demaille <akim@lrde.epita.fr>
Date: Fri, 23 Nov 2012 11:21:47 +0100
Subject: [PATCH] scanner: issue a single error for groups of invalid
 characters

* src/scan-gram.l: Scan groups of invalid characters together.
* tests/input.at, tests/named-refs.at: Adjust.
---
 src/scan-gram.l     | 22 ++++++++++++++--------
 tests/input.at      |  6 +-----
 tests/named-refs.at | 13 ++++---------
 3 files changed, 19 insertions(+), 22 deletions(-)

diff --git a/src/scan-gram.l b/src/scan-gram.l
index 8774dc0a..fd6458fa 100644
--- a/src/scan-gram.l
+++ b/src/scan-gram.l
@@ -103,9 +103,9 @@ static void unexpected_newline (boundary, char const *);
  /* Bracketed identifiers support. */
 %x SC_BRACKETED_ID SC_RETURN_BRACKETED_ID
 
-letter	  [.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]
+letter	   [.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]
+notletter [^.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]{-}[%\{]
 id	  {letter}({letter}|[-0-9])*
-directive %{id}
 int	  [0-9]+
 
 /* POSIX says that a tag must be both an id and a C union member, but
@@ -218,7 +218,7 @@ splice	 (\\[ \f\t\v]*\n)*
   "%verbose"                        return PERCENT_VERBOSE;
   "%yacc"                           return PERCENT_YACC;
 
-  {directive} {
+  "%"{id}|"%"{notletter}([[:graph:]])+ {
     complain_at (*loc, _("invalid directive: %s"), quote (yytext));
   }
 
@@ -290,8 +290,10 @@ splice	 (\\[ \f\t\v]*\n)*
     BEGIN SC_BRACKETED_ID;
   }
 
-  . {
-    complain_at (*loc, _("invalid character: %s"), quote_mem (yytext, yyleng));
+  [^\[%A-Za-z0-9_<>{}\"\'*;|=/, \f\n\t\v]+|. {
+    complain_at (*loc, "%s: %s",
+                 ngettext ("invalid character", "invalid characters", yyleng),
+                 quote_mem (yytext, yyleng));
   }
 
   <<EOF>> {
@@ -373,10 +375,14 @@ splice	 (\\[ \f\t\v]*\n)*
     else
       complain_at (*loc, _("an identifier expected"));
   }
-  . {
-    complain_at (*loc, _("invalid character in bracketed name: %s"),
-		 quote_mem (yytext, yyleng));
+
+  [^\].A-Za-z0-9_/ \f\n\t\v]+|. {
+    complain_at (*loc, "%s: %s",
+                 ngettext ("invalid character in bracketed name",
+                           "invalid characters in bracketed name", yyleng),
+                 quote_mem (yytext, yyleng));
   }
+
   <<EOF>> {
     BEGIN bracketed_id_context_state;
     unexpected_eof (bracketed_id_start, "]");
diff --git a/tests/input.at b/tests/input.at
index 35812c80..faa939c1 100644
--- a/tests/input.at
+++ b/tests/input.at
@@ -39,11 +39,7 @@ default: 'a' }
 AT_CHECK([[$PERL -pi -e 's/\\(\d{3})/chr(oct($1))/ge' input.y || exit 77]])
 
 AT_BISON_CHECK([input.y], [1], [],
-[[input.y:1.1: error: invalid character: '\0'
-input.y:1.1: error: invalid character: '\001'
-input.y:1.1: error: invalid character: '\002'
-input.y:1.1: error: invalid character: '\377'
-input.y:1.2: error: invalid character: '?'
+[[input.y:1.1-2: error: invalid characters: '\0\001\002\377?'
 input.y:3.1: error: invalid character: '?'
 input.y:4.14: error: invalid character: '}'
 input.y:5.1: error: invalid character: '%'
diff --git a/tests/named-refs.at b/tests/named-refs.at
index c8809c12..de48e0f7 100644
--- a/tests/named-refs.at
+++ b/tests/named-refs.at
@@ -443,19 +443,14 @@ AT_SETUP([Stray symbols in brackets])
 AT_DATA_GRAMMAR([test.y],
 [[
 %%
-start: foo[ /* aaa */ *&-.+\000\001\002\377 ] bar
+start: foo[ % /* aaa */ *&-.+\000\001\002\377 ] bar
   { s = $foo; }
 ]])
 AT_CHECK([[$PERL -pi -e 's/\\(\d{3})/chr(oct($1))/ge' test.y || exit 77]])
 AT_BISON_CHECK([-o test.c test.y], 1, [],
-[[test.y:11.23: error: invalid character in bracketed name: '*'
-test.y:11.24: error: invalid character in bracketed name: '&'
-test.y:11.25: error: invalid character in bracketed name: '-'
-test.y:11.27: error: invalid character in bracketed name: '+'
-test.y:11.28: error: invalid character in bracketed name: '\0'
-test.y:11.28: error: invalid character in bracketed name: '\001'
-test.y:11.28: error: invalid character in bracketed name: '\002'
-test.y:11.28: error: invalid character in bracketed name: '\377'
+[[test.y:11.13: error: invalid character in bracketed name: '%'
+test.y:11.25-27: error: invalid characters in bracketed name: '*&-'
+test.y:11.29-30: error: invalid characters in bracketed name: '+\0\001\002\377'
 ]])
 AT_CLEANUP
 
-- 
2.45.2