Fix complaints about escape sequences.

Discussed starting at
<http://lists.gnu.org/archive/html/bison-patches/2009-08/msg00036.html>.
* src/scan-gram.l (SC_ESCAPED_STRING, SC_ESCAPED_CHARACTER):
For a \0 and similar escape sequences meaning the null
character, report an invalid escape sequence instead of an
invalid null character because the latter does not actually
appear in the user's input.
In all escape sequence complaints, don't escape the initial
backslash, and don't quote when the sequence appears at the end
of the complaint line unless there's whitespace that quotearg
won't escape.
Consistently say "invalid" not "unrecognized".
Consistently prefer "empty character literal" over "extra
characters in character literal" warning for invalid escape
sequences; that is, consistently discard those sequences.
* tests/input.at (Bad escapes in literals): New.
(cherry picked from commit c2724603c9d87e816dbdf1a9bfd7d70ffc1bd137)

diff --git a/ChangeLog b/ChangeLog
index c7eb104311aa6bf1654e6a25a6e0e4d1c31cdd11..25762bc03673ebfdea77a305e77568ee995dbc99 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,23 @@
+2009-08-19  Joel E. Denny  <jdenny@clemson.edu>
+
+       Fix complaints about escape sequences.
+       Discussed starting at
+       <http://lists.gnu.org/archive/html/bison-patches/2009-08/msg00036.html>.
+       * src/scan-gram.l (SC_ESCAPED_STRING, SC_ESCAPED_CHARACTER):
+       For a \0 and similar escape sequences meaning the null
+       character, report an invalid escape sequence instead of an
+       invalid null character because the latter does not actually
+       appear in the user's input.
+       In all escape sequence complaints, don't escape the initial
+       backslash, and don't quote when the sequence appears at the end
+       of the complaint line unless there's whitespace that quotearg
+       won't escape.
+       Consistently say "invalid" not "unrecognized".
+       Consistently prefer "empty character literal" over "extra
+       characters in character literal" warning for invalid escape
+       sequences; that is, consistently discard those sequences.
+       * tests/input.at (Bad escapes in literals): New.
+
 2009-08-19  Akim Demaille  <demaille@gostai.com>
 
        doc: fixes.

diff --git a/src/scan-gram.l b/src/scan-gram.l
index 73eb3e800a983072fc8c122eea615423281c8875..9aec298e3ea44256cf19b05d2b0470cb3070410a 100644 (file)
--- a/src/scan-gram.l
+++ b/src/scan-gram.l
@@ -37,6 +37,7 @@
 #include "reader.h"
 #include "uniqstr.h"
 
+#include <ctype.h>
 #include <mbswidth.h>
 #include <quote.h>
 
@@ -521,10 +522,9 @@ splice      (\\[ \f\t\v]*\n)*
 {
   \\[0-7]{1,3} {
     unsigned long int c = strtoul (yytext + 1, NULL, 8);
-    if (UCHAR_MAX < c)
-      complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext));
-    else if (! c)
-      complain_at (*loc, _("invalid null character: %s"), quote (yytext));
+    if (!c || UCHAR_MAX < c)
+      complain_at (*loc, _("invalid number after \\-escape: %s"),
+                   yytext+1);
     else
       obstack_1grow (&obstack_for_string, c);
   }
@@ -532,10 +532,9 @@ splice      (\\[ \f\t\v]*\n)*
   \\x[0-9abcdefABCDEF]+ {
     verify (UCHAR_MAX < ULONG_MAX);
     unsigned long int c = strtoul (yytext + 2, NULL, 16);
-    if (UCHAR_MAX < c)
-      complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext));
-    else if (! c)
-      complain_at (*loc, _("invalid null character: %s"), quote (yytext));
+    if (!c || UCHAR_MAX < c)
+      complain_at (*loc, _("invalid number after \\-escape: %s"),
+                   yytext+1);
     else
       obstack_1grow (&obstack_for_string, c);
   }
@@ -553,16 +552,23 @@ splice     (\\[ \f\t\v]*\n)*
 
   \\(u|U[0-9abcdefABCDEF]{4})[0-9abcdefABCDEF]{4} {
     int c = convert_ucn_to_byte (yytext);
-    if (c < 0)
-      complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext));
-    else if (! c)
-      complain_at (*loc, _("invalid null character: %s"), quote (yytext));
+    if (c <= 0)
+      complain_at (*loc, _("invalid number after \\-escape: %s"),
+                   yytext+1);
     else
       obstack_1grow (&obstack_for_string, c);
   }
   \\(.|\n)     {
-    complain_at (*loc, _("unrecognized escape sequence: %s"), quote (yytext));
-    STRING_GROW;
+    char const *p = yytext + 1;
+    char quoted_ws[] = "` '";
+    if (isspace (*p) && isprint (*p))
+      {
+        quoted_ws[1] = *p;
+        p = quoted_ws;
+      }
+    else
+      p = quotearg_style_mem (escape_quoting_style, p, 1);
+    complain_at (*loc, _("invalid character after \\-escape: %s"), p);
   }
 }
 

diff --git a/tests/input.at b/tests/input.at
index 84f5a997532ce38e75bbc783008aba63c9771d83..0f3f8a383040ca636a1f67736c5b0a5ee242cc89 100644 (file)
--- a/tests/input.at
+++ b/tests/input.at
@@ -1214,3 +1214,46 @@ three.y:4.8-11: missing `'' at end of file
 ]])
 
 AT_CLEANUP
+
+## ------------------------- ##
+## Bad escapes in literals.  ##
+## ------------------------- ##
+
+AT_SETUP([[Bad escapes in literals]])
+
+AT_DATA([input.y],
+[[%%
+start: '\777' '\0' '\xfff' '\x0'
+       '\uffff' '\u0000' '\Uffffffff' '\U00000000'
+       '\ ' '\A';
+]])
+echo 'start: "\T\F\0\1" ;' | tr 'TF01' '\011\014\0\1' >> input.y
+
+AT_BISON_CHECK([input.y], [1], [],
+[[input.y:2.9-12: invalid number after \-escape: 777
+input.y:2.8-13: warning: empty character literal
+input.y:2.16-17: invalid number after \-escape: 0
+input.y:2.15-18: warning: empty character literal
+input.y:2.21-25: invalid number after \-escape: xfff
+input.y:2.20-26: warning: empty character literal
+input.y:2.29-31: invalid number after \-escape: x0
+input.y:2.28-32: warning: empty character literal
+input.y:3.9-14: invalid number after \-escape: uffff
+input.y:3.8-15: warning: empty character literal
+input.y:3.18-23: invalid number after \-escape: u0000
+input.y:3.17-24: warning: empty character literal
+input.y:3.27-36: invalid number after \-escape: Uffffffff
+input.y:3.26-37: warning: empty character literal
+input.y:3.40-49: invalid number after \-escape: U00000000
+input.y:3.39-50: warning: empty character literal
+input.y:4.9-10: invalid character after \-escape: ` '
+input.y:4.8-11: warning: empty character literal
+input.y:4.14-15: invalid character after \-escape: A
+input.y:4.13-16: warning: empty character literal
+input.y:5.9-16: invalid character after \-escape: \t
+input.y:5.17: invalid character after \-escape: \f
+input.y:5.18: invalid character after \-escape: \0
+input.y:5.19: invalid character after \-escape: \001
+]])
+
+AT_CLEANUP