# Checking the Bison scanner. -*- Autotest -*-
-# Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007 Free Software Foundation,
-# Inc.
+# Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009
+# Free Software Foundation, Inc.
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# _AT_UNUSED_VALUES_DECLARATIONS()
-# --------------------------------------------
+# --------------------------------
# Generate the token, type, and destructor
# declarations for the unused values tests.
-
m4_define([_AT_UNUSED_VALUES_DECLARATIONS],
[[[%token <integer> INT;
%type <integer> a b c d e f g h i j k l;
# AT_CHECK_UNUSED_VALUES(DECLARATIONS_AFTER, CHECK_MIDRULE_VALUES)
-# ------------------------------------------------------------------
-# Generate a grammar to test unused values,
-# compile it, run it. If DECLARATIONS_AFTER
-# is set, then the token, type, and destructor
-# declarations are generated after the rules
-# rather than before. If CHECK_MIDRULE_VALUES
-# is set, then --warnings=midrule-values is
-# set.
-
+# ----------------------------------------------------------------
+# Generate a grammar to test unused values, compile it, run it. If
+# DECLARATIONS_AFTER is set, then the token, type, and destructor
+# declarations are generated after the rules rather than before. If
+# CHECK_MIDRULE_VALUES is set, then --warnings=midrule-values is set.
m4_define([AT_CHECK_UNUSED_VALUES],
[AT_DATA([input.y],
m4_ifval($1, [
], [_AT_UNUSED_VALUES_DECLARATIONS
])[[%%
start:
- 'a' a { $]2[ } | 'b' b { $]2[ } | 'c' c { $]2[ } | 'd' d { $]2[ } | 'e' e { $]2[ }
-| 'f' f { $]2[ } | 'g' g { $]2[ } | 'h' h { $]2[ } | 'i' i { $]2[ } | 'j' j { $]2[ }
-| 'k' k { $]2[ } | 'l' l { $]2[ }
+ 'a' a { $]2[; } | 'b' b { $]2[; } | 'c' c { $]2[; } | 'd' d { $]2[; }
+| 'e' e { $]2[; } | 'f' f { $]2[; } | 'g' g { $]2[; } | 'h' h { $]2[; }
+| 'i' i { $]2[; } | 'j' j { $]2[; } | 'k' k { $]2[; } | 'l' l { $]2[; }
;
a: INT | INT { } INT { } INT { };
b: INT | /* empty */;
-c: INT | INT { $]1[ } INT { $<integer>2 } INT { $<integer>4 };
-d: INT | INT { } INT { $]1[ } INT { $<integer>2 };
-e: INT | INT { } INT { } INT { $]1[ };
+c: INT | INT { $]1[; } INT { $<integer>2; } INT { $<integer>4; };
+d: INT | INT { } INT { $]1[; } INT { $<integer>2; };
+e: INT | INT { } INT { } INT { $]1[; };
f: INT | INT { } INT { } INT { $]$[ = $]1[ + $]3[ + $]5[; };
g: INT | INT { $<integer>$; } INT { $<integer>$; } INT { };
h: INT | INT { $<integer>$; } INT { $<integer>$ = $<integer>2; } INT { };
input.y:11.10-32: warning: unused value: $]3[
input.y:11.10-32: warning: unused value: $]5[
input.y:12.9: warning: empty rule for typed nonterminal, and no action
-]]m4_ifval($2, [[[input.y:13.14-19: warning: unset value: $$
-input.y:13.25-39: warning: unset value: $$
-]]])[[input.y:13.10-59: warning: unset value: $]$[
-input.y:13.10-59: warning: unused value: $]3[
-input.y:13.10-59: warning: unused value: $]5[
+]]m4_ifval($2, [[[input.y:13.14-20: warning: unset value: $$
+input.y:13.26-41: warning: unset value: $$
+]]])[[input.y:13.10-62: warning: unset value: $]$[
+input.y:13.10-62: warning: unused value: $]3[
+input.y:13.10-62: warning: unused value: $]5[
]]m4_ifval($2, [[[input.y:14.14-16: warning: unset value: $$
-]]])[[input.y:14.10-47: warning: unset value: $]$[
-input.y:14.10-47: warning: unused value: $]3[
-input.y:14.10-47: warning: unused value: $]5[
-input.y:15.10-36: warning: unset value: $]$[
-input.y:15.10-36: warning: unused value: $]3[
-input.y:15.10-36: warning: unused value: $]5[
+]]])[[input.y:14.10-49: warning: unset value: $]$[
+input.y:14.10-49: warning: unused value: $]3[
+input.y:14.10-49: warning: unused value: $]5[
+input.y:15.10-37: warning: unset value: $]$[
+input.y:15.10-37: warning: unused value: $]3[
+input.y:15.10-37: warning: unused value: $]5[
input.y:17.10-58: warning: unset value: $]$[
input.y:17.10-58: warning: unused value: $]1[
]]m4_ifval($2, [[[input.y:17.10-58: warning: unused value: $]2[
AT_SETUP([String aliases for character tokens])
-# Bison once thought a character token and its alias were different symbols
-# with the same user token number.
+# Bison once thought a character token and its alias were different
+# symbols with the same user token number.
AT_DATA_GRAMMAR([input.y],
[[%token 'a' "a"
AT_CLEANUP
+## -------------- ##
+## Symbol names. ##
+## -------------- ##
+
+AT_SETUP([Symbols])
+
+AT_DATA_GRAMMAR([input.y],
+[[%token WITH-DASH
+%token WITHOUT_DASH "WITHOUT-DASH"
+%token WITH.PERIOD
+%token WITHOUT_PERIOD "WITHOUT.PERIOD"
+%code {
+ void yyerror (char const *);
+ int yylex (void);
+}
+%%
+start: with-dash without_dash with.period without_period;
+with-dash: WITH-DASH;
+without_dash: "WITHOUT-DASH";
+with.period: WITH.PERIOD;
+without_period: "WITHOUT.PERIOD";
+%%
+]])
+
+# POSIX Yacc accept periods, but not dashes.
+AT_BISON_CHECK([--yacc input.y], [1], [],
+[[input.y:9.8-16: POSIX Yacc forbids dashes in symbol names: WITH-DASH
+input.y:18.8-16: POSIX Yacc forbids dashes in symbol names: with-dash
+]])
+
+# So warn about them.
+AT_BISON_CHECK([-Wyacc input.y], [], [],
+[[input.y:9.8-16: warning: POSIX Yacc forbids dashes in symbol names: WITH-DASH
+input.y:18.8-16: warning: POSIX Yacc forbids dashes in symbol names: with-dash
+]])
+
+# Dashes are fine for GNU Bison.
+AT_BISON_CHECK([-o input.c input.y])
+
+# Make sure we don't export silly token identifiers with periods or dashes.
+AT_COMPILE([input.o], [-c input.c])
+
+
+# Periods and dashes are genuine letters, they can start identifiers.
+# Digits cannot.
+AT_DATA_GRAMMAR([input.y],
+[[%token .GOOD
+ -GOOD
+ 1NV4L1D
+%%
+start: .GOOD -GOOD
+]])
+AT_BISON_CHECK([-o input.c input.y], [1], [],
+[[input.y:11.10-16: invalid identifier: `1NV4L1D'
+]])
+
+AT_CLEANUP
+
+
+## ----------------- ##
+## Numbered tokens. ##
+## ----------------- ##
+
+AT_SETUP([Numbered tokens])
+
+AT_DATA_GRAMMAR([redecl.y],
+[[%token DECIMAL_1 11259375
+ HEXADECIMAL_1 0xabcdef
+ HEXADECIMAL_2 0xFEDCBA
+ DECIMAL_2 16702650
+%%
+start: DECIMAL_1 HEXADECIMAL_2;
+]])
+
+AT_BISON_CHECK([redecl.y], [1], [],
+[[redecl.y:10.10-22: user token number 11259375 redeclaration for HEXADECIMAL_1
+redecl.y:9.8-16: previous declaration for DECIMAL_1
+redecl.y:12.10-18: user token number 16702650 redeclaration for DECIMAL_2
+redecl.y:11.10-22: previous declaration for HEXADECIMAL_2
+]])
+
+AT_DATA_GRAMMAR([too-large.y],
+[[%token TOO_LARGE_DEC 999999999999999999999
+ TOO_LARGE_HEX 0xFFFFFFFFFFFFFFFFFFF
+%%
+start: TOO_LARGE_DEC TOO_LARGE_HEX
+%%
+]])
+
+AT_BISON_CHECK([too-large.y], [1], [],
+[[too-large.y:9.22-42: integer out of range: `999999999999999999999'
+too-large.y:10.24-44: integer out of range: `0xFFFFFFFFFFFFFFFFFFF'
+]])
+
+AT_CLEANUP
+
+
## --------------------- ##
## Unclosed constructs. ##
## --------------------- ##
AT_SETUP([Unclosed constructs])
-# Bison's scan-gram.l once forgot to STRING_FINISH some unclosed constructs, so
-# they were prepended to whatever it STRING_GROW'ed next. It also threw them
-# away rather than returning them to the parser. The effect was confusing
-# subsequent error messages.
+# Bison's scan-gram.l once forgot to STRING_FINISH some unclosed
+# constructs, so they were prepended to whatever it STRING_GROW'ed
+# next. It also threw them away rather than returning them to the
+# parser. The effect was confusing subsequent error messages.
AT_DATA([input.y],
[[%token A "a
AT_SETUP([%start after first rule])
-# Bison once complained that a %start after the first rule was a redeclaration
-# of the start symbol.
+# Bison once complained that a %start after the first rule was a
+# redeclaration of the start symbol.
AT_DATA([input.y],
[[%%
AT_SETUP([%define errors])
-AT_DATA([input.y],
+AT_DATA([input-redefined.y],
[[%define var "value1"
%define var "value1"
%define var "value2"
start: ;
]])
-AT_BISON_CHECK([[input.y]], [0], [],
-[[input.y:2.9-11: warning: %define variable `var' redefined
-input.y:1.9-11: warning: previous definition
-input.y:3.10-12: warning: %define variable `var' redefined
-input.y:2.9-11: warning: previous definition
-input.y:1.9-11: warning: %define variable `var' is not used
-input.y:2.9-11: warning: %define variable `var' is not used
-input.y:3.10-12: warning: %define variable `var' is not used
-input.y:4.9-16: warning: %define variable `special1' is not used
-input.y:5.9-16: warning: %define variable `special2' is not used
+AT_BISON_CHECK([[input-redefined.y]], [[1]], [],
+[[input-redefined.y:2.9-11: %define variable `var' redefined
+input-redefined.y:1.9-11: previous definition
+input-redefined.y:3.10-12: %define variable `var' redefined
+input-redefined.y:2.9-11: previous definition
+]])
+
+AT_DATA([input-unused.y],
+[[%define var "value"
+%%
+start: ;
+]])
+
+AT_BISON_CHECK([[input-unused.y]], [[0]], [],
+[[input-unused.y:1.9-11: warning: %define variable `var' is not used
+]])
+
+AT_CLEANUP
+
+
+## ----------------------------------- ##
+## %define, --define, --force-define. ##
+## ----------------------------------- ##
+
+AT_SETUP([%define, --define, --force-define])
+
+AT_DATA([skel.c],
+[[m4@&t@_divert_push(0)@
+@output(b4_parser_file_name@)@
+[var-dd: ]b4_percent_define_get([[var-dd]])[
+var-ff: ]b4_percent_define_get([[var-ff]])[
+var-dfg: ]b4_percent_define_get([[var-dfg]])[
+var-fd: ]b4_percent_define_get([[var-fd]])
+m4@&t@_divert_pop(0)
+]])
+
+AT_DATA([input.y],
+[[%define var-dfg "gram"
+%%
+start: ;
+]])
+
+AT_BISON_CHECK([[-Dvar-dd=cmd-d1 -Dvar-dd=cmd-d2 \
+ -Fvar-ff=cmd-f1 -Fvar-ff=cmd-f2 \
+ -Dvar-dfg=cmd-d -Fvar-dfg=cmd-f \
+ -Fvar-fd=cmd-f -Dvar-fd=cmd-d \
+ -Dunused-d -Funused-f \
+ --skeleton ./skel.c input.y]], [[0]], [],
+[[<command line>:10: warning: %define variable `unused-d' is not used
+<command line>:11: warning: %define variable `unused-f' is not used
+]])
+
+AT_CHECK([[cat input.tab.c]], [[0]],
+[[var-dd: cmd-d2
+var-ff: cmd-f2
+var-dfg: cmd-f
+var-fd: cmd-d
+]])
+
+AT_DATA([input-dg.y],
+[[%define var "gram"
+%%
+start: ;
+]])
+
+AT_BISON_CHECK([[-Dvar=cmd-d input-dg.y]], [[1]], [],
+[[input-dg.y:1.9-11: %define variable `var' redefined
+<command line>:2: previous definition
]])
AT_CLEANUP
AT_SETUP([[%define enum variables]])
+# Front-end.
+AT_DATA([[input.y]],
+[[%define lr.default-reductions "bogus"
+%%
+start: ;
+]])
+AT_BISON_CHECK([[input.y]], [[1]], [[]],
+[[input.y:1.9-29: invalid value for %define variable `lr.default-reductions': `bogus'
+input.y:1.9-29: accepted value: `all'
+input.y:1.9-29: accepted value: `consistent'
+input.y:1.9-29: accepted value: `accepting'
+]])
+
+# Back-end.
+AT_DATA([[input.y]],
+[[%define api.push-pull "neither"
+%%
+start: ;
+]])
+AT_BISON_CHECK([[input.y]], [1], [],
+[[input.y:1.9-21: invalid value for %define variable `api.push-pull': `neither'
+input.y:1.9-21: accepted value: `pull'
+input.y:1.9-21: accepted value: `push'
+input.y:1.9-21: accepted value: `both'
+]])
+
+AT_CLEANUP
+
+## -------------------------------- ##
+## %define backward compatibility. ##
+## -------------------------------- ##
+
+AT_SETUP([[%define backward compatibility]])
+
+# The error messages tell us whether underscores in these variables are
+# being converted to dashes.
+
AT_DATA([[input.y]],
[[%define api.push_pull "neither"
%%
start: ;
]])
+AT_BISON_CHECK([[input.y]], [1], [],
+[[input.y:1.9-21: invalid value for %define variable `api.push-pull': `neither'
+input.y:1.9-21: accepted value: `pull'
+input.y:1.9-21: accepted value: `push'
+input.y:1.9-21: accepted value: `both'
+]])
+AT_DATA([[input.y]],
+[[%define lr.keep_unreachable_states "maybe"
+%%
+start: ;
+]])
AT_BISON_CHECK([[input.y]], [1], [],
-[[input.y:1.9-21: invalid value for %define variable `api.push_pull': `neither'
+[[input.y:1.9-34: invalid value for %define Boolean variable `lr.keep-unreachable-states'
+]])
+
+AT_DATA([[input.y]],
+[[%define namespace "foo"
+%define api.namespace "foo"
+%%
+start: ;
+]])
+AT_BISON_CHECK([[input.y]], [1], [],
+[[input.y:2.9-21: %define variable `api.namespace' redefined
+input.y:1.9-17: previous definition
+]])
+
+AT_DATA([[input.y]],
+[[%define foo_bar "baz"
+%%
+start: ;
+]])
+AT_BISON_CHECK([[input.y]], [0], [],
+[[input.y:1.9-15: warning: %define variable `foo_bar' is not used
]])
AT_CLEANUP
AT_DATA([[input.y]],
[[%language "C++"
%defines
-%define namespace "]$1["
+%define api.namespace "]$1["
%%
start: ;
]])
AT_BISON_CHECK([[input.y]], [1], [],
[m4_foreach([b4_arg], m4_dquote(m4_shift($@)),
-[[input.y:3.9-17: ]b4_arg[
+[[input.y:3.9-21: ]b4_arg[
]])])
])
[[namespace reference has a trailing "::"]])
AT_CLEANUP
+
+## ------------------------ ##
+## Bad character literals. ##
+## ------------------------ ##
+
+# Bison used to accept character literals that were empty or contained
+# too many characters.
+
+# FIXME: $ECHO_N and $ECHO_C are not very portable according to the
+# Autoconf manual. Switch to AS_ECHO_N when Autoconf 2.64 is released?
+# Even better, AT_DATA or some variant of AT_DATA may eventually permit
+# a trailing newline. See the threads starting at
+# <http://lists.gnu.org/archive/html/bison-patches/2009-07/msg00019.html>.
+
+AT_SETUP([[Bad character literals]])
+
+AT_DATA([empty.y],
+[[%%
+start: '';
+start: '
+]])
+echo $ECHO_N "start: '$ECHO_C" >> empty.y
+
+AT_BISON_CHECK([empty.y], [1], [],
+[[empty.y:2.8-9: warning: empty character literal
+empty.y:3.8-4.0: warning: empty character literal
+empty.y:3.8-4.0: missing `'' at end of line
+empty.y:4.8: warning: empty character literal
+empty.y:4.8: missing `'' at end of file
+]])
+
+AT_DATA([two.y],
+[[%%
+start: 'ab';
+start: 'ab
+]])
+echo $ECHO_N "start: 'ab$ECHO_C" >> two.y
+
+AT_BISON_CHECK([two.y], [1], [],
+[[two.y:2.8-11: warning: extra characters in character literal
+two.y:3.8-4.0: warning: extra characters in character literal
+two.y:3.8-4.0: missing `'' at end of line
+two.y:4.8-10: warning: extra characters in character literal
+two.y:4.8-10: missing `'' at end of file
+]])
+
+AT_DATA([three.y],
+[[%%
+start: 'abc';
+start: 'abc
+]])
+echo $ECHO_N "start: 'abc$ECHO_C" >> three.y
+
+AT_BISON_CHECK([three.y], [1], [],
+[[three.y:2.8-12: warning: extra characters in character literal
+three.y:3.8-4.0: warning: extra characters in character literal
+three.y:3.8-4.0: missing `'' at end of line
+three.y:4.8-11: warning: extra characters in character literal
+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';
+]])
+
+# It is not easy to create special characters, we can only trust tr.
+# Beside we cannot even expect "echo '\0'" to output two characters
+# (well three with \n): at least Bash 3.2 converts the two-character
+# sequence "\0" into a single NUL character.
+#
+# Z for 0, O for 1.
+echo 'start: "\T\F\Z\O" ;' | tr 'TFZO' '\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
projects / bison.git / blobdiff