From eb8c66bbda06f71d107e2780503f2de9ba814ddd Mon Sep 17 00:00:00 2001 From: "Joel E. Denny" Date: Sat, 29 Jan 2011 12:54:28 -0500 Subject: [PATCH] Do not allow identifiers that start with a dash. This cleans up our previous fixes for a bug whereby Bison discarded `.field' in `$-1.field'. The previous fixes were less restrictive about where a dash could appear in an identifier, but the restrictions were hard to explain. That bug was reported and this final fix was originally suggested by Paul Hilfinger. This also fixes a remaining bug reported by Paul Eggert whereby Bison parses `%token ID -123' as `%token ID - 123' and handles `-' as an identifier. Now, `-' cannot be an identifier. Discussed in threads beginning at , . * NEWS (2.5): Update entry describing the dash extension to grammar symbol names. Also, move that entry before the named references entry because the latter mentions the former. * doc/bison.texinfo (Symbol): Update documentation for symbol names. As suggested by Paul Eggert, mention the effect of periods and dashes on named references. (Decl Summary): Update documentation for unquoted %define values, which, as a side effect, can no longer start with dashes either. * src/scan-code.l (id): Implement. * src/scan-gram.l (id): Implement. * tests/actions.at (Exotic Dollars): Extend test group to exercise bug reported by Paul Hilfinger. * tests/input.at (Symbols): Update test group, and extend to exercise bug reported by Paul Eggert. * tests/named-refs.at (Stray symbols in brackets): Update test group. ($ or @ followed by . or -): Likewise. * tests/regression.at (Invalid inputs): Likewise. (cherry picked from commit 82f3355eaf8d5988391021262dc9acfa6485c098) --- ChangeLog | 33 ++++++++++++++++++++++++++++++++ NEWS | 16 ++++++++-------- doc/bison.texinfo | 18 +++++++++--------- src/scan-code.l | 2 +- src/scan-gram.l | 2 +- tests/actions.at | 46 +++++++++++++++++++++++++++++++++++++++++++++ tests/input.at | 11 +++++++---- tests/named-refs.at | 27 +++++++++++++++----------- tests/regression.at | 3 ++- 9 files changed, 123 insertions(+), 35 deletions(-) diff --git a/ChangeLog b/ChangeLog index f987a067..1dacd346 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,36 @@ +2011-01-29 Joel E. Denny + + Do not allow identifiers that start with a dash. + This cleans up our previous fixes for a bug whereby Bison + discarded `.field' in `$-1.field'. The previous fixes were less + restrictive about where a dash could appear in an identifier, but + the restrictions were hard to explain. That bug was reported and + this final fix was originally suggested by Paul Hilfinger. This + also fixes a remaining bug reported by Paul Eggert whereby Bison + parses `%token ID -123' as `%token ID - 123' and handles `-' as an + identifier. Now, `-' cannot be an identifier. Discussed in + threads beginning at + , + . + * NEWS (2.5): Update entry describing the dash extension to + grammar symbol names. Also, move that entry before the named + references entry because the latter mentions the former. + * doc/bison.texinfo (Symbol): Update documentation for symbol + names. As suggested by Paul Eggert, mention the effect of periods + and dashes on named references. + (Decl Summary): Update documentation for unquoted %define values, + which, as a side effect, can no longer start with dashes either. + * src/scan-code.l (id): Implement. + * src/scan-gram.l (id): Implement. + * tests/actions.at (Exotic Dollars): Extend test group to exercise + bug reported by Paul Hilfinger. + * tests/input.at (Symbols): Update test group, and extend to + exercise bug reported by Paul Eggert. + * tests/named-refs.at (Stray symbols in brackets): Update test + group. + ($ or @ followed by . or -): Likewise. + * tests/regression.at (Invalid inputs): Likewise. + 2011-01-24 Joel E. Denny * data/yacc.c: Fix last apostrophe warning from xgettext. diff --git a/NEWS b/NEWS index be986bbc..88ec95cc 100644 --- a/NEWS +++ b/NEWS @@ -3,6 +3,14 @@ Bison News * Changes in version 2.5 (????-??-??): +** Grammar symbol names can now contain non-initial dashes: + + Consistently with directives (such as %error-verbose) and with + %define variables (e.g. push-pull), grammar symbol names may contain + dashes in any position except the beginning. This is a GNU + extension over POSIX Yacc. Thus, use of this extension is reported + by -Wyacc and rejected in Yacc mode (--yacc). + ** Named references: Historically, Yacc and Bison have supported positional references @@ -98,14 +106,6 @@ Bison News LAC is an experimental feature. More user feedback will help to stabilize it. -** Grammar symbol names can now contain dashes: - - Consistently with directives (such as %error-verbose) and variables - (e.g. push-pull), grammar symbol names may include dashes in any - position, similarly to periods and underscores. This is GNU - extension over POSIX Yacc whose use is reported by -Wyacc, and - rejected in Yacc mode (--yacc). - ** %define improvements: *** Can now be invoked via the command line: diff --git a/doc/bison.texinfo b/doc/bison.texinfo index dfd3a140..eb80f00b 100644 --- a/doc/bison.texinfo +++ b/doc/bison.texinfo @@ -3049,12 +3049,13 @@ A @dfn{nonterminal symbol} stands for a class of syntactically equivalent groupings. The symbol name is used in writing grammar rules. By convention, it should be all lower case. -Symbol names can contain letters, underscores, periods, dashes, and (not -at the beginning) digits. Dashes in symbol names are a GNU -extension, incompatible with POSIX Yacc. Terminal symbols -that contain periods or dashes make little sense: since they are not -valid symbols (in most programming languages) they are not exported as -token names. +Symbol names can contain letters, underscores, periods, and non-initial +digits and dashes. Dashes in symbol names are a GNU extension, incompatible +with POSIX Yacc. Periods and dashes make symbol names less convenient to +use with named references, which require brackets around such names +(@pxref{Named References}). Terminal symbols that contain periods or dashes +make little sense: since they are not valid symbols (in most programming +languages) they are not exported as token names. There are three ways of writing terminal symbols in the grammar: @@ -4959,9 +4960,8 @@ Define a variable to adjust Bison's behavior. It is an error if a @var{variable} is defined by @code{%define} multiple times, but see @ref{Bison Options,,-D @var{name}[=@var{value}]}. -@var{value} must be placed in quotation marks if it contains any -character other than a letter, underscore, period, dash, or non-initial -digit. +@var{value} must be placed in quotation marks if it contains any character +other than a letter, underscore, period, or non-initial dash or digit. Omitting @code{"@var{value}"} entirely is always equivalent to specifying @code{""}. diff --git a/src/scan-code.l b/src/scan-code.l index 0158e7c0..c13f8805 100644 --- a/src/scan-code.l +++ b/src/scan-code.l @@ -85,7 +85,7 @@ splice (\\[ \f\t\v]*\n)* named symbol references. Shall be kept synchronized with scan-gram.l "letter" and "id". */ letter [.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_] -id -*(-|{letter}({letter}|[-0-9])*) +id {letter}({letter}|[-0-9])* ref -?[0-9]+|{id}|"["{id}"]"|"$" %% diff --git a/src/scan-gram.l b/src/scan-gram.l index e1bda045..2f264f5f 100644 --- a/src/scan-gram.l +++ b/src/scan-gram.l @@ -104,7 +104,7 @@ static void unexpected_newline (boundary, char const *); %x SC_BRACKETED_ID SC_RETURN_BRACKETED_ID letter [.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_] -id -*(-|{letter}({letter}|[-0-9])*) +id {letter}({letter}|[-0-9])* directive %{id} int [0-9]+ diff --git a/tests/actions.at b/tests/actions.at index c2307cde..37616506 100644 --- a/tests/actions.at +++ b/tests/actions.at @@ -158,6 +158,52 @@ AT_PARSER_CHECK([./input], 0, [[15 ]]) +# Make sure that fields after $n or $-n are parsed correctly. At one +# point while implementing dashes in symbol names, we were dropping +# fields after $-n. +AT_DATA_GRAMMAR([[input.y]], +[[ +%{ +# include + static int yylex (void); + static void yyerror (char const *msg); + typedef struct { int val; } stype; +# define YYSTYPE stype +%} + +%% +start: one two { $$.val = $1.val + $2.val; } sum ; +one: { $$.val = 1; } ; +two: { $$.val = 2; } ; +sum: { printf ("%d\n", $0.val + $-1.val + $-2.val); } ; + +%% + +static int +yylex (void) +{ + return 0; +} + +static void +yyerror (char const *msg) +{ + fprintf (stderr, "%s\n", msg); +} + +int +main (void) +{ + return yyparse (); +} +]]) + +AT_BISON_CHECK([[-o input.c input.y]]) +AT_COMPILE([[input]]) +AT_PARSER_CHECK([[./input]], [[0]], +[[6 +]]) + AT_CLEANUP diff --git a/tests/input.at b/tests/input.at index 9aef0d7c..90b6b0b1 100644 --- a/tests/input.at +++ b/tests/input.at @@ -658,17 +658,20 @@ AT_BISON_CHECK([-o input.c input.y]) AT_COMPILE([input.o], [-c input.c]) -# Periods and dashes are genuine letters, they can start identifiers. -# Digits cannot. +# Periods are genuine letters, they can start identifiers. +# Digits and dashes cannot. AT_DATA_GRAMMAR([input.y], [[%token .GOOD -GOOD 1NV4L1D + -123 %% -start: .GOOD -GOOD +start: .GOOD GOOD ]]) AT_BISON_CHECK([-o input.c input.y], [1], [], -[[input.y:11.10-16: invalid identifier: `1NV4L1D' +[[input.y:10.10: invalid character: `-' +input.y:11.10-16: invalid identifier: `1NV4L1D' +input.y:12.10: invalid character: `-' ]]) AT_CLEANUP diff --git a/tests/named-refs.at b/tests/named-refs.at index f818e094..21473148 100644 --- a/tests/named-refs.at +++ b/tests/named-refs.at @@ -446,13 +446,14 @@ AT_SETUP([Stray symbols in brackets]) AT_DATA_GRAMMAR([test.y], [[ %% -start: foo[ /* aaa */ *&-+ ] bar +start: foo[ /* aaa */ *&-.+ ] bar { s = $foo; } ]]) AT_BISON_CHECK([-o test.c test.y], 1, [], [[test.y:11.23: invalid character in bracketed name: `*' test.y:11.24: invalid character in bracketed name: `&' -test.y:11.26: invalid character in bracketed name: `+' +test.y:11.25: invalid character in bracketed name: `-' +test.y:11.27: invalid character in bracketed name: `+' ]]) AT_CLEANUP @@ -570,23 +571,27 @@ AT_DATA([[test.y]], %% start: .field { $.field; } -| -field { @-field; } | 'a' { @.field; } -| 'a' { $-field; } ; .field: ; --field: ; ]]) AT_BISON_CHECK([[test.y]], [[1]], [], [[test.y:4.12-18: invalid reference: `$.field' test.y:4.13: syntax error after `$', expecting integer, letter, `_', `@<:@', or `$' test.y:4.3-8: possibly meant: $[.field] at $1 -test.y:5.12-18: invalid reference: `@-field' +test.y:5.12-18: invalid reference: `@.field' test.y:5.13: syntax error after `@', expecting integer, letter, `_', `@<:@', or `$' -test.y:5.3-8: possibly meant: @[-field] at $1 -test.y:6.12-18: invalid reference: `@.field' -test.y:6.13: syntax error after `@', expecting integer, letter, `_', `@<:@', or `$' -test.y:7.12-18: invalid reference: `$-field' -test.y:7.13: syntax error after `$', expecting integer, letter, `_', `@<:@', or `$' +]]) +AT_DATA([[test.y]], +[[ +%% +start: + 'a' { $-field; } +| 'b' { @-field; } +; +]]) +AT_BISON_CHECK([[test.y]], [[0]], [], +[[test.y:4.9: warning: stray `$' +test.y:5.9: warning: stray `@' ]]) AT_CLEANUP diff --git a/tests/regression.at b/tests/regression.at index fa77fff4..68a41319 100644 --- a/tests/regression.at +++ b/tests/regression.at @@ -392,7 +392,8 @@ input.y:3.14: invalid character: `}' input.y:4.1: invalid character: `%' input.y:4.2: invalid character: `&' input.y:5.1-17: invalid directive: `%a-does-not-exist' -input.y:6.1-2: invalid directive: `%-' +input.y:6.1: invalid character: `%' +input.y:6.2: invalid character: `-' input.y:7.1-8.0: missing `%}' at end of file input.y:7.1-8.0: syntax error, unexpected %{...%} ]]) -- 2.47.2