From ac9b0e954b1d3aed514a3bbd363da1514202af0f Mon Sep 17 00:00:00 2001 From: "Joel E. Denny" Date: Fri, 24 Jul 2009 10:29:07 -0400 Subject: [PATCH 1/1] Warn about character literals not of length one. * NEWS (2.5): Document. * src/scan-gram.l (INITIAL): Remove comment that we don't check the length. (SC_ESCAPED_CHARACTER): Warn if length is wrong. * tests/input.at (Bad character literals): New test group. --- ChangeLog | 9 +++++++ NEWS | 13 +++++++++++ src/scan-gram.l | 32 ++++++++++++++++++------- tests/input.at | 62 +++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 108 insertions(+), 8 deletions(-) diff --git a/ChangeLog b/ChangeLog index 0fed8229..3d4cf9f9 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,12 @@ +2009-07-24 Joel E. Denny + + Warn about character literals not of length one. + * NEWS (2.5): Document. + * src/scan-gram.l (INITIAL): Remove comment that we don't check + the length. + (SC_ESCAPED_CHARACTER): Warn if length is wrong. + * tests/input.at (Bad character literals): New test group. + 2009-07-24 Joel E. Denny * src/lalr.c (state_lookahead_tokens_count): Correct comment. diff --git a/NEWS b/NEWS index 7d401ad5..e4bb63f5 100644 --- a/NEWS +++ b/NEWS @@ -98,6 +98,19 @@ Bison News about a missing semicolon where it did not before. Future releases of Bison will cease to append semicolons entirely. +** Character literals not of length one. + + Previously, Bison quietly converted all character literals to length + one. For example, without warning, Bison interpreted the operators in + the following grammar to be the same token: + + exp: exp '++' + | exp '+' exp + ; + + Bison now warns when a character literal is not of length one. In + some future release, Bison will report an error instead. + * Changes in version 2.4.2 (????-??-??): ** %code is now a permanent feature. diff --git a/src/scan-gram.l b/src/scan-gram.l index 60813bb6..0c12cbaa 100644 --- a/src/scan-gram.l +++ b/src/scan-gram.l @@ -250,7 +250,7 @@ splice (\\[ \f\t\v]*\n)* complain_at (*loc, _("invalid identifier: %s"), quote (yytext)); } - /* Characters. We don't check there is only one. */ + /* Characters. */ "'" STRING_GROW; token_start = loc->start; BEGIN SC_ESCAPED_CHARACTER; /* Strings. */ @@ -465,24 +465,40 @@ splice (\\[ \f\t\v]*\n)* { "'"|"\n" { - if (yytext[0] == '\n') - unexpected_newline (token_start, "'"); STRING_GROW; STRING_FINISH; loc->start = token_start; val->character = last_string[1]; + { + /* FIXME: Eventually, make these errors. */ + size_t length = strlen (last_string); + if (strlen (last_string) < 3) + warn_at (*loc, _("empty character literal")); + else if (strlen (last_string) > 3) + warn_at (*loc, _("extra characters in character literal")); + } + if (yytext[0] == '\n') + unexpected_newline (token_start, "'"); STRING_FREE; BEGIN INITIAL; return CHAR; } <> { - unexpected_eof (token_start, "'"); STRING_FINISH; loc->start = token_start; - if (strlen (last_string) > 1) - val->character = last_string[1]; - else - val->character = last_string[0]; + { + size_t length = strlen (last_string); + /* FIXME: Eventually, make these errors. */ + if (length < 2) + warn_at (*loc, _("empty character literal")); + else if (length > 2) + warn_at (*loc, _("extra characters in character literal")); + if (length > 1) + val->character = last_string[1]; + else + val->character = last_string[0]; + } + unexpected_eof (token_start, "'"); STRING_FREE; BEGIN INITIAL; return CHAR; diff --git a/tests/input.at b/tests/input.at index f62a68d3..4d5d0bbc 100644 --- a/tests/input.at +++ b/tests/input.at @@ -1162,3 +1162,65 @@ AT_CHECK_NAMESPACE_ERROR([[::]], [[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 +# . + +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 -- 2.45.2