Message ID | 38b67944c0759299533ad163d002247996fa5e33.1666891579.git.lhyatt@gmail.com |
---|---|
State | New |
Headers | show |
Series | c++: libcpp: Support raw strings with newlines in directives [PR55971] | expand |
On 10/27/22 13:30, Lewis Hyatt wrote: > Hello- > > May I please ask for a review of this patch from June? I realize it's a > 10-year-old PR that doesn't seem to be bothering people much, but I still feel > like it's an unfortunate gap in C++11 support that is not hard to fix. > > Original submission is here: > https://gcc.gnu.org/pipermail/gcc-patches/2022-June/596820.html > > But I have attached a new version here that is simplified, all the > _Pragma-related stuff has been removed and I will handle that in a later patch > instead. I also removed the changes to c-ppoutput.cc that I realized were not > needed after all. Bootstrap+regtest all languages on x86-64 Linux still looks > good. Thanks! > > -Lewis OK, thanks. > -- >8 -- > > It's not currently possible to use a C++11 raw string containing a newline as > part of the definition of a macro, or in any other preprocessing directive, > such as: > > #define X R"(two > lines)" > > #error R"(this error has > two lines)" > > Add support for that by relaxing the conditions under which > _cpp_get_fresh_line() refuses to get a new line. For the case of lexing a raw > string, it's OK to do so as long as there is another line within the current > buffer. The code in cpp_get_fresh_line() was refactored into a new function > get_fresh_line_impl(), so that the new logic is applied only when processing a > raw string and not any other times. > > libcpp/ChangeLog: > > PR preprocessor/55971 > * lex.cc (get_fresh_line_impl): New function refactoring the code > from... > (_cpp_get_fresh_line): ...here. > (lex_raw_string): Use the new version of get_fresh_line_impl() to > support raw strings containing new lines when processing a directive. > > gcc/testsuite/ChangeLog: > > PR preprocessor/55971 > * c-c++-common/raw-string-directive-1.c: New test. > * c-c++-common/raw-string-directive-2.c: New test. > > gcc/c-family/ChangeLog: > > PR preprocessor/55971 > * c-ppoutput.cc (adjust_for_newlines): Update comment. > --- > gcc/c-family/c-ppoutput.cc | 10 ++- > .../c-c++-common/raw-string-directive-1.c | 74 +++++++++++++++++++ > .../c-c++-common/raw-string-directive-2.c | 33 +++++++++ > libcpp/lex.cc | 41 +++++++--- > 4 files changed, 148 insertions(+), 10 deletions(-) > create mode 100644 gcc/testsuite/c-c++-common/raw-string-directive-1.c > create mode 100644 gcc/testsuite/c-c++-common/raw-string-directive-2.c > > diff --git a/gcc/c-family/c-ppoutput.cc b/gcc/c-family/c-ppoutput.cc > index a99d9e9c5ca..6e054358e9e 100644 > --- a/gcc/c-family/c-ppoutput.cc > +++ b/gcc/c-family/c-ppoutput.cc > @@ -433,7 +433,15 @@ scan_translation_unit_directives_only (cpp_reader *pfile) > lang_hooks.preprocess_token (pfile, NULL, streamer.filter); > } > > -/* Adjust print.src_line for newlines embedded in output. */ > +/* Adjust print.src_line for newlines embedded in output. For example, if a raw > + string literal contains newlines, then we need to increment our notion of the > + current line to keep in sync and avoid outputting a line marker > + unnecessarily. If a raw string literal containing newlines is the result of > + macro expansion, then we have the opposite problem, where the token takes up > + more lines in the output than it did in the input, and hence a line marker is > + needed to restore the correct state for subsequent lines. In this case, > + incrementing print.src_line still does the job, because it will cause us to > + emit the line marker the next time a token is streamed. */ > static void > account_for_newlines (const unsigned char *str, size_t len) > { > diff --git a/gcc/testsuite/c-c++-common/raw-string-directive-1.c b/gcc/testsuite/c-c++-common/raw-string-directive-1.c > new file mode 100644 > index 00000000000..d6525e107bc > --- /dev/null > +++ b/gcc/testsuite/c-c++-common/raw-string-directive-1.c > @@ -0,0 +1,74 @@ > +/* { dg-do compile } */ > +/* { dg-options "-std=gnu99" { target c } } */ > +/* { dg-options "-std=c++11" { target c++ } } */ > + > +/* Test that multi-line raw strings are lexed OK for all preprocessing > + directives where one could appear. Test raw-string-directive-2.c > + checks that #define is also processed properly. */ > + > +/* Note that in cases where we cause GCC to produce a multi-line error > + message, we construct the string so that the second line looks enough > + like an error message for DejaGNU to process it as such, so that we > + can use dg-warning or dg-error directives to check for it. */ > + > +#warning R"delim(line1 /* { dg-warning "line1" } */ > +file:15:1: warning: line2)delim" /* { dg-warning "line2" } */ > + > +#error R"delim(line3 /* { dg-error "line3" } */ > +file:18:1: error: line4)delim" /* { dg-error "line4" } */ > + > +#define X1 R"(line 5 > +line 6 > +line 7 > +line 8 > +/* > +// > +line 9)" R"delim( > +line10)delim" > + > +#define X2(a) X1 #a R"(line 11 > +/* > +line12 > +)" > + > +#if R"(line 13 /* { dg-error "line13" } */ > +file:35:1: error: line14)" /* { dg-error "line14\\)\"\" is not valid" } */ > +#endif R"(line 15 /* { dg-warning "extra tokens at end of #endif" } */ > +\ > +line16)" "" > + > +#ifdef XYZ R"(line17 /* { dg-warning "extra tokens at end of #ifdef" } */ > +\ > +\ > +line18)" > +#endif > + > +#if 1 > +#else R"(line23 /* { dg-warning "extra tokens at end of #else" } */ > +\ > + > +line24)" > +#endif > + > +#if 0 > +#elif R"(line 25 /* { dg-error "line25" } */ > +file:55:1: error: line26)" /* { dg-error "line26\\)\"\" is not valid" } */ > +#endif > + > +#line 60 R"(file:60:1: warning: this file has a space > +in it!)" > +#warning "line27" /* { dg-warning "line27" } */ > +/* { dg-warning "this file has a space" "#line check" { target *-*-* } 60 } */ > +#line 63 "file" > + > +#undef X1 R"(line28 /* { dg-warning "extra tokens at end of #undef" } */ > +line29 > +\ > +)" > + > +#ident R"(line30 > +line31)" R"(line 32 /* { dg-warning "extra tokens at end of #ident" } */ > +line 33)" > + > +#pragma GCC diagnostic ignored R"(-Woption /* { dg-warning "-Wpragmas" } */ > +-with-a-newline)" > diff --git a/gcc/testsuite/c-c++-common/raw-string-directive-2.c b/gcc/testsuite/c-c++-common/raw-string-directive-2.c > new file mode 100644 > index 00000000000..6fc673ccd82 > --- /dev/null > +++ b/gcc/testsuite/c-c++-common/raw-string-directive-2.c > @@ -0,0 +1,33 @@ > +/* { dg-do run } */ > +/* { dg-options "-std=gnu99" { target c } } */ > +/* { dg-options "-std=c++11" { target c++ } } */ > + > +#define S1 R"(three > +line > +string)" > + > +#define S2 R"(pasted > +two line)" " string" > + > +#define X(a, b) a b R"( > +one more)" > + > +const char *s1 = S1; > +const char *s2 = S2; > +const char *s3 = X(S1, R"( > +with this line plus)"); > + > +int main () > +{ > + const char s1_correct[] = "three\nline\nstring"; > + if (__builtin_memcmp (s1, s1_correct, sizeof s1_correct)) > + __builtin_abort (); > + > + const char s2_correct[] = "pasted\ntwo line string"; > + if (__builtin_memcmp (s2, s2_correct, sizeof s2_correct)) > + __builtin_abort (); > + > + const char s3_correct[] = "three\nline\nstring\nwith this line plus\none more"; > + if (__builtin_memcmp (s3, s3_correct, sizeof s3_correct)) > + __builtin_abort (); > +} > diff --git a/libcpp/lex.cc b/libcpp/lex.cc > index cc12a52d282..b1107920c94 100644 > --- a/libcpp/lex.cc > +++ b/libcpp/lex.cc > @@ -1076,6 +1076,9 @@ _cpp_clean_line (cpp_reader *pfile) > buffer->next_line = s + 1; > } > > +template <bool lexing_raw_string> > +static bool get_fresh_line_impl (cpp_reader *pfile); > + > /* Return true if the trigraph indicated by NOTE should be warned > about in a comment. */ > static bool > @@ -2695,9 +2698,8 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base) > { > pos--; > pfile->buffer->cur = pos; > - if (pfile->state.in_directive > - || (pfile->state.parsing_args > - && pfile->buffer->next_line >= pfile->buffer->rlimit)) > + if ((pfile->state.in_directive || pfile->state.parsing_args) > + && pfile->buffer->next_line >= pfile->buffer->rlimit) > { > cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc, 0, > "unterminated raw string"); > @@ -2712,7 +2714,7 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base) > CPP_INCREMENT_LINE (pfile, 0); > pfile->buffer->need_line = true; > > - if (!_cpp_get_fresh_line (pfile)) > + if (!get_fresh_line_impl<true> (pfile)) > { > /* We ran out of file and failed to get a line. */ > location_t src_loc = token->src_loc; > @@ -2724,8 +2726,15 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base) > _cpp_release_buff (pfile, accum.first); > cpp_error_with_line (pfile, CPP_DL_ERROR, src_loc, 0, > "unterminated raw string"); > - /* Now pop the buffer that _cpp_get_fresh_line did not. */ > + > + /* Now pop the buffer that get_fresh_line_impl() did not. Popping > + is not safe if processing a directive, however this cannot > + happen as we already checked above that a line would be > + available, and get_fresh_line_impl() can't fail in this > + case. */ > + gcc_assert (!pfile->state.in_directive); > _cpp_pop_buffer (pfile); > + > return; > } > > @@ -3659,11 +3668,14 @@ _cpp_lex_token (cpp_reader *pfile) > } > > /* Returns true if a fresh line has been loaded. */ > -bool > -_cpp_get_fresh_line (cpp_reader *pfile) > +template <bool lexing_raw_string> > +static bool > +get_fresh_line_impl (cpp_reader *pfile) > { > - /* We can't get a new line until we leave the current directive. */ > - if (pfile->state.in_directive) > + /* We can't get a new line until we leave the current directive, unless we > + are lexing a raw string, in which case it will be OK as long as we don't > + pop the current buffer. */ > + if (!lexing_raw_string && pfile->state.in_directive) > return false; > > for (;;) > @@ -3679,6 +3691,10 @@ _cpp_get_fresh_line (cpp_reader *pfile) > return true; > } > > + /* We can't change buffers until we leave the current directive. */ > + if (lexing_raw_string && pfile->state.in_directive) > + return false; > + > /* First, get out of parsing arguments state. */ > if (pfile->state.parsing_args) > return false; > @@ -3706,6 +3722,13 @@ _cpp_get_fresh_line (cpp_reader *pfile) > } > } > > +bool > +_cpp_get_fresh_line (cpp_reader *pfile) > +{ > + return get_fresh_line_impl<false> (pfile); > +} > + > + > #define IF_NEXT_IS(CHAR, THEN_TYPE, ELSE_TYPE) \ > do \ > { \ >
diff --git a/gcc/c-family/c-ppoutput.cc b/gcc/c-family/c-ppoutput.cc index a99d9e9c5ca..6e054358e9e 100644 --- a/gcc/c-family/c-ppoutput.cc +++ b/gcc/c-family/c-ppoutput.cc @@ -433,7 +433,15 @@ scan_translation_unit_directives_only (cpp_reader *pfile) lang_hooks.preprocess_token (pfile, NULL, streamer.filter); } -/* Adjust print.src_line for newlines embedded in output. */ +/* Adjust print.src_line for newlines embedded in output. For example, if a raw + string literal contains newlines, then we need to increment our notion of the + current line to keep in sync and avoid outputting a line marker + unnecessarily. If a raw string literal containing newlines is the result of + macro expansion, then we have the opposite problem, where the token takes up + more lines in the output than it did in the input, and hence a line marker is + needed to restore the correct state for subsequent lines. In this case, + incrementing print.src_line still does the job, because it will cause us to + emit the line marker the next time a token is streamed. */ static void account_for_newlines (const unsigned char *str, size_t len) { diff --git a/gcc/testsuite/c-c++-common/raw-string-directive-1.c b/gcc/testsuite/c-c++-common/raw-string-directive-1.c new file mode 100644 index 00000000000..d6525e107bc --- /dev/null +++ b/gcc/testsuite/c-c++-common/raw-string-directive-1.c @@ -0,0 +1,74 @@ +/* { dg-do compile } */ +/* { dg-options "-std=gnu99" { target c } } */ +/* { dg-options "-std=c++11" { target c++ } } */ + +/* Test that multi-line raw strings are lexed OK for all preprocessing + directives where one could appear. Test raw-string-directive-2.c + checks that #define is also processed properly. */ + +/* Note that in cases where we cause GCC to produce a multi-line error + message, we construct the string so that the second line looks enough + like an error message for DejaGNU to process it as such, so that we + can use dg-warning or dg-error directives to check for it. */ + +#warning R"delim(line1 /* { dg-warning "line1" } */ +file:15:1: warning: line2)delim" /* { dg-warning "line2" } */ + +#error R"delim(line3 /* { dg-error "line3" } */ +file:18:1: error: line4)delim" /* { dg-error "line4" } */ + +#define X1 R"(line 5 +line 6 +line 7 +line 8 +/* +// +line 9)" R"delim( +line10)delim" + +#define X2(a) X1 #a R"(line 11 +/* +line12 +)" + +#if R"(line 13 /* { dg-error "line13" } */ +file:35:1: error: line14)" /* { dg-error "line14\\)\"\" is not valid" } */ +#endif R"(line 15 /* { dg-warning "extra tokens at end of #endif" } */ +\ +line16)" "" + +#ifdef XYZ R"(line17 /* { dg-warning "extra tokens at end of #ifdef" } */ +\ +\ +line18)" +#endif + +#if 1 +#else R"(line23 /* { dg-warning "extra tokens at end of #else" } */ +\ + +line24)" +#endif + +#if 0 +#elif R"(line 25 /* { dg-error "line25" } */ +file:55:1: error: line26)" /* { dg-error "line26\\)\"\" is not valid" } */ +#endif + +#line 60 R"(file:60:1: warning: this file has a space +in it!)" +#warning "line27" /* { dg-warning "line27" } */ +/* { dg-warning "this file has a space" "#line check" { target *-*-* } 60 } */ +#line 63 "file" + +#undef X1 R"(line28 /* { dg-warning "extra tokens at end of #undef" } */ +line29 +\ +)" + +#ident R"(line30 +line31)" R"(line 32 /* { dg-warning "extra tokens at end of #ident" } */ +line 33)" + +#pragma GCC diagnostic ignored R"(-Woption /* { dg-warning "-Wpragmas" } */ +-with-a-newline)" diff --git a/gcc/testsuite/c-c++-common/raw-string-directive-2.c b/gcc/testsuite/c-c++-common/raw-string-directive-2.c new file mode 100644 index 00000000000..6fc673ccd82 --- /dev/null +++ b/gcc/testsuite/c-c++-common/raw-string-directive-2.c @@ -0,0 +1,33 @@ +/* { dg-do run } */ +/* { dg-options "-std=gnu99" { target c } } */ +/* { dg-options "-std=c++11" { target c++ } } */ + +#define S1 R"(three +line +string)" + +#define S2 R"(pasted +two line)" " string" + +#define X(a, b) a b R"( +one more)" + +const char *s1 = S1; +const char *s2 = S2; +const char *s3 = X(S1, R"( +with this line plus)"); + +int main () +{ + const char s1_correct[] = "three\nline\nstring"; + if (__builtin_memcmp (s1, s1_correct, sizeof s1_correct)) + __builtin_abort (); + + const char s2_correct[] = "pasted\ntwo line string"; + if (__builtin_memcmp (s2, s2_correct, sizeof s2_correct)) + __builtin_abort (); + + const char s3_correct[] = "three\nline\nstring\nwith this line plus\none more"; + if (__builtin_memcmp (s3, s3_correct, sizeof s3_correct)) + __builtin_abort (); +} diff --git a/libcpp/lex.cc b/libcpp/lex.cc index cc12a52d282..b1107920c94 100644 --- a/libcpp/lex.cc +++ b/libcpp/lex.cc @@ -1076,6 +1076,9 @@ _cpp_clean_line (cpp_reader *pfile) buffer->next_line = s + 1; } +template <bool lexing_raw_string> +static bool get_fresh_line_impl (cpp_reader *pfile); + /* Return true if the trigraph indicated by NOTE should be warned about in a comment. */ static bool @@ -2695,9 +2698,8 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base) { pos--; pfile->buffer->cur = pos; - if (pfile->state.in_directive - || (pfile->state.parsing_args - && pfile->buffer->next_line >= pfile->buffer->rlimit)) + if ((pfile->state.in_directive || pfile->state.parsing_args) + && pfile->buffer->next_line >= pfile->buffer->rlimit) { cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc, 0, "unterminated raw string"); @@ -2712,7 +2714,7 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base) CPP_INCREMENT_LINE (pfile, 0); pfile->buffer->need_line = true; - if (!_cpp_get_fresh_line (pfile)) + if (!get_fresh_line_impl<true> (pfile)) { /* We ran out of file and failed to get a line. */ location_t src_loc = token->src_loc; @@ -2724,8 +2726,15 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base) _cpp_release_buff (pfile, accum.first); cpp_error_with_line (pfile, CPP_DL_ERROR, src_loc, 0, "unterminated raw string"); - /* Now pop the buffer that _cpp_get_fresh_line did not. */ + + /* Now pop the buffer that get_fresh_line_impl() did not. Popping + is not safe if processing a directive, however this cannot + happen as we already checked above that a line would be + available, and get_fresh_line_impl() can't fail in this + case. */ + gcc_assert (!pfile->state.in_directive); _cpp_pop_buffer (pfile); + return; } @@ -3659,11 +3668,14 @@ _cpp_lex_token (cpp_reader *pfile) } /* Returns true if a fresh line has been loaded. */ -bool -_cpp_get_fresh_line (cpp_reader *pfile) +template <bool lexing_raw_string> +static bool +get_fresh_line_impl (cpp_reader *pfile) { - /* We can't get a new line until we leave the current directive. */ - if (pfile->state.in_directive) + /* We can't get a new line until we leave the current directive, unless we + are lexing a raw string, in which case it will be OK as long as we don't + pop the current buffer. */ + if (!lexing_raw_string && pfile->state.in_directive) return false; for (;;) @@ -3679,6 +3691,10 @@ _cpp_get_fresh_line (cpp_reader *pfile) return true; } + /* We can't change buffers until we leave the current directive. */ + if (lexing_raw_string && pfile->state.in_directive) + return false; + /* First, get out of parsing arguments state. */ if (pfile->state.parsing_args) return false; @@ -3706,6 +3722,13 @@ _cpp_get_fresh_line (cpp_reader *pfile) } } +bool +_cpp_get_fresh_line (cpp_reader *pfile) +{ + return get_fresh_line_impl<false> (pfile); +} + + #define IF_NEXT_IS(CHAR, THEN_TYPE, ELSE_TYPE) \ do \ { \