diff options
Diffstat (limited to 'meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch')
-rw-r--r-- | meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch | 2906 |
1 files changed, 2906 insertions, 0 deletions
diff --git a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch new file mode 100644 index 0000000000..e0f4f7d32f --- /dev/null +++ b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch @@ -0,0 +1,2906 @@ +From 004bb936d6d5f177af26ad4905595e843d5665a5 Mon Sep 17 00:00:00 2001 +From: Lewis Hyatt <lhyatt@gmail.com> +Date: Tue, 14 Jul 2020 12:05:56 -0400 +Subject: [PATCH] diagnostics: Support conversion of tabs to spaces [PR49973] + [PR86904] + +Supports conversion of tabs to spaces when outputting diagnostics. Also +adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to +control how the column number is output, thereby resolving the two PRs. + +gcc/c-family/ChangeLog: + + PR other/86904 + * c-indentation.c (should_warn_for_misleading_indentation): Get + global tabstop from the new source. + * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which + is now a common option. + * c.opt: Likewise. + +gcc/ChangeLog: + + PR preprocessor/49973 + PR other/86904 + * common.opt: Handle -ftabstop here instead of in c-family + options. Add -fdiagnostics-column-unit= and + -fdiagnostics-column-origin= options. + * opts.c (common_handle_option): Handle the new options. + * diagnostic-format-json.cc (json_from_expanded_location): Add + diagnostic_context argument. Use it to convert column numbers as per + the new options. + (json_from_location_range): Likewise. + (json_from_fixit_hint): Likewise. + (json_end_diagnostic): Pass the new context argument to helper + functions above. Add "column-origin" field to the output. + (test_unknown_location): Add the new context argument to calls to + helper functions. + (test_bad_endpoints): Likewise. + * diagnostic-show-locus.c + (exploc_with_display_col::exploc_with_display_col): Support + tabstop parameter. + (layout_point::layout_point): Make use of class + exploc_with_display_col. + (layout_range::layout_range): Likewise. + (struct line_bounds): Clarify that the units are now always + display columns. Rename members accordingly. Add constructor. + (layout::print_source_line): Add support for tab expansion. + (make_range): Adapt to class layout_range changes. + (layout::maybe_add_location_range): Likewise. + (layout::layout): Adapt to class exploc_with_display_col changes. + (layout::calculate_x_offset_display): Support tabstop parameter. + (layout::print_annotation_line): Adapt to struct line_bounds changes. + (layout::print_line): Likewise. + (line_label::line_label): Add diagnostic_context argument. + (get_affected_range): Likewise. + (get_printed_columns): Likewise. + (layout::print_any_labels): Adapt to struct line_label changes. + (class correction): Add m_tabstop member. + (correction::correction): Add tabstop argument. + (correction::compute_display_cols): Use m_tabstop. + (class line_corrections): Add m_context member. + (line_corrections::line_corrections): Add diagnostic_context argument. + (line_corrections::add_hint): Use m_context to handle tabstops. + (layout::print_trailing_fixits): Adapt to class line_corrections + changes. + (test_layout_x_offset_display_utf8): Support tabstop parameter. + (test_layout_x_offset_display_tab): New selftest. + (test_one_liner_colorized_utf8): Likewise. + (test_tab_expansion): Likewise. + (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. + (diagnostic_show_locus_c_tests): Likewise. + (test_overlapped_fixit_printing): Adapt to helper class and + function changes. + (test_overlapped_fixit_printing_utf8): Likewise. + (test_overlapped_fixit_printing_2): Likewise. + * diagnostic.h (enum diagnostics_column_unit): New enum. + (struct diagnostic_context): Add members for the new options. + (diagnostic_converted_column): Declare. + (json_from_expanded_location): Add new context argument. + * diagnostic.c (diagnostic_initialize): Initialize new members. + (diagnostic_converted_column): New function. + (maybe_line_and_column): Be willing to output a column of 0. + (diagnostic_get_location_text): Convert column number as per the new + options. + (diagnostic_report_current_module): Likewise. + (assert_location_text): Add origin and column_unit arguments for + testing the new functionality. + (test_diagnostic_get_location_text): Test the new functionality. + * doc/invoke.texi: Document the new options and behavior. + * input.h (location_compute_display_column): Add tabstop argument. + * input.c (location_compute_display_column): Likewise. + (test_cpp_utf8): Add selftests for tab expansion. + * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the + new context argument to json_from_expanded_location(). + +libcpp/ChangeLog: + + PR preprocessor/49973 + PR other/86904 + * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, + which is now handled by diagnostic_context. + (class cpp_display_width_computation): New class. + (cpp_byte_column_to_display_column): Add optional tabstop argument. + (cpp_display_width): Likewise. + (cpp_display_column_to_byte_column): Likewise. + * charset.c + (cpp_display_width_computation::cpp_display_width_computation): New + function. + (cpp_display_width_computation::advance_display_cols): Likewise. + (compute_next_display_width): Removed and implemented this + functionality in a new function... + (cpp_display_width_computation::process_next_codepoint): ...here. + (cpp_byte_column_to_display_column): Added tabstop argument. + Reimplemented in terms of class cpp_display_width_computation. + (cpp_display_column_to_byte_column): Likewise. + * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now + handled by diagnostic_context. + +gcc/testsuite/ChangeLog: + + PR preprocessor/49973 + PR other/86904 + * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output + for new defaults. + * c-c++-common/Wmisleading-indentation.c: Likewise. + * c-c++-common/diagnostic-format-json-1.c: Likewise. + * c-c++-common/diagnostic-format-json-2.c: Likewise. + * c-c++-common/diagnostic-format-json-3.c: Likewise. + * c-c++-common/diagnostic-format-json-4.c: Likewise. + * c-c++-common/diagnostic-format-json-5.c: Likewise. + * c-c++-common/missing-close-symbol.c: Likewise. + * g++.dg/diagnostic/bad-binary-ops.C: Likewise. + * g++.dg/parse/error4.C: Likewise. + * g++.old-deja/g++.brendan/crash11.C: Likewise. + * g++.old-deja/g++.pt/overload2.C: Likewise. + * g++.old-deja/g++.robertl/eb109.C: Likewise. + * gcc.dg/analyzer/malloc-paths-9.c: Likewise. + * gcc.dg/bad-binary-ops.c: Likewise. + * gcc.dg/format/branch-1.c: Likewise. + * gcc.dg/format/pr79210.c: Likewise. + * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. + * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. + * gcc.dg/redecl-4.c: Likewise. + * gfortran.dg/diagnostic-format-json-1.F90: Likewise. + * gfortran.dg/diagnostic-format-json-2.F90: Likewise. + * gfortran.dg/diagnostic-format-json-3.F90: Likewise. + * go.dg/arrayclear.go: Add a comment explaining why adding a + comment was necessary to work around a dejagnu bug. + * c-c++-common/diagnostic-units-1.c: New test. + * c-c++-common/diagnostic-units-2.c: New test. + * c-c++-common/diagnostic-units-3.c: New test. + * c-c++-common/diagnostic-units-4.c: New test. + * c-c++-common/diagnostic-units-5.c: New test. + * c-c++-common/diagnostic-units-6.c: New test. + * c-c++-common/diagnostic-units-7.c: New test. + * c-c++-common/diagnostic-units-8.c: New test. + +CVE: CVE-2021-42574 +Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=004bb936d6d5f177af26ad4905595e843d5665a5] +Signed-off-by: Pgowda <pgowda.cve@gmail.com> +--- + gcc/c-family/c-indentation.c | 5 +- + gcc/c-family/c-opts.c | 6 - + gcc/c-family/c.opt | 4 - + gcc/common.opt | 21 + + gcc/diagnostic-format-json.cc | 55 +- + gcc/diagnostic-show-locus.c | 504 +++++++++++++----- + gcc/diagnostic.c | 113 +++- + gcc/diagnostic.h | 28 +- + gcc/doc/invoke.texi | 68 ++- + gcc/input.c | 72 ++- + gcc/input.h | 4 +- + gcc/opts.c | 14 + + .../c-c++-common/Wmisleading-indentation-3.c | 12 +- + .../c-c++-common/Wmisleading-indentation.c | 6 +- + .../c-c++-common/diagnostic-format-json-1.c | 5 + + .../c-c++-common/diagnostic-format-json-2.c | 5 + + .../c-c++-common/diagnostic-format-json-3.c | 5 + + .../c-c++-common/diagnostic-format-json-4.c | 9 + + .../c-c++-common/diagnostic-format-json-5.c | 9 + + .../c-c++-common/diagnostic-units-1.c | 28 + + .../c-c++-common/diagnostic-units-2.c | 28 + + .../c-c++-common/diagnostic-units-3.c | 28 + + .../c-c++-common/diagnostic-units-4.c | 28 + + .../c-c++-common/diagnostic-units-5.c | 28 + + .../c-c++-common/diagnostic-units-6.c | 28 + + .../c-c++-common/diagnostic-units-7.c | 28 + + .../c-c++-common/diagnostic-units-8.c | 28 + + .../c-c++-common/missing-close-symbol.c | 6 +- + .../g++.dg/diagnostic/bad-binary-ops.C | 8 +- + gcc/testsuite/g++.dg/parse/error4.C | 2 +- + .../g++.old-deja/g++.brendan/crash11.C | 4 +- + gcc/testsuite/g++.old-deja/g++.pt/overload2.C | 2 +- + .../g++.old-deja/g++.robertl/eb109.C | 4 +- + .../gcc.dg/analyzer/malloc-paths-9.c | 2 +- + gcc/testsuite/gcc.dg/bad-binary-ops.c | 8 +- + gcc/testsuite/gcc.dg/format/branch-1.c | 2 +- + gcc/testsuite/gcc.dg/format/pr79210.c | 2 +- + .../plugin/diagnostic-test-expressions-1.c | 16 +- + .../diagnostic-test-string-literals-1.c | 4 +- + gcc/testsuite/gcc.dg/redecl-4.c | 2 +- + .../gfortran.dg/diagnostic-format-json-1.F90 | 5 + + .../gfortran.dg/diagnostic-format-json-2.F90 | 5 + + .../gfortran.dg/diagnostic-format-json-3.F90 | 5 + + gcc/testsuite/go.dg/arrayclear.go | 3 + + gcc/tree-diagnostic-path.cc | 5 +- + libcpp/charset.c | 98 ++-- + libcpp/include/cpplib.h | 40 +- + libcpp/init.c | 1 - + 48 files changed, 1106 insertions(+), 287 deletions(-) + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-1.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-2.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-3.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-4.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-5.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-6.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-7.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-8.c + +diff --git a/gcc/c-family/c-indentation.c b/gcc/c-family/c-indentation.c +--- a/gcc/c-family/c-indentation.c 2020-07-22 23:35:17.296384022 -0700 ++++ b/gcc/c-family/c-indentation.c 2021-12-25 01:20:53.475636694 -0800 +@@ -24,8 +24,7 @@ along with GCC; see the file COPYING3. + #include "c-common.h" + #include "c-indentation.h" + #include "selftest.h" +- +-extern cpp_options *cpp_opts; ++#include "diagnostic.h" + + /* Round up VIS_COLUMN to nearest tab stop. */ + +@@ -294,7 +293,7 @@ should_warn_for_misleading_indentation ( + expanded_location next_stmt_exploc = expand_location (next_stmt_loc); + expanded_location guard_exploc = expand_location (guard_loc); + +- const unsigned int tab_width = cpp_opts->tabstop; ++ const unsigned int tab_width = global_dc->tabstop; + + /* They must be in the same file. */ + if (next_stmt_exploc.file != body_exploc.file) +diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt +--- a/gcc/c-family/c.opt 2021-12-24 20:23:42.816809230 -0800 ++++ b/gcc/c-family/c.opt 2021-12-25 01:20:53.475636694 -0800 +@@ -1876,10 +1876,6 @@ Enum(strong_eval_order) String(some) Val + EnumValue + Enum(strong_eval_order) String(all) Value(2) + +-ftabstop= +-C ObjC C++ ObjC++ Joined RejectNegative UInteger +--ftabstop=<number> Distance between tab stops for column reporting. +- + ftemplate-backtrace-limit= + C++ ObjC++ Joined RejectNegative UInteger Var(template_backtrace_limit) Init(10) + Set the maximum number of template instantiation notes for a single warning or error. +diff --git a/gcc/c-family/c-opts.c b/gcc/c-family/c-opts.c +--- a/gcc/c-family/c-opts.c 2021-12-24 20:23:44.824774786 -0800 ++++ b/gcc/c-family/c-opts.c 2021-12-25 01:20:53.475636694 -0800 +@@ -504,12 +504,6 @@ c_common_handle_option (size_t scode, co + cpp_opts->track_macro_expansion = 2; + break; + +- case OPT_ftabstop_: +- /* It is documented that we silently ignore silly values. */ +- if (value >= 1 && value <= 100) +- cpp_opts->tabstop = value; +- break; +- + case OPT_fexec_charset_: + cpp_opts->narrow_charset = arg; + break; +diff --git a/gcc/common.opt b/gcc/common.opt +--- a/gcc/common.opt 2021-12-24 20:23:42.480814993 -0800 ++++ b/gcc/common.opt 2021-12-25 01:20:53.475636694 -0800 +@@ -1325,6 +1325,14 @@ Enum(diagnostic_url_rule) String(always) + EnumValue + Enum(diagnostic_url_rule) String(auto) Value(DIAGNOSTICS_URL_AUTO) + ++fdiagnostics-column-unit= ++Common Joined RejectNegative Enum(diagnostics_column_unit) ++-fdiagnostics-column-unit=[display|byte] Select whether column numbers are output as display columns (default) or raw bytes. ++ ++fdiagnostics-column-origin= ++Common Joined RejectNegative UInteger ++-fdiagnostics-column-origin=<number> Set the number of the first column. The default is 1-based as per GNU style, but some utilities may expect 0-based, for example. ++ + fdiagnostics-format= + Common Joined RejectNegative Enum(diagnostics_output_format) + -fdiagnostics-format=[text|json] Select output format. +@@ -1334,6 +1342,15 @@ SourceInclude + diagnostic.h + + Enum ++Name(diagnostics_column_unit) Type(int) ++ ++EnumValue ++Enum(diagnostics_column_unit) String(display) Value(DIAGNOSTICS_COLUMN_UNIT_DISPLAY) ++ ++EnumValue ++Enum(diagnostics_column_unit) String(byte) Value(DIAGNOSTICS_COLUMN_UNIT_BYTE) ++ ++Enum + Name(diagnostics_output_format) Type(int) + + EnumValue +@@ -1362,6 +1379,10 @@ fdiagnostics-path-format= + Common Joined RejectNegative Var(flag_diagnostics_path_format) Enum(diagnostic_path_format) Init(DPF_INLINE_EVENTS) + Specify how to print any control-flow path associated with a diagnostic. + ++ftabstop= ++Common Joined RejectNegative UInteger ++-ftabstop=<number> Distance between tab stops for column reporting. ++ + Enum + Name(diagnostic_path_format) Type(int) + +diff --git a/gcc/diagnostic.c b/gcc/diagnostic.c +--- a/gcc/diagnostic.c 2020-07-22 23:35:17.556386887 -0700 ++++ b/gcc/diagnostic.c 2021-12-25 01:23:41.300841207 -0800 +@@ -38,6 +38,7 @@ along with GCC; see the file COPYING3. + #include "selftest.h" + #include "selftest-diagnostic.h" + #include "opts.h" ++#include "cpplib.h" + + #ifdef HAVE_TERMIOS_H + # include <termios.h> +@@ -219,6 +220,9 @@ diagnostic_initialize (diagnostic_contex + context->min_margin_width = 0; + context->show_ruler_p = false; + context->parseable_fixits_p = false; ++ context->column_unit = DIAGNOSTICS_COLUMN_UNIT_DISPLAY; ++ context->column_origin = 1; ++ context->tabstop = 8; + context->edit_context_ptr = NULL; + context->diagnostic_group_nesting_depth = 0; + context->diagnostic_group_emission_count = 0; +@@ -353,8 +357,51 @@ diagnostic_get_color_for_kind (diagnosti + return diagnostic_kind_color[kind]; + } + ++/* Given an expanded_location, convert the column (which is in 1-based bytes) ++ to the requested units, without converting the origin. ++ Return -1 if the column is invalid (<= 0). */ ++ ++static int ++convert_column_unit (enum diagnostics_column_unit column_unit, ++ int tabstop, ++ expanded_location s) ++{ ++ if (s.column <= 0) ++ return -1; ++ ++ switch (column_unit) ++ { ++ default: ++ gcc_unreachable (); ++ ++ case DIAGNOSTICS_COLUMN_UNIT_DISPLAY: ++ { ++ cpp_char_column_policy policy (tabstop, cpp_wcwidth); ++ return location_compute_display_column (s, policy); ++ } ++ ++ case DIAGNOSTICS_COLUMN_UNIT_BYTE: ++ return s.column; ++ } ++} ++ ++/* Given an expanded_location, convert the column (which is in 1-based bytes) ++ to the requested units and origin. Return -1 if the column is ++ invalid (<= 0). */ ++int ++diagnostic_converted_column (diagnostic_context *context, expanded_location s) ++{ ++ int one_based_col ++ = convert_column_unit (context->column_unit, context->tabstop, s); ++ if (one_based_col <= 0) ++ return -1; ++ return one_based_col + (context->column_origin - 1); ++} ++ + /* Return a formatted line and column ':%line:%column'. Elided if +- zero. The result is a statically allocated buffer. */ ++ line == 0 or col < 0. (A column of 0 may be valid due to the ++ -fdiagnostics-column-origin option.) ++ The result is a statically allocated buffer. */ + + static const char * + maybe_line_and_column (int line, int col) +@@ -363,8 +410,9 @@ maybe_line_and_column (int line, int col + + if (line) + { +- size_t l = snprintf (result, sizeof (result), +- col ? ":%d:%d" : ":%d", line, col); ++ size_t l ++ = snprintf (result, sizeof (result), ++ col >= 0 ? ":%d:%d" : ":%d", line, col); + gcc_checking_assert (l < sizeof (result)); + } + else +@@ -383,8 +431,14 @@ diagnostic_get_location_text (diagnostic + const char *locus_cs = colorize_start (pp_show_color (pp), "locus"); + const char *locus_ce = colorize_stop (pp_show_color (pp)); + const char *file = s.file ? s.file : progname; +- int line = strcmp (file, N_("<built-in>")) ? s.line : 0; +- int col = context->show_column ? s.column : 0; ++ int line = 0; ++ int col = -1; ++ if (strcmp (file, N_("<built-in>"))) ++ { ++ line = s.line; ++ if (context->show_column) ++ col = diagnostic_converted_column (context, s); ++ } + + const char *line_col = maybe_line_and_column (line, col); + return build_message_string ("%s%s%s:%s", locus_cs, file, +@@ -650,14 +704,20 @@ diagnostic_report_current_module (diagno + if (! MAIN_FILE_P (map)) + { + bool first = true; ++ expanded_location s = {}; + do + { + where = linemap_included_from (map); + map = linemap_included_from_linemap (line_table, map); +- const char *line_col +- = maybe_line_and_column (SOURCE_LINE (map, where), +- first && context->show_column +- ? SOURCE_COLUMN (map, where) : 0); ++ s.file = LINEMAP_FILE (map); ++ s.line = SOURCE_LINE (map, where); ++ int col = -1; ++ if (first && context->show_column) ++ { ++ s.column = SOURCE_COLUMN (map, where); ++ col = diagnostic_converted_column (context, s); ++ } ++ const char *line_col = maybe_line_and_column (s.line, col); + static const char *const msgs[] = + { + N_("In file included from"), +@@ -666,7 +726,7 @@ diagnostic_report_current_module (diagno + unsigned index = !first; + pp_verbatim (context->printer, "%s%s %r%s%s%R", + first ? "" : ",\n", _(msgs[index]), +- "locus", LINEMAP_FILE (map), line_col); ++ "locus", s.file, line_col); + first = false; + } + while (! MAIN_FILE_P (map)); +@@ -2042,10 +2102,15 @@ test_print_parseable_fixits_replace () + static void + assert_location_text (const char *expected_loc_text, + const char *filename, int line, int column, +- bool show_column) ++ bool show_column, ++ int origin = 1, ++ enum diagnostics_column_unit column_unit ++ = DIAGNOSTICS_COLUMN_UNIT_BYTE) + { + test_diagnostic_context dc; + dc.show_column = show_column; ++ dc.column_unit = column_unit; ++ dc.column_origin = origin; + + expanded_location xloc; + xloc.file = filename; +@@ -2069,7 +2134,10 @@ test_diagnostic_get_location_text () + assert_location_text ("PROGNAME:", NULL, 0, 0, true); + assert_location_text ("<built-in>:", "<built-in>", 42, 10, true); + assert_location_text ("foo.c:42:10:", "foo.c", 42, 10, true); +- assert_location_text ("foo.c:42:", "foo.c", 42, 0, true); ++ assert_location_text ("foo.c:42:9:", "foo.c", 42, 10, true, 0); ++ assert_location_text ("foo.c:42:1010:", "foo.c", 42, 10, true, 1001); ++ for (int origin = 0; origin != 2; ++origin) ++ assert_location_text ("foo.c:42:", "foo.c", 42, 0, true, origin); + assert_location_text ("foo.c:", "foo.c", 0, 10, true); + assert_location_text ("foo.c:42:", "foo.c", 42, 10, false); + assert_location_text ("foo.c:", "foo.c", 0, 10, false); +@@ -2077,6 +2145,41 @@ test_diagnostic_get_location_text () + maybe_line_and_column (INT_MAX, INT_MAX); + maybe_line_and_column (INT_MIN, INT_MIN); + ++ { ++ /* In order to test display columns vs byte columns, we need to create a ++ file for location_get_source_line() to read. */ ++ ++ const char *const content = "smile \xf0\x9f\x98\x82\n"; ++ const int line_bytes = strlen (content) - 1; ++ const int def_tabstop = 8; ++ const int display_width = cpp_display_width (content, line_bytes, ++ def_tabstop); ++ ASSERT_EQ (line_bytes - 2, display_width); ++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content); ++ const char *const fname = tmp.get_filename (); ++ const int buf_len = strlen (fname) + 16; ++ char *const expected = XNEWVEC (char, buf_len); ++ ++ snprintf (expected, buf_len, "%s:1:%d:", fname, line_bytes); ++ assert_location_text (expected, fname, 1, line_bytes, true, ++ 1, DIAGNOSTICS_COLUMN_UNIT_BYTE); ++ ++ snprintf (expected, buf_len, "%s:1:%d:", fname, line_bytes - 1); ++ assert_location_text (expected, fname, 1, line_bytes, true, ++ 0, DIAGNOSTICS_COLUMN_UNIT_BYTE); ++ ++ snprintf (expected, buf_len, "%s:1:%d:", fname, display_width); ++ assert_location_text (expected, fname, 1, line_bytes, true, ++ 1, DIAGNOSTICS_COLUMN_UNIT_DISPLAY); ++ ++ snprintf (expected, buf_len, "%s:1:%d:", fname, display_width - 1); ++ assert_location_text (expected, fname, 1, line_bytes, true, ++ 0, DIAGNOSTICS_COLUMN_UNIT_DISPLAY); ++ ++ XDELETEVEC (expected); ++ } ++ ++ + progname = old_progname; + } + +diff --git a/gcc/diagnostic-format-json.cc b/gcc/diagnostic-format-json.cc +--- a/gcc/diagnostic-format-json.cc 2020-07-22 23:35:17.556386887 -0700 ++++ b/gcc/diagnostic-format-json.cc 2021-12-25 01:20:53.475636694 -0800 +@@ -23,6 +23,7 @@ along with GCC; see the file COPYING3. + #include "system.h" + #include "coretypes.h" + #include "diagnostic.h" ++#include "selftest-diagnostic.h" + #include "diagnostic-metadata.h" + #include "json.h" + #include "selftest.h" +@@ -43,21 +44,43 @@ static json::array *cur_children_array; + /* Generate a JSON object for LOC. */ + + json::value * +-json_from_expanded_location (location_t loc) ++json_from_expanded_location (diagnostic_context *context, location_t loc) + { + expanded_location exploc = expand_location (loc); + json::object *result = new json::object (); + if (exploc.file) + result->set ("file", new json::string (exploc.file)); + result->set ("line", new json::integer_number (exploc.line)); +- result->set ("column", new json::integer_number (exploc.column)); ++ ++ const enum diagnostics_column_unit orig_unit = context->column_unit; ++ struct ++ { ++ const char *name; ++ enum diagnostics_column_unit unit; ++ } column_fields[] = { ++ {"display-column", DIAGNOSTICS_COLUMN_UNIT_DISPLAY}, ++ {"byte-column", DIAGNOSTICS_COLUMN_UNIT_BYTE} ++ }; ++ int the_column = INT_MIN; ++ for (int i = 0; i != sizeof column_fields / sizeof (*column_fields); ++i) ++ { ++ context->column_unit = column_fields[i].unit; ++ const int col = diagnostic_converted_column (context, exploc); ++ result->set (column_fields[i].name, new json::integer_number (col)); ++ if (column_fields[i].unit == orig_unit) ++ the_column = col; ++ } ++ gcc_assert (the_column != INT_MIN); ++ result->set ("column", new json::integer_number (the_column)); ++ context->column_unit = orig_unit; + return result; + } + + /* Generate a JSON object for LOC_RANGE. */ + + static json::object * +-json_from_location_range (const location_range *loc_range, unsigned range_idx) ++json_from_location_range (diagnostic_context *context, ++ const location_range *loc_range, unsigned range_idx) + { + location_t caret_loc = get_pure_location (loc_range->m_loc); + +@@ -68,13 +91,13 @@ json_from_location_range (const location + location_t finish_loc = get_finish (loc_range->m_loc); + + json::object *result = new json::object (); +- result->set ("caret", json_from_expanded_location (caret_loc)); ++ result->set ("caret", json_from_expanded_location (context, caret_loc)); + if (start_loc != caret_loc + && start_loc != UNKNOWN_LOCATION) +- result->set ("start", json_from_expanded_location (start_loc)); ++ result->set ("start", json_from_expanded_location (context, start_loc)); + if (finish_loc != caret_loc + && finish_loc != UNKNOWN_LOCATION) +- result->set ("finish", json_from_expanded_location (finish_loc)); ++ result->set ("finish", json_from_expanded_location (context, finish_loc)); + + if (loc_range->m_label) + { +@@ -91,14 +114,14 @@ json_from_location_range (const location + /* Generate a JSON object for HINT. */ + + static json::object * +-json_from_fixit_hint (const fixit_hint *hint) ++json_from_fixit_hint (diagnostic_context *context, const fixit_hint *hint) + { + json::object *fixit_obj = new json::object (); + + location_t start_loc = hint->get_start_loc (); +- fixit_obj->set ("start", json_from_expanded_location (start_loc)); ++ fixit_obj->set ("start", json_from_expanded_location (context, start_loc)); + location_t next_loc = hint->get_next_loc (); +- fixit_obj->set ("next", json_from_expanded_location (next_loc)); ++ fixit_obj->set ("next", json_from_expanded_location (context, next_loc)); + fixit_obj->set ("string", new json::string (hint->get_string ())); + + return fixit_obj; +@@ -190,11 +213,13 @@ json_end_diagnostic (diagnostic_context + else + { + /* Otherwise, make diag_obj be the top-level object within the group; +- add a "children" array. */ ++ add a "children" array and record the column origin. */ + toplevel_array->append (diag_obj); + cur_group = diag_obj; + cur_children_array = new json::array (); + diag_obj->set ("children", cur_children_array); ++ diag_obj->set ("column-origin", ++ new json::integer_number (context->column_origin)); + } + + const rich_location *richloc = diagnostic->richloc; +@@ -205,7 +230,7 @@ json_end_diagnostic (diagnostic_context + for (unsigned int i = 0; i < richloc->get_num_locations (); i++) + { + const location_range *loc_range = richloc->get_range (i); +- json::object *loc_obj = json_from_location_range (loc_range, i); ++ json::object *loc_obj = json_from_location_range (context, loc_range, i); + if (loc_obj) + loc_array->append (loc_obj); + } +@@ -217,7 +242,7 @@ json_end_diagnostic (diagnostic_context + for (unsigned int i = 0; i < richloc->get_num_fixit_hints (); i++) + { + const fixit_hint *hint = richloc->get_fixit_hint (i); +- json::object *fixit_obj = json_from_fixit_hint (hint); ++ json::object *fixit_obj = json_from_fixit_hint (context, hint); + fixit_array->append (fixit_obj); + } + } +@@ -320,7 +345,8 @@ namespace selftest { + static void + test_unknown_location () + { +- delete json_from_expanded_location (UNKNOWN_LOCATION); ++ test_diagnostic_context dc; ++ delete json_from_expanded_location (&dc, UNKNOWN_LOCATION); + } + + /* Verify that we gracefully handle attempts to serialize bad +@@ -338,7 +364,8 @@ test_bad_endpoints () + loc_range.m_range_display_kind = SHOW_RANGE_WITH_CARET; + loc_range.m_label = NULL; + +- json::object *obj = json_from_location_range (&loc_range, 0); ++ test_diagnostic_context dc; ++ json::object *obj = json_from_location_range (&dc, &loc_range, 0); + /* We should have a "caret" value, but no "start" or "finish" values. */ + ASSERT_TRUE (obj != NULL); + ASSERT_TRUE (obj->get ("caret") != NULL); +diff --git a/gcc/diagnostic.h b/gcc/diagnostic.h +--- a/gcc/diagnostic.h 2020-07-22 23:35:17.556386887 -0700 ++++ b/gcc/diagnostic.h 2021-12-25 01:20:53.479636627 -0800 +@@ -24,6 +24,20 @@ along with GCC; see the file COPYING3. + #include "pretty-print.h" + #include "diagnostic-core.h" + ++/* An enum for controlling what units to use for the column number ++ when diagnostics are output, used by the -fdiagnostics-column-unit option. ++ Tabs will be expanded or not according to the value of -ftabstop. The origin ++ (default 1) is controlled by -fdiagnostics-column-origin. */ ++ ++enum diagnostics_column_unit ++{ ++ /* The default from GCC 11 onwards: display columns. */ ++ DIAGNOSTICS_COLUMN_UNIT_DISPLAY, ++ ++ /* The behavior in GCC 10 and earlier: simple bytes. */ ++ DIAGNOSTICS_COLUMN_UNIT_BYTE ++}; ++ + /* Enum for overriding the standard output format. */ + + enum diagnostics_output_format +@@ -280,6 +294,15 @@ struct diagnostic_context + rest of the diagnostic. */ + bool parseable_fixits_p; + ++ /* What units to use when outputting the column number. */ ++ enum diagnostics_column_unit column_unit; ++ ++ /* The origin for the column number (1-based or 0-based typically). */ ++ int column_origin; ++ ++ /* The size of the tabstop for tab expansion. */ ++ int tabstop; ++ + /* If non-NULL, an edit_context to which fix-it hints should be + applied, for generating patches. */ + edit_context *edit_context_ptr; +@@ -458,6 +481,8 @@ diagnostic_same_line (const diagnostic_c + } + + extern const char *diagnostic_get_color_for_kind (diagnostic_t kind); ++extern int diagnostic_converted_column (diagnostic_context *context, ++ expanded_location s); + + /* Pure text formatting support functions. */ + extern char *file_name_as_prefix (diagnostic_context *, const char *); +@@ -470,6 +495,7 @@ extern void diagnostic_output_format_ini + /* Compute the number of digits in the decimal representation of an integer. */ + extern int num_digits (int); + +-extern json::value *json_from_expanded_location (location_t loc); ++extern json::value *json_from_expanded_location (diagnostic_context *context, ++ location_t loc); + + #endif /* ! GCC_DIAGNOSTIC_H */ +diff --git a/gcc/diagnostic-show-locus.c b/gcc/diagnostic-show-locus.c +--- a/gcc/diagnostic-show-locus.c 2020-07-22 23:35:17.556386887 -0700 ++++ b/gcc/diagnostic-show-locus.c 2021-12-25 01:20:53.479636627 -0800 +@@ -175,9 +175,10 @@ enum column_unit { + class exploc_with_display_col : public expanded_location + { + public: +- exploc_with_display_col (const expanded_location &exploc) ++ exploc_with_display_col (const expanded_location &exploc, int tabstop) + : expanded_location (exploc), +- m_display_col (location_compute_display_column (exploc)) {} ++ m_display_col (location_compute_display_column (exploc, tabstop)) ++ {} + + int m_display_col; + }; +@@ -189,11 +190,11 @@ class exploc_with_display_col : public e + class layout_point + { + public: +- layout_point (const expanded_location &exploc) ++ layout_point (const exploc_with_display_col &exploc) + : m_line (exploc.line) + { + m_columns[CU_BYTES] = exploc.column; +- m_columns[CU_DISPLAY_COLS] = location_compute_display_column (exploc); ++ m_columns[CU_DISPLAY_COLS] = exploc.m_display_col; + } + + linenum_type m_line; +@@ -205,10 +206,10 @@ class layout_point + class layout_range + { + public: +- layout_range (const expanded_location *start_exploc, +- const expanded_location *finish_exploc, ++ layout_range (const exploc_with_display_col &start_exploc, ++ const exploc_with_display_col &finish_exploc, + enum range_display_kind range_display_kind, +- const expanded_location *caret_exploc, ++ const exploc_with_display_col &caret_exploc, + unsigned original_idx, + const range_label *label); + +@@ -226,22 +227,18 @@ class layout_range + + /* A struct for use by layout::print_source_line for telling + layout::print_annotation_line the extents of the source line that +- it printed, so that underlines can be clipped appropriately. */ ++ it printed, so that underlines can be clipped appropriately. Units ++ are 1-based display columns. */ + + struct line_bounds + { +- int m_first_non_ws; +- int m_last_non_ws; ++ int m_first_non_ws_disp_col; ++ int m_last_non_ws_disp_col; + +- void convert_to_display_cols (char_span line) ++ line_bounds () + { +- m_first_non_ws = cpp_byte_column_to_display_column (line.get_buffer (), +- line.length (), +- m_first_non_ws); +- +- m_last_non_ws = cpp_byte_column_to_display_column (line.get_buffer (), +- line.length (), +- m_last_non_ws); ++ m_first_non_ws_disp_col = INT_MAX; ++ m_last_non_ws_disp_col = 0; + } + }; + +@@ -351,8 +348,8 @@ class layout + private: + bool will_show_line_p (linenum_type row) const; + void print_leading_fixits (linenum_type row); +- void print_source_line (linenum_type row, const char *line, int line_bytes, +- line_bounds *lbounds_out); ++ line_bounds print_source_line (linenum_type row, const char *line, ++ int line_bytes); + bool should_print_annotation_line_p (linenum_type row) const; + void start_annotation_line (char margin_char = ' ') const; + void print_annotation_line (linenum_type row, const line_bounds lbounds); +@@ -513,16 +510,16 @@ colorizer::get_color_by_name (const char + Initialize various layout_point fields from expanded_location + equivalents; we've already filtered on file. */ + +-layout_range::layout_range (const expanded_location *start_exploc, +- const expanded_location *finish_exploc, ++layout_range::layout_range (const exploc_with_display_col &start_exploc, ++ const exploc_with_display_col &finish_exploc, + enum range_display_kind range_display_kind, +- const expanded_location *caret_exploc, ++ const exploc_with_display_col &caret_exploc, + unsigned original_idx, + const range_label *label) +-: m_start (*start_exploc), +- m_finish (*finish_exploc), ++: m_start (start_exploc), ++ m_finish (finish_exploc), + m_range_display_kind (range_display_kind), +- m_caret (*caret_exploc), ++ m_caret (caret_exploc), + m_original_idx (original_idx), + m_label (label) + { +@@ -646,6 +643,9 @@ layout_range::intersects_line_p (linenum + + #if CHECKING_P + ++/* Default for when we don't care what the tab expansion is set to. */ ++static const int def_tabstop = 8; ++ + /* Create some expanded locations for testing layout_range. The filename + member of the explocs is set to the empty string. This member will only be + inspected by the calls to location_compute_display_column() made from the +@@ -662,8 +662,11 @@ make_range (int start_line, int start_co + = {"", start_line, start_col, NULL, false}; + const expanded_location finish_exploc + = {"", end_line, end_col, NULL, false}; +- return layout_range (&start_exploc, &finish_exploc, SHOW_RANGE_WITHOUT_CARET, +- &start_exploc, 0, NULL); ++ return layout_range (exploc_with_display_col (start_exploc, def_tabstop), ++ exploc_with_display_col (finish_exploc, def_tabstop), ++ SHOW_RANGE_WITHOUT_CARET, ++ exploc_with_display_col (start_exploc, def_tabstop), ++ 0, NULL); + } + + /* Selftests for layout_range::contains_point and +@@ -964,7 +967,7 @@ layout::layout (diagnostic_context * con + : m_context (context), + m_pp (context->printer), + m_primary_loc (richloc->get_range (0)->m_loc), +- m_exploc (richloc->get_expanded_location (0)), ++ m_exploc (richloc->get_expanded_location (0), context->tabstop), + m_colorizer (context, diagnostic_kind), + m_colorize_source_p (context->colorize_source_p), + m_show_labels_p (context->show_labels_p), +@@ -1060,7 +1063,10 @@ layout::maybe_add_location_range (const + + /* Everything is now known to be in the correct source file, + but it may require further sanitization. */ +- layout_range ri (&start, &finish, loc_range->m_range_display_kind, &caret, ++ layout_range ri (exploc_with_display_col (start, m_context->tabstop), ++ exploc_with_display_col (finish, m_context->tabstop), ++ loc_range->m_range_display_kind, ++ exploc_with_display_col (caret, m_context->tabstop), + original_idx, loc_range->m_label); + + /* If we have a range that finishes before it starts (perhaps +@@ -1394,7 +1400,7 @@ layout::calculate_x_offset_display () + = get_line_bytes_without_trailing_whitespace (line.get_buffer (), + line.length ()); + int eol_display_column +- = cpp_display_width (line.get_buffer (), line_bytes); ++ = cpp_display_width (line.get_buffer (), line_bytes, m_context->tabstop); + if (caret_display_column > eol_display_column + || !caret_display_column) + { +@@ -1445,16 +1451,13 @@ layout::calculate_x_offset_display () + } + + /* Print line ROW of source code, potentially colorized at any ranges, and +- populate *LBOUNDS_OUT. +- LINE is the source line (not necessarily 0-terminated) and LINE_BYTES +- is its length in bytes. +- This function deals only with byte offsets, not display columns, so +- m_x_offset_display must be converted from display to byte units. In +- particular, LINE_BYTES and LBOUNDS_OUT are in bytes. */ ++ return the line bounds. LINE is the source line (not necessarily ++ 0-terminated) and LINE_BYTES is its length in bytes. In order to handle both ++ colorization and tab expansion, this function tracks the line position in ++ both byte and display column units. */ + +-void +-layout::print_source_line (linenum_type row, const char *line, int line_bytes, +- line_bounds *lbounds_out) ++line_bounds ++layout::print_source_line (linenum_type row, const char *line, int line_bytes) + { + m_colorizer.set_normal_text (); + +@@ -1469,30 +1472,29 @@ layout::print_source_line (linenum_type + else + pp_space (m_pp); + +- /* We will stop printing the source line at any trailing whitespace, and start +- printing it as per m_x_offset_display. */ ++ /* We will stop printing the source line at any trailing whitespace. */ + line_bytes = get_line_bytes_without_trailing_whitespace (line, + line_bytes); +- int x_offset_bytes = 0; +- if (m_x_offset_display) +- { +- x_offset_bytes = cpp_display_column_to_byte_column (line, line_bytes, +- m_x_offset_display); +- /* In case the leading portion of the line that will be skipped over ends +- with a character with wcwidth > 1, then it is possible we skipped too +- much, so account for that by padding with spaces. */ +- const int overage +- = cpp_byte_column_to_display_column (line, line_bytes, x_offset_bytes) +- - m_x_offset_display; +- for (int column = 0; column < overage; ++column) +- pp_space (m_pp); +- line += x_offset_bytes; +- } + +- /* Print the line. */ +- int first_non_ws = INT_MAX; +- int last_non_ws = 0; +- for (int col_byte = 1 + x_offset_bytes; col_byte <= line_bytes; col_byte++) ++ /* This object helps to keep track of which display column we are at, which is ++ necessary for computing the line bounds in display units, for doing ++ tab expansion, and for implementing m_x_offset_display. */ ++ cpp_display_width_computation dw (line, line_bytes, m_context->tabstop); ++ ++ /* Skip the first m_x_offset_display display columns. In case the leading ++ portion that will be skipped ends with a character with wcwidth > 1, then ++ it is possible we skipped too much, so account for that by padding with ++ spaces. Note that this does the right thing too in case a tab was the last ++ character to be skipped over; the tab is effectively replaced by the ++ correct number of trailing spaces needed to offset by the desired number of ++ display columns. */ ++ for (int skipped_display_cols = dw.advance_display_cols (m_x_offset_display); ++ skipped_display_cols > m_x_offset_display; --skipped_display_cols) ++ pp_space (m_pp); ++ ++ /* Print the line and compute the line_bounds. */ ++ line_bounds lbounds; ++ while (!dw.done ()) + { + /* Assuming colorization is enabled for the caret and underline + characters, we may also colorize the associated characters +@@ -1510,7 +1512,8 @@ layout::print_source_line (linenum_type + { + bool in_range_p; + point_state state; +- in_range_p = get_state_at_point (row, col_byte, ++ const int start_byte_col = dw.bytes_processed () + 1; ++ in_range_p = get_state_at_point (row, start_byte_col, + 0, INT_MAX, + CU_BYTES, + &state); +@@ -1519,22 +1522,44 @@ layout::print_source_line (linenum_type + else + m_colorizer.set_normal_text (); + } +- char c = *line; +- if (c == '\0' || c == '\t' || c == '\r') +- c = ' '; +- if (c != ' ') ++ ++ /* Get the display width of the next character to be output, expanding ++ tabs and replacing some control bytes with spaces as necessary. */ ++ const char *c = dw.next_byte (); ++ const int start_disp_col = dw.display_cols_processed () + 1; ++ const int this_display_width = dw.process_next_codepoint (); ++ if (*c == '\t') ++ { ++ /* The returned display width is the number of spaces into which the ++ tab should be expanded. */ ++ for (int i = 0; i != this_display_width; ++i) ++ pp_space (m_pp); ++ continue; ++ } ++ if (*c == '\0' || *c == '\r') + { +- last_non_ws = col_byte; +- if (first_non_ws == INT_MAX) +- first_non_ws = col_byte; ++ /* cpp_wcwidth() promises to return 1 for all control bytes, and we ++ want to output these as a single space too, so this case is ++ actually the same as the '\t' case. */ ++ gcc_assert (this_display_width == 1); ++ pp_space (m_pp); ++ continue; + } +- pp_character (m_pp, c); +- line++; ++ ++ /* We have a (possibly multibyte) character to output; update the line ++ bounds if it is not whitespace. */ ++ if (*c != ' ') ++ { ++ lbounds.m_last_non_ws_disp_col = dw.display_cols_processed (); ++ if (lbounds.m_first_non_ws_disp_col == INT_MAX) ++ lbounds.m_first_non_ws_disp_col = start_disp_col; ++ } ++ ++ /* Output the character. */ ++ while (c != dw.next_byte ()) pp_character (m_pp, *c++); + } + print_newline (); +- +- lbounds_out->m_first_non_ws = first_non_ws; +- lbounds_out->m_last_non_ws = last_non_ws; ++ return lbounds; + } + + /* Determine if we should print an annotation line for ROW. +@@ -1576,14 +1601,13 @@ layout::start_annotation_line (char marg + } + + /* Print a line consisting of the caret/underlines for the given +- source line. This function works with display columns, rather than byte +- counts; in particular, LBOUNDS should be in display column units. */ ++ source line. */ + + void + layout::print_annotation_line (linenum_type row, const line_bounds lbounds) + { + int x_bound = get_x_bound_for_row (row, m_exploc.m_display_col, +- lbounds.m_last_non_ws); ++ lbounds.m_last_non_ws_disp_col); + + start_annotation_line (); + pp_space (m_pp); +@@ -1593,8 +1617,8 @@ layout::print_annotation_line (linenum_t + bool in_range_p; + point_state state; + in_range_p = get_state_at_point (row, column, +- lbounds.m_first_non_ws, +- lbounds.m_last_non_ws, ++ lbounds.m_first_non_ws_disp_col, ++ lbounds.m_last_non_ws_disp_col, + CU_DISPLAY_COLS, + &state); + if (in_range_p) +@@ -1631,12 +1655,14 @@ layout::print_annotation_line (linenum_t + class line_label + { + public: +- line_label (int state_idx, int column, label_text text) ++ line_label (diagnostic_context *context, int state_idx, int column, ++ label_text text) + : m_state_idx (state_idx), m_column (column), + m_text (text), m_label_line (0), m_has_vbar (true) + { + const int bytes = strlen (text.m_buffer); +- m_display_width = cpp_display_width (text.m_buffer, bytes); ++ m_display_width ++ = cpp_display_width (text.m_buffer, bytes, context->tabstop); + } + + /* Sorting is primarily by column, then by state index. */ +@@ -1696,7 +1722,7 @@ layout::print_any_labels (linenum_type r + if (text.m_buffer == NULL) + continue; + +- labels.safe_push (line_label (i, disp_col, text)); ++ labels.safe_push (line_label (m_context, i, disp_col, text)); + } + } + +@@ -1976,7 +2002,8 @@ public: + + /* Get the range of bytes or display columns that HINT would affect. */ + static column_range +-get_affected_range (const fixit_hint *hint, enum column_unit col_unit) ++get_affected_range (diagnostic_context *context, ++ const fixit_hint *hint, enum column_unit col_unit) + { + expanded_location exploc_start = expand_location (hint->get_start_loc ()); + expanded_location exploc_finish = expand_location (hint->get_next_loc ()); +@@ -1986,11 +2013,13 @@ get_affected_range (const fixit_hint *hi + int finish_column; + if (col_unit == CU_DISPLAY_COLS) + { +- start_column = location_compute_display_column (exploc_start); ++ start_column ++ = location_compute_display_column (exploc_start, context->tabstop); + if (hint->insertion_p ()) + finish_column = start_column - 1; + else +- finish_column = location_compute_display_column (exploc_finish); ++ finish_column ++ = location_compute_display_column (exploc_finish, context->tabstop); + } + else + { +@@ -2003,12 +2032,12 @@ get_affected_range (const fixit_hint *hi + /* Get the range of display columns that would be printed for HINT. */ + + static column_range +-get_printed_columns (const fixit_hint *hint) ++get_printed_columns (diagnostic_context *context, const fixit_hint *hint) + { + expanded_location exploc = expand_location (hint->get_start_loc ()); +- int start_column = location_compute_display_column (exploc); +- int hint_width = cpp_display_width (hint->get_string (), +- hint->get_length ()); ++ int start_column = location_compute_display_column (exploc, context->tabstop); ++ int hint_width = cpp_display_width (hint->get_string (), hint->get_length (), ++ context->tabstop); + int final_hint_column = start_column + hint_width - 1; + if (hint->insertion_p ()) + { +@@ -2018,7 +2047,8 @@ get_printed_columns (const fixit_hint *h + { + exploc = expand_location (hint->get_next_loc ()); + --exploc.column; +- int finish_column = location_compute_display_column (exploc); ++ int finish_column ++ = location_compute_display_column (exploc, context->tabstop); + return column_range (start_column, + MAX (finish_column, final_hint_column)); + } +@@ -2035,12 +2065,14 @@ public: + correction (column_range affected_bytes, + column_range affected_columns, + column_range printed_columns, +- const char *new_text, size_t new_text_len) ++ const char *new_text, size_t new_text_len, ++ int tabstop) + : m_affected_bytes (affected_bytes), + m_affected_columns (affected_columns), + m_printed_columns (printed_columns), + m_text (xstrdup (new_text)), + m_byte_length (new_text_len), ++ m_tabstop (tabstop), + m_alloc_sz (new_text_len + 1) + { + compute_display_cols (); +@@ -2058,7 +2090,7 @@ public: + + void compute_display_cols () + { +- m_display_cols = cpp_display_width (m_text, m_byte_length); ++ m_display_cols = cpp_display_width (m_text, m_byte_length, m_tabstop); + } + + void overwrite (int dst_offset, const char_span &src_span) +@@ -2086,6 +2118,7 @@ public: + char *m_text; + size_t m_byte_length; /* Not including null-terminator. */ + int m_display_cols; ++ int m_tabstop; + size_t m_alloc_sz; + }; + +@@ -2121,13 +2154,15 @@ correction::ensure_terminated () + class line_corrections + { + public: +- line_corrections (const char *filename, linenum_type row) +- : m_filename (filename), m_row (row) ++ line_corrections (diagnostic_context *context, const char *filename, ++ linenum_type row) ++ : m_context (context), m_filename (filename), m_row (row) + {} + ~line_corrections (); + + void add_hint (const fixit_hint *hint); + ++ diagnostic_context *m_context; + const char *m_filename; + linenum_type m_row; + auto_vec <correction *> m_corrections; +@@ -2173,9 +2208,10 @@ source_line::source_line (const char *fi + void + line_corrections::add_hint (const fixit_hint *hint) + { +- column_range affected_bytes = get_affected_range (hint, CU_BYTES); +- column_range affected_columns = get_affected_range (hint, CU_DISPLAY_COLS); +- column_range printed_columns = get_printed_columns (hint); ++ column_range affected_bytes = get_affected_range (m_context, hint, CU_BYTES); ++ column_range affected_columns = get_affected_range (m_context, hint, ++ CU_DISPLAY_COLS); ++ column_range printed_columns = get_printed_columns (m_context, hint); + + /* Potentially consolidate. */ + if (!m_corrections.is_empty ()) +@@ -2243,7 +2279,8 @@ line_corrections::add_hint (const fixit_ + affected_columns, + printed_columns, + hint->get_string (), +- hint->get_length ())); ++ hint->get_length (), ++ m_context->tabstop)); + } + + /* If there are any fixit hints on source line ROW, print them. +@@ -2257,7 +2294,7 @@ layout::print_trailing_fixits (linenum_t + { + /* Build a list of correction instances for the line, + potentially consolidating hints (for the sake of readability). */ +- line_corrections corrections (m_exploc.file, row); ++ line_corrections corrections (m_context, m_exploc.file, row); + for (unsigned int i = 0; i < m_fixit_hints.length (); i++) + { + const fixit_hint *hint = m_fixit_hints[i]; +@@ -2499,15 +2536,11 @@ layout::print_line (linenum_type row) + if (!line) + return; + +- line_bounds lbounds; + print_leading_fixits (row); +- print_source_line (row, line.get_buffer (), line.length (), &lbounds); ++ const line_bounds lbounds ++ = print_source_line (row, line.get_buffer (), line.length ()); + if (should_print_annotation_line_p (row)) +- { +- if (lbounds.m_first_non_ws != INT_MAX) +- lbounds.convert_to_display_cols (line); +- print_annotation_line (row, lbounds); +- } ++ print_annotation_line (row, lbounds); + if (m_show_labels_p) + print_any_labels (row); + print_trailing_fixits (row); +@@ -2670,9 +2703,11 @@ test_layout_x_offset_display_utf8 (const + + char_span lspan = location_get_source_line (tmp.get_filename (), 1); + ASSERT_EQ (line_display_cols, +- cpp_display_width (lspan.get_buffer (), lspan.length ())); ++ cpp_display_width (lspan.get_buffer (), lspan.length (), ++ def_tabstop)); + ASSERT_EQ (line_display_cols, +- location_compute_display_column (expand_location (line_end))); ++ location_compute_display_column (expand_location (line_end), ++ def_tabstop)); + ASSERT_EQ (0, memcmp (lspan.get_buffer () + (emoji_col - 1), + "\xf0\x9f\x98\x82\xf0\x9f\x98\x82", 8)); + +@@ -2774,6 +2809,111 @@ test_layout_x_offset_display_utf8 (const + + } + ++static void ++test_layout_x_offset_display_tab (const line_table_case &case_) ++{ ++ const char *content ++ = "This line is very long, so that we can use it to test the logic for " ++ "clipping long lines. Also this: `\t' is a tab that occupies 1 byte and " ++ "a variable number of display columns, starting at column #103.\n"; ++ ++ /* Number of bytes in the line, subtracting one to remove the newline. */ ++ const int line_bytes = strlen (content) - 1; ++ ++ /* The column where the tab begins. Byte or display is the same as there are ++ no multibyte characters earlier on the line. */ ++ const int tab_col = 103; ++ ++ /* Effective extra size of the tab beyond what a single space would have taken ++ up, indexed by tabstop. */ ++ static const int num_tabstops = 11; ++ int extra_width[num_tabstops]; ++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop) ++ { ++ const int this_tab_size = tabstop - (tab_col - 1) % tabstop; ++ extra_width[tabstop] = this_tab_size - 1; ++ } ++ /* Example of this calculation: if tabstop is 10, the tab starting at column ++ #103 has to expand into 8 spaces, covering columns 103-110, so that the ++ next character is at column #111. So it takes up 7 more columns than ++ a space would have taken up. */ ++ ASSERT_EQ (7, extra_width[10]); ++ ++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content); ++ line_table_test ltt (case_); ++ ++ linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 1); ++ ++ location_t line_end = linemap_position_for_column (line_table, line_bytes); ++ ++ /* Don't attempt to run the tests if column data might be unavailable. */ ++ if (line_end > LINE_MAP_MAX_LOCATION_WITH_COLS) ++ return; ++ ++ /* Check that cpp_display_width handles the tabs as expected. */ ++ char_span lspan = location_get_source_line (tmp.get_filename (), 1); ++ ASSERT_EQ ('\t', *(lspan.get_buffer () + (tab_col - 1))); ++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop) ++ { ++ ASSERT_EQ (line_bytes + extra_width[tabstop], ++ cpp_display_width (lspan.get_buffer (), lspan.length (), ++ tabstop)); ++ ASSERT_EQ (line_bytes + extra_width[tabstop], ++ location_compute_display_column (expand_location (line_end), ++ tabstop)); ++ } ++ ++ /* Check that the tab is expanded to the expected number of spaces. */ ++ rich_location richloc (line_table, ++ linemap_position_for_column (line_table, ++ tab_col + 1)); ++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop) ++ { ++ test_diagnostic_context dc; ++ dc.tabstop = tabstop; ++ layout test_layout (&dc, &richloc, DK_ERROR); ++ test_layout.print_line (1); ++ const char *out = pp_formatted_text (dc.printer); ++ ASSERT_EQ (NULL, strchr (out, '\t')); ++ const char *left_quote = strchr (out, '`'); ++ const char *right_quote = strchr (out, '\''); ++ ASSERT_NE (NULL, left_quote); ++ ASSERT_NE (NULL, right_quote); ++ ASSERT_EQ (right_quote - left_quote, extra_width[tabstop] + 2); ++ } ++ ++ /* Check that the line is offset properly and that the tab is broken up ++ into the expected number of spaces when it is the last character skipped ++ over. */ ++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop) ++ { ++ test_diagnostic_context dc; ++ dc.tabstop = tabstop; ++ static const int small_width = 24; ++ dc.caret_max_width = small_width - 4; ++ dc.min_margin_width = test_left_margin - test_linenum_sep + 1; ++ dc.show_line_numbers_p = true; ++ layout test_layout (&dc, &richloc, DK_ERROR); ++ test_layout.print_line (1); ++ ++ /* We have arranged things so that two columns will be printed before ++ the caret. If the tab results in more than one space, this should ++ produce two spaces in the output; otherwise, it will be a single space ++ preceded by the opening quote before the tab character. */ ++ const char *output1 ++ = " 1 | ' is a tab that occupies 1 byte and a variable number of " ++ "display columns, starting at column #103.\n" ++ " | ^\n\n"; ++ const char *output2 ++ = " 1 | ` ' is a tab that occupies 1 byte and a variable number of " ++ "display columns, starting at column #103.\n" ++ " | ^\n\n"; ++ const char *expected_output = (extra_width[tabstop] ? output1 : output2); ++ ASSERT_STREQ (expected_output, pp_formatted_text (dc.printer)); ++ } ++} ++ ++ + /* Verify that diagnostic_show_locus works sanely on UNKNOWN_LOCATION. */ + + static void +@@ -3854,6 +3994,27 @@ test_one_liner_labels_utf8 () + } + } + ++/* Make sure that colorization codes don't interrupt a multibyte ++ sequence, which would corrupt it. */ ++static void ++test_one_liner_colorized_utf8 () ++{ ++ test_diagnostic_context dc; ++ dc.colorize_source_p = true; ++ diagnostic_color_init (&dc, DIAGNOSTICS_COLOR_YES); ++ const location_t pi = linemap_position_for_column (line_table, 12); ++ rich_location richloc (line_table, pi); ++ diagnostic_show_locus (&dc, &richloc, DK_ERROR); ++ ++ /* In order to avoid having the test depend on exactly how the colorization ++ was effected, just confirm there are two pi characters in the output. */ ++ const char *result = pp_formatted_text (dc.printer); ++ const char *null_term = result + strlen (result); ++ const char *first_pi = strstr (result, "\xcf\x80"); ++ ASSERT_TRUE (first_pi && first_pi <= null_term - 2); ++ ASSERT_STR_CONTAINS (first_pi + 2, "\xcf\x80"); ++} ++ + /* Run the various one-liner tests. */ + + static void +@@ -3884,8 +4045,10 @@ test_diagnostic_show_locus_one_liner_utf + ASSERT_EQ (31, LOCATION_COLUMN (line_end)); + + char_span lspan = location_get_source_line (tmp.get_filename (), 1); +- ASSERT_EQ (25, cpp_display_width (lspan.get_buffer (), lspan.length ())); +- ASSERT_EQ (25, location_compute_display_column (expand_location (line_end))); ++ ASSERT_EQ (25, cpp_display_width (lspan.get_buffer (), lspan.length (), ++ def_tabstop)); ++ ASSERT_EQ (25, location_compute_display_column (expand_location (line_end), ++ def_tabstop)); + + test_one_liner_simple_caret_utf8 (); + test_one_liner_caret_and_range_utf8 (); +@@ -3900,6 +4063,7 @@ test_diagnostic_show_locus_one_liner_utf + test_one_liner_many_fixits_1_utf8 (); + test_one_liner_many_fixits_2_utf8 (); + test_one_liner_labels_utf8 (); ++ test_one_liner_colorized_utf8 (); + } + + /* Verify that gcc_rich_location::add_location_if_nearby works. */ +@@ -4272,25 +4436,28 @@ test_overlapped_fixit_printing (const li + /* Unit-test the line_corrections machinery. */ + ASSERT_EQ (3, richloc.get_num_fixit_hints ()); + const fixit_hint *hint_0 = richloc.get_fixit_hint (0); +- ASSERT_EQ (column_range (12, 12), get_affected_range (hint_0, CU_BYTES)); + ASSERT_EQ (column_range (12, 12), +- get_affected_range (hint_0, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (12, 22), get_printed_columns (hint_0)); ++ get_affected_range (&dc, hint_0, CU_BYTES)); ++ ASSERT_EQ (column_range (12, 12), ++ get_affected_range (&dc, hint_0, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0)); + const fixit_hint *hint_1 = richloc.get_fixit_hint (1); +- ASSERT_EQ (column_range (18, 18), get_affected_range (hint_1, CU_BYTES)); + ASSERT_EQ (column_range (18, 18), +- get_affected_range (hint_1, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (18, 20), get_printed_columns (hint_1)); ++ get_affected_range (&dc, hint_1, CU_BYTES)); ++ ASSERT_EQ (column_range (18, 18), ++ get_affected_range (&dc, hint_1, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1)); + const fixit_hint *hint_2 = richloc.get_fixit_hint (2); +- ASSERT_EQ (column_range (29, 28), get_affected_range (hint_2, CU_BYTES)); + ASSERT_EQ (column_range (29, 28), +- get_affected_range (hint_2, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (29, 29), get_printed_columns (hint_2)); ++ get_affected_range (&dc, hint_2, CU_BYTES)); ++ ASSERT_EQ (column_range (29, 28), ++ get_affected_range (&dc, hint_2, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (29, 29), get_printed_columns (&dc, hint_2)); + + /* Add each hint in turn to a line_corrections instance, + and verify that they are consolidated into one correction instance + as expected. */ +- line_corrections lc (tmp.get_filename (), 1); ++ line_corrections lc (&dc, tmp.get_filename (), 1); + + /* The first replace hint by itself. */ + lc.add_hint (hint_0); +@@ -4484,25 +4651,28 @@ test_overlapped_fixit_printing_utf8 (con + /* Unit-test the line_corrections machinery. */ + ASSERT_EQ (3, richloc.get_num_fixit_hints ()); + const fixit_hint *hint_0 = richloc.get_fixit_hint (0); +- ASSERT_EQ (column_range (14, 14), get_affected_range (hint_0, CU_BYTES)); ++ ASSERT_EQ (column_range (14, 14), ++ get_affected_range (&dc, hint_0, CU_BYTES)); + ASSERT_EQ (column_range (12, 12), +- get_affected_range (hint_0, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (12, 22), get_printed_columns (hint_0)); ++ get_affected_range (&dc, hint_0, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0)); + const fixit_hint *hint_1 = richloc.get_fixit_hint (1); +- ASSERT_EQ (column_range (22, 22), get_affected_range (hint_1, CU_BYTES)); ++ ASSERT_EQ (column_range (22, 22), ++ get_affected_range (&dc, hint_1, CU_BYTES)); + ASSERT_EQ (column_range (18, 18), +- get_affected_range (hint_1, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (18, 20), get_printed_columns (hint_1)); ++ get_affected_range (&dc, hint_1, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1)); + const fixit_hint *hint_2 = richloc.get_fixit_hint (2); +- ASSERT_EQ (column_range (35, 34), get_affected_range (hint_2, CU_BYTES)); ++ ASSERT_EQ (column_range (35, 34), ++ get_affected_range (&dc, hint_2, CU_BYTES)); + ASSERT_EQ (column_range (30, 29), +- get_affected_range (hint_2, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (30, 30), get_printed_columns (hint_2)); ++ get_affected_range (&dc, hint_2, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (30, 30), get_printed_columns (&dc, hint_2)); + + /* Add each hint in turn to a line_corrections instance, + and verify that they are consolidated into one correction instance + as expected. */ +- line_corrections lc (tmp.get_filename (), 1); ++ line_corrections lc (&dc, tmp.get_filename (), 1); + + /* The first replace hint by itself. */ + lc.add_hint (hint_0); +@@ -4689,6 +4859,8 @@ test_overlapped_fixit_printing_2 (const + + /* Two insertions, in the wrong order. */ + { ++ test_diagnostic_context dc; ++ + rich_location richloc (line_table, col_20); + richloc.add_fixit_insert_before (col_23, "{"); + richloc.add_fixit_insert_before (col_21, "}"); +@@ -4696,14 +4868,15 @@ test_overlapped_fixit_printing_2 (const + /* These fixits should be accepted; they can't be consolidated. */ + ASSERT_EQ (2, richloc.get_num_fixit_hints ()); + const fixit_hint *hint_0 = richloc.get_fixit_hint (0); +- ASSERT_EQ (column_range (23, 22), get_affected_range (hint_0, CU_BYTES)); +- ASSERT_EQ (column_range (23, 23), get_printed_columns (hint_0)); ++ ASSERT_EQ (column_range (23, 22), ++ get_affected_range (&dc, hint_0, CU_BYTES)); ++ ASSERT_EQ (column_range (23, 23), get_printed_columns (&dc, hint_0)); + const fixit_hint *hint_1 = richloc.get_fixit_hint (1); +- ASSERT_EQ (column_range (21, 20), get_affected_range (hint_1, CU_BYTES)); +- ASSERT_EQ (column_range (21, 21), get_printed_columns (hint_1)); ++ ASSERT_EQ (column_range (21, 20), ++ get_affected_range (&dc, hint_1, CU_BYTES)); ++ ASSERT_EQ (column_range (21, 21), get_printed_columns (&dc, hint_1)); + + /* Verify that they're printed correctly. */ +- test_diagnostic_context dc; + diagnostic_show_locus (&dc, &richloc, DK_ERROR); + ASSERT_STREQ (" int a5[][0][0] = { 1, 2 };\n" + " ^\n" +@@ -4955,6 +5128,65 @@ test_fixit_deletion_affecting_newline (c + pp_formatted_text (dc.printer)); + } + ++static void ++test_tab_expansion (const line_table_case &case_) ++{ ++ /* Create a tempfile and write some text to it. This example uses a tabstop ++ of 8, as the column numbers attempt to indicate: ++ ++ .....................000.01111111111.22222333333 display ++ .....................123.90123456789.56789012345 columns */ ++ const char *content = " \t This: `\t' is a tab.\n"; ++ /* ....................000 00000011111 11111222222 byte ++ ....................123 45678901234 56789012345 columns */ ++ ++ const int tabstop = 8; ++ const int first_non_ws_byte_col = 7; ++ const int right_quote_byte_col = 15; ++ const int last_byte_col = 25; ++ ASSERT_EQ (35, cpp_display_width (content, last_byte_col, tabstop)); ++ ++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content); ++ line_table_test ltt (case_); ++ linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 1); ++ ++ /* Don't attempt to run the tests if column data might be unavailable. */ ++ location_t line_end = linemap_position_for_column (line_table, last_byte_col); ++ if (line_end > LINE_MAP_MAX_LOCATION_WITH_COLS) ++ return; ++ ++ /* Check that the leading whitespace with mixed tabs and spaces is expanded ++ into 11 spaces. Recall that print_line() also puts one space before ++ everything too. */ ++ { ++ test_diagnostic_context dc; ++ dc.tabstop = tabstop; ++ rich_location richloc (line_table, ++ linemap_position_for_column (line_table, ++ first_non_ws_byte_col)); ++ layout test_layout (&dc, &richloc, DK_ERROR); ++ test_layout.print_line (1); ++ ASSERT_STREQ (" This: ` ' is a tab.\n" ++ " ^\n", ++ pp_formatted_text (dc.printer)); ++ } ++ ++ /* Confirm the display width was tracked correctly across the internal tab ++ as well. */ ++ { ++ test_diagnostic_context dc; ++ dc.tabstop = tabstop; ++ rich_location richloc (line_table, ++ linemap_position_for_column (line_table, ++ right_quote_byte_col)); ++ layout test_layout (&dc, &richloc, DK_ERROR); ++ test_layout.print_line (1); ++ ASSERT_STREQ (" This: ` ' is a tab.\n" ++ " ^\n", ++ pp_formatted_text (dc.printer)); ++ } ++} ++ + /* Verify that line numbers are correctly printed for the case of + a multiline range in which the width of the line numbers changes + (e.g. from "9" to "10"). */ +@@ -5012,6 +5244,7 @@ diagnostic_show_locus_c_tests () + test_layout_range_for_multiple_lines (); + + for_each_line_table_case (test_layout_x_offset_display_utf8); ++ for_each_line_table_case (test_layout_x_offset_display_tab); + + test_get_line_bytes_without_trailing_whitespace (); + +@@ -5029,6 +5262,7 @@ diagnostic_show_locus_c_tests () + for_each_line_table_case (test_fixit_insert_containing_newline_2); + for_each_line_table_case (test_fixit_replace_containing_newline); + for_each_line_table_case (test_fixit_deletion_affecting_newline); ++ for_each_line_table_case (test_tab_expansion); + + test_line_numbers_multiline_range (); + } +diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi +--- a/gcc/doc/invoke.texi 2021-12-24 20:23:46.876739587 -0800 ++++ b/gcc/doc/invoke.texi 2021-12-25 01:20:53.487636494 -0800 +@@ -293,7 +293,9 @@ Objective-C and Objective-C++ Dialects}. + -fdiagnostics-show-template-tree -fno-elide-type @gol + -fdiagnostics-path-format=@r{[}none@r{|}separate-events@r{|}inline-events@r{]} @gol + -fdiagnostics-show-path-depths @gol +--fno-show-column} ++-fno-show-column @gol ++-fdiagnostics-column-unit=@r{[}display@r{|}byte@r{]} @gol ++-fdiagnostics-column-origin=@var{origin}} + + @item Warning Options + @xref{Warning Options,,Options to Request or Suppress Warnings}. +@@ -4424,6 +4426,31 @@ Do not print column numbers in diagnosti + diagnostics are being scanned by a program that does not understand the + column numbers, such as @command{dejagnu}. + ++@item -fdiagnostics-column-unit=@var{UNIT} ++@opindex fdiagnostics-column-unit ++Select the units for the column number. This affects traditional diagnostics ++(in the absence of @option{-fno-show-column}), as well as JSON format ++diagnostics if requested. ++ ++The default @var{UNIT}, @samp{display}, considers the number of display ++columns occupied by each character. This may be larger than the number ++of bytes required to encode the character, in the case of tab ++characters, or it may be smaller, in the case of multibyte characters. ++For example, the character ``GREEK SMALL LETTER PI (U+03C0)'' occupies one ++display column, and its UTF-8 encoding requires two bytes; the character ++``SLIGHTLY SMILING FACE (U+1F642)'' occupies two display columns, and ++its UTF-8 encoding requires four bytes. ++ ++Setting @var{UNIT} to @samp{byte} changes the column number to the raw byte ++count in all cases, as was traditionally output by GCC prior to version 11.1.0. ++ ++@item -fdiagnostics-column-origin=@var{ORIGIN} ++@opindex fdiagnostics-column-origin ++Select the origin for column numbers, i.e. the column number assigned to the ++first column. The default value of 1 corresponds to traditional GCC ++behavior and to the GNU style guide. Some utilities may perform better with an ++origin of 0; any non-negative value may be specified. ++ + @item -fdiagnostics-format=@var{FORMAT} + @opindex fdiagnostics-format + Select a different format for printing diagnostics. +@@ -4459,11 +4486,15 @@ might be printed in JSON form (after for + "locations": [ + @{ + "caret": @{ ++ "display-column": 3, ++ "byte-column": 3, + "column": 3, + "file": "misleading-indentation.c", + "line": 15 + @}, + "finish": @{ ++ "display-column": 4, ++ "byte-column": 4, + "column": 4, + "file": "misleading-indentation.c", + "line": 15 +@@ -4479,6 +4510,8 @@ might be printed in JSON form (after for + "locations": [ + @{ + "caret": @{ ++ "display-column": 5, ++ "byte-column": 5, + "column": 5, + "file": "misleading-indentation.c", + "line": 17 +@@ -4488,6 +4521,7 @@ might be printed in JSON form (after for + "message": "...this statement, but the latter is @dots{}" + @} + ] ++ "column-origin": 1, + @}, + @dots{} + ] +@@ -4500,10 +4534,34 @@ A diagnostic has a @code{kind}. If this + an @code{option} key describing the command-line option controlling the + warning. + +-A diagnostic can contain zero or more locations. Each location has up +-to three positions within it: a @code{caret} position and optional +-@code{start} and @code{finish} positions. A location can also have +-an optional @code{label} string. For example, this error: ++A diagnostic can contain zero or more locations. Each location has an ++optional @code{label} string and up to three positions within it: a ++@code{caret} position and optional @code{start} and @code{finish} positions. ++A position is described by a @code{file} name, a @code{line} number, and ++three numbers indicating a column position: ++@itemize @bullet ++ ++@item ++@code{display-column} counts display columns, accounting for tabs and ++multibyte characters. ++ ++@item ++@code{byte-column} counts raw bytes. ++ ++@item ++@code{column} is equal to one of ++the previous two, as dictated by the @option{-fdiagnostics-column-unit} ++option. ++ ++@end itemize ++All three columns are relative to the origin specified by ++@option{-fdiagnostics-column-origin}, which is typically equal to 1 but may ++be set, for instance, to 0 for compatibility with other utilities that ++number columns from 0. The column origin is recorded in the JSON output in ++the @code{column-origin} tag. In the remaining examples below, the extra ++column number outputs have been omitted for brevity. ++ ++For example, this error: + + @smallexample + bad-binary-ops.c:64:23: error: invalid operands to binary + (have 'S' @{aka +diff --git a/gcc/input.c b/gcc/input.c +--- a/gcc/input.c 2020-07-22 23:35:17.664388078 -0700 ++++ b/gcc/input.c 2021-12-25 01:20:53.487636494 -0800 +@@ -913,7 +913,7 @@ make_location (location_t caret, source_ + source line in order to calculate the display width. If that cannot be done + for any reason, then returns the byte column as a fallback. */ + int +-location_compute_display_column (expanded_location exploc) ++location_compute_display_column (expanded_location exploc, int tabstop) + { + if (!(exploc.file && *exploc.file && exploc.line && exploc.column)) + return exploc.column; +@@ -921,7 +921,7 @@ location_compute_display_column (expande + /* If line is NULL, this function returns exploc.column which is the + desired fallback. */ + return cpp_byte_column_to_display_column (line.get_buffer (), line.length (), +- exploc.column); ++ exploc.column, tabstop); + } + + /* Dump statistics to stderr about the memory usage of the line_table +@@ -3608,33 +3608,46 @@ test_line_offset_overflow () + + void test_cpp_utf8 () + { ++ const int def_tabstop = 8; + /* Verify that wcwidth of invalid UTF-8 or control bytes is 1. */ + { +- int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8); ++ int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8, def_tabstop); + ASSERT_EQ (8, w_bad); +- int w_ctrl = cpp_display_width ("\r\t\n\v\0\1", 6); +- ASSERT_EQ (6, w_ctrl); ++ int w_ctrl = cpp_display_width ("\r\n\v\0\1", 5, def_tabstop); ++ ASSERT_EQ (5, w_ctrl); + } + + /* Verify that wcwidth of valid UTF-8 is as expected. */ + { +- const int w_pi = cpp_display_width ("\xcf\x80", 2); ++ const int w_pi = cpp_display_width ("\xcf\x80", 2, def_tabstop); + ASSERT_EQ (1, w_pi); +- const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4); ++ const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4, def_tabstop); + ASSERT_EQ (2, w_emoji); +- const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2); ++ const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2, ++ def_tabstop); + ASSERT_EQ (1, w_umlaut_precomposed); +- const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3); ++ const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3, ++ def_tabstop); + ASSERT_EQ (1, w_umlaut_combining); +- const int w_han = cpp_display_width ("\xe4\xb8\xba", 3); ++ const int w_han = cpp_display_width ("\xe4\xb8\xba", 3, def_tabstop); + ASSERT_EQ (2, w_han); +- const int w_ascii = cpp_display_width ("GCC", 3); ++ const int w_ascii = cpp_display_width ("GCC", 3, def_tabstop); + ASSERT_EQ (3, w_ascii); + const int w_mixed = cpp_display_width ("\xcf\x80 = 3.14 \xf0\x9f\x98\x82" +- "\x9f! \xe4\xb8\xba y\xcc\x88", 24); ++ "\x9f! \xe4\xb8\xba y\xcc\x88", ++ 24, def_tabstop); + ASSERT_EQ (18, w_mixed); + } + ++ /* Verify that display width properly expands tabs. */ ++ { ++ const char *tstr = "\tabc\td"; ++ ASSERT_EQ (6, cpp_display_width (tstr, 6, 1)); ++ ASSERT_EQ (10, cpp_display_width (tstr, 6, 3)); ++ ASSERT_EQ (17, cpp_display_width (tstr, 6, 8)); ++ ASSERT_EQ (1, cpp_display_column_to_byte_column (tstr, 6, 7, 8)); ++ } ++ + /* Verify that cpp_byte_column_to_display_column can go past the end, + and similar edge cases. */ + { +@@ -3645,10 +3658,13 @@ void test_cpp_utf8 () + /* 111122223456 + Byte columns. */ + +- ASSERT_EQ (5, cpp_display_width (str, 6)); +- ASSERT_EQ (105, cpp_byte_column_to_display_column (str, 6, 106)); +- ASSERT_EQ (10000, cpp_byte_column_to_display_column (NULL, 0, 10000)); +- ASSERT_EQ (0, cpp_byte_column_to_display_column (NULL, 10000, 0)); ++ ASSERT_EQ (5, cpp_display_width (str, 6, def_tabstop)); ++ ASSERT_EQ (105, ++ cpp_byte_column_to_display_column (str, 6, 106, def_tabstop)); ++ ASSERT_EQ (10000, ++ cpp_byte_column_to_display_column (NULL, 0, 10000, def_tabstop)); ++ ASSERT_EQ (0, ++ cpp_byte_column_to_display_column (NULL, 10000, 0, def_tabstop)); + } + + /* Verify that cpp_display_column_to_byte_column can go past the end, +@@ -3662,21 +3678,25 @@ void test_cpp_utf8 () + /* 000000000000000000000000000000000111111 + 111122223333444456666777788889999012345 + Byte columns. */ +- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2)); +- ASSERT_EQ (15, cpp_display_column_to_byte_column (str, 15, 11)); +- ASSERT_EQ (115, cpp_display_column_to_byte_column (str, 15, 111)); +- ASSERT_EQ (10000, cpp_display_column_to_byte_column (NULL, 0, 10000)); +- ASSERT_EQ (0, cpp_display_column_to_byte_column (NULL, 10000, 0)); ++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2, def_tabstop)); ++ ASSERT_EQ (15, ++ cpp_display_column_to_byte_column (str, 15, 11, def_tabstop)); ++ ASSERT_EQ (115, ++ cpp_display_column_to_byte_column (str, 15, 111, def_tabstop)); ++ ASSERT_EQ (10000, ++ cpp_display_column_to_byte_column (NULL, 0, 10000, def_tabstop)); ++ ASSERT_EQ (0, ++ cpp_display_column_to_byte_column (NULL, 10000, 0, def_tabstop)); + + /* Verify that we do not interrupt a UTF-8 sequence. */ +- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1)); ++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1, def_tabstop)); + + for (int byte_col = 1; byte_col <= 15; ++byte_col) + { +- const int disp_col = cpp_byte_column_to_display_column (str, 15, +- byte_col); +- const int byte_col2 = cpp_display_column_to_byte_column (str, 15, +- disp_col); ++ const int disp_col ++ = cpp_byte_column_to_display_column (str, 15, byte_col, def_tabstop); ++ const int byte_col2 ++ = cpp_display_column_to_byte_column (str, 15, disp_col, def_tabstop); + + /* If we ask for the display column in the middle of a UTF-8 + sequence, it will return the length of the partial sequence, +diff --git a/gcc/input.h b/gcc/input.h +--- a/gcc/input.h 2020-07-22 23:35:17.664388078 -0700 ++++ b/gcc/input.h 2021-12-25 01:20:53.487636494 -0800 +@@ -38,7 +38,9 @@ STATIC_ASSERT (BUILTINS_LOCATION < RESER + + extern bool is_location_from_builtin_token (location_t); + extern expanded_location expand_location (location_t); +-extern int location_compute_display_column (expanded_location); ++ ++extern int location_compute_display_column (expanded_location exploc, ++ int tabstop); + + /* A class capturing the bounds of a buffer, to allow for run-time + bounds-checking in a checked build. */ +diff --git a/gcc/opts.c b/gcc/opts.c +--- a/gcc/opts.c 2020-07-22 23:35:17.708388562 -0700 ++++ b/gcc/opts.c 2021-12-25 01:20:53.487636494 -0800 +@@ -2439,6 +2439,14 @@ common_handle_option (struct gcc_options + dc->parseable_fixits_p = value; + break; + ++ case OPT_fdiagnostics_column_unit_: ++ dc->column_unit = (enum diagnostics_column_unit)value; ++ break; ++ ++ case OPT_fdiagnostics_column_origin_: ++ dc->column_origin = value; ++ break; ++ + case OPT_fdiagnostics_show_cwe: + dc->show_cwe = value; + break; +@@ -2825,6 +2833,12 @@ common_handle_option (struct gcc_options + check_alignment_argument (loc, arg, "functions"); + break; + ++ case OPT_ftabstop_: ++ /* It is documented that we silently ignore silly values. */ ++ if (value >= 1 && value <= 100) ++ dc->tabstop = value; ++ break; ++ + default: + /* If the flag was handled in a standard way, assume the lack of + processing here is intentional. */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2020-07-22 23:35:17.908390765 -0700 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2021-12-25 01:20:53.487636494 -0800 +@@ -8,17 +8,22 @@ + We can't rely on any ordering of the keys. */ + + /* { dg-regexp "\"kind\": \"error\"" } */ ++/* { dg-regexp "\"column-origin\": 1" } */ + /* { dg-regexp "\"message\": \"#error message\"" } */ + + /* { dg-regexp "\"caret\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 2" } */ ++/* { dg-regexp "\"display-column\": 2" } */ ++/* { dg-regexp "\"byte-column\": 2" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 6" } */ ++/* { dg-regexp "\"display-column\": 6" } */ ++/* { dg-regexp "\"byte-column\": 6" } */ + + /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */ + /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2020-07-22 23:35:17.908390765 -0700 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2021-12-25 01:20:53.487636494 -0800 +@@ -8,6 +8,7 @@ + We can't rely on any ordering of the keys. */ + + /* { dg-regexp "\"kind\": \"warning\"" } */ ++/* { dg-regexp "\"column-origin\": 1" } */ + /* { dg-regexp "\"message\": \"#warning message\"" } */ + /* { dg-regexp "\"option\": \"-Wcpp\"" } */ + /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */ +@@ -16,11 +17,15 @@ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 2" } */ ++/* { dg-regexp "\"display-column\": 2" } */ ++/* { dg-regexp "\"byte-column\": 2" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 8" } */ ++/* { dg-regexp "\"display-column\": 8" } */ ++/* { dg-regexp "\"byte-column\": 8" } */ + + /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */ + /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2020-07-22 23:35:17.908390765 -0700 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2021-12-25 01:20:53.487636494 -0800 +@@ -8,6 +8,7 @@ + We can't rely on any ordering of the keys. */ + + /* { dg-regexp "\"kind\": \"error\"" } */ ++/* { dg-regexp "\"column-origin\": 1" } */ + /* { dg-regexp "\"message\": \"#warning message\"" } */ + /* { dg-regexp "\"option\": \"-Werror=cpp\"" } */ + /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */ +@@ -16,11 +17,15 @@ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 2" } */ ++/* { dg-regexp "\"display-column\": 2" } */ ++/* { dg-regexp "\"byte-column\": 2" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 8" } */ ++/* { dg-regexp "\"display-column\": 8" } */ ++/* { dg-regexp "\"byte-column\": 8" } */ + + /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */ + /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2020-07-22 23:35:17.908390765 -0700 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2021-12-25 01:20:53.487636494 -0800 +@@ -24,15 +24,20 @@ int test (void) + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 5" } */ ++/* { dg-regexp "\"display-column\": 5" } */ ++/* { dg-regexp "\"byte-column\": 5" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 10" } */ ++/* { dg-regexp "\"display-column\": 10" } */ ++/* { dg-regexp "\"byte-column\": 10" } */ + + /* The outer diagnostic. */ + + /* { dg-regexp "\"kind\": \"warning\"" } */ ++/* { dg-regexp "\"column-origin\": 1" } */ + /* { dg-regexp "\"message\": \"this 'if' clause does not guard...\"" } */ + /* { dg-regexp "\"option\": \"-Wmisleading-indentation\"" } */ + /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wmisleading-indentation\"" } */ +@@ -41,11 +46,15 @@ int test (void) + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */ + /* { dg-regexp "\"line\": 6" } */ + /* { dg-regexp "\"column\": 3" } */ ++/* { dg-regexp "\"display-column\": 3" } */ ++/* { dg-regexp "\"byte-column\": 3" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */ + /* { dg-regexp "\"line\": 6" } */ + /* { dg-regexp "\"column\": 4" } */ ++/* { dg-regexp "\"display-column\": 4" } */ ++/* { dg-regexp "\"byte-column\": 4" } */ + + /* More from the nested diagnostic (we can't guarantee what order the + "file" keys are consumed). */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2020-07-22 23:35:17.908390765 -0700 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2021-12-25 01:20:53.487636494 -0800 +@@ -13,6 +13,7 @@ int test (struct s *ptr) + We can't rely on any ordering of the keys. */ + + /* { dg-regexp "\"kind\": \"error\"" } */ ++/* { dg-regexp "\"column-origin\": 1" } */ + /* { dg-regexp "\"message\": \".*\"" } */ + + /* Verify fix-it hints. */ +@@ -23,11 +24,15 @@ int test (struct s *ptr) + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 15" } */ ++/* { dg-regexp "\"display-column\": 15" } */ ++/* { dg-regexp "\"byte-column\": 15" } */ + + /* { dg-regexp "\"next\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 21" } */ ++/* { dg-regexp "\"display-column\": 21" } */ ++/* { dg-regexp "\"byte-column\": 21" } */ + + /* { dg-regexp "\"fixits\": \[\[\{\}, \]*\]" } */ + +@@ -35,11 +40,15 @@ int test (struct s *ptr) + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 15" } */ ++/* { dg-regexp "\"display-column\": 15" } */ ++/* { dg-regexp "\"byte-column\": 15" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 20" } */ ++/* { dg-regexp "\"display-column\": 20" } */ ++/* { dg-regexp "\"byte-column\": 20" } */ + + /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */ + /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-1.c b/gcc/testsuite/c-c++-common/diagnostic-units-1.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-1.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-1.c 2021-12-25 01:20:53.487636494 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -Wmultichar" } */ ++ ++/* column units: bytes (via arg) ++ column origin: 1 (via default) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "19: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-2.c b/gcc/testsuite/c-c++-common/diagnostic-units-2.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-2.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-2.c 2021-12-25 01:20:53.487636494 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=display -fshow-column -fdiagnostics-show-caret -Wmultichar" } */ ++ ++/* column units: display (via arg) ++ column origin: 1 (via default) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "18: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "25: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-3.c b/gcc/testsuite/c-c++-common/diagnostic-units-3.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-3.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-3.c 2021-12-25 01:20:53.487636494 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -ftabstop=200 -Wmultichar" } */ ++ ++/* column units: bytes (via arg) ++ column origin: 1 (via fallback from overly large argument) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "19: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-4.c b/gcc/testsuite/c-c++-common/diagnostic-units-4.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-4.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-4.c 2021-12-25 01:20:53.487636494 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=0 -Wmultichar" } */ ++ ++/* column units: bytes (via arg) ++ column origin: 0 (via arg) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "10: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "17: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "18: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-5.c b/gcc/testsuite/c-c++-common/diagnostic-units-5.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-5.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-5.c 2021-12-25 01:20:53.491636427 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=display -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=0 -Wmultichar" } */ ++ ++/* column units: display (via arg) ++ column origin: 0 (via arg) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "17: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "17: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "24: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-6.c b/gcc/testsuite/c-c++-common/diagnostic-units-6.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-6.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-6.c 2021-12-25 01:20:53.491636427 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=100 -Wmultichar" } */ ++ ++/* column units: bytes (via arg) ++ column origin: 100 (via arg) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "110: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "117: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "118: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-7.c b/gcc/testsuite/c-c++-common/diagnostic-units-7.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-7.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-7.c 2021-12-25 01:20:53.491636427 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -ftabstop=9 -Wmultichar" } */ ++ ++/* column units: bytes (via arg) ++ column origin: 1 (via default) ++ tabstop: 9 (via arg) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "19: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "20: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-8.c b/gcc/testsuite/c-c++-common/diagnostic-units-8.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-8.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-8.c 2021-12-25 01:20:53.491636427 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fshow-column -fdiagnostics-show-caret -ftabstop=9 -Wmultichar" } */ ++ ++/* column units: display (via default) ++ column origin: 1 (via default) ++ tabstop: 9 (via arg) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "19: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "19: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "28: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/missing-close-symbol.c b/gcc/testsuite/c-c++-common/missing-close-symbol.c +--- a/gcc/testsuite/c-c++-common/missing-close-symbol.c 2020-07-22 23:35:17.912390810 -0700 ++++ b/gcc/testsuite/c-c++-common/missing-close-symbol.c 2021-12-25 01:20:53.491636427 -0800 +@@ -24,9 +24,9 @@ void test_static_assert_different_line ( + _Static_assert(sizeof(int) >= sizeof(char), /* { dg-message "to match this '\\('" } */ + "msg"; /* { dg-error "expected '\\)' before ';' token" } */ + /* { dg-begin-multiline-output "" } +- "msg"; +- ^ +- ) ++ "msg"; ++ ^ ++ ) + { dg-end-multiline-output "" } */ + /* { dg-begin-multiline-output "" } + _Static_assert(sizeof(int) >= sizeof(char), +diff --git a/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c b/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c +--- a/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c 2020-07-22 23:35:17.904390722 -0700 ++++ b/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c 2021-12-25 01:20:53.487636494 -0800 +@@ -36,20 +36,20 @@ int fn_6 (int a, int b, int c) + /* ... */ + if ((err = foo (a)) != 0) + goto fail; +- if ((err = foo (b)) != 0) /* { dg-message "2: this 'if' clause does not guard..." } */ ++ if ((err = foo (b)) != 0) /* { dg-message "9: this 'if' clause does not guard..." } */ + goto fail; +- goto fail; /* { dg-message "3: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ ++ goto fail; /* { dg-message "17: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ + if ((err = foo (c)) != 0) + goto fail; + /* ... */ + + /* { dg-begin-multiline-output "" } +- if ((err = foo (b)) != 0) +- ^~ ++ if ((err = foo (b)) != 0) ++ ^~ + { dg-end-multiline-output "" } */ + /* { dg-begin-multiline-output "" } +- goto fail; +- ^~~~ ++ goto fail; ++ ^~~~ + { dg-end-multiline-output "" } */ + + fail: +diff --git a/gcc/testsuite/c-c++-common/Wmisleading-indentation.c b/gcc/testsuite/c-c++-common/Wmisleading-indentation.c +--- a/gcc/testsuite/c-c++-common/Wmisleading-indentation.c 2020-07-22 23:35:17.904390722 -0700 ++++ b/gcc/testsuite/c-c++-common/Wmisleading-indentation.c 2021-12-25 01:20:53.487636494 -0800 +@@ -65,9 +65,9 @@ int fn_6 (int a, int b, int c) + /* ... */ + if ((err = foo (a)) != 0) + goto fail; +- if ((err = foo (b)) != 0) /* { dg-message "2: this 'if' clause does not guard..." } */ ++ if ((err = foo (b)) != 0) /* { dg-message "9: this 'if' clause does not guard..." } */ + goto fail; +- goto fail; /* { dg-message "3: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ ++ goto fail; /* { dg-message "17: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ + if ((err = foo (c)) != 0) + goto fail; + /* ... */ +@@ -178,7 +178,7 @@ void fn_16_tabs (void) + while (flagA) + if (flagB) /* { dg-message "7: this 'if' clause does not guard..." } */ + foo (0); +- foo (1);/* { dg-message "2: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ ++ foo (1);/* { dg-message "9: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ + } + + void fn_17_spaces (void) +diff --git a/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c b/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c +--- a/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c 2020-07-22 23:35:18.124393144 -0700 ++++ b/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c 2021-12-25 01:20:53.491636427 -0800 +@@ -288,7 +288,7 @@ int test_3 (int x, int y) + | | ~~~~~~~~~~ + | | | + | | (4) ...to here +- | NN | to dereference it above ++ | NN | to dereference it above + | NN | return *ptr; + | | ~~~~ + | | | +diff --git a/gcc/testsuite/gcc.dg/bad-binary-ops.c b/gcc/testsuite/gcc.dg/bad-binary-ops.c +--- a/gcc/testsuite/gcc.dg/bad-binary-ops.c 2020-07-22 23:35:18.128393190 -0700 ++++ b/gcc/testsuite/gcc.dg/bad-binary-ops.c 2021-12-25 01:20:53.491636427 -0800 +@@ -35,10 +35,10 @@ int test_2 (void) + ~~~~~~~~~~~~~~~~ + | + struct s +- + some_other_function ()); +- ^ ~~~~~~~~~~~~~~~~~~~~~~ +- | +- struct t ++ + some_other_function ()); ++ ^ ~~~~~~~~~~~~~~~~~~~~~~ ++ | ++ struct t + { dg-end-multiline-output "" } */ + } + +diff --git a/gcc/testsuite/gcc.dg/format/branch-1.c b/gcc/testsuite/gcc.dg/format/branch-1.c +--- a/gcc/testsuite/gcc.dg/format/branch-1.c 2020-07-22 23:35:18.152393454 -0700 ++++ b/gcc/testsuite/gcc.dg/format/branch-1.c 2021-12-25 01:20:53.491636427 -0800 +@@ -10,7 +10,7 @@ foo (long l, int nfoo) + { + printf ((nfoo > 1) ? "%d foos" : "%d foo", nfoo); + printf ((l > 1) ? "%d foos" /* { dg-warning "23:int" "wrong type in conditional expr" } */ +- : "%d foo", l); /* { dg-warning "16:int" "wrong type in conditional expr" } */ ++ : "%d foo", l); /* { dg-warning "23:int" "wrong type in conditional expr" } */ + printf ((l > 1) ? "%ld foos" : "%d foo", l); /* { dg-warning "36:int" "wrong type in conditional expr" } */ + printf ((l > 1) ? "%d foos" : "%ld foo", l); /* { dg-warning "23:int" "wrong type in conditional expr" } */ + /* Should allow one case to have extra arguments. */ +diff --git a/gcc/testsuite/gcc.dg/format/pr79210.c b/gcc/testsuite/gcc.dg/format/pr79210.c +--- a/gcc/testsuite/gcc.dg/format/pr79210.c 2020-07-22 23:35:18.152393454 -0700 ++++ b/gcc/testsuite/gcc.dg/format/pr79210.c 2021-12-25 01:20:53.491636427 -0800 +@@ -20,4 +20,4 @@ LPFC_VPORT_ATTR_R(peer_port_login, + "Allow peer ports on the same physical port to login to each " + "other."); + +-/* { dg-warning "6: format .%d. expects argument of type .int., but argument 4 has type .unsigned int. " "" { target *-*-* } .-12 } */ ++/* { dg-warning "20: format .%d. expects argument of type .int., but argument 4 has type .unsigned int. " "" { target *-*-* } .-12 } */ +diff --git a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c +--- a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c 2020-07-22 23:35:18.172393674 -0700 ++++ b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c 2021-12-25 01:20:53.491636427 -0800 +@@ -540,15 +540,15 @@ void test_builtin_types_compatible_p (un + __emit_expression_range (0, + f (i) + __builtin_types_compatible_p (long, int)); /* { dg-warning "range" } */ + /* { dg-begin-multiline-output "" } +- f (i) + __builtin_types_compatible_p (long, int)); +- ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ++ f (i) + __builtin_types_compatible_p (long, int)); ++ ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + { dg-end-multiline-output "" } */ + + __emit_expression_range (0, + __builtin_types_compatible_p (long, int) + f (i)); /* { dg-warning "range" } */ + /* { dg-begin-multiline-output "" } +- __builtin_types_compatible_p (long, int) + f (i)); +- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~ ++ __builtin_types_compatible_p (long, int) + f (i)); ++ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~ + { dg-end-multiline-output "" } */ + } + +@@ -671,8 +671,8 @@ void test_multiple_ordinary_maps (void) + /* { dg-begin-multiline-output "" } + __emit_expression_range (0, foo (0, + ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +- "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789")); +- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ++ "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789")); ++ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + { dg-end-multiline-output "" } */ + + /* Another expression that transitions between ordinary maps; this +@@ -685,8 +685,8 @@ void test_multiple_ordinary_maps (void) + /* { dg-begin-multiline-output "" } + __emit_expression_range (0, foo (0, "01234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789", + ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +- 0)); +- ~~ ++ 0)); ++ ~~ + { dg-end-multiline-output "" } */ + } + +diff --git a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c +--- a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c 2020-07-22 23:35:18.172393674 -0700 ++++ b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c 2021-12-25 01:20:53.491636427 -0800 +@@ -335,11 +335,11 @@ pr87652 (const char *stem, int counter) + /* { dg-error "unable to read substring location: unable to read source line" "" { target c } 329 } */ + /* { dg-error "unable to read substring location: failed to get ordinary maps" "" { target c++ } 329 } */ + /* { dg-begin-multiline-output "" } +- __emit_string_literal_range(__FILE__":%5d: " format, \ ++ __emit_string_literal_range(__FILE__":%5d: " format, \ + ^~~~~~~~ + { dg-end-multiline-output "" { target c } } */ + /* { dg-begin-multiline-output "" } +- __emit_string_literal_range(__FILE__":%5d: " format, \ ++ __emit_string_literal_range(__FILE__":%5d: " format, \ + ^ + { dg-end-multiline-output "" { target c++ } } */ + +diff --git a/gcc/testsuite/gcc.dg/redecl-4.c b/gcc/testsuite/gcc.dg/redecl-4.c +--- a/gcc/testsuite/gcc.dg/redecl-4.c 2020-07-22 23:35:18.192393895 -0700 ++++ b/gcc/testsuite/gcc.dg/redecl-4.c 2021-12-25 01:20:53.491636427 -0800 +@@ -15,7 +15,7 @@ f (void) + /* Should get format warnings even though the built-in declaration + isn't "visible". */ + printf ( +- "%s", 1); /* { dg-warning "8:format" } */ ++ "%s", 1); /* { dg-warning "15:format" } */ + /* The type of strcmp here should have no prototype. */ + if (0) + strcmp (1); +diff --git a/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C b/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C +--- a/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C 2020-07-22 23:35:17.972391472 -0700 ++++ b/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C 2021-12-25 01:20:53.491636427 -0800 +@@ -33,10 +33,10 @@ int test_2 (void) + ~~~~~~~~~~~~~~~~ + | + s +- + some_other_function ()); +- ^ ~~~~~~~~~~~~~~~~~~~~~~ +- | +- t ++ + some_other_function ()); ++ ^ ~~~~~~~~~~~~~~~~~~~~~~ ++ | ++ t + { dg-end-multiline-output "" } */ + } + +diff --git a/gcc/testsuite/g++.dg/parse/error4.C b/gcc/testsuite/g++.dg/parse/error4.C +--- a/gcc/testsuite/g++.dg/parse/error4.C 2020-07-22 23:35:18.012391910 -0700 ++++ b/gcc/testsuite/g++.dg/parse/error4.C 2021-12-25 01:20:53.491636427 -0800 +@@ -7,4 +7,4 @@ struct X { + int); + }; + +-// { dg-error "4:'itn' has not been declared" "" { target *-*-* } 6 } ++// { dg-error "18:'itn' has not been declared" "" { target *-*-* } 6 } +diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 +--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2020-07-22 23:35:18.512397420 -0700 ++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2021-12-25 01:20:53.491636427 -0800 +@@ -8,17 +8,22 @@ + ! We can't rely on any ordering of the keys. + + ! { dg-regexp "\"kind\": \"error\"" } ++! { dg-regexp "\"column-origin\": 1" } + ! { dg-regexp "\"message\": \"#error message\"" } + + ! { dg-regexp "\"caret\": \{" } + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 2" } ++! { dg-regexp "\"display-column\": 2" } ++! { dg-regexp "\"byte-column\": 2" } + + ! { dg-regexp "\"finish\": \{" } + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 6" } ++! { dg-regexp "\"display-column\": 6" } ++! { dg-regexp "\"byte-column\": 6" } + + ! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } + ! { dg-regexp "\"children\": \[\[\]\[\]\]" } +diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 +--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2020-07-22 23:35:18.512397420 -0700 ++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2021-12-25 01:20:53.491636427 -0800 +@@ -8,6 +8,7 @@ + ! We can't rely on any ordering of the keys. + + ! { dg-regexp "\"kind\": \"warning\"" } ++! { dg-regexp "\"column-origin\": 1" } + ! { dg-regexp "\"message\": \"#warning message\"" } + ! { dg-regexp "\"option\": \"-Wcpp\"" } + ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" } +@@ -16,11 +17,15 @@ + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 2" } ++! { dg-regexp "\"display-column\": 2" } ++! { dg-regexp "\"byte-column\": 2" } + + ! { dg-regexp "\"finish\": \{" } + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 8" } ++! { dg-regexp "\"display-column\": 8" } ++! { dg-regexp "\"byte-column\": 8" } + + ! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } + ! { dg-regexp "\"children\": \[\[\]\[\]\]" } +diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 +--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2020-07-22 23:35:18.512397420 -0700 ++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2021-12-25 01:20:53.491636427 -0800 +@@ -8,6 +8,7 @@ + ! We can't rely on any ordering of the keys. + + ! { dg-regexp "\"kind\": \"error\"" } ++! { dg-regexp "\"column-origin\": 1" } + ! { dg-regexp "\"message\": \"#warning message\"" } + ! { dg-regexp "\"option\": \"-Werror=cpp\"" } + ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" } +@@ -16,11 +17,15 @@ + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 2" } ++! { dg-regexp "\"display-column\": 2" } ++! { dg-regexp "\"byte-column\": 2" } + + ! { dg-regexp "\"finish\": \{" } + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 8" } ++! { dg-regexp "\"display-column\": 8" } ++! { dg-regexp "\"byte-column\": 8" } + + ! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } + ! { dg-regexp "\"children\": \[\[\]\[\]\]" } +diff --git a/gcc/testsuite/go.dg/arrayclear.go b/gcc/testsuite/go.dg/arrayclear.go +--- a/gcc/testsuite/go.dg/arrayclear.go 2020-07-22 23:35:18.588398257 -0700 ++++ b/gcc/testsuite/go.dg/arrayclear.go 2021-12-25 01:20:53.491636427 -0800 +@@ -1,5 +1,8 @@ + // { dg-do compile } + // { dg-options "-fgo-debug-optimization" } ++// This comment is necessary to work around a dejagnu bug. Otherwise, the ++// column of the second error message would equal the row of the first one, and ++// since the errors are also identical, dejagnu is not able to distinguish them. + + package p + +diff --git a/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C b/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C +--- a/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C 2020-07-22 23:35:18.048392308 -0700 ++++ b/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C 2021-12-25 01:20:53.491636427 -0800 +@@ -9,13 +9,13 @@ class A { + int h; + A() { i=10; j=20; } + virtual void f1() { printf("i=%d j=%d\n",i,j); } +- friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "9:virtual functions cannot be friends" } ++ friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "16:virtual functions cannot be friends" } + }; + + class B : public A { + public: + virtual void f1() { printf("i=%d j=%d\n",i,j); }// { dg-error "" } member.*// ERROR - member.* +- friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "9:virtual functions cannot be friends" } ++ friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "16:virtual functions cannot be friends" } + // { dg-error "private" "" { target *-*-* } .-1 } + }; + +diff --git a/gcc/testsuite/g++.old-deja/g++.pt/overload2.C b/gcc/testsuite/g++.old-deja/g++.pt/overload2.C +--- a/gcc/testsuite/g++.old-deja/g++.pt/overload2.C 2020-07-22 23:35:18.072392572 -0700 ++++ b/gcc/testsuite/g++.old-deja/g++.pt/overload2.C 2021-12-25 01:20:53.491636427 -0800 +@@ -12,5 +12,5 @@ int + main() + { + C<char*> c; +- char* p = Z(c.O); //{ dg-error "13:'Z' was not declared" } ambiguous c.O ++ char* p = Z(c.O); //{ dg-error "29:'Z' was not declared" } ambiguous c.O + } +diff --git a/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C b/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C +--- a/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C 2020-07-22 23:35:18.076392617 -0700 ++++ b/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C 2021-12-25 01:20:53.491636427 -0800 +@@ -48,8 +48,8 @@ ostream& operator<<(ostream& os, Graph<V + + // The compiler does not like this line!!!!!! + typename Graph<VertexType, EdgeType>::Successor::iterator +- startN = G[i].second.begin(), // { dg-error "14:no match" } no index operator +- endN = G[i].second.end(); // { dg-error "14:no match" } no index operator ++ startN = G[i].second.begin(), // { dg-error "21:no match" } no index operator ++ endN = G[i].second.end(); // { dg-error "21:no match" } no index operator + + while(startN != endN) + { +diff --git a/gcc/tree-diagnostic-path.cc b/gcc/tree-diagnostic-path.cc +--- a/gcc/tree-diagnostic-path.cc 2020-07-22 23:35:18.628398698 -0700 ++++ b/gcc/tree-diagnostic-path.cc 2021-12-25 01:20:53.491636427 -0800 +@@ -493,7 +493,7 @@ default_tree_diagnostic_path_printer (di + doesn't have access to trees (for m_fndecl). */ + + json::value * +-default_tree_make_json_for_path (diagnostic_context *, ++default_tree_make_json_for_path (diagnostic_context *context, + const diagnostic_path *path) + { + json::array *path_array = new json::array (); +@@ -504,7 +504,8 @@ default_tree_make_json_for_path (diagnos + json::object *event_obj = new json::object (); + if (event.get_location ()) + event_obj->set ("location", +- json_from_expanded_location (event.get_location ())); ++ json_from_expanded_location (context, ++ event.get_location ())); + label_text event_text (event.get_desc (false)); + event_obj->set ("description", new json::string (event_text.m_buffer)); + event_text.maybe_free (); +diff --git a/libcpp/charset.c b/libcpp/charset.c +--- a/libcpp/charset.c 2020-07-22 23:35:18.712399623 -0700 ++++ b/libcpp/charset.c 2021-12-25 01:20:53.491636427 -0800 +@@ -2276,49 +2276,90 @@ cpp_string_location_reader::get_next () + return result; + } + +-/* Helper for cpp_byte_column_to_display_column and its inverse. Given a +- pointer to a UTF-8-encoded character, compute its display width. *INBUFP +- points on entry to the start of the UTF-8 encoding of the character, and +- is updated to point just after the last byte of the encoding. *INBYTESLEFTP +- contains on entry the remaining size of the buffer into which *INBUFP +- points, and this is also updated accordingly. If *INBUFP does not ++cpp_display_width_computation:: ++cpp_display_width_computation (const char *data, int data_length, int tabstop) : ++ m_begin (data), ++ m_next (m_begin), ++ m_bytes_left (data_length), ++ m_tabstop (tabstop), ++ m_display_cols (0) ++{ ++ gcc_assert (m_tabstop > 0); ++} ++ ++ ++/* The main implementation function for class cpp_display_width_computation. ++ m_next points on entry to the start of the UTF-8 encoding of the next ++ character, and is updated to point just after the last byte of the encoding. ++ m_bytes_left contains on entry the remaining size of the buffer into which ++ m_next points, and this is also updated accordingly. If m_next does not + point to a valid UTF-8-encoded sequence, then it will be treated as a single +- byte with display width 1. */ ++ byte with display width 1. m_cur_display_col is the current display column, ++ relative to which tab stops should be expanded. Returns the display width of ++ the codepoint just processed. */ + +-static inline int +-compute_next_display_width (const uchar **inbufp, size_t *inbytesleftp) ++int ++cpp_display_width_computation::process_next_codepoint () + { + cppchar_t c; +- if (one_utf8_to_cppchar (inbufp, inbytesleftp, &c) != 0) ++ int next_width; ++ ++ if (*m_next == '\t') ++ { ++ ++m_next; ++ --m_bytes_left; ++ next_width = m_tabstop - (m_display_cols % m_tabstop); ++ } ++ else if (one_utf8_to_cppchar ((const uchar **) &m_next, &m_bytes_left, &c) ++ != 0) + { + /* Input is not convertible to UTF-8. This could be fine, e.g. in a + string literal, so don't complain. Just treat it as if it has a width + of one. */ +- ++*inbufp; +- --*inbytesleftp; +- return 1; ++ ++m_next; ++ --m_bytes_left; ++ next_width = 1; ++ } ++ else ++ { ++ /* one_utf8_to_cppchar() has updated m_next and m_bytes_left for us. */ ++ next_width = cpp_wcwidth (c); + } + +- /* one_utf8_to_cppchar() has updated inbufp and inbytesleftp for us. */ +- return cpp_wcwidth (c); ++ m_display_cols += next_width; ++ return next_width; ++} ++ ++/* Utility to advance the byte stream by the minimum amount needed to consume ++ N display columns. Returns the number of display columns that were ++ actually skipped. This could be less than N, if there was not enough data, ++ or more than N, if the last character to be skipped had a sufficiently large ++ display width. */ ++int ++cpp_display_width_computation::advance_display_cols (int n) ++{ ++ const int start = m_display_cols; ++ const int target = start + n; ++ while (m_display_cols < target && !done ()) ++ process_next_codepoint (); ++ return m_display_cols - start; + } + + /* For the string of length DATA_LENGTH bytes that begins at DATA, compute + how many display columns are occupied by the first COLUMN bytes. COLUMN + may exceed DATA_LENGTH, in which case the phantom bytes at the end are +- treated as if they have display width 1. */ ++ treated as if they have display width 1. Tabs are expanded to the next tab ++ stop, relative to the start of DATA. */ + + int + cpp_byte_column_to_display_column (const char *data, int data_length, +- int column) ++ int column, int tabstop) + { +- int display_col = 0; +- const uchar *udata = (const uchar *) data; + const int offset = MAX (0, column - data_length); +- size_t inbytesleft = column - offset; +- while (inbytesleft) +- display_col += compute_next_display_width (&udata, &inbytesleft); +- return display_col + offset; ++ cpp_display_width_computation dw (data, column - offset, tabstop); ++ while (!dw.done ()) ++ dw.process_next_codepoint (); ++ return dw.display_cols_processed () + offset; + } + + /* For the string of length DATA_LENGTH bytes that begins at DATA, compute +@@ -2328,14 +2369,11 @@ cpp_byte_column_to_display_column (const + + int + cpp_display_column_to_byte_column (const char *data, int data_length, +- int display_col) ++ int display_col, int tabstop) + { +- int column = 0; +- const uchar *udata = (const uchar *) data; +- size_t inbytesleft = data_length; +- while (column < display_col && inbytesleft) +- column += compute_next_display_width (&udata, &inbytesleft); +- return data_length - inbytesleft + MAX (0, display_col - column); ++ cpp_display_width_computation dw (data, data_length, tabstop); ++ const int avail_display = dw.advance_display_cols (display_col); ++ return dw.bytes_processed () + MAX (0, display_col - avail_display); + } + + /* Our own version of wcwidth(). We don't use the actual wcwidth() in glibc, +diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h +--- a/libcpp/include/cpplib.h 2020-07-22 23:35:18.712399623 -0700 ++++ b/libcpp/include/cpplib.h 2021-12-25 01:20:53.491636427 -0800 +@@ -312,9 +312,6 @@ enum cpp_normalize_level { + carries all the options visible to the command line. */ + struct cpp_options + { +- /* Characters between tab stops. */ +- unsigned int tabstop; +- + /* The language we're preprocessing. */ + enum c_lang lang; + +@@ -1322,14 +1319,43 @@ extern const char * cpp_get_userdef_suff + (const cpp_token *); + + /* In charset.c */ ++ ++/* A class to manage the state while converting a UTF-8 sequence to cppchar_t ++ and computing the display width one character at a time. */ ++class cpp_display_width_computation { ++ public: ++ cpp_display_width_computation (const char *data, int data_length, ++ int tabstop); ++ const char *next_byte () const { return m_next; } ++ int bytes_processed () const { return m_next - m_begin; } ++ int bytes_left () const { return m_bytes_left; } ++ bool done () const { return !bytes_left (); } ++ int display_cols_processed () const { return m_display_cols; } ++ ++ int process_next_codepoint (); ++ int advance_display_cols (int n); ++ ++ private: ++ const char *const m_begin; ++ const char *m_next; ++ size_t m_bytes_left; ++ const int m_tabstop; ++ int m_display_cols; ++}; ++ ++/* Convenience functions that are simple use cases for class ++ cpp_display_width_computation. Tab characters will be expanded to spaces ++ as determined by TABSTOP. */ + int cpp_byte_column_to_display_column (const char *data, int data_length, +- int column); +-inline int cpp_display_width (const char *data, int data_length) ++ int column, int tabstop); ++inline int cpp_display_width (const char *data, int data_length, ++ int tabstop) + { +- return cpp_byte_column_to_display_column (data, data_length, data_length); ++ return cpp_byte_column_to_display_column (data, data_length, data_length, ++ tabstop); + } + int cpp_display_column_to_byte_column (const char *data, int data_length, +- int display_col); ++ int display_col, int tabstop); + int cpp_wcwidth (cppchar_t c); + + #endif /* ! LIBCPP_CPPLIB_H */ +diff --git a/libcpp/init.c b/libcpp/init.c +--- a/libcpp/init.c 2020-07-22 23:35:18.712399623 -0700 ++++ b/libcpp/init.c 2021-12-25 01:20:53.491636427 -0800 +@@ -190,7 +190,6 @@ cpp_create_reader (enum c_lang lang, cpp + CPP_OPTION (pfile, discard_comments) = 1; + CPP_OPTION (pfile, discard_comments_in_macro_exp) = 1; + CPP_OPTION (pfile, max_include_depth) = 200; +- CPP_OPTION (pfile, tabstop) = 8; + CPP_OPTION (pfile, operator_names) = 1; + CPP_OPTION (pfile, warn_trigraphs) = 2; + CPP_OPTION (pfile, warn_endif_labels) = 1; |