From 3ac6b5cff1eca4e1748c671960ef7b4ca5e47fd2 Mon Sep 17 00:00:00 2001
From: Lewis Hyatt <lhyatt@gmail.com>
Date: Tue, 24 Aug 2021 19:30:44 -0400
Subject: diagnostics: Support for -finput-charset [PR93067]

Adds the logic to handle -finput-charset in layout_get_source_line(), so that
source lines are converted from their input encodings prior to being output by
diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly.

gcc/c-family/ChangeLog:

	PR other/93067
	* c-opts.c (c_common_input_charset_cb): New function.
	(c_common_post_options): Call new function
	diagnostic_initialize_input_context().

gcc/d/ChangeLog:

	PR other/93067
	* d-lang.cc (d_input_charset_callback): New function.
	(d_init): Call new function
	diagnostic_initialize_input_context().

gcc/fortran/ChangeLog:

	PR other/93067
	* cpp.c (gfc_cpp_post_options): Call new function
	diagnostic_initialize_input_context().

gcc/ChangeLog:

	PR other/93067
	* coretypes.h (typedef diagnostic_input_charset_callback): Declare.
	* diagnostic.c (diagnostic_initialize_input_context): New function.
	* diagnostic.h (diagnostic_initialize_input_context): Declare.
	* input.c (default_charset_callback): New function.
	(file_cache::initialize_input_context): New function.
	(file_cache_slot::create): Added ability to convert the input
	according to the input context.
	(file_cache::file_cache): Initialize the new input context.
	(class file_cache_slot): Added new m_alloc_offset member.
	(file_cache_slot::file_cache_slot): Initialize the new member.
	(file_cache_slot::~file_cache_slot): Handle potentially offset buffer.
	(file_cache_slot::maybe_grow): Likewise.
	(file_cache_slot::needs_read_p): Handle NULL fp, which is now possible.
	(file_cache_slot::get_next_line): Likewise.
	* input.h (class file_cache): Added input context member.

libcpp/ChangeLog:

	PR other/93067
	* charset.c (init_iconv_desc): Adapt to permit PFILE argument to
	be NULL.
	(_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to...
	(cpp_check_utf8_bom): ...here.  New function.
	(cpp_input_conversion_is_trivial): New function.
	* files.c (read_file_guts): Allow PFILE argument to be NULL.  Add
	INPUT_CHARSET argument as an alternate source of this information.
	(read_file): Pass the new argument to read_file_guts.
	(cpp_get_converted_source): New function.
	* include/cpplib.h (struct cpp_converted_source): Declare.
	(cpp_get_converted_source): Declare.
	(cpp_input_conversion_is_trivial): Declare.
	(cpp_check_utf8_bom): Declare.

gcc/testsuite/ChangeLog:

	PR other/93067
	* gcc.dg/diagnostic-input-charset-1.c: New test.
	* gcc.dg/diagnostic-input-utf8-bom.c: New test.
---
 gcc/c-family/c-opts.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'gcc/c-family/c-opts.c')

diff --git a/gcc/c-family/c-opts.c b/gcc/c-family/c-opts.c
index 373af0c..fdde082 100644
--- a/gcc/c-family/c-opts.c
+++ b/gcc/c-family/c-opts.c
@@ -188,6 +188,14 @@ c_common_diagnostics_set_defaults (diagnostic_context *context)
   context->opt_permissive = OPT_fpermissive;
 }
 
+/* Input charset configuration for diagnostics.  */
+static const char *
+c_common_input_charset_cb (const char * /*filename*/)
+{
+  const char *cs = cpp_opts->input_charset;
+  return cpp_input_conversion_is_trivial (cs) ? nullptr : cs;
+}
+
 /* Whether options from all C-family languages should be accepted
    quietly.  */
 static bool accept_all_c_family_options = false;
@@ -1136,6 +1144,11 @@ c_common_post_options (const char **pfilename)
   cpp_post_options (parse_in);
   init_global_opts_from_cpp (&global_options, cpp_get_options (parse_in));
 
+  /* Let diagnostics infrastructure know how to convert input files the same
+     way libcpp will do it, namely using the configured input charset and
+     skipping a UTF-8 BOM if present.  */
+  diagnostic_initialize_input_context (global_dc,
+				       c_common_input_charset_cb, true);
   input_location = UNKNOWN_LOCATION;
 
   *pfilename = this_input_filename
-- 
cgit v1.1