Support UTF-8 identifiers in C/C++ expressions (PR gdb/22973)

Factor out cp_ident_is_alpha/cp_ident_is_alnum out of
gdb/cp-name-parser.y and use it in the C/C++ expression parser too.

New test included.

gdb/ChangeLog:
2018-05-22  Pedro Alves  <palves@redhat.com>
	    張俊芝  <zjz@zjz.name>

	PR gdb/22973
	* c-exp.y: Include "c-support.h".
	(parse_number, c_parse_escape, lex_one_token): Use TOLOWER instead
	of tolower.  Use c_ident_is_alpha to scan names.
	* c-lang.c: Include "c-support.h".
	(convert_ucn, convert_octal, convert_hex, convert_escape): Use
	ISXDIGIT instead of isxdigit and ISDIGIT instead of isdigit.
	* c-support.h: New file, with bits factored out from ...
	* cp-name-parser.y: ... this file.
	Include "c-support.h".
	(cp_ident_is_alpha, cp_ident_is_alnum): Deleted, moved to
	c-support.h and renamed.
	(symbol_end, yylex): Adjust.

gdb/testsuite/ChangeLog:
2018-05-22  Pedro Alves  <palves@redhat.com>

	PR gdb/22973
	* gdb.base/utf8-identifiers.c: New file.
	* gdb.base/utf8-identifiers.exp: New file.

3 files changed, 154 insertions, 0 deletions

diff --git a/gdb/testsuite/ChangeLog b/gdb/testsuite/ChangeLog
index 208939b..393ab88 100644
--- a/gdb/testsuite/ChangeLog
+++ b/gdb/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2018-05-22  Pedro Alves  <palves@redhat.com>
+
+	PR gdb/22973
+	* gdb.base/utf8-identifiers.c: New file.
+	* gdb.base/utf8-identifiers.exp: New file.
+
 2018-05-22  Pedro Franco de Carvalho  <pedromfc@linux.vnet.ibm.com>
 
 	* gdb.arch/powerpc-fpscr-gcore.exp: New file.
diff --git a/gdb/testsuite/gdb.base/utf8-identifiers.c b/gdb/testsuite/gdb.base/utf8-identifiers.c
new file mode 100644
index 0000000..c80b42a
--- /dev/null
+++ b/gdb/testsuite/gdb.base/utf8-identifiers.c
@@ -0,0 +1,71 @@
+/* -*- coding: utf-8 -*- */
+
+/* This testcase is part of GDB, the GNU debugger.
+
+   Copyright 2017-2018 Free Software Foundation, Inc.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 3 of the License, or
+   (at your option) any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+/* UTF-8 "função1".  */
+#define FUNCAO1 fun\u00e7\u00e3o1
+
+/* UTF-8 "função2".  */
+#define FUNCAO2 fun\u00e7\u00e3o2
+
+/* UTF-8 "my_função".  */
+#define MY_FUNCAO my_fun\u00e7\u00e3o
+
+/* UTF-8 "num_€".  */
+#define NUM_EUROS num_\u20ac
+
+struct S
+{
+  int NUM_EUROS;
+} g_s;
+
+void
+FUNCAO1 (void)
+{
+  g_s.NUM_EUROS = 1000;
+}
+
+void
+FUNCAO2 (void)
+{
+  g_s.NUM_EUROS = 1000;
+}
+
+void
+MY_FUNCAO (void)
+{
+}
+
+int NUM_EUROS = 2000;
+
+static void
+done ()
+{
+}
+
+int
+main ()
+{
+  FUNCAO1 ();
+  done ();
+  FUNCAO2 ();
+  MY_FUNCAO ();
+
+  return 0;
+}
diff --git a/gdb/testsuite/gdb.base/utf8-identifiers.exp b/gdb/testsuite/gdb.base/utf8-identifiers.exp
new file mode 100644
index 0000000..12fe376
--- /dev/null
+++ b/gdb/testsuite/gdb.base/utf8-identifiers.exp
@@ -0,0 +1,77 @@
+# -*- coding: utf-8 -*- */
+
+# This testcase is part of GDB, the GNU debugger.
+
+# Copyright 2017-2018 Free Software Foundation, Inc.
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+# Test GDB's support for UTF-8 C/C++ identifiers.
+
+load_lib completion-support.exp
+
+standard_testfile
+
+# Enable basic use of UTF-8.  LC_ALL gets reset for each testfile.
+setenv LC_ALL C.UTF-8
+
+if { [prepare_for_testing "failed to prepare" ${testfile} [list $srcfile]] } {
+    return -1
+}
+
+if ![runto done] {
+    fail "couldn't run to done"
+    return
+}
+
+# Test expressions.
+gdb_test "print g_s.num_€" " = 1000"
+gdb_test "print num_€" " = 2000"
+
+# Test linespecs/breakpoints.
+gdb_test "break função2" "Breakpoint $decimal at .*$srcfile.*"
+
+set test "info breakpoints"
+gdb_test_multiple $test $test {
+    -re "in função2 at .*$srcfile.*$gdb_prompt $" {
+	pass $test
+    }
+}
+
+gdb_test "continue" \
+    "Breakpoint $decimal, função2 \\(\\) at .*$srcfile.*"
+
+# Unload symbols from shared libraries to avoid random symbol and file
+# names getting in the way of completion.
+gdb_test_no_output "nosharedlibrary"
+
+# Test linespec completion.
+
+# A unique completion.
+test_gdb_complete_unique "break my_fun" "break my_função"
+
+# A multiple-matches completion:
+
+# kfailed because gdb/readline display the completion match list like
+# this, with no separating space:
+#
+#  (gdb) break função[TAB]
+#  função1função2
+#
+# ... which is bogus.
+setup_kfail "gdb/23211" "*-*-*"
+test_gdb_complete_multiple "break " "fun" "ção" {"função1" "função2"}
+
+# Test expression completion.
+test_gdb_complete_unique "print g_s.num" "print g_s.num_€"