binutils-gdb/gdb/testsuite/gdb.ada/non-ascii-latin-3.exp

# Copyright 2022 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 UTF-8 identifiers.

load_lib "ada.exp"

if { [skip_ada_tests] } { return -1 }

# Enable basic use of UTF-8.  LC_ALL gets reset for each testfile.  We
# want this despite the program itself using Latin-1, as this test is
# written using UTF-8.
setenv LC_ALL C.UTF-8

standard_ada_testfile prog

set flags [list debug additional_flags=-gnati3]
if {[gdb_compile_ada "${srcfile}" "${binfile}" executable $flags] != ""} {
    return -1
}

# Restart without an executable so that we can set the encoding early.
clean_restart

gdb_test_no_output "set ada source-charset ISO-8859-3"

gdb_load ${binfile}

set bp_location [gdb_get_line_number "BREAK" ${testdir}/prog.adb]
runto "prog.adb:$bp_location"

gdb_test "print VAR_Ż" " = 23"
gdb_test "print var_ż" " = 23"

gdb_breakpoint "FUNC_Ż" message
gdb_breakpoint "func_ż" message

gdb_test "print var_𝕯" "warning: charset conversion failure.*"
-												Handle non-ASCII identifiers in Ada

Ada allows non-ASCII identifiers, and GNAT supports several such
encodings.  This patch adds the corresponding support to gdb.

GNAT encodes non-ASCII characters using special symbol names.

For character sets like Latin-1, where all characters are a single
byte, it uses a "U" followed by the hex for the character.  So, for
example, thorn would be encoded as "Ufe" (0xFE being lower case
thorn).

For wider characters, despite what the manual says (it claims
Shift-JIS and EUC can be used), in practice recent versions only
support Unicode.  Here, characters in the base plane are represented
using "Wxxxx" and characters outside the base plane using
"WWxxxxxxxx".

GNAT has some further quirks here.  Ada is case-insensitive, and GNAT
emits symbols that have been case-folded.  For characters in ASCII,
and for all characters in non-Unicode character sets, lower case is
used.  For Unicode, however, characters that fit in a single byte are
converted to lower case, but all others are converted to upper case.

Furthermore, there is a bug in GNAT where two symbols that differ only
in the case of "Y WITH DIAERESIS" (and potentially others, I did not
check exhaustively) can be used in one program.  I chose to omit
handling this case from gdb, on the theory that it is hard to figure
out the logic, and anyway if the bug is ever fixed, we'll regret
having a heuristic.

This patch introduces a new "ada source-charset" setting.  It defaults
to Latin-1, as that is GNAT's default.  This setting controls how "U"
characters are decoded -- W/WW are always handled as UTF-32.

The ada_tag_name_from_tsd change is needed because this function will
read memory from the inferior and interpret it -- and this caused an
encoding failure on PPC when running a test that tries to read
uninitialized memory.

This patch implements its own UTF-32-based case folder.  This avoids
host platform quirks, and is relatively simple.  A short Python
program to generate the case-folding table is included.  It simply
relies on whatever version of Unicode is used by the host Python,
which seems basically acceptable.

Test cases for UTF-8, Latin-1, and Latin-3 are included.  This
exercises most of the new code paths, aside from Y WITH DIAERESIS as
noted above.




											
										
										
											2022-02-04 01:42:07 +08:00
+								# Copyright 2022 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 UTF-8 identifiers.
 								load_lib "ada.exp"
 								if { [skip_ada_tests] } { return -1 }
 								# Enable basic use of UTF-8.  LC_ALL gets reset for each testfile.  We
 								# want this despite the program itself using Latin-1, as this test is
 								# written using UTF-8.
 								setenv LC_ALL C.UTF-8
 								standard_ada_testfile prog
 								set flags [list debug additional_flags=-gnati3]
 								if {[gdb_compile_ada "${srcfile}" "${binfile}" executable $flags] != ""} {
 								    return -1
 								}
 								# Restart without an executable so that we can set the encoding early.
 								clean_restart
 								gdb_test_no_output "set ada source-charset ISO-8859-3"
 								gdb_load ${binfile}
 								set bp_location [gdb_get_line_number "BREAK" ${testdir}/prog.adb]
 								runto "prog.adb:$bp_location"
 								gdb_test "print VAR_Ż" " = 23"
 								gdb_test "print var_ż" " = 23"
 								gdb_breakpoint "FUNC_Ż" message
 								gdb_breakpoint "func_ż" message
 								gdb_test "print var_𝕯" "warning: charset conversion failure.*"