1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
|
From c580e6466d6da8262820cdbad19f32c5546226cf Mon Sep 17 00:00:00 2001
From: Carlos O'Donell <carlos@redhat.com>
Date: Fri, 27 Mar 2020 17:03:36 -0400
Subject: [PATCH] Reset converter state after second wchar_t output (Bug 25734)
An input BIG5-HKSCS character may be converted into at most 2 wchar_t
characters. After outputting the second whcar_t character (which was
saved in the converter state) we must reset the state. If we fail
to reset the state we will be stuck continually copying that
character to the output even if we have further input to consider.
We add a new test case that covers the 4 BIG5-HKSCS characters
that may become 2 wchar_t characters.
Reviewed-by: Tom Honermann <tom@honermann.net>
---
iconvdata/Makefile | 17 ++-
iconvdata/big5hkscs.c | 3 +
iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c | 160 ++++++++++++++++++++++
3 files changed, 176 insertions(+), 4 deletions(-)
create mode 100644 iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c
diff --git a/iconvdata/Makefile b/iconvdata/Makefile
index c83962f351b..4ec2741cdce 100644
--- a/iconvdata/Makefile
+++ b/iconvdata/Makefile
@@ -73,7 +73,7 @@ modules.so := $(addsuffix .so, $(modules))
ifeq (yes,$(build-shared))
tests = bug-iconv1 bug-iconv2 tst-loading tst-e2big tst-iconv4 bug-iconv4 \
tst-iconv6 bug-iconv5 bug-iconv6 tst-iconv7 bug-iconv8 bug-iconv9 \
- bug-iconv10 bug-iconv11 bug-iconv12
+ bug-iconv10 bug-iconv11 bug-iconv12 tst-iconv-big5-hkscs-to-2ucs4
ifeq ($(have-thread-library),yes)
tests += bug-iconv3
endif
@@ -275,16 +275,21 @@ endif
endif
endif
-include ../Rules
-
ifeq ($(run-built-tests),yes)
-LOCALES := de_DE.UTF-8
+LOCALES := \
+ de_DE.UTF-8 \
+ zh_HK.BIG5-HKSCS \
+ $(NULL)
+
include ../gen-locales.mk
$(objpfx)bug-iconv6.out: $(gen-locales)
$(objpfx)tst-iconv7.out: $(gen-locales)
+$(objpfx)tst-iconv-big5-hkscs-to-2ucs4.out: $(gen-locales)
endif
+include ../Rules
+
# Set libof-* for each routine.
cpp-srcs-left := $(modules) $(generated-modules) $(libJIS-routines) \
$(libKSC-routines) $(libGB-routines) $(libCNS-routines) \
@@ -340,3 +345,7 @@ tst-tables-clean:
$(objpfx)gconv-modules: gconv-modules
cat $(sysdeps-gconv-modules) $^ > $@
+
+# Test requires BIG5HKSCS.
+$(objpfx)tst-iconv-big5-hkscs-to-2ucs4.out: $(objpfx)gconv-modules \
+ $(addprefix $(objpfx),$(modules.so))
diff --git a/iconvdata/big5hkscs.c b/iconvdata/big5hkscs.c
index 01fcfeba76b..ef325119b18 100644
--- a/iconvdata/big5hkscs.c
+++ b/iconvdata/big5hkscs.c
@@ -17895,6 +17895,9 @@ static struct
else \
++inptr; \
} \
+ else \
+ /* Clear the queue and proceed to output the saved character. */ \
+ *statep = 0; \
\
put32 (outptr, ch); \
outptr += 4; \
diff --git a/iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c b/iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c
new file mode 100644
index 00000000000..8389adebf27
--- /dev/null
+++ b/iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c
@@ -0,0 +1,160 @@
+/* Verify the BIG5HKSCS outputs that generate 2 wchar_t's (Bug 25734).
+ Copyright (C) 2020 Free Software Foundation, Inc.
+ This file is part of the GNU C Library.
+
+ The GNU C Library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ The GNU C Library 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
+ Lesser General Public License for more details.
+
+ You should have received a copy of the GNU Lesser General Public
+ License along with the GNU C Library; if not, see
+ <https://www.gnu.org/licenses/>. */
+
+#include <stdio.h>
+#include <string.h>
+#include <locale.h>
+#include <wchar.h>
+#include <support/check.h>
+#include <support/support.h>
+
+/* A few BIG5-HKSCS characters map in two unicode code points.
+ They are:
+ /x88/x62 => <U00CA><U0304>
+ /x88/x64 => <U00CA><U030C>
+ /x88/xa3 => <U00EA><U0304>
+ /x88/xa5 => <U00EA><U030C>
+ Each of these is special cased in iconvdata/big5hkscs.c.
+ This test ensures that we correctly reset the shift state after
+ outputting any of these characters. We do this by converting
+ each them followed by converting an ASCII character. If we fail
+ to reset the shift state (bug 25734) then we'll see the last
+ character in the queue output again. */
+
+/* Each test has name, input bytes, and expected wide character
+ output. */
+struct testdata {
+ const char *name;
+ const char input[3];
+ wchar_t expected[3];
+};
+
+/* In BIG5-HKSCS (2008) there are 4 characters that generate multiple
+ wide characters. */
+struct testdata tests[4] = {
+ /* <H-8862>X => <U+00CA><U+0304>X */
+ { "<H-8862>", "\x88\x62\x58", { 0x00CA, 0x0304, 0x0058 } },
+ /* <H-8864>X => <U+00CA><U+030C>X */
+ { "<H-8864>", "\x88\x64\x58", { 0x00CA, 0x030C, 0x0058 } },
+ /* <H-88A3>X => <U+00EA><U+0304>X */
+ { "<H-88A3>", "\x88\xa3\x58", { 0x00EA, 0x0304, 0x0058 } },
+ /* <H-88A5>X => <U+00EA><U+030C>X */
+ { "<H-88A5>", "\x88\xa5\x58", { 0x00EA, 0x030C, 0x0058 } }
+};
+
+/* Each test is of the form:
+ - Translate first code sequence (two bytes)
+ - Translate second (zero bytes)
+ - Translate the third (one byte). */
+static int
+check_conversion (struct testdata test)
+{
+ int err = 0;
+ wchar_t wc;
+ mbstate_t st;
+ size_t ret;
+ const char *mbs = test.input;
+ int consumed = 0;
+ /* Input is always 3 bytes long. */
+ int inlen = 3;
+
+ memset (&st, 0, sizeof (st));
+ /* First conversion: Consumes first 2 bytes. */
+ ret = mbrtowc (&wc, mbs, inlen - consumed, &st);
+ if (ret != 2)
+ {
+ printf ("error: First conversion consumed only %zd bytes.\n", ret);
+ err++;
+ }
+ /* Advance the two consumed bytes. */
+ mbs += ret;
+ consumed += ret;
+ if (wc != test.expected[0])
+ {
+ printf ("error: Result of first conversion was wrong.\n");
+ err++;
+ }
+ /* Second conversion: Consumes 0 bytes. */
+ ret = mbrtowc (&wc, mbs, inlen - consumed, &st);
+ if (ret != 0)
+ {
+ printf ("error: Second conversion consumed only %zd bytes.\n", ret);
+ err++;
+ }
+ /* Advance the zero consumed bytes. */
+ mbs += ret;
+ consumed += ret;
+ if (wc != test.expected[1])
+ {
+ printf ("error: Result of second conversion was wrong.\n");
+ err++;
+ }
+ /* After the second conversion the state of the converter should be
+ in the initial state. It is in the initial state because the two
+ input BIG5-HKSCS bytes have been consumed and the 2 wchar_t's have
+ been output. */
+ if (mbsinit (&st) == 0)
+ {
+ printf ("error: Converter not in initial state.\n");
+ err++;
+ }
+ /* Third conversion: Consumes 1 byte (it's an ASCII character). */
+ ret = mbrtowc (&wc, mbs, inlen - consumed, &st);
+ if (ret != 1)
+ {
+ printf ("error: Third conversion consumed only %zd bytes.\n", ret);
+ err++;
+ }
+ /* Advance the one byte. */
+ mbs += ret;
+ consumed += ret;
+ if (wc != test.expected[2])
+ {
+ printf ("error: Result of third conversion was wrong.\n");
+ err++;
+ }
+ /* Return 0 if we saw no errors. */
+ return err;
+}
+
+static int
+do_test (void)
+{
+ int err = 0;
+ int ret;
+ /* Testing BIG5-HKSCS. */
+ setlocale (LC_ALL, "zh_HK.BIG5-HKSCS");
+
+ /* Run all the special conversions. */
+ for (int i = 0; i < (sizeof (tests) / sizeof (struct testdata)); i++)
+ {
+ printf ("Running test for %s\n", tests[i].name);
+ ret = check_conversion (tests[i]);
+ if (ret > 0)
+ printf ("Test %s failed.\n", tests[i].name);
+ err += ret;
+ }
+
+ /* Fail if any conversion had an error. */
+ if (err > 0)
+ FAIL_EXIT1 ("One or more conversions failed.");
+
+ return 0;
+}
+
+#include <support/test-driver.c>
--
2.19.1
|
