summaryrefslogtreecommitdiff
path: root/tests/unistr/test-u8-mbtouc.c
diff options
context:
space:
mode:
authorManuel A. Fernandez Montecelo <manuel.montezelo@gmail.com>2016-05-27 14:35:40 +0100
committerManuel A. Fernandez Montecelo <manuel.montezelo@gmail.com>2016-05-27 14:35:40 +0100
commitb1de003dac299705a7f01c997d2b866bafe39926 (patch)
tree1cc16a3877e945116387a380f7f3023f81fa36e4 /tests/unistr/test-u8-mbtouc.c
parent752fd7247bc223bcea35bd89cf56d1c08ead9ba6 (diff)
parent3590c846d4c2febbc05b4ad6b14a06edc549e453 (diff)
Merge tag 'upstream/0.9.6+really0.9.6'
Upstream version 0.9.6+really0.9.6
Diffstat (limited to 'tests/unistr/test-u8-mbtouc.c')
-rw-r--r--tests/unistr/test-u8-mbtouc.c161
1 files changed, 160 insertions, 1 deletions
diff --git a/tests/unistr/test-u8-mbtouc.c b/tests/unistr/test-u8-mbtouc.c
index f6960a6..9e3b960 100644
--- a/tests/unistr/test-u8-mbtouc.c
+++ b/tests/unistr/test-u8-mbtouc.c
@@ -1,5 +1,5 @@
/* Test of u8_mbtouc() function.
- Copyright (C) 2010 Free Software Foundation, Inc.
+ Copyright (C) 2010-2015 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
@@ -24,10 +24,169 @@
#include "test-u8-mbtouc.h"
+static void
+test_safe_function (int (*my_u8_mbtouc) (ucs4_t *, const uint8_t *, size_t))
+{
+ ucs4_t uc;
+ int ret;
+
+ /* Test behaviour required by ISO 10646-1, sections R.7 and 2.3c, namely,
+ that a "malformed sequence" is interpreted in the same way as
+ "a character that is outside the adopted subset".
+ Reference:
+ Markus Kuhn: UTF-8 decoder capability and stress test
+ <http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt>
+ <http://www.w3.org/2001/06/utf-8-wrong/UTF-8-test.html>
+ */
+ /* 3.1. Test that each unexpected continuation byte is signalled as a
+ malformed sequence of its own. */
+ {
+ static const uint8_t input[] = { '"', 0x80, 0xBF, 0x80, 0xBF, '"' };
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input, 6);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 1, 5);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0xFFFD);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 2, 4);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0xFFFD);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 3, 3);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0xFFFD);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 4, 2);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0xFFFD);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 5, 1);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ }
+ /* 3.2. Lonely start characters. */
+ {
+ ucs4_t c;
+ uint8_t input[2];
+
+ for (c = 0xC0; c <= 0xFF; c++)
+ {
+ input[0] = c;
+ input[1] = ' ';
+
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input, 2);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0xFFFD);
+ }
+ }
+ /* 3.3. Sequences with last continuation byte missing. */
+ /* 3.3.1. 2-byte sequence with last byte missing. */
+ {
+ static const uint8_t input[] = { '"', 0xC0, '"' };
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input, 3);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 1, 2);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0xFFFD);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 2, 1);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ }
+ /* 3.3.6. 2-byte sequence with last byte missing. */
+ {
+ static const uint8_t input[] = { '"', 0xDF, '"' };
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input, 3);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 1, 2);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0xFFFD);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 2, 1);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ }
+ /* 3.3.2. 3-byte sequence with last byte missing. */
+ {
+ static const uint8_t input[] = { '"', 0xE0, 0x80, '"' };
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input, 4);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 1, 3);
+ ASSERT (ret == 2);
+ ASSERT (uc == 0xFFFD);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 3, 1);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ }
+ /* 3.3.7. 3-byte sequence with last byte missing. */
+ {
+ static const uint8_t input[] = { '"', 0xEF, 0xBF, '"' };
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input, 4);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 1, 3);
+ ASSERT (ret == 2);
+ ASSERT (uc == 0xFFFD);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 3, 1);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ }
+ /* 3.3.3. 4-byte sequence with last byte missing. */
+ {
+ static const uint8_t input[] = { '"', 0xF0, 0x80, 0x80, '"' };
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input, 5);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 1, 4);
+ ASSERT (ret == 3);
+ ASSERT (uc == 0xFFFD);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 4, 1);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ }
+ /* 3.3.8. 4-byte sequence with last byte missing. */
+ {
+ static const uint8_t input[] = { '"', 0xF7, 0xBF, 0xBF, '"' };
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input, 5);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 1, 4);
+ ASSERT (ret == 3);
+ ASSERT (uc == 0xFFFD);
+ uc = 0xBADFACE;
+ ret = my_u8_mbtouc (&uc, input + 4, 1);
+ ASSERT (ret == 1);
+ ASSERT (uc == 0x0022);
+ }
+}
+
int
main ()
{
test_function (u8_mbtouc);
+ test_safe_function (u8_mbtouc);
return 0;
}