Adding upstream version 9.1.upstream/9.1upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

3 files changed, 434 insertions, 0 deletions

diff --git a/gnulib-tests/unistr/test-strncat.h b/gnulib-tests/unistr/test-strncat.h
new file mode 100644
index 0000000..c66583e
--- /dev/null
+++ b/gnulib-tests/unistr/test-strncat.h
@@ -0,0 +1,90 @@
+/* Test of uN_strncat() functions.
+   Copyright (C) 2010-2022 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 <https://www.gnu.org/licenses/>.  */
+
+/* Written by Bruno Haible <bruno@clisp.org>, 2010.  */
+
+static void
+check_single (const UNIT *input, size_t length, size_t n)
+{
+  static const UNIT base[] = { 'C', 'h', 'a', 'n', 'g', 'i', 'n', 'g', 0 };
+  size_t m;
+
+  for (m = 0; m < SIZEOF (base); m++)
+    {
+      UNIT *dest;
+      UNIT *result;
+      size_t i;
+
+      dest = (UNIT *) malloc ((1 + m + n + 2) * sizeof (UNIT));
+      ASSERT (dest != NULL);
+
+      dest[0] = MAGIC;
+      for (i = 0; i < m; i++)
+        dest[1 + i] = base[i];
+      dest[1 + m] = 0;
+      for (i = 1; i < n + 2; i++)
+        dest[1 + m + i] = MAGIC;
+
+      result = U_STRNCAT (dest + 1, input, n);
+      ASSERT (result == dest + 1);
+
+      ASSERT (dest[0] == MAGIC);
+      for (i = 0; i < m; i++)
+        ASSERT (dest[1 + i] == base[i]);
+      for (i = 0; i < (n <= length ? n : length); i++)
+        ASSERT (dest[1 + m + i] == input[i]);
+      ASSERT (dest[1 + m + i] == 0);
+      ASSERT (dest[1 + m + i + 1] == MAGIC);
+
+      free (dest);
+    }
+}
+
+static void
+check (const UNIT *input, size_t input_length)
+{
+  size_t length;
+  size_t n;
+
+  ASSERT (input_length > 0);
+  ASSERT (input[input_length - 1] == 0);
+  length = input_length - 1; /* = U_STRLEN (input) */
+
+  for (n = 0; n <= 2 * length + 2; n++)
+    check_single (input, length, n);
+
+  /* Check that U_STRNCAT (D, S, N) does not look at more than
+     MIN (U_STRLEN (S) + 1, N) units.  */
+  {
+    char *page_boundary = (char *) zerosize_ptr ();
+
+    if (page_boundary != NULL)
+      {
+        for (n = 0; n <= 2 * length + 2; n++)
+          {
+            size_t n_to_copy = (n <= length ? n : length + 1);
+            UNIT *copy;
+            size_t i;
+
+            copy = (UNIT *) page_boundary - n_to_copy;
+            for (i = 0; i < n_to_copy; i++)
+              copy[i] = input[i];
+
+            check_single (copy, length, n);
+          }
+      }
+  }
+}
diff --git a/gnulib-tests/unistr/test-u8-mbtoucr.c b/gnulib-tests/unistr/test-u8-mbtoucr.c
new file mode 100644
index 0000000..e610260
--- /dev/null
+++ b/gnulib-tests/unistr/test-u8-mbtoucr.c
@@ -0,0 +1,187 @@
+/* Test of u8_mbtoucr() function.
+   Copyright (C) 2010-2022 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 <https://www.gnu.org/licenses/>.  */
+
+/* Written by Bruno Haible <bruno@clisp.org>, 2010.  */
+
+#include <config.h>
+
+#include "unistr.h"
+
+#include "macros.h"
+
+int
+main ()
+{
+  ucs4_t uc;
+  int ret;
+
+  /* Test NUL unit input.  */
+  {
+    static const uint8_t input[] = "";
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 1);
+    ASSERT (ret == 1);
+    ASSERT (uc == 0);
+  }
+
+  /* Test ISO 646 unit input.  */
+  {
+    ucs4_t c;
+    uint8_t buf[1];
+
+    for (c = 0; c < 0x80; c++)
+      {
+        buf[0] = c;
+        uc = 0xBADFACE;
+        ret = u8_mbtoucr (&uc, buf, 1);
+        ASSERT (ret == 1);
+        ASSERT (uc == c);
+      }
+  }
+
+  /* Test 2-byte character input.  */
+  {
+    static const uint8_t input[] = { 0xC3, 0x97 };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 2);
+    ASSERT (ret == 2);
+    ASSERT (uc == 0x00D7);
+  }
+
+  /* Test 3-byte character input.  */
+  {
+    static const uint8_t input[] = { 0xE2, 0x82, 0xAC };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 3);
+    ASSERT (ret == 3);
+    ASSERT (uc == 0x20AC);
+  }
+
+  /* Test 4-byte character input.  */
+  {
+    static const uint8_t input[] = { 0xF4, 0x8F, 0xBF, 0xBD };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 4);
+    ASSERT (ret == 4);
+    ASSERT (uc == 0x10FFFD);
+  }
+
+  /* Test incomplete/invalid 1-byte input.  */
+  {
+    static const uint8_t input[] = { 0xC1 };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 1);
+    ASSERT (ret == -1);
+    ASSERT (uc == 0xFFFD);
+  }
+  {
+    static const uint8_t input[] = { 0xC3 };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 1);
+    ASSERT (ret == -2);
+    ASSERT (uc == 0xFFFD);
+  }
+  {
+    static const uint8_t input[] = { 0xE2 };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 1);
+    ASSERT (ret == -2);
+    ASSERT (uc == 0xFFFD);
+  }
+  {
+    static const uint8_t input[] = { 0xF4 };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 1);
+    ASSERT (ret == -2);
+    ASSERT (uc == 0xFFFD);
+  }
+  {
+    static const uint8_t input[] = { 0xFE };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 1);
+    ASSERT (ret == -1);
+    ASSERT (uc == 0xFFFD);
+  }
+
+  /* Test incomplete/invalid 2-byte input.  */
+  {
+    static const uint8_t input[] = { 0xE0, 0x9F };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 2);
+    ASSERT (ret == -1);
+    ASSERT (uc == 0xFFFD);
+  }
+  {
+    static const uint8_t input[] = { 0xE2, 0x82 };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 2);
+    ASSERT (ret == -2);
+    ASSERT (uc == 0xFFFD);
+  }
+  {
+    static const uint8_t input[] = { 0xE2, 0xD0 };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 2);
+    ASSERT (ret == -1);
+    ASSERT (uc == 0xFFFD);
+  }
+  {
+    static const uint8_t input[] = { 0xF0, 0x8F };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 2);
+    ASSERT (ret == -1);
+    ASSERT (uc == 0xFFFD);
+  }
+  {
+    static const uint8_t input[] = { 0xF3, 0x8F };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 2);
+    ASSERT (ret == -2);
+    ASSERT (uc == 0xFFFD);
+  }
+  {
+    static const uint8_t input[] = { 0xF3, 0xD0 };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 2);
+    ASSERT (ret == -1);
+    ASSERT (uc == 0xFFFD);
+  }
+
+  /* Test incomplete/invalid 3-byte input.  */
+  {
+    static const uint8_t input[] = { 0xF3, 0x8F, 0xBF };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 3);
+    ASSERT (ret == -2);
+    ASSERT (uc == 0xFFFD);
+  }
+  {
+    static const uint8_t input[] = { 0xF3, 0xD0, 0xBF };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 3);
+    ASSERT (ret == -1);
+    ASSERT (uc == 0xFFFD);
+  }
+  {
+    static const uint8_t input[] = { 0xF3, 0x8F, 0xD0 };
+    uc = 0xBADFACE;
+    ret = u8_mbtoucr (&uc, input, 3);
+    ASSERT (ret == -1);
+    ASSERT (uc == 0xFFFD);
+  }
+
+  return 0;
+}
diff --git a/gnulib-tests/unistr/test-u8-uctomb.c b/gnulib-tests/unistr/test-u8-uctomb.c
new file mode 100644
index 0000000..cf37cb9
--- /dev/null
+++ b/gnulib-tests/unistr/test-u8-uctomb.c
@@ -0,0 +1,157 @@
+/* Test of u8_uctomb() function.
+   Copyright (C) 2010-2022 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 <https://www.gnu.org/licenses/>.  */
+
+/* Written by Bruno Haible <bruno@clisp.org>, 2010.  */
+
+#include <config.h>
+
+#include "unistr.h"
+
+#include "macros.h"
+
+#define MAGIC 0xBA
+
+int
+main ()
+{
+  /* Test ISO 646 character, in particular the NUL character.  */
+  {
+    ucs4_t uc;
+
+    for (uc = 0; uc < 0x80; uc++)
+      {
+        uint8_t buf[5] = { MAGIC, MAGIC, MAGIC, MAGIC, MAGIC };
+        int ret;
+
+        ret = u8_uctomb (buf, uc, 0);
+        ASSERT (ret == -2);
+        ASSERT (buf[0] == MAGIC);
+
+        ret = u8_uctomb (buf, uc, 1);
+        ASSERT (ret == 1);
+        ASSERT (buf[0] == uc);
+        ASSERT (buf[1] == MAGIC);
+      }
+  }
+
+  /* Test 2-byte character.  */
+  {
+    ucs4_t uc = 0x00D7;
+    uint8_t buf[5] = { MAGIC, MAGIC, MAGIC, MAGIC, MAGIC };
+    int ret;
+
+    ret = u8_uctomb (buf, uc, 0);
+    ASSERT (ret == -2);
+    ASSERT (buf[0] == MAGIC);
+
+    ret = u8_uctomb (buf, uc, 1);
+    ASSERT (ret == -2);
+    ASSERT (buf[0] == MAGIC);
+
+    ret = u8_uctomb (buf, uc, 2);
+    ASSERT (ret == 2);
+    ASSERT (buf[0] == 0xC3);
+    ASSERT (buf[1] == 0x97);
+    ASSERT (buf[2] == MAGIC);
+  }
+
+  /* Test 3-byte character.  */
+  {
+    ucs4_t uc = 0x20AC;
+    uint8_t buf[5] = { MAGIC, MAGIC, MAGIC, MAGIC, MAGIC };
+    int ret;
+
+    ret = u8_uctomb (buf, uc, 0);
+    ASSERT (ret == -2);
+    ASSERT (buf[0] == MAGIC);
+
+    ret = u8_uctomb (buf, uc, 1);
+    ASSERT (ret == -2);
+    ASSERT (buf[0] == MAGIC);
+
+    ret = u8_uctomb (buf, uc, 2);
+    ASSERT (ret == -2);
+    ASSERT (buf[0] == MAGIC);
+    ASSERT (buf[1] == MAGIC);
+
+    ret = u8_uctomb (buf, uc, 3);
+    ASSERT (ret == 3);
+    ASSERT (buf[0] == 0xE2);
+    ASSERT (buf[1] == 0x82);
+    ASSERT (buf[2] == 0xAC);
+    ASSERT (buf[3] == MAGIC);
+  }
+
+  /* Test 4-byte character.  */
+  {
+    ucs4_t uc = 0x10FFFD;
+    uint8_t buf[5] = { MAGIC, MAGIC, MAGIC, MAGIC, MAGIC };
+    int ret;
+
+    ret = u8_uctomb (buf, uc, 0);
+    ASSERT (ret == -2);
+    ASSERT (buf[0] == MAGIC);
+
+    ret = u8_uctomb (buf, uc, 1);
+    ASSERT (ret == -2);
+    ASSERT (buf[0] == MAGIC);
+
+    ret = u8_uctomb (buf, uc, 2);
+    ASSERT (ret == -2);
+    ASSERT (buf[0] == MAGIC);
+    ASSERT (buf[1] == MAGIC);
+
+    ret = u8_uctomb (buf, uc, 3);
+    ASSERT (ret == -2);
+    ASSERT (buf[0] == MAGIC);
+    ASSERT (buf[1] == MAGIC);
+    ASSERT (buf[2] == MAGIC);
+
+    ret = u8_uctomb (buf, uc, 4);
+    ASSERT (ret == 4);
+    ASSERT (buf[0] == 0xF4);
+    ASSERT (buf[1] == 0x8F);
+    ASSERT (buf[2] == 0xBF);
+    ASSERT (buf[3] == 0xBD);
+    ASSERT (buf[4] == MAGIC);
+  }
+
+  /* Test invalid characters.  */
+  {
+    ucs4_t invalid[] = { 0x110000, 0xD800, 0xDBFF, 0xDC00, 0xDFFF };
+    uint8_t buf[5] = { MAGIC, MAGIC, MAGIC, MAGIC, MAGIC };
+    size_t i;
+
+    for (i = 0; i < SIZEOF (invalid); i++)
+      {
+        ucs4_t uc = invalid[i];
+        int n;
+
+        for (n = 0; n <= 4; n++)
+          {
+            int ret = u8_uctomb (buf, uc, n);
+            ASSERT (ret == -1);
+            ASSERT (buf[0] == MAGIC);
+            ASSERT (buf[1] == MAGIC);
+            ASSERT (buf[2] == MAGIC);
+            ASSERT (buf[3] == MAGIC);
+            ASSERT (buf[4] == MAGIC);
+          }
+      }
+  }
+
+  return 0;
+}