X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=tests%2Ftest-striconveh.c;h=cfa877e92e087d3e006d1c2fb9bf3df186810a09;hb=800b95c20c636e1bd2e0f1c5e1ce3f84b5089942;hp=1243fcdfe4a3134a9f65b8bffd5e28d1d7460812;hpb=6984bc2a8dbe533274ee1869ba3c9e919040cf85;p=gnulib.git
diff --git a/tests/test-striconveh.c b/tests/test-striconveh.c
index 1243fcdfe..cfa877e92 100644
--- a/tests/test-striconveh.c
+++ b/tests/test-striconveh.c
@@ -1,10 +1,10 @@
/* Test of character set conversion with error handling.
- Copyright (C) 2007 Free Software Foundation, Inc.
+ Copyright (C) 2007-2010 Free Software Foundation, Inc.
- This program is free software; you can redistribute it and/or modify
+ 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 2, or (at your option)
- any later version.
+ 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
@@ -12,14 +12,11 @@
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, write to the Free Software Foundation,
- Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
+ along with this program. If not, see . */
/* Written by Bruno Haible , 2007. */
-#ifdef HAVE_CONFIG_H
-# include
-#endif
+#include
#include "striconveh.h"
@@ -31,91 +28,237 @@
#include
#include
-#define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
-#define ASSERT(expr) if (!(expr)) abort ();
+#include "macros.h"
+
+/* Magic number for detecting bounds violations. */
+#define MAGIC 0x1983EFF1
+
+static size_t *
+new_offsets (size_t n)
+{
+ size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t));
+ offsets[n] = MAGIC;
+ return offsets;
+}
int
main ()
{
static enum iconv_ilseq_handler handlers[] =
{ iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
+ size_t indirect;
size_t h;
+ size_t o;
+ size_t i;
#if HAVE_ICONV
/* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
ISO-8859-2, and UTF-8. */
+ iconv_t cd_ascii_to_88591 = iconv_open ("ISO-8859-1", "ASCII");
iconv_t cd_88591_to_88592 = iconv_open ("ISO-8859-2", "ISO-8859-1");
iconv_t cd_88592_to_88591 = iconv_open ("ISO-8859-1", "ISO-8859-2");
+ iconv_t cd_ascii_to_utf8 = iconv_open ("UTF-8", "ASCII");
iconv_t cd_88591_to_utf8 = iconv_open ("UTF-8", "ISO-8859-1");
iconv_t cd_utf8_to_88591 = iconv_open ("ISO-8859-1", "UTF-8");
iconv_t cd_88592_to_utf8 = iconv_open ("UTF-8", "ISO-8859-2");
iconv_t cd_utf8_to_88592 = iconv_open ("ISO-8859-2", "UTF-8");
+ iconv_t cd_utf7_to_utf8 = iconv_open ("UTF-8", "UTF-7");
+ iconveh_t cdeh_ascii_to_88591;
+ iconveh_t cdeh_ascii_to_88591_indirectly;
+ iconveh_t cdeh_88592_to_88591;
+ iconveh_t cdeh_88592_to_88591_indirectly;
+ iconveh_t cdeh_ascii_to_utf8;
+ iconveh_t cdeh_88591_to_utf8;
+ iconveh_t cdeh_utf8_to_88591;
+ iconveh_t cdeh_utf7_to_utf8;
- ASSERT (cd_88591_to_88592 != (iconv_t)(-1));
- ASSERT (cd_88592_to_88591 != (iconv_t)(-1));
+ ASSERT (cd_ascii_to_utf8 != (iconv_t)(-1));
ASSERT (cd_88591_to_utf8 != (iconv_t)(-1));
ASSERT (cd_utf8_to_88591 != (iconv_t)(-1));
ASSERT (cd_88592_to_utf8 != (iconv_t)(-1));
ASSERT (cd_utf8_to_88592 != (iconv_t)(-1));
+ cdeh_ascii_to_88591.cd = cd_ascii_to_88591;
+ cdeh_ascii_to_88591.cd1 = cd_ascii_to_utf8;
+ cdeh_ascii_to_88591.cd2 = cd_utf8_to_88591;
+
+ cdeh_ascii_to_88591_indirectly.cd = (iconv_t)(-1);
+ cdeh_ascii_to_88591_indirectly.cd1 = cd_ascii_to_utf8;
+ cdeh_ascii_to_88591_indirectly.cd2 = cd_utf8_to_88591;
+
+ cdeh_88592_to_88591.cd = cd_88592_to_88591;
+ cdeh_88592_to_88591.cd1 = cd_88592_to_utf8;
+ cdeh_88592_to_88591.cd2 = cd_utf8_to_88591;
+
+ cdeh_88592_to_88591_indirectly.cd = (iconv_t)(-1);
+ cdeh_88592_to_88591_indirectly.cd1 = cd_88592_to_utf8;
+ cdeh_88592_to_88591_indirectly.cd2 = cd_utf8_to_88591;
+
+ cdeh_ascii_to_utf8.cd = cd_ascii_to_utf8;
+ cdeh_ascii_to_utf8.cd1 = cd_ascii_to_utf8;
+ cdeh_ascii_to_utf8.cd2 = (iconv_t)(-1);
+
+ cdeh_88591_to_utf8.cd = cd_88591_to_utf8;
+ cdeh_88591_to_utf8.cd1 = cd_88591_to_utf8;
+ cdeh_88591_to_utf8.cd2 = (iconv_t)(-1);
+
+ cdeh_utf8_to_88591.cd = cd_utf8_to_88591;
+ cdeh_utf8_to_88591.cd1 = (iconv_t)(-1);
+ cdeh_utf8_to_88591.cd2 = cd_utf8_to_88591;
+
+ cdeh_utf7_to_utf8.cd = cd_utf7_to_utf8;
+ cdeh_utf7_to_utf8.cd1 = cd_utf7_to_utf8;
+ cdeh_utf7_to_utf8.cd2 = (iconv_t)(-1);
+
/* ------------------------ Test mem_cd_iconveh() ------------------------ */
/* Test conversion from ISO-8859-2 to ISO-8859-1 with no errors. */
- for (h = 0; h < SIZEOF (handlers); h++)
+ for (indirect = 0; indirect <= 1; indirect++)
{
- enum iconv_ilseq_handler handler = handlers[h];
- static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
- static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
- char *result = NULL;
- size_t length = 0;
- int retval = mem_cd_iconveh (input, strlen (input),
- cd_88592_to_88591,
- cd_88592_to_utf8, cd_utf8_to_88591,
- handler,
- &result, &length);
- ASSERT (retval == 0);
- ASSERT (length == strlen (expected));
- ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
- free (result);
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
+ static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_cd_iconveh (input, strlen (input),
+ (indirect
+ ? &cdeh_88592_to_88591_indirectly
+ : &cdeh_88592_to_88591),
+ handler,
+ offsets,
+ &result, &length);
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 37; i++)
+ ASSERT (offsets[i] == i);
+ ASSERT (offsets[37] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ }
+ }
+
+ /* Test conversion from ASCII to ISO-8859-1 with invalid input (EILSEQ). */
+ for (indirect = 0; indirect <= 1; indirect++)
+ {
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "Rafa\263 Maszkowski"; /* Rafa? Maszkowski */
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_cd_iconveh (input, strlen (input),
+ (indirect
+ ? &cdeh_ascii_to_88591_indirectly
+ : &cdeh_ascii_to_88591),
+ handler,
+ offsets,
+ &result, &length);
+ switch (handler)
+ {
+ case iconveh_error:
+ ASSERT (retval == -1 && errno == EILSEQ);
+ ASSERT (result == NULL);
+ if (o)
+ free (offsets);
+ break;
+ case iconveh_question_mark:
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Rafa? Maszkowski";
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 16; i++)
+ ASSERT (offsets[i] == i);
+ ASSERT (offsets[16] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ break;
+ }
+ }
+ }
}
/* Test conversion from ISO-8859-2 to ISO-8859-1 with EILSEQ. */
- for (h = 0; h < SIZEOF (handlers); h++)
+ for (indirect = 0; indirect <= 1; indirect++)
{
- enum iconv_ilseq_handler handler = handlers[h];
- static const char input[] = "Rafa\263 Maszkowski"; /* RafaÅ Maszkowski */
- char *result = NULL;
- size_t length = 0;
- int retval = mem_cd_iconveh (input, strlen (input),
- cd_88592_to_88591,
- cd_88592_to_utf8, cd_utf8_to_88591,
- handler,
- &result, &length);
- switch (handler)
- {
- case iconveh_error:
- ASSERT (retval == -1 && errno == EILSEQ);
- ASSERT (result == NULL);
- break;
- case iconveh_question_mark:
- {
- static const char expected[] = "Rafa? Maszkowski";
- ASSERT (retval == 0);
- ASSERT (length == strlen (expected));
- ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
- free (result);
- }
- break;
- case iconveh_escape_sequence:
- {
- static const char expected[] = "Rafa\\u0142 Maszkowski";
- ASSERT (retval == 0);
- ASSERT (length == strlen (expected));
- ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
- free (result);
- }
- break;
- }
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "Rafa\263 Maszkowski"; /* RafaÅ Maszkowski */
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_cd_iconveh (input, strlen (input),
+ (indirect
+ ? &cdeh_88592_to_88591_indirectly
+ : &cdeh_88592_to_88591),
+ handler,
+ offsets,
+ &result, &length);
+ switch (handler)
+ {
+ case iconveh_error:
+ ASSERT (retval == -1 && errno == EILSEQ);
+ ASSERT (result == NULL);
+ if (o)
+ free (offsets);
+ break;
+ case iconveh_question_mark:
+ {
+ static const char expected[] = "Rafa? Maszkowski";
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 16; i++)
+ ASSERT (offsets[i] == i);
+ ASSERT (offsets[16] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ break;
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Rafa\\u0142 Maszkowski";
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 16; i++)
+ ASSERT (offsets[i] == (i < 5 ? i :
+ i + 5));
+ ASSERT (offsets[16] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ break;
+ }
+ }
+ }
}
/* Test conversion from ISO-8859-1 to UTF-8 with no errors. */
@@ -124,17 +267,31 @@ main ()
enum iconv_ilseq_handler handler = handlers[h];
static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
- char *result = NULL;
- size_t length = 0;
- int retval = mem_cd_iconveh (input, strlen (input),
- cd_88591_to_utf8,
- cd_88591_to_utf8, (iconv_t)(-1),
- handler,
- &result, &length);
- ASSERT (retval == 0);
- ASSERT (length == strlen (expected));
- ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
- free (result);
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_cd_iconveh (input, strlen (input),
+ &cdeh_88591_to_utf8,
+ handler,
+ offsets,
+ &result, &length);
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 37; i++)
+ ASSERT (offsets[i] == (i < 1 ? i :
+ i < 12 ? i + 1 :
+ i < 18 ? i + 2 :
+ i + 3));
+ ASSERT (offsets[37] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
}
/* Test conversion from UTF-8 to ISO-8859-1 with no errors. */
@@ -143,17 +300,79 @@ main ()
enum iconv_ilseq_handler handler = handlers[h];
static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
- char *result = NULL;
- size_t length = 0;
- int retval = mem_cd_iconveh (input, strlen (input),
- cd_utf8_to_88591,
- (iconv_t)(-1), cd_utf8_to_88591,
- handler,
- &result, &length);
- ASSERT (retval == 0);
- ASSERT (length == strlen (expected));
- ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
- free (result);
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_cd_iconveh (input, strlen (input),
+ &cdeh_utf8_to_88591,
+ handler,
+ offsets,
+ &result, &length);
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 41; i++)
+ ASSERT (offsets[i] == (i < 1 ? i :
+ i == 1 ? (size_t)(-1) :
+ i < 13 ? i - 1 :
+ i == 13 ? (size_t)(-1) :
+ i < 20 ? i - 2 :
+ i == 20 ? (size_t)(-1) :
+ i < 40 ? i - 3 :
+ (size_t)(-1)));
+ ASSERT (offsets[41] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ }
+
+ /* Test conversion from ASCII to UTF-8 with invalid input (EILSEQ). */
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "Rafa\263 Maszkowski"; /* Rafa? Maszkowski */
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_cd_iconveh (input, strlen (input),
+ &cdeh_ascii_to_utf8,
+ handler,
+ offsets,
+ &result, &length);
+ switch (handler)
+ {
+ case iconveh_error:
+ ASSERT (retval == -1 && errno == EILSEQ);
+ ASSERT (result == NULL);
+ if (o)
+ free (offsets);
+ break;
+ case iconveh_question_mark:
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Rafa? Maszkowski";
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 16; i++)
+ ASSERT (offsets[i] == i);
+ ASSERT (offsets[16] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ break;
+ }
+ }
}
/* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */
@@ -161,38 +380,62 @@ main ()
{
enum iconv_ilseq_handler handler = handlers[h];
static const char input[] = "Rafa\305\202 Maszkowski"; /* RafaÅ Maszkowski */
- char *result = NULL;
- size_t length = 0;
- int retval = mem_cd_iconveh (input, strlen (input),
- cd_utf8_to_88591,
- (iconv_t)(-1), cd_utf8_to_88591,
- handler,
- &result, &length);
- switch (handler)
- {
- case iconveh_error:
- ASSERT (retval == -1 && errno == EILSEQ);
- ASSERT (result == NULL);
- break;
- case iconveh_question_mark:
- {
- static const char expected[] = "Rafa? Maszkowski";
- ASSERT (retval == 0);
- ASSERT (length == strlen (expected));
- ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
- free (result);
- }
- break;
- case iconveh_escape_sequence:
- {
- static const char expected[] = "Rafa\\u0142 Maszkowski";
- ASSERT (retval == 0);
- ASSERT (length == strlen (expected));
- ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
- free (result);
- }
- break;
- }
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_cd_iconveh (input, strlen (input),
+ &cdeh_utf8_to_88591,
+ handler,
+ offsets,
+ &result, &length);
+ switch (handler)
+ {
+ case iconveh_error:
+ ASSERT (retval == -1 && errno == EILSEQ);
+ ASSERT (result == NULL);
+ if (o)
+ free (offsets);
+ break;
+ case iconveh_question_mark:
+ {
+ static const char expected[] = "Rafa? Maszkowski";
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 17; i++)
+ ASSERT (offsets[i] == (i < 5 ? i :
+ i == 5 ? (size_t)(-1) :
+ i - 1));
+ ASSERT (offsets[17] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ break;
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Rafa\\u0142 Maszkowski";
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 17; i++)
+ ASSERT (offsets[i] == (i < 5 ? i :
+ i == 5 ? (size_t)(-1) :
+ i + 4));
+ ASSERT (offsets[17] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ break;
+ }
+ }
}
/* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */
@@ -200,67 +443,199 @@ main ()
{
enum iconv_ilseq_handler handler = handlers[h];
static const char input[] = "\342";
- char *result = NULL;
- size_t length = 0;
- int retval = mem_cd_iconveh (input, strlen (input),
- cd_utf8_to_88591,
- (iconv_t)(-1), cd_utf8_to_88591,
- handler,
- &result, &length);
- ASSERT (retval == 0);
- ASSERT (length == 0);
- if (result != NULL)
- free (result);
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_cd_iconveh (input, strlen (input),
+ &cdeh_utf8_to_88591,
+ handler,
+ offsets,
+ &result, &length);
+ ASSERT (retval == 0);
+ ASSERT (length == 0);
+ if (o)
+ {
+ ASSERT (offsets[0] == 0);
+ ASSERT (offsets[1] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ }
+
+ if (cd_utf7_to_utf8 != (iconv_t)(-1))
+ {
+ /* Disabled on Solaris, because Solaris 9 iconv() is buggy: it returns
+ -1 / EILSEQ when converting the 7th byte of the input "+VDLYP9hA". */
+# if !(defined __sun && !defined _LIBICONV_VERSION)
+ /* Test conversion from UTF-7 to UTF-8 with EINVAL. */
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ /* This is base64 encoded 0x54 0x32 0xD8 0x3F 0xD8 0x40. It would
+ convert to U+5432 U+D83F U+D840 but these are Unicode surrogates. */
+ static const char input[] = "+VDLYP9hA";
+ static const char expected1[] = "\345\220\262"; /* å² glibc */
+ static const char expected2[] = ""; /* libiconv */
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_cd_iconveh (input, 7,
+ &cdeh_utf7_to_utf8,
+ handler,
+ NULL,
+ &result, &length);
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected1) || length == strlen (expected2));
+ ASSERT (result != NULL);
+ if (length == strlen (expected1))
+ ASSERT (memcmp (result, expected1, strlen (expected1)) == 0);
+ else
+ ASSERT (memcmp (result, expected2, strlen (expected2)) == 0);
+ free (result);
+ }
+
+ /* Disabled on NetBSD, because NetBSD 5.0 iconv() is buggy: it converts
+ the input "+2D/YQNhB" to U+1FED8 U+3FD8 U+40D8. */
+# if !(defined __NetBSD__ && !defined _LIBICONV_VERSION)
+ /* Test conversion from UTF-7 to UTF-8 with EILSEQ. */
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ /* This is base64 encoded 0xD8 0x3F 0xD8 0x40 0xD8 0x41. It would
+ convert to U+D83F U+D840 U+D841 but these are Unicode surrogates. */
+ static const char input[] = "+2D/YQNhB";
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_cd_iconveh (input, strlen (input),
+ &cdeh_utf7_to_utf8,
+ handler,
+ NULL,
+ &result, &length);
+ switch (handler)
+ {
+ case iconveh_error:
+ ASSERT (retval == -1 && errno == EILSEQ);
+ ASSERT (result == NULL);
+ break;
+ case iconveh_question_mark:
+ case iconveh_escape_sequence:
+ {
+ /* glibc result */
+ static const char expected1[] = "?????";
+ /* libiconv <= 1.12 result */
+ static const char expected2[] = "?2D/YQNhB";
+ /* libiconv behaviour changed in version 1.13: the result is
+ '?' U+0FF6 U+1036; this is U+D83F U+D840 U+D841 shifted left
+ by 6 bits. */
+ static const char expected3[] = "?\340\277\266\341\200\266";
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected1)
+ || length == strlen (expected2)
+ || length == strlen (expected3));
+ ASSERT (result != NULL);
+ if (length == strlen (expected1))
+ ASSERT (memcmp (result, expected1, strlen (expected1)) == 0);
+ else if (length == strlen (expected2))
+ ASSERT (memcmp (result, expected2, strlen (expected2)) == 0);
+ else
+ ASSERT (memcmp (result, expected3, strlen (expected3)) == 0);
+ free (result);
+ }
+ break;
+ }
+ }
+# endif
+# endif
}
/* ------------------------ Test str_cd_iconveh() ------------------------ */
/* Test conversion from ISO-8859-2 to ISO-8859-1 with no errors. */
- for (h = 0; h < SIZEOF (handlers); h++)
+ for (indirect = 0; indirect <= 1; indirect++)
{
- enum iconv_ilseq_handler handler = handlers[h];
- static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
- static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
- char *result = str_cd_iconveh (input,
- cd_88592_to_88591,
- cd_88592_to_utf8, cd_utf8_to_88591,
- handler);
- ASSERT (result != NULL);
- ASSERT (strcmp (result, expected) == 0);
- free (result);
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
+ static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
+ char *result = str_cd_iconveh (input,
+ (indirect
+ ? &cdeh_88592_to_88591_indirectly
+ : &cdeh_88592_to_88591),
+ handler);
+ ASSERT (result != NULL);
+ ASSERT (strcmp (result, expected) == 0);
+ free (result);
+ }
+ }
+
+ /* Test conversion from ASCII to ISO-8859-1 with invalid input (EILSEQ). */
+ for (indirect = 0; indirect <= 1; indirect++)
+ {
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "Rafa\263 Maszkowski"; /* Rafa? Maszkowski */
+ char *result = str_cd_iconveh (input,
+ (indirect
+ ? &cdeh_ascii_to_88591_indirectly
+ : &cdeh_ascii_to_88591),
+ handler);
+ switch (handler)
+ {
+ case iconveh_error:
+ ASSERT (result == NULL && errno == EILSEQ);
+ break;
+ case iconveh_question_mark:
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Rafa? Maszkowski";
+ ASSERT (result != NULL);
+ ASSERT (strcmp (result, expected) == 0);
+ free (result);
+ }
+ break;
+ }
+ }
}
/* Test conversion from ISO-8859-2 to ISO-8859-1 with EILSEQ. */
- for (h = 0; h < SIZEOF (handlers); h++)
+ for (indirect = 0; indirect <= 1; indirect++)
{
- enum iconv_ilseq_handler handler = handlers[h];
- static const char input[] = "Rafa\263 Maszkowski"; /* RafaÅ Maszkowski */
- char *result = str_cd_iconveh (input,
- cd_88592_to_88591,
- cd_88592_to_utf8, cd_utf8_to_88591,
- handler);
- switch (handler)
- {
- case iconveh_error:
- ASSERT (result == NULL && errno == EILSEQ);
- break;
- case iconveh_question_mark:
- {
- static const char expected[] = "Rafa? Maszkowski";
- ASSERT (result != NULL);
- ASSERT (strcmp (result, expected) == 0);
- free (result);
- }
- break;
- case iconveh_escape_sequence:
- {
- static const char expected[] = "Rafa\\u0142 Maszkowski";
- ASSERT (result != NULL);
- ASSERT (strcmp (result, expected) == 0);
- free (result);
- }
- break;
- }
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "Rafa\263 Maszkowski"; /* RafaÅ Maszkowski */
+ char *result = str_cd_iconveh (input,
+ (indirect
+ ? &cdeh_88592_to_88591_indirectly
+ : &cdeh_88592_to_88591),
+ handler);
+ switch (handler)
+ {
+ case iconveh_error:
+ ASSERT (result == NULL && errno == EILSEQ);
+ break;
+ case iconveh_question_mark:
+ {
+ static const char expected[] = "Rafa? Maszkowski";
+ ASSERT (result != NULL);
+ ASSERT (strcmp (result, expected) == 0);
+ free (result);
+ }
+ break;
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Rafa\\u0142 Maszkowski";
+ ASSERT (result != NULL);
+ ASSERT (strcmp (result, expected) == 0);
+ free (result);
+ }
+ break;
+ }
+ }
}
/* Test conversion from ISO-8859-1 to UTF-8 with no errors. */
@@ -270,9 +645,8 @@ main ()
static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
char *result = str_cd_iconveh (input,
- cd_88591_to_utf8,
- cd_88591_to_utf8, (iconv_t)(-1),
- handler);
+ &cdeh_88591_to_utf8,
+ handler);
ASSERT (result != NULL);
ASSERT (strcmp (result, expected) == 0);
free (result);
@@ -285,45 +659,68 @@ main ()
static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
char *result = str_cd_iconveh (input,
- cd_utf8_to_88591,
- (iconv_t)(-1), cd_utf8_to_88591,
- handler);
+ &cdeh_utf8_to_88591,
+ handler);
ASSERT (result != NULL);
ASSERT (strcmp (result, expected) == 0);
free (result);
}
+ /* Test conversion from ASCII to UTF-8 with invalid input (EILSEQ). */
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "Rafa\263 Maszkowski"; /* Rafa? Maszkowski */
+ char *result = str_cd_iconveh (input,
+ &cdeh_ascii_to_utf8,
+ handler);
+ switch (handler)
+ {
+ case iconveh_error:
+ ASSERT (result == NULL && errno == EILSEQ);
+ break;
+ case iconveh_question_mark:
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Rafa? Maszkowski";
+ ASSERT (result != NULL);
+ ASSERT (strcmp (result, expected) == 0);
+ free (result);
+ }
+ break;
+ }
+ }
+
/* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */
for (h = 0; h < SIZEOF (handlers); h++)
{
enum iconv_ilseq_handler handler = handlers[h];
static const char input[] = "Costs: 27 \342\202\254"; /* EURO SIGN */
char *result = str_cd_iconveh (input,
- cd_utf8_to_88591,
- (iconv_t)(-1), cd_utf8_to_88591,
- handler);
+ &cdeh_utf8_to_88591,
+ handler);
switch (handler)
- {
- case iconveh_error:
- ASSERT (result == NULL && errno == EILSEQ);
- break;
- case iconveh_question_mark:
- {
- static const char expected[] = "Costs: 27 ?";
- ASSERT (result != NULL);
- ASSERT (strcmp (result, expected) == 0);
- free (result);
- }
- break;
- case iconveh_escape_sequence:
- {
- static const char expected[] = "Costs: 27 \\u20AC";
- ASSERT (result != NULL);
- ASSERT (strcmp (result, expected) == 0);
- free (result);
- }
- break;
- }
+ {
+ case iconveh_error:
+ ASSERT (result == NULL && errno == EILSEQ);
+ break;
+ case iconveh_question_mark:
+ {
+ static const char expected[] = "Costs: 27 ?";
+ ASSERT (result != NULL);
+ ASSERT (strcmp (result, expected) == 0);
+ free (result);
+ }
+ break;
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Costs: 27 \\u20AC";
+ ASSERT (result != NULL);
+ ASSERT (strcmp (result, expected) == 0);
+ free (result);
+ }
+ break;
+ }
}
/* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */
@@ -332,21 +729,274 @@ main ()
enum iconv_ilseq_handler handler = handlers[h];
static const char input[] = "\342";
char *result = str_cd_iconveh (input,
- cd_utf8_to_88591,
- (iconv_t)(-1), cd_utf8_to_88591,
- handler);
+ &cdeh_utf8_to_88591,
+ handler);
ASSERT (result != NULL);
ASSERT (strcmp (result, "") == 0);
free (result);
}
- iconv_close (cd_88591_to_88592);
- iconv_close (cd_88592_to_88591);
+ if (cd_88591_to_88592 != (iconv_t)(-1))
+ iconv_close (cd_88591_to_88592);
+ if (cd_88592_to_88591 != (iconv_t)(-1))
+ iconv_close (cd_88592_to_88591);
iconv_close (cd_88591_to_utf8);
iconv_close (cd_utf8_to_88591);
iconv_close (cd_88592_to_utf8);
iconv_close (cd_utf8_to_88592);
+ /* ------------------------- Test mem_iconveh() ------------------------- */
+
+ /* Test conversion from ISO-8859-2 to ISO-8859-1 with no errors. */
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
+ static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_iconveh (input, strlen (input),
+ "ISO-8859-2", "ISO-8859-1",
+ handler,
+ offsets,
+ &result, &length);
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 37; i++)
+ ASSERT (offsets[i] == i);
+ ASSERT (offsets[37] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ }
+
+ /* Test conversion from ISO-8859-2 to ISO-8859-1 with EILSEQ. */
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "Rafa\263 Maszkowski"; /* RafaÅ Maszkowski */
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_iconveh (input, strlen (input),
+ "ISO-8859-2", "ISO-8859-1",
+ handler,
+ offsets,
+ &result, &length);
+ switch (handler)
+ {
+ case iconveh_error:
+ ASSERT (retval == -1 && errno == EILSEQ);
+ ASSERT (result == NULL);
+ if (o)
+ free (offsets);
+ break;
+ case iconveh_question_mark:
+ {
+ static const char expected[] = "Rafa? Maszkowski";
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 16; i++)
+ ASSERT (offsets[i] == i);
+ ASSERT (offsets[16] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ break;
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Rafa\\u0142 Maszkowski";
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 16; i++)
+ ASSERT (offsets[i] == (i < 5 ? i :
+ i + 5));
+ ASSERT (offsets[16] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ break;
+ }
+ }
+ }
+
+ /* Test conversion from ISO-8859-1 to UTF-8 with no errors. */
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
+ static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_iconveh (input, strlen (input),
+ "ISO-8859-1", "UTF-8",
+ handler,
+ offsets,
+ &result, &length);
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 37; i++)
+ ASSERT (offsets[i] == (i < 1 ? i :
+ i < 12 ? i + 1 :
+ i < 18 ? i + 2 :
+ i + 3));
+ ASSERT (offsets[37] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ }
+
+ /* Test conversion from UTF-8 to ISO-8859-1 with no errors. */
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
+ static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_iconveh (input, strlen (input),
+ "UTF-8", "ISO-8859-1",
+ handler,
+ offsets,
+ &result, &length);
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 41; i++)
+ ASSERT (offsets[i] == (i < 1 ? i :
+ i == 1 ? (size_t)(-1) :
+ i < 13 ? i - 1 :
+ i == 13 ? (size_t)(-1) :
+ i < 20 ? i - 2 :
+ i == 20 ? (size_t)(-1) :
+ i < 40 ? i - 3 :
+ (size_t)(-1)));
+ ASSERT (offsets[41] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ }
+
+ /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "Rafa\305\202 Maszkowski"; /* RafaÅ Maszkowski */
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_iconveh (input, strlen (input),
+ "UTF-8", "ISO-8859-1",
+ handler,
+ offsets,
+ &result, &length);
+ switch (handler)
+ {
+ case iconveh_error:
+ ASSERT (retval == -1 && errno == EILSEQ);
+ ASSERT (result == NULL);
+ if (o)
+ free (offsets);
+ break;
+ case iconveh_question_mark:
+ {
+ static const char expected[] = "Rafa? Maszkowski";
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 17; i++)
+ ASSERT (offsets[i] == (i < 5 ? i :
+ i == 5 ? (size_t)(-1) :
+ i - 1));
+ ASSERT (offsets[17] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ break;
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Rafa\\u0142 Maszkowski";
+ ASSERT (retval == 0);
+ ASSERT (length == strlen (expected));
+ ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
+ if (o)
+ {
+ for (i = 0; i < 17; i++)
+ ASSERT (offsets[i] == (i < 5 ? i :
+ i == 5 ? (size_t)(-1) :
+ i + 4));
+ ASSERT (offsets[17] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ break;
+ }
+ }
+ }
+
+ /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */
+ for (h = 0; h < SIZEOF (handlers); h++)
+ {
+ enum iconv_ilseq_handler handler = handlers[h];
+ static const char input[] = "\342";
+ for (o = 0; o < 2; o++)
+ {
+ size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
+ char *result = NULL;
+ size_t length = 0;
+ int retval = mem_iconveh (input, strlen (input),
+ "UTF-8", "ISO-8859-1",
+ handler,
+ offsets,
+ &result, &length);
+ ASSERT (retval == 0);
+ ASSERT (length == 0);
+ if (o)
+ {
+ ASSERT (offsets[0] == 0);
+ ASSERT (offsets[1] == MAGIC);
+ free (offsets);
+ }
+ free (result);
+ }
+ }
+
/* ------------------------- Test str_iconveh() ------------------------- */
/* Test conversion from ISO-8859-2 to ISO-8859-1 with no errors. */
@@ -368,27 +1018,27 @@ main ()
static const char input[] = "Rafa\263 Maszkowski"; /* RafaÅ Maszkowski */
char *result = str_iconveh (input, "ISO-8859-2", "ISO-8859-1", handler);
switch (handler)
- {
- case iconveh_error:
- ASSERT (result == NULL && errno == EILSEQ);
- break;
- case iconveh_question_mark:
- {
- static const char expected[] = "Rafa? Maszkowski";
- ASSERT (result != NULL);
- ASSERT (strcmp (result, expected) == 0);
- free (result);
- }
- break;
- case iconveh_escape_sequence:
- {
- static const char expected[] = "Rafa\\u0142 Maszkowski";
- ASSERT (result != NULL);
- ASSERT (strcmp (result, expected) == 0);
- free (result);
- }
- break;
- }
+ {
+ case iconveh_error:
+ ASSERT (result == NULL && errno == EILSEQ);
+ break;
+ case iconveh_question_mark:
+ {
+ static const char expected[] = "Rafa? Maszkowski";
+ ASSERT (result != NULL);
+ ASSERT (strcmp (result, expected) == 0);
+ free (result);
+ }
+ break;
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Rafa\\u0142 Maszkowski";
+ ASSERT (result != NULL);
+ ASSERT (strcmp (result, expected) == 0);
+ free (result);
+ }
+ break;
+ }
}
/* Test conversion from ISO-8859-1 to UTF-8 with no errors. */
@@ -422,27 +1072,27 @@ main ()
static const char input[] = "Costs: 27 \342\202\254"; /* EURO SIGN */
char *result = str_iconveh (input, "UTF-8", "ISO-8859-1", handler);
switch (handler)
- {
- case iconveh_error:
- ASSERT (result == NULL && errno == EILSEQ);
- break;
- case iconveh_question_mark:
- {
- static const char expected[] = "Costs: 27 ?";
- ASSERT (result != NULL);
- ASSERT (strcmp (result, expected) == 0);
- free (result);
- }
- break;
- case iconveh_escape_sequence:
- {
- static const char expected[] = "Costs: 27 \\u20AC";
- ASSERT (result != NULL);
- ASSERT (strcmp (result, expected) == 0);
- free (result);
- }
- break;
- }
+ {
+ case iconveh_error:
+ ASSERT (result == NULL && errno == EILSEQ);
+ break;
+ case iconveh_question_mark:
+ {
+ static const char expected[] = "Costs: 27 ?";
+ ASSERT (result != NULL);
+ ASSERT (strcmp (result, expected) == 0);
+ free (result);
+ }
+ break;
+ case iconveh_escape_sequence:
+ {
+ static const char expected[] = "Costs: 27 \\u20AC";
+ ASSERT (result != NULL);
+ ASSERT (strcmp (result, expected) == 0);
+ free (result);
+ }
+ break;
+ }
}
/* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */