/*
- * Copyright (c) 2002-2004, Index Data
+ * Copyright (C) 1995-2007, Index Data ApS
* See the file LICENSE for details.
*
- * $Id: tsticonv.c,v 1.2 2004-03-15 21:39:06 adam Exp $
+ * $Id: tsticonv.c,v 1.25 2007-03-09 08:39:38 adam Exp $
*/
#if HAVE_CONFIG_H
#include <config.h>
#endif
+#include <stdlib.h>
#include <errno.h>
#include <string.h>
#include <ctype.h>
#include <yaz/yaz-util.h>
+#include <yaz/test.h>
-/* some test strings in ISO-8859-1 format */
-static const char *iso_8859_1_a[] = {
- "ax" ,
- "\330",
- "eneb\346r",
- "\xfc",
- "\xfb",
- "\xfbr",
- 0 };
-
-/* same test strings in MARC-8 format */
-static const char *marc8_a[] = {
- "ax",
- "\xa2", /* latin capital letter o with stroke */
- "eneb\xb5r", /* latin small letter ae */
- "\xe8\x75", /* latin small letter u with umlaut */
- "\xe3\x75", /* latin small letter u with circumflex */
- "\xe3\x75r", /* latin small letter u with circumflex */
- 0
-};
-
-static void marc8_tst_a()
+static int compare_buffers(char *msg, int no,
+ int expect_len, const char *expect_buf,
+ int got_len, const char *got_buf)
{
- int i;
- yaz_iconv_t cd;
-
- cd = yaz_iconv_open("ISO-8859-1", "MARC8");
- if (!cd)
+ if (expect_len == got_len
+ && !memcmp(expect_buf, got_buf, expect_len))
+ return 1;
+
+ if (0) /* use 1 see how the buffers differ (for debug purposes) */
{
- printf("tsticonv 10 yaz_iconv_open failed\n");
- exit(10);
+ int i;
+ printf("tsticonv test=%s i=%d failed\n", msg, no);
+ printf("off got exp\n");
+ for (i = 0; i<got_len || i<expect_len; i++)
+ {
+ char got_char[10];
+ char expect_char[10];
+
+ if (i < got_len)
+ sprintf(got_char, "%02X", got_buf[i]);
+ else
+ sprintf(got_char, "? ");
+
+ if (i < expect_len)
+ sprintf(expect_char, "%02X", expect_buf[i]);
+ else
+ sprintf(expect_char, "? ");
+
+ printf("%02d %s %s %c\n",
+ i, got_char, expect_char, got_buf[i] == expect_buf[i] ?
+ ' ' : '*');
+
+ }
}
- for (i = 0; iso_8859_1_a[i]; i++)
- {
- size_t r;
- char *inbuf= (char*) marc8_a[i];
- size_t inbytesleft = strlen(inbuf);
- char outbuf0[24];
- char *outbuf = outbuf0;
- size_t outbytesleft = sizeof(outbuf0);
+ return 0;
+}
+
+static int tst_convert_l(yaz_iconv_t cd, size_t in_len, const char *in_buf,
+ size_t expect_len, const char *expect_buf)
+{
+ size_t r;
+ char *inbuf= (char*) in_buf;
+ size_t inbytesleft = in_len > 0 ? in_len : strlen(in_buf);
+ char outbuf0[64];
+ char *outbuf = outbuf0;
+ while (inbytesleft)
+ {
+ size_t outbytesleft = outbuf0 + sizeof(outbuf0) - outbuf;
+ if (outbytesleft > 12)
+ outbytesleft = 12;
r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
if (r == (size_t) (-1))
{
int e = yaz_iconv_error(cd);
-
- printf ("tsticonv 11 i=%d e=%d\n", i, e);
- exit(11);
+ if (e != YAZ_ICONV_E2BIG)
+ return 0;
}
- if ((outbuf - outbuf0) != strlen(iso_8859_1_a[i])
- || memcmp(outbuf0, iso_8859_1_a[i],
- strlen(iso_8859_1_a[i])))
+ else
+ break;
+ }
+ return compare_buffers("tsticonv 22", 0,
+ expect_len, expect_buf,
+ outbuf - outbuf0, outbuf0);
+}
+
+static int tst_convert(yaz_iconv_t cd, const char *buf, const char *cmpbuf)
+{
+ int ret = 0;
+ WRBUF b = wrbuf_alloc();
+ char outbuf[12];
+ size_t inbytesleft = strlen(buf);
+ const char *inp = buf;
+ int rounds = 0;
+ for (rounds = 0; inbytesleft && rounds < sizeof(outbuf); rounds++)
+ {
+ size_t outbytesleft = sizeof(outbuf);
+ char *outp = outbuf;
+ size_t r = yaz_iconv(cd, (char**) &inp, &inbytesleft,
+ &outp, &outbytesleft);
+ wrbuf_write(b, outbuf, outp - outbuf);
+ if (r == (size_t) (-1))
{
- printf ("tsticonv 12 i=%d\n", i);
- printf ("buf=%s out=%s\n", iso_8859_1_a[i], outbuf0);
- exit(12);
+ int e = yaz_iconv_error(cd);
+ if (e != YAZ_ICONV_E2BIG)
+ break;
}
}
+ if (wrbuf_len(b) == strlen(cmpbuf)
+ && !memcmp(cmpbuf, wrbuf_buf(b), wrbuf_len(b)))
+ ret = 1;
+ else
+ yaz_log(YLOG_LOG, "GOT (%.*s)", wrbuf_len(b), wrbuf_buf(b));
+ wrbuf_free(b, 1);
+ return ret;
+}
+
+
+/* some test strings in ISO-8859-1 format */
+static const char *iso_8859_1_a[] = {
+ "ax" ,
+ "\xd8",
+ "eneb\346r",
+ "\xe5" "\xd8",
+ "\xe5" "\xd8" "b",
+ "\xe5" "\xe5",
+ 0 };
+
+static void tst_marc8_to_ucs4b(void)
+{
+ yaz_iconv_t cd = yaz_iconv_open("UCS4", "MARC8");
+ YAZ_CHECK(cd);
+ if (!cd)
+ return;
+
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 0,
+ "\033$1" "\x21\x2B\x3B" /* FF1F */ "\033(B" "o",
+ 8,
+ "\x00\x00\xFF\x1F" "\x00\x00\x00o"));
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 0,
+ "\033$1" "\x6F\x77\x29" /* AE0E */
+ "\x6F\x52\x7C" /* c0F4 */ "\033(B",
+ 8,
+ "\x00\x00\xAE\x0E" "\x00\x00\xC0\xF4"));
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 0,
+ "\033$1"
+ "\x21\x50\x6E" /* UCS 7CFB */
+ "\x21\x51\x31" /* UCS 7D71 */
+ "\x21\x3A\x67" /* UCS 5B89 */
+ "\x21\x33\x22" /* UCS 5168 */
+ "\x21\x33\x53" /* UCS 5206 */
+ "\x21\x44\x2B" /* UCS 6790 */
+ "\033(B",
+ 24,
+ "\x00\x00\x7C\xFB"
+ "\x00\x00\x7D\x71"
+ "\x00\x00\x5B\x89"
+ "\x00\x00\x51\x68"
+ "\x00\x00\x52\x06"
+ "\x00\x00\x67\x90"));
+
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 0,
+ "\xB0\xB2", /* AYN and oSLASH */
+ 8,
+ "\x00\x00\x02\xBB" "\x00\x00\x00\xF8"));
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 0,
+ "\xF6\x61", /* a underscore */
+ 8,
+ "\x00\x00\x00\x61" "\x00\x00\x03\x32"));
+
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 0,
+ "\x61\xC2", /* a, phonorecord mark */
+ 8,
+ "\x00\x00\x00\x61" "\x00\x00\x21\x17"));
+
+ /* bug #258 */
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 0,
+ "el" "\xe8" "am\xe8" "an", /* elaman where a is a" */
+ 32,
+ "\x00\x00\x00" "e"
+ "\x00\x00\x00" "l"
+ "\x00\x00\x00" "a"
+ "\x00\x00\x03\x08"
+ "\x00\x00\x00" "m"
+ "\x00\x00\x00" "a"
+ "\x00\x00\x03\x08"
+ "\x00\x00\x00" "n"));
+ /* bug #260 */
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 0,
+ "\xe5\xe8\x41",
+ 12,
+ "\x00\x00\x00\x41" "\x00\x00\x03\x04" "\x00\x00\x03\x08"));
+ /* bug #416 */
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 0,
+ "\xEB\x74\xEC\x73",
+ 12,
+ "\x00\x00\x00\x74" "\x00\x00\x03\x61" "\x00\x00\x00\x73"));
+ /* bug #416 */
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 0,
+ "\xFA\x74\xFB\x73",
+ 12,
+ "\x00\x00\x00\x74" "\x00\x00\x03\x60" "\x00\x00\x00\x73"));
+
+ yaz_iconv_close(cd);
+}
+
+static void tst_ucs4b_to_utf8(void)
+{
+ yaz_iconv_t cd = yaz_iconv_open("UTF8", "UCS4");
+ YAZ_CHECK(cd);
+ if (!cd)
+ return;
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 8,
+ "\x00\x00\xFF\x1F\x00\x00\x00o",
+ 4,
+ "\xEF\xBC\x9F\x6F"));
+
+ YAZ_CHECK(tst_convert_l(
+ cd,
+ 8,
+ "\x00\x00\xAE\x0E\x00\x00\xC0\xF4",
+ 6,
+ "\xEA\xB8\x8E\xEC\x83\xB4"));
yaz_iconv_close(cd);
}
-static void marc8_tst_b()
+static void dconvert(int mandatory, const char *tmpcode)
{
- static const char *marc8_b[] = {
- "\033$1" "\x21\x2B\x3B" /* FF1F */ "\033(B" "o",
- "\033$1" "\x6F\x77\x29" /* AE0E */ "\x6F\x52\x7C" /* c0F4 */ "\033(B",
- "\033$1"
- "\x21\x50\x6E" /* 7CFB */
- "\x21\x51\x31" /* 7D71 */
- "\x21\x3A\x67" /* 5B89 */
- "\x21\x33\x22" /* 5168 */
- "\x21\x33\x53" /* 5206 */
- "\x21\x44\x2B" /* 6790 */
- "\033(B",
- 0
- };
- static const char *ucs4_b[] = {
- "\x00\x00\xFF\x1F" "\x00\x00\x00o",
- "\x00\x00\xAE\x0E" "\x00\x00\xC0\xF4",
- "\x00\x00\x7C\xFB"
- "\x00\x00\x7D\x71"
- "\x00\x00\x5B\x89"
- "\x00\x00\x51\x68"
- "\x00\x00\x52\x06"
- "\x00\x00\x67\x90",
- 0
- };
int i;
+ int ret;
yaz_iconv_t cd;
-
- cd = yaz_iconv_open("UCS4", "MARC8");
- if (!cd)
- {
- printf ("tsticonv 20 yaz_iconv_open failed\n");
- exit(20);
- }
- for (i = 0; marc8_b[i]; i++)
+ for (i = 0; iso_8859_1_a[i]; i++)
{
size_t r;
- size_t len;
- size_t expect_len = (i == 2 ? 24 : 8);
- char *inbuf= (char*) marc8_b[i];
+ char *inbuf = (char*) iso_8859_1_a[i];
size_t inbytesleft = strlen(inbuf);
char outbuf0[24];
+ char outbuf1[10];
char *outbuf = outbuf0;
size_t outbytesleft = sizeof(outbuf0);
+ cd = yaz_iconv_open(tmpcode, "ISO-8859-1");
+ YAZ_CHECK(cd || !mandatory);
+ if (!cd)
+ return;
r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
+ YAZ_CHECK(r != (size_t) (-1));
+ yaz_iconv_close(cd);
if (r == (size_t) (-1))
- {
- int e = yaz_iconv_error(cd);
+ return;
+
+ cd = yaz_iconv_open("ISO-8859-1", tmpcode);
+ YAZ_CHECK(cd || !mandatory);
+ if (!cd)
+ return;
+ inbuf = outbuf0;
+ inbytesleft = sizeof(outbuf0) - outbytesleft;
- printf ("tsticonv 21 i=%d e=%d\n", i, e);
- exit(21);
- }
- len = outbuf - outbuf0;
- if (len != expect_len || memcmp(outbuf0, ucs4_b[i], len))
+ outbuf = outbuf1;
+ outbytesleft = sizeof(outbuf1);
+ r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
+ YAZ_CHECK(r != (size_t) (-1));
+ if (r != (size_t)(-1))
{
- printf ("tsticonv 22 len=%d gotlen=%d i=%d\n", expect_len, len, i);
- exit(22);
+ ret = compare_buffers("dconvert", i,
+ strlen(iso_8859_1_a[i]), iso_8859_1_a[i],
+ sizeof(outbuf1) - outbytesleft, outbuf1);
+ YAZ_CHECK(ret);
}
+ yaz_iconv_close(cd);
}
- yaz_iconv_close(cd);
}
-static void marc8_tst_c()
+int utf8_check(unsigned c)
{
- static const char *ucs4_c[] = {
- "\x00\x00\xFF\x1F\x00\x00\x00o",
- "\x00\x00\xAE\x0E\x00\x00\xC0\xF4",
- 0
- };
- static const char *utf8_c[] = {
- "\xEF\xBC\x9F\x6F",
- "\xEA\xB8\x8E\xEC\x83\xB4",
- 0
- };
-
- int i;
- yaz_iconv_t cd;
-
- cd = yaz_iconv_open("UTF8", "UCS4");
- if (!cd)
- {
- printf ("tsticonv 30 yaz_iconv_open failed\n");
- exit(30);
- }
- for (i = 0; ucs4_c[i]; i++)
+ if (sizeof(c) >= 4)
{
size_t r;
- size_t len;
- char *inbuf= (char*) ucs4_c[i];
- size_t inbytesleft = 8;
- char outbuf0[24];
- char *outbuf = outbuf0;
- size_t outbytesleft = sizeof(outbuf0);
+ char src[4];
+ char dst[4];
+ char utf8buf[6];
+ char *inbuf = src;
+ size_t inbytesleft = 4;
+ char *outbuf = utf8buf;
+ size_t outbytesleft = sizeof(utf8buf);
+ int i;
+ yaz_iconv_t cd = yaz_iconv_open("UTF-8", "UCS4LE");
+ if (!cd)
+ return 0;
+ for (i = 0; i<4; i++)
+ src[i] = c >> (i*8);
+
+ r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
+ yaz_iconv_close(cd);
+
+ if (r == (size_t)(-1))
+ return 0;
+
+ cd = yaz_iconv_open("UCS4LE", "UTF-8");
+ if (!cd)
+ return 0;
+ inbytesleft = sizeof(utf8buf) - outbytesleft;
+ inbuf = utf8buf;
+
+ outbuf = dst;
+ outbytesleft = 4;
r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
- if (r == (size_t) (-1))
- {
- int e = yaz_iconv_error(cd);
+ if (r == (size_t)(-1))
+ return 0;
- printf ("tsticonv 31 i=%d e=%d\n", i, e);
- exit(31);
- }
- len = outbuf - outbuf0;
- if (len != strlen(utf8_c[i]) || memcmp(outbuf0, utf8_c[i], len))
- {
- printf ("tsticonv 32 len=%d gotlen=%d i=%d\n",
- strlen(utf8_c[i]), len, i);
- exit(32);
- }
+ yaz_iconv_close(cd);
+
+ if (memcmp(src, dst, 4))
+ return 0;
}
+ return 1;
+}
+
+static void tst_marc8_to_utf8(void)
+{
+ yaz_iconv_t cd = yaz_iconv_open("UTF-8", "MARC8");
+
+ YAZ_CHECK(cd);
+ if (!cd)
+ return;
+
+ YAZ_CHECK(tst_convert(cd, "Cours de math",
+ "Cours de math"));
+ /* COMBINING ACUTE ACCENT */
+ YAZ_CHECK(tst_convert(cd, "Cours de mathâe",
+ "Cours de mathe\xcc\x81"));
+
+
+ YAZ_CHECK(tst_convert(cd, "a\xea\x1e", "a\x1e\xcc\x8a"));
+
+ YAZ_CHECK(tst_convert(cd, "a\xea", "a"));
yaz_iconv_close(cd);
}
-static void dconvert(int mandatory, const char *tmpcode)
+static void tst_marc8s_to_utf8(void)
{
- int i;
- yaz_iconv_t cd;
- for (i = 0; iso_8859_1_a[i]; i++)
- {
- size_t r;
- char *inbuf = (char*) iso_8859_1_a[i];
- size_t inbytesleft = strlen(inbuf);
- char outbuf0[24];
- char outbuf1[10];
- char *outbuf = outbuf0;
- size_t outbytesleft = sizeof(outbuf0);
+ yaz_iconv_t cd = yaz_iconv_open("UTF-8", "MARC8s");
- cd = yaz_iconv_open(tmpcode, "ISO-8859-1");
- if (!cd)
- {
- if (!mandatory)
- return;
- printf ("tsticonv code=%s 1\n", tmpcode);
- exit(1);
- }
- r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
- if (r == (size_t)(-1))
- {
- int e = yaz_iconv_error(cd);
+ YAZ_CHECK(cd);
+ if (!cd)
+ return;
- printf ("tsticonv code=%s 2 e=%d\n", tmpcode, e);
- exit(2);
- }
- yaz_iconv_close(cd);
-
- cd = yaz_iconv_open("ISO-8859-1", tmpcode);
- if (!cd)
- {
- if (!mandatory)
- return;
- printf ("tsticonv code=%s 3\n", tmpcode);
- exit(3);
- }
- inbuf = outbuf0;
- inbytesleft = sizeof(outbuf0) - outbytesleft;
+ YAZ_CHECK(tst_convert(cd, "Cours de math",
+ "Cours de math"));
+ /* E9: LATIN SMALL LETTER E WITH ACUTE */
+ YAZ_CHECK(tst_convert(cd, "Cours de mathâe",
+ "Cours de math\xc3\xa9"));
- outbuf = outbuf1;
- outbytesleft = sizeof(outbuf1);
- r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
- if (r == (size_t)(-1)) {
- int e = yaz_iconv_error(cd);
+ yaz_iconv_close(cd);
+}
- printf ("tsticonv code=%s 4 e=%d\n", tmpcode, e);
- exit(4);
- }
- if (strlen(iso_8859_1_a[i]) ==
- (sizeof(outbuf1) - outbytesleft) &&
- memcmp(outbuf1, iso_8859_1_a[i],
- strlen(iso_8859_1_a[i])))
- {
- printf ("tsticonv code=%s 5\n", tmpcode);
- exit(5);
- }
- yaz_iconv_close(cd);
- }
+
+static void tst_marc8_to_latin1(void)
+{
+ yaz_iconv_t cd = yaz_iconv_open("ISO-8859-1", "MARC8");
+
+ YAZ_CHECK(cd);
+ if (!cd)
+ return;
+
+ YAZ_CHECK(tst_convert(cd, "ax", "ax"));
+
+ /* latin capital letter o with stroke */
+ YAZ_CHECK(tst_convert(cd, "\xa2", "\xd8"));
+
+ /* with latin small letter ae */
+ YAZ_CHECK(tst_convert(cd, "eneb\xb5r", "eneb\346r"));
+
+ YAZ_CHECK(tst_convert(cd, "\xea" "a\xa2", "\xe5" "\xd8"));
+
+ YAZ_CHECK(tst_convert(cd, "\xea" "a\xa2" "b", "\xe5" "\xd8" "b"));
+
+ YAZ_CHECK(tst_convert(cd, "\xea" "a" "\xea" "a", "\xe5" "\xe5"));
+
+ YAZ_CHECK(tst_convert(cd, "Cours de math",
+ "Cours de math"));
+ YAZ_CHECK(tst_convert(cd, "Cours de mathâe",
+ "Cours de mathé"));
+ YAZ_CHECK(tst_convert(cd, "12345678âe",
+ "12345678é"));
+ YAZ_CHECK(tst_convert(cd, "123456789âe",
+ "123456789é"));
+ YAZ_CHECK(tst_convert(cd, "1234567890âe",
+ "1234567890é"));
+ YAZ_CHECK(tst_convert(cd, "12345678901âe",
+ "12345678901é"));
+ YAZ_CHECK(tst_convert(cd, "Cours de mathâem",
+ "Cours de mathém"));
+ YAZ_CHECK(tst_convert(cd, "Cours de mathâematiques",
+ "Cours de mathématiques"));
+
+ yaz_iconv_close(cd);
}
-
+
+static void tst_utf8_to_marc8(void)
+{
+ yaz_iconv_t cd = yaz_iconv_open("MARC8", "UTF-8");
+
+ YAZ_CHECK(cd);
+ if (!cd)
+ return;
+
+ YAZ_CHECK(tst_convert(cd, "Cours ", "Cours "));
+
+ /** Pure ASCII. 11 characters (sizeof(outbuf)-1) */
+ YAZ_CHECK(tst_convert(cd, "Cours de mat", "Cours de mat"));
+
+ /** Pure ASCII. 12 characters (sizeof(outbuf)) */
+ YAZ_CHECK(tst_convert(cd, "Cours de math", "Cours de math"));
+
+ /** Pure ASCII. 13 characters (sizeof(outbuf)) */
+ YAZ_CHECK(tst_convert(cd, "Cours de math.", "Cours de math."));
+
+ /** UPPERCASE SCANDINAVIAN O */
+ YAZ_CHECK(tst_convert(cd, "S\xc3\x98", "S\xa2"));
+
+ /** ARING */
+ YAZ_CHECK(tst_convert(cd, "A" "\xCC\x8A", "\xEA" "A"));
+
+ /** A MACRON + UMLAUT, DIAERESIS */
+ YAZ_CHECK(tst_convert(cd, "A" "\xCC\x84" "\xCC\x88",
+ "\xE5\xE8\x41"));
+
+ /* Ligature spanning two characters */
+ YAZ_CHECK(tst_convert(cd,
+ "\x74" "\xCD\xA1" "\x73", /* UTF-8 */
+ "\xEB\x74\xEC\x73")); /* MARC-8 */
+
+ /* Double title spanning two characters */
+ YAZ_CHECK(tst_convert(cd,
+ "\x74" "\xCD\xA0" "\x73", /* UTF-8 */
+ "\xFA\x74\xFB\x73")); /* MARC-8 */
+
+ /** Ideographic question mark (Unicode FF1F) */
+ YAZ_CHECK(tst_convert(cd,
+ "\xEF\xBC\x9F" "o", /* UTF-8 */
+ "\033$1" "\x21\x2B\x3B" "\033(B" "o" ));
+
+
+ /** Superscript 0 . bug #642 */
+ YAZ_CHECK(tst_convert(cd,
+ "(\xe2\x81\xb0)", /* UTF-8 */
+ "(\033p0\x1bs)"));
+
+
+ yaz_iconv_close(cd);
+}
+
+
+static void tst_latin1_to_marc8(void)
+{
+ yaz_iconv_t cd = yaz_iconv_open("MARC8", "ISO-8859-1");
+
+ YAZ_CHECK(cd);
+ if (!cd)
+ return;
+
+ YAZ_CHECK(tst_convert(cd, "Cours ", "Cours "));
+
+ /** Pure ASCII. 11 characters (sizeof(outbuf)-1) */
+ YAZ_CHECK(tst_convert(cd, "Cours de mat", "Cours de mat"));
+
+ /** Pure ASCII. 12 characters (sizeof(outbuf)) */
+ YAZ_CHECK(tst_convert(cd, "Cours de math", "Cours de math"));
+
+ /** Pure ASCII. 13 characters (sizeof(outbuf)) */
+ YAZ_CHECK(tst_convert(cd, "Cours de math.", "Cours de math."));
+
+ /** D8: UPPERCASE SCANDINAVIAN O */
+ YAZ_CHECK(tst_convert(cd, "S\xd8", "S\xa2"));
+
+ /** E9: LATIN SMALL LETTER E WITH ACUTE */
+ YAZ_CHECK(tst_convert(cd, "Cours de math\xe9", "Cours de mathâe"));
+ YAZ_CHECK(tst_convert(cd, "Cours de math", "Cours de math"
+ ));
+ YAZ_CHECK(tst_convert(cd, "Cours de mathé", "Cours de mathâe" ));
+ YAZ_CHECK(tst_convert(cd, "12345678é","12345678âe"));
+ YAZ_CHECK(tst_convert(cd, "123456789é", "123456789âe"));
+ YAZ_CHECK(tst_convert(cd, "1234567890é","1234567890âe"));
+ YAZ_CHECK(tst_convert(cd, "12345678901é", "12345678901âe"));
+ YAZ_CHECK(tst_convert(cd, "Cours de mathém", "Cours de mathâem"));
+ YAZ_CHECK(tst_convert(cd, "Cours de mathématiques",
+ "Cours de mathâematiques"));
+ yaz_iconv_close(cd);
+}
+
+static void tst_utf8_codes(void)
+{
+ YAZ_CHECK(utf8_check(3));
+ YAZ_CHECK(utf8_check(127));
+ YAZ_CHECK(utf8_check(128));
+ YAZ_CHECK(utf8_check(255));
+ YAZ_CHECK(utf8_check(256));
+ YAZ_CHECK(utf8_check(900));
+ YAZ_CHECK(utf8_check(1000));
+ YAZ_CHECK(utf8_check(10000));
+ YAZ_CHECK(utf8_check(100000));
+ YAZ_CHECK(utf8_check(1000000));
+ YAZ_CHECK(utf8_check(10000000));
+ YAZ_CHECK(utf8_check(100000000));
+}
+
int main (int argc, char **argv)
{
+ YAZ_CHECK_INIT(argc, argv);
+
+ tst_utf8_codes();
+
+ tst_marc8_to_utf8();
+
+ tst_marc8s_to_utf8();
+
+ tst_marc8_to_latin1();
+
+ tst_utf8_to_marc8();
+
+ tst_latin1_to_marc8();
+
+ tst_marc8_to_ucs4b();
+ tst_ucs4b_to_utf8();
+
dconvert(1, "UTF-8");
dconvert(1, "ISO-8859-1");
dconvert(1, "UCS4");
dconvert(1, "UCS4LE");
dconvert(0, "CP865");
- marc8_tst_a();
- marc8_tst_b();
- marc8_tst_c();
- exit (0);
+
+ YAZ_CHECK_TERM;
}
+/*
+ * Local variables:
+ * c-basic-offset: 4
+ * indent-tabs-mode: nil
+ * End:
+ * vim: shiftwidth=4 tabstop=8 expandtab
+ */
projects / yaz-moved-to-github.git / blobdiff