X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=test%2Ftsticonv.c;h=33b99449a724f48e99eb2283396269ca56b54180;hb=0725af5d06bfcdaf9888886f04c63810c1d8cf72;hp=55cd9d176ea4dbeee65bfcbf674d6785b4f0c236;hpb=6e30ece4502a0c2c875be511d2ec051598292133;p=yaz-moved-to-github.git diff --git a/test/tsticonv.c b/test/tsticonv.c index 55cd9d1..33b9944 100644 --- a/test/tsticonv.c +++ b/test/tsticonv.c @@ -1,8 +1,8 @@ /* - * Copyright (C) 1995-2006, Index Data ApS + * Copyright (C) 1995-2007, Index Data ApS * See the file LICENSE for details. * - * $Id: tsticonv.c,v 1.19 2006-05-03 13:01:04 adam Exp $ + * $Id: tsticonv.c,v 1.29 2007-03-20 21:37:32 adam Exp $ */ #if HAVE_CONFIG_H @@ -76,8 +76,12 @@ static int tst_convert_l(yaz_iconv_t cd, size_t in_len, const char *in_buf, return 0; } else + { + yaz_iconv(cd, 0, 0, &outbuf, &outbytesleft); break; + } } + return compare_buffers("tsticonv 22", 0, expect_len, expect_buf, outbuf - outbuf0, outbuf0); @@ -90,26 +94,35 @@ static int tst_convert(yaz_iconv_t cd, const char *buf, const char *cmpbuf) char outbuf[12]; size_t inbytesleft = strlen(buf); const char *inp = buf; - while (inbytesleft) + 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)) { int e = yaz_iconv_error(cd); if (e != YAZ_ICONV_E2BIG) break; } - wrbuf_write(b, outbuf, outp - outbuf); + else + { + size_t outbytesleft = sizeof(outbuf); + char *outp = outbuf; + r = yaz_iconv(cd, 0, 0, &outp, &outbytesleft); + wrbuf_write(b, outbuf, outp - outbuf); + 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); + wrbuf_destroy(b); return ret; } @@ -124,7 +137,7 @@ static const char *iso_8859_1_a[] = { "\xe5" "\xe5", 0 }; -static void tst_marc8_to_ucs4b() +static void tst_marc8_to_ucs4b(void) { yaz_iconv_t cd = yaz_iconv_open("UCS4", "MARC8"); YAZ_CHECK(cd); @@ -222,7 +235,7 @@ static void tst_marc8_to_ucs4b() yaz_iconv_close(cd); } -static void tst_ucs4b_to_utf8() +static void tst_ucs4b_to_utf8(void) { yaz_iconv_t cd = yaz_iconv_open("UTF8", "UCS4"); YAZ_CHECK(cd); @@ -265,6 +278,9 @@ static void dconvert(int mandatory, const char *tmpcode) return; r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft); YAZ_CHECK(r != (size_t) (-1)); + + r = yaz_iconv(cd, 0, 0, &outbuf, &outbytesleft); + YAZ_CHECK(r != (size_t) (-1)); yaz_iconv_close(cd); if (r == (size_t) (-1)) return; @@ -280,11 +296,19 @@ static void dconvert(int mandatory, const char *tmpcode) outbytesleft = sizeof(outbuf1); r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft); YAZ_CHECK(r != (size_t) (-1)); + + r = yaz_iconv(cd, 0, 0, &outbuf, &outbytesleft); + if (r == (size_t)(-1)) + { + fprintf(stderr, "failed\n"); + } + YAZ_CHECK(r != (size_t) (-1)); + if (r != (size_t)(-1)) { ret = compare_buffers("dconvert", i, strlen(iso_8859_1_a[i]), iso_8859_1_a[i], - sizeof(outbuf1) - outbytesleft, outbuf1); + sizeof(outbuf1) - outbytesleft, outbuf1); YAZ_CHECK(ret); } yaz_iconv_close(cd); @@ -337,7 +361,7 @@ int utf8_check(unsigned c) return 1; } -static void tst_marc8_to_utf8() +static void tst_marc8_to_utf8(void) { yaz_iconv_t cd = yaz_iconv_open("UTF-8", "MARC8"); @@ -350,10 +374,15 @@ static void tst_marc8_to_utf8() /* 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 tst_marc8s_to_utf8() +static void tst_marc8s_to_utf8(void) { yaz_iconv_t cd = yaz_iconv_open("UTF-8", "MARC8s"); @@ -371,7 +400,7 @@ static void tst_marc8s_to_utf8() } -static void tst_marc8_to_latin1() +static void tst_marc8_to_latin1(void) { yaz_iconv_t cd = yaz_iconv_open("ISO-8859-1", "MARC8"); @@ -413,7 +442,7 @@ static void tst_marc8_to_latin1() yaz_iconv_close(cd); } -static void tst_utf8_to_marc8() +static void tst_utf8_to_marc8(void) { yaz_iconv_t cd = yaz_iconv_open("MARC8", "UTF-8"); @@ -455,13 +484,78 @@ static void tst_utf8_to_marc8() /** Ideographic question mark (Unicode FF1F) */ YAZ_CHECK(tst_convert(cd, "\xEF\xBC\x9F" "o", /* UTF-8 */ - "\033(1" "\x21\x2B\x3B" "\033(B" "o" )); + "\033$1" "\x21\x2B\x3B" "\033(B" "o" )); + + + /** Superscript 0 . bug #642 */ + YAZ_CHECK(tst_convert(cd, + "(\xe2\x81\xb0)", /* UTF-8 */ + "(\033p0\x1bs)")); + + + { + char *inbuf0 = "\xe2\x81\xb0"; + char *inbuf = inbuf0; + size_t inbytesleft = strlen(inbuf); + char outbuf0[64]; + char *outbuf = outbuf0; + size_t outbytesleft = sizeof(outbuf0)-1; + size_t r; +#if 0 + int i; +#endif + r = yaz_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft); + YAZ_CHECK(r != (size_t) (-1)); +#if 0 + *outbuf = '\0'; /* so we know when to stop printing */ + for (i = 0; outbuf0[i]; i++) + { + int ch = outbuf0[i] & 0xff; + yaz_log(YLOG_LOG, "ch%d %02X %c", i, ch, ch >= ' ' ? ch : '?'); + } +#endif + + r = yaz_iconv(cd, 0, 0, &outbuf, &outbytesleft); + YAZ_CHECK(r != (size_t) (-1)); + *outbuf = '\0'; /* for strcmp test below and printing */ +#if 0 + for (i = 0; outbuf0[i]; i++) + { + int ch = outbuf0[i] & 0xff; + yaz_log(YLOG_LOG, "ch%d %02X %c", i, ch, ch >= ' ' ? ch : '?'); + } +#endif + YAZ_CHECK(strcmp("\033p0\x1bs", outbuf0) == 0); + } yaz_iconv_close(cd); } +static void tst_advance_to_utf8(void) +{ + yaz_iconv_t cd = yaz_iconv_open("utf-8", "advancegreek"); + + YAZ_CHECK(cd); + if (!cd) + return; -static void tst_latin1_to_marc8() + YAZ_CHECK(tst_convert(cd, "Cours ", "Cours ")); + yaz_iconv_close(cd); +} + +static void tst_utf8_to_advance(void) +{ + yaz_iconv_t cd = yaz_iconv_open("advancegreek", "utf-8"); + + YAZ_CHECK(cd); + if (!cd) + return; + + YAZ_CHECK(tst_convert(cd, "Cours ", "Cours ")); + yaz_iconv_close(cd); +} + +static void tst_latin1_to_marc8(void) { yaz_iconv_t cd = yaz_iconv_open("MARC8", "ISO-8859-1"); @@ -483,17 +577,22 @@ static void tst_latin1_to_marc8() /** D8: UPPERCASE SCANDINAVIAN O */ YAZ_CHECK(tst_convert(cd, "S\xd8", "S\xa2")); -#if 0 - /* does not pass yet */ /** E9: LATIN SMALL LETTER E WITH ACUTE */ - YAZ_CHECK(tst_convert(cd, - "Cours de math\xe9", - "Cours de mathâe")); -#endif + 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() +static void tst_utf8_codes(void) { YAZ_CHECK(utf8_check(3)); YAZ_CHECK(utf8_check(127)); @@ -521,6 +620,9 @@ int main (int argc, char **argv) tst_marc8_to_latin1(); + tst_advance_to_utf8(); + tst_utf8_to_advance(); + tst_utf8_to_marc8(); tst_latin1_to_marc8();