Fixed bug #2120: Different greek symbols, UTF-8 to MARC-8.
[yaz-moved-to-github.git] / test / tsticonv.c
index 33b9944..14129db 100644 (file)
@@ -2,7 +2,7 @@
  * Copyright (C) 1995-2007, Index Data ApS
  * See the file LICENSE for details.
  *
- * $Id: tsticonv.c,v 1.29 2007-03-20 21:37:32 adam Exp $
+ * $Id: tsticonv.c,v 1.35 2008-03-12 08:53:28 adam Exp $
  */
 
 #if HAVE_CONFIG_H
@@ -17,6 +17,8 @@
 #include <yaz/yaz-util.h>
 #include <yaz/test.h>
 
+#define ESC "\x1b"
+
 static int compare_buffers(char *msg, int no,
                            int expect_len, const char *expect_buf,
                            int got_len, const char *got_buf)
@@ -121,7 +123,24 @@ static int tst_convert(yaz_iconv_t cd, const char *buf, const char *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 w = wrbuf_alloc();
+
+        wrbuf_rewind(w);
+        wrbuf_puts_escaped(w, buf);
+        yaz_log(YLOG_LOG, "input %s", wrbuf_cstr(w));
+
+        wrbuf_rewind(w);
+        wrbuf_write_escaped(w, wrbuf_buf(b), wrbuf_len(b));
+        yaz_log(YLOG_LOG, "got %s", wrbuf_cstr(w));
+        
+        wrbuf_rewind(w);
+        wrbuf_puts_escaped(w, cmpbuf);
+        yaz_log(YLOG_LOG, "exp %s", wrbuf_cstr(w));
+
+        wrbuf_destroy(w);
+    }
+
     wrbuf_destroy(b);
     return ret;
 }
@@ -369,16 +388,20 @@ static void tst_marc8_to_utf8(void)
     if (!cd)
         return;
 
+    /* bug #2115 */
+    YAZ_CHECK(tst_convert(cd, ESC "(N" ESC ")Qp" ESC "(B", "\xd0\x9f"));
+
+
     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);
 }
 
@@ -458,7 +481,7 @@ static void tst_utf8_to_marc8(void)
     /** Pure ASCII. 12 characters (sizeof(outbuf)) */
     YAZ_CHECK(tst_convert(cd, "Cours de math", "Cours de math"));
 
-    /** Pure ASCII. 13 characters (sizeof(outbuf)) */
+    /** Pure ASCII. 13 characters (sizeof(outbuf)+1) */
     YAZ_CHECK(tst_convert(cd, "Cours de math.", "Cours de math."));
 
     /** UPPERCASE SCANDINAVIAN O */
@@ -487,11 +510,38 @@ static void tst_utf8_to_marc8(void)
                           "\033$1" "\x21\x2B\x3B" "\033(B" "o" ));
 
 
+    /** Ideographic space per ANSI Z39.64 */
+    YAZ_CHECK(tst_convert(cd,
+                          "\xe3\x80\x80" "o",        /* UTF-8 */
+                          "\033$1" "\x21\x23\x21" "\033(B" "o" ));
+
     /** Superscript 0 . bug #642 */
     YAZ_CHECK(tst_convert(cd,
                           "(\xe2\x81\xb0)",        /* UTF-8 */
                           "(\033p0\x1bs)"));
     
+    
+    /** bug #1778 */
+    YAZ_CHECK(tst_convert(cd,
+                          /* offset 0x530 in UTF-8 rec marccol4.u8.marc */
+                          "\xE3\x83\xB3" "\xE3\x82\xBF" 
+                          "\xCC\x84" "\xCC\x84" "\xE3\x83\xBC" /* UTF-8 */,
+                          "\x1B\x24\x31" "\x69\x25\x73"
+                          "\x1B\x28\x42" "\xE5\xE5" "\x1B\x24\x31" 
+                          "\x69\x25\x3F"
+                          "\x69\x21\x3C" "\x1B\x28\x42"));
+
+    
+    /** bug #2120 */
+    YAZ_CHECK(tst_convert(cd, 
+                          "\xCE\x94\xCE\xB5\xCF\x84"
+                          "\xCE\xBF\xCF\x81\xCE\xB1"
+                          "\xCE\xBA\xCE\xB7\xCF\x82\x2C",
+
+                          "\x1B\x28\x53\x45\x66\x78\x72\x75"
+                          "\x61\x6D\x6A\x77"
+                          "\x1B\x28\x42\x2C"
+                  ));
  
     {
         char *inbuf0 = "\xe2\x81\xb0";