Release 2.1.1.

[nkf/nkf.git] / nkf.c

diff --git a/nkf.c b/nkf.c
index a8bfc9a..6877afe 100644 (file)
--- a/nkf.c
+++ b/nkf.c
@@ -21,7 +21,7 @@
  * 3. This notice may not be removed or altered from any source distribution.
  */
 #define NKF_VERSION "2.1.1"
-#define NKF_RELEASE_DATE "2010-04-14"
+#define NKF_RELEASE_DATE "2010-08-08"
 #define COPY_RIGHT \
     "Copyright (C) 1987, FUJITSU LTD. (I.Ichikawa).\n" \
     "Copyright (C) 1996-2010, The nkf Project."
@@ -223,6 +223,7 @@ struct {
     {"ISO-2022-JP-2004",       ISO_2022_JP_2004},
     {"SHIFT_JIS",              SHIFT_JIS},
     {"SJIS",                   SHIFT_JIS},
+    {"MS_Kanji",               SHIFT_JIS},
     {"PCK",                    SHIFT_JIS},
     {"WINDOWS-31J",            WINDOWS_31J},
     {"CSWINDOWS31J",           WINDOWS_31J},
@@ -476,7 +477,7 @@ struct input_code input_code_list[] = {
     {"UTF-16",     0, 0, 0, {0, 0, 0}, NULL, w_iconv16, 0},
     {"UTF-32",     0, 0, 0, {0, 0, 0}, NULL, w_iconv32, 0},
 #endif
-    {0}
+    {NULL,        0, 0, 0, {0, 0, 0}, NULL, NULL, 0}
 };
 
 static int              mimeout_mode = 0; /* 0, -1, 'Q', 'B', 1, 2 */
@@ -901,7 +902,7 @@ usage(void)
            " Z[0-4]   Default/0: Convert JISX0208 Alphabet to ASCII\n"
            "          1: Kankaku to one space  2: to two spaces  3: HTML Entity\n"
            "          4: JISX0208 Katakana to JISX0201 Katakana\n"
-           " X,x      Assume X0201 kana in MS-Kanji, -x preserves X0201\n"
+           " X,x      Convert Halfwidth Katakana to Fullwidth or preserve it\n"
            );
     fprintf(HELP_OUTPUT,
            " O        Output to File (DEFAULT 'nkf.out')\n"
@@ -1208,10 +1209,10 @@ set_input_encoding(nkf_encoding *enc)
     case ISO_8859_1:
        iso8859_f = TRUE;
        break;
-    case CP50220:
     case CP50221:
     case CP50222:
        if (x0201_f == NKF_UNSPECIFIED) x0201_f = FALSE;        /* -x specified implicitly */
+    case CP50220:
 #ifdef SHIFTJIS_CP932
        cp51932_f = TRUE;
 #endif
@@ -1264,6 +1265,7 @@ set_input_encoding(nkf_encoding *enc)
 #endif
        break;
     case EUCJP_MS:
+       if (x0201_f == NKF_UNSPECIFIED) x0201_f = FALSE;        /* -x specified implicitly */
 #ifdef SHIFTJIS_CP932
        cp51932_f = FALSE;
 #endif
@@ -1272,6 +1274,7 @@ set_input_encoding(nkf_encoding *enc)
 #endif
        break;
     case EUCJP_ASCII:
+       if (x0201_f == NKF_UNSPECIFIED) x0201_f = FALSE;        /* -x specified implicitly */
 #ifdef SHIFTJIS_CP932
        cp51932_f = FALSE;
 #endif
@@ -1326,7 +1329,6 @@ set_output_encoding(nkf_encoding *enc)
 {
     switch (nkf_enc_to_index(enc)) {
     case CP50220:
-       if (x0201_f == NKF_UNSPECIFIED) x0201_f = FALSE;        /* -x specified implicitly */
 #ifdef SHIFTJIS_CP932
        if (cp932inv_f == TRUE) cp932inv_f = FALSE;
 #endif
@@ -1402,12 +1404,14 @@ set_output_encoding(nkf_encoding *enc)
 #endif
        break;
     case EUCJP_MS:
+       if (x0201_f == NKF_UNSPECIFIED) x0201_f = FALSE;        /* -x specified implicitly */
        x0212_f = TRUE;
 #ifdef UTF8_OUTPUT_ENABLE
        ms_ucs_map_f = UCS_MAP_MS;
 #endif
        break;
     case EUCJP_ASCII:
+       if (x0201_f == NKF_UNSPECIFIED) x0201_f = FALSE;        /* -x specified implicitly */
        x0212_f = TRUE;
 #ifdef UTF8_OUTPUT_ENABLE
        ms_ucs_map_f = UCS_MAP_ASCII;
@@ -2198,8 +2202,8 @@ unicode_iconv(nkf_char wc)
     return 0;
 }
 
-#define NKF_ICONV_NEED_ONE_MORE_BYTE -1
-#define NKF_ICONV_NEED_TWO_MORE_BYTES -2
+#define NKF_ICONV_NEED_ONE_MORE_BYTE (size_t)-1
+#define NKF_ICONV_NEED_TWO_MORE_BYTES (size_t)-2
 #define UTF16_TO_UTF32(lead, trail) (((lead) << 10) + (trail) - NKF_INT32_C(0x35FDC00))
 static size_t
 nkf_iconv_utf_16(nkf_char c1, nkf_char c2, nkf_char c3, nkf_char c4)
@@ -4631,7 +4635,7 @@ static const char basis_64[] =
 
 #define MIMEOUT_BUF_LENGTH 74
 static struct {
-    char buf[MIMEOUT_BUF_LENGTH+1];
+    unsigned char buf[MIMEOUT_BUF_LENGTH+1];
     int count;
 } mimeout_state;
 
@@ -4943,7 +4947,7 @@ mime_putc(nkf_char c)
                    i = 0;
 
                    for (; i < mimeout_state.count - len; ++i) {
-                       if (!strncmp(mimeout_state.buf+i, str, len)) {
+                       if (!strncmp((char *)(mimeout_state.buf+i), str, len)) {
                            i += len - 2;
                            break;
                        }
@@ -5414,7 +5418,7 @@ noconvert(FILE *f)
 #define NEXT continue        /* no output, get next */
 #define SKIP c2=0;continue        /* no output, get next */
 #define MORE c2=c1;continue  /* need one more byte */
-#define SEND ;               /* output c1 and c2, get next */
+#define SEND (void)0         /* output c1 and c2, get next */
 #define LAST break           /* end of loop, go closing  */
 #define set_input_mode(mode) do { \
     input_mode = mode; \
@@ -5459,7 +5463,7 @@ kanji_convert(FILE *f)
     else if (iconv == w_iconv16) {
        while ((c1 = (*i_getc)(f)) != EOF &&
               (c2 = (*i_getc)(f)) != EOF) {
-           if (nkf_iconv_utf_16(c1, c2, 0, 0) == -2 &&
+           if (nkf_iconv_utf_16(c1, c2, 0, 0) == NKF_ICONV_NEED_TWO_MORE_BYTES &&
                (c3 = (*i_getc)(f)) != EOF &&
                (c4 = (*i_getc)(f)) != EOF) {
                nkf_iconv_utf_16(c1, c2, c3, c4);
@@ -5899,7 +5903,7 @@ options(unsigned char *cp)
                option_mode = 1;
                return 0;
            }
-           for (i=0;i<sizeof(long_option)/sizeof(long_option[0]);i++) {
+           for (i=0;i<(int)(sizeof(long_option)/sizeof(long_option[0]));i++) {
                p = (unsigned char *)long_option[i].name;
                for (j=0;*p && *p != '=' && *p == cp[j];p++, j++);
                if (*p == cp[j] || cp[j] == SP){