OSDN Git Service

NKF.xs must follow nkf.c doesn't have WISH_TRUE AND NO_X0201.
[nkf/nkf.git] / nkf.c
diff --git a/nkf.c b/nkf.c
index 0743e5d..da1c766 100644 (file)
--- a/nkf.c
+++ b/nkf.c
@@ -20,8 +20,8 @@
  *
  * 3. This notice may not be removed or altered from any source distribution.
  */
-#define NKF_VERSION "2.0.8"
-#define NKF_RELEASE_DATE "2009-01-19"
+#define NKF_VERSION "2.0.9"
+#define NKF_RELEASE_DATE "2009-01-20"
 #define COPY_RIGHT \
     "Copyright (C) 1987, FUJITSU LTD. (I.Ichikawa).\n" \
     "Copyright (C) 1996-2009, The nkf Project."
@@ -501,7 +501,7 @@ static nkf_char
 no_connection2(nkf_char c2, nkf_char c1, nkf_char c0)
 {
     fprintf(stderr,"nkf internal module connection failure.\n");
-    exit(1);
+    exit(EXIT_FAILURE);
     return 0; /* LINT */
 }
 
@@ -802,7 +802,7 @@ nkf_default_encoding()
 typedef struct {
     long capa;
     long len;
-    unsigned char *ptr;
+    nkf_char *ptr;
 } nkf_buf_t;
 
 static nkf_buf_t *
@@ -841,7 +841,7 @@ nkf_buf_clear(nkf_buf_t *buf)
 }
 
 static void
-nkf_buf_push(nkf_buf_t *buf, unsigned char c)
+nkf_buf_push(nkf_buf_t *buf, nkf_char c)
 {
     if (buf->capa <= buf->len) {
        exit(EXIT_FAILURE);
@@ -872,79 +872,61 @@ static void
 usage(void)
 {
     fprintf(HELP_OUTPUT,
-           "USAGE:  nkf(nkf32,wnkf,nkf2) -[flags] [in file] .. [out file for -O flag]\n"
-           "Flags:\n"
-           "b,u      Output is buffered (DEFAULT),Output is unbuffered\n"
-           "j,s,e,w  Output code is ISO-2022-JP, Shift JIS, EUC-JP, UTF-8N\n"
+           "Usage:  nkf -[flags] [--] [in file] .. [out file for -O flag]\n"
 #ifdef UTF8_OUTPUT_ENABLE
-           "         After 'w' you can add more options. -w[ 8 [0], 16 [[BL] [0]] ]\n"
+           " j/s/e/w  Specify output encoding ISO-2022-JP, Shift_JIS, EUC-JP\n"
+           "          UTF options is -w[8[0],{16,32}[{B,L}[0]]]\n"
+#else
 #endif
-           "J,S,E,W  Input assumption is JIS 7 bit , Shift JIS, EUC-JP, UTF-8\n"
 #ifdef UTF8_INPUT_ENABLE
-           "         After 'W' you can add more options. -W[ 8, 16 [BL] ] \n"
+           " J/S/E/W  Specify input encoding ISO-2022-JP, Shift_JIS, EUC-JP\n"
+           "          UTF option is -W[8,[16,32][B,L]]\n"
+#else
+           " J/S/E    Specify output encoding ISO-2022-JP, Shift_JIS, EUC-JP\n"
 #endif
-           "t        no conversion\n"
            );
     fprintf(HELP_OUTPUT,
-           "i[@B]    Specify the Esc Seq for JIS X 0208-1978/83 (DEFAULT B)\n"
-           "o[BJH]   Specify the Esc Seq for ASCII/Roman        (DEFAULT B)\n"
-           "r        {de/en}crypt ROT13/47\n"
-           "h        1 katakana->hiragana, 2 hiragana->katakana, 3 both\n"
-           "m[BQSN0] MIME decode [B:base64,Q:quoted,S:strict,N:non-strict,0:no decode]\n"
-           "M[BQ]    MIME encode [B:base64 Q:quoted]\n"
-           "l        ISO8859-1 (Latin-1) support\n"
-           "f/F      Folding: -f60 or -f or -f60-10 (fold margin 10) F preserve nl\n"
+           " m[BQSN0] MIME decode [B:base64,Q:quoted,S:strict,N:nonstrict,0:no decode]\n"
+           " M[BQ]    MIME encode [B:base64 Q:quoted]\n"
+           " f/F      Folding: -f60 or -f or -f60-10 (fold margin 10) F preserve nl\n"
            );
     fprintf(HELP_OUTPUT,
-           "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"
-           "B[0-2]   Broken input  0: missing ESC,1: any X on ESC-[($]-X,2: ASCII on NL\n"
+           " 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"
            );
     fprintf(HELP_OUTPUT,
-#ifdef MSDOS
-           "T        Text mode output\n"
-#endif
-           "O        Output to File (DEFAULT 'nkf.out')\n"
-           "I        Convert non ISO-2022-JP charactor to GETA\n"
-           "d,c      Convert line breaks  -d: LF  -c: CRLF\n"
-           "-L[uwm]  line mode u:LF w:CRLF m:CR (DEFAULT noconversion)\n"
-           "v, V     Show this usage. V: show configuration\n"
-           "\n");
+           " O        Output to File (DEFAULT 'nkf.out')\n"
+           " L[uwm]   Line mode u:LF w:CRLF m:CR (DEFAULT noconversion)\n"
+           );
     fprintf(HELP_OUTPUT,
-           "Long name options\n"
-           " --ic=<input codeset>  --oc=<output codeset>\n"
-           "                   Specify the input or output codeset\n"
-           " --fj  --unix --mac  --windows\n"
-           " --jis  --euc  --sjis  --utf8  --utf16  --mime  --base64\n"
-           "                   Convert for the system or code\n"
-           " --hiragana  --katakana  --katakana-hiragana\n"
-           "                   To Hiragana/Katakana Conversion\n"
-           " --prefix=         Insert escape before troublesome characters of Shift_JIS\n"
+           " --ic=<encoding>        Specify the input encoding\n"
+           " --oc=<encoding>        Specify the output encoding\n"
+           " --hiragana --katakana  Hiragana/Katakana Conversion\n"
+           " --katakana-hiragana    Converts each other\n"
            );
     fprintf(HELP_OUTPUT,
 #ifdef INPUT_OPTION
-           " --cap-input, --url-input  Convert hex after ':' or '%%'\n"
+           " --{cap, url}-input     Convert hex after ':' or '%%'\n"
 #endif
 #ifdef NUMCHAR_OPTION
-           " --numchar-input   Convert Unicode Character Reference\n"
+           " --numchar-input        Convert Unicode Character Reference\n"
 #endif
 #ifdef UTF8_INPUT_ENABLE
            " --fb-{skip, html, xml, perl, java, subchar}\n"
-           "                   Specify how nkf handles unassigned characters\n"
+           "                        Specify unassigned character's replacement\n"
 #endif
            );
     fprintf(HELP_OUTPUT,
 #ifdef OVERWRITE
-           " --in-place[=SUFFIX]  --overwrite[=SUFFIX]\n"
-           "                   Overwrite original listed files by filtered result\n"
-           "                   --overwrite preserves timestamp of original files\n"
+           " --in-place[=SUF]       Overwrite original files\n"
+           " --overwrite[=SUF]      Preserve timestamp of original files\n"
 #endif
-           " -g  --guess       Guess the input code\n"
-           " --help  --version Show this help/the version\n"
-           "                   For more information, see also man nkf\n"
-           "\n");
+           " -g --guess             Guess the input code\n"
+           " -v --version           Print the version\n"
+           " --help/-V              Print this help / configuration\n"
+           );
     version();
 }
 
@@ -1142,7 +1124,7 @@ static const struct {
     {"euc","e"},
     {"euc-input","E"},
     {"fj","jm"},
-    {"help","v"},
+    {"help",""},
     {"jis","j"},
     {"jis-input","J"},
     {"mac","sLm"},
@@ -1152,7 +1134,7 @@ static const struct {
     {"sjis","s"},
     {"sjis-input","S"},
     {"unix","eLu"},
-    {"version","V"},
+    {"version","v"},
     {"windows","sLw"},
     {"hiragana","h1"},
     {"katakana","h2"},
@@ -4283,7 +4265,7 @@ nfc_getc(FILE *f)
 
     if (c == EOF || c > 0xFF || (c & 0xc0) == 0x80) return c;
 
-    nkf_buf_push(buf, (unsigned char)c);
+    nkf_buf_push(buf, c);
     do {
        while (lower <= upper) {
            int mid = (lower+upper) / 2;
@@ -5862,6 +5844,12 @@ options(unsigned char *cp)
                cp_back = cp;
                cp = (unsigned char *)long_option[i].alias;
            }else{
+#ifndef PERL_XS
+               if (strcmp(long_option[i].name, "help") == 0){
+                   usage();
+                   exit(EXIT_SUCCESS);
+               }
+#endif
                if (strcmp(long_option[i].name, "ic=") == 0){
                    enc = nkf_enc_find((char *)p);
                    if (!enc) continue;
@@ -6110,7 +6098,8 @@ options(unsigned char *cp)
            if (*cp=='@'||*cp=='B')
                kanji_intro = *cp++;
            continue;
-       case 'o':           /* ASCII IN ESC-(-J/B */
+       case 'o':           /* ASCII IN ESC-(-J/B/H */
+           /* ESC ( H was used in initial JUNET messages */
            if (*cp=='J'||*cp=='B'||*cp=='H')
                ascii_intro = *cp++;
            continue;
@@ -6135,11 +6124,11 @@ options(unsigned char *cp)
 #ifndef PERL_XS
        case 'V':
            show_configuration();
-           exit(1);
+           exit(EXIT_SUCCESS);
            break;
        case 'v':
-           usage();
-           exit(1);
+           version();
+           exit(EXIT_SUCCESS);
            break;
 #endif
 #ifdef UTF8_OUTPUT_ENABLE