* Copyright (c) 1987, Fujitsu LTD. (Itaru ICHIKAWA).
* Copyright (c) 1996-2009, The nkf Project.
*
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * This software is provided 'as-is', without any express or implied
+ * warranty. In no event will the authors be held liable for any damages
+ * arising from the use of this software.
+ *
+ * Permission is granted to anyone to use this software for any purpose,
+ * including commercial applications, and to alter it and redistribute it
+ * freely, subject to the following restrictions:
+ *
+ * 1. The origin of this software must not be misrepresented; you must not
+ * claim that you wrote the original software. If you use this software
+ * in a product, an acknowledgment in the product documentation would be
+ * appreciated but is not required.
+ *
+ * 2. Altered source versions must be plainly marked as such, and must not be
+ * misrepresented as being the original software.
+ *
+ * 3. This notice may not be removed or altered from any source distribution.
*/
-#define NKF_VERSION "2.0.8"
-#define NKF_RELEASE_DATE "2009-01-05"
+#define NKF_VERSION "2.1.0"
+#define NKF_RELEASE_DATE "2009-11-17"
#define COPY_RIGHT \
"Copyright (C) 1987, FUJITSU LTD. (I.Ichikawa).\n" \
"Copyright (C) 1996-2009, The nkf Project."
&& (c != '(') && (c != ')') && (c != '.') && (c != 0x22)))
#define is_ibmext_in_sjis(c2) (CP932_TABLE_BEGIN <= c2 && c2 <= CP932_TABLE_END)
-#define nkf_byte_jisx0201_katakana_p(c) (SP <= c && c < (0xE0&0x7F))
+#define nkf_byte_jisx0201_katakana_p(c) (SP <= c && c <= 0x5F)
#define HOLD_SIZE 1024
#if defined(INT_IS_SHORT)
{"Shift_JIS", 0, 0, 0, {0, 0, 0}, s_status, s_iconv, 0},
#ifdef UTF8_INPUT_ENABLE
{"UTF-8", 0, 0, 0, {0, 0, 0}, w_status, w_iconv, 0},
+ {"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}
};
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 */
}
typedef struct {
long capa;
long len;
- unsigned char *ptr;
+ nkf_char *ptr;
} nkf_buf_t;
static nkf_buf_t *
return buf;
}
+#if 0
static void
nkf_buf_dispose(nkf_buf_t *buf)
{
nkf_xfree(buf->ptr);
nkf_xfree(buf);
}
+#endif
#define nkf_buf_length(buf) ((buf)->len)
#define nkf_buf_empty_p(buf) ((buf)->len == 0)
}
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);
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();
}
{"euc","e"},
{"euc-input","E"},
{"fj","jm"},
- {"help","v"},
+ {"help",""},
{"jis","j"},
{"jis-input","J"},
{"mac","sLm"},
{"sjis","s"},
{"sjis-input","S"},
{"unix","eLu"},
- {"version","V"},
+ {"version","v"},
{"windows","sLw"},
{"hiragana","h1"},
{"katakana","h2"},
case CP50220:
case CP50221:
case CP50222:
+ x0201_f = TRUE;
#ifdef SHIFTJIS_CP932
cp51932_f = TRUE;
#endif
case SHIFT_JIS:
break;
case WINDOWS_31J:
+ x0201_f = TRUE;
#ifdef SHIFTJIS_CP932
cp51932_f = TRUE;
#endif
case EUCJP_NKF:
break;
case CP51932:
+ x0201_f = TRUE;
#ifdef SHIFTJIS_CP932
cp51932_f = TRUE;
#endif
#endif
break;
case CP50221:
+ x0201_f = TRUE;
#ifdef SHIFTJIS_CP932
if (cp932inv_f == TRUE) cp932inv_f = FALSE;
#endif
ms_ucs_map_f = UCS_MAP_CP932;
#endif
break;
+ case ISO_2022_JP:
+#ifdef SHIFTJIS_CP932
+ if (cp932inv_f == TRUE) cp932inv_f = FALSE;
+#endif
+ break;
case ISO_2022_JP_1:
x0212_f = TRUE;
#ifdef SHIFTJIS_CP932
case SHIFT_JIS:
break;
case WINDOWS_31J:
+ x0201_f = TRUE;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_CP932;
#endif
#endif
break;
case CP51932:
+ x0201_f = TRUE;
#ifdef SHIFTJIS_CP932
if (cp932inv_f == TRUE) cp932inv_f = FALSE;
#endif
output_endian = ENDIAN_LITTLE;
output_bom_f = TRUE;
break;
+ case UTF_32:
case UTF_32BE_BOM:
output_bom_f = TRUE;
break;
*p3 = 0x80 | ( val & 0x3f);
*p4 = 0;
} else if (nkf_char_unicode_value_p(val)) {
- *p1 = 0xe0 | (val >> 16);
+ *p1 = 0xf0 | (val >> 18);
*p2 = 0x80 | ((val >> 12) & 0x3f);
*p3 = 0x80 | ((val >> 6) & 0x3f);
*p4 = 0x80 | ( val & 0x3f);
nkf_char broken_state;
nkf_buf_t *broken_buf;
nkf_char mimeout_state;
+ nkf_buf_t *nfc_buf;
} nkf_state_t;
static nkf_state_t *nkf_state = NULL;
if (nkf_state) {
nkf_buf_clear(nkf_state->std_gc_buf);
nkf_buf_clear(nkf_state->broken_buf);
+ nkf_buf_clear(nkf_state->nfc_buf);
}
else {
nkf_state = nkf_xmalloc(sizeof(nkf_state_t));
nkf_state->std_gc_buf = nkf_buf_new(STD_GC_BUFSIZE);
nkf_state->broken_buf = nkf_buf_new(3);
+ nkf_state->nfc_buf = nkf_buf_new(9);
}
nkf_state->broken_state = 0;
nkf_state->mimeout_state = 0;
} else if ((c3 = (*i_getc)(f)) == EOF) {
ret = EOF;
break;
- } else {
- code_status(c3);
- if (hold_index < hold_count){
- c4 = hold_buf[hold_index++];
- } else if ((c4 = (*i_getc)(f)) == EOF) {
- c3 = ret = EOF;
- break;
- } else {
- code_status(c4);
- (*iconv)(c1, c2, (c3<<8)|c4);
- }
}
+ code_status(c3);
+ if (hold_index < hold_count){
+ c4 = hold_buf[hold_index++];
+ } else if ((c4 = (*i_getc)(f)) == EOF) {
+ c3 = ret = EOF;
+ break;
+ }
+ code_status(c4);
+ (*iconv)(c1, c2, (c3<<8)|c4);
break;
case -1:
/* 3 bytes EUC or UTF-8 */
f_prev = LF;
f_line = 0;
fold_state = LF; /* output newline and clear */
- } else if ( (c2==0 && c1==SP)||
- (c2==0 && c1==TAB)||
- (c2=='!'&& c1=='!')) {
+ } else if ((c2==0 && nkf_isblank(c1)) || (c2 == '!' && c1 == '!')) {
/* X0208 kankaku or ascii space */
if (f_prev == SP) {
fold_state = 0; /* remove duplicate spaces */
{
nkf_char (*g)(FILE *f) = i_nfc_getc;
nkf_char (*u)(nkf_char c ,FILE *f) = i_nfc_ungetc;
- nkf_buf_t *buf = nkf_buf_new(9);
+ nkf_buf_t *buf = nkf_state->nfc_buf;
const unsigned char *array;
int lower=0, upper=NORMALIZATION_TABLE_LENGTH-1;
nkf_char c = (*g)(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;
while (nkf_buf_length(buf) > 1) (*u)(nkf_buf_pop(buf), f);
c = nkf_buf_pop(buf);
- nkf_buf_dispose(buf);
return c;
}
case LF:
case CR:
if (c1==LF) {
- if ((c1=(*i_getc)(f))!=EOF && (c1==SP||c1==TAB)) {
+ if ((c1=(*i_getc)(f))!=EOF && nkf_isblank(c1)) {
i_ungetc(SP,f);
continue;
} else {
c1 = LF;
} else {
if ((c1=(*i_getc)(f))!=EOF && c1 == LF) {
- if ((c1=(*i_getc)(f))!=EOF && (c1==SP||c1==TAB)) {
+ if ((c1=(*i_getc)(f))!=EOF && nkf_isblank(c1)) {
i_ungetc(SP,f);
continue;
} else {
}
if (c1=='='&&c2<SP) { /* this is soft wrap */
while((c1 = (*i_mgetc)(f)) <=SP) {
- if ((c1 = (*i_mgetc)(f)) == EOF) return (EOF);
+ if (c1 == EOF) return (EOF);
}
mime_decode_mode = 'Q'; /* still in MIME */
goto restart_mime_q;
case LF:
case CR:
if (c1==LF) {
- if ((c1=(*i_getc)(f))!=EOF && (c1==SP||c1==TAB)) {
+ if ((c1=(*i_getc)(f))!=EOF && nkf_isblank(c1)) {
i_ungetc(SP,f);
continue;
} else {
if (c1==SP) {
i_ungetc(SP,f);
continue;
- } else if ((c1=(*i_getc)(f))!=EOF && (c1==SP||c1==TAB)) {
+ } else if ((c1=(*i_getc)(f))!=EOF && nkf_isblank(c1)) {
i_ungetc(SP,f);
continue;
} else {
PUT_NEWLINE((*o_mputc));
(*o_mputc)(SP);
base64_count = 1;
- if (mimeout_state.count>0
- && (mimeout_state.buf[i]==SP || mimeout_state.buf[i]==TAB
- || mimeout_state.buf[i]==CR || mimeout_state.buf[i]==LF)) {
+ if (mimeout_state.count>0 && nkf_isspace(mimeout_state.buf[i])) {
i++;
}
}
for (;i<mimeout_state.count;i++) {
- if (mimeout_state.buf[i]==SP || mimeout_state.buf[i]==TAB
- || mimeout_state.buf[i]==CR || mimeout_state.buf[i]==LF) {
+ if (nkf_isspace(mimeout_state.buf[i])) {
(*o_mputc)(mimeout_state.buf[i]);
base64_count ++;
} else {
return;
}
}
- (*o_mputc)(c);
- base64_count++;
+ if (c != 0x1B) {
+ (*o_mputc)(c);
+ base64_count++;
+ return;
+ }
}
- return;
+ else return;
}
if (mimeout_mode <= 0) {
mimeout_state.buf[mimeout_state.count++] = (char)c;
return;
}
- if (c==SP || c==TAB || c==CR || c==LF) {
+ if (nkf_isspace(c)) {
for (i=0;i<mimeout_state.count;i++) {
if (SP<mimeout_state.buf[i] && mimeout_state.buf[i]<DEL) {
eof_mime();
if (input_mode == JIS_X_0208 && DEL <= c1 && c1 < 0x92) {
/* CP5022x */
MORE;
+ }else if (input_codename && input_codename[0] == 'I' &&
+ 0xA1 <= c1 && c1 <= 0xDF) {
+ /* JIS X 0201 Katakana in 8bit JIS */
+ c2 = JIS_X_0201_1976_K;
+ c1 &= 0x7f;
+ SEND;
} else if (c1 > DEL) {
/* 8 bit code */
if (!estab_f && !iso8859_f) {
SKIP;
} else if (c1 == ESC && (!is_8bit || mime_decode_mode)) {
if ((c1 = (*i_getc)(f)) == EOF) {
- /* (*oconv)(0, ESC); don't send bogus code */
+ (*oconv)(0, ESC);
LAST;
}
else if (c1 == '&') {
} else if (c1 == ESC && iconv == s_iconv) {
/* ESC in Shift_JIS */
if ((c1 = (*i_getc)(f)) == EOF) {
- /* (*oconv)(0, ESC); don't send bogus code */
+ (*oconv)(0, ESC);
LAST;
} else if (c1 == '$') {
/* J-PHONE emoji */
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;
output_encoding = nkf_enc_from_index(EUCJP_NKF);
continue;
case 's': /* SJIS output */
- output_encoding = nkf_enc_from_index(WINDOWS_31J);
+ output_encoding = nkf_enc_from_index(SHIFT_JIS);
continue;
case 'l': /* ISO8859 Latin-1 support, no conversion */
iso8859_f = TRUE; /* Only compatible with ISO-2022-JP */
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;
#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
output_endian = ENDIAN_LITTLE;
} else if (cp[0] == 'B') {
cp++;
- } else {
- output_encoding = nkf_enc_from_index(enc_idx);
- continue;
}
if (cp[0] == '0'){
cp++;
case 'E': /* EUC-JP input */
input_encoding = nkf_enc_from_index(EUCJP_NKF);
continue;
- case 'S': /* Windows-31J input */
- input_encoding = nkf_enc_from_index(WINDOWS_31J);
+ case 'S': /* Shift_JIS input */
+ input_encoding = nkf_enc_from_index(SHIFT_JIS);
continue;
case 'Z': /* Convert X0208 alphabet to asii */
/* alpha_f
bit:3 Convert HTML Entity
bit:4 Convert JIS X 0208 Katakana to JIS X 0201 Katakana
*/
- while ('0'<= *cp && *cp <='9') {
+ while ('0'<= *cp && *cp <='4') {
alpha_f |= 1 << (*cp++ - '0');
}
- if (!alpha_f) alpha_f = 1;
+ alpha_f |= 1;
continue;
case 'x': /* Convert X0201 kana to X0208 or X0201 Conversion */
x0201_f = FALSE; /* No X0201->X0208 conversion */