/** Network Kanji Filter. (PDS Version)
************************************************************************
** Copyright (C) 1987, Fujitsu LTD. (Itaru ICHIKAWA)
-** \e$BO"Mm@h!'\e(B \e$B!J3t!KIY;NDL8&5f=j!!%=%U%H#38&!!;T@n!!;j\e(B
+** \e$BO"Mm@h!'\e(B \e$B!J3t!KIY;NDL8&5f=j!!%=%U%H#38&!!;T@n!!;j\e(B
** \e$B!J\e(BE-Mail Address: ichikawa@flab.fujitsu.co.jp\e$B!K\e(B
** Copyright (C) 1996,1998
** Copyright (C) 2002
** \e$B%P%$%J%j$NG[I[$N:]$K$O\e(Bversion message\e$B$rJ]B8$9$k$3$H$r>r7o$H$7$^$9!#\e(B
** \e$B$3$N%W%m%0%i%`$K$D$$$F$OFC$K2?$NJ]>Z$b$7$J$$!"0-$7$+$i$:!#\e(B
**
-** Everyone is permitted to do anything on this program
+** Everyone is permitted to do anything on this program
** including copying, modifying, improving,
** as long as you don't try to pretend that you wrote it.
-** i.e., the above copyright notice has to appear in all copies.
+** i.e., the above copyright notice has to appear in all copies.
** Binary distribution requires original version messages.
** You don't have to ask before copying, redistribution or publishing.
** THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE.
***********************************************************************/
/***********************************************************************
-** UTF-8 \e$B%5%]!<%H$K$D$$$F\e(B
-** \e$B=>Mh$N\e(B nkf \e$B$HF~$l$+$($F$=$N$^$^;H$($k$h$&$K$J$C$F$$$^$9\e(B
-** nkf -e \e$B$J$I$H$7$F5/F0$9$k$H!"<+F0H=JL$G\e(B UTF-8 \e$B$HH=Dj$5$l$l$P!"\e(B
-** \e$B$=$N$^$^\e(B euc-jp \e$B$KJQ49$5$l$^$9\e(B
-**
-** \e$B$^$@%P%0$,$"$k2DG=@-$,9b$$$G$9!#\e(B
-** (\e$BFC$K<+F0H=JL!"%3!<%I:.:_!"%(%i!<=hM}7O\e(B)
-**
-** \e$B2?$+LdBj$r8+$D$1$?$i!"\e(B
-** E-Mail: furukawa@tcp-ip.or.jp
-** \e$B$^$G8fO"Mm$r$*4j$$$7$^$9!#\e(B
+ * \e$B8=:_!"\e(Bnkf \e$B$O\e(B SorceForge \e$B$K$F%a%s%F%J%s%9$,B3$1$i$l$F$$$^$9!#\e(B
+ * http://sourceforge.jp/projects/nkf/
***********************************************************************/
-/* $Id: nkf.c,v 1.133 2007/09/19 13:03:15 naruse Exp $ */
+#define NKF_IDENT "$Id: nkf.c,v 1.166 2008/01/23 09:10:25 naruse Exp $"
#define NKF_VERSION "2.0.8"
-#define NKF_RELEASE_DATE "2007-09-19"
-#include "config.h"
-#include "utf8tbl.h"
-
+#define NKF_RELEASE_DATE "2008-01-23"
#define COPY_RIGHT \
"Copyright (C) 1987, FUJITSU LTD. (I.Ichikawa),2000 S. Kono, COW\n" \
- "Copyright (C) 2002-2007 Kono, Furukawa, Naruse, mastodon"
-
-
-/*
-**
-**
-**
-** USAGE: nkf [flags] [file]
-**
-** Flags:
-** b Output is buffered (DEFAULT)
-** u Output is unbuffered
-**
-** t no operation
-**
-** j Output code is JIS 7 bit (DEFAULT SELECT)
-** s Output code is MS Kanji (DEFAULT SELECT)
-** e Output code is AT&T JIS (DEFAULT SELECT)
-** w Output code is AT&T JIS (DEFAULT SELECT)
-** l Output code is JIS 7bit and ISO8859-1 Latin-1
-**
-** m MIME conversion for ISO-2022-JP
-** I Convert non ISO-2022-JP charactor to GETA by Pekoe <pekoe@lair.net>
-** i_ Output sequence to designate JIS-kanji (DEFAULT_J)
-** o_ Output sequence to designate single-byte roman characters (DEFAULT_R)
-** M MIME output conversion
-**
-** r {de/en}crypt ROT13/47
-**
-** v display Version
-**
-** T Text mode output (for MS-DOS)
-**
-** x Do not convert X0201 kana into X0208
-** Z Convert X0208 alphabet to ASCII
-**
-** f60 fold option
-**
-** m MIME decode
-** B try to fix broken JIS, missing Escape
-** B[1-9] broken level
-**
-** O Output to 'nkf.out' file or last file name
-** d Delete \r in line feed
-** c Add \r in line feed
-** -- other long option
-** -- ignore following option (don't use with -O )
-**
-**/
-
-#if (defined(__TURBOC__) || defined(_MSC_VER) || defined(LSI_C) || defined(__MINGW32__) || defined(__EMX__) || defined(__MSDOS__) || defined(__WINDOWS__) || defined(__DOS__) || defined(__OS2__)) && !defined(MSDOS)
-#define MSDOS
-#if (defined(__Win32__) || defined(_WIN32)) && !defined(__WIN32__)
-#define __WIN32__
-#endif
-#endif
-
-#ifdef PERL_XS
-#undef OVERWRITE
-#endif
-
-#ifndef PERL_XS
-#include <stdio.h>
-#endif
-
-#include <stdlib.h>
-#include <string.h>
-
-#if defined(MSDOS) || defined(__OS2__)
-#include <fcntl.h>
-#include <io.h>
-#if defined(_MSC_VER) || defined(__WATCOMC__)
-#define mktemp _mktemp
-#endif
-#endif
-
-#ifdef MSDOS
-#ifdef LSI_C
-#define setbinmode(fp) fsetbin(fp)
-#elif defined(__DJGPP__)
-#include <libc/dosio.h>
-#define setbinmode(fp) djgpp_setbinmode(fp)
-#else /* Microsoft C, Turbo C */
-#define setbinmode(fp) setmode(fileno(fp), O_BINARY)
-#endif
-#else /* UNIX */
-#define setbinmode(fp)
-#endif
-
-#if defined(__DJGPP__)
-void djgpp_setbinmode(FILE *fp)
-{
- /* we do not use libc's setmode(), which changes COOKED/RAW mode in device. */
- int fd, m;
- fd = fileno(fp);
- m = (__file_handle_modes[fd] & (~O_TEXT)) | O_BINARY;
- __file_handle_set(fd, m);
-}
-#endif
-
-#ifdef _IOFBF /* SysV and MSDOS, Windows */
-#define setvbuffer(fp, buf, size) setvbuf(fp, buf, _IOFBF, size)
-#else /* BSD */
-#define setvbuffer(fp, buf, size) setbuffer(fp, buf, size)
-#endif
-
-/*Borland C++ 4.5 EasyWin*/
-#if defined(__TURBOC__) && defined(_Windows) && !defined(__WIN32__) /*Easy Win */
-#define EASYWIN
-#ifndef __WIN16__
-#define __WIN16__
-#endif
-#include <windows.h>
-#endif
-
-#ifdef OVERWRITE
-/* added by satoru@isoternet.org */
-#if defined(__EMX__)
-#include <sys/types.h>
-#endif
-#include <sys/stat.h>
-#if !defined(MSDOS) || defined(__DJGPP__) /* UNIX, djgpp */
-#include <unistd.h>
-#if defined(__WATCOMC__)
-#include <sys/utime.h>
-#else
-#include <utime.h>
-#endif
-#else /* defined(MSDOS) */
-#ifdef __WIN32__
-#ifdef __BORLANDC__ /* BCC32 */
-#include <utime.h>
-#else /* !defined(__BORLANDC__) */
-#include <sys/utime.h>
-#endif /* (__BORLANDC__) */
-#else /* !defined(__WIN32__) */
-#if defined(_MSC_VER) || defined(__MINGW32__) || defined(__WATCOMC__) || defined(__OS2__) || defined(__EMX__) || defined(__IBMC__) || defined(__IBMCPP__) /* VC++, MinGW, Watcom, emx+gcc, IBM VAC++ */
-#include <sys/utime.h>
-#elif defined(__TURBOC__) /* BCC */
-#include <utime.h>
-#elif defined(LSI_C) /* LSI C */
-#endif /* (__WIN32__) */
-#endif
-#endif
-#endif
+ "Copyright (C) 2002-2008 Kono, Furukawa, Naruse, mastodon"
-#define FALSE 0
-#define TRUE 1
+#include "config.h"
+#include "nkf.h"
+#include "utf8tbl.h"
-/* state of output_mode and input_mode
+/* state of output_mode and input_mode
c2 0 means ASCII
- X0201
- ISO8859_1
- X0208
+ JIS_X_0201
+ ISO_8859_1
+ JIS_X_0208
EOF all termination
c1 32bit data
*/
-#define ASCII 0
-#define X0208 1
-#define X0201 2
-#define ISO8859_1 8
-#define NO_X0201 3
-#define X0212 0x2844
-#define X0213_1 0x284F
-#define X0213_2 0x2850
-
-/* Input Assumption */
-
-#define JIS_INPUT 4
-#define EUC_INPUT 16
-#define SJIS_INPUT 5
-#define LATIN1_INPUT 6
-#define FIXED_MIME 7
-#define STRICT_MIME 8
-
/* MIME ENCODE */
-#define ISO2022JP 9
-#define JAPANESE_EUC 10
-#define SHIFT_JIS 11
-
-#define UTF8 12
-#define UTF8_INPUT 13
-#define UTF16_INPUT 1015
-#define UTF32_INPUT 1017
+#define FIXED_MIME 7
+#define STRICT_MIME 8
/* byte order */
-
-#define ENDIAN_BIG 1234
-#define ENDIAN_LITTLE 4321
-#define ENDIAN_2143 2143
-#define ENDIAN_3412 3412
-
-#define WISH_TRUE 15
+enum byte_order {
+ ENDIAN_BIG = 1,
+ ENDIAN_LITTLE = 2,
+ ENDIAN_2143 = 3,
+ ENDIAN_3412 = 4
+};
/* ASCII CODE */
#define BS 0x08
#define TAB 0x09
-#define NL 0x0a
+#define LF 0x0a
#define CR 0x0d
#define ESC 0x1b
-#define SPACE 0x20
+#define SP 0x20
#define AT 0x40
#define SSP 0xa0
#define DEL 0x7f
#define SO 0x0e
#define SSO 0x8e
#define SS3 0x8f
+#define CRLF 0x0D0A
+
+
+/* encodings */
+
+enum nkf_encodings {
+ ASCII,
+ ISO_8859_1,
+ ISO_2022_JP,
+ CP50220,
+ CP50221,
+ CP50222,
+ ISO_2022_JP_1,
+ ISO_2022_JP_3,
+ SHIFT_JIS,
+ WINDOWS_31J,
+ CP10001,
+ EUC_JP,
+ CP51932,
+ EUCJP_MS,
+ EUCJP_ASCII,
+ SHIFT_JISX0213,
+ SHIFT_JIS_2004,
+ EUC_JISX0213,
+ EUC_JIS_2004,
+ UTF_8,
+ UTF_8N,
+ UTF_8_BOM,
+ UTF8_MAC,
+ UTF_16,
+ UTF_16BE,
+ UTF_16BE_BOM,
+ UTF_16LE,
+ UTF_16LE_BOM,
+ UTF_32,
+ UTF_32BE,
+ UTF_32BE_BOM,
+ UTF_32LE,
+ UTF_32LE_BOM,
+ NKF_ENCODING_TABLE_SIZE,
+ JIS_X_0201=0x1000,
+ JIS_X_0208=0x1001,
+ JIS_X_0212=0x1002,
+ JIS_X_0213_1=0x1003,
+ JIS_X_0213_2=0x1004,
+ BINARY
+};
+
+nkf_char s_iconv(nkf_char c2, nkf_char c1, nkf_char c0);
+nkf_char e_iconv(nkf_char c2, nkf_char c1, nkf_char c0);
+nkf_char w_iconv(nkf_char c2, nkf_char c1, nkf_char c0);
+nkf_char w_iconv16(nkf_char c2, nkf_char c1, nkf_char c0);
+nkf_char w_iconv32(nkf_char c2, nkf_char c1, nkf_char c0);
+void j_oconv(nkf_char c2, nkf_char c1);
+void s_oconv(nkf_char c2, nkf_char c1);
+void e_oconv(nkf_char c2, nkf_char c1);
+void w_oconv(nkf_char c2, nkf_char c1);
+void w_oconv16(nkf_char c2, nkf_char c1);
+void w_oconv32(nkf_char c2, nkf_char c1);
+
+typedef struct {
+ const char *name;
+ nkf_char (*iconv)(nkf_char c2, nkf_char c1, nkf_char c0);
+ void (*oconv)(nkf_char c2, nkf_char c1);
+} nkf_native_encoding;
+
+nkf_native_encoding NkfEncodingASCII = { "ASCII", e_iconv, e_oconv };
+nkf_native_encoding NkfEncodingISO_2022_JP = { "ISO-2022-JP", e_iconv, j_oconv };
+nkf_native_encoding NkfEncodingShift_JIS = { "Shift_JIS", s_iconv, s_oconv };
+nkf_native_encoding NkfEncodingEUC_JP = { "EUC-JP", e_iconv, e_oconv };
+nkf_native_encoding NkfEncodingUTF_8 = { "UTF-8", w_iconv, w_oconv };
+nkf_native_encoding NkfEncodingUTF_16 = { "UTF-16", w_iconv16, w_oconv16 };
+nkf_native_encoding NkfEncodingUTF_32 = { "UTF-32", w_iconv32, w_oconv32 };
+
+typedef struct {
+ const int id;
+ const char *name;
+ const nkf_native_encoding *base_encoding;
+} nkf_encoding;
+
+nkf_encoding nkf_encoding_table[] = {
+ {ASCII, "US-ASCII", &NkfEncodingASCII},
+ {ISO_8859_1, "ISO-8859-1", &NkfEncodingASCII},
+ {ISO_2022_JP, "ISO-2022-JP", &NkfEncodingISO_2022_JP},
+ {CP50220, "CP50220", &NkfEncodingISO_2022_JP},
+ {CP50221, "CP50221", &NkfEncodingISO_2022_JP},
+ {CP50222, "CP50222", &NkfEncodingISO_2022_JP},
+ {ISO_2022_JP_1, "ISO-2022-JP-1", &NkfEncodingISO_2022_JP},
+ {ISO_2022_JP_3, "ISO-2022-JP-3", &NkfEncodingISO_2022_JP},
+ {SHIFT_JIS, "Shift_JIS", &NkfEncodingShift_JIS},
+ {WINDOWS_31J, "Windows-31J", &NkfEncodingShift_JIS},
+ {CP10001, "CP10001", &NkfEncodingShift_JIS},
+ {EUC_JP, "EUC-JP", &NkfEncodingEUC_JP},
+ {CP51932, "CP51932", &NkfEncodingEUC_JP},
+ {EUCJP_MS, "eucJP-MS", &NkfEncodingEUC_JP},
+ {EUCJP_ASCII, "eucJP-ASCII", &NkfEncodingEUC_JP},
+ {SHIFT_JISX0213, "Shift_JISX0213", &NkfEncodingShift_JIS},
+ {SHIFT_JIS_2004, "Shift_JIS-2004", &NkfEncodingShift_JIS},
+ {EUC_JISX0213, "EUC-JISX0213", &NkfEncodingEUC_JP},
+ {EUC_JIS_2004, "EUC-JIS-2004", &NkfEncodingEUC_JP},
+ {UTF_8, "UTF-8", &NkfEncodingUTF_8},
+ {UTF_8N, "UTF-8N", &NkfEncodingUTF_8},
+ {UTF_8_BOM, "UTF-8-BOM", &NkfEncodingUTF_8},
+ {UTF8_MAC, "UTF8-MAC", &NkfEncodingUTF_8},
+ {UTF_16, "UTF-16", &NkfEncodingUTF_16},
+ {UTF_16BE, "UTF-16BE", &NkfEncodingUTF_16},
+ {UTF_16BE_BOM, "UTF-16BE-BOM", &NkfEncodingUTF_16},
+ {UTF_16LE, "UTF-16LE", &NkfEncodingUTF_16},
+ {UTF_16LE_BOM, "UTF-16LE-BOM", &NkfEncodingUTF_16},
+ {UTF_32, "UTF-32", &NkfEncodingUTF_32},
+ {UTF_32BE, "UTF-32BE", &NkfEncodingUTF_32},
+ {UTF_32BE_BOM, "UTF-32BE-BOM", &NkfEncodingUTF_32},
+ {UTF_32LE, "UTF-32LE", &NkfEncodingUTF_32},
+ {UTF_32LE_BOM, "UTF-32LE-BOM", &NkfEncodingUTF_32},
+ {BINARY, "BINARY", &NkfEncodingASCII},
+ {-1, NULL, NULL}
+};
+
+struct {
+ const char *name;
+ const int id;
+} encoding_name_to_id_table[] = {
+ {"US-ASCII", ASCII},
+ {"ASCII", ASCII},
+ {"ISO-2022-JP", ISO_2022_JP},
+ {"ISO2022JP-CP932", CP50220},
+ {"CP50220", CP50220},
+ {"CP50221", CP50221},
+ {"CP50222", CP50222},
+ {"ISO-2022-JP-1", ISO_2022_JP_1},
+ {"ISO-2022-JP-3", ISO_2022_JP_3},
+ {"SHIFT_JIS", SHIFT_JIS},
+ {"SJIS", SHIFT_JIS},
+ {"WINDOWS-31J", WINDOWS_31J},
+ {"CSWINDOWS31J", WINDOWS_31J},
+ {"CP932", WINDOWS_31J},
+ {"MS932", WINDOWS_31J},
+ {"CP10001", CP10001},
+ {"EUCJP", EUC_JP},
+ {"EUC-JP", EUC_JP},
+ {"CP51932", CP51932},
+ {"EUC-JP-MS", EUCJP_MS},
+ {"EUCJP-MS", EUCJP_MS},
+ {"EUCJPMS", EUCJP_MS},
+ {"EUC-JP-ASCII", EUCJP_ASCII},
+ {"EUCJP-ASCII", EUCJP_ASCII},
+ {"SHIFT_JISX0213", SHIFT_JISX0213},
+ {"SHIFT_JIS-2004", SHIFT_JIS_2004},
+ {"EUC-JISX0213", EUC_JISX0213},
+ {"EUC-JIS-2004", EUC_JIS_2004},
+ {"UTF-8", UTF_8},
+ {"UTF-8N", UTF_8N},
+ {"UTF-8-BOM", UTF_8_BOM},
+ {"UTF8-MAC", UTF8_MAC},
+ {"UTF-8-MAC", UTF8_MAC},
+ {"UTF-16", UTF_16},
+ {"UTF-16BE", UTF_16BE},
+ {"UTF-16BE-BOM", UTF_16BE_BOM},
+ {"UTF-16LE", UTF_16LE},
+ {"UTF-16LE-BOM", UTF_16LE_BOM},
+ {"UTF-32", UTF_32},
+ {"UTF-32BE", UTF_32BE},
+ {"UTF-32BE-BOM", UTF_32BE_BOM},
+ {"UTF-32LE", UTF_32LE},
+ {"UTF-32LE-BOM", UTF_32LE_BOM},
+ {"BINARY", BINARY},
+ {NULL, -1}
+};
+
+#if defined(DEFAULT_CODE_JIS)
+#define DEFAULT_ENCIDX ISO_2022_JP
+#elif defined(DEFAULT_CODE_SJIS)
+#define DEFAULT_ENCIDX SHIFT_JIS
+#elif defined(DEFAULT_CODE_EUC)
+#define DEFAULT_ENCIDX EUC_JP
+#elif defined(DEFAULT_CODE_UTF8)
+#define DEFAULT_ENCIDX UTF_8
+#endif
+
#define is_alnum(c) \
(('a'<=c && c<='z')||('A'<= c && c<='Z')||('0'<=c && c<='9'))
#define nkf_isoctal(c) ('0'<=c && c<='7')
#define nkf_isdigit(c) ('0'<=c && c<='9')
#define nkf_isxdigit(c) (nkf_isdigit(c) || ('a'<=c && c<='f') || ('A'<=c && c <= 'F'))
-#define nkf_isblank(c) (c == SPACE || c == TAB)
-#define nkf_isspace(c) (nkf_isblank(c) || c == CR || c == NL)
+#define nkf_isblank(c) (c == SP || c == TAB)
+#define nkf_isspace(c) (nkf_isblank(c) || c == CR || c == LF)
#define nkf_isalpha(c) (('a' <= c && c <= 'z') || ('A' <= c && c <= 'Z'))
#define nkf_isalnum(c) (nkf_isdigit(c) || nkf_isalpha(c))
-#define nkf_isprint(c) (' '<=c && c<='~')
+#define nkf_isprint(c) (SP<=c && c<='~')
#define nkf_isgraph(c) ('!'<=c && c<='~')
#define hex2bin(c) (('0'<=c&&c<='9') ? (c-'0') : \
('A'<=c&&c<='F') ? (c-'A'+10) : \
- ('a'<=c&&c<='f') ? (c-'a'+10) : 0 )
+ ('a'<=c&&c<='f') ? (c-'a'+10) : 0)
#define bin2hex(c) ("0123456789ABCDEF"[c&15])
#define is_eucg3(c2) (((unsigned short)c2 >> 8) == SS3)
+#define nkf_noescape_mime(c) ((c == CR) || (c == LF) || \
+ ((c > SP) && (c < DEL) && (c != '?') && (c != '=') && (c != '_') \
+ && (c != '(') && (c != ')') && (c != '.') && (c != 0x22)))
-#define CP932_TABLE_BEGIN 0xFA
-#define CP932_TABLE_END 0xFC
-#define CP932INV_TABLE_BEGIN 0xED
-#define CP932INV_TABLE_END 0xEE
#define is_ibmext_in_sjis(c2) (CP932_TABLE_BEGIN <= c2 && c2 <= CP932_TABLE_END)
#define HOLD_SIZE 1024
#define DEFAULT_J 'B'
#define DEFAULT_R 'B'
-#define SJ0162 0x00e1 /* 01 - 62 ku offset */
-#define SJ6394 0x0161 /* 63 - 94 ku offset */
#define RANGE_NUM_MAX 18
#define GETA1 0x22
#define GETA2 0x2e
-#if defined(UTF8_OUTPUT_ENABLE) || defined(UTF8_INPUT_ENABLE)
-#define sizeof_euc_to_utf8_1byte 94
-#define sizeof_euc_to_utf8_2bytes 94
-#define sizeof_utf8_to_euc_C2 64
-#define sizeof_utf8_to_euc_E5B8 64
-#define sizeof_utf8_to_euc_2bytes 112
-#define sizeof_utf8_to_euc_3bytes 16
-#endif
-
/* MIME preprocessor */
#ifdef EASYWIN /*Easy Win */
int _file_stat;
};
-static char *input_codename = "";
+static char *input_codename = NULL; /* NULL: unestablished, "": BINARY */
+static nkf_encoding *input_encoding = NULL;
+static nkf_encoding *output_encoding = NULL;
+static void set_output_encoding(nkf_encoding *enc);
-#ifndef PERL_XS
-static const char *CopyRight = COPY_RIGHT;
-#endif
#if !defined(PERL_XS) && !defined(WIN32DLL)
static nkf_char noconvert(FILE *f);
#endif
static nkf_char h_conv(FILE *f,nkf_char c2,nkf_char c1);
static nkf_char push_hold_buf(nkf_char c2);
static void set_iconv(nkf_char f, nkf_char (*iconv_func)(nkf_char c2,nkf_char c1,nkf_char c0));
-static nkf_char s_iconv(nkf_char c2,nkf_char c1,nkf_char c0);
static nkf_char s2e_conv(nkf_char c2, nkf_char c1, nkf_char *p2, nkf_char *p1);
-static nkf_char e_iconv(nkf_char c2,nkf_char c1,nkf_char c0);
#if defined(UTF8_INPUT_ENABLE) || defined(UTF8_OUTPUT_ENABLE)
/* UCS Mapping
* 0: Shift_JIS, eucJP-ascii
static void encode_fallback_subchar(nkf_char c);
static void (*encode_fallback)(nkf_char c) = NULL;
static nkf_char w2e_conv(nkf_char c2,nkf_char c1,nkf_char c0,nkf_char *p2,nkf_char *p1);
-static nkf_char w_iconv(nkf_char c2,nkf_char c1,nkf_char c0);
-static nkf_char w_iconv16(nkf_char c2,nkf_char c1,nkf_char c0);
-static nkf_char w_iconv32(nkf_char c2,nkf_char c1,nkf_char c0);
static nkf_char unicode_to_jis_common(nkf_char c2,nkf_char c1,nkf_char c0,nkf_char *p2,nkf_char *p1);
static nkf_char w_iconv_common(nkf_char c1,nkf_char c0,const unsigned short *const *pp,nkf_char psize,nkf_char *p2,nkf_char *p1);
static void w16w_conv(nkf_char val, nkf_char *p2, nkf_char *p1, nkf_char *p0);
static int output_bom_f = FALSE;
static int output_endian = ENDIAN_BIG;
static nkf_char e2w_conv(nkf_char c2,nkf_char c1);
-static void w_oconv(nkf_char c2,nkf_char c1);
-static void w_oconv16(nkf_char c2,nkf_char c1);
-static void w_oconv32(nkf_char c2,nkf_char c1);
#endif
-static void e_oconv(nkf_char c2,nkf_char c1);
static nkf_char e2s_conv(nkf_char c2, nkf_char c1, nkf_char *p2, nkf_char *p1);
-static void s_oconv(nkf_char c2,nkf_char c1);
-static void j_oconv(nkf_char c2,nkf_char c1);
static void fold_conv(nkf_char c2,nkf_char c1);
-static void cr_conv(nkf_char c2,nkf_char c1);
+static void nl_conv(nkf_char c2,nkf_char c1);
static void z_conv(nkf_char c2,nkf_char c1);
static void rot_conv(nkf_char c2,nkf_char c1);
static void hira_conv(nkf_char c2,nkf_char c1);
static void mimeout_addchar(nkf_char c);
#ifndef PERL_XS
static void usage(void);
-static void version(void);
+static void show_configuration(void);
#endif
static void options(unsigned char *c);
-#if defined(PERL_XS) || defined(WIN32DLL)
static void reinit(void);
-#endif
/* buffers */
/* MIME preprocessor fifo */
#define MIME_BUF_SIZE (1024) /* 2^n ring buffer */
-#define MIME_BUF_MASK (MIME_BUF_SIZE-1)
+#define MIME_BUF_MASK (MIME_BUF_SIZE-1)
#define Fifo(n) mime_buf[(n)&MIME_BUF_MASK]
static unsigned char mime_buf[MIME_BUF_SIZE];
static unsigned int mime_top = 0;
static int binmode_f = TRUE; /* binary mode */
static int rot_f = FALSE; /* rot14/43 mode */
static int hira_f = FALSE; /* hira/kata henkan */
-static int input_f = FALSE; /* non fixed input code */
static int alpha_f = FALSE; /* convert JIx0208 alphbet to ASCII */
-static int mime_f = STRICT_MIME; /* convert MIME B base64 or Q */
+static int mime_f = MIME_DECODE_DEFAULT; /* convert MIME B base64 or Q */
static int mime_decode_f = FALSE; /* mime decode is explicitly on */
static int mimebuf_f = FALSE; /* MIME buffered input */
static int broken_f = FALSE; /* convert ESC-less broken JIS */
static int iso8859_f = FALSE; /* ISO8859 through */
static int mimeout_f = FALSE; /* base64 mode */
-#if defined(MSDOS) || defined(__OS2__)
-static int x0201_f = TRUE; /* Assume JISX0201 kana */
-#else
-static int x0201_f = NO_X0201; /* Assume NO JISX0201 */
-#endif
-static int iso2022jp_f = FALSE; /* convert ISO-2022-JP */
+static int x0201_f = X0201_DEFAULT; /* convert JIS X 0201 */
+static int iso2022jp_f = FALSE; /* replace non ISO-2022-JP with GETA */
#ifdef UNICODE_NORMALIZATION
static int nfc_f = FALSE;
static nkf_char url_ungetc(nkf_char c,FILE *f);
#endif
-#if defined(INT_IS_SHORT)
-#define NKF_INT32_C(n) (n##L)
-#else
-#define NKF_INT32_C(n) (n)
-#endif
#define PREFIX_EUCG3 NKF_INT32_C(0x8F00)
#define CLASS_MASK NKF_INT32_C(0xFF000000)
#define CLASS_UNICODE NKF_INT32_C(0x01000000)
#ifdef CHECK_OPTION
static int noout_f = FALSE;
static void no_putc(nkf_char c);
-static nkf_char debug_f = FALSE;
+static int debug_f = FALSE;
static void debug(const char *str);
static nkf_char (*iconv_for_check)(nkf_char c2,nkf_char c1,nkf_char c0) = 0;
#endif
-static int guess_f = FALSE;
+static int guess_f = 0; /* 0: OFF, 1: ON, 2: VERBOSE */
#if !defined PERL_XS
static void print_guessed_code(char *filename);
#endif
static void set_input_codename(char *codename);
-static int is_inputcode_mixed = FALSE;
-static int is_inputcode_set = FALSE;
#ifdef EXEC_IO
static int exec_f = 0;
{0}
};
-static int mimeout_mode = 0;
+static int mimeout_mode = 0; /* 0, -1, 'Q', 'B', 1, 2 */
static int base64_count = 0;
/* X0208 -> ASCII converter */
static int fold_margin = FOLD_MARGIN;
-/* converters */
-
-#ifdef DEFAULT_CODE_JIS
-# define DEFAULT_CONV j_oconv
-#endif
-#ifdef DEFAULT_CODE_SJIS
-# define DEFAULT_CONV s_oconv
-#endif
-#ifdef DEFAULT_CODE_EUC
-# define DEFAULT_CONV e_oconv
-#endif
-#ifdef DEFAULT_CODE_UTF8
-# define DEFAULT_CONV w_oconv
-#endif
-
/* process default */
-static void (*output_conv)(nkf_char c2,nkf_char c1) = DEFAULT_CONV;
-
-static void (*oconv)(nkf_char c2,nkf_char c1) = no_connection;
-/* s_iconv or oconv */
static nkf_char (*iconv)(nkf_char c2,nkf_char c1,nkf_char c0) = no_connection2;
+static void (*oconv)(nkf_char c2,nkf_char c1) = no_connection;
static void (*o_zconv)(nkf_char c2,nkf_char c1) = no_connection;
static void (*o_fconv)(nkf_char c2,nkf_char c1) = no_connection;
-static void (*o_crconv)(nkf_char c2,nkf_char c1) = no_connection;
+static void (*o_nlconv)(nkf_char c2,nkf_char c1) = no_connection;
static void (*o_rot_conv)(nkf_char c2,nkf_char c1) = no_connection;
static void (*o_hira_conv)(nkf_char c2,nkf_char c1) = no_connection;
static void (*o_base64conv)(nkf_char c2,nkf_char c1) = no_connection;
} ;
-#define CRLF 1
static int file_out_f = FALSE;
#ifdef OVERWRITE
static char *get_backup_filename(const char *suffix, const char *filename);
#endif
-static int crmode_f = 0; /* CR, NL, CRLF */
-static nkf_char prev_cr = 0;
+static int nlmode_f = 0; /* CR, LF, CRLF */
+static int input_newline = 0; /* 0: unestablished, EOF: MIXED */
+static nkf_char prev_cr = 0; /* CR or 0 */
#ifdef EASYWIN /*Easy Win */
static int end_check;
#endif /*Easy Win */
nkf_char std_gc_buf[STD_GC_BUFSIZE];
nkf_char std_gc_ndx;
+char* nkf_strcpy(const char *str)
+{
+ char* result = malloc(strlen(str) + 1);
+ if (!result){
+ perror(str);
+ return "";
+ }
+ strcpy(result, str);
+ return result;
+}
+
+static void nkf_str_upcase(const char *src, char *dest, size_t length)
+{
+ int i = 0;
+ for (; i < length && src[i]; i++) {
+ dest[i] = nkf_toupper(src[i]);
+ }
+ dest[i] = 0;
+}
+
+static nkf_encoding *nkf_enc_from_index(int idx)
+{
+ if (idx < 0 || NKF_ENCODING_TABLE_SIZE <= idx) {
+ return 0;
+ }
+ return &nkf_encoding_table[idx];
+}
+
+static int nkf_enc_find_index(const char *name)
+{
+ int i, index = -1;
+ if (*name == 'X' && *(name+1) == '-') name += 2;
+ for (i = 0; encoding_name_to_id_table[i].id >= 0; i++) {
+ if (strcmp(name, encoding_name_to_id_table[i].name) == 0) {
+ return encoding_name_to_id_table[i].id;
+ }
+ }
+ return index;
+}
+
+static nkf_encoding *nkf_enc_find(const char *name)
+{
+ int idx = -1;
+ idx = nkf_enc_find_index(name);
+ if (idx < 0) return 0;
+ return nkf_enc_from_index(idx);
+}
+
+#define nkf_enc_name(enc) (enc)->name
+#define nkf_enc_to_index(enc) (enc)->id
+#define nkf_enc_to_base_encoding(enc) (enc)->base_encoding
+#define nkf_enc_to_iconv(enc) nkf_enc_to_base_encoding(enc)->iconv
+#define nkf_enc_to_oconv(enc) nkf_enc_to_base_encoding(enc)->oconv
+#define nkf_enc_asciicompat(enc) (\
+ nkf_enc_to_base_encoding(enc) == &NkfEncodingASCII ||\
+ nkf_enc_to_base_encoding(enc) == &NkfEncodingISO_2022_JP)
+#define nkf_enc_unicode_p(enc) (\
+ nkf_enc_to_base_encoding(enc) == &NkfEncodingUTF_8 ||\
+ nkf_enc_to_base_encoding(enc) == &NkfEncodingUTF_16 ||\
+ nkf_enc_to_base_encoding(enc) == &NkfEncodingUTF_32)
+#define nkf_enc_cp5022x_p(enc) (\
+ nkf_enc_to_index(enc) == CP50220 ||\
+ nkf_enc_to_index(enc) == CP50221 ||\
+ nkf_enc_to_index(enc) == CP50222)
+
+#ifndef DEFAULT_ENCIDX
+static char* nkf_locale_charmap()
+{
+#ifdef HAVE_LANGINFO_H
+ return nl_langinfo(CODESET);
+#elif defined(__WIN32__)
+ return sprintf("CP%d", GetACP());
+#else
+ return NULL;
+#endif
+}
+
+static nkf_encoding* nkf_locale_encoding()
+{
+ nkf_encoding *enc = 0;
+ char *encname = nkf_locale_charmap();
+ if (encname)
+ enc = nkf_enc_find(encname);
+ if (enc < 0) enc = 0;
+ return enc;
+}
+#endif
+
+static nkf_encoding* nkf_default_encoding()
+{
+#ifdef DEFAULT_ENCIDX
+ return nkf_enc_from_index(DEFAULT_ENCIDX);
+#else
+ nkf_encoding *enc = nkf_locale_encoding();
+ if (enc <= 0) enc = nkf_enc_from_index(ISO_2022_JP);
+ return enc;
+#endif
+}
+
#ifdef WIN32DLL
#include "nkf32dll.c"
#elif defined(PERL_XS)
#ifdef EASYWIN /*Easy Win */
_BufferSize.y = 400;/*Set Scroll Buffer Size*/
#endif
+ setlocale(LC_CTYPE, "");
for (argc--,argv++; (argc > 0) && **argv == '-'; argc--, argv++) {
cp = (unsigned char *)*argv;
}
#endif
}
- if(x0201_f == WISH_TRUE)
- x0201_f = ((!iso2022jp_f)? TRUE : NO_X0201);
+
+ if (guess_f) {
+#ifdef CHECK_OPTION
+ int debug_f_back = debug_f;
+#endif
+#ifdef EXEC_IO
+ int exec_f_back = exec_f;
+#endif
+#ifdef X0212_ENABLE
+ int x0212_f_back = x0212_f;
+#endif
+ int x0213_f_back = x0213_f;
+ int guess_f_back = guess_f;
+ reinit();
+ guess_f = guess_f_back;
+ mime_f = FALSE;
+#ifdef CHECK_OPTION
+ debug_f = debug_f_back;
+#endif
+#ifdef EXEC_IO
+ exec_f = exec_f_back;
+#endif
+#ifdef X0212_ENABLE
+ x0212_f = x0212_f_back;
+#endif
+ x0213_f = x0213_f_back;
+ }
if (binmode_f == TRUE)
#if defined(__OS2__) && (defined(__IBMC__) || defined(__IBMCPP__))
- if (freopen("","wb",stdout) == NULL)
+ if (freopen("","wb",stdout) == NULL)
return (-1);
#else
setbinmode(stdout);
int nfiles = argc;
int is_argument_error = FALSE;
while (argc--) {
- is_inputcode_mixed = FALSE;
- is_inputcode_set = FALSE;
- input_codename = "";
+ input_codename = NULL;
+ input_newline = 0;
#ifdef CHECK_OPTION
iconv_for_check = 0;
#endif
if ((fin = fopen((origfname = *argv++), "r")) == NULL) {
- perror(*--argv);
- *argv++;
+ perror(*(argv-1));
is_argument_error = TRUE;
continue;
} else {
}
}else
#endif
- if(argc == 1 ) {
+ if(argc == 1) {
outfname = *argv++;
argc--;
} else {
}
if (binmode_f == TRUE) {
#if defined(__OS2__) && (defined(__IBMC__) || defined(__IBMCPP__))
- if (freopen("","wb",stdout) == NULL)
+ if (freopen("","wb",stdout) == NULL)
return (-1);
#else
setbinmode(stdout);
}
if (binmode_f == TRUE)
#if defined(__OS2__) && (defined(__IBMC__) || defined(__IBMCPP__))
- if (freopen("","rb",fin) == NULL)
+ if (freopen("","rb",fin) == NULL)
return (-1);
#else
setbinmode(fin);
-#endif
+#endif
setvbuffer(fin, (char *) stdibuf, IOBUF_SIZE);
if (nop_f)
noconvert(fin);
return(-1);
}
#ifdef EASYWIN /*Easy Win */
- if (file_out_f == FALSE)
+ if (file_out_f == FALSE)
scanf("%d",&end_check);
- else
+ else
fclose(stdout);
#else /* for Other OS */
- if (file_out_f == TRUE)
+ if (file_out_f == TRUE)
fclose(stdout);
#endif /*Easy Win */
return (0);
{"hiragana","h1"},
{"katakana","h2"},
{"katakana-hiragana","h3"},
- {"guess", "g"},
+ {"guess=", ""},
+ {"guess", "g2"},
{"cp932", ""},
{"no-cp932", ""},
#ifdef X0212_ENABLE
{"prefix=", ""},
};
-static int option_mode = 0;
-
-void options(unsigned char *cp)
+static void set_input_encoding(nkf_encoding *enc)
{
- nkf_char i, j;
- unsigned char *p;
- unsigned char *cp_back = NULL;
- char codeset[32];
-
- if (option_mode==1)
- return;
- while(*cp && *cp++!='-');
- while (*cp || cp_back) {
- if(!*cp){
- cp = cp_back;
- cp_back = NULL;
- continue;
- }
- p = 0;
- switch (*cp++) {
- case '-': /* literal options */
- if (!*cp || *cp == SPACE) { /* ignore the rest of arguments */
- option_mode = 1;
- return;
- }
- for (i=0;i<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] == ' '){
- p = &cp[j] + 1;
- break;
- }
- p = 0;
- }
- if (p == 0) return;
- while(*cp && *cp != SPACE && cp++);
- if (long_option[i].alias[0]){
- cp_back = cp;
- cp = (unsigned char *)long_option[i].alias;
- }else{
- if (strcmp(long_option[i].name, "ic=") == 0){
- for (i=0; i < 16 && SPACE < p[i] && p[i] < DEL; i++){
- codeset[i] = nkf_toupper(p[i]);
- }
- codeset[i] = 0;
- if(strcmp(codeset, "ISO-2022-JP") == 0){
- input_f = JIS_INPUT;
- }else if(strcmp(codeset, "X-ISO2022JP-CP932") == 0 ||
- strcmp(codeset, "CP50220") == 0 ||
- strcmp(codeset, "CP50221") == 0 ||
- strcmp(codeset, "CP50222") == 0){
- input_f = JIS_INPUT;
+ switch (nkf_enc_to_index(enc)) {
+ case CP50220:
+ case CP50221:
+ case CP50222:
#ifdef SHIFTJIS_CP932
- cp51932_f = TRUE;
+ cp51932_f = TRUE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_CP932;
+ ms_ucs_map_f = UCS_MAP_CP932;
#endif
- }else if(strcmp(codeset, "ISO-2022-JP-1") == 0){
- input_f = JIS_INPUT;
+ break;
+ case ISO_2022_JP_1:
#ifdef X0212_ENABLE
- x0212_f = TRUE;
+ x0212_f = TRUE;
#endif
- }else if(strcmp(codeset, "ISO-2022-JP-3") == 0){
- input_f = JIS_INPUT;
+ break;
+ case ISO_2022_JP_3:
#ifdef X0212_ENABLE
- x0212_f = TRUE;
-#endif
- x0213_f = TRUE;
- }else if(strcmp(codeset, "SHIFT_JIS") == 0){
- input_f = SJIS_INPUT;
- }else if(strcmp(codeset, "WINDOWS-31J") == 0 ||
- strcmp(codeset, "CSWINDOWS31J") == 0 ||
- strcmp(codeset, "CP932") == 0 ||
- strcmp(codeset, "MS932") == 0){
- input_f = SJIS_INPUT;
+ x0212_f = TRUE;
+#endif
+ x0213_f = TRUE;
+ break;
+ case SHIFT_JIS:
+ break;
+ case WINDOWS_31J:
#ifdef SHIFTJIS_CP932
- cp51932_f = TRUE;
+ cp51932_f = TRUE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_CP932;
+ ms_ucs_map_f = UCS_MAP_CP932;
#endif
- }else if(strcmp(codeset, "CP10001") == 0){
- input_f = SJIS_INPUT;
+ break;
+ case EUC_JP:
+ break;
+ case CP10001:
#ifdef SHIFTJIS_CP932
- cp51932_f = TRUE;
+ cp51932_f = TRUE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_CP10001;
+ ms_ucs_map_f = UCS_MAP_CP10001;
#endif
- }else if(strcmp(codeset, "EUCJP") == 0 ||
- strcmp(codeset, "EUC-JP") == 0){
- input_f = EUC_INPUT;
- }else if(strcmp(codeset, "CP51932") == 0){
- input_f = EUC_INPUT;
+ break;
+ case CP51932:
#ifdef SHIFTJIS_CP932
- cp51932_f = TRUE;
+ cp51932_f = TRUE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_CP932;
+ ms_ucs_map_f = UCS_MAP_CP932;
#endif
- }else if(strcmp(codeset, "EUC-JP-MS") == 0 ||
- strcmp(codeset, "EUCJP-MS") == 0 ||
- strcmp(codeset, "EUCJPMS") == 0){
- input_f = EUC_INPUT;
+ break;
+ case EUCJP_MS:
#ifdef SHIFTJIS_CP932
- cp51932_f = FALSE;
+ cp51932_f = FALSE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_MS;
+ ms_ucs_map_f = UCS_MAP_MS;
#endif
- }else if(strcmp(codeset, "EUC-JP-ASCII") == 0 ||
- strcmp(codeset, "EUCJP-ASCII") == 0){
- input_f = EUC_INPUT;
+ break;
+ case EUCJP_ASCII:
#ifdef SHIFTJIS_CP932
- cp51932_f = FALSE;
+ cp51932_f = FALSE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_ASCII;
+ ms_ucs_map_f = UCS_MAP_ASCII;
#endif
- }else if(strcmp(codeset, "SHIFT_JISX0213") == 0 ||
- strcmp(codeset, "SHIFT_JIS-2004") == 0){
- input_f = SJIS_INPUT;
- x0213_f = TRUE;
+ break;
+ case SHIFT_JISX0213:
+ case SHIFT_JIS_2004:
+ x0213_f = TRUE;
#ifdef SHIFTJIS_CP932
- cp51932_f = FALSE;
+ cp51932_f = FALSE;
#endif
- }else if(strcmp(codeset, "EUC-JISX0213") == 0 ||
- strcmp(codeset, "EUC-JIS-2004") == 0){
- input_f = EUC_INPUT;
- x0213_f = TRUE;
+ break;
+ case EUC_JISX0213:
+ case EUC_JIS_2004:
+ x0213_f = TRUE;
#ifdef SHIFTJIS_CP932
- cp51932_f = FALSE;
+ cp51932_f = FALSE;
#endif
+ break;
#ifdef UTF8_INPUT_ENABLE
- }else if(strcmp(codeset, "UTF-8") == 0 ||
- strcmp(codeset, "UTF-8N") == 0 ||
- strcmp(codeset, "UTF-8-BOM") == 0){
- input_f = UTF8_INPUT;
#ifdef UNICODE_NORMALIZATION
- }else if(strcmp(codeset, "UTF8-MAC") == 0 ||
- strcmp(codeset, "UTF-8-MAC") == 0){
- input_f = UTF8_INPUT;
- nfc_f = TRUE;
-#endif
- }else if(strcmp(codeset, "UTF-16") == 0 ||
- strcmp(codeset, "UTF-16BE") == 0 ||
- strcmp(codeset, "UTF-16BE-BOM") == 0){
- input_f = UTF16_INPUT;
- input_endian = ENDIAN_BIG;
- }else if(strcmp(codeset, "UTF-16LE") == 0 ||
- strcmp(codeset, "UTF-16LE-BOM") == 0){
- input_f = UTF16_INPUT;
- input_endian = ENDIAN_LITTLE;
- }else if(strcmp(codeset, "UTF-32") == 0 ||
- strcmp(codeset, "UTF-32BE") == 0 ||
- strcmp(codeset, "UTF-32BE-BOM") == 0){
- input_f = UTF32_INPUT;
- input_endian = ENDIAN_BIG;
- }else if(strcmp(codeset, "UTF-32LE") == 0 ||
- strcmp(codeset, "UTF-32LE-BOM") == 0){
- input_f = UTF32_INPUT;
- input_endian = ENDIAN_LITTLE;
-#endif
- }
- continue;
- }
- if (strcmp(long_option[i].name, "oc=") == 0){
- x0201_f = FALSE;
- for (i=0; i < 16 && SPACE < p[i] && p[i] < DEL; i++){
- codeset[i] = nkf_toupper(p[i]);
- }
- codeset[i] = 0;
- if(strcmp(codeset, "ISO-2022-JP") == 0){
- output_conv = j_oconv;
- }else if(strcmp(codeset, "X-ISO2022JP-CP932") == 0){
- output_conv = j_oconv;
- no_cp932ext_f = TRUE;
-#ifdef SHIFTJIS_CP932
- cp932inv_f = FALSE;
+ case UTF8_MAC:
+ nfc_f = TRUE;
+ break;
#endif
-#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_CP932;
+ case UTF_16:
+ case UTF_16BE:
+ case UTF_16BE_BOM:
+ input_endian = ENDIAN_BIG;
+ break;
+ case UTF_16LE:
+ case UTF_16LE_BOM:
+ input_endian = ENDIAN_LITTLE;
+ break;
+ case UTF_32:
+ case UTF_32BE:
+ case UTF_32BE_BOM:
+ input_endian = ENDIAN_BIG;
+ break;
+ case UTF_32LE:
+ case UTF_32LE_BOM:
+ input_endian = ENDIAN_LITTLE;
+ break;
#endif
- }else if(strcmp(codeset, "CP50220") == 0){
- output_conv = j_oconv;
- x0201_f = TRUE;
+ }
+}
+
+static void set_output_encoding(nkf_encoding *enc)
+{
+ switch (nkf_enc_to_index(enc)) {
+ case CP50220:
+ x0201_f = TRUE;
#ifdef SHIFTJIS_CP932
- cp932inv_f = FALSE;
+ if (cp932inv_f == TRUE) cp932inv_f = FALSE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_CP932;
+ ms_ucs_map_f = UCS_MAP_CP932;
#endif
- }else if(strcmp(codeset, "CP50221") == 0){
- output_conv = j_oconv;
+ break;
+ case CP50221:
#ifdef SHIFTJIS_CP932
- cp932inv_f = FALSE;
+ if (cp932inv_f == TRUE) cp932inv_f = FALSE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_CP932;
+ ms_ucs_map_f = UCS_MAP_CP932;
#endif
- }else if(strcmp(codeset, "ISO-2022-JP-1") == 0){
- output_conv = j_oconv;
+ break;
+ case ISO_2022_JP_1:
#ifdef X0212_ENABLE
- x0212_f = TRUE;
+ x0212_f = TRUE;
#endif
#ifdef SHIFTJIS_CP932
- cp932inv_f = FALSE;
+ if (cp932inv_f == TRUE) cp932inv_f = FALSE;
#endif
- }else if(strcmp(codeset, "ISO-2022-JP-3") == 0){
- output_conv = j_oconv;
+ break;
+ case ISO_2022_JP_3:
#ifdef X0212_ENABLE
- x0212_f = TRUE;
+ x0212_f = TRUE;
#endif
- x0213_f = TRUE;
+ x0213_f = TRUE;
#ifdef SHIFTJIS_CP932
- cp932inv_f = FALSE;
-#endif
- }else if(strcmp(codeset, "SHIFT_JIS") == 0){
- output_conv = s_oconv;
- }else if(strcmp(codeset, "WINDOWS-31J") == 0 ||
- strcmp(codeset, "CSWINDOWS31J") == 0 ||
- strcmp(codeset, "CP932") == 0 ||
- strcmp(codeset, "MS932") == 0){
- output_conv = s_oconv;
+ if (cp932inv_f == TRUE) cp932inv_f = FALSE;
+#endif
+ break;
+ case SHIFT_JIS:
+ break;
+ case WINDOWS_31J:
+#ifdef UTF8_OUTPUT_ENABLE
+ ms_ucs_map_f = UCS_MAP_CP932;
+#endif
+ break;
+ case CP10001:
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_CP932;
+ ms_ucs_map_f = UCS_MAP_CP10001;
+#endif
+ break;
+ case EUC_JP:
+ x0212_f = TRUE;
+#ifdef SHIFTJIS_CP932
+ if (cp932inv_f == TRUE) cp932inv_f = FALSE;
#endif
- }else if(strcmp(codeset, "CP10001") == 0){
- output_conv = s_oconv;
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_CP10001;
+ ms_ucs_map_f = UCS_MAP_CP932;
#endif
- }else if(strcmp(codeset, "EUCJP") == 0 ||
- strcmp(codeset, "EUC-JP") == 0){
- output_conv = e_oconv;
- }else if(strcmp(codeset, "CP51932") == 0){
- output_conv = e_oconv;
+ break;
+ case CP51932:
#ifdef SHIFTJIS_CP932
- cp932inv_f = FALSE;
+ if (cp932inv_f == TRUE) cp932inv_f = FALSE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_CP932;
+ ms_ucs_map_f = UCS_MAP_CP932;
#endif
- }else if(strcmp(codeset, "EUC-JP-MS") == 0 ||
- strcmp(codeset, "EUCJP-MS") == 0 ||
- strcmp(codeset, "EUCJPMS") == 0){
- output_conv = e_oconv;
+ break;
+ case EUCJP_MS:
#ifdef X0212_ENABLE
- x0212_f = TRUE;
+ x0212_f = TRUE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_MS;
+ ms_ucs_map_f = UCS_MAP_MS;
#endif
- }else if(strcmp(codeset, "EUC-JP-ASCII") == 0 ||
- strcmp(codeset, "EUCJP-ASCII") == 0){
- output_conv = e_oconv;
+ break;
+ case EUCJP_ASCII:
#ifdef X0212_ENABLE
- x0212_f = TRUE;
+ x0212_f = TRUE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_ASCII;
+ ms_ucs_map_f = UCS_MAP_ASCII;
#endif
- }else if(strcmp(codeset, "SHIFT_JISX0213") == 0 ||
- strcmp(codeset, "SHIFT_JIS-2004") == 0){
- output_conv = s_oconv;
- x0213_f = TRUE;
+ break;
+ case SHIFT_JISX0213:
+ case SHIFT_JIS_2004:
+ x0213_f = TRUE;
#ifdef SHIFTJIS_CP932
- cp932inv_f = FALSE;
+ if (cp932inv_f == TRUE) cp932inv_f = FALSE;
#endif
- }else if(strcmp(codeset, "EUC-JISX0213") == 0 ||
- strcmp(codeset, "EUC-JIS-2004") == 0){
- output_conv = e_oconv;
+ break;
+ case EUC_JISX0213:
+ case EUC_JIS_2004:
#ifdef X0212_ENABLE
- x0212_f = TRUE;
+ x0212_f = TRUE;
#endif
- x0213_f = TRUE;
+ x0213_f = TRUE;
#ifdef SHIFTJIS_CP932
- cp932inv_f = FALSE;
+ if (cp932inv_f == TRUE) cp932inv_f = FALSE;
#endif
+ break;
#ifdef UTF8_OUTPUT_ENABLE
- }else if(strcmp(codeset, "UTF-8") == 0){
- output_conv = w_oconv;
- }else if(strcmp(codeset, "UTF-8N") == 0){
- output_conv = w_oconv;
- }else if(strcmp(codeset, "UTF-8-BOM") == 0){
- output_conv = w_oconv;
- output_bom_f = TRUE;
- }else if(strcmp(codeset, "UTF-16BE") == 0){
- output_conv = w_oconv16;
- }else if(strcmp(codeset, "UTF-16") == 0 ||
- strcmp(codeset, "UTF-16BE-BOM") == 0){
- output_conv = w_oconv16;
- output_bom_f = TRUE;
- }else if(strcmp(codeset, "UTF-16LE") == 0){
- output_conv = w_oconv16;
- output_endian = ENDIAN_LITTLE;
- }else if(strcmp(codeset, "UTF-16LE-BOM") == 0){
- output_conv = w_oconv16;
- output_endian = ENDIAN_LITTLE;
- output_bom_f = TRUE;
- }else if(strcmp(codeset, "UTF-32") == 0 ||
- strcmp(codeset, "UTF-32BE") == 0){
- output_conv = w_oconv32;
- }else if(strcmp(codeset, "UTF-32BE-BOM") == 0){
- output_conv = w_oconv32;
- output_bom_f = TRUE;
- }else if(strcmp(codeset, "UTF-32LE") == 0){
- output_conv = w_oconv32;
- output_endian = ENDIAN_LITTLE;
- }else if(strcmp(codeset, "UTF-32LE-BOM") == 0){
- output_conv = w_oconv32;
- output_endian = ENDIAN_LITTLE;
- output_bom_f = TRUE;
+ case UTF_8_BOM:
+ output_bom_f = TRUE;
+ break;
+ case UTF_16:
+ case UTF_16BE_BOM:
+ output_bom_f = TRUE;
+ break;
+ case UTF_16LE:
+ output_endian = ENDIAN_LITTLE;
+ output_bom_f = FALSE;
+ break;
+ case UTF_16LE_BOM:
+ output_endian = ENDIAN_LITTLE;
+ output_bom_f = TRUE;
+ break;
+ case UTF_32BE_BOM:
+ output_bom_f = TRUE;
+ break;
+ case UTF_32LE:
+ output_endian = ENDIAN_LITTLE;
+ output_bom_f = FALSE;
+ break;
+ case UTF_32LE_BOM:
+ output_endian = ENDIAN_LITTLE;
+ output_bom_f = TRUE;
+ break;
#endif
- }
+ }
+}
+
+static int option_mode = 0;
+
+void options(unsigned char *cp)
+{
+ nkf_char i, j;
+ unsigned char *p;
+ unsigned char *cp_back = NULL;
+ char codeset[32];
+ nkf_encoding *enc;
+
+ if (option_mode==1)
+ return;
+ while(*cp && *cp++!='-');
+ while (*cp || cp_back) {
+ if(!*cp){
+ cp = cp_back;
+ cp_back = NULL;
+ continue;
+ }
+ p = 0;
+ switch (*cp++) {
+ case '-': /* literal options */
+ if (!*cp || *cp == SP) { /* ignore the rest of arguments */
+ option_mode = 1;
+ return;
+ }
+ for (i=0;i<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){
+ p = &cp[j] + 1;
+ break;
+ }
+ p = 0;
+ }
+ if (p == 0) {
+ fprintf(stderr, "unknown long option: --%s\n", cp);
+ return;
+ }
+ while(*cp && *cp != SP && cp++);
+ if (long_option[i].alias[0]){
+ cp_back = cp;
+ cp = (unsigned char *)long_option[i].alias;
+ }else{
+ if (strcmp(long_option[i].name, "ic=") == 0){
+ nkf_str_upcase((char *)p, codeset, 32);
+ enc = nkf_enc_find(codeset);
+ if (!enc) continue;
+ input_encoding = enc;
continue;
}
+ if (strcmp(long_option[i].name, "oc=") == 0){
+ nkf_str_upcase((char *)p, codeset, 32);
+ enc = nkf_enc_find(codeset);
+ if (enc <= 0) continue;
+ output_encoding = enc;
+ continue;
+ }
+ if (strcmp(long_option[i].name, "guess=") == 0){
+ if (p[0] == '0' || p[0] == '1') {
+ guess_f = 1;
+ } else {
+ guess_f = 2;
+ }
+ continue;
+ }
#ifdef OVERWRITE
if (strcmp(long_option[i].name, "overwrite") == 0){
file_out_f = TRUE;
if (strcmp(long_option[i].name, "cp932") == 0){
#ifdef SHIFTJIS_CP932
cp51932_f = TRUE;
- cp932inv_f = TRUE;
+ cp932inv_f = -TRUE;
#endif
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_CP932;
}
#ifdef SHIFTJIS_CP932
if (strcmp(long_option[i].name, "cp932inv") == 0){
- cp932inv_f = TRUE;
+ cp932inv_f = -TRUE;
continue;
}
#endif
encode_fallback = encode_fallback_html;
continue;
}
- if (strcmp(long_option[i].name, "fb-xml" ) == 0){
+ if (strcmp(long_option[i].name, "fb-xml") == 0){
encode_fallback = encode_fallback_xml;
continue;
}
#endif
#ifdef UNICODE_NORMALIZATION
if (strcmp(long_option[i].name, "utf8mac-input") == 0){
- input_f = UTF8_INPUT;
nfc_f = TRUE;
continue;
}
case 't': /* transparent mode */
if (*cp=='1') {
/* alias of -t */
+ cp++;
nop_f = TRUE;
- *cp++;
} else if (*cp=='2') {
/*
* -t with put/get
* nkf -t2MB hoge.bin | nkf -t2mB | diff -s - hoge.bin
*
*/
+ cp++;
nop_f = 2;
- *cp++;
} else
nop_f = TRUE;
continue;
case 'j': /* JIS output */
case 'n':
- output_conv = j_oconv;
+ output_encoding = nkf_enc_from_index(ISO_2022_JP);
continue;
case 'e': /* AT&T EUC output */
- output_conv = e_oconv;
- cp932inv_f = FALSE;
+ output_encoding = nkf_enc_from_index(EUC_JP);
continue;
case 's': /* SJIS output */
- output_conv = s_oconv;
+ output_encoding = nkf_enc_from_index(WINDOWS_31J);
continue;
case 'l': /* ISO8859 Latin-1 support, no conversion */
iso8859_f = TRUE; /* Only compatible with ISO-2022-JP */
- input_f = LATIN1_INPUT;
+ input_encoding = nkf_enc_from_index(ISO_8859_1);
continue;
case 'i': /* Kanji IN ESC-$-@/B */
- if (*cp=='@'||*cp=='B')
+ if (*cp=='@'||*cp=='B')
kanji_intro = *cp++;
continue;
case 'o': /* ASCII IN ESC-(-J/B */
- if (*cp=='J'||*cp=='B'||*cp=='H')
+ if (*cp=='J'||*cp=='B'||*cp=='H')
ascii_intro = *cp++;
continue;
case 'h':
- /*
+ /*
bit:1 katakana->hiragana
bit:2 hiragana->katakana
*/
- if ('9'>= *cp && *cp>='0')
+ if ('9'>= *cp && *cp>='0')
hira_f |= (*cp++ -'0');
- else
+ else
hira_f |= 1;
continue;
case 'r':
rot_f = TRUE;
continue;
-#if defined(MSDOS) || defined(__OS2__)
+#if defined(MSDOS) || defined(__OS2__)
case 'T':
binmode_f = FALSE;
continue;
#endif
#ifndef PERL_XS
case 'V':
- version();
+ show_configuration();
exit(1);
break;
case 'v':
#ifdef UTF8_OUTPUT_ENABLE
case 'w': /* UTF-8 output */
if (cp[0] == '8') {
- output_conv = w_oconv; cp++;
+ cp++;
if (cp[0] == '0'){
cp++;
+ output_encoding = nkf_enc_from_index(UTF_8N);
} else {
output_bom_f = TRUE;
+ output_encoding = nkf_enc_from_index(UTF_8_BOM);
}
} else {
+ int enc_idx;
if ('1'== cp[0] && '6'==cp[1]) {
- output_conv = w_oconv16; cp+=2;
+ cp += 2;
+ enc_idx = UTF_16;
} else if ('3'== cp[0] && '2'==cp[1]) {
- output_conv = w_oconv32; cp+=2;
+ cp += 2;
+ enc_idx = UTF_32;
} else {
- output_conv = w_oconv;
+ output_encoding = nkf_enc_from_index(UTF_8);
continue;
}
if (cp[0]=='L') {
} else if (cp[0] == 'B') {
cp++;
} else {
+ output_encoding = nkf_enc_from_index(enc_idx);
continue;
}
if (cp[0] == '0'){
cp++;
+ enc_idx = enc_idx == UTF_16
+ ? (output_endian == ENDIAN_LITTLE ? UTF_16LE : UTF_16BE)
+ : (output_endian == ENDIAN_LITTLE ? UTF_32LE : UTF_32BE);
} else {
output_bom_f = TRUE;
+ enc_idx = enc_idx == UTF_16
+ ? (output_endian == ENDIAN_LITTLE ? UTF_16LE_BOM : UTF_16BE_BOM)
+ : (output_endian == ENDIAN_LITTLE ? UTF_32LE_BOM : UTF_32BE_BOM);
}
+ output_encoding = nkf_enc_from_index(enc_idx);
}
continue;
#endif
case 'W': /* UTF input */
if (cp[0] == '8') {
cp++;
- input_f = UTF8_INPUT;
+ input_encoding = nkf_enc_from_index(UTF_8);
}else{
+ int enc_idx;
if ('1'== cp[0] && '6'==cp[1]) {
cp += 2;
- input_f = UTF16_INPUT;
input_endian = ENDIAN_BIG;
+ enc_idx = UTF_16;
} else if ('3'== cp[0] && '2'==cp[1]) {
cp += 2;
- input_f = UTF32_INPUT;
input_endian = ENDIAN_BIG;
+ enc_idx = UTF_32;
} else {
- input_f = UTF8_INPUT;
+ input_encoding = nkf_enc_from_index(UTF_8);
continue;
}
if (cp[0]=='L') {
input_endian = ENDIAN_LITTLE;
} else if (cp[0] == 'B') {
cp++;
+ input_endian = ENDIAN_BIG;
}
+ enc_idx = enc_idx == UTF_16
+ ? (output_endian == ENDIAN_LITTLE ? UTF_16LE : UTF_16BE)
+ : (output_endian == ENDIAN_LITTLE ? UTF_32LE : UTF_32BE);
+ input_encoding = nkf_enc_from_index(enc_idx);
}
continue;
#endif
/* Input code assumption */
- case 'J': /* JIS input */
- input_f = JIS_INPUT;
- continue;
- case 'E': /* AT&T EUC input */
- input_f = EUC_INPUT;
- continue;
- case 'S': /* MS Kanji input */
- input_f = SJIS_INPUT;
- if (x0201_f==NO_X0201) x0201_f=TRUE;
- continue;
+ case 'J': /* ISO-2022-JP input */
+ input_encoding = nkf_enc_from_index(ISO_2022_JP);
+ continue;
+ case 'E': /* EUC-JP input */
+ input_encoding = nkf_enc_from_index(EUC_JP);
+ continue;
+ case 'S': /* Windows-31J input */
+ input_encoding = nkf_enc_from_index(WINDOWS_31J);
+ continue;
case 'Z': /* Convert X0208 alphabet to asii */
/* alpha_f
bit:0 Convert JIS X 0208 Alphabet to ASCII
ESC-(-I in JIS, EUC, MS Kanji
SI/SO in JIS, EUC, MS Kanji
SSO in EUC, JIS, not in MS Kanji
- MS Kanji (0xa0-0xdf)
+ MS Kanji (0xa0-0xdf)
output X0201
ESC-(-I in JIS (0x20-0x5f)
SSO in EUC (0xa0-0xdf)
- 0xa0-0xd in MS Kanji (0xa0-0xdf)
+ 0xa0-0xd in MS Kanji (0xa0-0xdf)
*/
continue;
- case 'X': /* Assume X0201 kana */
- /* Default value is NO_X0201 for EUC/MS-Kanji mix */
+ case 'X': /* Convert X0201 kana to X0208 */
x0201_f = TRUE;
continue;
case 'F': /* prserve new lines */
fold_len *= 10;
fold_len += *cp++ - '0';
}
- if (!(0<fold_len && fold_len<BUFSIZ))
+ if (!(0<fold_len && fold_len<BUFSIZ))
fold_len = DEFAULT_FOLD;
if (*cp=='-') {
fold_margin = 0;
} else if (*cp=='0') {
mime_decode_f = FALSE;
mime_f = FALSE; cp++;
+ } else {
+ mime_f = STRICT_MIME;
}
continue;
case 'M': /* MIME output */
bit:1 allow any x on ESC-(-x or ESC-$-x
bit:2 reset to ascii on NL
*/
- if ('9'>= *cp && *cp>='0')
+ if ('9'>= *cp && *cp>='0')
broken_f |= 1<<(*cp++ -'0');
- else
+ else
broken_f |= TRUE;
continue;
#ifndef PERL_XS
continue;
#endif
case 'c':/* add cr code */
- crmode_f = CRLF;
+ nlmode_f = CRLF;
continue;
case 'd':/* delete cr code */
- crmode_f = NL;
- continue;
- case 'I': /* ISO-2022-JP output */
- iso2022jp_f = TRUE;
+ nlmode_f = LF;
continue;
+ case 'I': /* ISO-2022-JP output */
+ iso2022jp_f = TRUE;
+ continue;
case 'L': /* line mode */
if (*cp=='u') { /* unix */
- crmode_f = NL; cp++;
+ nlmode_f = LF; cp++;
} else if (*cp=='m') { /* mac */
- crmode_f = CR; cp++;
+ nlmode_f = CR; cp++;
} else if (*cp=='w') { /* windows */
- crmode_f = CRLF; cp++;
+ nlmode_f = CRLF; cp++;
} else if (*cp=='0') { /* no conversion */
- crmode_f = 0; cp++;
+ nlmode_f = 0; cp++;
}
continue;
- case 'g':
#ifndef PERL_XS
- guess_f = TRUE;
-#endif
+ case 'g':
+ if ('2' <= *cp && *cp <= '9') {
+ guess_f = 2;
+ cp++;
+ } else if (*cp == '0' || *cp == '1') {
+ guess_f = 1;
+ cp++;
+ } else {
+ guess_f = 1;
+ }
continue;
- case ' ':
+#endif
+ case SP:
/* module muliple options in a string are allowed for Perl moudle */
while(*cp && *cp++!='-');
continue;
default:
+ fprintf(stderr, "unknown option: -%c\n", *(cp-1));
/* bogus option but ignored */
continue;
}
void set_iconv(nkf_char f, nkf_char (*iconv_func)(nkf_char c2,nkf_char c1,nkf_char c0))
{
#ifdef INPUT_CODE_FIX
- if (f || !input_f)
+ if (f || !input_encoding)
#endif
if (estab_f != f){
estab_f = f;
if (iconv_func
#ifdef INPUT_CODE_FIX
- && (f == -TRUE || !input_f) /* -TRUE means "FORCE" */
+ && (f == -TRUE || !input_encoding) /* -TRUE means "FORCE" */
#endif
){
iconv = iconv_func;
struct input_code *p = find_inputcode_byfunc(iconv);
if (p){
set_input_codename(p->name);
- debug(input_codename);
+ debug(p->name);
}
iconv_for_check = iconv;
}
#define SCORE_L2 (1) /* \e$BBh\e(B2\e$B?e=`4A;z\e(B */
#define SCORE_KANA (SCORE_L2 << 1) /* \e$B$$$o$f$kH>3Q%+%J\e(B */
#define SCORE_DEPEND (SCORE_KANA << 1) /* \e$B5!<o0MB8J8;z\e(B */
-#ifdef SHIFTJIS_CP932
-#define SCORE_CP932 (SCORE_DEPEND << 1) /* CP932 \e$B$K$h$kFI$_49$(\e(B */
-#define SCORE_NO_EXIST (SCORE_CP932 << 1) /* \e$BB8:_$7$J$$J8;z\e(B */
-#else
-#define SCORE_NO_EXIST (SCORE_DEPEND << 1) /* \e$BB8:_$7$J$$J8;z\e(B */
-#endif
+#define SCORE_CP932 (SCORE_DEPEND << 1) /* CP932 \e$B$K$h$kFI$_49$(\e(B (IBM extended characters) */
+#define SCORE_X0212 (SCORE_CP932 << 1) /* JIS X 0212 */
+#define SCORE_NO_EXIST (SCORE_X0212 << 1) /* \e$BB8:_$7$J$$J8;z\e(B */
#define SCORE_iMIME (SCORE_NO_EXIST << 1) /* MIME \e$B$K$h$k;XDj\e(B */
#define SCORE_ERROR (SCORE_iMIME << 1) /* \e$B%(%i!<\e(B */
static const char score_table_F0[] = {
SCORE_L2, SCORE_L2, SCORE_L2, SCORE_L2,
SCORE_L2, SCORE_DEPEND, SCORE_NO_EXIST, SCORE_NO_EXIST,
- SCORE_DEPEND, SCORE_DEPEND, SCORE_DEPEND, SCORE_DEPEND,
- SCORE_DEPEND, SCORE_NO_EXIST, SCORE_NO_EXIST, SCORE_ERROR,
+ SCORE_DEPEND, SCORE_DEPEND, SCORE_CP932, SCORE_CP932,
+ SCORE_CP932, SCORE_NO_EXIST, SCORE_NO_EXIST, SCORE_ERROR,
};
void set_code_score(struct input_code *ptr, nkf_char score)
set_code_score(ptr, SCORE_ERROR);
}else if (c2 == SSO){
set_code_score(ptr, SCORE_KANA);
+ }else if (c2 == 0x8f){
+ set_code_score(ptr, SCORE_X0212);
#ifdef UTF8_OUTPUT_ENABLE
}else if (!e2w_conv(c2, c1)){
set_code_score(ptr, SCORE_NO_EXIST);
status_push_ch(ptr, c);
code_score(ptr);
status_clear(ptr);
- }else if ((0x81 <= c && c < 0xa0) || (0xe0 <= c && c <= 0xef)){
+ }else if ((0x81 <= c && c < 0xa0) || (0xe0 <= c && c <= 0xea)){
ptr->stat = 1;
status_push_ch(ptr, c);
+ }else if (0xed <= c && c <= 0xee){
+ ptr->stat = 3;
+ status_push_ch(ptr, c);
#ifdef SHIFTJIS_CP932
- }else if (cp51932_f
- && is_ibmext_in_sjis(c)){
+ }else if (is_ibmext_in_sjis(c)){
ptr->stat = 2;
status_push_ch(ptr, c);
#endif /* SHIFTJIS_CP932 */
#ifdef X0212_ENABLE
- }else if (x0212_f && 0xf0 <= c && c <= 0xfc){
+ }else if (0xf0 <= c && c <= 0xfc){
ptr->stat = 1;
status_push_ch(ptr, c);
#endif /* X0212_ENABLE */
break;
case 2:
#ifdef SHIFTJIS_CP932
+ if ((0x40 <= c && c <= 0x7e) || (0x80 <= c && c <= 0xfc)) {
+ status_push_ch(ptr, c);
+ if (s2e_conv(ptr->buf[0], ptr->buf[1], &ptr->buf[0], &ptr->buf[1]) == 0) {
+ set_code_score(ptr, SCORE_CP932);
+ status_clear(ptr);
+ break;
+ }
+ }
+#endif /* SHIFTJIS_CP932 */
+ status_disable(ptr);
+ break;
+ case 3:
if ((0x40 <= c && c <= 0x7e) || (0x80 <= c && c <= 0xfc)){
status_push_ch(ptr, c);
- if (s2e_conv(ptr->buf[0], ptr->buf[1], &ptr->buf[0], &ptr->buf[1]) == 0){
- set_code_score(ptr, SCORE_CP932);
- status_clear(ptr);
- break;
- }
+ s2e_conv(ptr->buf[0], ptr->buf[1], &ptr->buf[0], &ptr->buf[1]);
+ set_code_score(ptr, SCORE_CP932);
+ status_clear(ptr);
+ }else{
+ status_disable(ptr);
}
-#endif /* SHIFTJIS_CP932 */
-#ifndef X0212_ENABLE
- status_disable(ptr);
-#endif
break;
}
}
void module_connection(void)
{
- oconv = output_conv;
+ if (input_encoding) set_input_encoding(input_encoding);
+ if (!output_encoding) {
+ output_encoding = nkf_default_encoding();
+ }
+ set_output_encoding(output_encoding);
+ oconv = nkf_enc_to_oconv(output_encoding);
o_putc = std_putc;
/* replace continucation module, from output side */
/* base64_count = 0; */
}
- if (crmode_f) {
- o_crconv = oconv; oconv = cr_conv;
+ if (nlmode_f || guess_f) {
+ o_nlconv = oconv; oconv = nl_conv;
}
if (rot_f) {
o_rot_conv = oconv; oconv = rot_conv;
}
#endif
#ifdef UNICODE_NORMALIZATION
- if (nfc_f && input_f == UTF8_INPUT){
+ if (nfc_f){
i_nfc_getc = i_getc; i_getc = nfc_getc;
i_nfc_ungetc = i_ungetc; i_ungetc= nfc_ungetc;
}
i_bgetc = i_getc; i_getc = broken_getc;
i_bungetc = i_ungetc; i_ungetc = broken_ungetc;
}
- if (input_f == JIS_INPUT || input_f == EUC_INPUT || input_f == LATIN1_INPUT) {
- set_iconv(-TRUE, e_iconv);
- } else if (input_f == SJIS_INPUT) {
- set_iconv(-TRUE, s_iconv);
-#ifdef UTF8_INPUT_ENABLE
- } else if (input_f == UTF8_INPUT) {
- set_iconv(-TRUE, w_iconv);
- } else if (input_f == UTF16_INPUT) {
- set_iconv(-TRUE, w_iconv16);
- } else if (input_f == UTF32_INPUT) {
- set_iconv(-TRUE, w_iconv32);
-#endif
+ if (input_encoding) {
+ set_iconv(-TRUE, nkf_enc_to_iconv(input_encoding));
} else {
set_iconv(FALSE, e_iconv);
}
if((c2 = (*i_getc)(f)) == 0x00){
if((c2 = (*i_getc)(f)) == 0xFE){
if((c2 = (*i_getc)(f)) == 0xFF){
- if(!input_f){
+ if(!input_encoding){
set_iconv(TRUE, w_iconv32);
}
if (iconv == w_iconv32) {
(*i_ungetc)(0xFE,f);
}else if(c2 == 0xFF){
if((c2 = (*i_getc)(f)) == 0xFE){
- if(!input_f){
+ if(!input_encoding){
set_iconv(TRUE, w_iconv32);
}
if (iconv == w_iconv32) {
case 0xEF:
if((c2 = (*i_getc)(f)) == 0xBB){
if((c2 = (*i_getc)(f)) == 0xBF){
- if(!input_f){
+ if(!input_encoding){
set_iconv(TRUE, w_iconv);
}
if (iconv == w_iconv) {
if((c2 = (*i_getc)(f)) == 0xFF){
if((c2 = (*i_getc)(f)) == 0x00){
if((c2 = (*i_getc)(f)) == 0x00){
- if(!input_f){
+ if(!input_encoding){
set_iconv(TRUE, w_iconv32);
}
if (iconv == w_iconv32) {
}else (*i_ungetc)(c2,f);
(*i_ungetc)(0x00,f);
}else (*i_ungetc)(c2,f);
- if(!input_f){
+ if(!input_encoding){
set_iconv(TRUE, w_iconv16);
}
if (iconv == w_iconv16) {
if((c2 = (*i_getc)(f)) == 0xFE){
if((c2 = (*i_getc)(f)) == 0x00){
if((c2 = (*i_getc)(f)) == 0x00){
- if(!input_f){
+ if(!input_encoding){
set_iconv(TRUE, w_iconv32);
}
if (iconv == w_iconv32) {
}else (*i_ungetc)(c2,f);
(*i_ungetc)(0x00,f);
}else (*i_ungetc)(c2,f);
- if(!input_f){
+ if(!input_encoding){
set_iconv(TRUE, w_iconv16);
}
if (iconv == w_iconv16) {
}
/*
- Conversion main loop. Code detection only.
+ Conversion main loop. Code detection only.
*/
nkf_char kanji_convert(FILE *f)
nkf_char c3, c2=0, c1, c0=0;
int is_8bit = FALSE;
- if(input_f == SJIS_INPUT || input_f == EUC_INPUT
-#ifdef UTF8_INPUT_ENABLE
- || input_f == UTF8_INPUT || input_f == UTF16_INPUT
-#endif
- ){
+ if (input_encoding && !nkf_enc_asciicompat(input_encoding)) {
is_8bit = TRUE;
}
while ((c1 = (*i_getc)(f)) != EOF) {
#ifdef INPUT_CODE_FIX
- if (!input_f)
+ if (!input_encoding)
#endif
code_status(c1);
if (c2) {
/* second byte */
- if (c2 > ((input_f == JIS_INPUT && ms_ucs_map_f) ? 0x92 : DEL)) {
+ if (c2 > ((input_encoding && nkf_enc_cp5022x_p(input_encoding)) ? 0x92 : DEL)) {
/* in case of 8th bit is on */
if (!estab_f&&!mime_decode_mode) {
/* in case of not established yet */
/* It is still ambiguious */
- if (h_conv(f, c2, c1)==EOF)
+ if (h_conv(f, c2, c1)==EOF)
LAST;
- else
+ else
c2 = 0;
NEXT;
} else {
} else
/* second byte, 7 bit code */
/* it might be kanji shitfted */
- if ((c1 == DEL) || (c1 <= SPACE)) {
+ if ((c1 == DEL) || (c1 <= SP)) {
/* ignore bogus first code */
c2 = 0;
NEXT;
SEND;
} else
#endif
- if (c1 > ((input_f == JIS_INPUT && ms_ucs_map_f) ? 0x92 : DEL)) {
+ if (c1 > ((input_encoding && nkf_enc_cp5022x_p(input_encoding)) ? 0x92 : DEL)) {
/* 8 bit code */
if (!estab_f && !iso8859_f) {
/* not established yet */
NEXT;
} else { /* estab_f==TRUE */
if (iso8859_f) {
- c2 = ISO8859_1;
+ c2 = ISO_8859_1;
c1 &= 0x7f;
SEND;
} else if (SSP<=c1 && c1<0xe0 && iconv == s_iconv) {
/* SJIS X0201 Case... */
- if(iso2022jp_f && x0201_f==NO_X0201) {
+ if (iso2022jp_f && !x0201_f) {
(*oconv)(GETA1, GETA2);
NEXT;
} else {
- c2 = X0201;
+ c2 = JIS_X_0201;
c1 &= 0x7f;
SEND;
}
c1 = (*i_getc)(f); /* skip SSO */
code_status(c1);
if (SSP<=c1 && c1<0xe0) {
- if(iso2022jp_f && x0201_f==NO_X0201) {
+ if (iso2022jp_f && !x0201_f) {
(*oconv)(GETA1, GETA2);
NEXT;
} else {
- c2 = X0201;
+ c2 = JIS_X_0201;
c1 &= 0x7f;
SEND;
}
} else if (ms_ucs_map_f == UCS_MAP_CP10001 &&
(c1 == 0xFD || c1 == 0xFE)) {
/* CP10001 */
- c2 = X0201;
+ c2 = JIS_X_0201;
c1 &= 0x7f;
SEND;
} else {
NEXT;
}
}
- } else if ((c1 > SPACE) && (c1 != DEL)) {
+ } else if ((c1 > SP) && (c1 != DEL)) {
/* in case of Roman characters */
- if (shift_mode) {
+ if (shift_mode) {
/* output 1 shifted byte */
if (iso8859_f) {
- c2 = ISO8859_1;
+ c2 = ISO_8859_1;
SEND;
- } else if (SPACE<=c1 && c1<(0xe0&0x7f) ){
+ } else if (SP <= c1 && c1 < (0xe0&0x7f)){
/* output 1 shifted byte */
- if(iso2022jp_f && x0201_f==NO_X0201) {
+ if (iso2022jp_f && !x0201_f) {
(*oconv)(GETA1, GETA2);
NEXT;
} else {
- c2 = X0201;
+ c2 = JIS_X_0201;
SEND;
}
} else {
/* look like bogus code */
NEXT;
}
- } else if (input_mode == X0208 || input_mode == X0212 ||
- input_mode == X0213_1 || input_mode == X0213_2) {
+ } else if (input_mode == JIS_X_0208 || input_mode == JIS_X_0212 ||
+ input_mode == JIS_X_0213_1 || input_mode == JIS_X_0213_2) {
/* in case of Kanji shifted */
c2 = c1;
NEXT;
- } else if (c1 == '=' && mime_f && !mime_decode_mode ) {
+ } else if (c1 == '=' && mime_f && !mime_decode_mode) {
/* Check MIME code */
if ((c1 = (*i_getc)(f)) == EOF) {
(*oconv)(0, '=');
/* =? is mime conversion start sequence */
if(mime_f == STRICT_MIME) {
/* check in real detail */
- if (mime_begin_strict(f) == EOF)
+ if (mime_begin_strict(f) == EOF)
LAST;
else
NEXT;
- } else if (mime_begin(f) == EOF)
+ } else if (mime_begin(f) == EOF)
LAST;
else
NEXT;
NEXT;
}
} else {
- /* normal ASCII code */
+ /* normal ASCII code */
SEND;
}
- } else if (c1 == SI && (!is_8bit || mime_decode_mode)) {\r
- shift_mode = FALSE;
+ } else if (c1 == SI && (!is_8bit || mime_decode_mode)) {
+ shift_mode = FALSE;
NEXT;
- } else if (c1 == SO && (!is_8bit || mime_decode_mode)) {\r
- shift_mode = TRUE;
+ } else if (c1 == SO && (!is_8bit || mime_decode_mode)) {
+ shift_mode = TRUE;
NEXT;
- } else if (c1 == ESC && (!is_8bit || mime_decode_mode)) {\r
+ } else if (c1 == ESC && (!is_8bit || mime_decode_mode)) {
if ((c1 = (*i_getc)(f)) == EOF) {
/* (*oconv)(0, ESC); don't send bogus code */
LAST;
} else if (c1 == '$') {
if ((c1 = (*i_getc)(f)) == EOF) {
/*
- (*oconv)(0, ESC); don't send bogus code
+ (*oconv)(0, ESC); don't send bogus code
(*oconv)(0, '$'); */
LAST;
} else if (c1 == '@'|| c1 == 'B') {
/* This is kanji introduction */
- input_mode = X0208;
+ input_mode = JIS_X_0208;
shift_mode = FALSE;
set_input_codename("ISO-2022-JP");
#ifdef CHECK_OPTION
- debug(input_codename);
+ debug("ISO-2022-JP");
#endif
NEXT;
} else if (c1 == '(') {
if ((c1 = (*i_getc)(f)) == EOF) {
- /* don't send bogus code
+ /* don't send bogus code
(*oconv)(0, ESC);
(*oconv)(0, '$');
(*oconv)(0, '(');
LAST;
} else if (c1 == '@'|| c1 == 'B') {
/* This is kanji introduction */
- input_mode = X0208;
+ input_mode = JIS_X_0208;
shift_mode = FALSE;
NEXT;
#ifdef X0212_ENABLE
} else if (c1 == 'D'){
- input_mode = X0212;
+ input_mode = JIS_X_0212;
shift_mode = FALSE;
NEXT;
#endif /* X0212_ENABLE */
- } else if (c1 == (X0213_1&0x7F)){
- input_mode = X0213_1;
+ } else if (c1 == 0x4F){
+ input_mode = JIS_X_0213_1;
shift_mode = FALSE;
NEXT;
- } else if (c1 == (X0213_2&0x7F)){
- input_mode = X0213_2;
+ } else if (c1 == 0x50){
+ input_mode = JIS_X_0213_2;
shift_mode = FALSE;
NEXT;
} else {
}
} else if (broken_f&0x2) {
/* accept any ESC-(-x as broken code ... */
- input_mode = X0208;
+ input_mode = JIS_X_0208;
shift_mode = FALSE;
NEXT;
} else {
}
} else if (c1 == '(') {
if ((c1 = (*i_getc)(f)) == EOF) {
- /* don't send bogus code
+ /* don't send bogus code
(*oconv)(0, ESC);
(*oconv)(0, '('); */
LAST;
} else {
if (c1 == 'I') {
/* This is X0201 kana introduction */
- input_mode = X0201; shift_mode = X0201;
+ input_mode = JIS_X_0201; shift_mode = JIS_X_0201;
NEXT;
} else if (c1 == 'B' || c1 == 'J' || c1 == 'H') {
/* This is X0208 kanji introduction */
SEND;
}
}
- } else if ( c1 == 'N' || c1 == 'n' ){
+ } else if ( c1 == 'N' || c1 == 'n'){
/* SS2 */
c3 = (*i_getc)(f); /* skip SS2 */
- if ( (SPACE<=c3 && c3 < 0x60) || (0xa0<=c3 && c3 < 0xe0)){
+ if ( (SP<=c3 && c3 < 0x60) || (0xa0<=c3 && c3 < 0xe0)){
c1 = c3;
- c2 = X0201;
+ c2 = JIS_X_0201;
SEND;
}else{
(*i_ungetc)(c3, f);
/* J-PHONE emoji */
if ((c1 = (*i_getc)(f)) == EOF) {
/*
- (*oconv)(0, ESC); don't send bogus code
+ (*oconv)(0, ESC); don't send bogus code
(*oconv)(0, '$'); */
LAST;
} else {
NUM : 2 0 3 4 5 X 1
*/
static const char jphone_emoji_first_table[7] = {2, 0, 3, 4, 5, 0, 1};
- c0 = (jphone_emoji_first_table[c1 % 7] << 8) - SPACE + 0xE000 + CLASS_UNICODE;
+ c0 = (jphone_emoji_first_table[c1 % 7] << 8) - SP + 0xE000 + CLASS_UNICODE;
while ((c1 = (*i_getc)(f)) != EOF) {
- if (SPACE <= c1 && c1 <= 'z') {
+ if (SP <= c1 && c1 <= 'z') {
(*oconv)(0, c1 + c0);
} else break; /* c1 == SO */
}
(*oconv)(0, ESC);
SEND;
}
- } else if (c1 == NL || c1 == CR) {
+ } else if (c1 == LF || c1 == CR) {
if (broken_f&4) {
input_mode = ASCII; set_iconv(FALSE, 0);
SEND;
} else if (mime_decode_f && !mime_decode_mode){
- if (c1 == NL) {
- if ((c1=(*i_getc)(f))!=EOF && c1 == SPACE) {
- i_ungetc(SPACE,f);
+ if (c1 == LF) {
+ if ((c1=(*i_getc)(f))!=EOF && c1 == SP) {
+ i_ungetc(SP,f);
continue;
} else {
i_ungetc(c1,f);
}
- c1 = NL;
+ c1 = LF;
SEND;
} else { /* if (c1 == CR)*/
if ((c1=(*i_getc)(f))!=EOF) {
- if (c1==SPACE) {
- i_ungetc(SPACE,f);
+ if (c1==SP) {
+ i_ungetc(SP,f);
continue;
- } else if (c1 == NL && (c1=(*i_getc)(f))!=EOF && c1 == SPACE) {
- i_ungetc(SPACE,f);
+ } else if (c1 == LF && (c1=(*i_getc)(f))!=EOF && c1 == SP) {
+ i_ungetc(SP,f);
continue;
} else {
i_ungetc(c1,f);
}
- i_ungetc(NL,f);
+ i_ungetc(LF,f);
} else {
i_ungetc(c1,f);
}
SEND;
}
}
- if (!crmode_f) {
- if (prev_cr && c1 == NL) crmode_f = CRLF;
- else crmode_f = c1;
- }
- } else if (c1 == DEL && input_mode == X0208 ) {
+ } else if (c1 == DEL && input_mode == JIS_X_0208) {
/* CP5022x */
c2 = c1;
NEXT;
- } else
+ } else
SEND;
}
/* send: */
break;
}
break;
- case X0208:
- case X0213_1:
+ case JIS_X_0208:
+ case JIS_X_0213_1:
if (ms_ucs_map_f &&
0x7F <= c2 && c2 <= 0x92 &&
0x21 <= c1 && c1 <= 0x7E) {
(*oconv)(c2, c1); /* this is JIS, not SJIS/EUC case */
break;
#ifdef X0212_ENABLE
- case X0212:
+ case JIS_X_0212:
(*oconv)(PREFIX_EUCG3 | c2, c1);
break;
#endif /* X0212_ENABLE */
- case X0213_2:
+ case JIS_X_0213_2:
(*oconv)(PREFIX_EUCG3 | c2, c1);
break;
default:
/* epilogue */
(*iconv)(EOF, 0, 0);
- if (!is_inputcode_set)
+ if (!input_codename)
{
if (is_8bit) {
struct input_code *p = input_code_list;
++p;
}
set_input_codename(result->name);
+#ifdef CHECK_OPTION
+ debug(result->name);
+#endif
}
}
return 1;
(*iconv)(0, c2, 0);
continue;
}else if (iconv == s_iconv && 0xa1 <= c2 && c2 <= 0xdf){
- (*iconv)(X0201, c2, 0);
+ (*iconv)(JIS_X_0201, c2, 0);
continue;
}
if (hold_index < hold_count){
if (0x9E < c1) c2++;
}
}else{
+#define SJ0162 0x00e1 /* 01 - 62 ku offset */
+#define SJ6394 0x0161 /* 63 - 94 ku offset */
c2 = c2 + c2 - ((c2 <= 0x9F) ? SJ0162 : SJ6394);
if (0x9E < c1) c2++;
}
if (c1 < 0x9F)
- c1 = c1 - ((c1 > DEL) ? SPACE : 0x1F);
+ c1 = c1 - ((c1 > DEL) ? SP : 0x1F);
else {
c1 = c1 - 0x7E;
}
nkf_char s_iconv(nkf_char c2, nkf_char c1, nkf_char c0)
{
- if (c2 == X0201) {
+ if (c2 == JIS_X_0201) {
c1 &= 0x7f;
- } else if ((c2 == EOF) || (c2 == 0) || c2 < SPACE) {
+ } else if ((c2 == EOF) || (c2 == 0) || c2 < SP) {
/* NOP */
} else if (!x0213_f && 0xF0 <= c2 && c2 <= 0xF9 && 0x40 <= c1 && c1 <= 0xFC) {
/* CP932 UDC */
nkf_char e_iconv(nkf_char c2, nkf_char c1, nkf_char c0)
{
- if (c2 == X0201) {
+ if (c2 == JIS_X_0201) {
c1 &= 0x7f;
#ifdef X0212_ENABLE
}else if (c2 == 0x8f){
}
#endif /* X0212_ENABLE */
} else if (c2 == SSO){
- c2 = X0201;
+ c2 = JIS_X_0201;
c1 &= 0x7f;
- } else if ((c2 == EOF) || (c2 == 0) || c2 < SPACE) {
+ } else if ((c2 == EOF) || (c2 == 0) || c2 < SP) {
/* NOP */
} else {
if (!cp51932_f && ms_ucs_map_f && 0xF5 <= c2 && c2 <= 0xFE && 0xA1 <= c1 && c1 <= 0xFE) {
21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21,
30, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 32, 33, 33,
40, 41, 41, 41, 42, 43, 43, 43, 50, 50, 50, 50, 60, 60, 70, 70};
-
+
if (c2 < 0 || 0xff < c2) {
}else if (c2 == 0) { /* 0 : 1 byte*/
c0 = 0;
c2 &= 0x7f;
c2 |= PREFIX_EUCG3;
}
- if (c2 == SO) c2 = X0201;
+ if (c2 == SO) c2 = JIS_X_0201;
c1 = val & 0x7f;
if (p2) *p2 = c2;
if (p1) *p1 = c1;
{
const unsigned short *p;
- if (c2 == X0201) {
+ if (c2 == JIS_X_0201) {
if (ms_ucs_map_f == UCS_MAP_CP10001) {
switch (c1) {
case 0x20:
}
#endif
- if (c2 == 0) {
+ if (c2 == 0) {
output_mode = ASCII;
(*o_putc)(c1);
- } else if (c2 == ISO8859_1) {
- output_mode = ISO8859_1;
+ } else if (c2 == ISO_8859_1) {
+ output_mode = UTF_8;
(*o_putc)(c1 | 0x080);
} else {
- output_mode = UTF8;
+ output_mode = UTF_8;
val = e2w_conv(c2, c1);
if (val){
w16w_conv(val, &c2, &c1, &c0);
return;
}
- if (c2 == ISO8859_1) {
+ if (c2 == ISO_8859_1) {
c2 = 0;
c1 |= 0x80;
#ifdef NUMCHAR_OPTION
return;
}
- if (c2 == ISO8859_1) {
+ if (c2 == ISO_8859_1) {
c1 |= 0x80;
#ifdef NUMCHAR_OPTION
} else if (c2 == 0 && is_unicode_capsule(c1)) {
if (c2 == EOF) {
(*o_putc)(EOF);
return;
- } else if (c2 == 0) {
+ } else if (c2 == 0) {
output_mode = ASCII;
(*o_putc)(c1);
- } else if (c2 == X0201) {
- output_mode = JAPANESE_EUC;
+ } else if (c2 == JIS_X_0201) {
+ output_mode = EUC_JP;
(*o_putc)(SSO); (*o_putc)(c1|0x80);
- } else if (c2 == ISO8859_1) {
- output_mode = ISO8859_1;
+ } else if (c2 == ISO_8859_1) {
+ output_mode = ISO_8859_1;
(*o_putc)(c1 | 0x080);
#ifdef X0212_ENABLE
} else if (is_eucg3(c2)){
- output_mode = JAPANESE_EUC;
+ output_mode = EUC_JP;
#ifdef SHIFTJIS_CP932
if (!cp932inv_f){
nkf_char s2, s1;
set_iconv(FALSE, 0);
return; /* too late to rescue this char */
}
- output_mode = JAPANESE_EUC;
+ output_mode = EUC_JP;
(*o_putc)(c2 | 0x080);
(*o_putc)(c1 | 0x080);
}
if (!x0213_f && 0xE000 <= c2 && c2 <= 0xE757) {
/* CP932 UDC */
c1 &= 0xFFF;
- c2 = c1 / 188 + 0xF0;
+ c2 = c1 / 188 + (cp932inv_f ? 0xF0 : 0xEB);
c1 = c1 % 188;
c1 += 0x40 + (c1 > 0x3e);
(*o_putc)(c2);
} else if (c2 == 0) {
output_mode = ASCII;
(*o_putc)(c1);
- } else if (c2 == X0201) {
+ } else if (c2 == JIS_X_0201) {
output_mode = SHIFT_JIS;
(*o_putc)(c1|0x80);
- } else if (c2 == ISO8859_1) {
- output_mode = ISO8859_1;
+ } else if (c2 == ISO_8859_1) {
+ output_mode = ISO_8859_1;
(*o_putc)(c1 | 0x080);
#ifdef X0212_ENABLE
} else if (is_eucg3(c2)){
}
#endif
if (c2 == EOF) {
- if (output_mode !=ASCII && output_mode!=ISO8859_1) {
+ if (output_mode !=ASCII && output_mode!=ISO_8859_1) {
(*o_putc)(ESC);
(*o_putc)('(');
(*o_putc)(ascii_intro);
#ifdef X0212_ENABLE
} else if (is_eucg3(c2)){
if(x0213_f){
- if(output_mode!=X0213_2){
- output_mode = X0213_2;
+ if(output_mode!=JIS_X_0213_2){
+ output_mode = JIS_X_0213_2;
(*o_putc)(ESC);
(*o_putc)('$');
(*o_putc)('(');
- (*o_putc)(X0213_2&0x7F);
+ (*o_putc)(0x50);
}
}else{
- if(output_mode!=X0212){
- output_mode = X0212;
+ if(output_mode!=JIS_X_0212){
+ output_mode = JIS_X_0212;
(*o_putc)(ESC);
(*o_putc)('$');
(*o_putc)('(');
- (*o_putc)(X0212&0x7F);
+ (*o_putc)(0x44);
}
}
(*o_putc)(c2 & 0x7f);
(*o_putc)(c1);
#endif
- } else if (c2==X0201) {
- if (output_mode!=X0201) {
- output_mode = X0201;
+ } else if (c2==JIS_X_0201) {
+ if (output_mode!=JIS_X_0201) {
+ output_mode = JIS_X_0201;
(*o_putc)(ESC);
(*o_putc)('(');
(*o_putc)('I');
}
(*o_putc)(c1);
- } else if (c2==ISO8859_1) {
+ } else if (c2==ISO_8859_1) {
/* iso8859 introduction, or 8th bit on */
- /* Can we convert in 7bit form using ESC-'-'-A ?
+ /* Can we convert in 7bit form using ESC-'-'-A ?
Is this popular? */
- output_mode = ISO8859_1;
+ output_mode = ISO_8859_1;
(*o_putc)(c1|0x80);
} else if (c2 == 0) {
- if (output_mode !=ASCII && output_mode!=ISO8859_1) {
+ if (output_mode !=ASCII && output_mode!=ISO_8859_1) {
(*o_putc)(ESC);
(*o_putc)('(');
(*o_putc)(ascii_intro);
? c2<0x20 || 0x92<c2 || c1<0x20 || 0x7e<c1
: c2<0x20 || 0x7e<c2 || c1<0x20 || 0x7e<c1) return;
if(x0213_f){
- if (output_mode!=X0213_1) {
- output_mode = X0213_1;
+ if (output_mode!=JIS_X_0213_1) {
+ output_mode = JIS_X_0213_1;
(*o_putc)(ESC);
(*o_putc)('$');
(*o_putc)('(');
- (*o_putc)(X0213_1&0x7F);
+ (*o_putc)(0x4F);
}
- }else if (output_mode != X0208) {
- output_mode = X0208;
+ }else if (output_mode != JIS_X_0208) {
+ output_mode = JIS_X_0208;
(*o_putc)(ESC);
(*o_putc)('$');
(*o_putc)(kanji_intro);
return broken_buf[--broken_counter];
}
c= (*i_bgetc)(f);
- if (c=='$' && broken_last != ESC
- && (input_mode==ASCII || input_mode==X0201)) {
+ if (c=='$' && broken_last != ESC
+ && (input_mode==ASCII || input_mode==JIS_X_0201)) {
c1= (*i_bgetc)(f);
broken_last = 0;
if (c1=='@'|| c1=='B') {
- broken_buf[0]=c1; broken_buf[1]=c;
+ broken_buf[0]=c1; broken_buf[1]=c;
broken_counter=2;
return ESC;
} else {
(*i_bungetc)(c1,f);
return c;
}
- } else if (c=='(' && broken_last != ESC
- && (input_mode==X0208 || input_mode==X0201)) { /* ) */
+ } else if (c=='(' && broken_last != ESC
+ && (input_mode==JIS_X_0208 || input_mode==JIS_X_0201)) { /* ) */
c1= (*i_bgetc)(f);
broken_last = 0;
if (c1=='J'|| c1=='B') {
return c;
}
-void cr_conv(nkf_char c2, nkf_char c1)
+void nl_conv(nkf_char c2, nkf_char c1)
{
- if (prev_cr) {
+ if (guess_f && input_newline != EOF) {
+ if (c2 == 0 && c1 == LF) {
+ if (!input_newline) input_newline = prev_cr ? CRLF : LF;
+ else if (input_newline != (prev_cr ? CRLF : LF)) input_newline = EOF;
+ } else if (c2 == 0 && c1 == CR && input_newline == LF) input_newline = EOF;
+ else if (!prev_cr);
+ else if (!input_newline) input_newline = CR;
+ else if (input_newline != CR) input_newline = EOF;
+ }
+ if (prev_cr || (c2 == 0 && c1 == LF)) {
prev_cr = 0;
- if (! (c2==0&&c1==NL) ) {
- cr_conv(0,'\n');
- }
- }
- if (c2) {
- (*o_crconv)(c2,c1);
- } else if (c1=='\r') {
- prev_cr = c1;
- } else if (c1=='\n') {
- if (crmode_f==CRLF) {
- (*o_crconv)(0,'\r');
- } else if (crmode_f==CR) {
- (*o_crconv)(0,'\r');
- return;
- }
- (*o_crconv)(0,NL);
- } else if (c1!='\032' || crmode_f!=NL){
- (*o_crconv)(c2,c1);
+ if (nlmode_f != LF) (*o_nlconv)(0, CR);
+ if (nlmode_f != CR) (*o_nlconv)(0, LF);
}
+ if (c2 == 0 && c1 == CR) prev_cr = CR;
+ else if (c2 != 0 || c1 != LF) (*o_nlconv)(c2, c1);
}
-/*
+/*
Return value of fold_conv()
- \n add newline and output char
- \r add newline and output nothing
- ' ' space
- 0 skip
- 1 (or else) normal output
+ LF add newline and output char
+ CR add newline and output nothing
+ SP space
+ 0 skip
+ 1 (or else) normal output
fold state in prev (previous character)
>0x80 Japanese (X0208/X0201)
<0x80 ASCII
- \n new line
- ' ' space
+ LF new line
+ SP space
This fold algorthm does not preserve heading space in a line.
This is the main difference from fmt.
#define char_size(c2,c1) (c2?2:1)
void fold_conv(nkf_char c2, nkf_char c1)
-{
+{
nkf_char prev0;
nkf_char fold_state;
- if (c1== '\r' && !fold_preserve_f) {
+ if (c1== CR && !fold_preserve_f) {
fold_state=0; /* ignore cr */
- }else if (c1== '\n'&&f_prev=='\r' && fold_preserve_f) {
- f_prev = '\n';
+ }else if (c1== LF&&f_prev==CR && fold_preserve_f) {
+ f_prev = LF;
fold_state=0; /* ignore cr */
} else if (c1== BS) {
if (f_line>0) f_line--;
fold_state = 1;
} else if (c2==EOF && f_line != 0) { /* close open last line */
- fold_state = '\n';
- } else if ((c1=='\n' && !fold_preserve_f)
- || ((c1=='\r'||(c1=='\n'&&f_prev!='\r'))
+ fold_state = LF;
+ } else if ((c1==LF && !fold_preserve_f)
+ || ((c1==CR||(c1==LF&&f_prev!=CR))
&& fold_preserve_f)) {
/* new line */
- if (fold_preserve_f) {
+ if (fold_preserve_f) {
f_prev = c1;
f_line = 0;
- fold_state = '\r';
+ fold_state = CR;
} else if ((f_prev == c1 && !fold_preserve_f)
- || (f_prev == '\n' && fold_preserve_f)
+ || (f_prev == LF && fold_preserve_f)
) { /* duplicate newline */
if (f_line) {
f_line = 0;
- fold_state = '\n'; /* output two newline */
+ fold_state = LF; /* output two newline */
} else {
f_line = 0;
fold_state = 1;
if (f_prev&0x80) { /* Japanese? */
f_prev = c1;
fold_state = 0; /* ignore given single newline */
- } else if (f_prev==' ') {
+ } else if (f_prev==SP) {
fold_state = 0;
} else {
f_prev = c1;
- if (++f_line<=fold_len)
- fold_state = ' ';
+ if (++f_line<=fold_len)
+ fold_state = SP;
else {
f_line = 0;
- fold_state = '\r'; /* fold and output nothing */
+ fold_state = CR; /* fold and output nothing */
}
}
}
} else if (c1=='\f') {
- f_prev = '\n';
+ f_prev = LF;
f_line = 0;
- fold_state = '\n'; /* output newline and clear */
- } else if ( (c2==0 && c1==' ')||
- (c2==0 && c1=='\t')||
+ fold_state = LF; /* output newline and clear */
+ } else if ( (c2==0 && c1==SP)||
+ (c2==0 && c1==TAB)||
(c2=='!'&& c1=='!')) {
/* X0208 kankaku or ascii space */
- if (f_prev == ' ') {
+ if (f_prev == SP) {
fold_state = 0; /* remove duplicate spaces */
} else {
- f_prev = ' ';
- if (++f_line<=fold_len)
- fold_state = ' '; /* output ASCII space only */
+ f_prev = SP;
+ if (++f_line<=fold_len)
+ fold_state = SP; /* output ASCII space only */
else {
- f_prev = ' '; f_line = 0;
- fold_state = '\r'; /* fold and output nothing */
+ f_prev = SP; f_line = 0;
+ fold_state = CR; /* fold and output nothing */
}
}
} else {
prev0 = f_prev; /* we still need this one... , but almost done */
f_prev = c1;
- if (c2 || c2==X0201)
+ if (c2 || c2==JIS_X_0201)
f_prev |= 0x80; /* this is Japanese */
f_line += char_size(c2,c1);
if (f_line<=fold_len) { /* normal case */
} else {
if (f_line>fold_len+fold_margin) { /* too many kinsoku suspension */
f_line = char_size(c2,c1);
- fold_state = '\n'; /* We can't wait, do fold now */
- } else if (c2==X0201) {
+ fold_state = LF; /* We can't wait, do fold now */
+ } else if (c2==JIS_X_0201) {
/* simple kinsoku rules return 1 means no folding */
if (c1==(0xde&0x7f)) fold_state = 1; /* \e$B!+\e(B*/
else if (c1==(0xdf&0x7f)) fold_state = 1; /* \e$B!,\e(B*/
else if (c1==(0xa3&0x7f)) fold_state = 1; /* \e$B!$\e(B*/
else if (c1==(0xa1&0x7f)) fold_state = 1; /* \e$B!W\e(B*/
else if (c1==(0xb0&0x7f)) fold_state = 1; /* - */
- else if (SPACE<=c1 && c1<=(0xdf&0x7f)) { /* X0201 */
+ else if (SP<=c1 && c1<=(0xdf&0x7f)) { /* X0201 */
f_line = 1;
- fold_state = '\n';/* add one new f_line before this character */
+ fold_state = LF;/* add one new f_line before this character */
} else {
f_line = 1;
- fold_state = '\n';/* add one new f_line before this character */
+ fold_state = LF;/* add one new f_line before this character */
}
} else if (c2==0) {
- /* kinsoku point in ASCII */
+ /* kinsoku point in ASCII */
if ( c1==')'|| /* { [ ( */
c1==']'||
c1=='}'||
c1=='?'||
c1=='/'||
c1==':'||
- c1==';' ) {
+ c1==';') {
fold_state = 1;
/* just after special */
} else if (!is_alnum(prev0)) {
f_line = char_size(c2,c1);
- fold_state = '\n';
- } else if ((prev0==' ') || /* ignored new f_line */
- (prev0=='\n')|| /* ignored new f_line */
+ fold_state = LF;
+ } else if ((prev0==SP) || /* ignored new f_line */
+ (prev0==LF)|| /* ignored new f_line */
(prev0&0x80)) { /* X0208 - ASCII */
f_line = char_size(c2,c1);
- fold_state = '\n';/* add one new f_line before this character */
+ fold_state = LF;/* add one new f_line before this character */
} else {
fold_state = 1; /* default no fold in ASCII */
}
else if (c1=='+') fold_state = 1; /* \e$B!+\e(B */
else if (c1==',') fold_state = 1; /* \e$B!,\e(B */
/* default no fold in kinsoku */
- else {
- fold_state = '\n';
+ else {
+ fold_state = LF;
f_line = char_size(c2,c1);
/* add one new f_line before this character */
}
} else {
f_line = char_size(c2,c1);
- fold_state = '\n';
+ fold_state = LF;
/* add one new f_line before this character */
}
}
}
/* terminator process */
switch(fold_state) {
- case '\n':
- (*o_fconv)(0,'\n');
+ case LF:
+ OCONV_NEWLINE((*o_fconv));
(*o_fconv)(c2,c1);
break;
- case 0:
+ case 0:
return;
- case '\r':
- (*o_fconv)(0,'\n');
+ case CR:
+ OCONV_NEWLINE((*o_fconv));
break;
- case '\t':
- case ' ':
- (*o_fconv)(0,' ');
+ case TAB:
+ case SP:
+ (*o_fconv)(0,SP);
break;
default:
(*o_fconv)(c2,c1);
/* if (c2) c1 &= 0x7f; assertion */
- if (c2 == X0201 && (c1 == 0x20 || c1 == 0x7D || c1 == 0x7E)) {
+ if (c2 == JIS_X_0201 && (c1 == 0x20 || c1 == 0x7D || c1 == 0x7E)) {
(*o_zconv)(c2,c1);
return;
}
if (x0201_f) {
- if (z_prev2 == X0201) {
- if (c2 == X0201) {
+ if (z_prev2 == JIS_X_0201) {
+ if (c2 == JIS_X_0201) {
if (c1 == (0xde&0x7f)) { /* \e$BByE@\e(B */
z_prev2 = 0;
- (*o_zconv)(dv[(z_prev1-SPACE)*2], dv[(z_prev1-SPACE)*2+1]);
+ (*o_zconv)(dv[(z_prev1-SP)*2], dv[(z_prev1-SP)*2+1]);
return;
- } else if (c1 == (0xdf&0x7f) && ev[(z_prev1-SPACE)*2]) { /* \e$BH>ByE@\e(B */
+ } else if (c1 == (0xdf&0x7f) && ev[(z_prev1-SP)*2]) { /* \e$BH>ByE@\e(B */
z_prev2 = 0;
- (*o_zconv)(ev[(z_prev1-SPACE)*2], ev[(z_prev1-SPACE)*2+1]);
+ (*o_zconv)(ev[(z_prev1-SP)*2], ev[(z_prev1-SP)*2+1]);
return;
}
}
z_prev2 = 0;
- (*o_zconv)(cv[(z_prev1-SPACE)*2], cv[(z_prev1-SPACE)*2+1]);
+ (*o_zconv)(cv[(z_prev1-SP)*2], cv[(z_prev1-SP)*2+1]);
}
- if (c2 == X0201) {
- if (dv[(c1-SPACE)*2] || ev[(c1-SPACE)*2]) {
+ if (c2 == JIS_X_0201) {
+ if (dv[(c1-SP)*2] || ev[(c1-SP)*2]) {
/* wait for \e$BByE@\e(B or \e$BH>ByE@\e(B */
z_prev1 = c1;
z_prev2 = c2;
return;
} else {
- (*o_zconv)(cv[(c1-SPACE)*2], cv[(c1-SPACE)*2+1]);
+ (*o_zconv)(cv[(c1-SP)*2], cv[(c1-SP)*2+1]);
return;
}
}
return;
}
- if (alpha_f&1 && c2 == 0x23 ) {
+ if (alpha_f&1 && c2 == 0x23) {
/* JISX0208 Alphabet */
c2 = 0;
- } else if (c2 == 0x21) {
+ } else if (c2 == 0x21) {
/* JISX0208 Kigou */
if (0x21==c1) {
if (alpha_f&2) {
c2 = 0;
- c1 = ' ';
+ c1 = SP;
} else if (alpha_f&4) {
- (*o_zconv)(0, ' ');
- (*o_zconv)(0, ' ');
+ (*o_zconv)(0, SP);
+ (*o_zconv)(0, SP);
return;
- }
+ }
} else if (alpha_f&1 && 0x20<c1 && c1<0x7f && fv[c1-0x20]) {
c2 = 0;
c1 = fv[c1-0x20];
- }
+ }
}
if (alpha_f&8 && c2 == 0) {
break;
}
if (c) {
- (*o_zconv)(X0201, c);
+ (*o_zconv)(JIS_X_0201, c);
return;
}
} else if (c2 == 0x25) {
};
if (fullwidth_to_halfwidth[c1-0x20]){
c2 = fullwidth_to_halfwidth[c1-0x20];
- (*o_zconv)(X0201, c2>>8);
+ (*o_zconv)(JIS_X_0201, c2>>8);
if (c2 & 0xFF) {
- (*o_zconv)(X0201, c2&0xFF);
+ (*o_zconv)(JIS_X_0201, c2&0xFF);
}
return;
}
#define rot13(c) ( \
- ( c < 'A' ) ? c: \
+ ( c < 'A') ? c: \
(c <= 'M') ? (c + 13): \
(c <= 'Z') ? (c - 13): \
(c < 'a') ? (c): \
)
#define rot47(c) ( \
- ( c < '!' ) ? c: \
- ( c <= 'O' ) ? (c + 47) : \
- ( c <= '~' ) ? (c - 47) : \
+ ( c < '!') ? c: \
+ ( c <= 'O') ? (c + 47) : \
+ ( c <= '~') ? (c - 47) : \
c \
)
void rot_conv(nkf_char c2, nkf_char c1)
{
- if (c2==0 || c2==X0201 || c2==ISO8859_1) {
+ if (c2==0 || c2==JIS_X_0201 || c2==ISO_8859_1) {
c1 = rot13(c1);
} else if (c2) {
c1 = rot47(c1);
c2 = 0x24;
(*o_hira_conv)(c2,c1);
return;
- } else if (c1 == 0x74 && (output_conv == w_oconv || output_conv == w_oconv16)) {
+ } else if (c1 == 0x74 && nkf_enc_unicode_p(output_encoding)) {
c2 = 0;
c1 = CLASS_UNICODE | 0x3094;
(*o_hira_conv)(c2,c1);
};
static const nkf_char mime_encode[] = {
- JAPANESE_EUC, SHIFT_JIS,ISO8859_1, ISO8859_1, X0208, X0201,
+ EUC_JP, SHIFT_JIS, ISO_8859_1, ISO_8859_1, JIS_X_0208, JIS_X_0201,
#if defined(UTF8_INPUT_ENABLE)
- UTF8, UTF8,
+ UTF_8, UTF_8,
#endif
ASCII,
0
p = mime_pattern[j];
r[0]='='; r[1]='?';
- for(i=2;p[i]>' ';i++) { /* start at =? */
- if ( ((r[i] = c1 = (*i_getc)(f))==EOF) || nkf_toupper(c1) != p[i] ) {
+ for(i=2;p[i]>SP;i++) { /* start at =? */
+ if (((r[i] = c1 = (*i_getc)(f))==EOF) || nkf_toupper(c1) != p[i]) {
/* pattern fails, try next one */
q = p;
while (mime_pattern[++j]) {
if (!unbuf_f) {
/* do MIME integrity check */
return mime_integrity(f,mime_pattern[j]);
- }
+ }
}
switch_mime_getc();
mimebuf_f = TRUE;
{
if (mimebuf_f)
(*i_mungetc_buf)(c,f);
- else
+ else
Fifo(--mime_input) = (unsigned char)c;
return c;
}
for(i=2;i<MAXRECOVER;i++) { /* start at =? */
/* We accept any character type even if it is breaked by new lines */
c1 = (*i_getc)(f); Fifo(mime_last++) = (unsigned char)c1;
- if (c1=='\n'||c1==' '||c1=='\r'||
- c1=='-'||c1=='_'||is_alnum(c1) ) continue;
+ if (c1==LF||c1==SP||c1==CR||
+ c1=='-'||c1=='_'||is_alnum(c1)) continue;
if (c1=='=') {
/* Failed. But this could be another MIME preemble */
(*i_ungetc)(c1,f);
void debug(const char *str)
{
if (debug_f){
- fprintf(stderr, "%s\n", str);
+ fprintf(stderr, "%s\n", str ? str : "NULL");
}
}
#endif
void set_input_codename(char *codename)
{
- if (guess_f &&
- is_inputcode_set &&
- strcmp(codename, "") != 0 &&
- strcmp(codename, input_codename) != 0)
- {
- is_inputcode_mixed = TRUE;
+ if (!input_codename) {
+ input_codename = codename;
+ } else if (strcmp(codename, input_codename) != 0) {
+ input_codename = "";
+ }
+}
+
+static char* get_guessed_code(void)
+{
+ if (input_codename && !*input_codename) {
+ input_codename = "BINARY";
+ } else {
+ struct input_code *p = find_inputcode_byfunc(iconv);
+ if (!input_codename) {
+ input_codename = "ASCII";
+ } else if (strcmp(input_codename, "Shift_JIS") == 0) {
+ if (p->score & (SCORE_DEPEND|SCORE_CP932))
+ input_codename = "CP932";
+ } else if (strcmp(input_codename, "EUC-JP") == 0) {
+ if (p->score & (SCORE_X0212))
+ input_codename = "EUCJP-MS";
+ else if (p->score & (SCORE_DEPEND|SCORE_CP932))
+ input_codename = "CP51932";
+ } else if (strcmp(input_codename, "ISO-2022-JP") == 0) {
+ if (p->score & (SCORE_KANA))
+ input_codename = "CP50221";
+ else if (p->score & (SCORE_DEPEND|SCORE_CP932))
+ input_codename = "CP50220";
+ }
}
- input_codename = codename;
- is_inputcode_set = TRUE;
+ return input_codename;
}
#if !defined(PERL_XS) && !defined(WIN32DLL)
void print_guessed_code(char *filename)
{
- char *codename = "BINARY";
- char *str_crmode = NULL;
- if (!is_inputcode_mixed) {
- if (strcmp(input_codename, "") == 0) {
- codename = "ASCII";
- } else {
- codename = input_codename;
- }
- if (crmode_f == CR) str_crmode = "CR";
- else if (crmode_f == NL) str_crmode = "LF";
- else if (crmode_f == CRLF) str_crmode = "CRLF";
+ if (filename != NULL) printf("%s: ", filename);
+ if (input_codename && !*input_codename) {
+ printf("BINARY\n");
+ } else {
+ input_codename = get_guessed_code();
+ if (guess_f == 1) {
+ printf("%s\n", input_codename);
+ } else {
+ printf("%s%s\n",
+ input_codename,
+ input_newline == CR ? " (CR)" :
+ input_newline == LF ? " (LF)" :
+ input_newline == CRLF ? " (CRLF)" :
+ input_newline == EOF ? " (MIXED NL)" :
+ "");
+ }
}
- if (filename != NULL) printf("%s:", filename);
- if (str_crmode != NULL) printf("%s (%s)\n", codename, str_crmode);
- else printf("%s\n", codename);
}
#endif /*WIN32DLL*/
-#ifdef INPUT_OPTION
+#ifdef INPUT_OPTION
nkf_char hex_getc(nkf_char ch, FILE *f, nkf_char (*g)(FILE *f), nkf_char (*u)(nkf_char c, FILE *f))
{
nkf_char (*u)(nkf_char c ,FILE *f) = i_nfc_ungetc;
int i=0, j, k=1, lower, upper;
nkf_char buf[9];
- const nkf_nfchar *array;
-
+ const unsigned char *array;
+
buf[i] = (*g)(f);
while (k > 0 && ((buf[i] & 0xc0) != 0x80)){
lower=0, upper=NORMALIZATION_TABLE_LENGTH-1;
#endif /* UNICODE_NORMALIZATION */
-nkf_char
+nkf_char
mime_getc(FILE *f)
{
nkf_char c1, c2, c3, c4, cc;
if (mime_decode_mode == 'Q') {
if ((c1 = (*i_mgetc)(f)) == EOF) return (EOF);
restart_mime_q:
- if (c1=='_' && mimebuf_f != FIXED_MIME) return ' ';
- if (c1<=' ' || DEL<=c1) {
+ if (c1=='_' && mimebuf_f != FIXED_MIME) return SP;
+ if (c1<=SP || DEL<=c1) {
mime_decode_mode = exit_mode; /* prepare for quit */
return c1;
}
if (c1!='=' && (c1!='?' || mimebuf_f == FIXED_MIME)) {
return c1;
}
-
+
mime_decode_mode = exit_mode; /* prepare for quit */
if ((c2 = (*i_mgetc)(f)) == EOF) return (EOF);
if (c1=='?'&&c2=='=' && mimebuf_f != FIXED_MIME) {
}
while ((c1=(*i_getc)(f))!=EOF) {
switch (c1) {
- case NL:
+ case LF:
case CR:
- if (c1==NL) {
- if ((c1=(*i_getc)(f))!=EOF && (c1==SPACE||c1==TAB)) {
- i_ungetc(SPACE,f);
+ if (c1==LF) {
+ if ((c1=(*i_getc)(f))!=EOF && (c1==SP||c1==TAB)) {
+ i_ungetc(SP,f);
continue;
} else {
i_ungetc(c1,f);
}
- c1 = NL;
+ c1 = LF;
} else {
- if ((c1=(*i_getc)(f))!=EOF && c1 == NL) {
- if ((c1=(*i_getc)(f))!=EOF && (c1==SPACE||c1==TAB)) {
- i_ungetc(SPACE,f);
+ if ((c1=(*i_getc)(f))!=EOF && c1 == LF) {
+ if ((c1=(*i_getc)(f))!=EOF && (c1==SP||c1==TAB)) {
+ i_ungetc(SP,f);
continue;
} else {
i_ungetc(c1,f);
}
- i_ungetc(NL,f);
+ i_ungetc(LF,f);
} else {
i_ungetc(c1,f);
}
c1 = CR;
}
break;
- case SPACE:
+ case SP:
case TAB:
lwsp_buf[lwsp_count] = (unsigned char)c1;
if (lwsp_count++>lwsp_size){
}
break;
}
- if (lwsp_count > 0 && (c1 != '=' || (lwsp_buf[lwsp_count-1] != SPACE && lwsp_buf[lwsp_count-1] != TAB))) {
+ if (lwsp_count > 0 && (c1 != '=' || (lwsp_buf[lwsp_count-1] != SP && lwsp_buf[lwsp_count-1] != TAB))) {
i_ungetc(c1,f);
for(lwsp_count--;lwsp_count>0;lwsp_count--)
i_ungetc(lwsp_buf[lwsp_count],f);
free(lwsp_buf);
return c1;
}
- if (c1=='='&&c2<' ') { /* this is soft wrap */
- while((c1 = (*i_mgetc)(f)) <=' ') {
+ if (c1=='='&&c2<SP) { /* this is soft wrap */
+ while((c1 = (*i_mgetc)(f)) <=SP) {
if ((c1 = (*i_mgetc)(f)) == EOF) return (EOF);
}
mime_decode_mode = 'Q'; /* still in MIME */
return c1;
}
if ((c3 = (*i_mgetc)(f)) == EOF) return (EOF);
- if (c2<=' ') return c2;
+ if (c2<=SP) return c2;
mime_decode_mode = 'Q'; /* still in MIME */
return ((hex2bin(c2)<<4) + hex2bin(c3));
}
/* Base64 encoding */
- /*
- MIME allows line break in the middle of
+ /*
+ MIME allows line break in the middle of
Base64, but we are very pessimistic in decoding
- in unbuf mode because MIME encoded code may broken by
+ in unbuf mode because MIME encoded code may broken by
less or editor's control sequence (such as ESC-[-K in unbuffered
mode. ignore incomplete MIME.
*/
mode = mime_decode_mode;
mime_decode_mode = exit_mode; /* prepare for quit */
- while ((c1 = (*i_mgetc)(f))<=' ') {
+ while ((c1 = (*i_mgetc)(f))<=SP) {
if (c1==EOF)
return (EOF);
}
mime_c2_retry:
- if ((c2 = (*i_mgetc)(f))<=' ') {
+ if ((c2 = (*i_mgetc)(f))<=SP) {
if (c2==EOF)
return (EOF);
if (mime_f != STRICT_MIME) goto mime_c2_retry;
- if (mimebuf_f!=FIXED_MIME) input_mode = ASCII;
+ if (mimebuf_f!=FIXED_MIME) input_mode = ASCII;
return c2;
}
if ((c1 == '?') && (c2 == '=')) {
}
while ((c1=(*i_getc)(f))!=EOF) {
switch (c1) {
- case NL:
+ case LF:
case CR:
- if (c1==NL) {
- if ((c1=(*i_getc)(f))!=EOF && (c1==SPACE||c1==TAB)) {
- i_ungetc(SPACE,f);
+ if (c1==LF) {
+ if ((c1=(*i_getc)(f))!=EOF && (c1==SP||c1==TAB)) {
+ i_ungetc(SP,f);
continue;
} else {
i_ungetc(c1,f);
}
- c1 = NL;
+ c1 = LF;
} else {
if ((c1=(*i_getc)(f))!=EOF) {
- if (c1==SPACE) {
- i_ungetc(SPACE,f);
+ if (c1==SP) {
+ i_ungetc(SP,f);
continue;
- } else if ((c1=(*i_getc)(f))!=EOF && (c1==SPACE||c1==TAB)) {
- i_ungetc(SPACE,f);
+ } else if ((c1=(*i_getc)(f))!=EOF && (c1==SP||c1==TAB)) {
+ i_ungetc(SP,f);
continue;
} else {
i_ungetc(c1,f);
}
- i_ungetc(NL,f);
+ i_ungetc(LF,f);
} else {
i_ungetc(c1,f);
}
c1 = CR;
}
break;
- case SPACE:
+ case SP:
case TAB:
lwsp_buf[lwsp_count] = (unsigned char)c1;
if (lwsp_count++>lwsp_size){
}
break;
}
- if (lwsp_count > 0 && (c1 != '=' || (lwsp_buf[lwsp_count-1] != SPACE && lwsp_buf[lwsp_count-1] != TAB))) {
+ if (lwsp_count > 0 && (c1 != '=' || (lwsp_buf[lwsp_count-1] != SP && lwsp_buf[lwsp_count-1] != TAB))) {
i_ungetc(c1,f);
for(lwsp_count--;lwsp_count>0;lwsp_count--)
i_ungetc(lwsp_buf[lwsp_count],f);
return c1;
}
mime_c3_retry:
- if ((c3 = (*i_mgetc)(f))<=' ') {
+ if ((c3 = (*i_mgetc)(f))<=SP) {
if (c3==EOF)
return (EOF);
if (mime_f != STRICT_MIME) goto mime_c3_retry;
- if (mimebuf_f!=FIXED_MIME) input_mode = ASCII;
+ if (mimebuf_f!=FIXED_MIME) input_mode = ASCII;
return c3;
}
mime_c4_retry:
- if ((c4 = (*i_mgetc)(f))<=' ') {
+ if ((c4 = (*i_mgetc)(f))<=SP) {
if (c4==EOF)
return (EOF);
if (mime_f != STRICT_MIME) goto mime_c4_retry;
- if (mimebuf_f!=FIXED_MIME) input_mode = ASCII;
+ if (mimebuf_f!=FIXED_MIME) input_mode = ASCII;
return c4;
}
if (c3 != '=') {
Fifo(mime_last++) = (unsigned char)cc;
cc = ((t3 << 6) & 0x0c0) | (t4 & 0x3f);
- if (c4 != '=')
+ if (c4 != '=')
Fifo(mime_last++) = (unsigned char)cc;
}
} else {
*/
mime_input = mime_top;
mime_last = mime_top;
-
+
while(*p) Fifo(mime_input++) = *p++;
d = 0;
q = mime_input;
/* checked. skip header, start decode */
Fifo(mime_input++) = (unsigned char)c;
/* mime_last_input = mime_input; */
- mime_input = q;
+ mime_input = q;
switch_mime_getc();
return 1;
}
if (c > '@') {
if (c < '[') {
i = c - 'A'; /* A..Z 0-25 */
+ } else if (c == '_') {
+ i = '?' /* 63 */ ; /* _ 63 */
} else {
i = c - 'G' /* - 'a' + 26 */ ; /* a..z 26-51 */
}
} else if (c > '/') {
i = c - '0' + '4' /* - '0' + 52 */ ; /* 0..9 52-61 */
- } else if (c == '+') {
- i = '>' /* 62 */ ; /* + 62 */
+ } else if (c == '+' || c == '-') {
+ i = '>' /* 62 */ ; /* + and - 62 */
} else {
i = '?' /* 63 */ ; /* / 63 */
}
#define MIMEOUT_BUF_LENGTH (60)
char mimeout_buf[MIMEOUT_BUF_LENGTH+1];
int mimeout_buf_count = 0;
-int mimeout_preserve_space = 0;
-#define itoh4(c) (c>=10?c+'A'-10:c+'0')
void open_mime(nkf_char mode)
{
}
}
mimeout_mode = mime_encode_method[i];
-
i = 0;
if (base64_count>45) {
if (mimeout_buf_count>0 && nkf_isblank(mimeout_buf[i])){
(*o_mputc)(mimeout_buf[i]);
i++;
}
- (*o_mputc)(NL);
- (*o_mputc)(SPACE);
+ PUT_NEWLINE((*o_mputc));
+ (*o_mputc)(SP);
base64_count = 1;
- if (!mimeout_preserve_space && mimeout_buf_count>0
- && (mimeout_buf[i]==SPACE || mimeout_buf[i]==TAB
- || mimeout_buf[i]==CR || mimeout_buf[i]==NL )) {
+ if (mimeout_buf_count>0
+ && (mimeout_buf[i]==SP || mimeout_buf[i]==TAB
+ || mimeout_buf[i]==CR || mimeout_buf[i]==LF)) {
i++;
}
}
- if (!mimeout_preserve_space) {
- for (;i<mimeout_buf_count;i++) {
- if (mimeout_buf[i]==SPACE || mimeout_buf[i]==TAB
- || mimeout_buf[i]==CR || mimeout_buf[i]==NL ) {
- (*o_mputc)(mimeout_buf[i]);
- base64_count ++;
- } else {
- break;
- }
+ for (;i<mimeout_buf_count;i++) {
+ if (mimeout_buf[i]==SP || mimeout_buf[i]==TAB
+ || mimeout_buf[i]==CR || mimeout_buf[i]==LF) {
+ (*o_mputc)(mimeout_buf[i]);
+ base64_count ++;
+ } else {
+ break;
}
}
- mimeout_preserve_space = FALSE;
-
while(*p) {
(*o_mputc)(*p++);
base64_count ++;
base64_count += 2;
break;
}
- if (mimeout_mode) {
+ if (mimeout_mode > 0) {
if (mimeout_f!=FIXED_MIME) {
- close_mime();
+ close_mime();
} else if (mimeout_mode != 'Q')
mimeout_mode = 'B';
}
{
switch(mimeout_mode) {
case 'Q':
- if (c==CR||c==NL) {
+ if (c==CR||c==LF) {
(*o_mputc)(c);
base64_count = 0;
} else if(!nkf_isalnum(c)) {
(*o_mputc)('=');
- (*o_mputc)(itoh4(((c>>4)&0xf)));
- (*o_mputc)(itoh4((c&0xf)));
+ (*o_mputc)(bin2hex(((c>>4)&0xf)));
+ (*o_mputc)(bin2hex((c&0xf)));
base64_count += 3;
} else {
(*o_mputc)(c);
void mime_prechar(nkf_char c2, nkf_char c1)
{
- if (mimeout_mode){
+ if (mimeout_mode > 0){
if (c2 == EOF){
if (base64_count + mimeout_buf_count/3*4> 73){
(*o_base64conv)(EOF,0);
- (*o_base64conv)(0,NL);
- (*o_base64conv)(0,SPACE);
+ OCONV_NEWLINE((*o_base64conv));
+ (*o_base64conv)(0,SP);
+ base64_count = 1;
}
- } else if (c2){
- if (base64_count + mimeout_buf_count/3*4> 66){
+ } else {
+ if (base64_count + mimeout_buf_count/3*4> 66) {
(*o_base64conv)(EOF,0);
- (*o_base64conv)(0,NL);
- (*o_base64conv)(0,SPACE);
- }
- }/*else if (mime_lastchar2){
- if (c1 <=DEL && !nkf_isspace(c1)){
- (*o_base64conv)(0,SPACE);
+ OCONV_NEWLINE((*o_base64conv));
+ (*o_base64conv)(0,SP);
+ base64_count = 1;
+ mimeout_mode = -1;
}
- }*/
- }/*else{
- if (c2 && mime_lastchar2 == 0
- && mime_lastchar1 && !nkf_isspace(mime_lastchar1)){
- (*o_base64conv)(0,SPACE);
}
- }*/
- /*mime_lastchar2 = c2;
- mime_lastchar1 = c1;*/
+ } else if (c2) {
+ if (c2 != EOF && base64_count + mimeout_buf_count/3*4> 60) {
+ mimeout_mode = (output_mode==ASCII ||output_mode == ISO_8859_1) ? 'Q' : 'B';
+ open_mime(output_mode);
+ (*o_base64conv)(EOF,0);
+ OCONV_NEWLINE((*o_base64conv));
+ (*o_base64conv)(0,SP);
+ base64_count = 1;
+ mimeout_mode = -1;
+ }
+ }
}
void mime_putc(nkf_char c)
if (mimeout_f == FIXED_MIME){
if (mimeout_mode == 'Q'){
if (base64_count > 71){
- if (c!=CR && c!=NL) {
+ if (c!=CR && c!=LF) {
(*o_mputc)('=');
- (*o_mputc)(NL);
+ PUT_NEWLINE((*o_mputc));
}
base64_count = 0;
}
}else{
if (base64_count > 71){
eof_mime();
- (*o_mputc)(NL);
+ PUT_NEWLINE((*o_mputc));
base64_count = 0;
}
if (c == EOF) { /* c==EOF */
}
return;
}
-
+
/* mimeout_f != FIXED_MIME */
if (c == EOF) { /* c==EOF */
+ if (mimeout_mode == -1 && mimeout_buf_count > 1) open_mime(output_mode);
j = mimeout_buf_count;
mimeout_buf_count = 0;
i = 0;
- if (mimeout_mode) {
+ if (mimeout_mode > 0) {
if (!nkf_isblank(mimeout_buf[j-1])) {
for (;i<j;i++) {
if (nkf_isspace(mimeout_buf[i]) && base64_count < 71){
return;
}
+ if (mimeout_buf_count > 0){
+ lastchar = mimeout_buf[mimeout_buf_count - 1];
+ }else{
+ lastchar = -1;
+ }
+
if (mimeout_mode=='Q') {
- if (c <= DEL && (output_mode==ASCII ||output_mode == ISO8859_1 ) ) {
- if (c == CR || c == NL) {
+ if (c <= DEL && (output_mode==ASCII ||output_mode == ISO_8859_1)) {
+ if (c == CR || c == LF) {
close_mime();
(*o_mputc)(c);
base64_count = 0;
return;
- } else if (c <= SPACE) {
+ } else if (c <= SP) {
close_mime();
if (base64_count > 70) {
- (*o_mputc)(NL);
+ PUT_NEWLINE((*o_mputc));
base64_count = 0;
}
if (!nkf_isblank(c)) {
- (*o_mputc)(SPACE);
+ (*o_mputc)(SP);
base64_count++;
}
- }
- (*o_mputc)(c);
- base64_count++;
+ } else {
+ if (base64_count > 70) {
+ close_mime();
+ PUT_NEWLINE((*o_mputc));
+ (*o_mputc)(SP);
+ base64_count = 1;
+ open_mime(output_mode);
+ }
+ if (!nkf_noescape_mime(c)) {
+ mimeout_addchar(c);
+ return;
+ }
+ }
+ (*o_mputc)(c);
+ base64_count++;
}
return;
}
- if (mimeout_buf_count > 0){
- lastchar = mimeout_buf[mimeout_buf_count - 1];
- }else{
- lastchar = -1;
- }
-
- if (!mimeout_mode) {
- if (c <= DEL && (output_mode==ASCII ||output_mode == ISO8859_1)) {
+ if (mimeout_mode <= 0) {
+ if (c <= DEL && (output_mode==ASCII ||output_mode == ISO_8859_1)) {
if (nkf_isspace(c)) {
- if (c==CR || c==NL) {
- base64_count=0;
+ int flag = 0;
+ if (mimeout_mode == -1) {
+ flag = 1;
+ }
+ if (c==CR || c==LF) {
+ if (flag) {
+ open_mime(output_mode);
+ output_mode = 0;
+ } else {
+ base64_count = 0;
+ }
}
for (i=0;i<mimeout_buf_count;i++) {
(*o_mputc)(mimeout_buf[i]);
- if (mimeout_buf[i] == CR || mimeout_buf[i] == NL){
+ if (mimeout_buf[i] == CR || mimeout_buf[i] == LF){
base64_count = 0;
}else{
base64_count++;
}
}
- mimeout_buf[0] = (char)c;
- mimeout_buf_count = 1;
+ if (flag) {
+ eof_mime();
+ base64_count = 0;
+ mimeout_mode = 0;
+ }
+ mimeout_buf[0] = (char)c;
+ mimeout_buf_count = 1;
}else{
if (base64_count > 1
&& base64_count + mimeout_buf_count > 76
- && mimeout_buf[0] != CR && mimeout_buf[0] != NL){
- (*o_mputc)(NL);
+ && mimeout_buf[0] != CR && mimeout_buf[0] != LF){
+ PUT_NEWLINE((*o_mputc));
base64_count = 0;
if (!nkf_isspace(mimeout_buf[0])){
- (*o_mputc)(SPACE);
+ (*o_mputc)(SP);
base64_count++;
}
}
}
return;
}else{
- if (lastchar==CR || lastchar == NL){
+ if (lastchar==CR || lastchar == LF){
for (i=0;i<mimeout_buf_count;i++) {
(*o_mputc)(mimeout_buf[i]);
}
base64_count = 0;
mimeout_buf_count = 0;
}
- if (lastchar==SPACE) {
+ if (lastchar==SP) {
for (i=0;i<mimeout_buf_count-1;i++) {
(*o_mputc)(mimeout_buf[i]);
base64_count++;
}
- mimeout_buf[0] = SPACE;
+ mimeout_buf[0] = SP;
mimeout_buf_count = 1;
}
open_mime(output_mode);
}
}else{
/* mimeout_mode == 'B', 1, 2 */
- if ( c<=DEL && (output_mode==ASCII ||output_mode == ISO8859_1 ) ) {
- if (lastchar == CR || lastchar == NL){
+ if ( c<=DEL && (output_mode==ASCII ||output_mode == ISO_8859_1)) {
+ if (lastchar == CR || lastchar == LF){
if (nkf_isblank(c)) {
for (i=0;i<mimeout_buf_count;i++) {
mimeout_addchar(mimeout_buf[i]);
}
mimeout_buf_count = 0;
- } else if (SPACE<c && c<DEL) {
+ } else if (SP<c && c<DEL) {
eof_mime();
for (i=0;i<mimeout_buf_count;i++) {
(*o_mputc)(mimeout_buf[i]);
base64_count = 0;
mimeout_buf_count = 0;
}
+ mimeout_buf[mimeout_buf_count++] = (char)c;
+ return;
}
- if (c==SPACE || c==TAB || c==CR || c==NL) {
+ if (c==SP || c==TAB || c==CR || c==LF) {
for (i=0;i<mimeout_buf_count;i++) {
- if (SPACE<mimeout_buf[i] && mimeout_buf[i]<DEL) {
+ if (SP<mimeout_buf[i] && mimeout_buf[i]<DEL) {
eof_mime();
for (i=0;i<mimeout_buf_count;i++) {
(*o_mputc)(mimeout_buf[i]);
mimeout_buf_count = 0;
}
return;
- }
- if (mimeout_buf_count>0 && SPACE<c && c!='=') {
+ }
+ if (mimeout_buf_count>0 && SP<c && c!='=') {
mimeout_buf[mimeout_buf_count++] = (char)c;
if (mimeout_buf_count>MIMEOUT_BUF_LENGTH) {
j = mimeout_buf_count;
j = mimeout_buf_count;
mimeout_buf_count = 0;
for (i=0;i<j;i++) {
- if (mimeout_buf[i]==CR || mimeout_buf[i]==NL)
+ if (mimeout_buf[i]==CR || mimeout_buf[i]==LF)
break;
mimeout_addchar(mimeout_buf[i]);
}
}
-#if defined(PERL_XS) || defined(WIN32DLL)
void reinit(void)
{
{
binmode_f = TRUE;
rot_f = FALSE;
hira_f = FALSE;
- input_f = FALSE;
alpha_f = FALSE;
- mime_f = STRICT_MIME;
+ mime_f = MIME_DECODE_DEFAULT;
mime_decode_f = FALSE;
mimebuf_f = FALSE;
broken_f = FALSE;
iso8859_f = FALSE;
mimeout_f = FALSE;
-#if defined(MSDOS) || defined(__OS2__)
- x0201_f = TRUE;
-#else
- x0201_f = NO_X0201;
-#endif
+ x0201_f = X0201_DEFAULT;
iso2022jp_f = FALSE;
#if defined(UTF8_INPUT_ENABLE) || defined(UTF8_OUTPUT_ENABLE)
ms_ucs_map_f = UCS_MAP_ASCII;
noout_f = FALSE;
debug_f = FALSE;
#endif
- guess_f = FALSE;
- is_inputcode_mixed = FALSE;
- is_inputcode_set = FALSE;
+ guess_f = 0;
#ifdef EXEC_IO
exec_f = 0;
#endif
kanji_intro = DEFAULT_J;
ascii_intro = DEFAULT_R;
fold_margin = FOLD_MARGIN;
- output_conv = DEFAULT_CONV;
- oconv = DEFAULT_CONV;
o_zconv = no_connection;
o_fconv = no_connection;
- o_crconv = no_connection;
+ o_nlconv = no_connection;
o_rot_conv = no_connection;
o_hira_conv = no_connection;
o_base64conv = no_connection;
shift_mode = FALSE;
mime_decode_mode = FALSE;
file_out_f = FALSE;
- crmode_f = 0;
+ nlmode_f = 0;
+ input_newline = 0;
+ prev_cr = 0;
option_mode = 0;
broken_counter = 0;
broken_last = 0;
#ifdef CHECK_OPTION
iconv_for_check = 0;
#endif
- input_codename = "";
+ input_codename = NULL;
+ input_encoding = NULL;
+ output_encoding = NULL;
#ifdef WIN32DLL
reinitdll();
#endif /*WIN32DLL*/
}
-#endif
void no_connection(nkf_char c2, nkf_char c1)
{
#ifdef WIN32DLL
#define fprintf dllprintf
#endif
+
+void version(void)
+{
+ fprintf(HELP_OUTPUT,"Network Kanji Filter Version " NKF_VERSION " (" NKF_RELEASE_DATE ") \n" COPY_RIGHT "\n");
+}
+
void usage(void)
{
- fprintf(stderr,"USAGE: nkf(nkf32,wnkf,nkf2) -[flags] [in file] .. [out file for -O flag]\n");
- fprintf(stderr,"Flags:\n");
- fprintf(stderr,"b,u Output is buffered (DEFAULT),Output is unbuffered\n");
-#ifdef DEFAULT_CODE_SJIS
- fprintf(stderr,"j,s,e,w Output code is JIS 7 bit, Shift_JIS (DEFAULT), EUC-JP, UTF-8N\n");
-#endif
-#ifdef DEFAULT_CODE_JIS
- fprintf(stderr,"j,s,e,w Output code is JIS 7 bit (DEFAULT), Shift JIS, EUC-JP, UTF-8N\n");
-#endif
-#ifdef DEFAULT_CODE_EUC
- fprintf(stderr,"j,s,e,w Output code is JIS 7 bit, Shift JIS, EUC-JP (DEFAULT), UTF-8N\n");
-#endif
-#ifdef DEFAULT_CODE_UTF8
- fprintf(stderr,"j,s,e,w Output code is JIS 7 bit, Shift JIS, EUC-JP, UTF-8N (DEFAULT)\n");
-#endif
+ 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"
#ifdef UTF8_OUTPUT_ENABLE
- fprintf(stderr," After 'w' you can add more options. -w[ 8 [0], 16 [[BL] [0]] ]\n");
+ " After 'w' you can add more options. -w[ 8 [0], 16 [[BL] [0]] ]\n"
#endif
- fprintf(stderr,"J,S,E,W Input assumption is JIS 7 bit , Shift JIS, EUC-JP, UTF-8\n");
+ "J,S,E,W Input assumption is JIS 7 bit , Shift JIS, EUC-JP, UTF-8\n"
#ifdef UTF8_INPUT_ENABLE
- fprintf(stderr," After 'W' you can add more options. -W[ 8, 16 [BL] ] \n");
-#endif
- fprintf(stderr,"t no conversion\n");
- fprintf(stderr,"i[@B] Specify the Esc Seq for JIS X 0208-1978/83 (DEFAULT B)\n");
- fprintf(stderr,"o[BJH] Specify the Esc Seq for ASCII/Roman (DEFAULT B)\n");
- fprintf(stderr,"r {de/en}crypt ROT13/47\n");
- fprintf(stderr,"h 1 katakana->hiragana, 2 hiragana->katakana, 3 both\n");
- fprintf(stderr,"v Show this usage. V: show version\n");
- fprintf(stderr,"m[BQN0] MIME decode [B:base64,Q:quoted,N:non-strict,0:no decode]\n");
- fprintf(stderr,"M[BQ] MIME encode [B:base64 Q:quoted]\n");
- fprintf(stderr,"l ISO8859-1 (Latin-1) support\n");
- fprintf(stderr,"f/F Folding: -f60 or -f or -f60-10 (fold margin 10) F preserve nl\n");
- fprintf(stderr,"Z[0-4] Default/0: Convert JISX0208 Alphabet to ASCII\n");
- fprintf(stderr," 1: Kankaku to one space 2: to two spaces 3: HTML Entity\n");
- fprintf(stderr," 4: JISX0208 Katakana to JISX0201 Katakana\n");
- fprintf(stderr,"X,x Assume X0201 kana in MS-Kanji, -x preserves X0201\n");
- fprintf(stderr,"B[0-2] Broken input 0: missing ESC,1: any X on ESC-[($]-X,2: ASCII on NL\n");
+ " After 'W' you can add more options. -W[ 8, 16 [BL] ] \n"
+#endif
+ "t no conversion\n"
+ "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"
+ "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"
#ifdef MSDOS
- fprintf(stderr,"T Text mode output\n");
-#endif
- fprintf(stderr,"O Output to File (DEFAULT 'nkf.out')\n");
- fprintf(stderr,"I Convert non ISO-2022-JP charactor to GETA\n");
- fprintf(stderr,"d,c Convert line breaks -d: LF -c: CRLF\n");
- fprintf(stderr,"-L[uwm] line mode u:LF w:CRLF m:CR (DEFAULT noconversion)\n");
- fprintf(stderr,"\n");
- fprintf(stderr,"Long name options\n");
- fprintf(stderr," --ic=<input codeset> --oc=<output codeset>\n");
- fprintf(stderr," Specify the input or output codeset\n");
- fprintf(stderr," --fj --unix --mac --windows\n");
- fprintf(stderr," --jis --euc --sjis --utf8 --utf16 --mime --base64\n");
- fprintf(stderr," Convert for the system or code\n");
- fprintf(stderr," --hiragana --katakana --katakana-hiragana\n");
- fprintf(stderr," To Hiragana/Katakana Conversion\n");
- fprintf(stderr," --prefix= Insert escape before troublesome characters of Shift_JIS\n");
+ "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"
+ "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"
#ifdef INPUT_OPTION
- fprintf(stderr," --cap-input, --url-input Convert hex after ':' or '%%'\n");
+ " --cap-input, --url-input Convert hex after ':' or '%%'\n"
#endif
#ifdef NUMCHAR_OPTION
- fprintf(stderr," --numchar-input Convert Unicode Character Reference\n");
+ " --numchar-input Convert Unicode Character Reference\n"
#endif
#ifdef UTF8_INPUT_ENABLE
- fprintf(stderr," --fb-{skip, html, xml, perl, java, subchar}\n");
- fprintf(stderr," Specify how nkf handles unassigned characters\n");
+ " --fb-{skip, html, xml, perl, java, subchar}\n"
+ " Specify how nkf handles unassigned characters\n"
#endif
#ifdef OVERWRITE
- fprintf(stderr," --in-place[=SUFFIX] --overwrite[=SUFFIX]\n");
- fprintf(stderr," Overwrite original listed files by filtered result\n");
- fprintf(stderr," --overwrite preserves timestamp of original files\n");
-#endif
- fprintf(stderr," -g --guess Guess the input code\n");
- fprintf(stderr," --help --version Show this help/the version\n");
- fprintf(stderr," For more information, see also man nkf\n");
- fprintf(stderr,"\n");
+ " --in-place[=SUFFIX] --overwrite[=SUFFIX]\n"
+ " Overwrite original listed files by filtered result\n"
+ " --overwrite preserves 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");
version();
}
-void version(void)
+void show_configuration(void)
{
- fprintf(stderr,"Network Kanji Filter Version %s (%s) "
-#if defined(MSDOS) && !defined(__WIN32__) && !defined(__WIN16__) && !defined(__OS2__)
- "for DOS"
+ fprintf(HELP_OUTPUT,
+ "Summary of my nkf " NKF_VERSION " (" NKF_RELEASE_DATE ") configuration:\n"
+ " nkf identity:\n"
+ " " NKF_IDENT "\n"
+ " Compile-time options:\n"
+ " Compiled at: " __DATE__ " " __TIME__ "\n"
+ );
+ fprintf(HELP_OUTPUT,
+ " Default output encoding: "
+#ifdef DEFAULT_ENCIDX
+ "%s\n", nkf_enc_name(nkf_default_encoding())
+#else
+ "%s (%s)\n", nkf_locale_encoding() ? "LOCALE" : "DEFAULT",
+ nkf_enc_name(nkf_default_encoding())
+#endif
+ );
+ fprintf(HELP_OUTPUT,
+ " Default output newline: "
+#if DEFAULT_NEWLINE == CR
+ "CR"
+#elif DEFAULT_NEWLINE == CRLF
+ "CRLF"
+#else
+ "LF"
#endif
-#if defined(MSDOS) && defined(__WIN16__)
- "for Win16"
+ "\n"
+ " Decode MIME encoded string: "
+#if MIME_DECODE_DEFAULT
+ "ON"
+#else
+ "OFF"
#endif
-#if defined(MSDOS) && defined(__WIN32__)
- "for Win32"
+ "\n"
+ " Convert JIS X 0201 Katakana: "
+#if X0201_DEFAULT
+ "ON"
+#else
+ "OFF"
#endif
-#ifdef __OS2__
- "for OS/2"
+ "\n"
+ " --help, --version output: "
+#if HELP_OUTPUT_HELP_OUTPUT
+ "HELP_OUTPUT"
+#else
+ "STDOUT"
#endif
- ,NKF_VERSION,NKF_RELEASE_DATE);
- fprintf(stderr,"\n%s\n",CopyRight);
+ "\n");
}
#endif /*PERL_XS*/
-
-/**
- ** \e$B%Q%C%A@):n<T\e(B
- ** void@merope.pleiades.or.jp (Kusakabe Youichi)
- ** NIDE Naoyuki <nide@ics.nara-wu.ac.jp>
- ** ohta@src.ricoh.co.jp (Junn Ohta)
- ** inouet@strl.nhk.or.jp (Tomoyuki Inoue)
- ** kiri@pulser.win.or.jp (Tetsuaki Kiriyama)
- ** Kimihiko Sato <sato@sail.t.u-tokyo.ac.jp>
- ** a_kuroe@kuroe.aoba.yokohama.jp (Akihiko Kuroe)
- ** kono@ie.u-ryukyu.ac.jp (Shinji Kono)
- ** GHG00637@nifty-serve.or.jp (COW)
- **
- **/
-
-/* end */