* \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 1.143 2007/10/10 19:35:39 naruse Exp $ */
+/* $Id: nkf.c,v 1.156 2007/12/19 08:57:58 naruse Exp $ */
#define NKF_VERSION "2.0.8"
-#define NKF_RELEASE_DATE "2007-10-11"
+#define NKF_RELEASE_DATE "2007-12-19"
#define COPY_RIGHT \
"Copyright (C) 1987, FUJITSU LTD. (I.Ichikawa),2000 S. Kono, COW\n" \
"Copyright (C) 2002-2007 Kono, Furukawa, Naruse, mastodon"
#include "config.h"
#include "utf8tbl.h"
+
+#if defined(DEFAULT_CODE_JIS)
+#elif defined(DEFAULT_CODE_SJIS)
+#elif defined(DEFAULT_CODE_EUC)
+#elif defined(DEFAULT_CODE_UTF8)
+#else
+#define DEFAULT_CODE_JIS 1
+#endif
+
+#ifndef MIME_DECODE_DEFAULT
+#define MIME_DECODE_DEFAULT STRICT_MIME
+#endif
+#ifndef X0201_DEFAULT
+#define X0201_DEFAULT TRUE
+#endif
+
+#if DEFAULT_NEWLINE == 0x0D0A
+#define PUT_NEWLINE(func) do {\
+ func(0x0D);\
+ func(0x0A);\
+} while (0)
+#define OCONV_NEWLINE(func) do {\
+ func(0, 0x0D);\
+ func(0, 0x0A);\
+} while (0)
+#elif DEFAULT_NEWLINE == 0x0D
+#define PUT_NEWLINE(func) func(0x0D)
+#define OCONV_NEWLINE(func) func(0, 0x0D)
+#else
+#define DEFAULT_NEWLINE 0x0A
+#define PUT_NEWLINE(func) func(0x0A)
+#define OCONV_NEWLINE(func) func(0, 0x0A)
+#endif
+
#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__)
/* 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 UTF8_INPUT 13
+#define UTF16_INPUT 1015
+#define UTF32_INPUT 1017
+
#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
/* byte order */
#define ENDIAN_2143 2143
#define ENDIAN_3412 3412
-#define WISH_TRUE 15
-
/* ASCII CODE */
#define BS 0x08
#define SS3 0x8f
#define CRLF 0x0D0A
+
+/* encodings */
+
+enum nkf_encodings {
+ ASCII,
+ JIS_X_0208,
+ JIS_X_0201,
+ 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,
+ JIS_X_0212=0x2844,
+ JIS_X_0213_1=0x284F,
+ JIS_X_0213_2=0x2850,
+ BINARY
+};
+static const struct {
+ const int id;
+ const char *name;
+} encoding_id_to_name_table[] = {
+ {ASCII, "ASCII"},
+ {ISO_8859_1, "ISO-8859-1"},
+ {ISO_2022_JP, "ISO-2022-JP"},
+ {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"},
+ {WINDOWS_31J, "WINDOWS-31J"},
+ {CP10001, "CP10001"},
+ {EUC_JP, "EUC-JP"},
+ {CP51932, "CP51932"},
+ {EUCJP_MS, "eucJP-MS"},
+ {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_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"},
+ {-1, ""}
+};
+static const struct {
+ const char *name;
+ const int id;
+} encoding_name_to_id_table[] = {
+ {"ASCII", ASCII},
+ {"ISO-2022-JP", ISO_2022_JP},
+ {"X-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},
+ {"", -1}
+};
+#if defined(DEFAULT_CODE_JIS)
+#define DEFAULT_ENCODING ISO_2022_JP
+#elif defined(DEFAULT_CODE_SJIS)
+#define DEFAULT_ENCODING SHIFT_JIS
+#elif defined(DEFAULT_CODE_EUC)
+#define DEFAULT_ENCODING EUC_JP
+#elif defined(DEFAULT_CODE_UTF8)
+#define DEFAULT_ENCODING UTF_8
+#endif
+
+
#define is_alnum(c) \
(('a'<=c && c<='z')||('A'<= c && c<='Z')||('0'<=c && c<='9'))
('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
};
static char *input_codename = NULL; /* NULL: unestablished, "": BINARY */
+static int output_encoding = DEFAULT_ENCODING;
-#ifndef PERL_XS
-static const char *CopyRight = COPY_RIGHT;
-#endif
#if !defined(PERL_XS) && !defined(WIN32DLL)
static nkf_char noconvert(FILE *f);
#endif
#ifndef PERL_XS
static void usage(void);
static void version(void);
+static void show_configuration(void);
#endif
static void options(unsigned char *c);
static void reinit(void);
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;
{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 */
#endif
static int nlmode_f = 0; /* CR, LF, CRLF */
-static int input_nextline = 0; /* 0: unestablished, EOF: MIXED */
+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;
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 *str, char *res, size_t length)
+{
+ int i = 0;
+ for (; i < length && str[i]; i++) {
+ res[i] = nkf_toupper(str[i]);
+ }
+ res[i] = 0;
+}
+
+static int nkf_enc_find_index(const char *name)
+{
+ int i, index = -1;
+ 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;
+}
+
+#if defined(PERL_XS) || defined(WIN32DLL)
+static char* nkf_enc_name(const int index)
+{
+ int i;
+ const char* name = "ASCII";
+ for (i = 0; encoding_id_to_name_table[i].id >= 0; i++) {
+ if (encoding_id_to_name_table[i].id == index) {
+ return nkf_strcpy(encoding_id_to_name_table[i].name);
+ }
+ }
+ return nkf_strcpy(name);
+}
+#endif
+
#ifdef WIN32DLL
#include "nkf32dll.c"
#elif defined(PERL_XS)
#ifdef X0212_ENABLE
int x0212_f_back = x0212_f;
#endif
-#ifdef X0212_ENABLE
int x0213_f_back = x0213_f;
-#endif
int guess_f_back = guess_f;
reinit();
guess_f = guess_f_back;
#ifdef X0212_ENABLE
x0212_f = x0212_f_back;
#endif
-#ifdef X0213_ENABLE
x0213_f = x0213_f_back;
-#endif
- }
+ }
#ifdef EXEC_IO
if (exec_f){
int fds[2], pid;
}
#endif
}
- if(x0201_f == WISH_TRUE)
- x0201_f = ((!iso2022jp_f)? TRUE : NO_X0201);
if (binmode_f == TRUE)
#if defined(__OS2__) && (defined(__IBMC__) || defined(__IBMCPP__))
int is_argument_error = FALSE;
while (argc--) {
input_codename = NULL;
- input_nextline = 0;
+ input_newline = 0;
#ifdef CHECK_OPTION
iconv_for_check = 0;
#endif
{"katakana","h2"},
{"katakana-hiragana","h3"},
{"guess=", ""},
- {"guess", "g"},
+ {"guess", "g1"},
{"cp932", ""},
{"no-cp932", ""},
#ifdef X0212_ENABLE
cp = (unsigned char *)long_option[i].alias;
}else{
if (strcmp(long_option[i].name, "ic=") == 0){
- for (i=0; i < 16 && SP < p[i] && p[i] < DEL; i++){
- codeset[i] = nkf_toupper(p[i]);
- }
- codeset[i] = 0;
- if(strcmp(codeset, "ISO-2022-JP") == 0){
+ nkf_str_upcase(p, codeset, 32);
+ i = nkf_enc_find_index(codeset);
+ switch (i) {
+ case ISO_2022_JP:
input_f = JIS_INPUT;
- }else if(strcmp(codeset, "X-ISO2022JP-CP932") == 0 ||
- strcmp(codeset, "CP50220") == 0 ||
- strcmp(codeset, "CP50221") == 0 ||
- strcmp(codeset, "CP50222") == 0){
+ break;
+ case CP50220:
+ case CP50221:
+ case CP50222:
input_f = JIS_INPUT;
#ifdef SHIFTJIS_CP932
cp51932_f = TRUE;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_CP932;
#endif
- }else if(strcmp(codeset, "ISO-2022-JP-1") == 0){
+ break;
+ case ISO_2022_JP_1:
input_f = JIS_INPUT;
#ifdef X0212_ENABLE
x0212_f = TRUE;
#endif
- }else if(strcmp(codeset, "ISO-2022-JP-3") == 0){
+ break;
+ case ISO_2022_JP_3:
input_f = JIS_INPUT;
#ifdef X0212_ENABLE
x0212_f = TRUE;
#endif
x0213_f = TRUE;
- }else if(strcmp(codeset, "SHIFT_JIS") == 0){
+ break;
+ case SHIFT_JIS:
input_f = SJIS_INPUT;
- }else if(strcmp(codeset, "WINDOWS-31J") == 0 ||
- strcmp(codeset, "CSWINDOWS31J") == 0 ||
- strcmp(codeset, "CP932") == 0 ||
- strcmp(codeset, "MS932") == 0){
+ break;
+ case WINDOWS_31J:
input_f = SJIS_INPUT;
#ifdef SHIFTJIS_CP932
cp51932_f = TRUE;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_CP932;
#endif
- }else if(strcmp(codeset, "CP10001") == 0){
+ break;
+ case CP10001:
input_f = SJIS_INPUT;
#ifdef SHIFTJIS_CP932
cp51932_f = TRUE;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_CP10001;
#endif
- }else if(strcmp(codeset, "EUCJP") == 0 ||
- strcmp(codeset, "EUC-JP") == 0){
+ break;
+ case EUC_JP:
input_f = EUC_INPUT;
- }else if(strcmp(codeset, "CP51932") == 0){
+ break;
+ case CP51932:
input_f = EUC_INPUT;
#ifdef SHIFTJIS_CP932
cp51932_f = TRUE;
#ifdef UTF8_OUTPUT_ENABLE
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){
+ break;
+ case EUCJP_MS:
input_f = EUC_INPUT;
#ifdef SHIFTJIS_CP932
cp51932_f = FALSE;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_MS;
#endif
- }else if(strcmp(codeset, "EUC-JP-ASCII") == 0 ||
- strcmp(codeset, "EUCJP-ASCII") == 0){
+ break;
+ case EUCJP_ASCII:
input_f = EUC_INPUT;
#ifdef SHIFTJIS_CP932
cp51932_f = FALSE;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_ASCII;
#endif
- }else if(strcmp(codeset, "SHIFT_JISX0213") == 0 ||
- strcmp(codeset, "SHIFT_JIS-2004") == 0){
+ break;
+ case SHIFT_JISX0213:
+ case SHIFT_JIS_2004:
input_f = SJIS_INPUT;
x0213_f = TRUE;
#ifdef SHIFTJIS_CP932
cp51932_f = FALSE;
#endif
- }else if(strcmp(codeset, "EUC-JISX0213") == 0 ||
- strcmp(codeset, "EUC-JIS-2004") == 0){
+ break;
+ case EUC_JISX0213:
+ case EUC_JIS_2004:
input_f = EUC_INPUT;
x0213_f = TRUE;
#ifdef SHIFTJIS_CP932
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){
+ case UTF_8:
+ case UTF_8N:
+ case UTF_8_BOM:
input_f = UTF8_INPUT;
+ break;
#ifdef UNICODE_NORMALIZATION
- }else if(strcmp(codeset, "UTF8-MAC") == 0 ||
- strcmp(codeset, "UTF-8-MAC") == 0){
+ case UTF8_MAC:
input_f = UTF8_INPUT;
nfc_f = TRUE;
+ break;
#endif
- }else if(strcmp(codeset, "UTF-16") == 0 ||
- strcmp(codeset, "UTF-16BE") == 0 ||
- strcmp(codeset, "UTF-16BE-BOM") == 0){
+ case UTF_16:
+ case UTF_16BE:
+ case UTF_16BE_BOM:
input_f = UTF16_INPUT;
input_endian = ENDIAN_BIG;
- }else if(strcmp(codeset, "UTF-16LE") == 0 ||
- strcmp(codeset, "UTF-16LE-BOM") == 0){
+ break;
+ case UTF_16LE:
+ case UTF_16LE_BOM:
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){
+ break;
+ case UTF_32:
+ case UTF_32BE:
+ case UTF_32BE_BOM:
input_f = UTF32_INPUT;
input_endian = ENDIAN_BIG;
- }else if(strcmp(codeset, "UTF-32LE") == 0 ||
- strcmp(codeset, "UTF-32LE-BOM") == 0){
+ break;
+ case UTF_32LE:
+ case UTF_32LE_BOM:
input_f = UTF32_INPUT;
input_endian = ENDIAN_LITTLE;
+ break;
#endif
- } else {
+ default:
fprintf(stderr, "unknown input encoding: %s\n", codeset);
+ break;
}
continue;
}
if (strcmp(long_option[i].name, "oc=") == 0){
+ nkf_str_upcase(p, codeset, 32);
+ output_encoding = nkf_enc_find_index(codeset);
x0201_f = FALSE;
- for (i=0; i < 16 && SP < 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){
+ switch (output_encoding) {
+ case ISO_2022_JP:
output_conv = j_oconv;
- no_cp932ext_f = TRUE;
-#ifdef SHIFTJIS_CP932
- cp932inv_f = FALSE;
-#endif
-#ifdef UTF8_OUTPUT_ENABLE
- ms_ucs_map_f = UCS_MAP_CP932;
-#endif
- }else if(strcmp(codeset, "CP50220") == 0){
- output_conv = j_oconv;
- x0201_f = TRUE;
+ break;
+ case CP50220:
+ output_conv = j_oconv;
+ x0201_f = TRUE;
#ifdef SHIFTJIS_CP932
- cp932inv_f = FALSE;
+ 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){
+ break;
+ case CP50221:
output_conv = j_oconv;
#ifdef SHIFTJIS_CP932
cp932inv_f = FALSE;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_CP932;
#endif
- }else if(strcmp(codeset, "ISO-2022-JP-1") == 0){
+ break;
+ case ISO_2022_JP_1:
output_conv = j_oconv;
#ifdef X0212_ENABLE
x0212_f = TRUE;
#ifdef SHIFTJIS_CP932
cp932inv_f = FALSE;
#endif
- }else if(strcmp(codeset, "ISO-2022-JP-3") == 0){
+ break;
+ case ISO_2022_JP_3:
output_conv = j_oconv;
#ifdef X0212_ENABLE
x0212_f = TRUE;
#ifdef SHIFTJIS_CP932
cp932inv_f = FALSE;
#endif
- }else if(strcmp(codeset, "SHIFT_JIS") == 0){
+ break;
+ case SHIFT_JIS:
output_conv = s_oconv;
- }else if(strcmp(codeset, "WINDOWS-31J") == 0 ||
- strcmp(codeset, "CSWINDOWS31J") == 0 ||
- strcmp(codeset, "CP932") == 0 ||
- strcmp(codeset, "MS932") == 0){
+ break;
+ case WINDOWS_31J:
output_conv = s_oconv;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_CP932;
#endif
- }else if(strcmp(codeset, "CP10001") == 0){
+ break;
+ case CP10001:
output_conv = s_oconv;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_CP10001;
#endif
- }else if(strcmp(codeset, "EUCJP") == 0 ||
- strcmp(codeset, "EUC-JP") == 0){
+ break;
+ case EUC_JP:
output_conv = e_oconv;
- }else if(strcmp(codeset, "CP51932") == 0){
+ break;
+ case CP51932:
output_conv = e_oconv;
#ifdef SHIFTJIS_CP932
cp932inv_f = FALSE;
#ifdef UTF8_OUTPUT_ENABLE
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){
+ break;
+ case EUCJP_MS:
output_conv = e_oconv;
#ifdef X0212_ENABLE
x0212_f = TRUE;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_MS;
#endif
- }else if(strcmp(codeset, "EUC-JP-ASCII") == 0 ||
- strcmp(codeset, "EUCJP-ASCII") == 0){
+ break;
+ case EUCJP_ASCII:
output_conv = e_oconv;
#ifdef X0212_ENABLE
x0212_f = TRUE;
#ifdef UTF8_OUTPUT_ENABLE
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:
+ output_conv = s_oconv;
+ x0213_f = TRUE;
#ifdef SHIFTJIS_CP932
- cp932inv_f = FALSE;
+ cp932inv_f = FALSE;
#endif
- }else if(strcmp(codeset, "EUC-JISX0213") == 0 ||
- strcmp(codeset, "EUC-JIS-2004") == 0){
+ break;
+ case EUC_JISX0213:
+ case EUC_JIS_2004:
output_conv = e_oconv;
#ifdef X0212_ENABLE
x0212_f = TRUE;
#ifdef SHIFTJIS_CP932
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){
+ case UTF_8:
+ case UTF_8N:
output_conv = w_oconv;
- }else if(strcmp(codeset, "UTF-8-BOM") == 0){
+ break;
+ case UTF_8_BOM:
output_conv = w_oconv;
output_bom_f = TRUE;
- }else if(strcmp(codeset, "UTF-16BE") == 0){
+ break;
+ case UTF_16BE:
output_conv = w_oconv16;
- }else if(strcmp(codeset, "UTF-16") == 0 ||
- strcmp(codeset, "UTF-16BE-BOM") == 0){
+ break;
+ case UTF_16:
+ case UTF_16BE_BOM:
output_conv = w_oconv16;
output_bom_f = TRUE;
- }else if(strcmp(codeset, "UTF-16LE") == 0){
+ break;
+ case UTF_16LE:
output_conv = w_oconv16;
output_endian = ENDIAN_LITTLE;
- }else if(strcmp(codeset, "UTF-16LE-BOM") == 0){
+ break;
+ case UTF_16LE_BOM:
output_conv = w_oconv16;
output_endian = ENDIAN_LITTLE;
output_bom_f = TRUE;
- }else if(strcmp(codeset, "UTF-32") == 0 ||
- strcmp(codeset, "UTF-32BE") == 0){
+ break;
+ case UTF_32:
+ case UTF_32BE:
output_conv = w_oconv32;
- }else if(strcmp(codeset, "UTF-32BE-BOM") == 0){
+ break;
+ case UTF_32BE_BOM:
output_conv = w_oconv32;
output_bom_f = TRUE;
- }else if(strcmp(codeset, "UTF-32LE") == 0){
+ break;
+ case UTF_32LE:
output_conv = w_oconv32;
output_endian = ENDIAN_LITTLE;
- }else if(strcmp(codeset, "UTF-32LE-BOM") == 0){
+ break;
+ case UTF_32LE_BOM:
output_conv = w_oconv32;
output_endian = ENDIAN_LITTLE;
output_bom_f = TRUE;
+ break;
#endif
- } else {
+ default:
fprintf(stderr, "unknown output encoding: %s\n", codeset);
+ break;
}
continue;
}
case 'j': /* JIS output */
case 'n':
output_conv = j_oconv;
+ output_encoding = ISO_2022_JP;
continue;
case 'e': /* AT&T EUC output */
output_conv = e_oconv;
cp932inv_f = FALSE;
+ output_encoding = EUC_JP;
continue;
case 's': /* SJIS output */
output_conv = s_oconv;
+ output_encoding = SHIFT_JIS;
continue;
case 'l': /* ISO8859 Latin-1 support, no conversion */
iso8859_f = TRUE; /* Only compatible with ISO-2022-JP */
#endif
#ifndef PERL_XS
case 'V':
- version();
+ show_configuration();
exit(1);
break;
case 'v':
output_conv = w_oconv; cp++;
if (cp[0] == '0'){
cp++;
+ output_encoding = UTF_8N;
} else {
output_bom_f = TRUE;
+ output_encoding = UTF_8_BOM;
}
} else {
if ('1'== cp[0] && '6'==cp[1]) {
output_conv = w_oconv16; cp+=2;
+ output_encoding = UTF_16;
} else if ('3'== cp[0] && '2'==cp[1]) {
output_conv = w_oconv32; cp+=2;
+ output_encoding = UTF_32;
} else {
output_conv = w_oconv;
+ output_encoding = UTF_8;
continue;
}
if (cp[0]=='L') {
}
if (cp[0] == '0'){
cp++;
+ output_encoding = output_encoding == UTF_16
+ ? (output_endian == ENDIAN_LITTLE ? UTF_16LE : UTF_16BE)
+ : (output_endian == ENDIAN_LITTLE ? UTF_32LE : UTF_32BE);
} else {
output_bom_f = TRUE;
+ output_encoding = output_encoding == UTF_16
+ ? (output_endian == ENDIAN_LITTLE ? UTF_16LE_BOM : UTF_16BE_BOM)
+ : (output_endian == ENDIAN_LITTLE ? UTF_32LE_BOM : UTF_32BE_BOM);
}
}
continue;
continue;
case 'S': /* MS Kanji input */
input_f = SJIS_INPUT;
- if (x0201_f==NO_X0201) x0201_f=TRUE;
continue;
case 'Z': /* Convert X0208 alphabet to asii */
/* alpha_f
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 */
case 'd':/* delete cr code */
nlmode_f = LF;
continue;
- case 'I': /* ISO-2022-JP output */
- iso2022jp_f = TRUE;
- continue;
+ case 'I': /* ISO-2022-JP output */
+ iso2022jp_f = TRUE;
+ continue;
case 'L': /* line mode */
if (*cp=='u') { /* unix */
nlmode_f = LF; cp++;
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 {
if (shift_mode) {
/* output 1 shifted byte */
if (iso8859_f) {
- c2 = ISO8859_1;
+ c2 = ISO_8859_1;
SEND;
} 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;
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
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 == (JIS_X_0213_1&0x7F)){
+ input_mode = JIS_X_0213_1;
shift_mode = FALSE;
NEXT;
- } else if (c1 == (X0213_2&0x7F)){
- input_mode = X0213_2;
+ } else if (c1 == (JIS_X_0213_2&0x7F)){
+ 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 == '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 */
c3 = (*i_getc)(f); /* skip SS2 */
if ( (SP<=c3 && c3 < 0x60) || (0xa0<=c3 && c3 < 0xe0)){
c1 = c3;
- c2 = X0201;
+ c2 = JIS_X_0201;
SEND;
}else{
(*i_ungetc)(c3, f);
SEND;
}
}
- } else if (c1 == DEL && input_mode == X0208) {
+ } else if (c1 == DEL && input_mode == JIS_X_0208) {
/* CP5022x */
c2 = c1;
NEXT;
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:
(*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){
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 < SP) {
/* NOP */
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 < SP) {
/* NOP */
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:
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)) {
} 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);
}
} 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)('$');
(*o_putc)('(');
- (*o_putc)(X0213_2&0x7F);
+ (*o_putc)(JIS_X_0213_2&0x7F);
}
}else{
- if(output_mode!=X0212){
- output_mode = X0212;
+ if(output_mode!=JIS_X_0212){
+ output_mode = JIS_X_0212;
(*o_putc)(ESC);
(*o_putc)('$');
(*o_putc)('(');
- (*o_putc)(X0212&0x7F);
+ (*o_putc)(JIS_X_0212&0x7F);
}
}
(*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 ?
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)('$');
(*o_putc)('(');
- (*o_putc)(X0213_1&0x7F);
+ (*o_putc)(JIS_X_0213_1&0x7F);
}
- }else if (output_mode != X0208) {
- output_mode = X0208;
+ }else if (output_mode != JIS_X_0208) {
+ output_mode = JIS_X_0208;
(*o_putc)(ESC);
(*o_putc)('$');
(*o_putc)(kanji_intro);
}
c= (*i_bgetc)(f);
if (c=='$' && broken_last != ESC
- && (input_mode==ASCII || input_mode==X0201)) {
+ && (input_mode==ASCII || input_mode==JIS_X_0201)) {
c1= (*i_bgetc)(f);
broken_last = 0;
if (c1=='@'|| c1=='B') {
return c;
}
} else if (c=='(' && broken_last != ESC
- && (input_mode==X0208 || input_mode==X0201)) { /* ) */
+ && (input_mode==JIS_X_0208 || input_mode==JIS_X_0201)) { /* ) */
c1= (*i_bgetc)(f);
broken_last = 0;
if (c1=='J'|| c1=='B') {
void nl_conv(nkf_char c2, nkf_char c1)
{
- if (guess_f && input_nextline != EOF) {
+ if (guess_f && input_newline != EOF) {
if (c2 == 0 && c1 == LF) {
- if (!input_nextline) input_nextline = prev_cr ? CRLF : LF;
- else if (input_nextline != (prev_cr ? CRLF : LF)) input_nextline = EOF;
- } else if (c2 == 0 && c1 == CR && input_nextline == LF) input_nextline = EOF;
+ if (!input_newline) input_newline = prev_cr ? CRLF : LF;
+ else if (input_newline != (prev_cr ? CRLF : LF)) input_newline = EOF;
+ } else if (c2 == 0 && c1 == CR && input_newline == LF) input_newline = EOF;
else if (!prev_cr);
- else if (!input_nextline) input_nextline = CR;
- else if (input_nextline != CR) input_nextline = EOF;
+ else if (!input_newline) input_newline = CR;
+ else if (input_newline != CR) input_newline = EOF;
}
- if (prev_cr || c2 == 0 && c1 == LF) {
+ if (prev_cr || (c2 == 0 && c1 == LF)) {
prev_cr = 0;
if (nlmode_f != LF) (*o_nlconv)(0, CR);
if (nlmode_f != CR) (*o_nlconv)(0, LF);
} else {
prev0 = f_prev; /* we still need this one... , but almost done */
f_prev = c1;
- if (c2 || c2==X0201)
+ if (c2 || c2==JIS_X_0201)
f_prev |= 0x80; /* this is Japanese */
f_line += char_size(c2,c1);
if (f_line<=fold_len) { /* normal case */
if (f_line>fold_len+fold_margin) { /* too many kinsoku suspension */
f_line = char_size(c2,c1);
fold_state = LF; /* We can't wait, do fold now */
- } else if (c2==X0201) {
+ } else if (c2==JIS_X_0201) {
/* simple kinsoku rules return 1 means no folding */
if (c1==(0xde&0x7f)) fold_state = 1; /* \e$B!+\e(B*/
else if (c1==(0xdf&0x7f)) fold_state = 1; /* \e$B!,\e(B*/
/* terminator process */
switch(fold_state) {
case LF:
- (*o_fconv)(0,LF);
+ OCONV_NEWLINE((*o_fconv));
(*o_fconv)(c2,c1);
break;
case 0:
return;
case CR:
- (*o_fconv)(0,LF);
+ OCONV_NEWLINE((*o_fconv));
break;
case TAB:
case SP:
/* if (c2) c1 &= 0x7f; assertion */
- if (c2 == X0201 && (c1 == 0x20 || c1 == 0x7D || c1 == 0x7E)) {
+ if (c2 == JIS_X_0201 && (c1 == 0x20 || c1 == 0x7D || c1 == 0x7E)) {
(*o_zconv)(c2,c1);
return;
}
if (x0201_f) {
- if (z_prev2 == X0201) {
- if (c2 == X0201) {
+ if (z_prev2 == JIS_X_0201) {
+ if (c2 == JIS_X_0201) {
if (c1 == (0xde&0x7f)) { /* \e$BByE@\e(B */
z_prev2 = 0;
(*o_zconv)(dv[(z_prev1-SP)*2], dv[(z_prev1-SP)*2+1]);
z_prev2 = 0;
(*o_zconv)(cv[(z_prev1-SP)*2], cv[(z_prev1-SP)*2+1]);
}
- if (c2 == X0201) {
+ 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;
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;
}
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);
};
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
}
}
+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";
+ }
+ }
+ return input_codename;
+}
+
#if !defined(PERL_XS) && !defined(WIN32DLL)
void print_guessed_code(char *filename)
{
- char *codename = "BINARY";
- char *str_nlmode = NULL;
if (filename != NULL) printf("%s: ", filename);
if (input_codename && !*input_codename) {
printf("BINARY\n");
} else {
- struct input_code *p = find_inputcode_byfunc(iconv);
+ input_codename = get_guessed_code();
if (guess_f == 1) {
- printf("%s\n", input_codename ? input_codename : "ASCII");
+ printf("%s\n", input_codename);
} else {
- 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";
- }
printf("%s%s\n",
input_codename,
- input_nextline == CR ? " (CR)" :
- input_nextline == LF ? " (LF)" :
- input_nextline == CRLF ? " (CRLF)" :
- input_nextline == EOF ? " (MIXED NL)" :
+ input_newline == CR ? " (CR)" :
+ input_newline == LF ? " (LF)" :
+ input_newline == CRLF ? " (CRLF)" :
+ input_newline == EOF ? " (MIXED NL)" :
"");
}
}
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)(LF);
+ PUT_NEWLINE((*o_mputc));
(*o_mputc)(SP);
base64_count = 1;
- if (!mimeout_preserve_space && mimeout_buf_count>0
+ 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]==SP || mimeout_buf[i]==TAB
- || mimeout_buf[i]==CR || mimeout_buf[i]==LF) {
- (*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();
} else if (mimeout_mode != 'Q')
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,LF);
+ 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,LF);
- (*o_base64conv)(0,SP);
- }
- }/*else if (mime_lastchar2){
- if (c1 <=DEL && !nkf_isspace(c1)){
+ 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,SP);
}
- }*/
- /*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 (base64_count > 71){
if (c!=CR && c!=LF) {
(*o_mputc)('=');
- (*o_mputc)(LF);
+ PUT_NEWLINE((*o_mputc));
}
base64_count = 0;
}
}else{
if (base64_count > 71){
eof_mime();
- (*o_mputc)(LF);
+ PUT_NEWLINE((*o_mputc));
base64_count = 0;
}
if (c == EOF) { /* c==EOF */
/* 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 <= DEL && (output_mode==ASCII ||output_mode == ISO_8859_1)) {
if (c == CR || c == LF) {
close_mime();
(*o_mputc)(c);
} else if (c <= SP) {
close_mime();
if (base64_count > 70) {
- (*o_mputc)(LF);
+ PUT_NEWLINE((*o_mputc));
base64_count = 0;
}
if (!nkf_isblank(c)) {
(*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)) {
+ int flag = 0;
+ if (mimeout_mode == -1) {
+ flag = 1;
+ }
if (c==CR || c==LF) {
- base64_count=0;
+ 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]);
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] != LF){
- (*o_mputc)(LF);
+ PUT_NEWLINE((*o_mputc));
base64_count = 0;
if (!nkf_isspace(mimeout_buf[0])){
(*o_mputc)(SP);
}
}else{
/* mimeout_mode == 'B', 1, 2 */
- if ( c<=DEL && (output_mode==ASCII ||output_mode == ISO8859_1)) {
+ 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++) {
base64_count = 0;
mimeout_buf_count = 0;
}
+ mimeout_buf[mimeout_buf_count++] = (char)c;
+ return;
}
if (c==SP || c==TAB || c==CR || c==LF) {
for (i=0;i<mimeout_buf_count;i++) {
mimeout_buf_count = 0;
}
return;
- }
+ }
if (mimeout_buf_count>0 && SP<c && c!='=') {
mimeout_buf[mimeout_buf_count++] = (char)c;
if (mimeout_buf_count>MIMEOUT_BUF_LENGTH) {
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;
mime_decode_mode = FALSE;
file_out_f = FALSE;
nlmode_f = 0;
- input_nextline = 0;
+ input_newline = 0;
prev_cr = 0;
option_mode = 0;
broken_counter = 0;
iconv_for_check = 0;
#endif
input_codename = NULL;
+ output_encoding = DEFAULT_ENCODING;
#ifdef WIN32DLL
reinitdll();
#endif /*WIN32DLL*/
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,"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,"v, V Show this usage. V: show configuration\n");
fprintf(stderr,"\n");
fprintf(stderr,"Long name options\n");
fprintf(stderr," --ic=<input codeset> --oc=<output codeset>\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"
-#endif
-#if defined(MSDOS) && defined(__WIN16__)
- "for Win16"
+ fprintf(stderr, "Summary of my nkf " NKF_VERSION " (" NKF_RELEASE_DATE ") configuration:\n");
+ fprintf(stderr, " Compile-time options:\n");
+ fprintf(stderr, " Default output encoding: "
+#if defined(DEFAULT_CODE_JIS)
+ "ISO-2022-JP"
+#elif defined(DEFAULT_CODE_SJIS)
+ "Shift_JIS"
+#elif defined(DEFAULT_CODE_EUC)
+ "EUC-JP"
+#elif defined(DEFAULT_CODE_UTF8)
+ "UTF-8"
+#endif
+ "\n");
+ fprintf(stderr, " Default output newline: "
+#if DEFAULT_NEWLINE == CR
+ "CR"
+#elif DEFAULT_NEWLINE == CRLF
+ "CRLF"
+#else
+ "LF"
#endif
-#if defined(MSDOS) && defined(__WIN32__)
- "for Win32"
+ "\n");
+ fprintf(stderr, " Decode MIME encoded string: "
+#if MIME_DECODE_DEFAULT
+ "ON"
+#else
+ "OFF"
#endif
-#ifdef __OS2__
- "for OS/2"
+ "\n");
+ fprintf(stderr, " Convert JIS X 0201 Katakana: "
+#if X0201_DEFAULT
+ "ON"
+#else
+ "OFF"
#endif
- ,NKF_VERSION,NKF_RELEASE_DATE);
- fprintf(stderr,"\n%s\n",CopyRight);
+ "\n");
+}
+
+void version(void)
+{
+ fprintf(stderr,"Network Kanji Filter Version " NKF_VERSION " (" NKF_RELEASE_DATE ") \n" COPY_RIGHT "\n");
}
#endif /*PERL_XS*/
OSDN Git Service
