** E-Mail: furukawa@tcp-ip.or.jp
** \e$B$^$G8fO"Mm$r$*4j$$$7$^$9!#\e(B
***********************************************************************/
-/* $Id: nkf.c,v 1.122 2007/03/15 05:38:59 naruse Exp $ */
+/* $Id: nkf.c,v 1.135 2007/10/01 12:37:58 naruse Exp $ */
#define NKF_VERSION "2.0.8"
-#define NKF_RELEASE_DATE "2007-03-14"
+#define NKF_RELEASE_DATE "2007-10-01"
#include "config.h"
#include "utf8tbl.h"
#define COPY_RIGHT \
"Copyright (C) 1987, FUJITSU LTD. (I.Ichikawa),2000 S. Kono, COW\n" \
- "Copyright (C) 2002-2006 Kono, Furukawa, Naruse, mastodon"
+ "Copyright (C) 2002-2007 Kono, Furukawa, Naruse, mastodon"
/*
#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
#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 )
+#define bin2hex(c) ("0123456789ABCDEF"[c&15])
#define is_eucg3(c2) (((unsigned short)c2 >> 8) == SS3)
#define CP932_TABLE_BEGIN 0xFA
* 0: Shift_JIS, eucJP-ascii
* 1: eucJP-ms
* 2: CP932, CP51932
+ * 3: CP10001
*/
-#define UCS_MAP_ASCII 0
-#define UCS_MAP_MS 1
-#define UCS_MAP_CP932 2
+#define UCS_MAP_ASCII 0
+#define UCS_MAP_MS 1
+#define UCS_MAP_CP932 2
+#define UCS_MAP_CP10001 3
static int ms_ucs_map_f = UCS_MAP_ASCII;
#endif
#ifdef UTF8_INPUT_ENABLE
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 (*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;
/* X0201 kana conversion table */
/* 90-9F A0-DF */
-static const
-unsigned char cv[]= {
+static const unsigned char cv[]= {
0x21,0x21,0x21,0x23,0x21,0x56,0x21,0x57,
0x21,0x22,0x21,0x26,0x25,0x72,0x25,0x21,
0x25,0x23,0x25,0x25,0x25,0x27,0x25,0x29,
/* X0201 kana conversion table for daguten */
/* 90-9F A0-DF */
-static const
-unsigned char dv[]= {
+static const unsigned char dv[]= {
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
/* X0201 kana conversion table for han-daguten */
/* 90-9F A0-DF */
-static const
-unsigned char ev[]= {
+static const unsigned char ev[]= {
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
/* X0208 kigou conversion table */
/* 0x8140 - 0x819e */
-static const
-unsigned char fv[] = {
+static const unsigned char fv[] = {
0x00,0x00,0x00,0x00,0x2c,0x2e,0x00,0x3a,
0x3b,0x3f,0x21,0x00,0x00,0x27,0x60,0x00,
} ;
-#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 int nlmode_f = 0; /* CR, LF, CRLF */
+static nkf_char prev_cr = 0;
#ifdef EASYWIN /*Easy Win */
static int end_check;
#endif /*Easy Win */
}
#endif
-static const
-struct {
+static const struct {
const char *name;
const char *alias;
} long_option[] = {
p = 0;
switch (*cp++) {
case '-': /* literal options */
- if (!*cp || *cp == SPACE) { /* ignore the rest of arguments */
+ 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] == ' '){
+ if (*p == cp[j] || cp[j] == SP){
p = &cp[j] + 1;
break;
}
p = 0;
}
if (p == 0) return;
- while(*cp && *cp != SPACE && cp++);
+ 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){
- for (i=0; i < 16 && SPACE < p[i] && p[i] < DEL; i++){
+ for (i=0; i < 16 && SP < p[i] && p[i] < DEL; i++){
codeset[i] = nkf_toupper(p[i]);
}
codeset[i] = 0;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_CP932;
#endif
+ }else if(strcmp(codeset, "CP10001") == 0){
+ input_f = SJIS_INPUT;
+#ifdef SHIFTJIS_CP932
+ cp51932_f = TRUE;
+#endif
+#ifdef UTF8_OUTPUT_ENABLE
+ ms_ucs_map_f = UCS_MAP_CP10001;
+#endif
}else if(strcmp(codeset, "EUCJP") == 0 ||
strcmp(codeset, "EUC-JP") == 0){
input_f = EUC_INPUT;
}
if (strcmp(long_option[i].name, "oc=") == 0){
x0201_f = FALSE;
- for (i=0; i < 16 && SPACE < p[i] && p[i] < DEL; i++){
+ for (i=0; i < 16 && SP < p[i] && p[i] < DEL; i++){
codeset[i] = nkf_toupper(p[i]);
}
codeset[i] = 0;
#ifdef UTF8_OUTPUT_ENABLE
ms_ucs_map_f = UCS_MAP_CP932;
#endif
+ }else if(strcmp(codeset, "CP10001") == 0){
+ 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){
output_conv = e_oconv;
if (x0201_f==NO_X0201) x0201_f=TRUE;
continue;
case 'Z': /* Convert X0208 alphabet to asii */
- /* bit:0 Convert X0208
- bit:1 Convert Kankaku to one space
- bit:2 Convert Kankaku to two spaces
- bit:3 Convert HTML Entity
+ /* alpha_f
+ bit:0 Convert JIS X 0208 Alphabet to ASCII
+ bit:1 Convert Kankaku to one space
+ bit:2 Convert Kankaku to two spaces
+ bit:3 Convert HTML Entity
+ bit:4 Convert JIS X 0208 Katakana to JIS X 0201 Katakana
*/
- if ('9'>= *cp && *cp>='0')
- alpha_f |= 1<<(*cp++ -'0');
- else
- alpha_f |= TRUE;
+ while ('0'<= *cp && *cp <='9') {
+ alpha_f |= 1 << (*cp++ - '0');
+ }
+ if (!alpha_f) alpha_f = 1;
continue;
case 'x': /* Convert X0201 kana to X0208 or X0201 Conversion */
x0201_f = FALSE; /* No X0201->X0208 conversion */
continue;
#endif
case 'c':/* add cr code */
- crmode_f = CRLF;
+ nlmode_f = CRLF;
continue;
case 'd':/* delete cr code */
- crmode_f = NL;
+ 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':
guess_f = TRUE;
#endif
continue;
- case ' ':
+ case SP:
/* module muliple options in a string are allowed for Perl moudle */
while(*cp && *cp++!='-');
continue;
#define SCORE_INIT (SCORE_iMIME)
-const nkf_char score_table_A0[] = {
+static const char score_table_A0[] = {
0, 0, 0, 0,
0, 0, 0, 0,
0, SCORE_DEPEND, SCORE_DEPEND, SCORE_DEPEND,
SCORE_DEPEND, SCORE_DEPEND, SCORE_DEPEND, SCORE_NO_EXIST,
};
-const nkf_char score_table_F0[] = {
+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,
/* base64_count = 0; */
}
- if (crmode_f) {
- o_crconv = oconv; oconv = cr_conv;
+ if (nlmode_f) {
+ o_nlconv = oconv; oconv = nl_conv;
}
if (rot_f) {
o_rot_conv = oconv; oconv = rot_conv;
} 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;
} else { /* bogus code, skip SSO and one byte */
NEXT;
}
+ } else if (ms_ucs_map_f == UCS_MAP_CP10001 &&
+ (c1 == 0xFD || c1 == 0xFE)) {
+ /* CP10001 */
+ c2 = X0201;
+ c1 &= 0x7f;
+ SEND;
} else {
/* already established */
c2 = c1;
NEXT;
}
}
- } else if ((c1 > SPACE) && (c1 != DEL)) {
+ } else if ((c1 > SP) && (c1 != DEL)) {
/* in case of Roman characters */
if (shift_mode) {
/* output 1 shifted byte */
if (iso8859_f) {
c2 = ISO8859_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) {
(*oconv)(GETA1, GETA2);
/* normal ASCII code */
SEND;
}
- } else if (c1 == SI && (!is_8bit || mime_decode_mode)) {\r
+ } else if (c1 == SI && (!is_8bit || mime_decode_mode)) {
shift_mode = FALSE;
NEXT;
- } else if (c1 == SO && (!is_8bit || mime_decode_mode)) {\r
+ } 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 == '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;
SEND;
C%7 : 0 1 2 3 4 5 6
NUM : 2 0 3 4 5 X 1
*/
- static const int jphone_emoji_first_table[7] = {2, 0, 3, 4, 5, 0, 1};
- c0 = (jphone_emoji_first_table[c1 % 7] << 8) - SPACE + 0xE000 + CLASS_UNICODE;
+ static const char jphone_emoji_first_table[7] = {2, 0, 3, 4, 5, 0, 1};
+ 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) && broken_f&4) {
- input_mode = ASCII; set_iconv(FALSE, 0);
- SEND;
- } else if (c1 == NL && mime_decode_f && !mime_decode_mode ) {
- if ((c1=(*i_getc)(f))!=EOF && c1 == SPACE) {
- i_ungetc(SPACE,f);
- continue;
- } else {
- i_ungetc(c1,f);
- }
- c1 = NL;
- SEND;
- } else if (c1 == CR && mime_decode_f && !mime_decode_mode ) {
- if ((c1=(*i_getc)(f))!=EOF) {
- if (c1==SPACE) {
- i_ungetc(SPACE,f);
- continue;
- } else if (c1 == NL && (c1=(*i_getc)(f))!=EOF && c1 == SPACE) {
- i_ungetc(SPACE,f);
- continue;
- } else {
- i_ungetc(c1,f);
+ } 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 == LF) {
+ if ((c1=(*i_getc)(f))!=EOF && c1 == SP) {
+ i_ungetc(SP,f);
+ continue;
+ } else {
+ i_ungetc(c1,f);
+ }
+ c1 = LF;
+ SEND;
+ } else { /* if (c1 == CR)*/
+ if ((c1=(*i_getc)(f))!=EOF) {
+ if (c1==SP) {
+ i_ungetc(SP,f);
+ continue;
+ } else if (c1 == LF && (c1=(*i_getc)(f))!=EOF && c1 == SP) {
+ i_ungetc(SP,f);
+ continue;
+ } else {
+ i_ungetc(c1,f);
+ }
+ i_ungetc(LF,f);
+ } else {
+ i_ungetc(c1,f);
+ }
+ c1 = CR;
+ SEND;
}
- i_ungetc(NL,f);
- } else {
- i_ungetc(c1,f);
}
- c1 = CR;
- SEND;
+ if (!nlmode_f) {
+ if (prev_cr && c1 == LF) nlmode_f = CRLF;
+ else nlmode_f = c1;
+ }
} else if (c1 == DEL && input_mode == X0208 ) {
/* CP5022x */
c2 = c1;
code_status(c1);
}
while (p->name){
- if (p->score < result->score){
+ if (p->status_func && p->score < result->score){
result = p;
}
++p;
}
- set_iconv(FALSE, result->iconv_func);
+ set_iconv(TRUE, result->iconv_func);
}
#if defined(SHIFTJIS_CP932) || defined(X0212_ENABLE)
nkf_char val;
#endif
- static const nkf_char shift_jisx0213_s1a3_table[5][2] ={ { 1, 8}, { 3, 4}, { 5,12}, {13,14}, {15, 0} };
+ static const char shift_jisx0213_s1a3_table[5][2] ={ { 1, 8}, { 3, 4}, { 5,12}, {13,14}, {15, 0} };
#ifdef SHIFTJIS_CP932
if (!cp932inv_f && is_ibmext_in_sjis(c2)){
-#if 0
- extern const unsigned short shiftjis_cp932[3][189];
-#endif
val = shiftjis_cp932[c2 - CP932_TABLE_BEGIN][c1 - 0x40];
if (val){
c2 = val >> 8;
}
if (cp932inv_f
&& CP932INV_TABLE_BEGIN <= c2 && c2 <= CP932INV_TABLE_END){
-#if 0
- extern const unsigned short cp932inv[2][189];
-#endif
nkf_char c = cp932inv[c2 - CP932INV_TABLE_BEGIN][c1 - 0x40];
if (c){
c2 = c >> 8;
#endif /* SHIFTJIS_CP932 */
#ifdef X0212_ENABLE
if (!x0213_f && is_ibmext_in_sjis(c2)){
-#if 0
- extern const unsigned short shiftjis_x0212[3][189];
-#endif
val = shiftjis_x0212[c2 - 0xfa][c1 - 0x40];
if (val){
if (val > 0x7FFF){
if (0x9E < c1) c2++;
}
if (c1 < 0x9F)
- c1 = c1 - ((c1 > DEL) ? SPACE : 0x1F);
+ c1 = c1 - ((c1 > DEL) ? SP : 0x1F);
else {
c1 = c1 - 0x7E;
}
{
if (c2 == X0201) {
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 */
} else if (c2 == SSO){
c2 = X0201;
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) {
nkf_char w_iconv(nkf_char c2, nkf_char c1, nkf_char c0)
{
nkf_char ret = 0;
- static const int w_iconv_utf8_1st_byte[] =
+ static const char w_iconv_utf8_1st_byte[] =
{ /* 0xC0 - 0xFF */
20, 20, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21,
21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21,
nkf_char unicode_to_jis_common(nkf_char c2, nkf_char c1, nkf_char c0, nkf_char *p2, nkf_char *p1)
{
-#if 0
- extern const unsigned short *const utf8_to_euc_2bytes[];
- extern const unsigned short *const utf8_to_euc_2bytes_ms[];
- extern const unsigned short *const utf8_to_euc_2bytes_932[];
- extern const unsigned short *const *const utf8_to_euc_3bytes[];
- extern const unsigned short *const *const utf8_to_euc_3bytes_ms[];
- extern const unsigned short *const *const utf8_to_euc_3bytes_932[];
-#endif
const unsigned short *const *pp;
const unsigned short *const *const *ppp;
- static const int no_best_fit_chars_table_C2[] =
+ static const char no_best_fit_chars_table_C2[] =
{1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 2, 1, 1, 2,
0, 0, 1, 1, 0, 1, 0, 1, 2, 1, 1, 1, 1, 1, 1, 1};
- static const int no_best_fit_chars_table_C2_ms[] =
+ static const char no_best_fit_chars_table_C2_ms[] =
{1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0,
0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 0};
- static const int no_best_fit_chars_table_932_C2[] =
+ static const char no_best_fit_chars_table_932_C2[] =
{1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1,
0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0};
- static const int no_best_fit_chars_table_932_C3[] =
+ static const char no_best_fit_chars_table_932_C3[] =
{1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
}
}else if(ms_ucs_map_f == UCS_MAP_MS){
if(c2 == 0xC2 && no_best_fit_chars_table_C2_ms[c1&0x3F]) return 1;
+ }else if(ms_ucs_map_f == UCS_MAP_CP10001){
+ switch(c2){
+ case 0xC2:
+ switch(c1){
+ case 0xA2:
+ case 0xA3:
+ case 0xA5:
+ case 0xA6:
+ case 0xAC:
+ case 0xAF:
+ case 0xB8:
+ return 1;
+ }
+ break;
+ }
}
}
pp =
ms_ucs_map_f == UCS_MAP_CP932 ? utf8_to_euc_2bytes_932 :
ms_ucs_map_f == UCS_MAP_MS ? utf8_to_euc_2bytes_ms :
+ ms_ucs_map_f == UCS_MAP_CP10001 ? utf8_to_euc_2bytes_mac :
utf8_to_euc_2bytes;
ret = w_iconv_common(c2, c1, pp, sizeof_utf8_to_euc_2bytes, p2, p1);
}else if(c0 < 0xF0){
if(c1 == 0x80 || c0 == 0x9C) return 1;
break;
}
+ }else if(ms_ucs_map_f == UCS_MAP_CP10001){
+ switch(c2){
+ case 0xE3:
+ switch(c1){
+ case 0x82:
+ if(c0 == 0x94) return 1;
+ break;
+ case 0x83:
+ if(c0 == 0xBB) return 1;
+ break;
+ }
+ break;
+ }
}else{
switch(c2){
case 0xE2:
ppp =
ms_ucs_map_f == UCS_MAP_CP932 ? utf8_to_euc_3bytes_932 :
ms_ucs_map_f == UCS_MAP_MS ? utf8_to_euc_3bytes_ms :
+ ms_ucs_map_f == UCS_MAP_CP10001 ? utf8_to_euc_3bytes_mac :
utf8_to_euc_3bytes;
ret = w_iconv_common(c1, c0, ppp[c2 - 0xE0], sizeof_utf8_to_euc_C2, p2, p1);
}else return -1;
void nkf_each_char_to_hex(void (*f)(nkf_char c2,nkf_char c1), nkf_char c)
{
- const char *hex = "0123456789ABCDEF";
int shift = 20;
c &= VALUE_MASK;
while(shift >= 0){
if(c >= 1<<shift){
while(shift >= 0){
- (*f)(0, hex[(c>>shift)&0xF]);
+ (*f)(0, bin2hex(c>>shift));
shift -= 4;
}
}else{
void encode_fallback_java(nkf_char c)
{
- const char *hex = "0123456789ABCDEF";
(*oconv)(0, '\\');
c &= VALUE_MASK;
if(!is_unicode_bmp(c)){
(*oconv)(0, 'U');
(*oconv)(0, '0');
(*oconv)(0, '0');
- (*oconv)(0, hex[(c>>20)&0xF]);
- (*oconv)(0, hex[(c>>16)&0xF]);
+ (*oconv)(0, bin2hex(c>>20));
+ (*oconv)(0, bin2hex(c>>16));
}else{
(*oconv)(0, 'u');
}
- (*oconv)(0, hex[(c>>12)&0xF]);
- (*oconv)(0, hex[(c>> 8)&0xF]);
- (*oconv)(0, hex[(c>> 4)&0xF]);
- (*oconv)(0, hex[ c &0xF]);
+ (*oconv)(0, bin2hex(c>>12));
+ (*oconv)(0, bin2hex(c>> 8));
+ (*oconv)(0, bin2hex(c>> 4));
+ (*oconv)(0, bin2hex(c ));
return;
}
#ifdef UTF8_OUTPUT_ENABLE
nkf_char e2w_conv(nkf_char c2, nkf_char c1)
{
-#if 0
- extern const unsigned short euc_to_utf8_1byte[];
- extern const unsigned short *const euc_to_utf8_2bytes[];
- extern const unsigned short *const euc_to_utf8_2bytes_ms[];
- extern const unsigned short *const x0212_to_utf8_2bytes[];
-#endif
const unsigned short *p;
if (c2 == X0201) {
+ if (ms_ucs_map_f == UCS_MAP_CP10001) {
+ switch (c1) {
+ case 0x20:
+ return 0xA0;
+ case 0x7D:
+ return 0xA9;
+ }
+ }
p = euc_to_utf8_1byte;
#ifdef X0212_ENABLE
} else if (is_eucg3(c2)){
c2 &= 0x7f;
c2 = (c2&0x7f) - 0x21;
if (0<=c2 && c2<sizeof_euc_to_utf8_2bytes)
- p = ms_ucs_map_f != UCS_MAP_ASCII ? euc_to_utf8_2bytes_ms[c2] : euc_to_utf8_2bytes[c2];
+ p =
+ ms_ucs_map_f == UCS_MAP_ASCII ? euc_to_utf8_2bytes[c2] :
+ ms_ucs_map_f == UCS_MAP_CP10001 ? euc_to_utf8_2bytes_mac[c2] :
+ euc_to_utf8_2bytes_ms[c2];
else
return 0;
}
else if(nkf_isgraph(ndx)){
nkf_char val = 0;
const unsigned short *ptr;
-#if 0
- extern const unsigned short *const x0212_shiftjis[];
-#endif
ptr = x0212_shiftjis[ndx - 0x21];
if (ptr){
val = ptr[(c1 & 0x7f) - 0x21];
#ifdef SHIFTJIS_CP932
if (cp932inv_f
&& CP932INV_TABLE_BEGIN <= c2 && c2 <= CP932INV_TABLE_END){
-#if 0
- extern const unsigned short cp932inv[2][189];
-#endif
nkf_char c = cp932inv[c2 - CP932INV_TABLE_BEGIN][c1 - 0x40];
if (c){
c2 = c >> 8;
return c;
}
-static nkf_char prev_cr = 0;
-
-void cr_conv(nkf_char c2, nkf_char c1)
+void nl_conv(nkf_char c2, nkf_char c1)
{
if (prev_cr) {
prev_cr = 0;
- if (! (c2==0&&c1==NL) ) {
- cr_conv(0,'\n');
+ if (! (c2==0&&c1==LF) ) {
+ nl_conv(0,LF);
}
}
if (c2) {
- (*o_crconv)(c2,c1);
- } else if (c1=='\r') {
+ (*o_nlconv)(c2,c1);
+ } else if (c1==CR) {
prev_cr = c1;
- } else if (c1=='\n') {
- if (crmode_f==CRLF) {
- (*o_crconv)(0,'\r');
- } else if (crmode_f==CR) {
- (*o_crconv)(0,'\r');
+ } else if (c1==LF) {
+ if (nlmode_f==CRLF) {
+ (*o_nlconv)(0,CR);
+ } else if (nlmode_f==CR) {
+ (*o_nlconv)(0,CR);
return;
}
- (*o_crconv)(0,NL);
- } else if (c1!='\032' || crmode_f!=NL){
- (*o_crconv)(c2,c1);
+ (*o_nlconv)(0,LF);
+ } else if (c1!='\032' || nlmode_f!=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.
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) {
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 = ' ';
+ 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 = ' ';
+ f_prev = SP;
if (++f_line<=fold_len)
- fold_state = ' '; /* output ASCII space only */
+ 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 {
} 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 */
+ fold_state = LF; /* We can't wait, do fold now */
} else if (c2==X0201) {
/* simple kinsoku rules return 1 means no folding */
if (c1==(0xde&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 */
/* 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$B!,\e(B */
/* default no fold in kinsoku */
else {
- fold_state = '\n';
+ fold_state = LF;
f_line = char_size(c2,c1);
/* add one new f_line before this character */
}
} else {
f_line = char_size(c2,c1);
- fold_state = '\n';
+ fold_state = LF;
/* add one new f_line before this character */
}
}
}
/* terminator process */
switch(fold_state) {
- case '\n':
- (*o_fconv)(0,'\n');
+ case LF:
+ (*o_fconv)(0,LF);
(*o_fconv)(c2,c1);
break;
case 0:
return;
- case '\r':
- (*o_fconv)(0,'\n');
+ case CR:
+ (*o_fconv)(0,LF);
break;
- case '\t':
- case ' ':
- (*o_fconv)(0,' ');
+ case TAB:
+ case SP:
+ (*o_fconv)(0,SP);
break;
default:
(*o_fconv)(c2,c1);
/* if (c2) c1 &= 0x7f; assertion */
- if (x0201_f && z_prev2==X0201) { /* X0201 */
- if (c1==(0xde&0x7f)) { /* \e$BByE@\e(B */
- z_prev2=0;
- (*o_zconv)(dv[(z_prev1-SPACE)*2],dv[(z_prev1-SPACE)*2+1]);
- return;
- } else if (c1==(0xdf&0x7f)&&ev[(z_prev1-SPACE)*2]) { /* \e$BH>ByE@\e(B */
- z_prev2=0;
- (*o_zconv)(ev[(z_prev1-SPACE)*2],ev[(z_prev1-SPACE)*2+1]);
- return;
- } else {
- z_prev2=0;
- (*o_zconv)(cv[(z_prev1-SPACE)*2],cv[(z_prev1-SPACE)*2+1]);
- }
+ if (c2 == X0201 && (c1 == 0x20 || c1 == 0x7D || c1 == 0x7E)) {
+ (*o_zconv)(c2,c1);
+ return;
}
- if (c2==EOF) {
- (*o_zconv)(c2,c1);
- return;
+ if (x0201_f) {
+ if (z_prev2 == X0201) {
+ if (c2 == X0201) {
+ if (c1 == (0xde&0x7f)) { /* \e$BByE@\e(B */
+ z_prev2 = 0;
+ (*o_zconv)(dv[(z_prev1-SP)*2], dv[(z_prev1-SP)*2+1]);
+ return;
+ } else if (c1 == (0xdf&0x7f) && ev[(z_prev1-SP)*2]) { /* \e$BH>ByE@\e(B */
+ z_prev2 = 0;
+ (*o_zconv)(ev[(z_prev1-SP)*2], ev[(z_prev1-SP)*2+1]);
+ return;
+ }
+ }
+ z_prev2 = 0;
+ (*o_zconv)(cv[(z_prev1-SP)*2], cv[(z_prev1-SP)*2+1]);
+ }
+ if (c2 == X0201) {
+ if (dv[(c1-SP)*2] || ev[(c1-SP)*2]) {
+ /* wait for \e$BByE@\e(B or \e$BH>ByE@\e(B */
+ z_prev1 = c1;
+ z_prev2 = c2;
+ return;
+ } else {
+ (*o_zconv)(cv[(c1-SP)*2], cv[(c1-SP)*2+1]);
+ return;
+ }
+ }
}
- if (x0201_f && c2==X0201) {
- if (dv[(c1-SPACE)*2]||ev[(c1-SPACE)*2]) {
- /* wait for \e$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]);
- return;
- }
+ if (c2 == EOF) {
+ (*o_zconv)(c2, c1);
+ return;
}
- /* JISX0208 Alphabet */
- if (alpha_f && c2 == 0x23 ) {
+ if (alpha_f&1 && c2 == 0x23 ) {
+ /* JISX0208 Alphabet */
c2 = 0;
- } else if (alpha_f && c2 == 0x21 ) {
- /* JISX0208 Kigou */
+ } else if (c2 == 0x21) {
+ /* JISX0208 Kigou */
if (0x21==c1) {
- if (alpha_f&0x2) {
- c1 = ' ';
+ if (alpha_f&2) {
c2 = 0;
- } else if (alpha_f&0x4) {
- (*o_zconv)(0,' ');
- (*o_zconv)(0,' ');
+ c1 = SP;
+ } else if (alpha_f&4) {
+ (*o_zconv)(0, SP);
+ (*o_zconv)(0, SP);
return;
}
- } else if (0x20<c1 && c1<0x7f && fv[c1-0x20]) {
- c1 = fv[c1-0x20];
+ } else if (alpha_f&1 && 0x20<c1 && c1<0x7f && fv[c1-0x20]) {
c2 = 0;
- if (alpha_f&0x8) {
- char *entity = 0;
- switch (c1){
- case '>': entity = ">"; break;
- case '<': entity = "<"; break;
- case '\"': entity = """; break;
- case '&': entity = "&"; break;
- }
- if (entity){
- while (*entity) (*o_zconv)(0, *entity++);
- return;
- }
- }
+ c1 = fv[c1-0x20];
}
}
+
+ if (alpha_f&8 && c2 == 0) {
+ /* HTML Entity */
+ char *entity = 0;
+ switch (c1){
+ case '>': entity = ">"; break;
+ case '<': entity = "<"; break;
+ case '\"': entity = """; break;
+ case '&': entity = "&"; break;
+ }
+ if (entity){
+ while (*entity) (*o_zconv)(0, *entity++);
+ return;
+ }
+ }
+
+ if (alpha_f & 16) {
+ /* JIS X 0208 Katakana to JIS X 0201 Katakana */
+ if (c2 == 0x21) {
+ char c = 0;
+ switch (c1) {
+ case 0x23:
+ /* U+3002 (0x8142) Ideographic Full Stop -> U+FF61 (0xA1) Halfwidth Ideographic Full Stop */
+ c = 0xA1;
+ break;
+ case 0x56:
+ /* U+300C (0x8175) Left Corner Bracket -> U+FF62 (0xA2) Halfwidth Left Corner Bracket */
+ c = 0xA2;
+ break;
+ case 0x57:
+ /* U+300D (0x8176) Right Corner Bracket -> U+FF63 (0xA3) Halfwidth Right Corner Bracket */
+ c = 0xA3;
+ break;
+ case 0x22:
+ /* U+3001 (0x8141) Ideographic Comma -> U+FF64 (0xA4) Halfwidth Ideographic Comma */
+ c = 0xA4;
+ break;
+ case 0x26:
+ /* U+30FB (0x8145) Katakana Middle Dot -> U+FF65 (0xA5) Halfwidth Katakana Middle Dot */
+ c = 0xA5;
+ break;
+ case 0x3C:
+ /* U+30FC (0x815B) Katakana-Hiragana Prolonged Sound Mark -> U+FF70 (0xB0) Halfwidth Katakana-Hiragana Prolonged Sound Mark */
+ c = 0xB0;
+ break;
+ case 0x2B:
+ /* U+309B (0x814A) Katakana-Hiragana Voiced Sound Mark -> U+FF9E (0xDE) Halfwidth Katakana Voiced Sound Mark */
+ c = 0xDE;
+ break;
+ case 0x2C:
+ /* U+309C (0x814B) Katakana-Hiragana Semi-Voiced Sound Mark -> U+FF9F (0xDF) Halfwidth Katakana Semi-Voiced Sound Mark */
+ c = 0xDF;
+ break;
+ }
+ if (c) {
+ (*o_zconv)(X0201, c);
+ return;
+ }
+ } else if (c2 == 0x25) {
+ /* JISX0208 Katakana */
+ static const int fullwidth_to_halfwidth[] =
+ {
+ 0x0000, 0x2700, 0x3100, 0x2800, 0x3200, 0x2900, 0x3300, 0x2A00,
+ 0x3400, 0x2B00, 0x3500, 0x3600, 0x365E, 0x3700, 0x375E, 0x3800,
+ 0x385E, 0x3900, 0x395E, 0x3A00, 0x3A5E, 0x3B00, 0x3B5E, 0x3C00,
+ 0x3C5E, 0x3D00, 0x3D5E, 0x3E00, 0x3E5E, 0x3F00, 0x3F5E, 0x4000,
+ 0x405E, 0x4100, 0x415E, 0x2F00, 0x4200, 0x425E, 0x4300, 0x435E,
+ 0x4400, 0x445E, 0x4500, 0x4600, 0x4700, 0x4800, 0x4900, 0x4A00,
+ 0x4A5E, 0x4A5F, 0x4B00, 0x4B5E, 0x4B5F, 0x4C00, 0x4C5E, 0x4C5F,
+ 0x4D00, 0x4D5E, 0x4D5F, 0x4E00, 0x4E5E, 0x4E5F, 0x4F00, 0x5000,
+ 0x5100, 0x5200, 0x5300, 0x2C00, 0x5400, 0x2D00, 0x5500, 0x2E00,
+ 0x5600, 0x5700, 0x5800, 0x5900, 0x5A00, 0x5B00, 0x0000, 0x5C00,
+ 0x0000, 0x0000, 0x2600, 0x5D00, 0x335E, 0x0000, 0x0000, 0x0000,
+ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000
+ };
+ if (fullwidth_to_halfwidth[c1-0x20]){
+ c2 = fullwidth_to_halfwidth[c1-0x20];
+ (*o_zconv)(X0201, c2>>8);
+ if (c2 & 0xFF) {
+ (*o_zconv)(X0201, c2&0xFF);
+ }
+ return;
+ }
+ }
+ }
(*o_zconv)(c2,c1);
}
/* This converts =?ISO-2022-JP?B?HOGE HOGE?= */
-const unsigned char *mime_pattern[] = {
+static const unsigned char *mime_pattern[] = {
(const unsigned char *)"\075?EUC-JP?B?",
(const unsigned char *)"\075?SHIFT_JIS?B?",
(const unsigned char *)"\075?ISO-8859-1?Q?",
0,
};
-const nkf_char mime_encode[] = {
+static const nkf_char mime_encode[] = {
JAPANESE_EUC, SHIFT_JIS,ISO8859_1, ISO8859_1, X0208, X0201,
#if defined(UTF8_INPUT_ENABLE)
UTF8, UTF8,
0
};
-const nkf_char mime_encode_method[] = {
+static const nkf_char mime_encode_method[] = {
'B', 'B','Q', 'B', 'B', 'Q',
#if defined(UTF8_INPUT_ENABLE)
'B', 'Q',
p = mime_pattern[j];
r[0]='='; r[1]='?';
- for(i=2;p[i]>' ';i++) { /* start at =? */
+ 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;
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'||
+ if (c1==LF||c1==SP||c1==CR||
c1=='-'||c1=='_'||is_alnum(c1) ) continue;
if (c1=='=') {
/* Failed. But this could be another MIME preemble */
void print_guessed_code(char *filename)
{
char *codename = "BINARY";
+ char *str_nlmode = NULL;
if (!is_inputcode_mixed) {
if (strcmp(input_codename, "") == 0) {
codename = "ASCII";
} else {
codename = input_codename;
}
+ if (nlmode_f == CR) str_nlmode = "CR";
+ else if (nlmode_f == LF) str_nlmode = "LF";
+ else if (nlmode_f == CRLF) str_nlmode = "CRLF";
}
if (filename != NULL) printf("%s:", filename);
- printf("%s\n", codename);
+ if (str_nlmode != NULL) printf("%s (%s)\n", codename, str_nlmode);
+ else printf("%s\n", codename);
}
#endif /*WIN32DLL*/
int i=0, j, k=1, lower, upper;
nkf_char buf[9];
const nkf_nfchar *array;
-#if 0
- extern const struct normalization_pair normalization_table[];
-#endif
buf[i] = (*g)(f);
while (k > 0 && ((buf[i] & 0xc0) != 0x80)){
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;
}
}
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));
}
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;
}
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;
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;
(*o_mputc)(mimeout_buf[i]);
i++;
}
- (*o_mputc)(NL);
- (*o_mputc)(SPACE);
+ (*o_mputc)(LF);
+ (*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 )) {
+ && (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 ) {
+ 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 {
{
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)) {
}
}
-nkf_char mime_lastchar2, mime_lastchar1;
+/*nkf_char mime_lastchar2, mime_lastchar1;*/
void mime_prechar(nkf_char c2, nkf_char c1)
{
if (mimeout_mode){
- if (c2){
+ if (c2 == EOF){
+ if (base64_count + mimeout_buf_count/3*4> 73){
+ (*o_base64conv)(EOF,0);
+ (*o_base64conv)(0,LF);
+ (*o_base64conv)(0,SP);
+ }
+ } else if (c2){
if (base64_count + mimeout_buf_count/3*4> 66){
(*o_base64conv)(EOF,0);
- (*o_base64conv)(0,NL);
- (*o_base64conv)(0,SPACE);
+ (*o_base64conv)(0,LF);
+ (*o_base64conv)(0,SP);
}
}/*else if (mime_lastchar2){
if (c1 <=DEL && !nkf_isspace(c1)){
- (*o_base64conv)(0,SPACE);
+ (*o_base64conv)(0,SP);
}
}*/
}/*else{
if (c2 && mime_lastchar2 == 0
&& mime_lastchar1 && !nkf_isspace(mime_lastchar1)){
- (*o_base64conv)(0,SPACE);
+ (*o_base64conv)(0,SP);
}
}*/
- mime_lastchar2 = c2;
- mime_lastchar1 = c1;
+ /*mime_lastchar2 = c2;
+ mime_lastchar1 = c1;*/
}
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);
+ (*o_mputc)(LF);
}
base64_count = 0;
}
}else{
if (base64_count > 71){
eof_mime();
- (*o_mputc)(NL);
+ (*o_mputc)(LF);
base64_count = 0;
}
if (c == EOF) { /* c==EOF */
mimeout_buf_count = 0;
i = 0;
if (mimeout_mode) {
- for (;i<j;i++) {
- if (nkf_isspace(mimeout_buf[i]) && base64_count < 71){
- break;
+ if (!nkf_isblank(mimeout_buf[j-1])) {
+ for (;i<j;i++) {
+ if (nkf_isspace(mimeout_buf[i]) && base64_count < 71){
+ break;
+ }
+ mimeout_addchar(mimeout_buf[i]);
}
- mimeout_addchar(mimeout_buf[i]);
- }
- eof_mime();
- for (;i<j;i++) {
- mimeout_addchar(mimeout_buf[i]);
+ eof_mime();
+ for (;i<j;i++) {
+ mimeout_addchar(mimeout_buf[i]);
+ }
+ } else {
+ for (;i<j;i++) {
+ mimeout_addchar(mimeout_buf[i]);
+ }
+ eof_mime();
}
} else {
for (;i<j;i++) {
if (mimeout_mode=='Q') {
if (c <= DEL && (output_mode==ASCII ||output_mode == ISO8859_1 ) ) {
- if (c == CR || c == NL) {
+ 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);
+ (*o_mputc)(LF);
base64_count = 0;
}
if (!nkf_isblank(c)) {
- (*o_mputc)(SPACE);
+ (*o_mputc)(SP);
base64_count++;
}
}
if (!mimeout_mode) {
if (c <= DEL && (output_mode==ASCII ||output_mode == ISO8859_1)) {
if (nkf_isspace(c)) {
- if (c==CR || c==NL) {
+ if (c==CR || c==LF) {
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++;
}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){
+ (*o_mputc)(LF);
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 (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]);
mimeout_buf_count = 0;
}
}
- 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]);
}
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]);
}
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;
option_mode = 0;
broken_counter = 0;
broken_last = 0;
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[0-3] Convert X0208 alphabet to ASCII\n");
- fprintf(stderr," 1: Kankaku to 1 space 2: to 2 spaces 3: Convert to HTML Entity\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");
#ifdef MSDOS
OSDN Git Service
