aboutsummaryrefslogtreecommitdiff
path: root/src/mbyte.c
diff options
context:
space:
mode:
Diffstat (limited to 'src/mbyte.c')
-rw-r--r--src/mbyte.c4041
1 files changed, 0 insertions, 4041 deletions
diff --git a/src/mbyte.c b/src/mbyte.c
deleted file mode 100644
index 09cb1ce35b..0000000000
--- a/src/mbyte.c
+++ /dev/null
@@ -1,4041 +0,0 @@
-/*
- * VIM - Vi IMproved by Bram Moolenaar
- * Multibyte extensions partly by Sung-Hoon Baek
- *
- * Do ":help uganda" in Vim to read copying and usage conditions.
- * Do ":help credits" in Vim to see a list of people who contributed.
- * See README.txt for an overview of the Vim source code.
- */
-/*
- * mbyte.c: Code specifically for handling multi-byte characters.
- *
- * The encoding used in the core is set with 'encoding'. When 'encoding' is
- * changed, the following four variables are set (for speed).
- * Currently these types of character encodings are supported:
- *
- * "enc_dbcs" When non-zero it tells the type of double byte character
- * encoding (Chinese, Korean, Japanese, etc.).
- * The cell width on the display is equal to the number of
- * bytes. (exception: DBCS_JPNU with first byte 0x8e)
- * Recognizing the first or second byte is difficult, it
- * requires checking a byte sequence from the start.
- * "enc_utf8" When TRUE use Unicode characters in UTF-8 encoding.
- * The cell width on the display needs to be determined from
- * the character value.
- * Recognizing bytes is easy: 0xxx.xxxx is a single-byte
- * char, 10xx.xxxx is a trailing byte, 11xx.xxxx is a leading
- * byte of a multi-byte character.
- * To make things complicated, up to six composing characters
- * are allowed. These are drawn on top of the first char.
- * For most editing the sequence of bytes with composing
- * characters included is considered to be one character.
- * "enc_unicode" When 2 use 16-bit Unicode characters (or UTF-16).
- * When 4 use 32-but Unicode characters.
- * Internally characters are stored in UTF-8 encoding to
- * avoid NUL bytes. Conversion happens when doing I/O.
- * "enc_utf8" will also be TRUE.
- *
- * "has_mbyte" is set when "enc_dbcs" or "enc_utf8" is non-zero.
- *
- * If none of these is TRUE, 8-bit bytes are used for a character. The
- * encoding isn't currently specified (TODO).
- *
- * 'encoding' specifies the encoding used in the core. This is in registers,
- * text manipulation, buffers, etc. Conversion has to be done when characters
- * in another encoding are received or send:
- *
- * clipboard
- * ^
- * | (2)
- * V
- * +---------------+
- * (1) | | (3)
- * keyboard ----->| core |-----> display
- * | |
- * +---------------+
- * ^
- * | (4)
- * V
- * file
- *
- * (1) Typed characters arrive in the current locale. Conversion is to be
- * done when 'encoding' is different from 'termencoding'.
- * (2) Text will be made available with the encoding specified with
- * 'encoding'. If this is not sufficient, system-specific conversion
- * might be required.
- * (3) For the GUI the correct font must be selected, no conversion done.
- * Otherwise, conversion is to be done when 'encoding' differs from
- * 'termencoding'. (Different in the GTK+ 2 port -- 'termencoding'
- * is always used for both input and output and must always be set to
- * "utf-8". gui_mch_init() does this automatically.)
- * (4) The encoding of the file is specified with 'fileencoding'. Conversion
- * is to be done when it's different from 'encoding'.
- *
- * The viminfo file is a special case: Only text is converted, not file names.
- * Vim scripts may contain an ":encoding" command. This has an effect for
- * some commands, like ":menutrans"
- */
-
-#include <string.h>
-# include <wchar.h>
-
-#include "vim.h"
-#include "mbyte.h"
-#include "charset.h"
-#include "fileio.h"
-#include "memline.h"
-#include "message.h"
-#include "misc1.h"
-#include "misc2.h"
-#include "memory.h"
-#include "option.h"
-#include "screen.h"
-#include "spell.h"
-#include "ui.h"
-#include "os/os.h"
-
-# define WINBYTE BYTE
-
-static int enc_canon_search(char_u *name);
-static int dbcs_char2len(int c);
-static int dbcs_char2bytes(int c, char_u *buf);
-static int dbcs_ptr2len(char_u *p);
-static int dbcs_ptr2len_len(char_u *p, int size);
-static int utf_ptr2cells_len(char_u *p, int size);
-static int dbcs_char2cells(int c);
-static int dbcs_ptr2cells_len(char_u *p, int size);
-static int dbcs_ptr2char(char_u *p);
-static int utf_safe_read_char_adv(char_u **s, size_t *n);
-
-/*
- * Lookup table to quickly get the length in bytes of a UTF-8 character from
- * the first byte of a UTF-8 string.
- * Bytes which are illegal when used as the first byte have a 1.
- * The NUL byte has length 1.
- */
-static char utf8len_tab[256] =
-{
- 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,
- 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
- 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
- 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
- 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
- 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
- 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
- 3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1,
-};
-
-/*
- * Like utf8len_tab above, but using a zero for illegal lead bytes.
- */
-static char utf8len_tab_zero[256] =
-{
- 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,
- 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
- 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
- 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
- 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
- 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
- 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
- 3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,0,0,
-};
-
-/*
- * Canonical encoding names and their properties.
- * "iso-8859-n" is handled by enc_canonize() directly.
- */
-static struct
-{ char *name; int prop; int codepage; }
-enc_canon_table[] =
-{
-#define IDX_LATIN_1 0
- {"latin1", ENC_8BIT + ENC_LATIN1, 1252},
-#define IDX_ISO_2 1
- {"iso-8859-2", ENC_8BIT, 0},
-#define IDX_ISO_3 2
- {"iso-8859-3", ENC_8BIT, 0},
-#define IDX_ISO_4 3
- {"iso-8859-4", ENC_8BIT, 0},
-#define IDX_ISO_5 4
- {"iso-8859-5", ENC_8BIT, 0},
-#define IDX_ISO_6 5
- {"iso-8859-6", ENC_8BIT, 0},
-#define IDX_ISO_7 6
- {"iso-8859-7", ENC_8BIT, 0},
-#define IDX_ISO_8 7
- {"iso-8859-8", ENC_8BIT, 0},
-#define IDX_ISO_9 8
- {"iso-8859-9", ENC_8BIT, 0},
-#define IDX_ISO_10 9
- {"iso-8859-10", ENC_8BIT, 0},
-#define IDX_ISO_11 10
- {"iso-8859-11", ENC_8BIT, 0},
-#define IDX_ISO_13 11
- {"iso-8859-13", ENC_8BIT, 0},
-#define IDX_ISO_14 12
- {"iso-8859-14", ENC_8BIT, 0},
-#define IDX_ISO_15 13
- {"iso-8859-15", ENC_8BIT + ENC_LATIN9, 0},
-#define IDX_KOI8_R 14
- {"koi8-r", ENC_8BIT, 0},
-#define IDX_KOI8_U 15
- {"koi8-u", ENC_8BIT, 0},
-#define IDX_UTF8 16
- {"utf-8", ENC_UNICODE, 0},
-#define IDX_UCS2 17
- {"ucs-2", ENC_UNICODE + ENC_ENDIAN_B + ENC_2BYTE, 0},
-#define IDX_UCS2LE 18
- {"ucs-2le", ENC_UNICODE + ENC_ENDIAN_L + ENC_2BYTE, 0},
-#define IDX_UTF16 19
- {"utf-16", ENC_UNICODE + ENC_ENDIAN_B + ENC_2WORD, 0},
-#define IDX_UTF16LE 20
- {"utf-16le", ENC_UNICODE + ENC_ENDIAN_L + ENC_2WORD, 0},
-#define IDX_UCS4 21
- {"ucs-4", ENC_UNICODE + ENC_ENDIAN_B + ENC_4BYTE, 0},
-#define IDX_UCS4LE 22
- {"ucs-4le", ENC_UNICODE + ENC_ENDIAN_L + ENC_4BYTE, 0},
-
- /* For debugging DBCS encoding on Unix. */
-#define IDX_DEBUG 23
- {"debug", ENC_DBCS, DBCS_DEBUG},
-#define IDX_EUC_JP 24
- {"euc-jp", ENC_DBCS, DBCS_JPNU},
-#define IDX_SJIS 25
- {"sjis", ENC_DBCS, DBCS_JPN},
-#define IDX_EUC_KR 26
- {"euc-kr", ENC_DBCS, DBCS_KORU},
-#define IDX_EUC_CN 27
- {"euc-cn", ENC_DBCS, DBCS_CHSU},
-#define IDX_EUC_TW 28
- {"euc-tw", ENC_DBCS, DBCS_CHTU},
-#define IDX_BIG5 29
- {"big5", ENC_DBCS, DBCS_CHT},
-
- /* MS-DOS and MS-Windows codepages are included here, so that they can be
- * used on Unix too. Most of them are similar to ISO-8859 encodings, but
- * not exactly the same. */
-#define IDX_CP437 30
- {"cp437", ENC_8BIT, 437}, /* like iso-8859-1 */
-#define IDX_CP737 31
- {"cp737", ENC_8BIT, 737}, /* like iso-8859-7 */
-#define IDX_CP775 32
- {"cp775", ENC_8BIT, 775}, /* Baltic */
-#define IDX_CP850 33
- {"cp850", ENC_8BIT, 850}, /* like iso-8859-4 */
-#define IDX_CP852 34
- {"cp852", ENC_8BIT, 852}, /* like iso-8859-1 */
-#define IDX_CP855 35
- {"cp855", ENC_8BIT, 855}, /* like iso-8859-2 */
-#define IDX_CP857 36
- {"cp857", ENC_8BIT, 857}, /* like iso-8859-5 */
-#define IDX_CP860 37
- {"cp860", ENC_8BIT, 860}, /* like iso-8859-9 */
-#define IDX_CP861 38
- {"cp861", ENC_8BIT, 861}, /* like iso-8859-1 */
-#define IDX_CP862 39
- {"cp862", ENC_8BIT, 862}, /* like iso-8859-1 */
-#define IDX_CP863 40
- {"cp863", ENC_8BIT, 863}, /* like iso-8859-8 */
-#define IDX_CP865 41
- {"cp865", ENC_8BIT, 865}, /* like iso-8859-1 */
-#define IDX_CP866 42
- {"cp866", ENC_8BIT, 866}, /* like iso-8859-5 */
-#define IDX_CP869 43
- {"cp869", ENC_8BIT, 869}, /* like iso-8859-7 */
-#define IDX_CP874 44
- {"cp874", ENC_8BIT, 874}, /* Thai */
-#define IDX_CP932 45
- {"cp932", ENC_DBCS, DBCS_JPN},
-#define IDX_CP936 46
- {"cp936", ENC_DBCS, DBCS_CHS},
-#define IDX_CP949 47
- {"cp949", ENC_DBCS, DBCS_KOR},
-#define IDX_CP950 48
- {"cp950", ENC_DBCS, DBCS_CHT},
-#define IDX_CP1250 49
- {"cp1250", ENC_8BIT, 1250}, /* Czech, Polish, etc. */
-#define IDX_CP1251 50
- {"cp1251", ENC_8BIT, 1251}, /* Cyrillic */
- /* cp1252 is considered to be equal to latin1 */
-#define IDX_CP1253 51
- {"cp1253", ENC_8BIT, 1253}, /* Greek */
-#define IDX_CP1254 52
- {"cp1254", ENC_8BIT, 1254}, /* Turkish */
-#define IDX_CP1255 53
- {"cp1255", ENC_8BIT, 1255}, /* Hebrew */
-#define IDX_CP1256 54
- {"cp1256", ENC_8BIT, 1256}, /* Arabic */
-#define IDX_CP1257 55
- {"cp1257", ENC_8BIT, 1257}, /* Baltic */
-#define IDX_CP1258 56
- {"cp1258", ENC_8BIT, 1258}, /* Vietnamese */
-
-#define IDX_MACROMAN 57
- {"macroman", ENC_8BIT + ENC_MACROMAN, 0}, /* Mac OS */
-#define IDX_DECMCS 58
- {"dec-mcs", ENC_8BIT, 0}, /* DEC MCS */
-#define IDX_HPROMAN8 59
- {"hp-roman8", ENC_8BIT, 0}, /* HP Roman8 */
-#define IDX_COUNT 60
-};
-
-/*
- * Aliases for encoding names.
- */
-static struct
-{ char *name; int canon; }
-enc_alias_table[] =
-{
- {"ansi", IDX_LATIN_1},
- {"iso-8859-1", IDX_LATIN_1},
- {"latin2", IDX_ISO_2},
- {"latin3", IDX_ISO_3},
- {"latin4", IDX_ISO_4},
- {"cyrillic", IDX_ISO_5},
- {"arabic", IDX_ISO_6},
- {"greek", IDX_ISO_7},
- {"hebrew", IDX_ISO_8},
- {"latin5", IDX_ISO_9},
- {"turkish", IDX_ISO_9}, /* ? */
- {"latin6", IDX_ISO_10},
- {"nordic", IDX_ISO_10}, /* ? */
- {"thai", IDX_ISO_11}, /* ? */
- {"latin7", IDX_ISO_13},
- {"latin8", IDX_ISO_14},
- {"latin9", IDX_ISO_15},
- {"utf8", IDX_UTF8},
- {"unicode", IDX_UCS2},
- {"ucs2", IDX_UCS2},
- {"ucs2be", IDX_UCS2},
- {"ucs-2be", IDX_UCS2},
- {"ucs2le", IDX_UCS2LE},
- {"utf16", IDX_UTF16},
- {"utf16be", IDX_UTF16},
- {"utf-16be", IDX_UTF16},
- {"utf16le", IDX_UTF16LE},
- {"ucs4", IDX_UCS4},
- {"ucs4be", IDX_UCS4},
- {"ucs-4be", IDX_UCS4},
- {"ucs4le", IDX_UCS4LE},
- {"utf32", IDX_UCS4},
- {"utf-32", IDX_UCS4},
- {"utf32be", IDX_UCS4},
- {"utf-32be", IDX_UCS4},
- {"utf32le", IDX_UCS4LE},
- {"utf-32le", IDX_UCS4LE},
- {"932", IDX_CP932},
- {"949", IDX_CP949},
- {"936", IDX_CP936},
- {"gbk", IDX_CP936},
- {"950", IDX_CP950},
- {"eucjp", IDX_EUC_JP},
- {"unix-jis", IDX_EUC_JP},
- {"ujis", IDX_EUC_JP},
- {"shift-jis", IDX_SJIS},
- {"euckr", IDX_EUC_KR},
- {"5601", IDX_EUC_KR}, /* Sun: KS C 5601 */
- {"euccn", IDX_EUC_CN},
- {"gb2312", IDX_EUC_CN},
- {"euctw", IDX_EUC_TW},
- {"japan", IDX_EUC_JP},
- {"korea", IDX_EUC_KR},
- {"prc", IDX_EUC_CN},
- {"chinese", IDX_EUC_CN},
- {"taiwan", IDX_EUC_TW},
- {"cp950", IDX_BIG5},
- {"950", IDX_BIG5},
- {"mac", IDX_MACROMAN},
- {"mac-roman", IDX_MACROMAN},
- {NULL, 0}
-};
-
-#ifndef CP_UTF8
-# define CP_UTF8 65001 /* magic number from winnls.h */
-#endif
-
-/*
- * Find encoding "name" in the list of canonical encoding names.
- * Returns -1 if not found.
- */
-static int enc_canon_search(char_u *name)
-{
- int i;
-
- for (i = 0; i < IDX_COUNT; ++i)
- if (STRCMP(name, enc_canon_table[i].name) == 0)
- return i;
- return -1;
-}
-
-
-
-/*
- * Find canonical encoding "name" in the list and return its properties.
- * Returns 0 if not found.
- */
-int enc_canon_props(char_u *name)
-{
- int i;
-
- i = enc_canon_search(name);
- if (i >= 0)
- return enc_canon_table[i].prop;
- if (STRNCMP(name, "2byte-", 6) == 0)
- return ENC_DBCS;
- if (STRNCMP(name, "8bit-", 5) == 0 || STRNCMP(name, "iso-8859-", 9) == 0)
- return ENC_8BIT;
- return 0;
-}
-
-/*
- * Set up for using multi-byte characters.
- * Called in three cases:
- * - by main() to initialize (p_enc == NULL)
- * - by set_init_1() after 'encoding' was set to its default.
- * - by do_set() when 'encoding' has been set.
- * p_enc must have been passed through enc_canonize() already.
- * Sets the "enc_unicode", "enc_utf8", "enc_dbcs" and "has_mbyte" flags.
- * Fills mb_bytelen_tab[] and returns NULL when there are no problems.
- * When there is something wrong: Returns an error message and doesn't change
- * anything.
- */
-char_u * mb_init()
-{
- int i;
- int idx;
- int n;
- int enc_dbcs_new = 0;
-#if defined(USE_ICONV) && !defined(WIN3264) && !defined(WIN32UNIX) \
- && !defined(MACOS)
-# define LEN_FROM_CONV
- vimconv_T vimconv;
- char_u *p;
-#endif
-
- if (p_enc == NULL) {
- /* Just starting up: set the whole table to one's. */
- for (i = 0; i < 256; ++i)
- mb_bytelen_tab[i] = 1;
- input_conv.vc_type = CONV_NONE;
- input_conv.vc_factor = 1;
- output_conv.vc_type = CONV_NONE;
- return NULL;
- } else if (STRNCMP(p_enc, "8bit-", 5) == 0
- || STRNCMP(p_enc, "iso-8859-", 9) == 0) {
- /* Accept any "8bit-" or "iso-8859-" name. */
- enc_unicode = 0;
- enc_utf8 = FALSE;
- } else if (STRNCMP(p_enc, "2byte-", 6) == 0) {
- /* Unix: accept any "2byte-" name, assume current locale. */
- enc_dbcs_new = DBCS_2BYTE;
- } else if ((idx = enc_canon_search(p_enc)) >= 0) {
- i = enc_canon_table[idx].prop;
- if (i & ENC_UNICODE) {
- /* Unicode */
- enc_utf8 = TRUE;
- if (i & (ENC_2BYTE | ENC_2WORD))
- enc_unicode = 2;
- else if (i & ENC_4BYTE)
- enc_unicode = 4;
- else
- enc_unicode = 0;
- } else if (i & ENC_DBCS) {
- /* 2byte, handle below */
- enc_dbcs_new = enc_canon_table[idx].codepage;
- } else {
- /* Must be 8-bit. */
- enc_unicode = 0;
- enc_utf8 = FALSE;
- }
- } else /* Don't know what encoding this is, reject it. */
- return e_invarg;
-
- if (enc_dbcs_new != 0) {
- enc_unicode = 0;
- enc_utf8 = FALSE;
- }
- enc_dbcs = enc_dbcs_new;
- has_mbyte = (enc_dbcs != 0 || enc_utf8);
-
-
- /* Detect an encoding that uses latin1 characters. */
- enc_latin1like = (enc_utf8 || STRCMP(p_enc, "latin1") == 0
- || STRCMP(p_enc, "iso-8859-15") == 0);
-
- /*
- * Set the function pointers.
- */
- if (enc_utf8) {
- mb_ptr2len = utfc_ptr2len;
- mb_ptr2len_len = utfc_ptr2len_len;
- mb_char2len = utf_char2len;
- mb_char2bytes = utf_char2bytes;
- mb_ptr2cells = utf_ptr2cells;
- mb_ptr2cells_len = utf_ptr2cells_len;
- mb_char2cells = utf_char2cells;
- mb_off2cells = utf_off2cells;
- mb_ptr2char = utf_ptr2char;
- mb_head_off = utf_head_off;
- } else if (enc_dbcs != 0) {
- mb_ptr2len = dbcs_ptr2len;
- mb_ptr2len_len = dbcs_ptr2len_len;
- mb_char2len = dbcs_char2len;
- mb_char2bytes = dbcs_char2bytes;
- mb_ptr2cells = dbcs_ptr2cells;
- mb_ptr2cells_len = dbcs_ptr2cells_len;
- mb_char2cells = dbcs_char2cells;
- mb_off2cells = dbcs_off2cells;
- mb_ptr2char = dbcs_ptr2char;
- mb_head_off = dbcs_head_off;
- } else {
- mb_ptr2len = latin_ptr2len;
- mb_ptr2len_len = latin_ptr2len_len;
- mb_char2len = latin_char2len;
- mb_char2bytes = latin_char2bytes;
- mb_ptr2cells = latin_ptr2cells;
- mb_ptr2cells_len = latin_ptr2cells_len;
- mb_char2cells = latin_char2cells;
- mb_off2cells = latin_off2cells;
- mb_ptr2char = latin_ptr2char;
- mb_head_off = latin_head_off;
- }
-
- /*
- * Fill the mb_bytelen_tab[] for MB_BYTE2LEN().
- */
-#ifdef LEN_FROM_CONV
- /* When 'encoding' is different from the current locale mblen() won't
- * work. Use conversion to "utf-8" instead. */
- vimconv.vc_type = CONV_NONE;
- if (enc_dbcs) {
- p = enc_locale();
- if (p == NULL || STRCMP(p, p_enc) != 0) {
- convert_setup(&vimconv, p_enc, (char_u *)"utf-8");
- vimconv.vc_fail = TRUE;
- }
- free(p);
- }
-#endif
-
- for (i = 0; i < 256; ++i) {
- /* Our own function to reliably check the length of UTF-8 characters,
- * independent of mblen(). */
- if (enc_utf8)
- n = utf8len_tab[i];
- else if (enc_dbcs == 0)
- n = 1;
- else {
- char buf[MB_MAXBYTES + 1];
- if (i == NUL) /* just in case mblen() can't handle "" */
- n = 1;
- else {
- buf[0] = i;
- buf[1] = 0;
-#ifdef LEN_FROM_CONV
- if (vimconv.vc_type != CONV_NONE) {
- /*
- * string_convert() should fail when converting the first
- * byte of a double-byte character.
- */
- p = string_convert(&vimconv, (char_u *)buf, NULL);
- if (p != NULL) {
- free(p);
- n = 1;
- } else
- n = 2;
- } else
-#endif
- {
- /*
- * mblen() should return -1 for invalid (means the leading
- * multibyte) character. However there are some platforms
- * where mblen() returns 0 for invalid character.
- * Therefore, following condition includes 0.
- */
- ignored = mblen(NULL, 0); /* First reset the state. */
- if (mblen(buf, (size_t)1) <= 0)
- n = 2;
- else
- n = 1;
- }
- }
- }
- mb_bytelen_tab[i] = n;
- }
-
-#ifdef LEN_FROM_CONV
- convert_setup(&vimconv, NULL, NULL);
-#endif
-
- /* The cell width depends on the type of multi-byte characters. */
- (void)init_chartab();
-
- /* When enc_utf8 is set or reset, (de)allocate ScreenLinesUC[] */
- screenalloc(FALSE);
-
- /* When using Unicode, set default for 'fileencodings'. */
- if (enc_utf8 && !option_was_set((char_u *)"fencs"))
- set_string_option_direct((char_u *)"fencs", -1,
- (char_u *)"ucs-bom,utf-8,default,latin1", OPT_FREE, 0);
-
-#ifdef HAVE_WORKING_LIBINTL
- /* GNU gettext 0.10.37 supports this feature: set the codeset used for
- * translated messages independently from the current locale. */
- (void)bind_textdomain_codeset(VIMPACKAGE,
- enc_utf8 ? "utf-8" : (char *)p_enc);
-#endif
-
-
- /* Fire an autocommand to let people do custom font setup. This must be
- * after Vim has been setup for the new encoding. */
- apply_autocmds(EVENT_ENCODINGCHANGED, NULL, (char_u *)"", FALSE, curbuf);
-
- /* Need to reload spell dictionaries */
- spell_reload();
-
- return NULL;
-}
-
-/*
- * Return the size of the BOM for the current buffer:
- * 0 - no BOM
- * 2 - UCS-2 or UTF-16 BOM
- * 4 - UCS-4 BOM
- * 3 - UTF-8 BOM
- */
-int bomb_size()
-{
- int n = 0;
-
- if (curbuf->b_p_bomb && !curbuf->b_p_bin) {
- if (*curbuf->b_p_fenc == NUL) {
- if (enc_utf8) {
- if (enc_unicode != 0)
- n = enc_unicode;
- else
- n = 3;
- }
- } else if (STRCMP(curbuf->b_p_fenc, "utf-8") == 0)
- n = 3;
- else if (STRNCMP(curbuf->b_p_fenc, "ucs-2", 5) == 0
- || STRNCMP(curbuf->b_p_fenc, "utf-16", 6) == 0)
- n = 2;
- else if (STRNCMP(curbuf->b_p_fenc, "ucs-4", 5) == 0)
- n = 4;
- }
- return n;
-}
-
-/*
- * Remove all BOM from "s" by moving remaining text.
- */
-void remove_bom(char_u *s)
-{
- if (enc_utf8) {
- char_u *p = s;
-
- while ((p = vim_strbyte(p, 0xef)) != NULL) {
- if (p[1] == 0xbb && p[2] == 0xbf)
- STRMOVE(p, p + 3);
- else
- ++p;
- }
- }
-}
-
-/*
- * Get class of pointer:
- * 0 for blank or NUL
- * 1 for punctuation
- * 2 for an (ASCII) word character
- * >2 for other word characters
- */
-int mb_get_class(char_u *p)
-{
- return mb_get_class_buf(p, curbuf);
-}
-
-int mb_get_class_buf(char_u *p, buf_T *buf)
-{
- if (MB_BYTE2LEN(p[0]) == 1) {
- if (p[0] == NUL || vim_iswhite(p[0]))
- return 0;
- if (vim_iswordc_buf(p[0], buf))
- return 2;
- return 1;
- }
- if (enc_dbcs != 0 && p[0] != NUL && p[1] != NUL)
- return dbcs_class(p[0], p[1]);
- if (enc_utf8)
- return utf_class(utf_ptr2char(p));
- return 0;
-}
-
-/*
- * Get class of a double-byte character. This always returns 3 or bigger.
- * TODO: Should return 1 for punctuation.
- */
-int dbcs_class(unsigned lead, unsigned trail)
-{
- switch (enc_dbcs) {
- /* please add classify routine for your language in here */
-
- case DBCS_JPNU: /* ? */
- case DBCS_JPN:
- {
- /* JIS code classification */
- unsigned char lb = lead;
- unsigned char tb = trail;
-
- /* convert process code to JIS */
- /*
- * XXX: Code page identification can not use with all
- * system! So, some other encoding information
- * will be needed.
- * In japanese: SJIS,EUC,UNICODE,(JIS)
- * Note that JIS-code system don't use as
- * process code in most system because it uses
- * escape sequences(JIS is context depend encoding).
- */
- /* assume process code is JAPANESE-EUC */
- lb &= 0x7f;
- tb &= 0x7f;
- /* exceptions */
- switch (lb << 8 | tb) {
- case 0x2121: /* ZENKAKU space */
- return 0;
- case 0x2122: /* TOU-TEN (Japanese comma) */
- case 0x2123: /* KU-TEN (Japanese period) */
- case 0x2124: /* ZENKAKU comma */
- case 0x2125: /* ZENKAKU period */
- return 1;
- case 0x213c: /* prolongedsound handled as KATAKANA */
- return 13;
- }
- /* sieved by KU code */
- switch (lb) {
- case 0x21:
- case 0x22:
- /* special symbols */
- return 10;
- case 0x23:
- /* alpha-numeric */
- return 11;
- case 0x24:
- /* hiragana */
- return 12;
- case 0x25:
- /* katakana */
- return 13;
- case 0x26:
- /* greek */
- return 14;
- case 0x27:
- /* russian */
- return 15;
- case 0x28:
- /* lines */
- return 16;
- default:
- /* kanji */
- return 17;
- }
- }
-
- case DBCS_KORU: /* ? */
- case DBCS_KOR:
- {
- /* KS code classification */
- unsigned char c1 = lead;
- unsigned char c2 = trail;
-
- /*
- * 20 : Hangul
- * 21 : Hanja
- * 22 : Symbols
- * 23 : Alpha-numeric/Roman Letter (Full width)
- * 24 : Hangul Letter(Alphabet)
- * 25 : Roman Numeral/Greek Letter
- * 26 : Box Drawings
- * 27 : Unit Symbols
- * 28 : Circled/Parenthesized Letter
- * 29 : Hiragana/Katakana
- * 30 : Cyrillic Letter
- */
-
- if (c1 >= 0xB0 && c1 <= 0xC8)
- /* Hangul */
- return 20;
-
- else if (c1 >= 0xCA && c1 <= 0xFD)
- /* Hanja */
- return 21;
- else switch (c1) {
- case 0xA1:
- case 0xA2:
- /* Symbols */
- return 22;
- case 0xA3:
- /* Alpha-numeric */
- return 23;
- case 0xA4:
- /* Hangul Letter(Alphabet) */
- return 24;
- case 0xA5:
- /* Roman Numeral/Greek Letter */
- return 25;
- case 0xA6:
- /* Box Drawings */
- return 26;
- case 0xA7:
- /* Unit Symbols */
- return 27;
- case 0xA8:
- case 0xA9:
- if (c2 <= 0xAF)
- return 25; /* Roman Letter */
- else if (c2 >= 0xF6)
- return 22; /* Symbols */
- else
- /* Circled/Parenthesized Letter */
- return 28;
- case 0xAA:
- case 0xAB:
- /* Hiragana/Katakana */
- return 29;
- case 0xAC:
- /* Cyrillic Letter */
- return 30;
- }
- }
- default:
- break;
- }
- return 3;
-}
-
-/*
- * mb_char2len() function pointer.
- * Return length in bytes of character "c".
- * Returns 1 for a single-byte character.
- */
-int latin_char2len(int c)
-{
- return 1;
-}
-
-static int dbcs_char2len(int c)
-{
- if (c >= 0x100)
- return 2;
- return 1;
-}
-
-/*
- * mb_char2bytes() function pointer.
- * Convert a character to its bytes.
- * Returns the length in bytes.
- */
-int latin_char2bytes(int c, char_u *buf)
-{
- buf[0] = c;
- return 1;
-}
-
-static int dbcs_char2bytes(int c, char_u *buf)
-{
- if (c >= 0x100) {
- buf[0] = (unsigned)c >> 8;
- buf[1] = c;
- /* Never use a NUL byte, it causes lots of trouble. It's an invalid
- * character anyway. */
- if (buf[1] == NUL)
- buf[1] = '\n';
- return 2;
- }
- buf[0] = c;
- return 1;
-}
-
-/*
- * mb_ptr2len() function pointer.
- * Get byte length of character at "*p" but stop at a NUL.
- * For UTF-8 this includes following composing characters.
- * Returns 0 when *p is NUL.
- */
-int latin_ptr2len(char_u *p)
-{
- return MB_BYTE2LEN(*p);
-}
-
-static int dbcs_ptr2len(char_u *p)
-{
- int len;
-
- /* Check if second byte is not missing. */
- len = MB_BYTE2LEN(*p);
- if (len == 2 && p[1] == NUL)
- len = 1;
- return len;
-}
-
-/*
- * mb_ptr2len_len() function pointer.
- * Like mb_ptr2len(), but limit to read "size" bytes.
- * Returns 0 for an empty string.
- * Returns 1 for an illegal char or an incomplete byte sequence.
- */
-int latin_ptr2len_len(char_u *p, int size)
-{
- if (size < 1 || *p == NUL)
- return 0;
- return 1;
-}
-
-static int dbcs_ptr2len_len(char_u *p, int size)
-{
- int len;
-
- if (size < 1 || *p == NUL)
- return 0;
- if (size == 1)
- return 1;
- /* Check that second byte is not missing. */
- len = MB_BYTE2LEN(*p);
- if (len == 2 && p[1] == NUL)
- len = 1;
- return len;
-}
-
-struct interval {
- long first;
- long last;
-};
-static int intable(struct interval *table, size_t size, int c);
-
-/*
- * Return TRUE if "c" is in "table[size / sizeof(struct interval)]".
- */
-static int intable(struct interval *table, size_t size, int c)
-{
- int mid, bot, top;
-
- /* first quick check for Latin1 etc. characters */
- if (c < table[0].first)
- return FALSE;
-
- /* binary search in table */
- bot = 0;
- top = (int)(size / sizeof(struct interval) - 1);
- while (top >= bot) {
- mid = (bot + top) / 2;
- if (table[mid].last < c)
- bot = mid + 1;
- else if (table[mid].first > c)
- top = mid - 1;
- else
- return TRUE;
- }
- return FALSE;
-}
-
-/*
- * For UTF-8 character "c" return 2 for a double-width character, 1 for others.
- * Returns 4 or 6 for an unprintable character.
- * Is only correct for characters >= 0x80.
- * When p_ambw is "double", return 2 for a character with East Asian Width
- * class 'A'(mbiguous).
- */
-int utf_char2cells(int c)
-{
- /* Sorted list of non-overlapping intervals of East Asian double width
- * characters, generated with ../runtime/tools/unicode.vim. */
- static struct interval doublewidth[] =
- {
- {0x1100, 0x115f},
- {0x11a3, 0x11a7},
- {0x11fa, 0x11ff},
- {0x2329, 0x232a},
- {0x2e80, 0x2e99},
- {0x2e9b, 0x2ef3},
- {0x2f00, 0x2fd5},
- {0x2ff0, 0x2ffb},
- {0x3000, 0x3029},
- {0x3030, 0x303e},
- {0x3041, 0x3096},
- {0x309b, 0x30ff},
- {0x3105, 0x312d},
- {0x3131, 0x318e},
- {0x3190, 0x31b7},
- {0x31c0, 0x31e3},
- {0x31f0, 0x321e},
- {0x3220, 0x3247},
- {0x3250, 0x32fe},
- {0x3300, 0x4dbf},
- {0x4e00, 0xa48c},
- {0xa490, 0xa4c6},
- {0xa960, 0xa97c},
- {0xac00, 0xd7a3},
- {0xd7b0, 0xd7c6},
- {0xd7cb, 0xd7fb},
- {0xf900, 0xfaff},
- {0xfe10, 0xfe19},
- {0xfe30, 0xfe52},
- {0xfe54, 0xfe66},
- {0xfe68, 0xfe6b},
- {0xff01, 0xff60},
- {0xffe0, 0xffe6},
- {0x1f200, 0x1f200},
- {0x1f210, 0x1f231},
- {0x1f240, 0x1f248},
- {0x20000, 0x2fffd},
- {0x30000, 0x3fffd}
- };
- /* Sorted list of non-overlapping intervals of East Asian Ambiguous
- * characters, generated with ../runtime/tools/unicode.vim. */
- static struct interval ambiguous[] =
- {
- {0x00a1, 0x00a1},
- {0x00a4, 0x00a4},
- {0x00a7, 0x00a8},
- {0x00aa, 0x00aa},
- {0x00ad, 0x00ae},
- {0x00b0, 0x00b4},
- {0x00b6, 0x00ba},
- {0x00bc, 0x00bf},
- {0x00c6, 0x00c6},
- {0x00d0, 0x00d0},
- {0x00d7, 0x00d8},
- {0x00de, 0x00e1},
- {0x00e6, 0x00e6},
- {0x00e8, 0x00ea},
- {0x00ec, 0x00ed},
- {0x00f0, 0x00f0},
- {0x00f2, 0x00f3},
- {0x00f7, 0x00fa},
- {0x00fc, 0x00fc},
- {0x00fe, 0x00fe},
- {0x0101, 0x0101},
- {0x0111, 0x0111},
- {0x0113, 0x0113},
- {0x011b, 0x011b},
- {0x0126, 0x0127},
- {0x012b, 0x012b},
- {0x0131, 0x0133},
- {0x0138, 0x0138},
- {0x013f, 0x0142},
- {0x0144, 0x0144},
- {0x0148, 0x014b},
- {0x014d, 0x014d},
- {0x0152, 0x0153},
- {0x0166, 0x0167},
- {0x016b, 0x016b},
- {0x01ce, 0x01ce},
- {0x01d0, 0x01d0},
- {0x01d2, 0x01d2},
- {0x01d4, 0x01d4},
- {0x01d6, 0x01d6},
- {0x01d8, 0x01d8},
- {0x01da, 0x01da},
- {0x01dc, 0x01dc},
- {0x0251, 0x0251},
- {0x0261, 0x0261},
- {0x02c4, 0x02c4},
- {0x02c7, 0x02c7},
- {0x02c9, 0x02cb},
- {0x02cd, 0x02cd},
- {0x02d0, 0x02d0},
- {0x02d8, 0x02db},
- {0x02dd, 0x02dd},
- {0x02df, 0x02df},
- {0x0391, 0x03a1},
- {0x03a3, 0x03a9},
- {0x03b1, 0x03c1},
- {0x03c3, 0x03c9},
- {0x0401, 0x0401},
- {0x0410, 0x044f},
- {0x0451, 0x0451},
- {0x2010, 0x2010},
- {0x2013, 0x2016},
- {0x2018, 0x2019},
- {0x201c, 0x201d},
- {0x2020, 0x2022},
- {0x2024, 0x2027},
- {0x2030, 0x2030},
- {0x2032, 0x2033},
- {0x2035, 0x2035},
- {0x203b, 0x203b},
- {0x203e, 0x203e},
- {0x2074, 0x2074},
- {0x207f, 0x207f},
- {0x2081, 0x2084},
- {0x20ac, 0x20ac},
- {0x2103, 0x2103},
- {0x2105, 0x2105},
- {0x2109, 0x2109},
- {0x2113, 0x2113},
- {0x2116, 0x2116},
- {0x2121, 0x2122},
- {0x2126, 0x2126},
- {0x212b, 0x212b},
- {0x2153, 0x2154},
- {0x215b, 0x215e},
- {0x2160, 0x216b},
- {0x2170, 0x2179},
- {0x2189, 0x2189},
- {0x2190, 0x2199},
- {0x21b8, 0x21b9},
- {0x21d2, 0x21d2},
- {0x21d4, 0x21d4},
- {0x21e7, 0x21e7},
- {0x2200, 0x2200},
- {0x2202, 0x2203},
- {0x2207, 0x2208},
- {0x220b, 0x220b},
- {0x220f, 0x220f},
- {0x2211, 0x2211},
- {0x2215, 0x2215},
- {0x221a, 0x221a},
- {0x221d, 0x2220},
- {0x2223, 0x2223},
- {0x2225, 0x2225},
- {0x2227, 0x222c},
- {0x222e, 0x222e},
- {0x2234, 0x2237},
- {0x223c, 0x223d},
- {0x2248, 0x2248},
- {0x224c, 0x224c},
- {0x2252, 0x2252},
- {0x2260, 0x2261},
- {0x2264, 0x2267},
- {0x226a, 0x226b},
- {0x226e, 0x226f},
- {0x2282, 0x2283},
- {0x2286, 0x2287},
- {0x2295, 0x2295},
- {0x2299, 0x2299},
- {0x22a5, 0x22a5},
- {0x22bf, 0x22bf},
- {0x2312, 0x2312},
- {0x2460, 0x24e9},
- {0x24eb, 0x254b},
- {0x2550, 0x2573},
- {0x2580, 0x258f},
- {0x2592, 0x2595},
- {0x25a0, 0x25a1},
- {0x25a3, 0x25a9},
- {0x25b2, 0x25b3},
- {0x25b6, 0x25b7},
- {0x25bc, 0x25bd},
- {0x25c0, 0x25c1},
- {0x2