static CharsetTable *get_charset_table(void)
{
static CharsetTable *ctable = NULL;
EncArray *encarray;
gint i;
if (!ctable) {
ctable = g_malloc(sizeof(CharsetTable));
ctable->num = 0;
ctable->charset[ctable->num] = get_default_charset();
ctable->str[ctable->num] = g_strdup_printf(_("Current Locale (%s)"), get_default_charset());
ctable->num++;
ctable->charset[ctable->num] = "UTF-8";
ctable->str[ctable->num] = ctable->charset[ctable->num];
ctable->num++;
encarray = get_encoding_items(get_encoding_code());
for (i = 0; i < ENCODING_MAX_ITEM_NUM; i++)
if (encarray->item[i]) {
ctable->charset[ctable->num] = encarray->item[i];
ctable->str[ctable->num] = encarray->item[i];
ctable->num++;
}
}
return ctable;
}
static const gchar *detect_charset_cylillic(const gchar *text)
{
guint8 c = *text;
gboolean noniso = FALSE;
guint32 xc = 0, xd = 0, xef = 0;
const gchar *charset = get_encoding_items(get_encoding_code())->item[OPENI18N];
while ((c = *text++) != '\0') {
if (c >= 0x80 && c <= 0x9F)
noniso = TRUE;
else if (c >= 0xC0 && c <= 0xCF)
xc++;
else if (c >= 0xD0 && c <= 0xDF)
xd++;
else if (c >= 0xE0)
xef++;
}
if (!noniso && ((xc + xef) < xd))
charset = "ISO-8859-5";
else if ((xc + xd) < xef)
charset = "CP1251";
return charset;
}
static const gchar *detect_charset_chinese(const gchar *text)
{
guint8 c = *text;
const gchar *charset = get_encoding_items(get_encoding_code())->item[IANA];
while ((c = *text++) != '\0') {
if (c >= 0x81 && c <= 0x87) {
charset = "GB18030";
break;
}
else if (c >= 0x88 && c <= 0xA0) {
c = *text++;
if ((c >= 0x30 && c <= 0x39) || (c >= 0x80 && c <= 0xA0)) {
charset = "GB18030";
break;
} //else GBK/Big5-HKSCS cannot determine
}
else if ((c >= 0xA1 && c <= 0xC6) || (c >= 0xC9 && c <= 0xF9)) {
c = *text++;
if (c >= 0x40 && c <= 0x7E)
charset = "BIG5";
else if ((c >= 0x30 && c <= 0x39) || (c >= 0x80 && c <= 0xA0)) {
charset = "GB18030";
break;
}
}
else if (c >= 0xC7) {
c = *text++;
if ((c >= 0x30 && c <= 0x39) || (c >= 0x80 && c <= 0xA0)) {
charset = "GB18030";
break;
}
}
}
return charset;
}
static void parse_args(gint argc, gchar **argv, FileInfo *fi)
{
EncArray *encarray;
gint i;
GError *error = NULL;
#if GLIB_CHECK_VERSION(2, 6, 0)
GOptionContext *context;
gchar *opt_codeset = NULL;
gint opt_tab_width = 0;
gboolean opt_jump = 0;
gboolean opt_version = FALSE;
GOptionEntry entries[] =
{
{ "codeset", 0, 0, G_OPTION_ARG_STRING, &opt_codeset, "Set codeset to open file", "CODESET" },
{ "tab-width", 0, 0, G_OPTION_ARG_INT, &opt_tab_width, "Set tab width", "WIDTH" },
{ "jump", 0, 0, G_OPTION_ARG_INT, &opt_jump, "Jump to specified line", "LINENUM" },
{ "version", 0, 0, G_OPTION_ARG_NONE, &opt_version, "Show version number", NULL },
{ NULL }
};
//Structure defined in glib for entries and commandline option parser
//4th argument is an enum defined in glib
context = g_option_context_new("[Filename]"); //Creates new context for option parsing
g_option_context_add_main_entries(context, entries, PACKAGE); //PACKAGE == Translation Domain ??
g_option_context_add_group(context, gtk_get_option_group(TRUE));
g_option_context_set_ignore_unknown_options(context, FALSE); //sets error when unknown command
g_option_context_parse(context, &argc, &argv, &error); //passes the arguments
g_option_context_free(context); //free for gcontext
if (error) {
g_print("%s: %s\n", PACKAGE, error->message); //things to do for each option
g_error_free(error);
exit(-1);
}
if (opt_version) {
g_print("%s\n", PACKAGE_STRING);
exit(0);
}
if (opt_codeset) {
g_convert("TEST", -1, "UTF-8", opt_codeset, NULL, NULL, &error);
if (error) {
g_error_free(error);
error = NULL;
} else {
g_free(fi->charset);
fi->charset = g_strdup(opt_codeset);
}
}
if (opt_tab_width)
indent_set_default_tab_width(opt_tab_width);
if (opt_jump)
jump_linenum = opt_jump;
#else //code for older version of glib
gint c; //getopt also parses the command line argument
do {
c = getopt_long(argc, argv, "", longopts, NULL);
switch (c) {
case 0:
if (optarg) {
g_convert("TEST", -1, "UTF-8", optarg, NULL, NULL, &error);
if (error) {
g_error_free(error);
error = NULL;
} else {
g_free(fi->charset);
fi->charset = g_strdup(optarg);
}
}
break;
case 't':
if (optarg)
indent_set_default_tab_width(atoi(optarg));
break;
case 'j':
if (optarg)
jump_linenum = atoi(optarg);
break;
case 'v':
g_print("%s\n", PACKAGE_STRING);
exit(0);
case '?':
print_usage();
exit(0);
}
} while (c != -1);
#endif
if (fi->charset //Find fileinfo encarray data structure
&& (g_strcasecmp(fi->charset, get_default_charset()) != 0)
&& (g_strcasecmp(fi->charset, "UTF-8") != 0)) {
encarray = get_encoding_items(get_encoding_code());
for (i = 0; i < ENCODING_MAX_ITEM_NUM; i++)
if (encarray->item[i])
if (g_strcasecmp(fi->charset, encarray->item[i]) == 0)
break;
if (i == ENCODING_MAX_ITEM_NUM)
fi->charset_flag = TRUE;
}
#if GLIB_CHECK_VERSION(2, 6, 0)
if (argc >= 2)
fi->filename = parse_file_uri(argv[1]);
#else
if (optind < argc)
fi->filename = parse_file_uri(argv[optind]);
#endif
}
const gchar *detect_charset(const gchar *text)
{
guint8 c = *text;
const gchar *charset = NULL;
if (g_utf8_validate(text, -1, NULL)) {
while ((c = *text++) != '\0') {
if (c > 0x7F) {
charset = "UTF-8";
break;
}
if (c == 0x1B) /* ESC */ {
c = *text++;
if (c == '$') {
c = *text++;
switch (c) {
case 'B': // JIS X 0208-1983
case '@': // JIS X 0208-1978
charset = "ISO-2022-JP";
continue;
case 'A': // GB2312-1980
charset = "ISO-2022-JP-2";
break;
case '(':
c = *text++;
switch (c) {
case 'C': // KSC5601-1987
case 'D': // JIS X 0212-1990
charset = "ISO-2022-JP-2";
}
break;
case ')':
c = *text++;
if (c == 'C')
charset = "ISO-2022-KR"; // KSC5601-1987
}
break;
}
}
}
if (!charset)
charset = get_default_charset();
}
if (!charset) {
switch (get_encoding_code()) {
case LATINC:
case LATINC_UA:
case LATINC_TJ:
charset = detect_charset_cylillic(text); // fuzzy...
break;
case CHINESE_CN:
case CHINESE_TW:
case CHINESE_HK:
charset = detect_charset_chinese(text);
break;
case JAPANESE:
charset = detect_charset_japanese(text);
break;
case KOREAN:
charset = detect_charset_korean(text);
break;
case VIETNAMESE:
case THAI:
case GEORGIAN:
charset = get_encoding_items(get_encoding_code())->item[OPENI18N];
break;
default:
if (strcmp(get_default_charset(), "UTF-8") != 0)
charset = get_default_charset();
else if (detect_noniso(text))
charset = get_encoding_items(get_encoding_code())->item[CODEPAGE];
else
charset = get_encoding_items(get_encoding_code())->item[OPENI18N];
if (!charset)
charset = get_encoding_items(get_encoding_code())->item[IANA];
}
}
return charset;
}
static void parse_args(gint argc, gchar **argv, FileInfo *fi)
{
EncArray *encarray;
gint i;
GError *error = NULL;
GOptionContext *context;
gchar *opt_codeset = NULL;
gint opt_tab_width = 0;
gboolean opt_jump = 0;
gboolean opt_version = FALSE;
GOptionEntry entries[] =
{
{ "codeset", 0, 0, G_OPTION_ARG_STRING, &opt_codeset, "Set codeset to open file", "CODESET" },
{ "tab-width", 0, 0, G_OPTION_ARG_INT, &opt_tab_width, "Set tab width", "WIDTH" },
{ "jump", 0, 0, G_OPTION_ARG_INT, &opt_jump, "Jump to specified line", "LINENUM" },
{ "version", 0, 0, G_OPTION_ARG_NONE, &opt_version, "Show version number", NULL },
{ NULL, 0, 0, G_OPTION_ARG_NONE, NULL, NULL, NULL }
};
context = g_option_context_new("[filename]");
g_option_context_add_main_entries(context, entries, PACKAGE);
g_option_context_add_group(context, gtk_get_option_group(TRUE));
g_option_context_set_ignore_unknown_options(context, FALSE);
g_option_context_parse(context, &argc, &argv, &error);
g_option_context_free(context);
if (error) {
g_print("%s: %s\n", PACKAGE, error->message);
g_error_free(error);
exit(-1);
}
if (opt_version) {
g_print("%s\n", PACKAGE_STRING);
exit(0);
}
if (opt_codeset) {
g_convert("TEST", -1, "UTF-8", opt_codeset, NULL, NULL, &error);
if (error) {
g_error_free(error);
error = NULL;
} else {
g_free(fi->charset);
fi->charset = g_strdup(opt_codeset);
}
}
if (opt_tab_width)
indent_set_default_tab_width(opt_tab_width);
if (opt_jump)
jump_linenum = opt_jump;
if (fi->charset
&& (g_ascii_strcasecmp(fi->charset, get_default_charset()) != 0)
&& (g_ascii_strcasecmp(fi->charset, "UTF-8") != 0)) {
encarray = get_encoding_items(get_encoding_code());
for (i = 0; i < ENCODING_MAX_ITEM_NUM; i++)
if (encarray->item[i])
if (g_ascii_strcasecmp(fi->charset, encarray->item[i]) == 0)
break;
if (i == ENCODING_MAX_ITEM_NUM)
fi->charset_flag = TRUE;
}
if (argc >= 2)
fi->filename = parse_file_uri(argv[1]);
}
