mirrors/mc
1
0
Fork 0
mirror of https://github.com/MidnightCommander/mc synced 2025-01-01 00:54:24 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'm-utf-8' of ssh://angel_il@midnight-commander.org:2222/git/mc into m-utf-8

Browse Source
This commit is contained in:
Ilia Maslakov 2009-04-16 16:38:05 +00:00
commit 9cb41f7b43
11 changed files with 192 additions and 145 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
edit/edit-widget.h
View File

@ -46,7 +46,7 @@ struct WEdit {
unsigned char *buffers2[MAXBUFF + 1]; /* all data from end of file down to curs2 */
/* UTF8 */
unsigned char charbuf[MB_LEN_MAX];
unsigned char charbuf[4 + 1];
int charpoint;
/* search variables */
long search_start; /* First character to start searching from */

60
edit/editkeys.c
View File

@ -44,6 +44,7 @@
#include "../src/tty.h" /* keys */
#include "../src/charsets.h" /* convert_from_input_c() */
#include "../src/selcodepage.h" /* do_select_codepage() */
#include "../src/main.h" /* display_codepage */
/*
* Ordinary translations. Note that the keys listed first take priority
@ -191,6 +192,8 @@ edit_translate_key (WEdit *edit, long x_key, int *cmd, int *ch)
int char_for_insertion = -1;
int i = 0;
int extmod = 0;
int c;
const edit_key_map_type *key_map = NULL;
switch (edit_key_emulation) {
case EDIT_KEY_EMULATION_NORMAL:
@ -243,23 +246,55 @@ edit_translate_key (WEdit *edit, long x_key, int *cmd, int *ch)
/* an ordinary insertable character */
if (x_key < 256 && !extmod) {
if ( edit->charpoint >= 4 ) {
edit->charpoint = 0;
edit->charbuf[edit->charpoint] = '\0';
}
if ( edit->charpoint < 4 ) {
edit->charbuf[edit->charpoint++] = x_key;
edit->charbuf[edit->charpoint] = '\0';
}
if (!edit->utf8) {
int c = convert_from_input_c (x_key);
if (is_printable (c)) {
char_for_insertion = c;
goto fin;
}
} else {
if (edit->charpoint >= MB_LEN_MAX) {
goto fin;
edit->charpoint = 0;
/* input from 8-bit locale */
if ( str_isutf8 (get_codepage_id( display_codepage )) == 1 ) {
c = convert_from_input_c (x_key);
if (is_printable (c)) {
char_for_insertion = c;
goto fin;
}
} else {
edit->charbuf[edit->charpoint + 1] = '\0';
int res = str_is_valid_char (edit->charbuf, edit->charpoint);
if (res < 0) {
if (res != -2) {
edit->charpoint = 0; /* broken multibyte char, skip */
goto fin;
}
/* not finised multibyte input (in meddle multibyte utf-8 char) */
goto fin;
} else {
if ( g_unichar_isprint (g_utf8_get_char(edit->charbuf)) ) {
c = convert_from_utf_to_current ( edit->charbuf );
edit->charbuf[0] = '\0';
edit->charpoint = 0;
if (is_printable (c)) {
char_for_insertion = c;
goto fin;
}
}
/* unprinteble utf input, skip it */
edit->charbuf[0] = '\0';
edit->charpoint = 0;
goto fin;
}
}
edit->charbuf[edit->charpoint] = x_key;
edit->charpoint++;
} else {
int res = str_is_valid_char (edit->charbuf, edit->charpoint);
mc_log("res:%i, edit->charpoint : %i\n",res, edit->charpoint);
if (res < 0) {
if (res != -2) {
edit->charpoint = 0; /* broken multibyte char, skip */
@ -271,6 +306,7 @@ edit_translate_key (WEdit *edit, long x_key, int *cmd, int *ch)
edit->charbuf[edit->charpoint]='\0';
edit->charpoint = 0;
if ( g_unichar_isprint (g_utf8_get_char(edit->charbuf))) {
mc_log("input:%s \n", edit->charbuf);
char_for_insertion = x_key;
goto fin;
}

32
src/charsets.c
View File

@ -29,6 +29,8 @@
#include "global.h"
#include "charsets.h"
#include "strutil.h" /* utf-8 functions */
#include "main.h"
int n_codepages = 0;
@ -249,4 +251,34 @@ convert_from_input (char *str)
str++;
}
}
unsigned char
convert_from_utf_to_current (char *str)
{
if (!str)
return '.';
unsigned char ch;
char *cp_to = NULL;
GIConv conv;
GString *translated_data;
translated_data = g_string_new ("");
cp_to = g_strdup ( get_codepage_id ( display_codepage ) );
conv = str_crt_conv_to (cp_to);
if (conv != INVALID_CONV) {
if (str_convert (conv, str, translated_data) != ESTR_FAILURE) {
ch = translated_data->str[0];
} else {
ch = '.';
}
str_close_conv (conv);
}
g_free (cp_to);
g_string_free (translated_data, TRUE);
return ch;
}
#endif /* HAVE_CHARSET */

2
src/charsets.h
View File

@ -6,7 +6,6 @@
#define UNKNCHAR '\001'
#define CHARSETS_INDEX "mc.charsets"
extern int n_codepages;
extern unsigned char conv_displ[256];
@ -27,6 +26,7 @@ const char *init_translation_table (int cpsource, int cpdisplay);
void convert_to_display (char *str);
void convert_from_input (char *str);
void convert_string (unsigned char *str);
unsigned char convert_from_utf_to_current (char *str);
/* Convert single characters */
static inline int

17
src/cmd.c
View File

@ -1395,9 +1395,9 @@ static char
char *result;
char *semi;
char *slash;
semi = g_strrstr (path, "#enc:");
if (semi != NULL) {
slash = strchr (semi, PATH_SEP);
if (slash != NULL) {
@ -1410,23 +1410,26 @@ static char
} else {
result = g_strconcat (path, "/#enc:", encoding, NULL);
}
return result;
}
static void
set_panel_encoding (WPanel *panel)
{
char *encoding;
char *encoding = NULL;
char *cd_path;
encoding = input_dialog ("Encoding", "Select encoding", NULL, "");
do_select_codepage ();
encoding = g_strdup( get_codepage_id ( source_codepage ) );
if (encoding) {
cd_path = add_encoding_to_path (panel->cwd, encoding);
if (!do_panel_cd (MENU_PANEL, cd_path, 0))
message (1, MSG_ERROR, _(" Cannot chdir to %s "), cd_path);
g_free (cd_path);
g_free (encoding);
}
}

30
src/strutil.c
View File

@ -37,9 +37,9 @@
//names, that are used for utf-8
static const char *str_utf8_encodings[] = {
"utf-8",
"utf8",
NULL
"utf-8",
"utf8",
NULL
};
// standard 8bit encodings, no wide or multibytes characters
@ -284,17 +284,11 @@ str_translate_char (GIConv conv, char *keys, size_t ch_size,
left = (ch_size == (size_t) (-1)) ? strlen (keys) : ch_size;
cnv = g_iconv (conv, &keys, &left, &output, &out_size);
if (cnv == (size_t) (-1))
{
if (errno == EINVAL)
return ESTR_PROBLEM;
else
return ESTR_FAILURE;
}
else
{
output[0] = '\0';
return 0;
if (cnv == (size_t)(-1)) {
if (errno == EINVAL) return ESTR_PROBLEM; else return ESTR_FAILURE;
} else {
output[0] = '\0';
return 0;
}
}
@ -316,7 +310,6 @@ str_test_encoding_class (const char *encoding, const char **table)
result += (g_ascii_strncasecmp (encoding, table[t],
strlen (table[t])) == 0);
}
return result;
}
@ -351,8 +344,9 @@ str_isutf8 (char *codeset_name)
void
str_init_strings (const char *termenc)
{
codeset = g_strdup ((termenc != NULL)
? termenc : str_detect_termencoding ());
codeset = g_strdup ((termenc != NULL)
? termenc
: str_detect_termencoding ());
str_cnv_not_convert = g_iconv_open (codeset, codeset);
if (str_cnv_not_convert == INVALID_CONV)
@ -425,7 +419,7 @@ str_get_next_char (char *text)
const char *
str_cget_next_char (const char *text)
{
used_class.cnext_char (&text);
used_class.cnext_char(&text);
return text;
}

2
src/strutil8bit.c
View File

@ -490,7 +490,7 @@ str_8bit_offset_to_pos (const char *text, size_t length)
static int
str_8bit_column_to_pos (const char *text, size_t pos)
{
return (int) pos;
return (int)pos;
}
static char *

2
src/strutilascii.c
View File

@ -512,7 +512,7 @@ str_ascii_offset_to_pos (const char *text, size_t length)
static int
str_ascii_column_to_pos (const char *text, size_t pos)
{
return (int) pos;
return (int)pos;
}
static char *

149
src/strutilutf8.c
View File

@ -342,7 +342,6 @@ str_utf8_vfs_convert_to (GIConv coder, const char *string,
result = 0;
}
else
// result = _str_utf8_vfs_convert_to (coder, string, size, buffer);
result = str_nconvert (coder, (char *) string, size, buffer);
return result;
@ -386,44 +385,31 @@ str_utf8_make_make_term_form (const char *text, size_t length)
}
}
}
while (length != 0 && text[0] != '\0')
{
uni = g_utf8_get_char_validated (text, -1);
if ((uni != (gunichar) (-1)) && (uni != (gunichar) (-2)))
{
if (g_unichar_isprint (uni))
{
left = g_unichar_to_utf8 (uni, actual);
actual += left;
if (!str_unichar_iscombiningmark (uni))
{
result.width++;
if (g_unichar_iswide (uni))
result.width++;
}
else
result.compose = 1;
}
else
{
actual[0] = '.';
actual++;
result.width++;
}
text = g_utf8_next_char (text);
}
else
{
text++;
//actual[0] = '?';
memcpy (actual, replch, strlen (replch));
actual += strlen (replch);
result.width++;
}
if (length != (size_t) (-1))
length--;
}
while (length != 0 && text[0] != '\0') {
uni = g_utf8_get_char_validated (text, -1);
if ((uni != (gunichar)(-1)) && (uni != (gunichar)(-2))) {
if (g_unichar_isprint(uni)) {
left = g_unichar_to_utf8 (uni, actual);
actual+= left;
if (!str_unichar_iscombiningmark (uni)) {
result.width++;
if (g_unichar_iswide(uni)) result.width++;
} else result.compose = 1;
} else {
actual[0] = '.';
actual++;
result.width++;
}
text = g_utf8_next_char (text);
} else {
text++;
//actual[0] = '?';
memcpy (actual, replch, strlen (replch));
actual+= strlen (replch);
result.width++;
}
if (length != (size_t) (-1)) length--; }
actual[0] = '\0';
return &result;
@ -1218,51 +1204,48 @@ str_utf8_create_key_gen (const char *text, int case_sen,
gchar * (*keygen) (const gchar *, gssize size))
{
char *result;
if (case_sen) {
result = str_utf8_normalize (text);
} else {
const char *start, *end;
char *fold, *key;
GString *fixed = g_string_new ("");
if (case_sen)
{
result = str_utf8_normalize (text);
}
else
{
const char *start, *end;
char *fold, *key;
GString *fixed = g_string_new ("");
start = text;
while (!g_utf8_validate (start, -1, &end) && start[0] != '\0')
{
if (start != end)
{
fold = g_utf8_casefold (start, end - start);
key = keygen (fold, -1);
g_string_append (fixed, key);
g_free (key);
g_free (fold);
}
g_string_append_c (fixed, end[0]);
start = end + 1;
}
start = text;
while (!g_utf8_validate (start, -1, &end) && start[0] != '\0')
{
if (start != end)
{
fold = g_utf8_casefold (start, end - start);
key = keygen (fold, -1);
g_string_append (fixed, key);
g_free (key);
g_free (fold);
}
g_string_append_c (fixed, end[0]);
start = end + 1;
}
if (start == text)
{
fold = g_utf8_casefold (text, -1);
result = keygen (fold, -1);
g_free (fold);
}
else
{
if (start[0] != '\0' && start != end)
{
fold = g_utf8_casefold (start, end - start);
key = keygen (fold, -1);
g_string_append (fixed, key);
g_free (key);
g_free (fold);
}
result = g_strdup (fixed->str);
}
g_string_free (fixed, TRUE);
if (start == text)
{
fold = g_utf8_casefold (text, -1);
result = keygen (fold, -1);
g_free (fold);
}
else
{
if (start[0] != '\0' && start != end)
{
fold = g_utf8_casefold (start, end - start);
key = keygen (fold, -1);
g_string_append (fixed, key);
g_free (key);
g_free (fold);
}
result = g_strdup (fixed->str);
}
g_string_free (fixed, TRUE);
}
return result;
}
@ -1292,7 +1275,7 @@ str_utf8_release_key (char *key, int case_sen)
g_free (key);
}
struct str_class
struct str_class
str_utf8_init ()
{
struct str_class result;

35
src/view.c
View File

@ -2457,24 +2457,24 @@ view_display_text (WView * view)
} else {
addch ('.');
}
} else {
GString *comb = g_string_new ("");
if (str_isprint (info.cact)) {
g_string_append(comb,info.cact);
} else {
g_string_append(comb,".");
}
while (str_iscombiningmark (info.cnxt)) {
view_read_continue (view, &info);
g_string_append(comb,info.cact);
}
addstr (str_term_form (comb->str));
g_string_free (comb, TRUE);
}
} else {
GString *comb = g_string_new ("");
if (str_isprint (info.cact)) {
g_string_append(comb,info.cact);
} else {
g_string_append(comb,".");
}
while (str_iscombiningmark (info.cnxt)) {
view_read_continue (view, &info);
g_string_append(comb,info.cact);
}
addstr (str_term_form (comb->str));
g_string_free (comb, TRUE);
}
} else {
while (str_iscombiningmark (info.cnxt)) {
view_read_continue (view, &info);
}
while (str_iscombiningmark (info.cnxt)) {
view_read_continue (view, &info);
}
}
col+= w;
@ -2780,7 +2780,6 @@ view_get_line_at (WView *view, offset_type from, GString * buffer,
continue;
if (view_read_test_nroff_back (view, &info)) {
// !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
g_string_truncate (buffer, buffer->len-1);
continue;
}

6
vfs/vfs.c
View File

@ -382,7 +382,7 @@ vfs_supported_enconding (const char *encoding) {
* buffer - used to store result of translation
*/
static int
_vfs_translate_path (const char *path, int size,
_vfs_translate_path (const char *path, int size,
GIConv defcnv, GString *buffer)
{
const char *semi;
@ -459,7 +459,7 @@ char *
vfs_translate_path (const char *path)
{
int state;
g_string_set_size(vfs_str_buffer,0);
state = _vfs_translate_path (path, -1, str_cnv_from_term, vfs_str_buffer);
// strict version
@ -1218,7 +1218,7 @@ vfs_shut (void)
(*vfs->done) (vfs);
g_slist_free (vfs_openfiles);
g_string_free (vfs_str_buffer, TRUE);
}