/* allocates space and returns the index part of a string */
static char *
_new_get_index(const char *_string)
{
if (!_string)
return NULL;
size_t size;
gunichar u;
char *string = NULL;
if (g_ascii_isalnum(_string[0])) {
size = sizeof(char);
string = malloc(size+1);
string[0] = g_ascii_toupper(_string[0]);
} else {
u = g_utf8_get_char_validated(_string, -1);
if ((u != (gunichar)-1 || u != (gunichar)-2) && g_unichar_isalnum(u)) {
u = g_unichar_toupper(u);
size = g_unichar_to_utf8(u, NULL);
string = malloc(size+1);
g_unichar_to_utf8(u, string);
}
}
if (string)
string[size] = '\0';
return string;
}
char *str_replace_char(const char *str, gunichar orig, gunichar repl)
{
int result_size = strlen(str) + 6;
char *result = malloc(result_size);
const char *r = str;
char *w = result;
while (*r) {
int len;
gunichar c = g_utf8_get_char(r);
/* ensure there is room for at least 1 more character */
if (w - result + 7 > result_size) {
int offset = w - result;
result_size += max(6, 0.5 * result_size);
result = realloc(result, result_size);
w = result + offset;
}
if (c == orig)
len = g_unichar_to_utf8(repl, w);
else
len = g_unichar_to_utf8(c, w);
w += len;
r = g_utf8_next_char(r);
}
*w = 0;
return result;
}
/* append text to the end of 'f' with attribute 'attr' and color
* 'color'
*/
void owl_fmtext_append_attr(owl_fmtext *f, const char *text, char attr, short fgcolor, short bgcolor)
{
char attrbuff[6];
int newlen, a = 0, fg = 0, bg = 0;
if (attr != OWL_FMTEXT_ATTR_NONE) a=1;
if (fgcolor != OWL_COLOR_DEFAULT) fg=1;
if (bgcolor != OWL_COLOR_DEFAULT) bg=1;
/* Plane-16 characters in UTF-8 are 4 bytes long. */
newlen = strlen(f->textbuff) + strlen(text) + (8 * (a + fg + bg));
_owl_fmtext_realloc(f, newlen);
/* Set attributes */
if (a)
strncat(f->textbuff, attrbuff,
g_unichar_to_utf8(OWL_FMTEXT_UC_ATTR | attr, attrbuff));
if (fg)
strncat(f->textbuff, attrbuff,
g_unichar_to_utf8(OWL_FMTEXT_UC_FGCOLOR | fgcolor, attrbuff));
if (bg)
strncat(f->textbuff, attrbuff,
g_unichar_to_utf8(OWL_FMTEXT_UC_BGCOLOR | bgcolor, attrbuff));
strcat(f->textbuff, text);
/* Reset attributes */
if (bg) strcat(f->textbuff, OWL_FMTEXT_UTF8_BGDEFAULT);
if (fg) strcat(f->textbuff, OWL_FMTEXT_UTF8_FGDEFAULT);
if (a) strcat(f->textbuff, OWL_FMTEXT_UTF8_ATTR_NONE);
f->textlen=newlen;
}
static bool _tokenize_identifier(GSDLTokenizer *self, GSDLToken *result, gunichar c, GError **err) {
int length = 7;
char *output = result->val = g_malloc(length);
GUnicodeType type;
int i = g_unichar_to_utf8(c, output);
while (_peek(self, &c, err) && (c == '-' || c == '.' || g_unichar_isalpha(c) || g_unichar_isdigit(c) || (type = g_unichar_type(c)) == G_UNICODE_CURRENCY_SYMBOL || type == G_UNICODE_CONNECT_PUNCTUATION || type == G_UNICODE_LETTER_NUMBER || type == G_UNICODE_SPACING_MARK || type == G_UNICODE_NON_SPACING_MARK)) {
GROW_IF_NEEDED(output = result->val, i + 5, length);
_consume(self);
i += g_unichar_to_utf8(c, output + i);
}
FAIL_IF_ERR();
output[i] = '\0';
if (
strcmp(output, "true") == 0 ||
strcmp(output, "on") == 0 ||
strcmp(output, "false") == 0 ||
strcmp(output, "off") == 0) {
result->type = T_BOOLEAN;
} else if (strcmp(output, "null") == 0) {
result->type = T_NULL;
}
return true;
}
static char *convert_title_case(const char *str)
{
int result_size = strlen(str) + 12;
char *result = malloc(result_size);
const char *r = str;
char *w = result;
gboolean upcase_next = TRUE;
while (*r) {
int len;
gunichar c = g_utf8_get_char(r);
/* ensure there is room for at least 1 more character */
if (w - result + 7 > result_size) {
int offset = w - result;
result_size += max(6, 0.5 * result_size);
result = realloc(result, result_size);
w = result + offset;
}
if (upcase_next)
len = g_unichar_to_utf8(g_unichar_toupper(c), w);
else
len = g_unichar_to_utf8(g_unichar_tolower(c), w);
w += len;
upcase_next = !g_unichar_isalnum(c) && c != '\'';
r = g_utf8_next_char(r);
}
*w = 0;
return result;
}
/* utiliti function, that copy characters from cheked to actual until ident is
* smaller than to_ident */
static gboolean
utf8_tool_copy_chars_to (struct utf8_tool *tool, int to_ident)
{
tool->compose = FALSE;
while (tool->cheked[0] != '\0')
{
gunichar uni;
size_t left;
int w = 0;
uni = g_utf8_get_char (tool->cheked);
if (str_unichar_iscombiningmark (uni))
tool->compose = TRUE;
else
{
w = 1;
if (g_unichar_iswide (uni))
w++;
if (tool->ident + w > to_ident)
return TRUE;
}
left = g_unichar_to_utf8 (uni, NULL);
if (tool->remain <= left)
return FALSE;
left = g_unichar_to_utf8 (uni, tool->actual);
tool->actual += left;
tool->remain -= left;
tool->cheked = g_utf8_next_char (tool->cheked);
tool->ident += w;
}
return TRUE;
}
static char *convert_sentence_case(const char *str)
{
int result_size = strlen(str) + 12;
char *result = malloc(result_size);
const char *r = str;
char *w = result;
while (*r) {
int len;
gunichar c = g_utf8_get_char(r);
/* ensure there is room for at least 1 more character */
if (w - result + 7 > result_size) {
int offset = w - result;
result_size += max(6, 0.5 * result_size);
result = realloc(result, result_size);
w = result + offset;
}
if (r == str)
len = g_unichar_to_utf8(g_unichar_toupper(c), w);
else
len = g_unichar_to_utf8(g_unichar_tolower(c), w);
w += len;
r = g_utf8_next_char(r);
}
*w = 0;
return result;
}
/* check for characters that are invalid in XML */
static gboolean is_valid_string (const gchar * s, gchar * * subst)
{
if (! g_utf8_validate (s, -1, NULL))
goto NOT_VALID;
const gchar * p = s;
while (* p)
{
gunichar c = g_utf8_get_char (p);
if (IS_VALID_CHAR (c))
p = g_utf8_next_char (p);
else
goto NOT_VALID;
}
return TRUE;
NOT_VALID:;
gint len = 0;
p = s;
while (* p)
{
gunichar c = g_utf8_get_char_validated (p, -1);
if (IS_VALID_CHAR (c))
{
len += g_unichar_to_utf8 (c, NULL);
p = g_utf8_next_char (p);
}
else
p ++;
}
* subst = g_malloc (len + 1);
gchar * w = * subst;
p = s;
while (* p)
{
gunichar c = g_utf8_get_char_validated (p, -1);
if (IS_VALID_CHAR (c))
{
w += g_unichar_to_utf8 (c, w);
p = g_utf8_next_char (p);
}
else
p ++;
}
* w = 0;
return FALSE;
}
static UniToStrPair ipa_to_unicode_make_pair(gunichar from,
gunichar to1,
gunichar to2)
{
gchar buf[7];
UniToStrPair res;
res.first = from;
buf[g_unichar_to_utf8(to1, buf)] = '\0';
res.second = buf;
buf[g_unichar_to_utf8(to2, buf)] = '\0';
res.second += buf;
return res;
}
unsigned char
convert_from_utf_to_current_c (const int input_char, GIConv conv)
{
unsigned char str[6 + 1];
unsigned char buf_ch[6 + 1];
unsigned char ch = '.';
int res = 0;
res = g_unichar_to_utf8 (input_char, (char *) str);
if (res == 0)
{
return ch;
}
str[res] = '\0';
switch (str_translate_char (conv, (char *) str, -1, (char *) buf_ch, sizeof (buf_ch)))
{
case ESTR_SUCCESS:
ch = buf_ch[0];
break;
case ESTR_PROBLEM:
case ESTR_FAILURE:
ch = '.';
break;
}
return ch;
}
static gboolean on_input(UNUSED GIOChannel *src, GIOCondition cond, gpointer ud) /*{{{*/
{
LuaState *L = ud;
if (cond & G_IO_IN) {
lua_getglobal(L, "on_input");
if (!lua_isnil(L, -1)) {
gunichar ch = 0;
gboolean ok = ms_term_getkey(&ch);
if (ok) {
char buf[8];
memset(buf, 0, sizeof(buf));
g_unichar_to_utf8(ch, buf);
lua_pushstring(L, buf);
}
else {
lua_pushnil(L);
}
if (lua_pcall(L, 1, 0, 0) != 0) {
g_warning("lua error in on_input(): %s", lua_tostring(L, -1));
}
}
else {
lua_pop(L, 1);
}
return TRUE;
}
return FALSE;
}/* }}} */
gchar *
gebr_geoxml_line_create_key(const gchar *title)
{
gchar *lower_no_accents = g_utf8_strdown(title, -1);
lower_no_accents = gebr_g_string_remove_accents(lower_no_accents);
GString *buffer = g_string_new(NULL);
gchar *tmp = lower_no_accents;
gunichar c;
for (; tmp && *tmp; tmp = g_utf8_next_char(tmp)) {
c = g_utf8_get_char(tmp);
if (c == ' ' || !g_ascii_isalnum((char)c)) {
g_string_append_c(buffer, '_');
} else {
gchar str[7];
gint len = g_unichar_to_utf8(c, str);
g_string_append_len(buffer, str, len);
}
}
g_string_append_c(buffer, '\0');
g_free(lower_no_accents);
return g_string_free(buffer, FALSE);
}
void
tty_print_anychar (int c)
{
char str[6 + 1];
if (c > 255)
{
int res = g_unichar_to_utf8 (c, str);
if (res == 0)
{
str[0] = '.';
str[1] = '\0';
}
else
{
str[res] = '\0';
}
SLsmg_write_string ((char *) str_term_form (str));
}
else
{
if (!is_printable (c))
c = '.';
SLsmg_write_char ((SLwchar_Type) ((unsigned int) c));
}
}
PyObject *
_pygi_marshal_to_py_unichar (PyGIInvokeState *state,
PyGICallableCache *callable_cache,
PyGIArgCache *arg_cache,
GIArgument *arg)
{
PyObject *py_obj = NULL;
/* Preserve the bidirectional mapping between 0 and "" */
if (arg->v_uint32 == 0) {
py_obj = PYGLIB_PyUnicode_FromString ("");
} else if (g_unichar_validate (arg->v_uint32)) {
gchar utf8[6];
gint bytes;
bytes = g_unichar_to_utf8 (arg->v_uint32, utf8);
py_obj = PYGLIB_PyUnicode_FromStringAndSize ((char*)utf8, bytes);
} else {
/* TODO: Convert the error to an exception. */
PyErr_Format (PyExc_TypeError,
"Invalid unicode codepoint %" G_GUINT32_FORMAT,
arg->v_uint32);
}
return py_obj;
}
static void
text_insert_char(Text *text, gunichar c)
{
gchar ch[7];
int unilen;
int row;
gchar *line, *str;
gchar *utf8_before;
gchar *str1;
/* Make a string of the the char */
unilen = g_unichar_to_utf8 (c, ch);
ch[unilen] = 0;
row = text->cursor_row;
/* Copy the before and after parts with the new char in between */
line = text_get_line(text, row);
utf8_before = g_utf8_offset_to_pointer(line, (glong)(text->cursor_pos));
str1 = g_strndup(line, utf8_before - line);
str = g_strconcat(str1, ch, utf8_before, NULL);
text_set_line_text(text, row, str);
g_free(str);
g_free(str1);
text->cursor_pos++;
text->max_width = MAX(text->max_width, text_get_line_width(text, row));
}
GList* get_radical_of_kanji(gunichar kanji, GHashTable *kanji_info_hash) {
GList *kanji_info_list = NULL;
GList *radical_list = NULL; //list of radical to be returned
//convert to UTF8
gchar utf8kanji[3];
int at = g_unichar_to_utf8(kanji, utf8kanji);
utf8kanji[at] = '\0';
//lookup in the kanji info hash and get the kanji info
KanjiInfo *kanji_info = g_hash_table_lookup(kanji_info_hash, utf8kanji);
if(kanji_info == NULL){
return NULL;
}
//puts the radical field of the kanji_info into a list
for (kanji_info_list = kanji_info->rad_info_list;
kanji_info_list != NULL;
kanji_info_list = kanji_info_list->next) {
radical_list = g_list_prepend(radical_list,
(gpointer) ((RadInfo *) kanji_info_list->data)->radical
);
}
return radical_list;
}
static void
unichar_changed (GObject *object, GParamSpec *pspec, gpointer data)
{
GtkEntry *entry = GTK_ENTRY (data);
gunichar new_val;
gunichar old_val = unichar_get_value (entry);
GValue val = G_VALUE_INIT;
gchar buf[7];
gint len;
g_value_init (&val, pspec->value_type);
get_property_value (object, pspec, &val);
new_val = (gunichar)g_value_get_uint (&val);
if (new_val != old_val)
{
if (!new_val)
len = 0;
else
len = g_unichar_to_utf8 (new_val, buf);
buf[len] = '\0';
block_controller (G_OBJECT (entry));
gtk_entry_set_text (entry, buf);
unblock_controller (G_OBJECT (entry));
}
}
/** Converts unicode strings such as \003d into =
* Code blatantly nicked from the Facebook plugin */
gchar *
convert_unicode(const gchar *input)
{
gunichar unicode_char;
gchar unicode_char_str[6];
gint unicode_char_len;
gchar *next_pos;
gchar *input_string;
gchar *output_string;
if (input == NULL)
return NULL;
next_pos = input_string = g_strdup(input);
while ((next_pos = strstr(next_pos, "\\u")))
{
/* grab the unicode */
sscanf(next_pos, "\\u%4x", &unicode_char);
/* turn it to a char* */
unicode_char_len = g_unichar_to_utf8(unicode_char, unicode_char_str);
/* shove it back into the string */
g_memmove(next_pos, unicode_char_str, unicode_char_len);
/* move all the data after the \u0000 along */
g_stpcpy(next_pos + unicode_char_len, next_pos + 6);
}
output_string = g_strcompress(input_string);
g_free(input_string);
return output_string;
}
static gboolean
option_print_cb (const gchar *option_name,
const gchar *value,
gpointer data,
GError **error)
{
const char *p;
for (p = value; *p; p = g_utf8_next_char (p)) {
gunichar c;
char utf[7];
c = g_utf8_get_char (p);
if (c == (gunichar)-1)
continue;
utf[g_unichar_to_utf8 (c, utf)] = '\0';
g_print("%s\tU+%04X\t%s\n",
utf, c,
gucharmap_get_unicode_name (c));
}
exit (EXIT_SUCCESS);
return FALSE;
}
static gchar* enchant_utf8_strtitle(const gchar*str, gssize len)
{
gunichar title_case_char;
gchar* result;
gchar* upperStr, * upperTail, * lowerTail;
gchar title_case_utf8[7];
gint utf8len;
upperStr = g_utf8_strup(str, len); /* for locale sensitive casing */
title_case_char = g_unichar_totitle(g_utf8_get_char(upperStr));
utf8len = g_unichar_to_utf8(title_case_char, title_case_utf8);
title_case_utf8[utf8len] = '\0';
upperTail = g_utf8_next_char(upperStr);
lowerTail = g_utf8_strdown(upperTail, -1);
result = g_strconcat(title_case_utf8,
lowerTail,
NULL);
g_free(upperStr);
g_free(lowerTail);
return result;
}
static guchar*
rhk_sm3_read_string(const guchar **buffer,
gsize len)
{
gchar *s, *p;
guint i, n;
gunichar chr;
if (len < 2)
return NULL;
n = gwy_get_guint16_le(buffer);
len -= 2;
if (len < 2*n)
return NULL;
if (!n)
return g_strdup("");
p = s = g_new(gchar, 6*n + 1);
for (i = 0; i < n; i++) {
chr = gwy_get_guint16_le(buffer);
p += g_unichar_to_utf8(chr, p);
}
*p = '\0';
g_strstrip(s);
gwy_debug("String: <%s>", s);
return s;
}
static PangoGlyph pango_font_get_glyph(PangoFont* font, PangoContext* context, gunichar wc)
{
PangoGlyph result = 0;
gchar buffer[7];
gint length = g_unichar_to_utf8(wc, buffer);
g_return_val_if_fail(length, 0);
GList* items = pango_itemize(context, buffer, 0, length, NULL, NULL);
if (g_list_length(items) == 1) {
PangoItem* item = reinterpret_cast<PangoItem*>(items->data);
PangoFont* tmpFont = item->analysis.font;
item->analysis.font = font;
PangoGlyphString* glyphs = pango_glyph_string_new();
pango_shape(buffer, length, &item->analysis, glyphs);
item->analysis.font = tmpFont;
if (glyphs->num_glyphs == 1)
result = glyphs->glyphs[0].glyph;
else
g_warning("didn't get 1 glyph but %d", glyphs->num_glyphs);
pango_glyph_string_free(glyphs);
}
g_list_foreach(items, (GFunc)pango_item_free, NULL);
g_list_free(items);
return result;
}
static const gchar *
get_invisible_text (void)
{
GtkWidget *entry;
gunichar invisible_char;
static gchar invisible_text[40];
gchar *p;
gint i;
entry = gtk_entry_new ();
invisible_char = gtk_entry_get_invisible_char (GTK_ENTRY (entry));
if (invisible_char == 0)
invisible_char = 0x2022;
g_object_ref_sink (entry);
g_object_unref (entry);
/* five bullets */
p = invisible_text;
for (i = 0; i < 5; i++)
p += g_unichar_to_utf8 (invisible_char, p);
*p = 0;
return invisible_text;
}
int
plugin_emit_keypress (session *sess, unsigned int state, unsigned int keyval, gunichar key)
{
char *word[PDIWORDS];
char keyval_str[16];
char state_str[16];
char len_str[16];
char key_str[7];
int i, len;
if (!hook_list)
return 0;
sprintf (keyval_str, "%u", keyval);
sprintf (state_str, "%u", state);
if (!key)
len = 0;
else
len = g_unichar_to_utf8 (key, key_str);
key_str[len] = '\0';
sprintf (len_str, "%d", len);
word[0] = "Key Press";
word[1] = keyval_str;
word[2] = state_str;
word[3] = key_str;
word[4] = len_str;
for (i = 5; i < PDIWORDS; i++)
word[i] = "\000";
return plugin_hook_run (sess, word[0], word, NULL, NULL, HOOK_PRINT);
}
static void
_vte_pango_x_draw_text(struct _vte_draw *draw,
struct _vte_draw_text_request *requests,
gsize n_requests,
GdkColor *color, guchar alpha)
{
Display *display;
GC gc;
struct _vte_pango_x_data *data;
char buf[VTE_UTF8_BPC];
gsize i, length;
GdkColor wcolor;
data = (struct _vte_pango_x_data*) draw->impl_data;
wcolor = *color;
gdk_rgb_find_color(gdk_drawable_get_colormap(draw->widget->window),
&wcolor);
gdk_gc_set_foreground(data->gc, &wcolor);
display = gdk_x11_drawable_get_xdisplay(draw->widget->window);
gc = gdk_x11_gc_get_xgc(data->gc);
for (i = 0; i < n_requests; i++) {
length = g_unichar_to_utf8(requests[i].c, buf);
pango_layout_set_text(data->layout, buf, length);
pango_x_render_layout(display,
data->drawable,
gc,
data->layout,
requests[i].x - data->x_offs,
requests[i].y - data->y_offs);
}
}
unsigned
utf8_width(const char *str)
{
assert(str != NULL);
#if defined(ENABLE_MULTIBYTE) && !defined(HAVE_CURSES_ENHANCED)
return g_utf8_strlen(str, -1);
#else
#ifdef HAVE_CURSES_ENHANCED
if (g_utf8_validate(str, -1, NULL)) {
size_t len = g_utf8_strlen(str, -1);
unsigned width = 0;
gunichar c;
while (len--) {
c = g_utf8_get_char(str);
width += unicode_char_width(c);
str += g_unichar_to_utf8(c, NULL);
}
return width;
} else
#endif
return strlen(str);
#endif
}
static char *
random_utf8_string (void *ctx, size_t char_count)
{
size_t offset = 0;
size_t i;
gchar *buf = NULL;
size_t buf_size = 0;
for (i = 0; i < char_count; i++) {
gunichar randomchar;
size_t written;
/* 6 for one glyph, one for null, one for luck */
while (buf_size <= offset + 8) {
buf_size = 2 * buf_size + 8;
buf = talloc_realloc (ctx, buf, gchar, buf_size);
}
do {
randomchar = random_unichar ();
} while (randomchar == '\n');
written = g_unichar_to_utf8 (randomchar, buf + offset);
if (written <= 0) {
fprintf (stderr, "error converting to utf8\n");
exit (1);
}
offset += written;
}
buf[offset] = 0;
return buf;
}
static void
charprop_reset_widget(CharProperty *prop, WIDGET *widget)
{
gchar ch[7];
int unilen = g_unichar_to_utf8 (prop->char_data, ch);
ch[unilen] = 0;
gtk_entry_set_text(GTK_ENTRY(widget), ch);
}
static VALUE
rg_char(VALUE self)
{
gchar buf[10];
gint len = g_unichar_to_utf8(gtk_text_iter_get_char(_SELF(self)), buf);
buf[len] = '\0';
return CSTR2RVAL(buf);
}
/* markup unescape code stolen and adapted from gmarkup.c
*/
static gchar *
char_str (gunichar c,
gchar *buf)
{
memset (buf, 0, 8);
g_unichar_to_utf8 (c, buf);
return buf;
}
