/* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */
+typedef unsigned int ucs_char_t; /* assuming 32bit int */
+
struct interval {
int first;
int last;
};
/* auxiliary function for binary search in interval table */
-static int bisearch(wchar_t ucs, const struct interval *table, int max) {
+static int bisearch(ucs_char_t ucs, const struct interval *table, int max) {
int min = 0;
int mid;
* ISO 8859-1 and WGL4 characters, Unicode control characters,
* etc.) have a column width of 1.
*
- * This implementation assumes that wchar_t characters are encoded
+ * This implementation assumes that ucs_char_t characters are encoded
* in ISO 10646.
*/
-static int wcwidth(wchar_t ch)
+static int wcwidth(ucs_char_t ch)
{
/*
* Sorted list of non-overlapping intervals of non-spacing characters,
int utf8_width(const char **start)
{
unsigned char *s = (unsigned char *)*start;
- wchar_t ch;
+ ucs_char_t ch;
if (*s < 0x80) {
/* 0xxxxxxx */
}
}
+int is_encoding_utf8(const char *name)
+{
+ if (!name)
+ return 1;
+ if (!strcasecmp(name, "utf-8") || !strcasecmp(name, "utf8"))
+ return 1;
+ return 0;
+}
+
/*
* Given a buffer and its encoding, return it re-encoded
* with iconv. If the conversion fails, returns NULL.
*/
#ifndef NO_ICONV
+#ifdef OLD_ICONV
+ typedef const char * iconv_ibp;
+#else
+ typedef char * iconv_ibp;
+#endif
char *reencode_string(const char *in, const char *out_encoding, const char *in_encoding)
{
iconv_t conv;
size_t insz, outsz, outalloc;
- char *out, *outpos, *cp;
+ char *out, *outpos;
+ iconv_ibp cp;
if (!in_encoding)
return NULL;
outalloc = outsz + 1; /* for terminating NUL */
out = xmalloc(outalloc);
outpos = out;
- cp = (char *)in;
+ cp = (iconv_ibp)in;
while (1) {
size_t cnt = iconv(conv, &cp, &insz, &outpos, &outsz);