/* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */
struct interval {
- int first;
- int last;
+ ucs_char_t first;
+ ucs_char_t last;
};
+size_t display_mode_esc_sequence_len(const char *s)
+{
+ const char *p = s;
+ if (*p++ != '\033')
+ return 0;
+ if (*p++ != '[')
+ return 0;
+ while (isdigit(*p) || *p == ';')
+ p++;
+ if (*p++ != 'm')
+ return 0;
+ return p - s;
+}
+
/* auxiliary function for binary search in interval table */
static int bisearch(ucs_char_t ucs, const struct interval *table, int max)
{
* "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c".
*/
static const struct interval combining[] = {
- { 0x0300, 0x0357 }, { 0x035D, 0x036F }, { 0x0483, 0x0486 },
- { 0x0488, 0x0489 }, { 0x0591, 0x05A1 }, { 0x05A3, 0x05B9 },
- { 0x05BB, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
- { 0x05C4, 0x05C4 }, { 0x0600, 0x0603 }, { 0x0610, 0x0615 },
- { 0x064B, 0x0658 }, { 0x0670, 0x0670 }, { 0x06D6, 0x06E4 },
+ { 0x0300, 0x036F }, { 0x0483, 0x0489 }, { 0x0591, 0x05BD },
+ { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, { 0x05C4, 0x05C5 },
+ { 0x05C7, 0x05C7 }, { 0x0600, 0x0604 }, { 0x0610, 0x061A },
+ { 0x064B, 0x065F }, { 0x0670, 0x0670 }, { 0x06D6, 0x06E4 },
{ 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, { 0x070F, 0x070F },
{ 0x0711, 0x0711 }, { 0x0730, 0x074A }, { 0x07A6, 0x07B0 },
{ 0x0901, 0x0902 }, { 0x093C, 0x093C }, { 0x0941, 0x0948 },
* string, assuming that the string is utf8. Returns strlen() instead
* if the string does not look like a valid utf8 string.
*/
-int utf8_strwidth(const char *string)
+int utf8_strnwidth(const char *string, int len, int skip_ansi)
{
int width = 0;
const char *orig = string;
- while (1) {
- if (!string)
- return strlen(orig);
- if (!*string)
- return width;
+ if (len == -1)
+ len = strlen(string);
+ while (string && string < orig + len) {
+ int skip;
+ while (skip_ansi &&
+ (skip = display_mode_esc_sequence_len(string)) != 0)
+ string += skip;
width += utf8_width(&string, NULL);
}
+ return string ? width : len;
+}
+
+int utf8_strwidth(const char *string)
+{
+ return utf8_strnwidth(string, -1, 0);
}
int is_utf8(const char *text)
}
}
-static size_t display_mode_esc_sequence_len(const char *s)
-{
- const char *p = s;
- if (*p++ != '\033')
- return 0;
- if (*p++ != '[')
- return 0;
- while (isdigit(*p) || *p == ';')
- p++;
- if (*p++ != 'm')
- return 0;
- return p - s;
-}
-
/*
* Wrap the text, if necessary. The variable indent is the indent for the
* first line, indent2 is the indent for all other lines.
free(tmp);
}
+void strbuf_utf8_replace(struct strbuf *sb_src, int pos, int width,
+ const char *subst)
+{
+ struct strbuf sb_dst = STRBUF_INIT;
+ char *src = sb_src->buf;
+ char *end = src + sb_src->len;
+ char *dst;
+ int w = 0, subst_len = 0;
+
+ if (subst)
+ subst_len = strlen(subst);
+ strbuf_grow(&sb_dst, sb_src->len + subst_len);
+ dst = sb_dst.buf;
+
+ while (src < end) {
+ char *old;
+ size_t n;
+
+ while ((n = display_mode_esc_sequence_len(src))) {
+ memcpy(dst, src, n);
+ src += n;
+ dst += n;
+ }
+
+ old = src;
+ n = utf8_width((const char**)&src, NULL);
+ if (!src) /* broken utf-8, do nothing */
+ return;
+ if (n && w >= pos && w < pos + width) {
+ if (subst) {
+ memcpy(dst, subst, subst_len);
+ dst += subst_len;
+ subst = NULL;
+ }
+ w += n;
+ continue;
+ }
+ memcpy(dst, old, src - old);
+ dst += src - old;
+ w += n;
+ }
+ strbuf_setlen(&sb_dst, dst - sb_dst.buf);
+ strbuf_swap(sb_src, &sb_dst);
+ strbuf_release(&sb_dst);
+}
+
int is_encoding_utf8(const char *name)
{
if (!name)
}
/*
+ * Wrapper for fprintf and returns the total number of columns required
+ * for the printed string, assuming that the string is utf8.
+ */
+int utf8_fprintf(FILE *stream, const char *format, ...)
+{
+ struct strbuf buf = STRBUF_INIT;
+ va_list arg;
+ int columns;
+
+ va_start(arg, format);
+ strbuf_vaddf(&buf, format, arg);
+ va_end(arg);
+
+ columns = fputs(buf.buf, stream);
+ if (0 <= columns) /* keep the error from the I/O */
+ columns = utf8_strwidth(buf.buf);
+ strbuf_release(&buf);
+ return columns;
+}
+
+/*
* Given a buffer and its encoding, return it re-encoded
* with iconv. If the conversion fails, returns NULL.
*/
#else
typedef char * iconv_ibp;
#endif
-char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv)
+char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outsz_p)
{
size_t outsz, outalloc;
char *out, *outpos;
while (1) {
size_t cnt = iconv(conv, &cp, &insz, &outpos, &outsz);
- if (cnt == -1) {
+ if (cnt == (size_t) -1) {
size_t sofar;
if (errno != E2BIG) {
free(out);
}
else {
*outpos = '\0';
+ if (outsz_p)
+ *outsz_p = outpos - out;
break;
}
}
return out;
}
-char *reencode_string(const char *in, const char *out_encoding, const char *in_encoding)
+char *reencode_string_len(const char *in, int insz,
+ const char *out_encoding, const char *in_encoding,
+ int *outsz)
{
iconv_t conv;
char *out;
if (!in_encoding)
return NULL;
+
conv = iconv_open(out_encoding, in_encoding);
- if (conv == (iconv_t) -1)
- return NULL;
- out = reencode_string_iconv(in, strlen(in), conv);
+ if (conv == (iconv_t) -1) {
+ /*
+ * Some platforms do not have the variously spelled variants of
+ * UTF-8, so let's fall back to trying the most official
+ * spelling. We do so only as a fallback in case the platform
+ * does understand the user's spelling, but not our official
+ * one.
+ */
+ if (is_encoding_utf8(in_encoding))
+ in_encoding = "UTF-8";
+ if (is_encoding_utf8(out_encoding))
+ out_encoding = "UTF-8";
+ conv = iconv_open(out_encoding, in_encoding);
+ if (conv == (iconv_t) -1)
+ return NULL;
+ }
+
+ out = reencode_string_iconv(in, insz, conv, outsz);
iconv_close(conv);
return out;
}
#endif
+
+/*
+ * Returns first character length in bytes for multi-byte `text` according to
+ * `encoding`.
+ *
+ * - The `text` pointer is updated to point at the next character.
+ * - When `remainder_p` is not NULL, on entry `*remainder_p` is how much bytes
+ * we can consume from text, and on exit `*remainder_p` is reduced by returned
+ * character length. Otherwise `text` is treated as limited by NUL.
+ */
+int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding)
+{
+ int chrlen;
+ const char *p = *text;
+ size_t r = (remainder_p ? *remainder_p : SIZE_MAX);
+
+ if (r < 1)
+ return 0;
+
+ if (is_encoding_utf8(encoding)) {
+ pick_one_utf8_char(&p, &r);
+
+ chrlen = p ? (p - *text)
+ : 1 /* not valid UTF-8 -> raw byte sequence */;
+ }
+ else {
+ /*
+ * TODO use iconv to decode one char and obtain its chrlen
+ * for now, let's treat encodings != UTF-8 as one-byte
+ */
+ chrlen = 1;
+ }
+
+ *text += chrlen;
+ if (remainder_p)
+ *remainder_p -= chrlen;
+
+ return chrlen;
+}
projects / platform / upstream / git.git / blobdiff