Documentation: wording fixes in the user manual and glossary

diff --git a/utf8.c b/utf8.c
index 7c342ff4b6eb2e8c94bb3fa5c86b77b5de9abfae..77c28d492cccfcbcb8a302d168a81b21d909ef12 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -5,11 +5,11 @@
 /* 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;
 };
 
-static size_t display_mode_esc_sequence_len(const char *s)
+size_t display_mode_esc_sequence_len(const char *s)
 {
        const char *p = s;
        if (*p++ != '\033')
@@ -84,11 +84,10 @@ static int git_wcwidth(ucs_char_t ch)
         *   "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 },
@@ -421,6 +420,52 @@ void strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len,
        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)
@@ -483,7 +528,7 @@ char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outs
        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);