utf8pad: fix byte-seek issue with negative width codepoints in the range >= 127 - stagit-gopher - A git gopher frontend. (mirror)

git clone git://bitreich.org/stagit-gopher/ git://enlrupgkhuxnvlhsf6lc3fziv5h2hhfrinws65d7roiv6bfj7d652fid.onion/stagit-gopher/

Log

Files

Refs

Tags

README

LICENSE

---

commit 05a08e8ab50a8da5b2896c3f5887801d059f48dd

parent a9c90b585f158f98dd0997d1509e83f85dd87498

Author: Hiltjo Posthuma 

Date:   Sat,  9 Jan 2021 16:19:18 +0100

utf8pad: fix byte-seek issue with negative width codepoints in the range >= 127

For example: "\xef\xbf\xb7" (codepoint 0xfff7), returns wcwidth(wc) == -1.
The next byte was incorrected seeked, but the codepoint itself was valid
(mbtowc).

Diffstat:
  M stagit-gopher-index.c               |       7 +++----
  M stagit-gopher.c                     |       7 +++----

2 files changed, 6 insertions(+), 8 deletions(-)
---

diff --git a/stagit-gopher-index.c b/stagit-gopher-index.c

@@ -38,19 +38,18 @@ utf8pad(char *buf, size_t bufsiz, const char *s, size_t len, int pad)
 
         slen = strlen(s);
         for (i = 0; i < slen; i += inc) {
-                inc = 1;
+                inc = 1; /* next byte */
                 if ((unsigned char)s[i] < 32)
                         continue;
 
                 rl = mbtowc(&wc, &s[i], slen - i < 4 ? slen - i : 4);
+                inc = rl;
                 if (rl < 0) {
                         mbtowc(NULL, NULL, 0); /* reset state */
-                        inc = 1; /* next byte */
+                        inc = 1; /* invalid, seek next byte */
                         w = 1; /* replacement char is one width */
                 } else if ((w = wcwidth(wc)) == -1) {
                         continue;
-                } else {
-                        inc = rl;
                 }
 
                 if (col + w > len || (col + w == len && s[i + inc])) {

diff --git a/stagit-gopher.c b/stagit-gopher.c

@@ -100,19 +100,18 @@ utf8pad(char *buf, size_t bufsiz, const char *s, size_t len, int pad)
 
         slen = strlen(s);
         for (i = 0; i < slen; i += inc) {
-                inc = 1;
+                inc = 1; /* next byte */
                 if ((unsigned char)s[i] < 32)
                         continue;
 
                 rl = mbtowc(&wc, &s[i], slen - i < 4 ? slen - i : 4);
+                inc = rl;
                 if (rl < 0) {
                         mbtowc(NULL, NULL, 0); /* reset state */
-                        inc = 1; /* next byte */
+                        inc = 1; /* invalid, seek next byte */
                         w = 1; /* replacement char is one width */
                 } else if ((w = wcwidth(wc)) == -1) {
                         continue;
-                } else {
-                        inc = rl;
                 }
 
                 if (col + w > len || (col + w == len && s[i + inc])) {