From 8872acfd3bb11e0bdbd221a6616c7c74b549b313 Mon Sep 17 00:00:00 2001 From: Joerg Sonnenberger Date: Sun, 5 Feb 2012 16:46:15 +0000 Subject: Don't silently skip non-ASCII characters, but replace them with ``?''. This is less likely to break the syntax of macros. --- read.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'read.c') diff --git a/read.c b/read.c index dd456468..be788c2b 100644 --- a/read.c +++ b/read.c @@ -325,9 +325,9 @@ mparse_buf_r(struct mparse *curp, struct buf blk, int start) * Warn about bogus characters. If you're using * non-ASCII encoding, you're screwing your * readers. Since I'd rather this not happen, - * I'll be helpful and drop these characters so - * we don't display gibberish. Note to manual - * writers: use special characters. + * I'll be helpful and replace these characters + * with "?", so we don't display gibberish. + * Note to manual writers: use special characters. */ c = (unsigned char) blk.buf[i]; @@ -335,8 +335,11 @@ mparse_buf_r(struct mparse *curp, struct buf blk, int start) if ( ! (isascii(c) && (isgraph(c) || isblank(c)))) { mandoc_msg(MANDOCERR_BADCHAR, curp, - curp->line, pos, "ignoring byte"); + curp->line, pos, NULL); i++; + if (pos >= (int)ln.sz) + resize_buf(&ln, 256); + ln.buf[pos++] = '?'; continue; } -- cgit