summaryrefslogtreecommitdiffstats
path: root/term.c
diff options
context:
space:
mode:
authorIngo Schwarze <schwarze@openbsd.org>2018-12-15 19:30:25 +0000
committerIngo Schwarze <schwarze@openbsd.org>2018-12-15 19:30:25 +0000
commit0e3f0b740ea18224c3b2c07114be601dd8be97bb (patch)
treec930c6fd7e739e926a7fad1c372897af5ea601fb /term.c
parent2b0b19a54638a1b40d908611acc8498a911df29c (diff)
downloadmandoc-0e3f0b740ea18224c3b2c07114be601dd8be97bb.tar.gz
Several improvements to escape sequence handling.
* Add the missing special character \_ (underscore). * Partial implementations of \a (leader character) and \E (uninterpreted escape character). * Parse and ignore \r (reverse line feed). * Add a WARNING message about undefined escape sequences. * Add an UNSUPP message about unsupported escape sequences. * Mark \! and \? (transparent throughput) and \O (suppress output) as unsupported. * Treat the various variants of zero-width spaces as one-byte escape sequences rather than as special characters, to avoid defining bogus forms with square brackets. * For special characters with one-byte names, do not define bogus forms with square brackets, except for \[-], which is valid. * In the form with square brackets, undefined special characters do not fall back to printing the name verbatim, not even for one-byte names. * Starting a special character name with a blank is an error. * Undefined escape sequences never abort formatting of the input string, not even in HTML output mode. * Document the newly handled escapes, and a few that were missing. * Regression tests for most of the above.
Diffstat (limited to 'term.c')
-rw-r--r--term.c18
1 files changed, 10 insertions, 8 deletions
diff --git a/term.c b/term.c
index 0ceb28d6..b0f6fb0d 100644
--- a/term.c
+++ b/term.c
@@ -477,9 +477,6 @@ term_word(struct termp *p, const char *word)
word++;
esc = mandoc_escape(&word, &seq, &sz);
- if (ESCAPE_ERROR == esc)
- continue;
-
switch (esc) {
case ESCAPE_UNICODE:
uc = mchars_num2uc(seq + 1, sz - 1);
@@ -500,6 +497,9 @@ term_word(struct termp *p, const char *word)
encode1(p, uc);
}
continue;
+ case ESCAPE_UNDEF:
+ uc = *seq;
+ break;
case ESCAPE_FONTBOLD:
term_fontrepl(p, TERMFONT_BOLD);
continue;
@@ -587,6 +587,9 @@ term_word(struct termp *p, const char *word)
case ESCAPE_SPECIAL:
uc = mchars_spec2cp(cp, sz);
break;
+ case ESCAPE_UNDEF:
+ uc = *seq;
+ break;
default:
uc = -1;
break;
@@ -845,12 +848,8 @@ term_strlen(const struct termp *p, const char *cp)
switch (*cp) {
case '\\':
cp++;
- esc = mandoc_escape(&cp, &seq, &ssz);
- if (ESCAPE_ERROR == esc)
- continue;
-
rhs = NULL;
-
+ esc = mandoc_escape(&cp, &seq, &ssz);
switch (esc) {
case ESCAPE_UNICODE:
uc = mchars_num2uc(seq + 1, ssz - 1);
@@ -871,6 +870,9 @@ term_strlen(const struct termp *p, const char *cp)
sz += cond_width(p, uc, &skip);
}
continue;
+ case ESCAPE_UNDEF:
+ uc = *seq;
+ break;
case ESCAPE_DEVICE:
if (p->type == TERMTYPE_PDF) {
rhs = "pdf";