scdoc2mdoc

commit f1db2e16795ae3e5a4b829e6f3b3d512ab855361
parent 533c284ee89113e15fdaa96ec16b5b49ca6e1657
Author: Carlo Abelli <carlo.abelli@gmail.com>
Date:   Tue, 26 Feb 2019 15:52:03 -0500

fix underscores in underlined words

Currently, the first underscore encountered while underlining ends
underlining. As a result, underscores in underlined words are not
ignored e.g. _hello_world_ does not parse correctly.

This checks the next character to see if it is still in a word before
ending underlining.

Diffstat:
M
src/main.c
 | 
6
++++--
M
test/inline-formatting
 | 
10
+++++++++-

2 files changed, 13 insertions(+), 3 deletions(-)
diff --git a/src/main.c b/src/main.c
@@ -195,7 +195,7 @@ static void parse_linebreak(struct parser *p) {
 }
 
 static void parse_text(struct parser *p) {
-	uint32_t ch, last = ' ';
+	uint32_t ch, next, last = ' ';
 	int i = 0;
 	while ((ch = parser_getch(p)) != UTF8_INVALID) {
 		switch (ch) {
@@ -213,11 +213,13 @@ static void parse_text(struct parser *p) {
 			parse_format(p, FORMAT_BOLD);
 			break;
 		case '_':
-			if (!isalnum(last) || (p->flags & FORMAT_UNDERLINE)) {
+			next = parser_getch(p);
+			if (!isalnum(last) || ((p->flags & FORMAT_UNDERLINE) && !isalnum(next))) {
 				parse_format(p, FORMAT_UNDERLINE);
 			} else {
 				utf8_fputch(p->output, ch);
 			}
+			parser_pushch(p, next);
 			break;
 		case '+':
 			parse_linebreak(p);
diff --git a/test/inline-formatting b/test/inline-formatting
@@ -17,7 +17,15 @@ hello_world
 EOF
 end 0
 
-begin "Allows underscores in bolded words"
+begin "Ignores underscores in underlined words"
+scdoc <<EOF | grep '\\fIhello_world\\fR' >/dev/null
+test(8)
+
+_hello_world_
+EOF
+end0
+
+begin "Ignores underscores in bolded words"
 scdoc <<EOF | grep '^\\fBhello_world\\fR' >/dev/null
 test(8)