add -a option

3 files changed, 30 insertions, 11 deletions

diff --git a/uxd.1 b/uxd.1
index 6dc19c4..178ed24 100644
--- a/uxd.1
+++ b/uxd.1
@@ -86,6 +86,10 @@ Don\(aqt alternate colors.
 .
 .INDENT 0.0
 .TP
+.B  \-a
+Don\(aqt dump lines that consist entirely of ASCII characters (codepoints
+U+00 to U+7f).
+.TP
 .B  \-b
 Bold output. This may be more or less readable, depending on your
 terminal and its color settings. Ignored if \fB\-m\fP given.
@@ -492,7 +496,7 @@ Only UTF\-8 and a couple of variants (WTF\-8, MUTF\-8) are supported.
 There is no support for UTF\-16, UTF\-32, UTF\-EBCDIC, or any other
 non\-UTF\-8 encoding.
 .sp
-There\(aqs no support for any number base except hex.
+There\(aqs no support for any output number base except hex.
 .sp
 The input is read one byte at a time, so a search or regex match
 option would be difficult or impossible to implement.
@@ -517,6 +521,6 @@ Watson <\fI\%urchlay@slackware.uk\fP>.
 .UNINDENT
 .SH SEE ALSO
 .sp
-xxd(1), bvi(1), utf\-8(7), unicode(7)
+xxd(1), bvi(1), utf\-8(7), unicode(7), console_codes(4)
 .\" Generated by docutils manpage writer.
 .
diff --git a/uxd.c b/uxd.c
index a11347f..9926386 100644
--- a/uxd.c
+++ b/uxd.c
@@ -157,6 +157,9 @@ int restore_term = 0; /* -T only */
 int java_mode = 0;    /* -j */
 int wtf8_mode = 0;    /* -w */
 int permissive = 0;   /* -l */
+int skip_ascii = 0;   /* -a */
+
+int line_all_ascii = 1; /* used by -a */
 
 /* stats for -i option */
 long byte_count = 0;
@@ -284,8 +287,10 @@ void parse_args(int argc, char **argv) {
 			version();
 	}
 
-	while((opt = my_getopt(argc, argv, "jwptTd:1ic:nbl:rmo:S:s:uhv")) != -1) {
+	while((opt = my_getopt(argc, argv, "ajwptTd:1ic:nbl:rmo:S:s:uhv")) != -1) {
 		switch(opt) {
+			case 'a':
+				skip_ascii = 1; break;
 			case 'j':
 				java_mode = 1; break;
 			case 'w':
@@ -422,19 +427,23 @@ void set_self(const char *argv0) {
 
 void print_line(void) {
 	int spacing = MAX_DUMP_COLS - dump_column;
+	int skip = skip_ascii ? line_all_ascii : 0;
 
-	printf("%s", left_buf);
+	if(!skip) {
+		printf("%s", left_buf);
 
-	/* line up the rightmost field (human-readable), for the partial
-	   line at the end of the output (if there is one). */
-	while(spacing--) printf("   ");
-	if(dump_column < (MAX_DUMP_COLS / 2)) putchar(' ');
+		/* line up the rightmost field (human-readable), for the partial
+			line at the end of the output (if there is one). */
+		while(spacing--) printf("   ");
+		if(dump_column < (MAX_DUMP_COLS / 2)) putchar(' ');
 
-	printf(" %s\n", right_buf);
+		printf(" %s\n", right_buf);
+	}
 
 	/* clear the buffers, start a new line */
 	left_buf[0] = right_buf[0] = '\0';
 	dump_column = 0;
+	line_all_ascii = 1;
 }
 
 void next_normal_hilite(void) {
@@ -726,6 +735,8 @@ int dump_utf8_char(void) {
 		bad = 1;
 	}
 
+	if(bad || cont_count) line_all_ascii = 0;
+
 	/* read and validate the continuation bytes, if any */
 	for(i = 0; i < cont_count; i++) {
 		int cb;
diff --git a/uxd.rst b/uxd.rst
index ae62093..ed52a84 100644
--- a/uxd.rst
+++ b/uxd.rst
@@ -71,6 +71,10 @@ Also, a decimal point can be used: **1.5K** is 1500 bytes, **1.5k** is
 
 .. don't alternate colors.
 
+-a
+   Don't dump lines that consist entirely of ASCII characters (codepoints
+   U+00 to U+7f).
+
 -b
   Bold output. This may be more or less readable, depending on your
   terminal and its color settings. Ignored if **-m** given.
@@ -426,7 +430,7 @@ Only UTF-8 and a couple of variants (WTF-8, MUTF-8) are supported.
 There is no support for UTF-16, UTF-32, UTF-EBCDIC, or any other
 non-UTF-8 encoding.
 
-There's no support for any number base except hex.
+There's no support for any output number base except hex.
 
 The input is read one byte at a time, so a search or regex match
 option would be difficult or impossible to implement.
@@ -457,4 +461,4 @@ B. Watson <urchlay@slackware.uk>.
 SEE ALSO
 ========
 
-xxd(1), bvi(1), utf-8(7), unicode(7)
+xxd(1), bvi(1), utf-8(7), unicode(7), console_codes(4)