add -i (info) option.

3 files changed, 42 insertions, 1 deletions

diff --git a/uxd.1 b/uxd.1
index 493002f..9107d3b 100644
--- a/uxd.1
+++ b/uxd.1
@@ -76,6 +76,11 @@ option.
 .B  \-h\fP,\fB  \-\-help
 Print built\-in usage message and exit.
 .TP
+.B  \-i
+After dumping, print information about the input: number of bytes,
+characters, ASCII (one\-byte) characters, multi\-byte characters, and
+bad sequences.
+.TP
 .BI \-l \ length
 Stop dumping after \fIlength\fP bytes (not characters). If the limit is
 reached in the middle of a multibyte character, the entire character
diff --git a/uxd.c b/uxd.c
index aebc224..93368a1 100644
--- a/uxd.c
+++ b/uxd.c
@@ -95,6 +95,7 @@ char * const special_symbols[] = {
 };
 
 /* options */
+int print_info = 0; /* -i */
 int bold = 0; /* -b */
 int hilite_multi = 0; /* -r */
 int mono = 0; /* -m */
@@ -105,6 +106,13 @@ long limit; /* -l */
 const char *hex_byte_fmt = "%02x";   /* -u */
 const char *hex_word_fmt = "%04x: "; /* "  */
 
+/* stats for -i option */
+long byte_count = 0;
+long ascii_count = 0;
+long multi_count = 0;
+long bad_count = 0;
+long char_count = 0;
+
 void usage(void) {
 	printf("uxd (Utf-8 heX Dump) v" VERSION " by B. Watson. WTFPL.\n");
 	printf("Usage: %s [<file>]\n", self);
@@ -174,8 +182,10 @@ void parse_args(int argc, char **argv) {
 			version();
 	}
 
-	while((opt = my_getopt(argc, argv, "c:nbl:rmo:S:s:uhv")) != -1) {
+	while((opt = my_getopt(argc, argv, "ic:nbl:rmo:S:s:uhv")) != -1) {
 		switch(opt) {
+			case 'i':
+				print_info = 1; break;
 			case 'c':
 				mono = 0; parse_colors(optarg); break;
 			case 'n':
@@ -395,6 +405,8 @@ int dump_utf8_char(void) {
 	if(c == EOF)
 		return 0;
 
+	byte_count++;
+
 	bytes[0] = (unsigned char)c;
 
 	if(filepos == 0) {
@@ -404,6 +416,7 @@ int dump_utf8_char(void) {
 	}
 
 	if(c < 0x7f) {
+		ascii_count++;
 		cont_count = 0;
 		if(c <= ' ' || c == 0x7f)
 			special = 1;
@@ -429,6 +442,8 @@ int dump_utf8_char(void) {
 			break;
 		}
 
+		byte_count++;
+
 		cb = cont_bytes[i] = (unsigned char)c;
 		if((cb & 0xc0) != 0x80) {
 			/* Expected 10xxxxxx, got something else */
@@ -443,6 +458,14 @@ int dump_utf8_char(void) {
 		bad = 1;
 
 	if(bad) {
+		bad_count++;
+	} else {
+		char_count++;
+		if(cont_count)
+			multi_count++;
+	}
+
+	if(bad) {
 		fg = BAD_FG;
 		bg = BAD_BG;
 		/* replacement character � is U+FFFD */
@@ -538,6 +561,14 @@ void dump_file(void) {
 	/* handle the last line, if the file size not divisible by 16. */
 	if(dump_column)
 		print_line();
+
+	if(print_info) {
+		printf("Bytes: %ld\n", byte_count);
+		printf("Characters: %ld\n", char_count);
+		printf("  ASCII: %ld\n", ascii_count);
+		printf("  Multibyte: %ld\n", multi_count);
+		printf("Bad sequences: %ld\n", bad_count);
+	}
 }
 
 int main(int argc, char **argv) {
diff --git a/uxd.rst b/uxd.rst
index 2acd120..0290f20 100644
--- a/uxd.rst
+++ b/uxd.rst
@@ -65,6 +65,11 @@ by itself.
 -h, --help
   Print built-in usage message and exit.
 
+-i
+  After dumping, print information about the input: number of bytes,
+  characters, ASCII (one-byte) characters, multi-byte characters, and
+  bad sequences.
+
 -l length
   Stop dumping after *length* bytes (not characters). If the limit is
   reached in the middle of a multibyte character, the entire character