xxd: new applet

Yet Another Hexdumper

function                                             old     new   delta
xxd_main                                               -     364    +364
packed_usage                                       31046   31116     +70
applet_names                                        2560    2564      +4
applet_main                                         1476    1480      +4
rewrite                                             1022    1013      -9
------------------------------------------------------------------------------
(add/remove: 2/0 grow/shrink: 3/1 up/down: 442/-9)            Total: 433 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>

3 files changed, 149 insertions, 16 deletions

diff --git a/libbb/dump.c b/libbb/dump.c
index 154be5d..e9ac0c6 100644
--- a/libbb/dump.c
+++ b/libbb/dump.c
@@ -165,16 +165,14 @@ static NOINLINE void rewrite(priv_dumper_t *dumper, FS *fs)
 				byte_count_str = "\001";
  DO_BYTE_COUNT:
 				if (fu->bcnt) {
-					do {
-						if (fu->bcnt == *byte_count_str) {
+					for (;;) {
+						if (fu->bcnt == *byte_count_str)
 							break;
-						}
-					} while (*++byte_count_str);
+						if (*++byte_count_str == 0)
+							bb_error_msg_and_die("bad byte count for conversion character %s", p1);
+					}
 				}
 				/* Unlike the original, output the remainder of the format string. */
-				if (!*byte_count_str) {
-					bb_error_msg_and_die("bad byte count for conversion character %s", p1);
-				}
 				pr->bcnt = *byte_count_str;
 			} else if (*p1 == 'l') {
 				++p2;
diff --git a/util-linux/hexdump.c b/util-linux/hexdump.c
index 4a7f641..4b536e1 100644
--- a/util-linux/hexdump.c
+++ b/util-linux/hexdump.c
@@ -47,6 +47,7 @@
 //usage:     "\n	-d		Two-byte decimal display"
 //usage:     "\n	-e FORMAT_STRING"
 //usage:     "\n	-f FORMAT_FILE"
+// exactly the same help text lines in hexdump and xxd:
 //usage:     "\n	-n LENGTH	Interpret only LENGTH bytes of input"
 //usage:     "\n	-o		Two-byte octal display"
 //usage:     "\n	-s OFFSET	Skip OFFSET bytes"
@@ -83,11 +84,11 @@ static void bb_dump_addfile(dumper_t *dumper, char *name)
 }
 
 static const char *const add_strings[] = {
-	"\"%07.7_ax \" 16/1 \"%03o \" \"\\n\"",   /* b */
-	"\"%07.7_ax \" 16/1 \"%3_c \" \"\\n\"",   /* c */
-	"\"%07.7_ax \" 8/2 \"  %05u \" \"\\n\"",  /* d */
-	"\"%07.7_ax \" 8/2 \" %06o \" \"\\n\"",   /* o */
-	"\"%07.7_ax \" 8/2 \"   %04x \" \"\\n\"", /* x */
+	"\"%07.7_ax \"16/1 \"%03o \"\"\n\"",   /* b */
+	"\"%07.7_ax \"16/1 \"%3_c \"\"\n\"",   /* c */
+	"\"%07.7_ax \"8/2 \"  %05u \"\"\n\"",  /* d */
+	"\"%07.7_ax \"8/2 \" %06o \"\"\n\"",   /* o */
+	"\"%07.7_ax \"8/2 \"   %04x \"\"\n\"", /* x */
 };
 
 static const char add_first[] ALIGN1 = "\"%07.7_Ax\n\"";
@@ -125,9 +126,11 @@ int hexdump_main(int argc, char **argv)
 		/* Save a little bit of space below by omitting the 'else's. */
 		if (ch == 'C') {
  hd_applet:
-			bb_dump_add(dumper, "\"%08.8_Ax\n\"");
-			bb_dump_add(dumper, "\"%08.8_ax  \" 8/1 \"%02x \" \"  \" 8/1 \"%02x \" ");
-			bb_dump_add(dumper, "\"  |\" 16/1 \"%_p\" \"|\\n\"");
+			bb_dump_add(dumper, "\"%08.8_Ax\n\""); // final address line after dump
+			//------------------- "address  "  8 * "xx "      "  " 8 * "xx "
+			bb_dump_add(dumper, "\"%08.8_ax  \"8/1 \"%02x \" \"  \"8/1 \"%02x \"");
+			//------------------- "  |ASCII...........|\n"
+			bb_dump_add(dumper, "\"  |\"16/1 \"%_p\"\"|\n\"");
 		}
 		if (ch == 'e') {
 			bb_dump_add(dumper, optarg);
@@ -158,7 +161,7 @@ int hexdump_main(int argc, char **argv)
 
 	if (!dumper->fshead) {
 		bb_dump_add(dumper, add_first);
-		bb_dump_add(dumper, "\"%07.7_ax \" 8/2 \"%04x \" \"\\n\"");
+		bb_dump_add(dumper, "\"%07.7_ax \"8/2 \"%04x \"\"\n\"");
 	}
 
 	argv += optind;
diff --git a/util-linux/hexdump_xxd.c b/util-linux/hexdump_xxd.c
new file mode 100644
index 0000000..3a7e64b
--- /dev/null
+++ b/util-linux/hexdump_xxd.c
@@ -0,0 +1,132 @@
+/* vi: set sw=4 ts=4: */
+/*
+ * xxd implementation for busybox
+ *
+ * Copyright (c) 2017 Denys Vlasenko <vda.linux@gmail.com>
+ *
+ * Licensed under GPLv2, see file LICENSE in this source tree.
+ */
+//config:config XXD
+//config:	bool "xxd"
+//config:	default y
+//config:	help
+//config:	  The xxd utility is used to display binary data in a readable
+//config:	  way that is comparable to the output from most hex editors.
+
+//applet:IF_XXD(APPLET_NOEXEC(xxd, xxd, BB_DIR_USR_BIN, BB_SUID_DROP, xxd))
+
+//kbuild:lib-$(CONFIG_XXD) += hexdump_xxd.o
+
+// $ xxd --version
+// xxd V1.10 27oct98 by Juergen Weigert
+// $ xxd --help
+// Usage:
+//       xxd [options] [infile [outfile]]
+//    or
+//       xxd -r [-s [-]offset] [-c cols] [-ps] [infile [outfile]]
+// Options:
+//    -a          toggle autoskip: A single '*' replaces nul-lines. Default off.
+//    -b          binary digit dump (incompatible with -ps,-i,-r). Default hex.
+//    -c cols     format <cols> octets per line. Default 16 (-i: 12, -ps: 30).
+//    -E          show characters in EBCDIC. Default ASCII.
+//    -e          little-endian dump (incompatible with -ps,-i,-r).
+//    -g          number of octets per group in normal output. Default 2 (-e: 4).
+//    -i          output in C include file style.
+//    -l len      stop after <len> octets.
+//    -o off      add <off> to the displayed file position.
+//    -ps         output in postscript plain hexdump style.
+//    -r          reverse operation: convert (or patch) hexdump into binary.
+//    -r -s off   revert with <off> added to file positions found in hexdump.
+//    -s [+][-]seek  start at <seek> bytes abs. (or +: rel.) infile offset.
+//    -u          use upper case hex letters.
+
+//usage:#define xxd_trivial_usage
+//usage:       "[OPTIONS] [FILE]"
+//usage:#define xxd_full_usage "\n\n"
+//usage:       "Hex dump FILE (or stdin)\n"
+//usage:     "\n	-g N		Bytes per group"
+//usage:     "\n	-c N		Bytes per line"
+// exactly the same help text lines in hexdump and xxd:
+//usage:     "\n	-l LENGTH	Interpret only LENGTH bytes of input"
+//usage:     "\n	-s OFFSET	Skip OFFSET bytes"
+
+#include "libbb.h"
+#include "dump.h"
+
+/* This is a NOEXEC applet. Be very careful! */
+
+int xxd_main(int argc, char **argv) MAIN_EXTERNALLY_VISIBLE;
+int xxd_main(int argc UNUSED_PARAM, char **argv)
+{
+	char buf[80];
+	dumper_t *dumper;
+	char *opt_l, *opt_s;
+	unsigned bytes = 2;
+	unsigned cols = 0;
+	unsigned opt;
+
+	dumper = alloc_dumper();
+
+#define OPT_l (1 << 0)
+#define OPT_s (1 << 1)
+#define OPT_a (1 << 2)
+	opt_complementary = "?1"; /* 1 argument max */
+	opt = getopt32(argv, "l:s:ag:+c:+", &opt_l, &opt_s, &bytes, &cols);
+	argv += optind;
+
+//	dumper->dump_vflag = ALL; // default
+//	if (opt & OPT_a)
+//		dumper->dump_vflag = SKIPNUL; ..does not exist
+	if (opt & OPT_l) {
+		dumper->dump_length = xstrtou_range(
+				opt_l,
+				/*base:*/ 0,
+				/*lo:*/ 0, /*hi:*/ INT_MAX
+		);
+	}
+	if (opt & OPT_s) {
+		dumper->dump_skip = xstrtoull_range(
+				opt_s,
+				/*base:*/ 0,
+				/*lo:*/ 0, /*hi:*/ OFF_T_MAX
+		);
+		//BUGGY for /proc/version (unseekable?)
+	}
+
+	bb_dump_add(dumper, "\"%08.8_ax: \""); // "address: "
+	if (cols == 0)
+		cols = 16;
+	if (bytes < 1 || bytes >= cols) {
+		sprintf(buf, "%u/1 \"%%02x\"", cols); // cols * "xx"
+		bb_dump_add(dumper, buf);
+	}
+	else if (bytes == 1) {
+		sprintf(buf, "%u/1 \"%%02x \"", cols); // cols * "xx "
+		bb_dump_add(dumper, buf);
+	}
+	else {
+/* Format "print byte" with and without trailing space */
+#define BS "/1 \"%02x \""
+#define B  "/1 \"%02x\""
+		unsigned i;
+		char *bigbuf = xmalloc(1 + cols * (sizeof(BS)-1));
+		char *p = bigbuf;
+		for (i = 1; i <= cols; i++) {
+			if (i == cols || i % bytes)
+				p = stpcpy(p, B);
+			else
+				p = stpcpy(p, BS);
+		}
+		// for -g3, this results in B B BS B B BS... B = "xxxxxx xxxxxx .....xx"
+		// todo: can be more clever and use
+		// one "cols-1/B" format instead of many "B B B..." formats
+		//bb_error_msg("ADDED:'%s'", bigbuf);
+		bb_dump_add(dumper, bigbuf);
+		free(bigbuf);
+	}
+
+	sprintf(buf, "\"  \" %u/1 \"%%_p\" \"\n\"", cols); // "  ASCII\n"
+	bb_dump_add(dumper, buf);
+
+	return bb_dump_dump(dumper, argv);
+}