Add binary output option (-b) to kstool (keystone-engine#453)

* Add binary output option (-b) to kstool

Using -b option, kstool will print the encoded instructions to stdout
in binary format.

For example:

```
kstool -b arm64 "CCMP X0, X1, 4, EQ" 0xcafebaba | xxd
00000000: 0400 41fa                                ..A.
```

For `getopt`, this commit reuse the getopt.c from capstone-engine.

* Fix build for MSVC

kstool/CMakeLists.txt

@@ -7,7 +7,12 @@ project(kstool)
 
 include_directories("../include")
 
-add_executable(kstool kstool.cpp)
+if (${CMAKE_CXX_COMPILER_ID} STREQUAL MSVC)
+  include_directories("./")
+  add_executable(kstool getopt.c kstool.cpp)
+else()
+  add_executable(kstool kstool.cpp)
+endif()
 
 target_link_libraries(kstool keystone)
 

kstool/getopt.c

@@ -0,0 +1,79 @@
+extern "C" {
+
+#include <string.h>
+#include <stdio.h>
+
+#include "getopt.h"
+
+int opterr = 1, /* if error message should be printed */
+optind = 1, /* index into parent argv vector */
+optopt, /* character checked for validity */
+optreset; /* reset getopt */
+const char *optarg; /* argument associated with option */
+
+#define BADCH (int)'?'
+#define BADARG (int)':'
+#define EMSG ""
+
+/*
+ * getopt --
+ *      Parse argc/argv argument vector.
+ */
+int getopt (int nargc, char * const nargv[], const char *ostr)
+{
+	static const char *place = EMSG;              /* option letter processing */
+	const char *oli;                        /* option letter list index */
+
+	if (optreset || !*place) {              /* update scanning pointer */
+		optreset = 0;
+		if (optind >= nargc || *(place = nargv[optind]) != '-') {
+			place = EMSG;
+			return (-1);
+		}
+
+		if (place[1] && *++place == '-') {      /* found "--" */
+			++optind;
+			place = EMSG;
+			return (-1);
+		}
+	}                                       /* option letter okay? */
+
+	if ((optopt = (int)*place++) == (int)':' ||
+		!(oli = strchr (ostr, optopt))) {
+		/*
+		* if the user didn't specify '-' as an option,
+		* assume it means -1.
+		*/
+		if (optopt == (int)'-')
+			return (-1);
+		if (!*place)
+			++optind;
+		if (opterr && *ostr != ':')
+			(void)printf ("illegal option -- %c\n", optopt);
+		return (BADCH);
+	}
+
+	if (*++oli != ':') {                    /* don't need argument */
+		optarg = NULL;
+		if (!*place)
+			++optind;
+	} else {                                  /* need an argument */
+		if (*place)                     /* no white space */
+			optarg = place;
+		else if (nargc <= ++optind) {   /* no arg */
+			place = EMSG;
+			if (*ostr == ':')
+				return (BADARG);
+			if (opterr)
+				(void)printf ("option requires an argument -- %c\n", optopt);
+			return (BADCH);
+		} else                            /* white space */
+			optarg = nargv[optind];
+		place = EMSG;
+		++optind;
+	}
+
+	return optopt;        /* dump back option letter */
+}
+
+} // end extern "C"

kstool/getopt.h

@@ -0,0 +1,18 @@
+extern "C" {
+
+#ifndef KSTOOL_GETOPT_H
+#define KSTOOL_GETOPT_H
+
+// global
+extern int opterr, /* if error message should be printed */
+optind, /* index into parent argv vector */
+optopt, /* character checked for validity */
+optreset; /* reset getopt */
+
+extern const char *optarg; /* argument associated with option */
+
+int getopt (int nargc, char *const nargv[], const char *ostr);
+
+#endif
+
+} // end extern "C"

kstool/kstool.cpp

@@ -14,11 +14,15 @@
 
 #include <keystone/keystone.h>
 
+#if defined(WIN32) || defined(WIN64) || defined(_WIN32) || defined(_WIN64)
+#include "getopt.h"
+#endif
+
 static void usage(char *prog)
 {
     printf("Kstool v%u.%u.%u for Keystone Assembler Engine (www.keystone-engine.org)\nBy Nguyen Anh Quynh, 2016-2018\n\n",
             KS_VERSION_MAJOR, KS_VERSION_MINOR, KS_VERSION_EXTRA);
-    printf("Syntax: %s <arch+mode> <assembly-string> [start-address-in-hex-format]\n", prog);
+    printf("Syntax: %s [-b] <arch+mode> <assembly-string> [start-address-in-hex-format]\n", prog);
     printf("\nThe following <arch+mode> options are supported:\n");
 
     if (ks_arch_supported(KS_ARCH_X86)) {
@@ -79,7 +83,8 @@ static void usage(char *prog)
         printf("        evm:       Ethereum Virtual Machine\n");
     }
 
-    printf("\n");
+    printf("\nExtra options:\n");
+    printf("        -b binary output\n\n");
 }
 
 int main(int argc, char **argv)
@@ -92,15 +97,33 @@ int main(int argc, char **argv)
     size_t count;
     unsigned char *insn = NULL;
     size_t size;
-
-    if (argc == 2) {
+    bool binary_output = false;
+    int c;
+    int args_left;
+
+    while ((c = getopt(argc, argv, "bh")) != -1) {
+      switch (c) {
+        case 'b':
+          binary_output = true;
+          break;
+        case 'h':
+          usage(argv[0]);
+          return 0;
+        default:
+          usage(argv[0]);
+          return -1;
+      }
+    }
+
+    args_left = argc - optind;
+    if (args_left == 1) {
         // handle code from stdin
 #if !defined(WIN32) && !defined(WIN64) && !defined(_WIN32) && !defined(_WIN64)
         int flags;
         size_t index = 0;
         char buf[1024];
 
-        mode = argv[1];
+        mode = argv[optind];
 
         if ((flags = fcntl(STDIN_FILENO, F_GETFL, 0)) == -1)
             flags = 0;
@@ -129,17 +152,17 @@ int main(int argc, char **argv)
         usage(argv[0]);
         return -1;
 #endif
-    } else if (argc == 3) {
+    } else if (args_left == 2) {
         // kstool <arch> <assembly>
-        mode = argv[1];
-        assembly = argv[2];
-    } else if (argc == 4) {
+        mode = argv[optind];
+        assembly = argv[optind + 1];
+    } else if (args_left == 3) {
         // kstool <arch> <assembly> <address>
         char *temp;
-        mode = argv[1];
-        assembly = argv[2];
-        start_addr = strtoull(argv[3], &temp, 16);
-        if (temp == argv[3] || *temp != '\0' || errno == ERANGE) {
+        mode = argv[optind];
+        assembly = argv[optind + 1];
+        start_addr = strtoull(argv[optind + 2], &temp, 16);
+        if (temp == argv[optind + 2] || *temp != '\0' || errno == ERANGE) {
             printf("ERROR: invalid address argument, quit!\n");
             return -2;
         }
@@ -293,13 +316,20 @@ int main(int argc, char **argv)
     if (ks_asm(ks, assembly, start_addr, &insn, &size, &count)) {
         printf("ERROR: failed on ks_asm() with count = %zu, error = '%s' (code = %u)\n", count, ks_strerror(ks_errno(ks)), ks_errno(ks));
     } else {
-        size_t i;
-        printf("%s = [ ", assembly);
-        for (i = 0; i < size; i++) {
-            printf("%02x ", insn[i]);
+        if (binary_output) {
+          size_t i;
+          for (i = 0; i < size; ++i) {
+            putchar(insn[i]);
+          }
+        } else {
+          size_t i;
+          printf("%s = [ ", assembly);
+          for (i = 0; i < size; i++) {
+              printf("%02x ", insn[i]);
+          }
+          printf("]\n");
+          //printf("Assembled: %lu bytes, %lu statement(s)\n", size, count);
         }
-        printf("]\n");
-        //printf("Assembled: %lu bytes, %lu statement(s)\n", size, count);
     }
 
     // NOTE: free insn after usage to avoid leaking memory