Cleanup pass on file.c, and add detection of different ELF architectures.

1 files changed, 97 insertions, 135 deletions

diff --git a/toys/pending/file.c b/toys/pending/file.c
index 1ebafdb0..2c2f2864 100644
--- a/toys/pending/file.c
+++ b/toys/pending/file.c
@@ -22,177 +22,143 @@ GLOBALS(
   int max_name_len;
 )
 
-// TODO: all the ELF magic numbers are available in <elf.h> --- use that?
-
-static char *elf_arch(int e_machine)
-{
-  // TODO: include obsolete stuff we'll never see, like "PDP-10" and "VAX"?
-  switch (e_machine) {
-  case 3: return "Intel 80386";
-  case 8: return "MIPS";
-  case 40: return "ARM";
-  case 62: return "x86-64";
-  case 183: return "ARM aarch64";
-  default: return NULL;
-  }
-}
-
-static int64_t elf_int(int endian, char *data, int bytes)
-{
-  if (endian == 1) return peek_le(data, bytes);
-  return peek_be(data, bytes);
-}
-
 static void do_elf_file()
 {
-  int elf_endian = toybuf[5];
-  int e_type, e_machine;
-
-  xprintf("ELF");
+  int elf_endian = toybuf[5], e_type, e_machine, i;
+  int64_t (*elf_int)(void *ptr, unsigned size) = peek_le;
+  // Values from include/linux/elf-em.h (plus arch/*/include/asm/elf.h)
+  // Names are linux/arch/ directory name
+  struct {int val; char *name;} type[] = {{0x9026, "alpha"},
+    {40, "arm"}, {183, "arm"}, {0x18ad, "avr32"}, {106, "blackfin"},
+    {76, "cris"}, {0x5441, "frv"}, {46, "h8300"}, {50, "ia64"},//ia intel ftaghn
+    {88, "m32r"}, {4, "m68k"}, {0xbaab, "microblaze"}, {8, "mips"},
+    {10, "mips"}, {89, "mn10300"}, {15, "parisc"}, {22, "s390"},
+    {135, "score"}, {42, "sh"}, {2, "sparc"}, {18, "sparc"}, {43, "sparc"},
+    {187, "tile"}, {188, "tile"}, {191, "tile"}, {3, "x86"}, {6, "x86"},
+    {62, "x86"}, {94, "xtensa"}, {0xabc7, "xtensa"}};
+
+  xprintf("ELF ");
 
   // "64-bit"
-  if (toybuf[4] == 1) xprintf(" 32-bit");
-  else if (toybuf[4] == 2) xprintf(" 64-bit");
-  else xprintf(" (invalid class %d)", toybuf[4]);
+  if (toybuf[4] == 1) xprintf("32-bit ");
+  else if (toybuf[4] == 2) xprintf("64-bit ");
+  else xprintf("(bad class %d)", toybuf[4]);
 
   // "LSB"
-  if (elf_endian == 1) xprintf(" LSB");
-  else if (elf_endian == 2) xprintf(" MSB");
-  else xprintf("(invalid endian %d) ", elf_endian);
-
-  if (elf_endian == 1 || elf_endian == 2) {
-    char *arch;
-
-    // ", executable"
-    e_type = elf_int(elf_endian, &toybuf[0x10], 2);
-    if (e_type == 1) xprintf(" relocatable");
-    else if (e_type == 2) xprintf(" executable");
-    else if (e_type == 3) xprintf(" shared object");
-    else if (e_type == 4) xprintf(" core dump");
-    else xprintf(" (invalid type %d)", e_type);
-
-    // ", x86-64"
-    e_machine = elf_int(elf_endian, &toybuf[0x12], 2);
-    arch = elf_arch(e_machine);
-    if (arch) xprintf(", %s", arch);
-    else xprintf(", (unknown arch %d)", e_machine);
+  if (elf_endian == 1) xprintf("LSB ");
+  else if (elf_endian == 2) {
+    xprintf("MSB ");
+    elf_int = peek_be;
+  } else {
+    xprintf("(bad endian %d)\n", elf_endian);
+
+    // At this point we can't parse remaining fields.
+    return;
   }
 
+  // ", executable"
+  e_type = elf_int(&toybuf[0x10], 2);
+  if (e_type == 1) xprintf("relocatable");
+  else if (e_type == 2) xprintf("executable");
+  else if (e_type == 3) xprintf("shared object");
+  else if (e_type == 4) xprintf("core dump");
+  else xprintf("(invalid type %d)", e_type);
+
+  // ", x86-64"
+  e_machine = elf_int(&toybuf[0x12], 2);
+  for (i = 0; i<ARRAY_LEN(type); i++) if (e_machine == type[i].val) break;
+  if (i<ARRAY_LEN(type)) xprintf(", %s", type[i].name);
+  else xprintf(", (unknown arch %d)", e_machine);
+
   // "version 1"
   xprintf(", version %d", toybuf[6]);
 
   // " (SYSV)"
   // TODO: will we ever meet any of the others in practice?
-  if (toybuf[7] == 0) xprintf(" (SYSV)");
+  if (!toybuf[7]) xprintf(" (SYSV)");
   else xprintf(" (OS %d)", toybuf[7]);
 
   // TODO: we'd need to actually parse the ELF file to report the rest...
   // ", dynamically linked"
   // " (uses shared libs)"
-  // ", for GNU/Linux 2.6.24"
+  // ", for Linux 2.6.24"
   // ", BuildID[sha1]=SHA"
   // ", stripped"
 
-  xputs("");
+  xputc('\n');
 }
 
-// https://www.w3.org/TR/PNG/#6Colour-values
-static char *png_color_type(int color_type)
+static void do_regular_file(int fd, char *name)
 {
-  switch (color_type) {
-  case 0: return "grayscale";
-  case 2: return "color RGB";
-  case 3: return "indexed color";
-  case 4: return "grayscale with alpha";
-  case 6: return "color RGBA";
-  default: return "unknown";
-  }
-}
+  char *s;
+  int len = read(fd, s = toybuf, sizeof(toybuf)-256);
 
-static void do_png_file()
-{
-  // PNG is big-endian: https://www.w3.org/TR/PNG/#7Integers-and-byte-order
-  int chunk_length = peek_be(&toybuf[8], 4);
-
-  xprintf("PNG image data");
-
-  // The IHDR chunk comes first.
-  // https://www.w3.org/TR/PNG/#11IHDR
-  if (chunk_length == 13 && memcmp(&toybuf[12], "IHDR", 4) == 0) {
-    int width = peek_be(&toybuf[16], 4);
-    int height = peek_be(&toybuf[20], 4);
-    int bits = toybuf[24] & 0xff;
-    int type = toybuf[25] & 0xff;
-    int interlaced = toybuf[28] & 0xff;
-
-    xprintf(", %d x %d, %d-bit/%s, %s", width, height, bits,
-            png_color_type(type),
-            interlaced ? "interlaced" : "non-interlaced");
-  }
+  if (len<0) perror_msg("%s", name);
 
-  xputs("");
-}
+  if (len>20 && strstart(&s, "\177ELF")) {
+    do_elf_file(len);
+  } else if (len>28 && strstart(&s, "\x89PNG\x0d\x0a\x1a\x0a")) {
+    // PNG is big-endian: https://www.w3.org/TR/PNG/#7Integers-and-byte-order
+    int chunk_length = peek_be(s, 4);
 
-static void do_gif_file()
-{
-  // https://www.w3.org/Graphics/GIF/spec-gif89a.txt
-  int width = peek_le(&toybuf[6], 2);
-  int height = peek_le(&toybuf[8], 2);
+    xprintf("PNG image data");
 
-  xprintf("GIF image data, %d x %d\n", width, height);
-}
+    // The IHDR chunk comes first: https://www.w3.org/TR/PNG/#11IHDR
+    s += 4;
+    if (chunk_length == 13 && strstart(&s, "IHDR")) {
+      // https://www.w3.org/TR/PNG/#6Colour-values
+      char *c = 0, *colors[] = {"grayscale", 0, "color RGB", "indexed color",
+                                "grayscale with alpha", 0, "color RGBA"};
 
-static void do_jpeg_file()
-{
-  // TODO: parsing JPEG for width/height is harder than GIF or PNG.
-  xprintf("JPEG image data\n");
-}
+      if (s[9]<ARRAY_LEN(colors)) c = colors[s[9]];
+      if (!c) c = "unknown";
 
-static void do_java_class_file()
-{
-  // https://docs.oracle.com/javase/specs/jvms/se7/html/jvms-4.html
-  int minor = peek_be(&toybuf[4], 2);
-  int major = peek_be(&toybuf[6], 2);
+      xprintf(", %d x %d, %d-bit/%s, %sinterlaced", (int)peek_be(s, 4),
+        (int)peek_be(s+4, 4), s[8], c, s[12] ? "" : "non-");
+    }
 
-  xprintf("Java class file, version %d.%d\n", major, minor);
-}
+    xputc('\n');
 
-static void do_regular_file(int fd, char *name)
-{
-  int len = read(fd, toybuf, sizeof(toybuf));
+  // https://www.w3.org/Graphics/GIF/spec-gif89a.txt
+  } else if (len>16 && (strstart(&s, "GIF87a") || strstart(&s, "GIF89a")))
+    xprintf("GIF image data, %d x %d\n",
+      (int)peek_le(s, 2), (int)peek_le(s+8, 2));
 
-  if (len<0) perror_msg("cannot open");
+  // TODO: parsing JPEG for width/height is harder than GIF or PNG.
+  else if (len>32 && memcmp(toybuf, "\xff\xd8", 2) == 0)
+    xprintf("JPEG image data\n");
 
-  if (len>20 && memcmp(toybuf, "\177ELF", 4) == 0) {
-    do_elf_file(len);
-  } else if (len>28 && memcmp(toybuf, "\x89PNG\x0d\x0a\x1a\x0a", 8) == 0) {
-    do_png_file();
-  } else if (len>16 && (memcmp(toybuf, "GIF87a", 6) == 0 ||
-                        memcmp(toybuf, "GIF89a", 6) == 0)) {
-    do_gif_file();
-  } else if (len>32 && memcmp(toybuf, "\xff\xd8", 2) == 0) {
-    do_jpeg_file();
-  } else if (len>8 && memcmp(toybuf, "\xca\xfe\xba\xbe", 4) == 0) {
-    do_java_class_file();
+  // https://docs.oracle.com/javase/specs/jvms/se7/html/jvms-4.html
+  else if (len>8 && strstart(&s, "\xca\xfe\xba\xbe"))
+    xprintf("Java class file, version %d.%d\n",
+      (int)peek_be(s+6, 2), (int)peek_be(s, 2));
 
     // TODO: cpio archive.
     // TODO: tar archive.
     // TODO: zip/jar/apk archive.
-  } else {
-    char *what = "ASCII text";
-    int i;
+  else {
+    char *what = 0;
+    int i, bytes;
 
-    // TODO: report which interpreter?
-    if (strncmp(toybuf, "#!", 2) == 0) what = "commands text";
+    // If shell script, report which interpreter
+    if (len>3 && strstart(&s, "#!")) {
+      for (what = s; (s-toybuf)<len && !isspace(*s); s++);
+      strcpy(s, " script");
 
-    // TODO: try UTF-8 too before falling back to "data".
-    for (i = 0; i < len; ++i) {
+    // Distinguish ASCII text, UTF-8 text, or data
+    } else for (i = 0; i<len; ++i) {
       if (!(isprint(toybuf[i]) || isspace(toybuf[i]))) {
-        what = "data";
-        break;
+        wchar_t wc;
+        if ((bytes = mbrtowc(&wc, s+i, len-i, 0))>0 && wcwidth(wc)>=0) {
+          i += bytes-1;
+          if (!what) what = "UTF-8 text";
+        } else {
+          what = "data";
+          break;
+        }
       }
     }
-    xputs(what);
+    xputs(what ? what : "ASCII text");
   }
 }
 
@@ -219,19 +185,15 @@ static void do_file(int fd, char *name)
   xputs(what);
 }
 
-static void init_max_name_len()
+void file_main(void)
 {
   char **name;
-  int name_len;
 
   for (name = toys.optargs; *name; ++name) {
-    name_len = strlen(*name);
+    int name_len = strlen(*name);
+
     if (name_len > TT.max_name_len) TT.max_name_len = name_len;
   }
-}
 
-void file_main(void)
-{
-  init_max_name_len();
   loopfiles(toys.optargs, do_file);
 }