Unlike the POSIX file(1), there's no magic file here, just hard-coded common (non-obsolete) file formats. Personally most of my use of file(1) is as a one-line readelf(1) summarizer, so although I assume a full POSIX file(1) is out of scope (because just the database would likely be larger than all the rest of toybox), a subset that only supports in-use file types actually covers most of the use cases I encounter personally.
Also fix peek_be/peek_le. --- lib/lib.c | 7 +- toys/pending/file.c | 237 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 240 insertions(+), 4 deletions(-) create mode 100644 toys/pending/file.c
From 3ec14dd809c9bf39053eea4b956b18effb5f72d2 Mon Sep 17 00:00:00 2001 From: Elliott Hughes <[email protected]> Date: Sat, 13 Feb 2016 09:50:20 -0800 Subject: [PATCH] Implement file(1). Unlike the POSIX file(1), there's no magic file here, just hard-coded common (non-obsolete) file formats. Personally most of my use of file(1) is as a one-line readelf(1) summarizer, so although I assume a full POSIX file(1) is out of scope (because just the database would likely be larger than all the rest of toybox), a subset that only supports in-use file types actually covers most of the use cases I encounter personally. Also fix peek_be/peek_le. --- lib/lib.c | 7 +- toys/pending/file.c | 237 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 240 insertions(+), 4 deletions(-) create mode 100644 toys/pending/file.c diff --git a/lib/lib.c b/lib/lib.c index 681d4d2..e80b8b1 100644 --- a/lib/lib.c +++ b/lib/lib.c @@ -508,8 +508,7 @@ int64_t peek_le(void *ptr, unsigned size) char *c = ptr; int i; - for (i=0; i<size; i++) ret |= ((int64_t)c[i])<<i; - + for (i=0; i<size; i++) ret |= ((int64_t)c[i])<<(i*8); return ret; } @@ -517,9 +516,9 @@ int64_t peek_be(void *ptr, unsigned size) { int64_t ret = 0; char *c = ptr; + int i; - while (size--) ret = (ret<<8)|c[size]; - + for (i=0; i<size; i++) ret = (ret<<8)|(c[i]&0xff); return ret; } diff --git a/toys/pending/file.c b/toys/pending/file.c new file mode 100644 index 0000000..fc7e621 --- /dev/null +++ b/toys/pending/file.c @@ -0,0 +1,237 @@ +/* file.c - describe file type + * + * Copyright 2016 The Android Open Source Project + * + * See http://pubs.opengroup.org/onlinepubs/9699919799/utilities/file.html + +USE_FILE(NEWTOY(file, "<1", TOYFLAG_USR|TOYFLAG_BIN)) + +config FILE + bool "file" + default y + help + usage: file [file...] + + Examine the given files and describe their content types. +*/ + +#define FOR_file +#include "toys.h" + +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"); + + // "64-bit" + if (toybuf[4] == 1) xprintf(" 32-bit"); + else if (toybuf[4] == 2) xprintf(" 64-bit"); + else xprintf(" (invalid 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); + } + + // "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)"); + 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" + // ", BuildID[sha1]=SHA" + // ", stripped" + + xputs(""); +} + +// https://www.w3.org/TR/PNG/#6Colour-values +static char *png_color_type(int color_type) +{ + 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"; + } +} + +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"); + } + + xputs(""); +} + +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("GIF image data, %d x %d\n", width, height); +} + +static void do_jpeg_file() +{ + // TODO: parsing JPEG for width/height is harder than GIF or PNG. + xprintf("JPEG image data\n"); +} + +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("Java class file, version %d.%d\n", major, minor); +} + +static void do_regular_file(int fd, char *name) +{ + int len = read(fd, toybuf, sizeof(toybuf)); + + if (len<0) perror_msg("cannot open"); + + 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(); + + // TODO: cpio archive. + // TODO: tar archive. + // TODO: zip/jar/apk archive. + } else { + char *what = "ASCII text"; + int i; + + // TODO: report which interpreter? + if (strncmp(toybuf, "#!", 2) == 0) what = "commands text"; + + // TODO: try UTF-8 too before falling back to "data". + for (i = 0; i < len; ++i) { + if (!(isprint(toybuf[i]) || isspace(toybuf[i]))) { + what = "data"; + break; + } + } + xputs(what); + } +} + +static void do_file(int fd, char *name) +{ + struct stat sb; + char *what = "unknown"; + + xprintf("%s: %*s", name, (int)(TT.max_name_len - strlen(name)), ""); + + if (!fstat(fd, &sb)) what = "cannot open"; + if (S_ISREG(sb.st_mode)) { + if (sb.st_size == 0) what = "empty"; + else { + do_regular_file(fd, name); + return; + } + } else if (S_ISBLK(sb.st_mode)) what = "block special"; + else if (S_ISCHR(sb.st_mode)) what = "character special"; + else if (S_ISDIR(sb.st_mode)) what = "directory"; + else if (S_ISFIFO(sb.st_mode)) what = "fifo"; + else if (S_ISSOCK(sb.st_mode)) what = "socket"; + else if (S_ISLNK(sb.st_mode)) what = "symbolic link"; + xputs(what); +} + +static void init_max_name_len() +{ + char **name; + int name_len; + + for (name = toys.optargs; *name; ++name) { + 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); +} -- 2.7.0.rc3.207.g0ac5344
_______________________________________________ Toybox mailing list [email protected] http://lists.landley.net/listinfo.cgi/toybox-landley.net
