#include "file.h"
#include "magic.h"
#include <stdio.h>
#include <string.h>
#include <memory.h>
#include <ctype.h>
#include <stdlib.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#include "names.h"
#ifndef lint
FILE_RCSID("@(#)$Id: ascmagic.c,v 1.45 2006/03/12 22:09:33 christos Exp $")
#endif
typedef unsigned long unichar;
#define MAXLINELEN 300
#define ISSPC(x) ((x) == ' ' || (x) == '\t' || (x) == '\r' || (x) == '\n' \
|| (x) == 0x85 || (x) == '\f')
private int looks_ascii(const unsigned char *, size_t, unichar *, size_t *);
private int looks_utf8(const unsigned char *, size_t, unichar *, size_t *);
private int looks_unicode(const unsigned char *, size_t, unichar *, size_t *);
private int looks_latin1(const unsigned char *, size_t, unichar *, size_t *);
private int looks_extended(const unsigned char *, size_t, unichar *, size_t *);
private void from_ebcdic(const unsigned char *, size_t, unsigned char *);
private int ascmatch(const unsigned char *, const unichar *, size_t);
protected int
file_ascmagic(struct magic_set *ms, const unsigned char *buf, size_t nbytes)
{
size_t i;
unsigned char *nbuf = NULL;
unichar *ubuf = NULL;
size_t ulen;
struct names *p;
int rv = -1;
const char *code = NULL;
const char *code_mime = NULL;
const char *type = NULL;
const char *subtype = NULL;
const char *subtype_mime = NULL;
int has_escapes = 0;
int has_backspace = 0;
int seen_cr = 0;
int n_crlf = 0;
int n_lf = 0;
int n_cr = 0;
int n_nel = 0;
int last_line_end = -1;
int has_long_lines = 0;
while (nbytes > 1 && buf[nbytes - 1] == '\0')
nbytes--;
if ((nbuf = malloc((nbytes + 1) * sizeof(nbuf[0]))) == NULL)
goto done;
if ((ubuf = malloc((nbytes + 1) * sizeof(ubuf[0]))) == NULL)
goto done;
if (looks_ascii(buf, nbytes, ubuf, &ulen)) {
code = "ASCII";
code_mime = "us-ascii";
type = "text";
} else if (looks_utf8(buf, nbytes, ubuf, &ulen)) {
code = "UTF-8 Unicode";
code_mime = "utf-8";
type = "text";
} else if ((i = looks_unicode(buf, nbytes, ubuf, &ulen)) != 0) {
if (i == 1)
code = "Little-endian UTF-16 Unicode";
else
code = "Big-endian UTF-16 Unicode";
type = "character data";
code_mime = "utf-16";
} else if (looks_latin1(buf, nbytes, ubuf, &ulen)) {
code = "ISO-8859";
type = "text";
code_mime = "iso-8859-1";
} else if (looks_extended(buf, nbytes, ubuf, &ulen)) {
code = "Non-ISO extended-ASCII";
type = "text";
code_mime = "unknown";
} else {
from_ebcdic(buf, nbytes, nbuf);
if (looks_ascii(nbuf, nbytes, ubuf, &ulen)) {
code = "EBCDIC";
type = "character data";
code_mime = "ebcdic";
} else if (looks_latin1(nbuf, nbytes, ubuf, &ulen)) {
code = "International EBCDIC";
type = "character data";
code_mime = "ebcdic";
} else {
rv = 0;
goto done;
}
}
if (nbytes <= 1) {
rv = 0;
goto done;
}
if (*ubuf == '.') {
unichar *tp = ubuf + 1;
while (ISSPC(*tp))
++tp;
if ((tp[0] == '\\' && tp[1] == '\"') ||
(isascii((unsigned char)tp[0]) &&
isalnum((unsigned char)tp[0]) &&
isascii((unsigned char)tp[1]) &&
isalnum((unsigned char)tp[1]) &&
ISSPC(tp[2]))) {
subtype_mime = "text/troff";
subtype = "troff or preprocessor input";
goto subtype_identified;
}
}
if ((*buf == 'c' || *buf == 'C') && ISSPC(buf[1])) {
subtype_mime = "text/fortran";
subtype = "fortran program";
goto subtype_identified;
}
i = 0;
while (i < ulen) {
size_t end;
while (i < ulen && ISSPC(ubuf[i]))
i++;
if (i >= ulen)
break;
for (end = i + 1; end < nbytes; end++)
if (ISSPC(ubuf[end]))
break;
for (p = names; p < names + NNAMES; p++) {
if (ascmatch((const unsigned char *)p->name, ubuf + i,
end - i)) {
subtype = types[p->type].human;
subtype_mime = types[p->type].mime;
goto subtype_identified;
}
}
i = end;
}
subtype_identified:
for (i = 0; i < ulen; i++) {
if (ubuf[i] == '\n') {
if (seen_cr)
n_crlf++;
else
n_lf++;
last_line_end = i;
} else if (seen_cr)
n_cr++;
seen_cr = (ubuf[i] == '\r');
if (seen_cr)
last_line_end = i;
if (ubuf[i] == 0x85) {
n_nel++;
last_line_end = i;
}
if (i > last_line_end + MAXLINELEN)
has_long_lines = 1;
if (ubuf[i] == '\033')
has_escapes = 1;
if (ubuf[i] == '\b')
has_backspace = 1;
}
if (seen_cr && nbytes < HOWMANY)
n_cr++;
if ((ms->flags & MAGIC_MIME)) {
if (subtype_mime) {
if (file_printf(ms, subtype_mime) == -1)
goto done;
} else {
if (file_printf(ms, "text/plain") == -1)
goto done;
}
if (code_mime) {
if (file_printf(ms, "; charset=") == -1)
goto done;
if (file_printf(ms, code_mime) == -1)
goto done;
}
} else {
if (file_printf(ms, code) == -1)
goto done;
if (subtype) {
if (file_printf(ms, " ") == -1)
goto done;
if (file_printf(ms, subtype) == -1)
goto done;
}
if (file_printf(ms, " ") == -1)
goto done;
if (file_printf(ms, type) == -1)
goto done;
if (has_long_lines)
if (file_printf(ms, ", with very long lines") == -1)
goto done;
if ((n_crlf == 0 && n_cr == 0 && n_nel == 0 && n_lf == 0) ||
(n_crlf != 0 || n_cr != 0 || n_nel != 0)) {
if (file_printf(ms, ", with") == -1)
goto done;
if (n_crlf == 0 && n_cr == 0 && n_nel == 0 && n_lf == 0) {
if (file_printf(ms, " no") == -1)
goto done;
} else {
if (n_crlf) {
if (file_printf(ms, " CRLF") == -1)
goto done;
if (n_cr || n_lf || n_nel)
if (file_printf(ms, ",") == -1)
goto done;
}
if (n_cr) {
if (file_printf(ms, " CR") == -1)
goto done;
if (n_lf || n_nel)
if (file_printf(ms, ",") == -1)
goto done;
}
if (n_lf) {
if (file_printf(ms, " LF") == -1)
goto done;
if (n_nel)
if (file_printf(ms, ",") == -1)
goto done;
}
if (n_nel)
if (file_printf(ms, " NEL") == -1)
goto done;
}
if (file_printf(ms, " line terminators") == -1)
goto done;
}
if (has_escapes)
if (file_printf(ms, ", with escape sequences") == -1)
goto done;
if (has_backspace)
if (file_printf(ms, ", with overstriking") == -1)
goto done;
}
rv = 1;
done:
if (nbuf)
free(nbuf);
if (ubuf)
free(ubuf);
return rv;
}
private int
ascmatch(const unsigned char *s, const unichar *us, size_t ulen)
{
size_t i;
for (i = 0; i < ulen; i++) {
if (s[i] != us[i])
return 0;
}
if (s[i])
return 0;
else
return 1;
}
#define F 0
#define T 1
#define I 2
#define X 3
private char text_chars[256] = {
F, F, F, F, F, F, F, T, T, T, T, F, T, T, F, F,
F, F, F, F, F, F, F, F, F, F, F, T, F, F, F, F,
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, T,
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, T,
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, T,
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, T,
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, T,
T, T, T, T, T, T, T, T, T, T, T, T, T, T, T, F,
X, X, X, X, X, T, X, X, X, X, X, X, X, X, X, X,
X, X, X, X, X, X, X, X, X, X, X, X, X, X, X, X,
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I,
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I,
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I,
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I,
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I,
I, I, I, I, I, I, I, I, I, I, I, I, I, I, I, I
};
private int
looks_ascii(const unsigned char *buf, size_t nbytes, unichar *ubuf,
size_t *ulen)
{
int i;
*ulen = 0;
for (i = 0; i < nbytes; i++) {
int t = text_chars[buf[i]];
if (t != T)
return 0;
ubuf[(*ulen)++] = buf[i];
}
return 1;
}
private int
looks_latin1(const unsigned char *buf, size_t nbytes, unichar *ubuf, size_t *ulen)
{
int i;
*ulen = 0;
for (i = 0; i < nbytes; i++) {
int t = text_chars[buf[i]];
if (t != T && t != I)
return 0;
ubuf[(*ulen)++] = buf[i];
}
return 1;
}
private int
looks_extended(const unsigned char *buf, size_t nbytes, unichar *ubuf,
size_t *ulen)
{
int i;
*ulen = 0;
for (i = 0; i < nbytes; i++) {
int t = text_chars[buf[i]];
if (t != T && t != I && t != X)
return 0;
ubuf[(*ulen)++] = buf[i];
}
return 1;
}
private int
looks_utf8(const unsigned char *buf, size_t nbytes, unichar *ubuf, size_t *ulen)
{
int i, n;
unichar c;
int gotone = 0;
*ulen = 0;
for (i = 0; i < nbytes; i++) {
if ((buf[i] & 0x80) == 0) {
if (text_chars[buf[i]] != T)
return 0;
ubuf[(*ulen)++] = buf[i];
} else if ((buf[i] & 0x40) == 0) {
return 0;
} else {
int following;
if ((buf[i] & 0x20) == 0) {
c = buf[i] & 0x1f;
following = 1;
} else if ((buf[i] & 0x10) == 0) {
c = buf[i] & 0x0f;
following = 2;
} else if ((buf[i] & 0x08) == 0) {
c = buf[i] & 0x07;
following = 3;
} else if ((buf[i] & 0x04) == 0) {
c = buf[i] & 0x03;
following = 4;
} else if ((buf[i] & 0x02) == 0) {
c = buf[i] & 0x01;
following = 5;
} else
return 0;
for (n = 0; n < following; n++) {
i++;
if (i >= nbytes)
goto done;
if ((buf[i] & 0x80) == 0 || (buf[i] & 0x40))
return 0;
c = (c << 6) + (buf[i] & 0x3f);
}
ubuf[(*ulen)++] = c;
gotone = 1;
}
}
done:
return gotone;
}
private int
looks_unicode(const unsigned char *buf, size_t nbytes, unichar *ubuf,
size_t *ulen)
{
int bigend;
int i;
if (nbytes < 2)
return 0;
if (buf[0] == 0xff && buf[1] == 0xfe)
bigend = 0;
else if (buf[0] == 0xfe && buf[1] == 0xff)
bigend = 1;
else
return 0;
*ulen = 0;
for (i = 2; i + 1 < nbytes; i += 2) {
if (bigend)
ubuf[(*ulen)++] = buf[i + 1] + 256 * buf[i];
else
ubuf[(*ulen)++] = buf[i] + 256 * buf[i + 1];
if (ubuf[*ulen - 1] == 0xfffe)
return 0;
if (ubuf[*ulen - 1] < 128 &&
text_chars[(size_t)ubuf[*ulen - 1]] != T)
return 0;
}
return 1 + bigend;
}
#undef F
#undef T
#undef I
#undef X
private unsigned char ebcdic_to_ascii[] = {
0, 1, 2, 3, 156, 9, 134, 127, 151, 141, 142, 11, 12, 13, 14, 15,
16, 17, 18, 19, 157, 133, 8, 135, 24, 25, 146, 143, 28, 29, 30, 31,
128, 129, 130, 131, 132, 10, 23, 27, 136, 137, 138, 139, 140, 5, 6, 7,
144, 145, 22, 147, 148, 149, 150, 4, 152, 153, 154, 155, 20, 21, 158, 26,
' ', 160, 161, 162, 163, 164, 165, 166, 167, 168, 213, '.', '<', '(', '+', '|',
'&', 169, 170, 171, 172, 173, 174, 175, 176, 177, '!', '$', '*', ')', ';', '~',
'-', '/', 178, 179, 180, 181, 182, 183, 184, 185, 203, ',', '%', '_', '>', '?',
186, 187, 188, 189, 190, 191, 192, 193, 194, '`', ':', '#', '@', '\'','=', '"',
195, 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 196, 197, 198, 199, 200, 201,
202, 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', '^', 204, 205, 206, 207, 208,
209, 229, 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 210, 211, 212, '[', 214, 215,
216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, ']', 230, 231,
'{', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 232, 233, 234, 235, 236, 237,
'}', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 238, 239, 240, 241, 242, 243,
'\\',159, 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 244, 245, 246, 247, 248, 249,
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 250, 251, 252, 253, 254, 255
};
#ifdef notdef
private unsigned char ebcdic_1047_to_8859[] = {
0x00,0x01,0x02,0x03,0x9C,0x09,0x86,0x7F,0x97,0x8D,0x8E,0x0B,0x0C,0x0D,0x0E,0x0F,
0x10,0x11,0x12,0x13,0x9D,0x0A,0x08,0x87,0x18,0x19,0x92,0x8F,0x1C,0x1D,0x1E,0x1F,
0x80,0x81,0x82,0x83,0x84,0x85,0x17,0x1B,0x88,0x89,0x8A,0x8B,0x8C,0x05,0x06,0x07,
0x90,0x91,0x16,0x93,0x94,0x95,0x96,0x04,0x98,0x99,0x9A,0x9B,0x14,0x15,0x9E,0x1A,
0x20,0xA0,0xE2,0xE4,0xE0,0xE1,0xE3,0xE5,0xE7,0xF1,0xA2,0x2E,0x3C,0x28,0x2B,0x7C,
0x26,0xE9,0xEA,0xEB,0xE8,0xED,0xEE,0xEF,0xEC,0xDF,0x21,0x24,0x2A,0x29,0x3B,0x5E,
0x2D,0x2F,0xC2,0xC4,0xC0,0xC1,0xC3,0xC5,0xC7,0xD1,0xA6,0x2C,0x25,0x5F,0x3E,0x3F,
0xF8,0xC9,0xCA,0xCB,0xC8,0xCD,0xCE,0xCF,0xCC,0x60,0x3A,0x23,0x40,0x27,0x3D,0x22,
0xD8,0x61,0x62,0x63,0x64,0x65,0x66,0x67,0x68,0x69,0xAB,0xBB,0xF0,0xFD,0xFE,0xB1,
0xB0,0x6A,0x6B,0x6C,0x6D,0x6E,0x6F,0x70,0x71,0x72,0xAA,0xBA,0xE6,0xB8,0xC6,0xA4,
0xB5,0x7E,0x73,0x74,0x75,0x76,0x77,0x78,0x79,0x7A,0xA1,0xBF,0xD0,0x5B,0xDE,0xAE,
0xAC,0xA3,0xA5,0xB7,0xA9,0xA7,0xB6,0xBC,0xBD,0xBE,0xDD,0xA8,0xAF,0x5D,0xB4,0xD7,
0x7B,0x41,0x42,0x43,0x44,0x45,0x46,0x47,0x48,0x49,0xAD,0xF4,0xF6,0xF2,0xF3,0xF5,
0x7D,0x4A,0x4B,0x4C,0x4D,0x4E,0x4F,0x50,0x51,0x52,0xB9,0xFB,0xFC,0xF9,0xFA,0xFF,
0x5C,0xF7,0x53,0x54,0x55,0x56,0x57,0x58,0x59,0x5A,0xB2,0xD4,0xD6,0xD2,0xD3,0xD5,
0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37,0x38,0x39,0xB3,0xDB,0xDC,0xD9,0xDA,0x9F
};
#endif
private void
from_ebcdic(const unsigned char *buf, size_t nbytes, unsigned char *out)
{
int i;
for (i = 0; i < nbytes; i++) {
out[i] = ebcdic_to_ascii[buf[i]];
}
}