![[BACK]](/icons/cvsweb/back.gif){kind=icon}
Return to ascmagic.c CVS log ![[TXT]](/icons/cvsweb/text.gif){kind=icon}
![[DIR]](/icons/cvsweb/dir.gif){kind=icon}
Up to [ELWIX - Embedded LightWeight unIX -] / embedaddon / php / ext / fileinfo / libmagic|
Return to ascmagic.c CVS log | Up to [ELWIX - Embedded LightWeight unIX -] / embedaddon / php / ext / fileinfo / libmagic |
1.1 misho 1: /*
2: * Copyright (c) Ian F. Darwin 1986-1995.
3: * Software written by Ian F. Darwin and others;
4: * maintained 1995-present by Christos Zoulas and others.
5: *
6: * Redistribution and use in source and binary forms, with or without
7: * modification, are permitted provided that the following conditions
8: * are met:
9: * 1. Redistributions of source code must retain the above copyright
10: * notice immediately at the beginning of the file, without modification,
11: * this list of conditions, and the following disclaimer.
12: * 2. Redistributions in binary form must reproduce the above copyright
13: * notice, this list of conditions and the following disclaimer in the
14: * documentation and/or other materials provided with the distribution.
15: *
16: * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
17: * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18: * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19: * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR
20: * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
21: * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
22: * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
23: * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
24: * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
25: * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
26: * SUCH DAMAGE.
27: */
28: /*
1.1.1.2 ! misho 29: * ASCII magic -- try to detect text encoding.
1.1 misho 30: *
31: * Extensively modified by Eric Fischer <enf@pobox.com> in July, 2000,
32: * to handle character codes other than ASCII on a unified basis.
33: */
34:
35: #include "file.h"
36:
37: #ifndef lint
1.1.1.2 ! misho 38: FILE_RCSID("@(#)$File: ascmagic.c,v 1.84 2011/12/08 12:38:24 rrt Exp $")
1.1 misho 39: #endif /* lint */
40:
41: #include "magic.h"
42: #include <string.h>
43: #include <memory.h>
44: #include <ctype.h>
45: #include <stdlib.h>
46: #ifdef HAVE_UNISTD_H
47: #include <unistd.h>
48: #endif
49:
50: #define MAXLINELEN 300 /* longest sane line length */
51: #define ISSPC(x) ((x) == ' ' || (x) == '\t' || (x) == '\r' || (x) == '\n' \
52: || (x) == 0x85 || (x) == '\f')
53:
54: private unsigned char *encode_utf8(unsigned char *, size_t, unichar *, size_t);
55: private size_t trim_nuls(const unsigned char *, size_t);
56:
57: /*
58: * Undo the NUL-termination kindly provided by process()
59: * but leave at least one byte to look at
60: */
61: private size_t
62: trim_nuls(const unsigned char *buf, size_t nbytes)
63: {
64: while (nbytes > 1 && buf[nbytes - 1] == '\0')
65: nbytes--;
66:
67: return nbytes;
68: }
69:
70: protected int
1.1.1.2 ! misho 71: file_ascmagic(struct magic_set *ms, const unsigned char *buf, size_t nbytes,
! 72: int text)
1.1 misho 73: {
74: unichar *ubuf = NULL;
75: size_t ulen;
76: int rv = 1;
77:
78: const char *code = NULL;
79: const char *code_mime = NULL;
80: const char *type = NULL;
81:
82: if (ms->flags & MAGIC_APPLE)
83: return 0;
84:
85: nbytes = trim_nuls(buf, nbytes);
86:
87: /* If file doesn't look like any sort of text, give up. */
88: if (file_encoding(ms, buf, nbytes, &ubuf, &ulen, &code, &code_mime,
1.1.1.2 ! misho 89: &type) == 0)
1.1 misho 90: rv = 0;
1.1.1.2 ! misho 91: else
! 92: rv = file_ascmagic_with_encoding(ms, buf, nbytes, ubuf, ulen, code,
! 93: type, text);
1.1 misho 94:
1.1.1.2 ! misho 95: free(ubuf);
1.1 misho 96:
97: return rv;
98: }
99:
100: protected int
101: file_ascmagic_with_encoding(struct magic_set *ms, const unsigned char *buf,
102: size_t nbytes, unichar *ubuf, size_t ulen, const char *code,
1.1.1.2 ! misho 103: const char *type, int text)
1.1 misho 104: {
105: unsigned char *utf8_buf = NULL, *utf8_end;
106: size_t mlen, i;
107: int rv = -1;
108: int mime = ms->flags & MAGIC_MIME;
109:
110: const char *subtype = NULL;
111: const char *subtype_mime = NULL;
112:
113: int has_escapes = 0;
114: int has_backspace = 0;
115: int seen_cr = 0;
116:
117: int n_crlf = 0;
118: int n_lf = 0;
119: int n_cr = 0;
120: int n_nel = 0;
1.1.1.2 ! misho 121: int executable = 0;
1.1 misho 122:
123: size_t last_line_end = (size_t)-1;
124: int has_long_lines = 0;
125:
126: if (ms->flags & MAGIC_APPLE)
127: return 0;
128:
129: nbytes = trim_nuls(buf, nbytes);
130:
131: /* If we have fewer than 2 bytes, give up. */
132: if (nbytes <= 1) {
133: rv = 0;
134: goto done;
135: }
136:
1.1.1.2 ! misho 137: if ((ms->flags & MAGIC_NO_CHECK_SOFT) == 0) {
! 138: /* Convert ubuf to UTF-8 and try text soft magic */
! 139: /* malloc size is a conservative overestimate; could be
! 140: improved, or at least realloced after conversion. */
! 141: mlen = ulen * 6;
! 142: utf8_buf = emalloc(mlen);
1.1 misho 143:
1.1.1.2 ! misho 144: if ((utf8_end = encode_utf8(utf8_buf, mlen, ubuf, ulen))
! 145: == NULL)
! 146: goto done;
! 147: if ((rv = file_softmagic(ms, utf8_buf,
! 148: (size_t)(utf8_end - utf8_buf), TEXTTEST, text)) == 0)
! 149: rv = -1;
1.1 misho 150: }
151:
152: /* Now try to discover other details about the file. */
153: for (i = 0; i < ulen; i++) {
154: if (ubuf[i] == '\n') {
155: if (seen_cr)
156: n_crlf++;
157: else
158: n_lf++;
159: last_line_end = i;
160: } else if (seen_cr)
161: n_cr++;
162:
163: seen_cr = (ubuf[i] == '\r');
164: if (seen_cr)
165: last_line_end = i;
166:
167: if (ubuf[i] == 0x85) { /* X3.64/ECMA-43 "next line" character */
168: n_nel++;
169: last_line_end = i;
170: }
171:
172: /* If this line is _longer_ than MAXLINELEN, remember it. */
173: if (i > last_line_end + MAXLINELEN)
174: has_long_lines = 1;
175:
176: if (ubuf[i] == '\033')
177: has_escapes = 1;
178: if (ubuf[i] == '\b')
179: has_backspace = 1;
180: }
181:
182: /* Beware, if the data has been truncated, the final CR could have
183: been followed by a LF. If we have HOWMANY bytes, it indicates
184: that the data might have been truncated, probably even before
185: this function was called. */
186: if (seen_cr && nbytes < HOWMANY)
187: n_cr++;
188:
189: if (strcmp(type, "binary") == 0) {
190: rv = 0;
191: goto done;
192: }
193: if (mime) {
1.1.1.2 ! misho 194: if (!file_printedlen(ms) && (mime & MAGIC_MIME_TYPE) != 0) {
1.1 misho 195: if (subtype_mime) {
196: if (file_printf(ms, "%s", subtype_mime) == -1)
197: goto done;
198: } else {
199: if (file_printf(ms, "text/plain") == -1)
200: goto done;
201: }
202: }
203: } else {
1.1.1.2 ! misho 204: if (file_printedlen(ms)) {
! 205: switch (file_replace(ms, " text$", ", ")) {
! 206: case 0:
! 207: switch (file_replace(ms, " text executable$",
! 208: ", ")) {
! 209: case 0:
! 210: if (file_printf(ms, ", ") == -1)
! 211: goto done;
! 212: case -1:
! 213: goto done;
! 214: default:
! 215: executable = 1;
! 216: break;
! 217: }
! 218: break;
! 219: case -1:
! 220: goto done;
! 221: default:
! 222: break;
! 223: }
! 224: }
! 225:
1.1 misho 226: if (file_printf(ms, "%s", code) == -1)
227: goto done;
228:
229: if (subtype) {
230: if (file_printf(ms, " %s", subtype) == -1)
231: goto done;
232: }
233:
234: if (file_printf(ms, " %s", type) == -1)
235: goto done;
236:
1.1.1.2 ! misho 237: if (executable)
! 238: if (file_printf(ms, " executable") == -1)
! 239: goto done;
! 240:
1.1 misho 241: if (has_long_lines)
242: if (file_printf(ms, ", with very long lines") == -1)
243: goto done;
244:
245: /*
246: * Only report line terminators if we find one other than LF,
247: * or if we find none at all.
248: */
249: if ((n_crlf == 0 && n_cr == 0 && n_nel == 0 && n_lf == 0) ||
250: (n_crlf != 0 || n_cr != 0 || n_nel != 0)) {
251: if (file_printf(ms, ", with") == -1)
252: goto done;
253:
254: if (n_crlf == 0 && n_cr == 0 && n_nel == 0 && n_lf == 0) {
255: if (file_printf(ms, " no") == -1)
256: goto done;
257: } else {
258: if (n_crlf) {
259: if (file_printf(ms, " CRLF") == -1)
260: goto done;
261: if (n_cr || n_lf || n_nel)
262: if (file_printf(ms, ",") == -1)
263: goto done;
264: }
265: if (n_cr) {
266: if (file_printf(ms, " CR") == -1)
267: goto done;
268: if (n_lf || n_nel)
269: if (file_printf(ms, ",") == -1)
270: goto done;
271: }
272: if (n_lf) {
273: if (file_printf(ms, " LF") == -1)
274: goto done;
275: if (n_nel)
276: if (file_printf(ms, ",") == -1)
277: goto done;
278: }
279: if (n_nel)
280: if (file_printf(ms, " NEL") == -1)
281: goto done;
282: }
283:
284: if (file_printf(ms, " line terminators") == -1)
285: goto done;
286: }
287:
288: if (has_escapes)
289: if (file_printf(ms, ", with escape sequences") == -1)
290: goto done;
291: if (has_backspace)
292: if (file_printf(ms, ", with overstriking") == -1)
293: goto done;
294: }
295: rv = 1;
296: done:
297: if (utf8_buf)
298: efree(utf8_buf);
299:
300: return rv;
301: }
302:
303: /*
304: * Encode Unicode string as UTF-8, returning pointer to character
305: * after end of string, or NULL if an invalid character is found.
306: */
307: private unsigned char *
308: encode_utf8(unsigned char *buf, size_t len, unichar *ubuf, size_t ulen)
309: {
310: size_t i;
311: unsigned char *end = buf + len;
312:
313: for (i = 0; i < ulen; i++) {
314: if (ubuf[i] <= 0x7f) {
315: if (end - buf < 1)
316: return NULL;
317: *buf++ = (unsigned char)ubuf[i];
318: } else if (ubuf[i] <= 0x7ff) {
319: if (end - buf < 2)
320: return NULL;
321: *buf++ = (unsigned char)((ubuf[i] >> 6) + 0xc0);
322: *buf++ = (unsigned char)((ubuf[i] & 0x3f) + 0x80);
323: } else if (ubuf[i] <= 0xffff) {
324: if (end - buf < 3)
325: return NULL;
326: *buf++ = (unsigned char)((ubuf[i] >> 12) + 0xe0);
327: *buf++ = (unsigned char)(((ubuf[i] >> 6) & 0x3f) + 0x80);
328: *buf++ = (unsigned char)((ubuf[i] & 0x3f) + 0x80);
329: } else if (ubuf[i] <= 0x1fffff) {
330: if (end - buf < 4)
331: return NULL;
332: *buf++ = (unsigned char)((ubuf[i] >> 18) + 0xf0);
333: *buf++ = (unsigned char)(((ubuf[i] >> 12) & 0x3f) + 0x80);
334: *buf++ = (unsigned char)(((ubuf[i] >> 6) & 0x3f) + 0x80);
335: *buf++ = (unsigned char)((ubuf[i] & 0x3f) + 0x80);
336: } else if (ubuf[i] <= 0x3ffffff) {
337: if (end - buf < 5)
338: return NULL;
339: *buf++ = (unsigned char)((ubuf[i] >> 24) + 0xf8);
340: *buf++ = (unsigned char)(((ubuf[i] >> 18) & 0x3f) + 0x80);
341: *buf++ = (unsigned char)(((ubuf[i] >> 12) & 0x3f) + 0x80);
342: *buf++ = (unsigned char)(((ubuf[i] >> 6) & 0x3f) + 0x80);
343: *buf++ = (unsigned char)((ubuf[i] & 0x3f) + 0x80);
344: } else if (ubuf[i] <= 0x7fffffff) {
345: if (end - buf < 6)
346: return NULL;
347: *buf++ = (unsigned char)((ubuf[i] >> 30) + 0xfc);
348: *buf++ = (unsigned char)(((ubuf[i] >> 24) & 0x3f) + 0x80);
349: *buf++ = (unsigned char)(((ubuf[i] >> 18) & 0x3f) + 0x80);
350: *buf++ = (unsigned char)(((ubuf[i] >> 12) & 0x3f) + 0x80);
351: *buf++ = (unsigned char)(((ubuf[i] >> 6) & 0x3f) + 0x80);
352: *buf++ = (unsigned char)((ubuf[i] & 0x3f) + 0x80);
353: } else /* Invalid character */
354: return NULL;
355: }
356:
357: return buf;
358: }