![[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
1.1.1.3 misho 38: FILE_RCSID("@(#)$File: ascmagic.c,v 1.85 2012/08/09 16:33:15 christos 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:
1.1.1.3 misho 137: if (ulen > 0 && (ms->flags & MAGIC_NO_CHECK_SOFT) == 0) {
1.1.1.2 misho 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;
1.1.1.3 misho 142: if ((utf8_buf = CAST(unsigned char *, emalloc(mlen))) == NULL) {
143: file_oomem(ms, mlen);
144: goto done;
145: }
1.1.1.2 misho 146: if ((utf8_end = encode_utf8(utf8_buf, mlen, ubuf, ulen))
147: == NULL)
148: goto done;
149: if ((rv = file_softmagic(ms, utf8_buf,
1.1.1.4 ! misho 150: (size_t)(utf8_end - utf8_buf), 0, TEXTTEST, text)) == 0)
1.1.1.2 misho 151: rv = -1;
1.1 misho 152: }
153:
154: /* Now try to discover other details about the file. */
155: for (i = 0; i < ulen; i++) {
156: if (ubuf[i] == '\n') {
157: if (seen_cr)
158: n_crlf++;
159: else
160: n_lf++;
161: last_line_end = i;
162: } else if (seen_cr)
163: n_cr++;
164:
165: seen_cr = (ubuf[i] == '\r');
166: if (seen_cr)
167: last_line_end = i;
168:
169: if (ubuf[i] == 0x85) { /* X3.64/ECMA-43 "next line" character */
170: n_nel++;
171: last_line_end = i;
172: }
173:
174: /* If this line is _longer_ than MAXLINELEN, remember it. */
175: if (i > last_line_end + MAXLINELEN)
176: has_long_lines = 1;
177:
178: if (ubuf[i] == '\033')
179: has_escapes = 1;
180: if (ubuf[i] == '\b')
181: has_backspace = 1;
182: }
183:
184: /* Beware, if the data has been truncated, the final CR could have
185: been followed by a LF. If we have HOWMANY bytes, it indicates
186: that the data might have been truncated, probably even before
187: this function was called. */
188: if (seen_cr && nbytes < HOWMANY)
189: n_cr++;
190:
191: if (strcmp(type, "binary") == 0) {
192: rv = 0;
193: goto done;
194: }
195: if (mime) {
1.1.1.2 misho 196: if (!file_printedlen(ms) && (mime & MAGIC_MIME_TYPE) != 0) {
1.1 misho 197: if (subtype_mime) {
198: if (file_printf(ms, "%s", subtype_mime) == -1)
199: goto done;
200: } else {
201: if (file_printf(ms, "text/plain") == -1)
202: goto done;
203: }
204: }
205: } else {
1.1.1.2 misho 206: if (file_printedlen(ms)) {
207: switch (file_replace(ms, " text$", ", ")) {
208: case 0:
209: switch (file_replace(ms, " text executable$",
210: ", ")) {
211: case 0:
212: if (file_printf(ms, ", ") == -1)
213: goto done;
1.1.1.3 misho 214: break;
1.1.1.2 misho 215: case -1:
216: goto done;
217: default:
218: executable = 1;
219: break;
220: }
221: break;
222: case -1:
223: goto done;
224: default:
225: break;
226: }
227: }
228:
1.1 misho 229: if (file_printf(ms, "%s", code) == -1)
230: goto done;
231:
232: if (subtype) {
233: if (file_printf(ms, " %s", subtype) == -1)
234: goto done;
235: }
236:
237: if (file_printf(ms, " %s", type) == -1)
238: goto done;
239:
1.1.1.2 misho 240: if (executable)
241: if (file_printf(ms, " executable") == -1)
242: goto done;
243:
1.1 misho 244: if (has_long_lines)
245: if (file_printf(ms, ", with very long lines") == -1)
246: goto done;
247:
248: /*
249: * Only report line terminators if we find one other than LF,
250: * or if we find none at all.
251: */
252: if ((n_crlf == 0 && n_cr == 0 && n_nel == 0 && n_lf == 0) ||
253: (n_crlf != 0 || n_cr != 0 || n_nel != 0)) {
254: if (file_printf(ms, ", with") == -1)
255: goto done;
256:
257: if (n_crlf == 0 && n_cr == 0 && n_nel == 0 && n_lf == 0) {
258: if (file_printf(ms, " no") == -1)
259: goto done;
260: } else {
261: if (n_crlf) {
262: if (file_printf(ms, " CRLF") == -1)
263: goto done;
264: if (n_cr || n_lf || n_nel)
265: if (file_printf(ms, ",") == -1)
266: goto done;
267: }
268: if (n_cr) {
269: if (file_printf(ms, " CR") == -1)
270: goto done;
271: if (n_lf || n_nel)
272: if (file_printf(ms, ",") == -1)
273: goto done;
274: }
275: if (n_lf) {
276: if (file_printf(ms, " LF") == -1)
277: goto done;
278: if (n_nel)
279: if (file_printf(ms, ",") == -1)
280: goto done;
281: }
282: if (n_nel)
283: if (file_printf(ms, " NEL") == -1)
284: goto done;
285: }
286:
287: if (file_printf(ms, " line terminators") == -1)
288: goto done;
289: }
290:
291: if (has_escapes)
292: if (file_printf(ms, ", with escape sequences") == -1)
293: goto done;
294: if (has_backspace)
295: if (file_printf(ms, ", with overstriking") == -1)
296: goto done;
297: }
298: rv = 1;
299: done:
300: if (utf8_buf)
301: efree(utf8_buf);
302:
303: return rv;
304: }
305:
306: /*
307: * Encode Unicode string as UTF-8, returning pointer to character
308: * after end of string, or NULL if an invalid character is found.
309: */
310: private unsigned char *
311: encode_utf8(unsigned char *buf, size_t len, unichar *ubuf, size_t ulen)
312: {
313: size_t i;
314: unsigned char *end = buf + len;
315:
316: for (i = 0; i < ulen; i++) {
317: if (ubuf[i] <= 0x7f) {
318: if (end - buf < 1)
319: return NULL;
320: *buf++ = (unsigned char)ubuf[i];
321: } else if (ubuf[i] <= 0x7ff) {
322: if (end - buf < 2)
323: return NULL;
324: *buf++ = (unsigned char)((ubuf[i] >> 6) + 0xc0);
325: *buf++ = (unsigned char)((ubuf[i] & 0x3f) + 0x80);
326: } else if (ubuf[i] <= 0xffff) {
327: if (end - buf < 3)
328: return NULL;
329: *buf++ = (unsigned char)((ubuf[i] >> 12) + 0xe0);
330: *buf++ = (unsigned char)(((ubuf[i] >> 6) & 0x3f) + 0x80);
331: *buf++ = (unsigned char)((ubuf[i] & 0x3f) + 0x80);
332: } else if (ubuf[i] <= 0x1fffff) {
333: if (end - buf < 4)
334: return NULL;
335: *buf++ = (unsigned char)((ubuf[i] >> 18) + 0xf0);
336: *buf++ = (unsigned char)(((ubuf[i] >> 12) & 0x3f) + 0x80);
337: *buf++ = (unsigned char)(((ubuf[i] >> 6) & 0x3f) + 0x80);
338: *buf++ = (unsigned char)((ubuf[i] & 0x3f) + 0x80);
339: } else if (ubuf[i] <= 0x3ffffff) {
340: if (end - buf < 5)
341: return NULL;
342: *buf++ = (unsigned char)((ubuf[i] >> 24) + 0xf8);
343: *buf++ = (unsigned char)(((ubuf[i] >> 18) & 0x3f) + 0x80);
344: *buf++ = (unsigned char)(((ubuf[i] >> 12) & 0x3f) + 0x80);
345: *buf++ = (unsigned char)(((ubuf[i] >> 6) & 0x3f) + 0x80);
346: *buf++ = (unsigned char)((ubuf[i] & 0x3f) + 0x80);
347: } else if (ubuf[i] <= 0x7fffffff) {
348: if (end - buf < 6)
349: return NULL;
350: *buf++ = (unsigned char)((ubuf[i] >> 30) + 0xfc);
351: *buf++ = (unsigned char)(((ubuf[i] >> 24) & 0x3f) + 0x80);
352: *buf++ = (unsigned char)(((ubuf[i] >> 18) & 0x3f) + 0x80);
353: *buf++ = (unsigned char)(((ubuf[i] >> 12) & 0x3f) + 0x80);
354: *buf++ = (unsigned char)(((ubuf[i] >> 6) & 0x3f) + 0x80);
355: *buf++ = (unsigned char)((ubuf[i] & 0x3f) + 0x80);
356: } else /* Invalid character */
357: return NULL;
358: }
359:
360: return buf;
361: }