Commit | Line | Data |
---|---|---|
18b3351a MW |
1 | /* -*-c-*- |
2 | * | |
3 | * Common functions for hashing utilities | |
4 | * | |
5 | * (c) 2011 Straylight/Edgeware | |
6 | */ | |
7 | ||
8 | /*----- Licensing notice --------------------------------------------------* | |
9 | * | |
10 | * This file is part of Catacomb. | |
11 | * | |
12 | * Catacomb is free software; you can redistribute it and/or modify | |
13 | * it under the terms of the GNU Library General Public License as | |
14 | * published by the Free Software Foundation; either version 2 of the | |
15 | * License, or (at your option) any later version. | |
16 | * | |
17 | * Catacomb is distributed in the hope that it will be useful, | |
18 | * but WITHOUT ANY WARRANTY; without even the implied warranty of | |
19 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
20 | * GNU Library General Public License for more details. | |
21 | * | |
22 | * You should have received a copy of the GNU Library General Public | |
23 | * License along with Catacomb; if not, write to the Free | |
24 | * Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, | |
25 | * MA 02111-1307, USA. | |
26 | */ | |
27 | ||
28 | /*----- Header files ------------------------------------------------------*/ | |
29 | ||
30 | #define _FILE_OFFSET_BITS 64 | |
31 | ||
32 | #include "config.h" | |
33 | ||
34 | #include <ctype.h> | |
35 | #include <stdio.h> | |
36 | #include <stdlib.h> | |
37 | #include <string.h> | |
38 | ||
39 | #include <mLib/dstr.h> | |
f377eee1 | 40 | #include <mLib/str.h> |
18b3351a MW |
41 | |
42 | #include <mLib/hex.h> | |
43 | #include <mLib/base32.h> | |
44 | #include <mLib/base64.h> | |
45 | ||
46 | #include "ghash.h" | |
47 | #include "cc.h" | |
48 | ||
49 | /*----- Encoding and decoding ---------------------------------------------*/ | |
50 | ||
51 | /* --- Hex encoding --- */ | |
52 | ||
53 | static void puthex(const octet *buf, size_t sz, FILE *fp) | |
54 | { | |
55 | while (sz) { | |
56 | fprintf(fp, "%02x", *buf++); | |
57 | sz--; | |
58 | } | |
59 | } | |
60 | ||
61 | static size_t gethex(const char *p, octet *q, size_t sz, char **pp) | |
62 | { | |
63 | size_t i = 0; | |
64 | while (sz > 0 && | |
65 | isxdigit((unsigned char)p[0]) && | |
66 | isxdigit((unsigned char)p[1])) { | |
67 | char buf[3]; | |
68 | buf[0] = p[0]; | |
69 | buf[1] = p[1]; | |
70 | buf[2] = 0; | |
71 | *q++ = strtoul(buf, 0, 16); | |
72 | sz--; | |
73 | p += 2; | |
74 | i++; | |
75 | } | |
76 | if (pp) | |
77 | *pp = (char *)p; | |
78 | return (i); | |
79 | } | |
80 | ||
81 | /* --- Base64 encoding --- */ | |
82 | ||
83 | static void putbase64(const octet *buf, size_t sz, FILE *fp) | |
84 | { | |
85 | base64_ctx b; | |
86 | dstr d = DSTR_INIT; | |
87 | ||
88 | base64_init(&b); | |
89 | b.indent = ""; | |
90 | b.maxline = 0; | |
91 | base64_encode(&b, buf, sz, &d); | |
92 | base64_encode(&b, 0, 0, &d); | |
93 | dstr_write(&d, fp); | |
94 | dstr_destroy(&d); | |
95 | } | |
96 | ||
97 | static size_t getbase64(const char *p, octet *q, size_t sz, char **pp) | |
98 | { | |
99 | base64_ctx b; | |
100 | dstr d = DSTR_INIT; | |
101 | size_t n = strlen(p); | |
102 | ||
103 | base64_init(&b); | |
104 | base64_decode(&b, p, n, &d); | |
105 | if (pp) *pp = (/*unconst*/ char *)p + n; | |
106 | base64_decode(&b, 0, 0, &d); | |
107 | assert(d.len <= sz); | |
108 | memcpy(q, d.buf, sz); | |
109 | n = d.len; | |
110 | dstr_destroy(&d); | |
111 | return (n); | |
112 | } | |
113 | ||
114 | /* --- Base32 encoding --- */ | |
115 | ||
116 | static void putbase32(const octet *buf, size_t sz, FILE *fp) | |
117 | { | |
118 | base32_ctx b; | |
119 | dstr d = DSTR_INIT; | |
120 | ||
121 | base32_init(&b); | |
122 | b.indent = ""; | |
123 | b.maxline = 0; | |
124 | base32_encode(&b, buf, sz, &d); | |
125 | base32_encode(&b, 0, 0, &d); | |
126 | dstr_write(&d, fp); | |
127 | dstr_destroy(&d); | |
128 | } | |
129 | ||
130 | static size_t getbase32(const char *p, octet *q, size_t sz, char **pp) | |
131 | { | |
132 | base32_ctx b; | |
133 | dstr d = DSTR_INIT; | |
134 | size_t n = strlen(p); | |
135 | ||
136 | base32_init(&b); | |
137 | base32_decode(&b, p, n, &d); | |
138 | if (pp) *pp = (/*unconst*/ char *)p + n; | |
139 | base32_decode(&b, 0, 0, &d); | |
140 | assert(d.len <= sz); | |
141 | memcpy(q, d.buf, sz); | |
142 | n = d.len; | |
143 | dstr_destroy(&d); | |
144 | return (n); | |
145 | } | |
146 | ||
147 | /* --- Table --- */ | |
148 | ||
149 | const encodeops encodingtab[] = { | |
150 | #define TAB(tag, name) { #name, put##name, get##name }, | |
151 | ENCODINGS(TAB) | |
152 | #undef TAB | |
153 | { 0, 0, 0 } | |
154 | }; | |
155 | ||
156 | const encodeops *getencoding(const char *ename) | |
157 | { | |
158 | const encodeops *e; | |
159 | ||
160 | for (e = encodingtab; e->name; e++) { | |
161 | if (strcmp(ename, e->name) == 0) | |
162 | return (e); | |
163 | } | |
164 | return (0); | |
165 | } | |
166 | ||
167 | /*----- File hashing ------------------------------------------------------*/ | |
168 | ||
f377eee1 MW |
169 | /* --- @gethash@ --- * |
170 | * | |
171 | * Arguments: @const char *name@ = pointer to name string | |
172 | * | |
173 | * Returns: Pointer to appropriate hash class. | |
174 | * | |
175 | * Use: Chooses a hash function by name. | |
176 | */ | |
177 | ||
178 | const gchash *gethash(const char *name) | |
179 | { | |
180 | const gchash *const *g, *gg = 0; | |
181 | size_t sz = strlen(name); | |
182 | for (g = ghashtab; *g; g++) { | |
183 | if (strncmp(name, (*g)->name, sz) == 0) { | |
184 | if ((*g)->name[sz] == 0) { | |
185 | gg = *g; | |
186 | break; | |
187 | } else if (gg) | |
188 | return (0); | |
189 | else | |
190 | gg = *g; | |
191 | } | |
192 | } | |
193 | return (gg); | |
194 | } | |
195 | ||
18b3351a MW |
196 | /* --- @fhash@ --- * |
197 | * | |
198 | * Arguments: @const gchash *gch@ = pointer to hash function to use | |
199 | * @unsigned f@ = flags to set | |
200 | * @const char *file@ = file name to be hashed (null for stdin) | |
201 | * @void *buf@ = pointer to hash output buffer | |
202 | * | |
203 | * Returns: Zero if it worked, nonzero on error. | |
204 | * | |
205 | * Use: Hashes a file. | |
206 | */ | |
207 | ||
208 | int fhash(const gchash *gch, unsigned f, const char *file, void *buf) | |
209 | { | |
210 | FILE *fp; | |
211 | char fbuf[1024 * 128]; | |
212 | size_t sz; | |
213 | ghash *h; | |
214 | int rc = 0; | |
215 | fprogress ff; | |
216 | ||
217 | if (!file || strcmp(file, "-") == 0) | |
218 | fp = stdin; | |
219 | else if ((fp = fopen(file, f & FHF_BINARY ? "rb" : "r")) == 0) | |
220 | return (-1); | |
221 | ||
222 | if (f & FHF_PROGRESS) { | |
223 | if (fprogress_init(&ff, file, fp)) return (-1); | |
224 | } | |
225 | ||
226 | h = GH_INIT(gch); | |
227 | while ((sz = fread(fbuf, 1, sizeof(fbuf), fp)) > 0) { | |
228 | GH_HASH(h, fbuf, sz); | |
229 | if (f & FHF_PROGRESS) fprogress_update(&ff, sz); | |
230 | } | |
231 | if (ferror(fp)) rc = -1; | |
232 | if (fp != stdin) fclose(fp); | |
233 | if (f & FHF_PROGRESS) fprogress_done(&ff); | |
234 | GH_DONE(h, buf); | |
235 | GH_DESTROY(h); | |
236 | return (rc); | |
237 | } | |
238 | ||
f377eee1 MW |
239 | /* --- @hfparse@ --- * |
240 | * | |
241 | * Arguments: @hfpctx *hfp@ = pointer to the context structure | |
242 | * | |
243 | * Returns: A code indicating what happened. | |
244 | * | |
245 | * Use: Parses a line from the input file. | |
246 | */ | |
247 | ||
248 | int hfparse(hfpctx *hfp) | |
249 | { | |
250 | char *p, *q; | |
251 | const gchash *gch; | |
252 | const encodeops *ee; | |
253 | dstr *d = hfp->dline; | |
254 | size_t hsz; | |
255 | ||
256 | /* --- Fetch the input line and get ready to parse --- */ | |
257 | ||
258 | DRESET(d); | |
259 | if (dstr_putline(d, hfp->fp) == EOF) return (HF_EOF); | |
260 | p = d->buf; | |
261 | ||
262 | /* --- Parse magic comments --- */ | |
263 | ||
264 | if (*p == '#') { | |
265 | p++; | |
266 | if ((q = str_getword(&p)) == 0) return (HF_BAD); | |
267 | if (strcmp(q, "hash") == 0) { | |
268 | if ((q = str_getword(&p)) == 0) return (HF_BAD); | |
269 | if ((gch = gethash(q)) == 0) return (HF_BAD); | |
270 | hfp->gch = gch; | |
271 | return (HF_HASH); | |
272 | } else if (strcmp(q, "encoding") == 0) { | |
273 | if ((q = str_getword(&p)) == 0) return (HF_BAD); | |
274 | if ((ee = getencoding(q)) == 0) return (HF_BAD); | |
275 | hfp->ee = ee; | |
276 | return (HF_ENC); | |
277 | } else if (strcmp(q, "escape") == 0) { | |
278 | hfp->f |= HFF_ESCAPE; | |
279 | return (HF_ESC); | |
280 | } | |
281 | return (HF_BAD); | |
282 | } | |
283 | ||
284 | /* --- Otherwise it's a file line --- */ | |
285 | ||
286 | q = p; | |
287 | while (*p && *p != ' ') p++; | |
288 | if (!*p) return (HF_BAD); | |
289 | *p++ = 0; | |
290 | hsz = hfp->gch->hashsz; | |
291 | if (hfp->ee->get(q, hfp->hbuf, hsz, 0) < hsz) return (HF_BAD); | |
292 | switch (*p) { | |
293 | case '*': hfp->f |= FHF_BINARY; break; | |
294 | case ' ': hfp->f &= ~FHF_BINARY; break; | |
295 | default: return (HF_BAD); | |
296 | } | |
297 | p++; | |
298 | ||
299 | DRESET(hfp->dfile); | |
300 | if (hfp->f & HFF_ESCAPE) | |
301 | getstring(&p, hfp->dfile, GSF_STRING); | |
302 | else { | |
303 | dstr_putm(hfp->dfile, p, d->len - (p - d->buf)); | |
304 | dstr_putz(hfp->dfile); | |
305 | } | |
306 | ||
307 | return (HF_FILE); | |
308 | } | |
309 | ||
18b3351a MW |
310 | /*----- String I/O --------------------------------------------------------*/ |
311 | ||
312 | /* --- @getstring@ --- * | |
313 | * | |
314 | * Arguments: @void *in@ = input source | |
315 | * @dstr *d@ = destination string | |
316 | * @unsigned f@ = input flags | |
317 | * | |
318 | * Returns: Zero if OK, nonzero on end-of-file. | |
319 | * | |
320 | * Use: Reads a filename (or something similar) from a stream. | |
321 | */ | |
322 | ||
323 | static int nextch_file(void *in) | |
324 | { FILE *fp = in; return (getc(fp)); } | |
325 | ||
326 | static int nextch_string(void *in) | |
327 | { const unsigned char **p = in; return (*(*p)++); } | |
328 | ||
329 | int getstring(void *in, dstr *d, unsigned f) | |
330 | { | |
331 | int ch; | |
332 | int eofch = (f & GSF_STRING) ? 0 : EOF; | |
333 | int (*nextch)(void *) = (f & GSF_STRING) ? nextch_string : nextch_file; | |
334 | int q = 0; | |
335 | ||
336 | /* --- Raw: just read exactly what's written up to a null byte --- */ | |
337 | ||
338 | if (f & GSF_RAW) { | |
339 | if ((ch = nextch(in)) == eofch) | |
340 | return (EOF); | |
341 | for (;;) { | |
342 | if (!ch) | |
343 | break; | |
344 | DPUTC(d, ch); | |
345 | if ((ch = nextch(in)) == eofch) | |
346 | break; | |
347 | } | |
348 | DPUTZ(d); | |
349 | return (0); | |
350 | } | |
351 | ||
352 | /* --- Skip as far as whitespace --- * | |
353 | * | |
354 | * Also skip past comments. | |
355 | */ | |
356 | ||
357 | again: | |
358 | ch = nextch(in); | |
359 | while (isspace(ch)) | |
360 | ch = nextch(in); | |
361 | if (ch == '#') { | |
362 | do ch = nextch(in); while (ch != '\n' && ch != eofch); | |
363 | goto again; | |
364 | } | |
365 | if (ch == eofch) | |
366 | return (EOF); | |
367 | ||
368 | /* --- If the character is a quote then read a quoted string --- */ | |
369 | ||
370 | switch (ch) { | |
371 | case '`': | |
372 | ch = '\''; | |
373 | case '\'': | |
374 | case '\"': | |
375 | q = ch; | |
376 | ch = nextch(in); | |
377 | break; | |
378 | } | |
379 | ||
380 | /* --- Now read all sorts of interesting things --- */ | |
381 | ||
382 | for (;;) { | |
383 | ||
384 | /* --- Handle an escaped thing --- */ | |
385 | ||
386 | if (ch == '\\') { | |
387 | ch = nextch(in); | |
388 | if (ch == eofch) | |
389 | break; | |
390 | switch (ch) { | |
391 | case 'a': ch = '\a'; break; | |
392 | case 'b': ch = '\b'; break; | |
393 | case 'f': ch = '\f'; break; | |
394 | case 'n': ch = '\n'; break; | |
395 | case 'r': ch = '\r'; break; | |
396 | case 't': ch = '\t'; break; | |
397 | case 'v': ch = '\v'; break; | |
398 | } | |
399 | DPUTC(d, ch); | |
400 | ch = nextch(in); | |
401 | continue; | |
402 | } | |
403 | ||
404 | /* --- If it's a quote or some other end marker then stop --- */ | |
405 | ||
406 | if (ch == q) | |
407 | break; | |
408 | if (!q && isspace(ch)) | |
409 | break; | |
410 | ||
411 | /* --- Otherwise contribute and continue --- */ | |
412 | ||
413 | DPUTC(d, ch); | |
414 | if ((ch = nextch(in)) == eofch) | |
415 | break; | |
416 | } | |
417 | ||
418 | /* --- Done --- */ | |
419 | ||
420 | DPUTZ(d); | |
421 | return (0); | |
422 | } | |
423 | ||
424 | /* --- @putstring@ --- * | |
425 | * | |
426 | * Arguments: @FILE *fp@ = stream to write on | |
427 | * @const char *p@ = pointer to text | |
428 | * @unsigned f@ = output flags | |
429 | * | |
430 | * Returns: --- | |
431 | * | |
432 | * Use: Emits a string to a stream. | |
433 | */ | |
434 | ||
435 | void putstring(FILE *fp, const char *p, unsigned f) | |
436 | { | |
437 | size_t sz = strlen(p); | |
438 | unsigned qq; | |
439 | const char *q; | |
440 | ||
441 | /* --- Just write the string null terminated if raw --- */ | |
442 | ||
443 | if (f & GSF_RAW) { | |
444 | fwrite(p, 1, sz + 1, fp); | |
445 | return; | |
446 | } | |
447 | ||
448 | /* --- Check for any dodgy characters --- */ | |
449 | ||
450 | qq = 0; | |
451 | for (q = p; *q; q++) { | |
452 | if (isspace((unsigned char)*q)) { | |
453 | qq = '\"'; | |
454 | break; | |
455 | } | |
456 | } | |
457 | ||
458 | if (qq) | |
459 | putc(qq, fp); | |
460 | ||
461 | /* --- Emit the string --- */ | |
462 | ||
463 | for (q = p; *q; q++) { | |
464 | switch (*q) { | |
465 | case '\a': fputc('\\', fp); fputc('a', fp); break; | |
466 | case '\b': fputc('\\', fp); fputc('b', fp); break; | |
467 | case '\f': fputc('\\', fp); fputc('f', fp); break; | |
468 | case '\n': fputc('\\', fp); fputc('n', fp); break; | |
469 | case '\r': fputc('\\', fp); fputc('r', fp); break; | |
470 | case '\t': fputc('\\', fp); fputc('t', fp); break; | |
471 | case '\v': fputc('\\', fp); fputc('v', fp); break; | |
472 | case '`': fputc('\\', fp); fputc('`', fp); break; | |
473 | case '\'': fputc('\\', fp); fputc('\'', fp); break; | |
474 | case '\"': fputc('\\', fp); fputc('\"', fp); break; | |
475 | default: | |
476 | putc(*q, fp); | |
477 | break; | |
478 | } | |
479 | } | |
480 | ||
481 | /* --- Done --- */ | |
482 | ||
483 | if (qq) | |
484 | putc(qq, fp); | |
485 | } | |
486 | ||
487 | /*----- That's all, folks -------------------------------------------------*/ |