git.distorted.org.uk Git - u/mdw/catacomb/blob - cc-hash.c

   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>
  40 #include <mLib/str.h>
  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
 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
 196 /* --- @fhash_init@ ---*
 197  *
 198  * Arguments:   @fhashstate *fh@ = pointer to fhash state to initialize
 199  *              @const gchash *gch@ = hash class to set
 200  *              @unsigned f@ initial flags to set
 201  *
 202  * Returns:     ---
 203  *
 204  * Use:         Initializes an @fhashstate@ structure.
 205  */
 206
 207 void fhash_init(fhashstate *fh, const gchash *gch, unsigned f)
 208   { fh->f = f; fh->gch = gch; }
 209
 210 /* --- @fhash_free@ --- *
 211  *
 212  * Arguments:   @fhashstate *fh@ = pointer to fhash state to free
 213  *
 214  * Returns:     ---
 215  *
 216  * Use:         Frees an fhash state.
 217  */
 218
 219 void fhash_free(fhashstate *fh) { return; }
 220
 221 /* --- @fhash@ --- *
 222  *
 223  * Arguments:   @fhashstate *fh@ = pointer to fhash state
 224  *              @const char *file@ = file name to be hashed (null for stdin)
 225  *              @void *buf@ = pointer to hash output buffer
 226  *
 227  * Returns:     Zero if it worked, nonzero on error.
 228  *
 229  * Use:         Hashes a file.
 230  */
 231
 232 int fhash(fhashstate *fh, const char *file, void *buf)
 233 {
 234   FILE *fp;
 235   char fbuf[1024 * 128];
 236   size_t sz;
 237   ghash *h;
 238   int rc = 0;
 239   fprogress ff;
 240
 241   if (!file || strcmp(file, "-") == 0)
 242     fp = stdin;
 243   else if ((fp = fopen(file, fh->f & FHF_BINARY ? "rb" : "r")) == 0)
 244     return (-1);
 245
 246   if (fh->f & FHF_PROGRESS) {
 247     if (fprogress_init(&ff, file, fp)) return (-1);
 248   }
 249
 250   h = GH_INIT(fh->gch);
 251   while ((sz = fread(fbuf, 1, sizeof(fbuf), fp)) > 0) {
 252     GH_HASH(h, fbuf, sz);
 253     if (fh->f & FHF_PROGRESS) fprogress_update(&ff, sz);
 254   }
 255   if (ferror(fp)) rc = -1;
 256   if (fp != stdin) fclose(fp);
 257   if (fh->f & FHF_PROGRESS) fprogress_done(&ff);
 258   GH_DONE(h, buf);
 259   GH_DESTROY(h);
 260   return (rc);
 261 }
 262
 263 /* --- @hfparse@ --- *
 264  *
 265  * Arguments:   @hfpctx *hfp@ = pointer to the context structure
 266  *
 267  * Returns:     A code indicating what happened.
 268  *
 269  * Use:         Parses a line from the input file.
 270  */
 271
 272 int hfparse(hfpctx *hfp)
 273 {
 274   char *p, *q;
 275   const gchash *gch;
 276   const encodeops *ee;
 277   dstr *d = hfp->dline;
 278   size_t hsz;
 279
 280   /* --- Fetch the input line and get ready to parse --- */
 281
 282   DRESET(d);
 283   if (dstr_putline(d, hfp->fp) == EOF) return (HF_EOF);
 284   p = d->buf;
 285
 286   /* --- Parse magic comments --- */
 287
 288   if (*p == '#') {
 289     p++;
 290     if ((q = str_getword(&p)) == 0) return (HF_BAD);
 291     if (strcmp(q, "hash") == 0) {
 292       if ((q = str_getword(&p)) == 0) return (HF_BAD);
 293       if ((gch = gethash(q)) == 0) return (HF_BAD);
 294       hfp->gch = gch;
 295       return (HF_HASH);
 296     } else if (strcmp(q, "encoding") == 0) {
 297       if ((q = str_getword(&p)) == 0) return (HF_BAD);
 298       if ((ee = getencoding(q)) == 0) return (HF_BAD);
 299       hfp->ee = ee;
 300       return (HF_ENC);
 301     } else if (strcmp(q, "escape") == 0) {
 302       hfp->f |= HFF_ESCAPE;
 303       return (HF_ESC);
 304     }
 305     return (HF_BAD);
 306   }
 307
 308   /* --- Otherwise it's a file line --- */
 309
 310   q = p;
 311   while (*p && *p != ' ') p++;
 312   if (!*p) return (HF_BAD);
 313   *p++ = 0;
 314   hsz = hfp->gch->hashsz;
 315   if (hfp->ee->get(q, hfp->hbuf, hsz, 0) < hsz) return (HF_BAD);
 316   switch (*p) {
 317     case '*': hfp->f |= FHF_BINARY; break;
 318     case ' ': hfp->f &= ~FHF_BINARY; break;
 319     default: return (HF_BAD);
 320   }
 321   p++;
 322
 323   DRESET(hfp->dfile);
 324   if (hfp->f & HFF_ESCAPE)
 325     getstring(&p, hfp->dfile, GSF_STRING);
 326   else {
 327     dstr_putm(hfp->dfile, p, d->len - (p - d->buf));
 328     dstr_putz(hfp->dfile);
 329   }
 330
 331   return (HF_FILE);
 332 }
 333
 334 /*----- String I/O --------------------------------------------------------*/
 335
 336 /* --- @getstring@ --- *
 337  *
 338  * Arguments:   @void *in@ = input source
 339  *              @dstr *d@ = destination string
 340  *              @unsigned f@ = input flags
 341  *
 342  * Returns:     Zero if OK, nonzero on end-of-file.
 343  *
 344  * Use:         Reads a filename (or something similar) from a stream.
 345  */
 346
 347 static int nextch_file(void *in)
 348   { FILE *fp = in; return (getc(fp)); }
 349
 350 static int nextch_string(void *in)
 351   { const unsigned char **p = in; return (*(*p)++); }
 352
 353 int getstring(void *in, dstr *d, unsigned f)
 354 {
 355   int ch;
 356   int eofch = (f & GSF_STRING) ? 0 : EOF;
 357   int (*nextch)(void *) = (f & GSF_STRING) ? nextch_string : nextch_file;
 358   int q = 0;
 359
 360   /* --- Raw: just read exactly what's written up to a null byte --- */
 361
 362   if (f & GSF_RAW) {
 363     if ((ch = nextch(in)) == eofch)
 364       return (EOF);
 365     for (;;) {
 366       if (!ch)
 367         break;
 368       DPUTC(d, ch);
 369       if ((ch = nextch(in)) == eofch)
 370         break;
 371     }
 372     DPUTZ(d);
 373     return (0);
 374   }
 375
 376   /* --- Skip as far as whitespace --- *
 377    *
 378    * Also skip past comments.
 379    */
 380
 381 again:
 382   ch = nextch(in);
 383   while (isspace(ch))
 384     ch = nextch(in);
 385   if (ch == '#') {
 386     do ch = nextch(in); while (ch != '\n' && ch != eofch);
 387     goto again;
 388   }
 389   if (ch == eofch)
 390     return (EOF);
 391
 392   /* --- If the character is a quote then read a quoted string --- */
 393
 394   switch (ch) {
 395     case '`':
 396       ch = '\'';
 397     case '\'':
 398     case '\"':
 399       q = ch;
 400       ch = nextch(in);
 401       break;
 402   }
 403
 404   /* --- Now read all sorts of interesting things --- */
 405
 406   for (;;) {
 407
 408     /* --- Handle an escaped thing --- */
 409
 410     if (ch == '\\') {
 411       ch = nextch(in);
 412       if (ch == eofch)
 413         break;
 414       switch (ch) {
 415         case 'a': ch = '\a'; break;
 416         case 'b': ch = '\b'; break;
 417         case 'f': ch = '\f'; break;
 418         case 'n': ch = '\n'; break;
 419         case 'r': ch = '\r'; break;
 420         case 't': ch = '\t'; break;
 421         case 'v': ch = '\v'; break;
 422       }
 423       DPUTC(d, ch);
 424       ch = nextch(in);
 425       continue;
 426     }
 427
 428     /* --- If it's a quote or some other end marker then stop --- */
 429
 430     if (ch == q)
 431       break;
 432     if (!q && isspace(ch))
 433       break;
 434
 435     /* --- Otherwise contribute and continue --- */
 436
 437     DPUTC(d, ch);
 438     if ((ch = nextch(in)) == eofch)
 439       break;
 440   }
 441
 442   /* --- Done --- */
 443
 444   DPUTZ(d);
 445   return (0);
 446 }
 447
 448 /* --- @putstring@ --- *
 449  *
 450  * Arguments:   @FILE *fp@ = stream to write on
 451  *              @const char *p@ = pointer to text
 452  *              @unsigned f@ = output flags
 453  *
 454  * Returns:     ---
 455  *
 456  * Use:         Emits a string to a stream.
 457  */
 458
 459 void putstring(FILE *fp, const char *p, unsigned f)
 460 {
 461   size_t sz = strlen(p);
 462   unsigned qq;
 463   const char *q;
 464
 465   /* --- Just write the string null terminated if raw --- */
 466
 467   if (f & GSF_RAW) {
 468     fwrite(p, 1, sz + 1, fp);
 469     return;
 470   }
 471
 472   /* --- Check for any dodgy characters --- */
 473
 474   qq = 0;
 475   for (q = p; *q; q++) {
 476     if (isspace((unsigned char)*q)) {
 477       qq = '\"';
 478       break;
 479     }
 480   }
 481
 482   if (qq)
 483     putc(qq, fp);
 484
 485   /* --- Emit the string --- */
 486
 487   for (q = p; *q; q++) {
 488     switch (*q) {
 489       case '\a': fputc('\\', fp); fputc('a',  fp); break;
 490       case '\b': fputc('\\', fp); fputc('b',  fp); break;
 491       case '\f': fputc('\\', fp); fputc('f',  fp); break;
 492       case '\n': fputc('\\', fp); fputc('n',  fp); break;
 493       case '\r': fputc('\\', fp); fputc('r',  fp); break;
 494       case '\t': fputc('\\', fp); fputc('t',  fp); break;
 495       case '\v': fputc('\\', fp); fputc('v',  fp); break;
 496       case '`':  fputc('\\', fp); fputc('`',  fp); break;
 497       case '\'': fputc('\\', fp); fputc('\'', fp); break;
 498       case '\"': fputc('\\', fp); fputc('\"', fp); break;
 499       default:
 500         putc(*q, fp);
 501         break;
 502     }
 503   }
 504
 505   /* --- Done --- */
 506
 507   if (qq)
 508     putc(qq, fp);
 509 }
 510
 511 /*----- That's all, folks -------------------------------------------------*/