/************************************************************** lzhuf.c written by Haruyasu Yoshizaki 11/20/1988 some minor changes 4/6/1989 comments translated by Haruhiko Okumura 4/7/1989 MSX-C PROFI adaptation by MaxWolf, Aug-Sep 1992 EOF bugfix 1st April 1993 Компиляция: cc1 -m -c lzh3.c cc2 lzh3 **************************************************************/ #define EOF (-1) int getc(), putc(); char encount(), deinc(), decount(), memmove(); #pragma nonrec /********** LZSS compression *************/ #define N 4096 /* размер буфера */ #define F 60 /* предварительный размер буфера */ #define THRESHOLD 2 #define NIL N /* лист дерева */ extern char text_buf[N + F - 1]; static int matchposition, matchlength; extern int lson[N + 1], rson[N + 257], dad[N + 1]; /* инициализация дерева(ев) */ static int InitTree() { int *i, n; for(i = &rson[N + 1], n = 256; n--;) *i++ = NIL; /* корень */ for(i = dad, n = N; n--;) *i++ = NIL; /* узел */ } /* занести (вставить) в дерево */ static int InsertNode(r) int r; { int i, p, cmp; char *key; unsigned c; cmp = 1; key = &text_buf[r]; p = N + 1 + (int)key[0]; rson[r] = lson[r] = NIL; matchlength = 0; for (;;) { if (cmp >= 0) { if (rson[p] != NIL) p = rson[p]; else { rson[p] = r; goto i1; } } else { if (lson[p] != NIL) p = lson[p]; else { lson[p] = r; i1: dad[r] = p; return; } } for (i = 1; i < F; i++) if ((cmp = (int)key[i] - (int)text_buf[p + i]) != 0) break; if (i > THRESHOLD) { if (i > matchlength) { matchposition = ((r - p) & (N - 1)) - 1; if ((matchlength = i) >= F) break; } if (i == matchlength) { if ((c = ((r - p) & (N - 1)) - 1) < matchposition) { matchposition = c; } } } } dad[r] = dad[p]; dad[ lson[r] = lson[p] ] = r; dad[ rson[r] = rson[p] ] = r; if (rson[ i = dad[p] ] == p) rson[i] = r; else lson[i] = r; dad[p] = NIL; /* удалить p */ } /* удалить из дерева */ static int DeleteNode(p) int p; { int q, i; if (dad[p] == NIL) return; /* not registered */ if (rson[p] == NIL) q = lson[p]; else if (lson[p] == NIL) q = rson[p]; else { q = lson[p]; if (rson[q] != NIL) { do { q = rson[q]; } while (rson[q] != NIL); dad[ rson[dad[q]] = lson[q] ] = dad[q]; ; dad[ lson[q] = lson[p] ] = q; } dad[ rson[q] = rson[p] ] = q; } if (rson[ i = dad[q] = dad[p] ] == p) rson[i] = q; else lson[i] = q; dad[p] = NIL; } /* Кодирование Хаффмана */ #define N_CHAR (256 - THRESHOLD + F) /* kinds of characters (character code = 0..N_CHAR-1) */ #define T (N_CHAR * 2 - 1) /* размер таблицы */ #define R (T - 1) /* позиция корня */ #define MAX_FREQ 0x8000 /* updates tree when the */ /* root frequency comes to this value */ typedef char uchar; /* Таблицы кодирования и декодирования 6-ти верхних (upper) бит позиции */ /* для кодирования */ static uchar p_len[64] = { 0x03, 0x04, 0x04, 0x04, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08 }; static uchar p_code[64] = { 0x00, 0x20, 0x30, 0x40, 0x50, 0x58, 0x60, 0x68, 0x70, 0x78, 0x80, 0x88, 0x90, 0x94, 0x98, 0x9C, 0xA0, 0xA4, 0xA8, 0xAC, 0xB0, 0xB4, 0xB8, 0xBC, 0xC0, 0xC2, 0xC4, 0xC6, 0xC8, 0xCA, 0xCC, 0xCE, 0xD0, 0xD2, 0xD4, 0xD6, 0xD8, 0xDA, 0xDC, 0xDE, 0xE0, 0xE2, 0xE4, 0xE6, 0xE8, 0xEA, 0xEC, 0xEE, 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF }; /* для декодирования */ static uchar d_code[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0B, 0x0B, 0x0B, 0x0B, 0x0B, 0x0B, 0x0B, 0x0B, 0x0C, 0x0C, 0x0C, 0x0C, 0x0D, 0x0D, 0x0D, 0x0D, 0x0E, 0x0E, 0x0E, 0x0E, 0x0F, 0x0F, 0x0F, 0x0F, 0x10, 0x10, 0x10, 0x10, 0x11, 0x11, 0x11, 0x11, 0x12, 0x12, 0x12, 0x12, 0x13, 0x13, 0x13, 0x13, 0x14, 0x14, 0x14, 0x14, 0x15, 0x15, 0x15, 0x15, 0x16, 0x16, 0x16, 0x16, 0x17, 0x17, 0x17, 0x17, 0x18, 0x18, 0x19, 0x19, 0x1A, 0x1A, 0x1B, 0x1B, 0x1C, 0x1C, 0x1D, 0x1D, 0x1E, 0x1E, 0x1F, 0x1F, 0x20, 0x20, 0x21, 0x21, 0x22, 0x22, 0x23, 0x23, 0x24, 0x24, 0x25, 0x25, 0x26, 0x26, 0x27, 0x27, 0x28, 0x28, 0x29, 0x29, 0x2A, 0x2A, 0x2B, 0x2B, 0x2C, 0x2C, 0x2D, 0x2D, 0x2E, 0x2E, 0x2F, 0x2F, 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F, }; static uchar d_len[256] = { 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, }; extern unsigned freq[T + 1]; /* таблица частоты */ extern int prnt[T + N_CHAR]; /* pointers to parent nodes, except for the */ /* elements [T..T + N_CHAR - 1] which are used to get */ /* the positions of leaves corresponding to the codes. */ extern int son[T]; /* pointers to child nodes (son[], son[] + 1) */ static unsigned getbuf; static uchar getlen; #define GetBit() _GetBit((char)0) #define GetByte() _GetBit((char)1) /* получить один/восемь бит */ /* get one/eight bit(s) */ static int _GetBit(f) char f; { unsigned i; while (getlen <= 8) { if ((int)(i = getc()) == EOF) break; /* i = 0; */ getbuf |= i << (8 - getlen); getlen += 8; } i = getbuf; if (f) { getbuf <<= 8; getlen -= 8; return i >> 8; } else { getbuf <<= 1; --getlen; return ((int)i < 0); } } /*int GetByte() { unsigned i; while (getlen <= 8) { if ((i = getc()) == EOF) i = 0; getbuf |= i << (8 - getlen); getlen += 8; } i = getbuf; getbuf <<= 8; getlen -= 8; return i >> 8; }*/ static unsigned putbuf; static uchar putlen; static int Putcode(l,c) int l;unsigned c; /* output c bits of code */ { putbuf |= c >> putlen; if ((putlen += l) >= 8) { putc(putbuf >> 8); if ((putlen -= 8) >= 8) { putc(putbuf); putlen -= 8; putbuf = c << (l - putlen); } else { putbuf <<= 8; } } } /* initialization of tree */ static int StartHuff() { int i, j; for (i = 0; i < N_CHAR; i++) { freq[i] = 1; son[i] = i + T; prnt[i + T] = i; } i = 0; j = N_CHAR; while (j <= R) { freq[j] = freq[i] + freq[i + 1]; son[j] = i; prnt[i] = prnt[i + 1] = j; i += 2; j++; } freq[T] = 0xFFFF; prnt[R] = 0; } /* reconstruction of tree */ static int reconst() { int i, j, k; unsigned f, l; /* collect leaf nodes in the first half of the table */ /* and replace the freq by (freq + 1) / 2. */ j = 0; for (i = 0; i < T; i++) { if (son[i] >= T) { freq[j] = (freq[i] + 1) / 2; son[j] = son[i]; j++; } } /* begin constructing tree by connecting sons */ for (i = 0, j = N_CHAR; j < T; i += 2, j++) { k = i + 1; f = freq[j] = freq[i] + freq[k]; for (k = j - 1; f < freq[k]; k--); k++; l = (j - k) * 2; memmove(&freq[k + 1], &freq[k], l); freq[k] = f; memmove(&son[k + 1], &son[k], l); son[k] = i; } /* connect prnt */ for (i = 0; i < T; i++) { if ((k = son[i]) >= T) { prnt[k] = i; } else { prnt[k] = prnt[k + 1] = i; } } } /* increment frequency of given code by one, and update tree */ static int update(c) int c; { int i, j, k, l; if (freq[R] == MAX_FREQ) { reconst(); } c = prnt[c + T]; do { k = ++freq[c]; /* if the order is disturbed, exchange nodes */ if (k > freq[l = c + 1]) { while (k > freq[++l]); l--; freq[c] = freq[l]; freq[l] = k; i = son[c]; prnt[i] = l; if (i < T) prnt[i + 1] = l; j = son[l]; son[l] = i; prnt[j] = c; if (j < T) prnt[j + 1] = c; son[c] = j; c = l; } } while ((c = prnt[c]) != 0); /* repeat up to root */ } static EncodeChar(c) unsigned c; { unsigned i; int j, k; #ifdef DEBUG printf("char[%x]\n",c); #endif i = j = 0; k = prnt[c + T]; /* travel from leaf to root */ do { i >>= 1; /* if node's address is odd-numbered, choose bigger brother node */ if (k & 1) i += 0x8000; j++; } while ((k = prnt[k]) != R); Putcode(j, i); update(c); } static EncodePosition(c) unsigned c; { unsigned i; #ifdef DEBUG printf("pos[%x]\n",c); #endif /* output upper 6 bits by table lookup */ i = c >> 6; Putcode((int)p_len[i], (unsigned)p_code[i] << 8); /* output lower 6 bits verbatim */ Putcode(6, (c & 0x3f) << 10); } static EncodeEnd() { if (putlen) { putc(putbuf >> 8); } } static int DecodeChar() { unsigned c; c = son[R]; /* travel from root to leaf, */ /* choosing the smaller child node (son[]) if the read bit is 0, */ /* the bigger (son[]+1} if 1 */ while (c < T) { c += GetBit(); c = son[c]; } c -= T; update(c); #ifdef DEBUG printf("char[%x]\n",c); #endif return c; } static int DecodePosition() { unsigned i, j, c; /* recover upper 6 bits from table */ i = GetByte(); c = (unsigned)d_code[i] << 6; j = d_len[i] - 2; /* read lower 6 bits verbatim */ while (j--) { i = (i << 1) + GetBit(); } c |= (i & 0x3F); #ifdef DEBUG printf("pos[%x]\n",c); #endif return c; } /*-- Упаковка/Распаковка --*/ /* Упаковка */ char Encode() { int i, c, len, r, s, last_matchlength; StartHuff(); InitTree(); putbuf = putlen = 0; s = 0; r = N - F; for (i = s; i < r; i++) text_buf[i] = ' '; for (len = 0; len < F && (c = getc()) != EOF; len++) text_buf[r + len] = c; encount(len); for (i = 1; i <= F; i++) InsertNode(r - i); InsertNode(r); do { if (matchlength > len) matchlength = len; if (matchlength <= THRESHOLD) { matchlength = 1; EncodeChar((int)text_buf[r]); } else { EncodeChar(255 - THRESHOLD + matchlength); EncodePosition(matchposition); } last_matchlength = matchlength; for (i = 0; i < last_matchlength && (c = getc()) != EOF; i++) { DeleteNode(s); text_buf[s] = c; if (s < F - 1) text_buf[s + N] = c; s = (s + 1) & (N - 1); r = (r + 1) & (N - 1); InsertNode(r); } encount(i); while (i++ < last_matchlength) { DeleteNode(s); s = (s + 1) & (N - 1); r = (r + 1) & (N - 1); if (--len) InsertNode(r); } } while (len > 0); EncodeEnd(); } /* Распаковка */ char Decode() { int i, j, k, r, c; StartHuff(); getbuf = getlen = 0; for (i = 0; i < N - F; i++) text_buf[i] = ' '; r = N - F; while (decount() || getlen) { c = DecodeChar(); if (c < 256) { putc(c); text_buf[r++] = c; r &= (N - 1); deinc(); } else { i = (r - DecodePosition() - 1) & (N - 1); j = c - 255 + THRESHOLD; for (k = 0; k < j; k++) { c = text_buf[(i + k) & (N - 1)]; putc(c); text_buf[r++] = c; r &= (N - 1); deinc(); } } } }