/* bms.c * Author: Masanao Izumo */ #include #include #include #include #include /* for UCHAR_MAX */ #include #include #include #include #ifdef __WIN32__ #include #define MAXPATHLEN MAX_PATH #define PATH_SEP '\\' #define PATH_STR "\\" #define IS_PATH_SEP(c) ((c) == '/' || (c) == '\\') extern char *optarg; extern int optind; extern int getopt(int argc, char *argv[], char *optionS); #define chdir(path) (SetCurrentDirectory(path) != 0 ? 0 : -1) #else #include #include #define PATH_SEP '/' #define IS_PATH_SEP(c) ((c) == '/') #define PATH_STR "/" #endif /* __WIN32__ */ #include #include #define BMS_VERSION "2.2.1" #define VERBOSE 0 /* #define MEMCHR_FAST */ #if !defined(SVR4) && (defined(SYSTYPE_SVR4) || defined(__svr4__)) #define SVR4 #endif /* SVR4 */ #if defined(sun) && !defined(__svr4__) /* sun4 */ #include #define memcpy(x, y, n) bcopy(y, x, n) #endif /* sun */ #ifndef __WIN32__ #if !defined(sun) && defined(SVR4) #include #define dirent direct #else #include #endif #endif /* __WIN32__ */ #ifndef MAXPATHLEN #define MAXPATHLEN 1024 #endif /* MAXPATHLEN */ #define FBAG_PACKSIZE 256 #define SIZEOF_FBAGNODE ((unsigned long)((struct FBagNode *)0)->bag) #define HASHSIZE 1023 typedef struct FBagNode { struct FBagNode* next; int nelms; char bag[1]; } FBagNode; typedef struct FBag { FBagNode **entry; int size; int elmsiz; } FBag; void init_fbag(FBag* bag, int hash_size, int elmsiz); void add_fbag(FBag* bag, void* elem); int search_fbag(FBag* bag, void* elem); char* zcat(char* gzfile, long *size); typedef struct _MAPFile { void *map; long siz; #ifdef __WIN32__ HANDLE hFile, hMap; #endif /* __WIN32__ */ } MAPFile; int case_ignore = 0; int jis_to_euc_flag = 0; int around = 0; int once_flag = 0; int recursive_flag = 0; int disp_lineno_flag = 0; char* current_dir = NULL; char subdir[MAXPATHLEN]; char* wild_pattern = NULL; FBag bag_ino; int disp_path_skip = 0; int mark_flag; char* match_in = "\033[7m"; char* match_out = "\033[m"; int match_count_mode = 0; int disp_except_match = 0; int disp_filename = 0; int only_disp_filename = 0; int entirely_match = 0; int zcat_flag = 0; int directory_depth = 0; #ifdef __WIN32__ int directory_max_depth = -1; #else int directory_max_depth = 15; #endif /* __WIN32__ */ int cr2lf = 0; int pettern_length; struct file_id { dev_t dev; ino_t ino; }; /* ascii ESC $ [@B] * ----+---->{0}----+----->{1}--+----->{2}--+-----> kanji-mode * /|\ | | | * | | | | * +------------+[^ESC] | | * | | | * +------------------------+[^$] | * | | * +------------------------------------+[^@B] * * kanji ESC ( [JB] * ----+---->{0}----+----->{1}--+----->{2}--+-----> ascii-mode * /|\ | | | * | | | | * +------------+[^ESC] | | * | | | * +------------------------+[^(] | * | | * +------------------------------------+[^JB] */ #define ESC 033 long jistoeuc(unsigned char* eptr, unsigned char* jptr, long jlength) { unsigned char* eptr_begin = eptr; long j; /* Be careful: eptr - eptr_begin <= j */ j = 0; ascii: while(j < jlength && jptr[j] != ESC) { int c = jptr[j++]; if(c >= ' ' || c == '\n' || c == '\t') /* skip control sequences */ *eptr++ = c; else if(c == '\r' && jptr[j] != '\n') /* for *junet*mac */ *eptr++ = '\n'; } if(j >= jlength) goto done; /* 1 */ j++; if(jptr[j] != '$') /* ?? \033[^$] */ { if(j == jlength) goto done; goto ascii; } /* 2 */ j++; if(jptr[j] != '@' && jptr[j] != 'B') /* ?? \033$[^@B] */ { if(j == jlength) goto done; goto ascii; } kanji: j++; /* -1 for truncated jis character */ while(j < jlength - 1 && jptr[j] != ESC) { /* assume that correct jis code */ *eptr++ = (jptr[j++] | 0x80); *eptr++ = (jptr[j++] | 0x80); } if(j == jlength - 1) *eptr++ = jptr[j++]; if(j >= jlength) goto done; /* 1 */ j++; if(jptr[j] != '(') { if(j == jlength) goto done; goto kanji; } /* 2 */ j++; if(jptr[j] != 'J' && jptr[j] != 'B') { if(j == jlength) goto done; goto kanji; } j++; goto ascii; done: *eptr = '\0'; /* terminate a string */ return (long)(eptr - eptr_begin); } static void convert_cr2lf(char *to, char *from, long n) { long i; for(i = 0; i < n; i++) { if(from[i] == '\r') to[i] = '\n'; else to[i] = from[i]; } } const unsigned long crc_32_tab[256] = { 0x00000000L, 0x77073096L, 0xee0e612cL, 0x990951baL, 0x076dc419L, 0x706af48fL, 0xe963a535L, 0x9e6495a3L, 0x0edb8832L, 0x79dcb8a4L, 0xe0d5e91eL, 0x97d2d988L, 0x09b64c2bL, 0x7eb17cbdL, 0xe7b82d07L, 0x90bf1d91L, 0x1db71064L, 0x6ab020f2L, 0xf3b97148L, 0x84be41deL, 0x1adad47dL, 0x6ddde4ebL, 0xf4d4b551L, 0x83d385c7L, 0x136c9856L, 0x646ba8c0L, 0xfd62f97aL, 0x8a65c9ecL, 0x14015c4fL, 0x63066cd9L, 0xfa0f3d63L, 0x8d080df5L, 0x3b6e20c8L, 0x4c69105eL, 0xd56041e4L, 0xa2677172L, 0x3c03e4d1L, 0x4b04d447L, 0xd20d85fdL, 0xa50ab56bL, 0x35b5a8faL, 0x42b2986cL, 0xdbbbc9d6L, 0xacbcf940L, 0x32d86ce3L, 0x45df5c75L, 0xdcd60dcfL, 0xabd13d59L, 0x26d930acL, 0x51de003aL, 0xc8d75180L, 0xbfd06116L, 0x21b4f4b5L, 0x56b3c423L, 0xcfba9599L, 0xb8bda50fL, 0x2802b89eL, 0x5f058808L, 0xc60cd9b2L, 0xb10be924L, 0x2f6f7c87L, 0x58684c11L, 0xc1611dabL, 0xb6662d3dL, 0x76dc4190L, 0x01db7106L, 0x98d220bcL, 0xefd5102aL, 0x71b18589L, 0x06b6b51fL, 0x9fbfe4a5L, 0xe8b8d433L, 0x7807c9a2L, 0x0f00f934L, 0x9609a88eL, 0xe10e9818L, 0x7f6a0dbbL, 0x086d3d2dL, 0x91646c97L, 0xe6635c01L, 0x6b6b51f4L, 0x1c6c6162L, 0x856530d8L, 0xf262004eL, 0x6c0695edL, 0x1b01a57bL, 0x8208f4c1L, 0xf50fc457L, 0x65b0d9c6L, 0x12b7e950L, 0x8bbeb8eaL, 0xfcb9887cL, 0x62dd1ddfL, 0x15da2d49L, 0x8cd37cf3L, 0xfbd44c65L, 0x4db26158L, 0x3ab551ceL, 0xa3bc0074L, 0xd4bb30e2L, 0x4adfa541L, 0x3dd895d7L, 0xa4d1c46dL, 0xd3d6f4fbL, 0x4369e96aL, 0x346ed9fcL, 0xad678846L, 0xda60b8d0L, 0x44042d73L, 0x33031de5L, 0xaa0a4c5fL, 0xdd0d7cc9L, 0x5005713cL, 0x270241aaL, 0xbe0b1010L, 0xc90c2086L, 0x5768b525L, 0x206f85b3L, 0xb966d409L, 0xce61e49fL, 0x5edef90eL, 0x29d9c998L, 0xb0d09822L, 0xc7d7a8b4L, 0x59b33d17L, 0x2eb40d81L, 0xb7bd5c3bL, 0xc0ba6cadL, 0xedb88320L, 0x9abfb3b6L, 0x03b6e20cL, 0x74b1d29aL, 0xead54739L, 0x9dd277afL, 0x04db2615L, 0x73dc1683L, 0xe3630b12L, 0x94643b84L, 0x0d6d6a3eL, 0x7a6a5aa8L, 0xe40ecf0bL, 0x9309ff9dL, 0x0a00ae27L, 0x7d079eb1L, 0xf00f9344L, 0x8708a3d2L, 0x1e01f268L, 0x6906c2feL, 0xf762575dL, 0x806567cbL, 0x196c3671L, 0x6e6b06e7L, 0xfed41b76L, 0x89d32be0L, 0x10da7a5aL, 0x67dd4accL, 0xf9b9df6fL, 0x8ebeeff9L, 0x17b7be43L, 0x60b08ed5L, 0xd6d6a3e8L, 0xa1d1937eL, 0x38d8c2c4L, 0x4fdff252L, 0xd1bb67f1L, 0xa6bc5767L, 0x3fb506ddL, 0x48b2364bL, 0xd80d2bdaL, 0xaf0a1b4cL, 0x36034af6L, 0x41047a60L, 0xdf60efc3L, 0xa867df55L, 0x316e8eefL, 0x4669be79L, 0xcb61b38cL, 0xbc66831aL, 0x256fd2a0L, 0x5268e236L, 0xcc0c7795L, 0xbb0b4703L, 0x220216b9L, 0x5505262fL, 0xc5ba3bbeL, 0xb2bd0b28L, 0x2bb45a92L, 0x5cb36a04L, 0xc2d7ffa7L, 0xb5d0cf31L, 0x2cd99e8bL, 0x5bdeae1dL, 0x9b64c2b0L, 0xec63f226L, 0x756aa39cL, 0x026d930aL, 0x9c0906a9L, 0xeb0e363fL, 0x72076785L, 0x05005713L, 0x95bf4a82L, 0xe2b87a14L, 0x7bb12baeL, 0x0cb61b38L, 0x92d28e9bL, 0xe5d5be0dL, 0x7cdcefb7L, 0x0bdbdf21L, 0x86d3d2d4L, 0xf1d4e242L, 0x68ddb3f8L, 0x1fda836eL, 0x81be16cdL, 0xf6b9265bL, 0x6fb077e1L, 0x18b74777L, 0x88085ae6L, 0xff0f6a70L, 0x66063bcaL, 0x11010b5cL, 0x8f659effL, 0xf862ae69L, 0x616bffd3L, 0x166ccf45L, 0xa00ae278L, 0xd70dd2eeL, 0x4e048354L, 0x3903b3c2L, 0xa7672661L, 0xd06016f7L, 0x4969474dL, 0x3e6e77dbL, 0xaed16a4aL, 0xd9d65adcL, 0x40df0b66L, 0x37d83bf0L, 0xa9bcae53L, 0xdebb9ec5L, 0x47b2cf7fL, 0x30b5ffe9L, 0xbdbdf21cL, 0xcabac28aL, 0x53b39330L, 0x24b4a3a6L, 0xbad03605L, 0xcdd70693L, 0x54de5729L, 0x23d967bfL, 0xb3667a2eL, 0xc4614ab8L, 0x5d681b02L, 0x2a6f2b94L, 0xb40bbe37L, 0xc30c8ea1L, 0x5a05df1bL, 0x2d02ef8dL }; static unsigned long hash(void* val, int size) { unsigned long c = (unsigned long)0xffffffffL; unsigned char *p; int i; p = (unsigned char *)val; for(i = 0; i < size; i++) c = (c >> 8) ^ crc_32_tab[(c ^ p[i]) & 0xff]; return c ^ 0xffffffffL; } void init_fbag(FBag* bag, int hash_size, int elmsiz) { int i; if((bag->entry = (FBagNode **)malloc(hash_size * sizeof(FBagNode *))) == NULL) { perror("malloc"); exit(1); } for(i = 0; i < hash_size; i++) bag->entry[i] = NULL; bag->size = hash_size; bag->elmsiz = elmsiz; } void add_fbag(FBag* bag, void* elem) { int elmsiz = bag->elmsiz; unsigned int addr = hash(elem, elmsiz) % bag->size; FBagNode* np = bag->entry[addr]; if(np == NULL) { if((np = (FBagNode *)malloc(SIZEOF_FBAGNODE + elmsiz * FBAG_PACKSIZE)) == NULL) { perror("malloc"); exit(1); } np->nelms = 0; np->next = NULL; bag->entry[addr] = np; } else if(np->nelms == FBAG_PACKSIZE) { if((np = (FBagNode *)malloc(SIZEOF_FBAGNODE + elmsiz * FBAG_PACKSIZE)) == NULL) { perror("malloc"); exit(1); } np->nelms = 0; np->next = bag->entry[addr]; bag->entry[addr] = np; } memcpy(np->bag + np->nelms * elmsiz, elem, elmsiz); np->nelms++; } int search_fbag(FBag* bag, void* elem) { int elmsiz = bag->elmsiz; unsigned int addr = hash(elem, elmsiz) % bag->size; FBagNode* np = bag->entry[addr]; int i, n; char* bp; while(np) { bp = np->bag; n = np->nelms; for(i = 0; i < n; i++, bp += elmsiz) if(memcmp(elem, bp, elmsiz) == 0) return 1; np = np->next; } return 0; /* Not found */ } void make_bm_skip(const unsigned char* pattern, long* skip) { long i, len; /* make the skip table */ len = (long)strlen((char *)pattern); for(i = 0; i <= UCHAR_MAX; i++) skip[i] = len; for(i = 0; i < len - 1; i++) skip[pattern[i]] = len - 1 - i; } long BM_search(unsigned char* text, unsigned char* pattern, long tlen, long* skip) { long i, j, k, len; unsigned char c, tail; len = (long)strlen((char *)pattern); if(len == 0) return -1; if(len == tlen) { if(strcmp((const char *)text, (const char *)pattern) == 0) return 0; return -1; } tail = pattern[len - 1]; if(len == 1) { for(i = 0; i < tlen; i++) if(text[i] == tail) return i; } else { /* matching procedure */ #ifndef MEMCHR_FAST i = len - 1; while(i < tlen) { if((c = text[i]) == tail) { j = len - 1; k = i; while(pattern[--j] == text[--k]) if(j == 0) return k; /* found */ } i += skip[c]; } #else unsigned char *tailp; long orig_tlen; orig_tlen = tlen; text += len - 1; tlen -= len - 1; i = skip[tail]; while(tlen > 0 && (tailp = (unsigned char *)memchr(text, tail, tlen)) != NULL) { k = (long)(tailp - text); text += (k + i); tlen -= (k + i); j = len - 1; while(pattern[--j] == *(--tailp)) if(j == 0) return orig_tlen - tlen - i; /* found */ } #endif } return -1; } long BM_search_case(unsigned char* text, unsigned char* pattern, long tlen, long* skip) { long i, j, k, len; unsigned char c, tail; len = (long)strlen((char *)pattern); if(len == 0) return -1; if(len == tlen) { if(strcasecmp((const char *)text, (const char *)pattern) == 0) return 0; return -1; } tail = pattern[len - 1]; if(len == 1) { for(i = 0; i < tlen; i++) if(tolower(text[i]) == tail) return i; } else { /* matching procedure */ i = len - 1; while(i < tlen) { c = tolower(text[i]); if(c == tail) { j = len - 1; k = i; while(--j, --k, pattern[j] == tolower(text[k])) if(j == 0) return k; /* found */ } i += skip[c]; } } return -1; } static const char* make_path_name(const char* fname) { static char buff[BUFSIZ]; if(fname == NULL) return "(standard input)"; if(subdir[0]) { int len; len = strlen(subdir + disp_path_skip); strcpy(buff, subdir + disp_path_skip); buff[len] = PATH_SEP; strcpy(buff + len + 1, fname); return buff; } return fname; } static void report_near(const char* fname, const char* text, long tlen, long pos, int around, int lineno) { int i, mark; long match_start = pos; long match_end = pos + pettern_length; if(only_disp_filename) { puts(make_path_name(fname)); fflush(stdout); return; } if(match_end > tlen) match_end = tlen; if(around == 0) { if(disp_filename && fname != NULL) { fputs(make_path_name(fname), stdout); putchar(':'); } if(disp_lineno_flag) fprintf(stdout, "%d:", lineno); while(pos > 0 && text[pos] != '\n') pos--; if(text[pos] == '\n') pos++; if(mark_flag) { mark = 0; while(pos < tlen && text[pos] != '\n') { if(pos == match_start) { mark = 1; fputs(match_in, stdout); } else if(pos == match_end) { mark = 0; fputs(match_out, stdout); } putchar(text[pos]); pos++; } if(mark) fputs(match_out, stdout); } else while(pos < tlen && text[pos] != '\n') { putchar(text[pos]); pos++; } putchar('\n'); fflush(stdout); return; } if(disp_filename) { fputs(make_path_name(fname), stdout); putchar(':'); } else fputs("Found:", stdout); if(disp_lineno_flag) fprintf(stdout, "%d:", lineno); putchar('\n'); i = 0; for(;;) { while(pos > 0 && text[pos] != '\n') pos--; if(pos == 0 || i == around) break; pos--; i++; } if(text[pos] == '\n') pos++; i = -around; mark = 0; for(;;) { fputs(" ", stdout); while(pos < tlen && text[pos] != '\n') { if(mark_flag && pos == match_start) { mark = 1; fputs(match_in, stdout); } else if(mark_flag && pos == match_end) { mark = 0; fputs(match_out, stdout); } putchar(text[pos]); pos++; } if(mark) { fputs(match_out, stdout); mark = 0; } putchar('\n'); if(pos == tlen || i == around) break; pos++; i++; } if(mark) fputs(match_out, stdout); fflush(stdout); } #ifdef __WIN32__ int readfile(const char* fname, MAPFile *mp) { int fd; HANDLE hFile, hMap; mp->map = NULL; hFile = CreateFile(fname, GENERIC_READ, 0, NULL, OPEN_EXISTING, FILE_ATTRIBUTE_NORMAL, NULL); if(hFile == INVALID_HANDLE_VALUE) return 0; if(mp->siz == -1) { mp->siz = GetFileSize(hFile, NULL); if(mp->siz == 0xffffffff) { CloseHandle(hFile); return 0; } } hMap = CreateFileMapping(hFile, NULL, PAGE_READONLY, 0, 0, NULL); if(hMap == NULL) { CloseHandle(hFile); return NULL; } mp->map = MapViewOfFile(hMap, FILE_MAP_READ, 0, 0, 0); if(mp->map == NULL) { CloseHandle(hMap); CloseHandle(hFile); return NULL; } mp->hFile = hFile; mp->hMap = hMap; return 1; } void end_readfile(MAPFile *mp) { UnmapViewOfFile(mp->map); CloseHandle(mp->hMap); CloseHandle(mp->hFile); } #else int readfile(const char* fname, MAPFile *mp) { int fd; mp->map = NULL; if((fd = open(fname, O_RDONLY)) < 0) { #if 0 perror(make_path_name(fname)); #endif return 0; } if(mp->siz == -1) { struct stat buf; if(fstat(fd, &buf) < 0) { #if VERBOSE perror(make_path_name(fname)); #endif close(fd); return 0; } if(!S_ISREG(buf.st_mode)) { #if VERBOSE fprintf(stderr, "%s: Not a regular file.\n", make_path_name(fname)); #endif close(fd); return 0; } mp->siz = (long)buf.st_size; } if((mp->map = mmap(0, mp->siz, PROT_READ, MAP_SHARED, fd, 0)) == (caddr_t)-1) { if(mp->siz > 0) perror("mmap"); close(fd); return 0; } close(fd); return 1; } void end_readfile(MAPFile *mp) { munmap(mp->map, mp->siz); } #endif /* __WIN32__ */ static int bms_text(const char* text, unsigned char* ptn, long* skip, long n, const char* fname) { long pos, offset; long found, lineno; offset = 0; found = 0; lineno = 1; if(!disp_except_match) { while(offset < n) { if(case_ignore) pos = BM_search_case((unsigned char *)text + offset, ptn, n - offset, skip); else pos = BM_search((unsigned char *)text + offset, ptn, n - offset, skip); if(pos == -1) break; if(entirely_match) { long i; int bolp, eolp; i = offset + pos; bolp = (i == 0 || text[i - 1] == '\n'); eolp = ((i + pettern_length == n) || (i + pettern_length < n && text[i + pettern_length] == '\n') || (i + pettern_length + 1 < n && text[i + pettern_length] == '\r' && text[i + pettern_length + 1] == '\n')); if(!bolp || !eolp) { offset += pos; while(offset < n && text[offset++] != '\n') ; continue; } } found++; if(match_count_mode) { if(once_flag) break; offset += pos; while(offset < n && text[offset++] != '\n') ; continue; } if(disp_lineno_flag) { long i; for(i = offset; i < pos + offset; i++) lineno += (text[i] == '\n'); } offset += pos; report_near(fname, text, n, offset, around, lineno); if(once_flag) break; while(offset < n && text[offset++] != '\n'); lineno++; } } else { long i, skip_line; while(offset < n) { skip_line = 1; if(case_ignore) pos = BM_search_case((unsigned char *)text + offset, ptn, n - offset, skip); else pos = BM_search((unsigned char *)text + offset, ptn, n - offset, skip); if(pos != -1 && entirely_match) { int bolp, eolp; i = offset + pos; bolp = (i == 0 || text[i - 1] == '\n'); eolp = ((i + pettern_length == n) || (i + pettern_length < n && text[i + pettern_length] == '\n') || (i + pettern_length + 1 < n && text[i + pettern_length] == '\r' && text[i + pettern_length + 1] == '\n')); if(!bolp || !eolp) { while(offset + pos < n && text[offset + pos] != '\n') pos++; if(offset + pos < n && text[offset + pos] == '\n') pos++; skip_line = 0; } } if(pos == -1) pos = n - offset; for(i = offset; i < pos + offset; i++) { if(text[i] == '\n' || i == n - 1) { /* found no match line */ found++; if(!match_count_mode) { long j; if(i == 0) j = 0; else j = i - 1; report_near(fname, text, n, j, around, lineno); } lineno++; if(once_flag) goto loopout; } } offset += pos; if(skip_line) while(offset < n && text[offset++] != '\n') ; lineno++; } } loopout: return found; } char* readtty(long* nread); int wildmat(char *text, char *p); static int bms_file(char* fname, long n, unsigned char* ptn, long* skip) { char* text; char* gzfile; int found, mapflag; if(fname == NULL) { text = readtty(&n); if(zcat_flag) { gzfile = zcat(text, &n); if(gzfile != NULL) { free(text); text = gzfile; } } if(jis_to_euc_flag) n = jistoeuc((unsigned char *)text, (unsigned char *)text, n); if(cr2lf) convert_cr2lf(text, text, n); found = bms_text(text, ptn, skip, n, NULL); free(text); if(match_count_mode && (!only_disp_filename || found)) printf("%d\n", found); } else { char* p; MAPFile mp; if(wild_pattern != NULL && wildmat(fname, wild_pattern) != 1) return 0; mp.siz = n; if(!readfile(fname, &mp)) return 0; p = (char *)mp.map; n = mp.siz; mapflag = 1; if(zcat_flag) { long newsize; newsize = n; gzfile = zcat(p, &newsize); if(gzfile != NULL) { end_readfile(&mp); p = gzfile; n = newsize; mapflag = 0; } } if(!jis_to_euc_flag) { text = p; if(cr2lf) { if((text = malloc(n + 1)) == NULL) { perror("malloc"); exit(1); } convert_cr2lf(text, p, n); text[n] = '\0'; if(mapflag) end_readfile(&mp); else free(p); mapflag = 0; } } else { long newsize; if((text = malloc(n + 1)) == NULL) { perror("malloc"); exit(1); } newsize = jistoeuc((unsigned char *)text, (unsigned char *)p, n); if(cr2lf) convert_cr2lf(text, text, newsize); if(mapflag) end_readfile(&mp); else free(p); n = newsize; text[n] = '\0'; mapflag = 0; } found = bms_text(text, ptn, skip, n, fname); if(mapflag) end_readfile(&mp); else free(text); if(match_count_mode && (!only_disp_filename || found)) printf("%s:%d\n", make_path_name(fname), found); } fflush(stdout); return found; } #ifdef __WIN32__ typedef struct _W32DirEnt { HANDLE h; WIN32_FIND_DATA f; int cnt; char *dir; } W32DirEnt; static void init_w32dirent(W32DirEnt *p, char *dir) { p->h = NULL; p->cnt = 0; p->dir = dir; } static char *next_w32dirent(W32DirEnt *p) { if(p->cnt++ == 0) { if((p->h = FindFirstFile(p->dir, &p->f)) == INVALID_HANDLE_VALUE) return NULL; return p->f.cFileName; } if(FindNextFile(p->h, &p->f)) return p->f.cFileName; return NULL; } static void end_w32dirent(W32DirEnt *p) { FindClose(p->h); } static int bms_directory(unsigned char* ptn, long* skip) { int found, subdir_len; W32DirEnt dir; char *fname; if(directory_max_depth >= 0 && directory_depth > directory_max_depth) return 0; #if VERBOSE printf("%s" PATH_STR ":\n", make_path_name("")); #endif subdir_len = strlen(subdir); init_w32dirent(&dir, "*"); found = 0; while((fname = next_w32dirent(&dir)) != NULL) { if(!strcmp(fname, ".") || !strcmp(fname, "..")) continue; if(dir.f.dwFileAttributes == FILE_ATTRIBUTE_DIRECTORY) { if(chdir(fname) < 0) continue; if(strlen(fname) + subdir_len + 2 >= MAXPATHLEN) { fprintf(stderr, "%s/%s: Path name is too long.\n", subdir, fname); continue; } subdir[subdir_len] = PATH_SEP; strcpy(subdir + subdir_len + 1, fname); directory_depth++; found += bms_directory(ptn, skip); directory_depth--; subdir[subdir_len] = '\0'; // if(chdir(subdir) < 0) if(chdir("..") < 0) { perror(subdir); continue; } } else found += bms_file(fname, dir.f.nFileSizeLow, ptn, skip); } end_w32dirent(&dir); return found; } #else static int bms_directory(unsigned char* ptn, long* skip) { int found, subdir_len; DIR *dirp; struct dirent *d; struct stat sbuf; if(directory_max_depth >= 0 && directory_depth > directory_max_depth) return 0; #if VERBOSE printf("%s" PATH_STR ":\n", make_path_name("")); #endif subdir_len = strlen(subdir); if((dirp = opendir(".")) == NULL) { perror("opendir"); return 0; } found = 0; while((d = readdir(dirp)) != NULL) { char* fname = d->d_name; if(d->d_ino == 0 || !strcmp(fname, ".") || !strcmp(fname, "..")) continue; if(stat(fname, &sbuf) < 0) { #if VERBOSE perror(make_path_name(fname)); #endif continue; } if(S_ISDIR(sbuf.st_mode)) { struct file_id fid; memset(&fid, 0, sizeof(fid)); fid.dev = sbuf.st_dev; fid.ino = sbuf.st_ino; if(search_fbag(&bag_ino, &fid)) continue; add_fbag(&bag_ino, &fid); if(chdir(fname) < 0) { #if VERBOSE perror(fname); #endif continue; } if(strlen(fname) + subdir_len + 2 >= MAXPATHLEN) { fprintf(stderr, "%s/%s: Path name is too long.\n", subdir, fname); continue; } subdir[subdir_len] = PATH_SEP; strcpy(subdir + subdir_len + 1, fname); directory_depth++; found += bms_directory(ptn, skip); directory_depth--; subdir[subdir_len] = '\0'; if(chdir(subdir) < 0) { perror(subdir); continue; } } else if(S_ISREG(sbuf.st_mode)) found += bms_file(fname, (long)sbuf.st_size, ptn, skip); } closedir(dirp); return found; } #endif /* __WIN32__ */ void init_mark(const char* term) { if(!strcmp(term, "iris-ansi")) { match_in = "\033[1;7m"; return; } } char* progname; void usage(void) { fprintf(stderr, "usage: %s [-1cEhilMmnRrVvxz] [-C ] [-f ] [-e] pattern [file ...]\n", progname); } int main(int argc, char** argv) { unsigned char* ptn = NULL; int found; long i, skip[UCHAR_MAX + 1]; #ifdef sun extern char *optarg; extern int optind; #endif /* sun */ #ifdef __WIN32__ SetThreadPriority(GetCurrentThread(), THREAD_PRIORITY_HIGHEST); #endif /* __WIN32__ */ if((progname = strrchr(argv[0], PATH_SEP)) == NULL) progname = argv[0]; else progname++; if(argc < 2) { usage(); return 1; } mark_flag = isatty(1); while ((i = getopt(argc, argv, "1cC:d:Ee:f:hilMmnRrVvxz")) > 0) { switch(i) { case '1': once_flag = 1; break; case 'c': match_count_mode = 1; break; case 'C': around = atoi(optarg); if(around < 0) { fprintf(stderr, "Invalid number: %d\n", around); return 1; } break; case 'd': directory_max_depth = atoi(optarg); break; case 'E': jis_to_euc_flag = 1; break; case 'e': ptn = (unsigned char *)optarg; break; case 'f': wild_pattern = optarg; break; case 'h': usage(); return 0; case 'i': case_ignore = 1; break; case 'l': only_disp_filename = 1; break; case 'M': mark_flag = 0; break; case 'm': mark_flag = 1; break; case 'n': disp_lineno_flag = 1; break; case 'R': cr2lf = 1; break; case 'r': recursive_flag = 1; break; case 'V': printf("bms Version %s\n", BMS_VERSION); return 0; case 'v': disp_except_match = 1; break; case 'x': entirely_match = 1; break; case 'z': zcat_flag = 1; break; case '?': usage(); return 1; } } if(ptn == NULL && optind >= argc) { usage(); return 1; } if(disp_except_match) mark_flag = 0; // if(match_count_mode) // only_disp_filename = 0; if(only_disp_filename && !match_count_mode) once_flag = 1; if(ptn == NULL) ptn = (unsigned char *)argv[optind++]; if(jis_to_euc_flag) jistoeuc(ptn, ptn, (long)strlen((char *)ptn)); pettern_length = strlen((char *)ptn); if(mark_flag) { char* term; term = getenv("TERM"); if(term != NULL) init_mark(term); } if(case_ignore) for(i = 0; ptn[i]; i++) if(isupper(ptn[i])) ptn[i] = tolower(ptn[i]); make_bm_skip(ptn, skip); found = 0; if(optind == argc) { disp_filename = 0; if(bms_file(NULL, -1, ptn, skip) == 0) return 1; return 0; } if(recursive_flag) init_fbag(&bag_ino, HASHSIZE, sizeof(struct file_id)); if(recursive_flag || argc - optind > 1) disp_filename = 1; for(; optind < argc; optind++) { char* fname; fname = argv[optind]; if(strlen(fname) + 1 >= MAXPATHLEN) { fprintf(stderr, "%s: Path name is too long.\n", fname); continue; } if(!strcmp(fname, "-")) { found += bms_file(NULL, -1, ptn, skip); } else { if(recursive_flag) { #ifdef __WIN32__ if(GetFileAttributes(fname) == FILE_ATTRIBUTE_DIRECTORY) { if(current_dir == NULL) { if((current_dir = getcwd(NULL, BUFSIZ)) == NULL) { perror("getcwd"); return 1; } } #else struct stat sbuf; if(stat(fname, &sbuf) < 0) continue; if(S_ISDIR(sbuf.st_mode)) { struct file_id fid; if(current_dir == NULL) { if((current_dir = getcwd(NULL, BUFSIZ)) == NULL) { perror("getcwd"); return 1; } } memset(&fid, 0, sizeof(fid)); fid.dev = sbuf.st_dev; fid.ino = sbuf.st_ino; if(search_fbag(&bag_ino, &fid)) continue; add_fbag(&bag_ino, &fid); #endif /* __WIN32__ */ if(chdir(fname) < 0) { #if VERBOSE perror(fname); #endif chdir(current_dir); continue; } if(IS_PATH_SEP(fname[0])) { disp_path_skip = 0; strcpy(subdir, fname); } else { disp_path_skip = strlen(current_dir) + 1; if(disp_path_skip + strlen(fname) + 2 > MAXPATHLEN) { fprintf(stderr, "Pathname is too long.\n"); continue; } strcpy(subdir, current_dir); strcat(subdir, PATH_STR); strcat(subdir, fname); } directory_depth++; found += bms_directory(ptn, skip); directory_depth--; subdir[0] = '\0'; chdir(current_dir); } else found += bms_file(fname, -1, ptn, skip); } else found += bms_file(fname, -1, ptn, skip); } } if(found == 0) return 1; return 0; } #define UNIT_SIZE 1048576 /* 1M */ #define READ_UNIT (1024*64) /* 64k */ struct list { struct list* next; int n; char buffer[1]; }; static struct list* first = NULL; static struct list* last = NULL; static struct list* newlist(void) { struct list* node; if((node = (struct list *)malloc(sizeof(struct list) + UNIT_SIZE)) == NULL) { perror("malloc"); exit(1); } node->n = 0; node->next = NULL; return node; } static void next_string(char* s, int n) { struct list* p; if(first == NULL) last = first = newlist(); p = last; if(p->n + n < UNIT_SIZE) { memcpy(p->buffer + p->n, s, n); p->n += n; } else { int n0; n0 = UNIT_SIZE - p->n; memcpy(p->buffer + p->n, s, n0); p->n = UNIT_SIZE; last = p->next = newlist(); p = last; memcpy(p->buffer, s + n0, n - n0); p->n = n - n0; } } static char* concat_string(char* s, long* nread) { struct list* p; struct list* cur; char* start = s; cur = first; *nread = 0; while(cur != NULL) { p = cur; cur = cur->next; memcpy(s, p->buffer, p->n); s += p->n; *nread += p->n; free(p); } last = first = NULL; return start; } char* readtty(long* nread) { char buff[READ_UNIT]; int fd = 0; long n, t; char* s; t = 0; while((n = read(fd, buff, READ_UNIT)) > 0) { t += n; next_string(buff, n); } if(n < 0) { perror("read"); exit(1); } if(t == 0) { s = (char *)malloc(1); s[0] = '\0'; *nread = 0; return s; } if((s = (char *)malloc(t)) == NULL) { fprintf(stderr, "Can't allocate memory\n"); exit(1); } return concat_string(s, nread); } /************** wildmat ***************/ /* $Revision: 1.9 $ ** ** Do shell-style pattern matching for ?, \, [], and * characters. ** Might not be robust in face of malformed patterns; e.g., "foo[a-" ** could cause a segmentation violation. It is 8bit clean. ** ** Written by Rich $alz, mirror!rs, Wed Nov 26 19:03:17 EST 1986. ** Rich $alz is now . ** April, 1991: Replaced mutually-recursive calls with in-line code ** for the star character. ** ** Special thanks to Lars Mathiesen for the ABORT code. ** This can greatly speed up failing wildcard patterns. For example: ** pattern: -*-*-*-*-*-*-12-*-*-*-m-*-*-* ** text 1: -adobe-courier-bold-o-normal--12-120-75-75-m-70-iso8859-1 ** text 2: -adobe-courier-bold-o-normal--12-120-75-75-X-70-iso8859-1 ** Text 1 matches with 51 calls, while text 2 fails with 54 calls. Without ** the ABORT code, it takes 22310 calls to fail. Ugh. The following ** explanation is from Lars: ** The precondition that must be fulfilled is that DoMatch will consume ** at least one character in text. This is true if *p is neither '*' nor ** '\0'.) The last return has ABORT instead of FALSE to avoid quadratic ** behaviour in cases like pattern "*a*b*c*d" with text "abcxxxxx". With ** FALSE, each star-loop has to run to the end of the text; with ABORT ** only the last one does. ** ** Once the control of one instance of DoMatch enters the star-loop, that ** instance will return either TRUE or ABORT, and any calling instance ** will therefore return immediately after (without calling recursively ** again). In effect, only one star-loop is ever active. It would be ** possible to modify the code to maintain this context explicitly, ** eliminating all recursive calls at the cost of some complication and ** loss of clarity (and the ABORT stuff seems to be unclear enough by ** itself). I think it would be unwise to try to get this into a ** released version unless you have a good test data base to try it out ** on. */ #define TRUE 1 #define FALSE 0 #define ABORT -1 /* What character marks an inverted character class? */ #define NEGATE_CLASS '^' /* Is "*" a common pattern? */ #define OPTIMIZE_JUST_STAR /* Do tar(1) matching rules, which ignore a trailing slash? */ #undef MATCH_TAR_PATTERN /* ** Match text and p, return TRUE, FALSE, or ABORT. */ static int DoMatch(char *text, char *p) { register int last; register int matched; register int reverse; for ( ; *p; text++, p++) { if (*text == '\0' && *p != '*') return ABORT; switch (*p) { case '\\': /* Literal match with following character. */ p++; /* FALLTHROUGH */ default: if (*text != *p) return FALSE; continue; case '?': /* Match anything. */ continue; case '*': while (*++p == '*') /* Consecutive stars act just like one. */ continue; if (*p == '\0') /* Trailing star matches everything. */ return TRUE; while (*text) if ((matched = DoMatch(text++, p)) != FALSE) return matched; return ABORT; case '[': reverse = p[1] == NEGATE_CLASS ? TRUE : FALSE; if (reverse) /* Inverted character class. */ p++; matched = FALSE; if (p[1] == ']' || p[1] == '-') if (*++p == *text) matched = TRUE; for (last = *p; *++p && *p != ']'; last = *p) /* This next line requires a good C compiler. */ if (*p == '-' && p[1] != ']' ? *text <= *++p && *text >= last : *text == *p) matched = TRUE; if (matched == reverse) return FALSE; continue; } } #ifdef MATCH_TAR_PATTERN if (IS_PATH_SEP(*text)) return TRUE; #endif /* MATCH_TAR_ATTERN */ return *text == '\0'; } /* ** User-level routine. Returns TRUE or FALSE. */ int wildmat(char *text, char *p) { #ifdef OPTIMIZE_JUST_STAR if (p[0] == '*' && p[1] == '\0') return TRUE; #endif /* OPTIMIZE_JUST_STAR */ return DoMatch(text, p) == TRUE; } /* * zcat */ typedef struct _InflateHandler* InflateHandler; InflateHandler open_inflate_handler( long (* read_func)(char* buf, long size, void* user_val), void* user_val); long inflate(InflateHandler decoder, char* decode_buff, long decode_buff_size); void close_inflate_handler(InflateHandler decoder); #define GZIP_ASCIIFLAG (1u<<0) #define GZIP_MULTIPARTFLAG (1u<<1) #define GZIP_EXTRAFLAG (1u<<2) #define GZIP_FILEFLAG (1u<<3) #define GZIP_COMMFLAG (1u<<4) #define GZIP_ENCFLAG (1u<<5) struct zcat_read_arg { char* ptr; long len; }; long zcat_reader(char* buf, long size, void* user_val) { struct zcat_read_arg* arg; long n; arg = (struct zcat_read_arg *)user_val; n = arg->len; if(n > size) n = size; memcpy(buf, arg->ptr, n); arg->ptr += n; arg->len -= n; return n; } char* zcat(char* gzfile, long *size) { int method, flags; unsigned char* p = (unsigned char *)gzfile; unsigned char* q = p + *size; InflateHandler decoder; struct zcat_read_arg zcat_arg; char *buff; long newsize, n, buffsize; /* check & skip gzip header */ if(*size == 0 || p[0] != 0x1f || p[1] != 0x8b) return NULL; p += 2; /* Method */ if(p >= q) return NULL; method = *p++; if(method != 8) { /* Not suppoted */ return NULL; } /* Flags */ if(p >= q) return NULL; flags = *p++; if(flags & GZIP_ENCFLAG) return NULL; /* Time, extra flags, OS type */ p += 6; if(flags & GZIP_MULTIPARTFLAG) { /* part number */ p += 2; } if(flags & GZIP_EXTRAFLAG) { unsigned short len; /* extra field */ if(p + 1 >= q) return NULL; len = *p++; len |= ((unsigned short)(*p++)) << 8; p += len; } if(flags & GZIP_FILEFLAG) { /* file name */ int c; do { if(p >= q) return NULL; c = *p++; } while(c != '\0'); } if(flags & GZIP_COMMFLAG) { /* file name */ int c; do { if(p >= q) return NULL; c = *p++; } while(c != '\0'); } if(p >= q) return NULL; zcat_arg.ptr = (char *)p; zcat_arg.len = q - p; buffsize = (long)(zcat_arg.len * 1.5 + 256); buff = (char *)malloc(buffsize); newsize = 0; decoder = open_inflate_handler(zcat_reader, &zcat_arg); while(newsize < buffsize && (n = inflate(decoder, buff + newsize, buffsize - newsize))) newsize += n; close_inflate_handler(decoder); *size = newsize; return buff; } /* Memory block for decreasing malloc * * +------+ +------+ +-------+ * |BLOCK1|--->|BLOCK2|---> ... --->|BLOCK N|---> NULL * +------+ +------+ +-------+ * * * BLOCK: * +-----------------------+ * | memory 1 | * | | * +-----------------------+ * | memory 2 | * +-----------------------+ * | memory 3 | * | | * | | * +-----------------------+ * | unused ... | * +-----------------------+ */ #define MIN_MBLOCK_SIZE 8192 typedef struct _MBlockNode { size_t block_size; size_t offset; struct _MBlockNode *next; #ifndef MBLOCK_NOPAD void *pad; #endif /* MBLOCK_NOPAD */ char buffer[1]; } MBlockNode; typedef struct _MBlockList { MBlockNode *first; size_t allocated; } MBlockList; extern void init_mblock(MBlockList *mblock); extern void *new_segment(MBlockList *mblock, size_t nbytes); extern void reuse_mblock(MBlockList *mblock); static MBlockNode *free_mblock_list = NULL; #define ADDRALIGN 8 /* #define DEBUG */ void init_mblock(MBlockList *mblock) { mblock->first = NULL; mblock->allocated = 0; } static MBlockNode *new_mblock_node(size_t n) { MBlockNode *p; if(n > MIN_MBLOCK_SIZE) { if((p = (MBlockNode *)malloc(n + sizeof(MBlockNode))) == NULL) return NULL; p->block_size = n; } else if(free_mblock_list == NULL) { if((p = (MBlockNode *)malloc(sizeof(MBlockNode) + MIN_MBLOCK_SIZE)) == NULL) return NULL; p->block_size = MIN_MBLOCK_SIZE; } else { p = free_mblock_list; free_mblock_list = free_mblock_list->next; } p->offset = 0; p->next = NULL; return p; } static int enough_block_memory(MBlockList *mblock, size_t n) { size_t newoffset; if(mblock->first == NULL) return 0; newoffset = mblock->first->offset + n; if(newoffset < mblock->first->offset) /* exceed representable in size_t */ return 0; if(newoffset > mblock->first->block_size) return 0; return 1; } void *new_segment(MBlockList *mblock, size_t nbytes) { MBlockNode *p; void *addr; /* round up to ADDRALIGN */ nbytes = ((nbytes + ADDRALIGN - 1) & ~(ADDRALIGN - 1)); if(!enough_block_memory(mblock, nbytes)) { p = new_mblock_node(nbytes); p->next = mblock->first; mblock->first = p; mblock->allocated += p->block_size; } else p = mblock->first; addr = (void *)(p->buffer + p->offset); p->offset += nbytes; #ifdef DEBUG if(((unsigned long)addr) & (ADDRALIGN-1)) { fprintf(stderr, "Bad address: 0x%x\n", addr); exit(1); } #endif /* DEBUG */ return addr; } static void reuse_mblock1(MBlockNode *p) { if(p->block_size > MIN_MBLOCK_SIZE) free(p); else /* p->block_size <= MIN_MBLOCK_SIZE */ { p->next = free_mblock_list; free_mblock_list = p; } } void reuse_mblock(MBlockList *mblock) { MBlockNode *p; if((p = mblock->first) == NULL) return; /* There is nothing to collect memory */ while(p) { MBlockNode *tmp; tmp = p; p = p->next; reuse_mblock1(tmp); } init_mblock(mblock); } /* inflate.c -- Not copyrighted 1992 by Mark Adler version c10p1, 10 January 1993 */ /* You can do whatever you like with this source file, though I would prefer that if you modify it and redistribute it that you include comments to that effect with your name and the date. Thank you. [The history has been moved to the file ChangeLog.] */ /* Inflate deflated (PKZIP's method 8 compressed) data. The compression method searches for as much of the current string of bytes (up to a length of 258) in the previous 32K bytes. If it doesn't find any matches (of at least length 3), it codes the next byte. Otherwise, it codes the length of the matched string and its distance backwards from the current position. There is a single Huffman code that codes both single bytes (called "literals") and match lengths. A second Huffman code codes the distance information, which follows a length code. Each length or distance code actually represents a base value and a number of "extra" (sometimes zero) bits to get to add to the base value. At the end of each deflated block is a special end-of-block (EOB) literal/ length code. The decoding process is basically: get a literal/length code; if EOB then done; if a literal, emit the decoded byte; if a length then get the distance and emit the referred-to bytes from the sliding window of previously emitted data. There are (currently) three kinds of inflate blocks: stored, fixed, and dynamic. The compressor outputs a chunk of data at a time and decides which method to use on a chunk-by-chunk basis. A chunk might typically be 32K to 64K, uncompressed. If the chunk is uncompressible, then the "stored" method is used. In this case, the bytes are simply stored as is, eight bits per byte, with none of the above coding. The bytes are preceded by a count, since there is no longer an EOB code. If the data are compressible, then either the fixed or dynamic methods are used. In the dynamic method, the compressed data are preceded by an encoding of the literal/length and distance Huffman codes that are to be used to decode this block. The representation is itself Huffman coded, and so is preceded by a description of that code. These code descriptions take up a little space, and so for small blocks, there is a predefined set of codes, called the fixed codes. The fixed method is used if the block ends up smaller that way (usually for quite small chunks); otherwise the dynamic method is used. In the latter case, the codes are customized to the probabilities in the current block and so can code it much better than the pre-determined fixed codes can. The Huffman codes themselves are decoded using a multi-level table lookup, in order to maximize the speed of decoding plus the speed of building the decoding tables. See the comments below that precede the lbits and dbits tuning parameters. */ /* Notes beyond the 1.93a appnote.txt: 1. Distance pointers never point before the beginning of the output stream. 2. Distance pointers can point back across blocks, up to 32k away. 3. There is an implied maximum of 7 bits for the bit length table and 15 bits for the actual data. 4. If only one code exists, then it is encoded using one bit. (Zero would be more efficient, but perhaps a little confusing.) If two codes exist, they are coded using one bit each (0 and 1). 5. There is no way of sending zero distance codes--a dummy must be sent if there are none. (History: a pre 2.0 version of PKZIP would store blocks with no distance codes, but this was discovered to be too harsh a criterion.) Valid only for 1.93a. 2.04c does allow zero distance codes, which is sent as one code of zero bits in length. 6. There are up to 286 literal/length codes. Code 256 represents the end-of-block. Note however that the static length tree defines 288 codes just to fill out the Huffman codes. Codes 286 and 287 cannot be used though, since there is no length base or extra bits defined for them. Similarily, there are up to 30 distance codes. However, static trees define 32 codes (all 5 bits) to fill out the Huffman codes, but the last two had better not show up in the data. 7. Unzip can check dynamic Huffman blocks for complete code sets. The exception is that a single code would not be complete (see #4). 8. The five bits following the block type is really the number of literal codes sent minus 257. 9. Length codes 8,16,16 are interpreted as 13 length codes of 8 bits (1+6+6). Therefore, to output three times the length, you output three codes (1+1+1), whereas to output four times the same length, you only need two codes (1+3). Hmm. 10. In the tree reconstruction algorithm, Code = Code + Increment only if BitLength(i) is not zero. (Pretty obvious.) 11. Correction: 4 Bits: # of Bit Length codes - 4 (4 - 19) 12. Note: length code 284 can represent 227-258, but length code 285 really is 258. The last length deserves its own, short code since it gets used a lot in very redundant files. The length 258 is special since 258 - 3 (the min match length) is 255. 13. The literal/length and distance code bit lengths are read as a single stream of lengths. It is possible (and advantageous) for a repeat code (16, 17, or 18) to go across the boundary between the two sets of lengths. */ typedef unsigned char uch; typedef unsigned short ush; typedef unsigned long ulg; #define STORED_BLOCK 0 #define STATIC_TREES 1 #define DYN_TREES 2 #define WSIZE 32768 #define INBUF_EXTRA 64 #define OUTBUF_EXTRA 2048 #ifdef SMALL_MEM # define INBUFSIZ 8192 /* input buffer size */ #else # define INBUFSIZ 32768 /* input buffer size */ #endif #ifdef SMALL_MEM # define OUTBUFSIZ 8192 /* output buffer size */ #else # define OUTBUFSIZ 16384 /* output buffer size */ #endif /* Huffman code lookup table entry--this entry is four bytes for machines that have 16-bit pointers (e.g. PC's in the small or medium model). Valid extra bits are 0..13. e == 15 is EOB (end of block), e == 16 means that v is a literal, 16 < e < 32 means that v is a pointer to the next table, which codes e - 16 bits, and lastly e == 99 indicates an unused code. If a code with e == 99 is looked up, this implies an error in the data. */ struct huft { uch e; /* number of extra bits or operation */ uch b; /* number of bits in this code or subcode */ union { ush n; /* literal, length base, or distance base */ struct huft *t; /* pointer to next level of table */ } v; }; /* Save to local */ #define BITS_SAVE \ ulg bit_buf = decoder->bit_buf; \ ulg bit_len = decoder->bit_len; /* Restore to decoder */ #define BITS_RESTORE \ decoder->bit_buf = bit_buf; \ decoder->bit_len = bit_len; #define MASK_BITS(n) ((((ulg)1)<<(n))-1) #define GET_BYTE() (decoder->inptr < decoder->insize ? decoder->inbuf[decoder->inptr++] : fill_inbuf(decoder)) #define NEEDBITS(n) {while(bit_len<(n)){bit_buf|=((ulg)GET_BYTE())<>=(n);bit_len-=(n);} /* variables */ struct _InflateHandler { void* user_val; long (*read_func)(char *buf, long size, void* user_val); uch slide[2L * WSIZE]; uch inbuf[INBUFSIZ + INBUF_EXTRA]; unsigned wp; /* current position in slide */ unsigned insize; /* valid bytes in inbuf */ unsigned inptr; /* index of next byte to be processed in inbuf */ struct huft *fixed_tl; /* inflate static */ struct huft *fixed_td; /* inflate static */ int fixed_bl, fixed_bd; /* inflate static */ ulg bit_buf; /* bit buffer */ ulg bit_len; /* bits in bit buffer */ int method; int eof; unsigned copy_leng; unsigned copy_dist; struct huft *tl, *td; /* literal/length and distance decoder tables */ int bl, bd; /* number of bits decoded by tl[] and td[] */ MBlockList pool; /* memory buffer for tl, td */ unsigned char* obuf; }; /* Function prototypes */ static int fill_inbuf(InflateHandler); static int huft_build(unsigned *, unsigned, unsigned, ush *, ush *, struct huft **, int *, MBlockList* pool); static int huft_free(struct huft *); static long inflate_codes(InflateHandler, char *, long); static long inflate_stored(InflateHandler, char *, long); static long inflate_fixed(InflateHandler, char *, long); static long inflate_dynamic(InflateHandler, char *, long); static void inflate_start(InflateHandler); /* The inflate algorithm uses a sliding 32K byte window on the uncompressed stream to find repeated byte strings. This is implemented here as a circular buffer. The index is updated simply by incrementing and then and'ing with 0x7fff (32K-1). */ /* It is left to other modules to supply the 32K area. It is assumed to be usable as if it were declared "uch slide[32768];" or as just "uch *slide;" and then malloc'ed in the latter case. The definition must be in unzip.h, included above. */ #define lbits 9 /* bits in base literal/length lookup table */ #define dbits 6 /* bits in base distance lookup table */ /* Tables for deflate from PKZIP's appnote.txt. */ static ush cplens[] = { /* Copy lengths for literal codes 257..285 */ 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31, 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0}; /* note: see note #13 above about the 258 in this list. */ static ush cplext[] = { /* Extra bits for literal codes 257..285 */ 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0, 99, 99}; /* 99==invalid */ static ush cpdist[] = { /* Copy offsets for distance codes 0..29 */ 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145, 8193, 12289, 16385, 24577}; static ush cpdext[] = { /* Extra bits for distance codes */ 0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13}; /* Huffman code decoding is performed using a multi-level table lookup. The fastest way to decode is to simply build a lookup table whose size is determined by the longest code. However, the time it takes to build this table can also be a factor if the data being decoded are not very long. The most common codes are necessarily the shortest codes, so those codes dominate the decoding time, and hence the speed. The idea is you can have a shorter table that decodes the shorter, more probable codes, and then point to subsidiary tables for the longer codes. The time it costs to decode the longer codes is then traded against the time it takes to make longer tables. This results of this trade are in the variables lbits and dbits below. lbits is the number of bits the first level table for literal/ length codes can decode in one step, and dbits is the same thing for the distance codes. Subsequent tables are also less than or equal to those sizes. These values may be adjusted either when all of the codes are shorter than that, in which case the longest code length in bits is used, or when the shortest code is *longer* than the requested table size, in which case the length of the shortest code in bits is used. There are two different values for the two tables, since they code a different number of possibilities each. The literal/length table codes 286 possible values, or in a flat code, a little over eight bits. The distance table codes 30 possible values, or a little less than five bits, flat. The optimum values for speed end up being about one bit more than those, so lbits is 8+1 and dbits is 5+1. The optimum values may differ though from machine to machine, and possibly even between compilers. Your mileage may vary. */ /* If BMAX needs to be larger than 16, then h and x[] should be ulg. */ #define BMAX 16 /* maximum bit length of any code (16 for explode) */ #define N_MAX 288 /* maximum number of codes in any set */ static int huft_build( unsigned *b, /* code lengths in bits (all assumed <= BMAX) */ unsigned n, /* number of codes (assumed <= N_MAX) */ unsigned s, /* number of simple-valued codes (0..s-1) */ ush *d, /* list of base values for non-simple codes */ ush *e, /* list of extra bits for non-simple codes */ struct huft **t, /* result: starting table */ int *m, /* maximum lookup bits, returns actual */ MBlockList* pool) /* memory pool */ /* Given a list of code lengths and a maximum table size, make a set of tables to decode that set of codes. Return zero on success, one if the given code set is incomplete (the tables are still built in this case), two if the input is invalid (all zero length codes or an oversubscribed set of lengths), and three if not enough memory. The code with value 256 is special, and the tables are constructed so that no bits beyond that code are fetched when that code is decoded. */ { unsigned a; /* counter for codes of length k */ unsigned c[BMAX+1]; /* bit length count table */ unsigned el; /* length of EOB code (value 256) */ unsigned f; /* i repeats in table every f entries */ int g; /* maximum code length */ int h; /* table level */ register unsigned i; /* counter, current code */ register unsigned j; /* counter */ register int k; /* number of bits in current code */ int lx[BMAX+1]; /* memory for l[-1..BMAX-1] */ int *l = lx+1; /* stack of bits per table */ register unsigned *p; /* pointer into c[], b[], or v[] */ register struct huft *q; /* points to current table */ struct huft r; /* table entry for structure assignment */ struct huft *u[BMAX]; /* table stack */ unsigned v[N_MAX]; /* values in order of bit length */ register int w; /* bits before this table == (l * h) */ unsigned x[BMAX+1]; /* bit offsets, then code stack */ unsigned *xp; /* pointer into x */ int y; /* number of dummy codes added */ unsigned z; /* number of entries in current table */ /* Generate counts for each bit length */ el = n > 256 ? b[256] : BMAX; /* set length of EOB code, if any */ memset(c, 0, sizeof(c)); p = b; i = n; do { c[*p]++; /* assume all entries <= BMAX */ p++; /* Can't combine with above line (Solaris bug) */ } while(--i); if(c[0] == n) /* null input--all zero length codes */ { *t = (struct huft *)NULL; *m = 0; return 0; } /* Find minimum and maximum length, bound *m by those */ for(j = 1; j <= BMAX; j++) if(c[j]) break; k = j; /* minimum code length */ if((unsigned)*m < j) *m = j; for(i = BMAX; i; i--) if(c[i]) break; g = i; /* maximum code length */ if((unsigned)*m > i) *m = i; /* Adjust last length count to fill out codes, if needed */ for(y = 1 << j; j < i; j++, y <<= 1) if((y -= c[j]) < 0) return 2; /* bad input: more codes than bits */ if((y -= c[i]) < 0) return 2; c[i] += y; /* Generate starting offsets into the value table for each length */ x[1] = j = 0; p = c + 1; xp = x + 2; while(--i) /* note that i == g from above */ *xp++ = (j += *p++); /* Make a table of values in order of bit lengths */ memset(v, 0, sizeof(v)); p = b; i = 0; do { if((j = *p++) != 0) v[x[j]++] = i; } while(++i < n); n = x[g]; /* set n to length of v */ /* Generate the Huffman codes and for each, make the table entries */ x[0] = i = 0; /* first Huffman code is zero */ p = v; /* grab values in bit order */ h = -1; /* no tables yet--level -1 */ w = l[-1] = 0; /* no bits decoded yet */ u[0] = (struct huft *)NULL; /* just to keep compilers happy */ q = (struct huft *)NULL; /* ditto */ z = 0; /* ditto */ /* go through the bit lengths (k already is bits in shortest code) */ for(; k <= g; k++) { a = c[k]; while(a--) { /* here i is the Huffman code of length k bits for value *p */ /* make tables up to required level */ while(k > w + l[h]) { w += l[h++]; /* add bits already decoded */ /* compute minimum size table less than or equal to *m bits */ z = (z = g - w) > (unsigned)*m ? *m : z; /* upper limit */ if((f = 1 << (j = k - w)) > a + 1) /* try a k-w bit table */ { /* too few codes for k-w bit table */ f -= a + 1; /* deduct codes from patterns left */ xp = c + k; while(++j < z)/* try smaller tables up to z bits */ { if((f <<= 1) <= *++xp) break; /* enough codes to use up j bits */ f -= *xp; /* else deduct codes from patterns */ } } if((unsigned)w + j > el && (unsigned)w < el) j = el - w; /* make EOB code end at table */ z = 1 << j; /* table entries for j-bit table */ l[h] = j; /* set table size in stack */ /* allocate and link in new table */ if(pool == NULL) q = (struct huft *)malloc((z + 1)*sizeof(struct huft)); else q = (struct huft *) new_segment(pool, (z + 1)*sizeof(struct huft)); if(q == NULL) { if(h && pool == NULL) huft_free(u[0]); return 3; /* not enough memory */ } *t = q + 1; /* link to list for huft_free() */ *(t = &(q->v.t)) = (struct huft *)NULL; u[h] = ++q; /* table starts after link */ /* connect to last table, if there is one */ if(h) { x[h] = i; /* save pattern for backing up */ r.b = (uch)l[h-1]; /* bits to dump before this table */ r.e = (uch)(16 + j);/* bits in this table */ r.v.t = q; /* pointer to this table */ j = (i & ((1 << w) - 1)) >> (w - l[h-1]); u[h-1][j] = r; /* connect to last table */ } } /* set up table entry in r */ r.b = (uch)(k - w); if(p >= v + n) r.e = 99; /* out of values--invalid code */ else if(*p < s) { r.e = (uch)(*p < 256 ? 16 : 15); /* 256 is end-of-block code */ r.v.n = (ush)*p++; /* simple code is just the value */ } else { r.e = (uch)e[*p - s]; /* non-simple--look up in lists */ r.v.n = d[*p++ - s]; } /* fill code-like entries with r */ f = 1 << (k - w); for(j = i >> w; j < z; j += f) q[j] = r; /* backwards increment the k-bit code i */ for(j = 1 << (k - 1); i & j; j >>= 1) i ^= j; i ^= j; /* backup over finished tables */ while((i & ((1 << w) - 1)) != x[h]) w -= l[--h]; /* don't need to update q */ } } /* return actual size of base table */ *m = l[0]; /* Return true (1) if we were given an incomplete table */ return y != 0 && g != 1; } static int huft_free(struct huft *t) /* Free the malloc'ed tables built by huft_build(), which makes a linked list of the tables it made, with the links in a dummy first entry of each table. */ { register struct huft *p, *q; /* Go through linked list, freeing from the malloced (t[-1]) address. */ p = t; while(p != (struct huft *)NULL) { q = (--p)->v.t; free((char*)p); p = q; } return 0; } static long inflate_codes(InflateHandler decoder, char* buff, long size) /* inflate (decompress) the codes in a deflated (compressed) block. Return an error code or zero if it all goes ok. */ { register unsigned e;/* table entry flag/number of extra bits */ struct huft *t; /* pointer to table entry */ int n; struct huft *tl, *td;/* literal/length and distance decoder tables */ int bl, bd; /* number of bits decoded by tl[] and td[] */ unsigned l, w, d; uch *slide; BITS_SAVE; if(size == 0) return 0; slide = decoder->slide; tl = decoder->tl; td = decoder->td; bl = decoder->bl; bd = decoder->bd; #ifdef DEBUG if(decoder->copy_leng != 0) { fprintf(stderr, "What ? (decoder->copy_leng = %d)\n", decoder->copy_leng); abort(); } #endif /* DEBUG */ w = decoder->wp; /* inflate the coded data */ n = 0; for(;;) /* do until end of block */ { NEEDBITS((unsigned)bl); t = tl + GETBITS(bl); e = t->e; while(e > 16) { if(e == 99) return -1; DUMPBITS(t->b); e -= 16; NEEDBITS(e); t = t->v.t + GETBITS(e); e = t->e; } DUMPBITS(t->b); if(e == 16) /* then it's a literal */ { w &= WSIZE - 1; buff[n++] = slide[w++] = (uch)t->v.n; if(n == size) { decoder->wp = w; BITS_RESTORE; return size; } continue; } /* exit if end of block */ if(e == 15) break; /* it's an EOB or a length */ /* get length of block to copy */ NEEDBITS(e); l = t->v.n + GETBITS(e); DUMPBITS(e); /* decode distance of block to copy */ NEEDBITS((unsigned)bd); t = td + GETBITS(bd); e = t->e; while(e > 16) { if(e == 99) return -1; DUMPBITS(t->b); e -= 16; NEEDBITS(e); t = t->v.t + GETBITS(e); e = t->e; } DUMPBITS(t->b); NEEDBITS(e); d = w - t->v.n - GETBITS(e); DUMPBITS(e); /* do the copy */ while(l > 0 && n < size) { l--; d &= WSIZE - 1; w &= WSIZE - 1; buff[n++] = slide[w++] = slide[d++]; } if(n == size) { decoder->copy_leng = l; decoder->wp = w; decoder->copy_dist = d; BITS_RESTORE; return n; } } decoder->wp = w; decoder->method = -1; /* done */ BITS_RESTORE; return n; } static long inflate_stored(InflateHandler decoder, char* buff, long size) /* "decompress" an inflated type 0 (stored) block. */ { unsigned n, l, w; BITS_SAVE; /* go to byte boundary */ n = bit_len & 7; DUMPBITS(n); /* get the length and its complement */ NEEDBITS(16); n = GETBITS(16); DUMPBITS(16); NEEDBITS(16); if(n != (unsigned)((~bit_buf) & 0xffff)) { BITS_RESTORE; return -1; /* error in compressed data */ } DUMPBITS(16); /* read and output the compressed data */ decoder->copy_leng = n; n = 0; l = decoder->copy_leng; w = decoder->wp; while(l > 0 && n < size) { l--; w &= WSIZE - 1; NEEDBITS(8); buff[n++] = decoder->slide[w++] = (uch)GETBITS(8); DUMPBITS(8); } if(l == 0) decoder->method = -1; /* done */ decoder->copy_leng = l; decoder->wp = w; BITS_RESTORE; return (long)n; } static long inflate_fixed(InflateHandler decoder, char* buff, long size) /* decompress an inflated type 1 (fixed Huffman codes) block. We should either replace this with a custom decoder, or at least precompute the Huffman tables. */ { /* if first time, set up tables for fixed blocks */ if(decoder->fixed_tl == NULL) { int i; /* temporary variable */ unsigned l[288]; /* length list for huft_build */ /* literal table */ for(i = 0; i < 144; i++) l[i] = 8; for(; i < 256; i++) l[i] = 9; for(; i < 280; i++) l[i] = 7; for(; i < 288; i++) /* make a complete, but wrong code set */ l[i] = 8; decoder->fixed_bl = 7; if((i = huft_build(l, 288, 257, cplens, cplext, &decoder->fixed_tl, &decoder->fixed_bl, NULL)) != 0) { decoder->fixed_tl = NULL; return -1; } /* distance table */ for(i = 0; i < 30; i++) /* make an incomplete code set */ l[i] = 5; decoder->fixed_bd = 5; if((i = huft_build(l, 30, 0, cpdist, cpdext, &decoder->fixed_td, &decoder->fixed_bd, NULL)) > 1) { huft_free(decoder->fixed_tl); decoder->fixed_tl = NULL; return -1; } } decoder->tl = decoder->fixed_tl; decoder->td = decoder->fixed_td; decoder->bl = decoder->fixed_bl; decoder->bd = decoder->fixed_bd; return inflate_codes(decoder, buff, size); } static long inflate_dynamic(InflateHandler decoder, char* buff, long size) /* decompress an inflated type 2 (dynamic Huffman codes) block. */ { int i; /* temporary variables */ unsigned j; unsigned l; /* last length */ unsigned n; /* number of lengths to get */ struct huft *tl; /* literal/length code table */ struct huft *td; /* distance code table */ int bl; /* lookup bits for tl */ int bd; /* lookup bits for td */ unsigned nb; /* number of bit length codes */ unsigned nl; /* number of literal/length codes */ unsigned nd; /* number of distance codes */ #ifdef PKZIP_BUG_WORKAROUND unsigned ll[288+32];/* literal/length and distance code lengths */ #else unsigned ll[286+30];/* literal/length and distance code lengths */ #endif static unsigned border[] = { /* Order of the bit length code lengths */ 16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; BITS_SAVE; reuse_mblock(&decoder->pool); /* read in table lengths */ NEEDBITS(5); nl = 257 + GETBITS(5); /* number of literal/length codes */ DUMPBITS(5); NEEDBITS(5); nd = 1 + GETBITS(5); /* number of distance codes */ DUMPBITS(5); NEEDBITS(4); nb = 4 + GETBITS(4); /* number of bit length codes */ DUMPBITS(4); #ifdef PKZIP_BUG_WORKAROUND if(nl > 288 || nd > 32) #else if(nl > 286 || nd > 30) #endif { BITS_RESTORE; return -1; /* bad lengths */ } /* read in bit-length-code lengths */ for(j = 0; j < nb; j++) { NEEDBITS(3); ll[border[j]] = GETBITS(3); DUMPBITS(3); } for(; j < 19; j++) ll[border[j]] = 0; /* build decoding table for trees--single level, 7 bit lookup */ bl = 7; if((i = huft_build(ll, 19, 19, NULL, NULL, &tl, &bl, &decoder->pool)) != 0) { reuse_mblock(&decoder->pool); BITS_RESTORE; return -1; /* incomplete code set */ } /* read in literal and distance code lengths */ n = nl + nd; i = l = 0; while((unsigned)i < n) { NEEDBITS((unsigned)bl); j = (td = tl + (GETBITS(bl)))->b; DUMPBITS(j); j = td->v.n; if(j < 16) /* length of code in bits (0..15) */ ll[i++] = l = j; /* save last length in l */ else if(j == 16) /* repeat last length 3 to 6 times */ { NEEDBITS(2); j = 3 + GETBITS(2); DUMPBITS(2); if((unsigned)i + j > n) { BITS_RESTORE; return -1; } while(j--) ll[i++] = l; } else if(j == 17) /* 3 to 10 zero length codes */ { NEEDBITS(3); j = 3 + GETBITS(3); DUMPBITS(3); if((unsigned)i + j > n) { BITS_RESTORE; return -1; } while(j--) ll[i++] = 0; l = 0; } else /* j == 18: 11 to 138 zero length codes */ { NEEDBITS(7); j = 11 + GETBITS(7); DUMPBITS(7); if((unsigned)i + j > n) { BITS_RESTORE; return -1; } while(j--) ll[i++] = 0; l = 0; } } BITS_RESTORE; /* free decoding table for trees */ reuse_mblock(&decoder->pool); /* build the decoding tables for literal/length and distance codes */ bl = lbits; i = huft_build(ll, nl, 257, cplens, cplext, &tl, &bl, &decoder->pool); if(bl == 0) /* no literals or lengths */ i = 1; if(i) { if(i == 1) fprintf(stderr, " incomplete literal tree\n"); reuse_mblock(&decoder->pool); return -1; /* incomplete code set */ } bd = dbits; i = huft_build(ll + nl, nd, 0, cpdist, cpdext, &td, &bd, &decoder->pool); if(bd == 0 && nl > 257) /* lengths but no distances */ { fprintf(stderr, " incomplete distance tree\n"); reuse_mblock(&decoder->pool); return -1; } if(i == 1) { #ifdef PKZIP_BUG_WORKAROUND i = 0; #else fprintf(stderr, " incomplete distance tree\n"); #endif } if(i) { reuse_mblock(&decoder->pool); return -1; } /* decompress until an end-of-block code */ decoder->tl = tl; decoder->td = td; decoder->bl = bl; decoder->bd = bd; i = inflate_codes(decoder, buff, size); if(i == -1) /* error */ { reuse_mblock(&decoder->pool); return -1; } /* free the decoding tables, return */ return i; } static void inflate_start(InflateHandler decoder) /* initialize window, bit buffer */ { decoder->wp = 0; decoder->bit_buf = 0; decoder->bit_len = 0; decoder->insize = decoder->inptr = 0; decoder->fixed_td = decoder->fixed_tl = NULL; decoder->method = -1; decoder->eof = 0; decoder->copy_leng = decoder->copy_dist = 0; decoder->tl = NULL; init_mblock(&decoder->pool); } /*ARGSUSED*/ static long default_read_func(char* buf, long size, void* v) { return (long)fread(buf, 1, size, stdin); } InflateHandler open_inflate_handler( long (* read_func)(char* buf, long size, void* user_val), void* user_val) { InflateHandler decoder; decoder = (InflateHandler) malloc(sizeof(struct _InflateHandler)); inflate_start(decoder); decoder->user_val = user_val; if(read_func == NULL) decoder->read_func = default_read_func; else decoder->read_func = read_func; return decoder; } void close_inflate_handler(InflateHandler decoder) { if(decoder->fixed_tl != NULL) { huft_free(decoder->fixed_td); huft_free(decoder->fixed_tl); decoder->fixed_td = decoder->fixed_tl = NULL; } reuse_mblock(&decoder->pool); free(decoder); } /* decompress an inflated entry */ long inflate( InflateHandler decoder, char* buff, long size) { long n, i; n = 0; while(n < size) { if(decoder->eof && decoder->method == -1) return n; if(decoder->copy_leng > 0) { unsigned l, w, d; l = decoder->copy_leng; w = decoder->wp; if(decoder->method != STORED_BLOCK) { /* STATIC_TREES or DYN_TREES */ d = decoder->copy_dist; while(l > 0 && n < size) { l--; d &= WSIZE - 1; w &= WSIZE - 1; buff[n++] = decoder->slide[w++] = decoder->slide[d++]; } decoder->copy_dist = d; } else { BITS_SAVE; while(l > 0 && n < size) { l--; w &= WSIZE - 1; NEEDBITS(8); buff[n++] = decoder->slide[w++] = (uch)GETBITS(8); DUMPBITS(8); } BITS_RESTORE; if(l == 0) decoder->method = -1; /* done */ } decoder->copy_leng = l; decoder->wp = w; if(n == size) return n; } if(decoder->method == -1) { BITS_SAVE; if(decoder->eof) { BITS_RESTORE; break; } /* read in last block bit */ NEEDBITS(1); if(GETBITS(1)) decoder->eof = 1; DUMPBITS(1); /* read in block type */ NEEDBITS(2); decoder->method = (int)GETBITS(2); DUMPBITS(2); decoder->tl = NULL; decoder->copy_leng = 0; BITS_RESTORE; } switch(decoder->method) { case STORED_BLOCK: i = inflate_stored(decoder, buff + n, size - n); break; case STATIC_TREES: if(decoder->tl != NULL) i = inflate_codes(decoder, buff + n, size - n); else i = inflate_fixed(decoder, buff + n, size - n); break; case DYN_TREES: if(decoder->tl != NULL) i = inflate_codes(decoder, buff + n, size - n); else i = inflate_dynamic(decoder, buff + n, size - n); break; default: /* error */ i = -1; break; } if(i == -1) { if(decoder->eof) return 0; return -1; /* error */ } n += i; } return n; } /* =========================================================================== * Fill the input buffer. This is called only when the buffer is empty. */ static int fill_inbuf(InflateHandler decoder) { int len; /* Read as much as possible */ decoder->insize = 0; errno = 0; do { len = decoder->read_func((char*)decoder->inbuf + decoder->insize, (long)(INBUFSIZ - decoder->insize), decoder->user_val); if(len == 0 || len == EOF) break; decoder->insize += len; } while(decoder->insize < INBUFSIZ); if(decoder->insize == 0) return EOF; decoder->inptr = 1; return decoder->inbuf[0]; } #ifdef __WIN32__ int optind = 1; /* index of which argument is next */ char *optarg; /* pointer to argument of current option */ int opterr = 1; /* allow error message */ static char *letP = NULL; /* remember next option char's location */ #if 0 static char SW = 0; /* DOS switch character, either '-' or '/' */ #endif #define SW '-' /* On Win32 can't call DOS! */ /* Parse the command line options, System V style. Standard option syntax is: option ::= SW [optLetter]* [argLetter space* argument] where - SW is either '/' or '-', according to the current setting of the MSDOS switchar (int 21h function 37h). - there is no space before any optLetter or argLetter. - opt/arg letters are alphabetic, not punctuation characters. - optLetters, if present, must be matched in optionS. - argLetters, if present, are found in optionS followed by ':'. - argument is any white-space delimited string. Note that it can include the SW character. - upper and lower case letters are distinct. There may be multiple option clusters on a command line, each beginning with a SW, but all must appear before any non-option arguments (arguments not introduced by SW). Opt/arg letters may be repeated: it is up to the caller to decide if that is an error. The character SW appearing alone as the last argument is an error. The lead-in sequence SWSW ("--" or "//") causes itself and all the rest of the line to be ignored (allowing non-options which begin with the switch char). The string *optionS allows valid opt/arg letters to be recognized. argLetters are followed with ':'. Getopt () returns the value of the option character found, or EOF if no more options are in the command line. If option is an argLetter then the global optarg is set to point to the argument string (having skipped any white-space). The global optind is initially 1 and is always left as the index of the next argument of argv[] which getopt has not taken. Note that if "--" or "//" are used then optind is stepped to the next argument before getopt() returns EOF. If an error occurs, that is an SW char precedes an unknown letter, then getopt() will return a '?' character and normally prints an error message via perror(). If the global variable opterr is set to false (zero) before calling getopt() then the error message is not printed. For example, if the MSDOS switch char is '/' (the MSDOS norm) and *optionS == "A:F:PuU:wXZ:" then 'P', 'u', 'w', and 'X' are option letters and 'F', 'U', 'Z' are followed by arguments. A valid command line may be: aCommand /uPFPi /X /A L someFile where: - 'u' and 'P' will be returned as isolated option letters. - 'F' will return with "Pi" as its argument string. - 'X' is an isolated option. - 'A' will return with "L" as its argument. - "someFile" is not an option, and terminates getOpt. The caller may collect remaining arguments using argv pointers. */ int getopt(int argc, char *argv[], char *optionS) { unsigned char ch; char *optP; #if 0 if (SW == 0) { /* get SW using dos call 0x37 */ _AX = 0x3700; geninterrupt(0x21); SW = _DL; } #endif if (argc > optind) { if (letP == NULL) { if ((letP = argv[optind]) == NULL || *(letP++) != SW) goto gopEOF; if (*letP == SW) { optind++; goto gopEOF; } } if (0 == (ch = *(letP++))) { optind++; goto gopEOF; } if (':' == ch || (optP = strchr(optionS, ch)) == NULL) goto gopError; if (':' == *(++optP)) { optind++; if (0 == *letP) { if (argc <= optind) goto gopError; letP = argv[optind++]; } optarg = letP; letP = NULL; } else { if (0 == *letP) { optind++; letP = NULL; } optarg = NULL; } return ch; } gopEOF: optarg = letP = NULL; return EOF; gopError: if (argc > optind) optind++; optarg = letP = NULL; errno = EINVAL; if (opterr) perror ("get command line option"); return ('?'); } #endif /* __WIN32__ */