diff options
Diffstat (limited to 'neozip/gzread.c')
| -rw-r--r-- | neozip/gzread.c | 609 |
1 files changed, 609 insertions, 0 deletions
diff --git a/neozip/gzread.c b/neozip/gzread.c new file mode 100644 index 0000000000..10ed519f2c --- /dev/null +++ b/neozip/gzread.c @@ -0,0 +1,609 @@ +/* gzread.c -- zlib functions for reading gzip files + * Copyright (C) 2004-2017 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "zbuild.h" +#include "zutil_p.h" +#include "gzguts.h" +#include "gzread_mangle.h" + +/* Local functions */ +static int gz_read_init(gz_state *state); +static int gz_load(gz_state *, unsigned char *, unsigned, unsigned *); +static int gz_avail(gz_state *); +static int gz_look(gz_state *); +static int gz_decomp(gz_state *); +static int gz_fetch(gz_state *); +static int gz_skip(gz_state *, z_off64_t); +static size_t gz_read(gz_state *, void *, size_t); + +static int gz_read_init(gz_state *state) { + /* Allocate gz buffers */ + if (gz_buffer_alloc(state) != 0) { + PREFIX(gz_error)(state, Z_MEM_ERROR, "out of memory"); + return -1; + } + + /* Initialize inflate state */ + int ret = PREFIX(inflateInit2)(&(state->strm), MAX_WBITS + 16); + if (ret != Z_OK) { + gz_buffer_free(state); + if (ret == Z_MEM_ERROR) { + PREFIX(gz_error)(state, Z_MEM_ERROR, "out of memory"); + } else { + PREFIX(gz_error)(state, Z_STREAM_ERROR, "invalid compression parameters"); + } + return -1; + } + return 0; +} + +/* Use read() to load a buffer -- return -1 on error, otherwise 0. Read from + state->fd, and update state->eof, state->err, and state->msg as appropriate. + This function needs to loop on read(), since read() is not guaranteed to + read the number of bytes requested, depending on the type of descriptor. */ +static int gz_load(gz_state *state, unsigned char *buf, unsigned len, unsigned *have) { + ssize_t ret; + + *have = 0; + do { + ret = read(state->fd, buf + *have, len - *have); + if (ret <= 0) + break; + *have += (unsigned)ret; + } while (*have < len); + if (ret < 0) { + PREFIX(gz_error)(state, Z_ERRNO, zstrerror()); + return -1; + } + if (ret == 0) + state->eof = 1; + return 0; +} + +/* Load up input buffer and set eof flag if last data loaded -- return -1 on + error, 0 otherwise. Note that the eof flag is set when the end of the input + file is reached, even though there may be unused data in the buffer. Once + that data has been used, no more attempts will be made to read the file. + If strm->avail_in != 0, then the current data is moved to the beginning of + the input buffer, and then the remainder of the buffer is loaded with the + available data from the input file. */ +static int gz_avail(gz_state *state) { + unsigned got; + PREFIX3(stream) *strm = &(state->strm); + + if (state->err != Z_OK && state->err != Z_BUF_ERROR) + return -1; + if (state->eof == 0) { + if (strm->avail_in) { /* copy what's there to the start */ + unsigned char *p = state->in; + unsigned const char *q = strm->next_in; + unsigned n = strm->avail_in; + do { + *p++ = *q++; + } while (--n); + } + if (gz_load(state, state->in + strm->avail_in, state->size - strm->avail_in, &got) == -1) + return -1; + strm->avail_in += got; + strm->next_in = state->in; + } + return 0; +} + +/* Look for gzip header, set up for inflate or copy. state->x.have must be 0. + If this is the first time in, allocate required memory. state->how will be + left unchanged if there is no more input data available, will be set to COPY + if there is no gzip header and direct copying will be performed, or it will + be set to GZIP for decompression. If direct copying, then leftover input + data from the input buffer will be copied to the output buffer. In that + case, all further file reads will be directly to either the output buffer or + a user buffer. If decompressing, the inflate state will be initialized. + gz_look() will return 0 on success or -1 on failure. */ +static int gz_look(gz_state *state) { + PREFIX3(stream) *strm = &(state->strm); + + /* allocate memory if this is the first time through */ + if (state->size == 0 && gz_read_init(state) == -1) + return -1; + + /* get at least the magic bytes in the input buffer */ + if (strm->avail_in < 2) { + if (gz_avail(state) == -1) + return -1; + if (strm->avail_in == 0) + return 0; + } + + /* look for gzip magic bytes -- if there, do gzip decoding (note: there is + a logical dilemma here when considering the case of a partially written + gzip file, to wit, if a single 31 byte is written, then we cannot tell + whether this is a single-byte file, or just a partially written gzip + file -- for here we assume that if a gzip file is being written, then + the header will be written in a single operation, so that reading a + single byte is sufficient indication that it is not a gzip file) */ + if (strm->avail_in > 1 && + strm->next_in[0] == 31 && strm->next_in[1] == 139) { + PREFIX(inflateReset)(strm); + state->how = GZIP; + state->direct = 0; + return 0; + } + + /* no gzip header -- if we were decoding gzip before, then this is trailing + garbage. Ignore the trailing garbage and finish. */ + if (state->direct == 0) { + strm->avail_in = 0; + state->eof = 1; + state->x.have = 0; + return 0; + } + + /* doing raw i/o, copy any leftover input to output -- this assumes that + the output buffer is larger than the input buffer, which also assures + space for gzungetc() */ + state->x.next = state->out; + memcpy(state->x.next, strm->next_in, strm->avail_in); + state->x.have = strm->avail_in; + strm->avail_in = 0; + state->how = COPY; + state->direct = 1; + return 0; +} + +/* Decompress from input to the provided next_out and avail_out in the state. + On return, state->x.have and state->x.next point to the just decompressed + data. If the gzip stream completes, state->how is reset to LOOK to look for + the next gzip stream or raw data, once state->x.have is depleted. Returns 0 + on success, -1 on failure. */ +static int gz_decomp(gz_state *state) { + int ret = Z_OK; + unsigned had; + PREFIX3(stream) *strm = &(state->strm); + + /* fill output buffer up to end of deflate stream */ + had = strm->avail_out; + do { + /* get more input for inflate() */ + if (strm->avail_in == 0 && gz_avail(state) == -1) + return -1; + if (strm->avail_in == 0) { + PREFIX(gz_error)(state, Z_BUF_ERROR, "unexpected end of file"); + break; + } + + /* decompress and handle errors */ + ret = PREFIX(inflate)(strm, Z_NO_FLUSH); + if (ret == Z_STREAM_ERROR || ret == Z_NEED_DICT) { + PREFIX(gz_error)(state, Z_STREAM_ERROR, "internal error: inflate stream corrupt"); + return -1; + } + if (ret == Z_MEM_ERROR) { + PREFIX(gz_error)(state, Z_MEM_ERROR, "out of memory"); + return -1; + } + if (ret == Z_DATA_ERROR) { /* deflate stream invalid */ + PREFIX(gz_error)(state, Z_DATA_ERROR, strm->msg == NULL ? "compressed data error" : strm->msg); + return -1; + } + } while (strm->avail_out && ret != Z_STREAM_END); + + /* update available output */ + state->x.have = had - strm->avail_out; + state->x.next = strm->next_out - state->x.have; + + /* if the gzip stream completed successfully, look for another */ + if (ret == Z_STREAM_END) + state->how = LOOK; + + /* good decompression */ + return 0; +} + +/* Fetch data and put it in the output buffer. Assumes state->x.have is 0. + Data is either copied from the input file or decompressed from the input + file depending on state->how. If state->how is LOOK, then a gzip header is + looked for to determine whether to copy or decompress. Returns -1 on error, + otherwise 0. gz_fetch() will leave state->how as COPY or GZIP unless the + end of the input file has been reached and all data has been processed. */ +static int gz_fetch(gz_state *state) { + PREFIX3(stream) *strm = &(state->strm); + Assert(state->x.have == 0, "Invalid state->x.have"); + + do { + switch (state->how) { + case LOOK: /* -> LOOK, COPY (only if never GZIP), or GZIP */ + if (gz_look(state) == -1) + return -1; + if (state->how == LOOK) + return 0; + break; + case COPY: /* -> COPY */ + if (gz_load(state, state->out, state->size << 1, &(state->x.have)) + == -1) + return -1; + state->x.next = state->out; + return 0; + case GZIP: /* -> GZIP or LOOK (if end of gzip stream) */ + strm->avail_out = state->size << 1; + strm->next_out = state->out; + if (gz_decomp(state) == -1) + return -1; + continue; + default: // Can't happen + Z_UNREACHABLE(); +#if !defined(__STDC_VERSION__) || __STDC_VERSION__ < 202311L + return -1; +#endif + } + } while (state->x.have == 0 && (!state->eof || strm->avail_in)); + return 0; +} + +/* Skip len uncompressed bytes of output. Return -1 on error, 0 on success. */ +static int gz_skip(gz_state *state, z_off64_t len) { + unsigned n; + + /* skip over len bytes or reach end-of-file, whichever comes first */ + while (len) + /* skip over whatever is in output buffer */ + if (state->x.have) { + n = GT_OFF(state->x.have) || (z_off64_t)state->x.have > len ? + (unsigned)len : state->x.have; + state->x.have -= n; + state->x.next += n; + state->x.pos += n; + len -= n; + } else if (state->eof && state->strm.avail_in == 0) { + /* output buffer empty -- return if we're at the end of the input */ + break; + } else { + /* need more data to skip -- load up output buffer */ + /* get more output, looking for header if required */ + if (gz_fetch(state) == -1) + return -1; + } + return 0; +} + +/* Read len bytes into buf from file, or less than len up to the end of the + input. Return the number of bytes read. If zero is returned, either the + end of file was reached, or there was an error. state->err must be + consulted in that case to determine which. */ +static size_t gz_read(gz_state *state, void *buf, size_t len) { + size_t got; + unsigned n; + + /* if len is zero, avoid unnecessary operations */ + if (len == 0) + return 0; + + /* process a skip request */ + if (state->seek) { + state->seek = 0; + if (gz_skip(state, state->skip) == -1) + return 0; + } + + /* get len bytes to buf, or less than len if at the end */ + got = 0; + do { + /* set n to the maximum amount of len that fits in an unsigned int */ + n = (unsigned)-1; + if (n > len) + n = (unsigned)len; + + /* first just try copying data from the output buffer */ + if (state->x.have) { + if (state->x.have < n) + n = state->x.have; + memcpy(buf, state->x.next, n); + state->x.next += n; + state->x.have -= n; + } + + /* output buffer empty -- return if we're at the end of the input */ + else if (state->eof && state->strm.avail_in == 0) { + state->past = 1; /* tried to read past end */ + break; + } + + /* need output data -- for small len or new stream load up our output + buffer */ + else if (state->how == LOOK || n < (state->size << 1)) { + /* get more output, looking for header if required */ + if (gz_fetch(state) == -1) + return 0; + continue; /* no progress yet -- go back to copy above */ + /* the copy above assures that we will leave with space in the + output buffer, allowing at least one gzungetc() to succeed */ + } + + /* large len -- read directly into user buffer */ + else if (state->how == COPY) { /* read directly */ + if (gz_load(state, (unsigned char *)buf, n, &n) == -1) + return 0; + } + + /* large len -- decompress directly into user buffer */ + else { /* state->how == GZIP */ + state->strm.avail_out = n; + state->strm.next_out = (unsigned char *)buf; + if (gz_decomp(state) == -1) + return 0; + n = state->x.have; + state->x.have = 0; + } + + /* update progress */ + len -= n; + buf = (char *)buf + n; + got += n; + state->x.pos += n; + } while (len); + + /* return number of bytes read into user buffer */ + return got; +} + +/* -- see zlib.h -- */ +z_int32_t Z_EXPORT PREFIX(gzread)(gzFile file, void *buf, z_uint32_t len) { + gz_state *state; + + /* get internal structure */ + if (file == NULL) + return -1; + state = (gz_state *)file; + + /* check that we're reading and that there's no (serious) error */ + if (state->mode != GZ_READ || + (state->err != Z_OK && state->err != Z_BUF_ERROR)) + return -1; + + /* since an int is returned, make sure len fits in one, otherwise return + with an error (this avoids a flaw in the interface) */ + if ((z_int32_t)len < 0) { + PREFIX(gz_error)(state, Z_STREAM_ERROR, "request does not fit in an int"); + return -1; + } + + /* read len or fewer bytes to buf */ + len = (unsigned)gz_read(state, buf, len); + + /* check for an error */ + if (len == 0 && state->err != Z_OK && state->err != Z_BUF_ERROR) + return -1; + + /* return the number of bytes read (this is assured to fit in an int) */ + return (z_int32_t)len; +} + +/* -- see zlib.h -- */ +size_t Z_EXPORT PREFIX(gzfread)(void *buf, size_t size, size_t nitems, gzFile file) { + size_t len; + gz_state *state; + + /* Exit early if size is zero, also prevents potential division by zero */ + if (size == 0) + return 0; + + /* get internal structure */ + if (file == NULL) + return 0; + state = (gz_state *)file; + + /* check that we're reading and that there's no (serious) error */ + if (state->mode != GZ_READ || + (state->err != Z_OK && state->err != Z_BUF_ERROR)) + return 0; + + /* compute bytes to read -- error on overflow */ + if (size && SIZE_MAX / size < nitems) { + PREFIX(gz_error)(state, Z_STREAM_ERROR, "request does not fit in a size_t"); + return 0; + } + len = nitems * size; + + /* read len or fewer bytes to buf, return the number of full items read */ + return len ? gz_read(state, buf, len) / size : 0; +} + +/* -- see zlib.h -- */ +z_int32_t Z_EXPORT PREFIX(gzgetc)(gzFile file) { + unsigned char buf[1]; + gz_state *state; + + /* get internal structure */ + if (file == NULL) + return -1; + state = (gz_state *)file; + + /* check that we're reading and that there's no (serious) error */ + if (state->mode != GZ_READ || (state->err != Z_OK && state->err != Z_BUF_ERROR)) + return -1; + + /* try output buffer (no need to check for skip request) */ + if (state->x.have) { + state->x.have--; + state->x.pos++; + return *(state->x.next)++; + } + + /* nothing there -- try gz_read() */ + return gz_read(state, buf, 1) < 1 ? -1 : buf[0]; +} + +#ifdef ZLIB_COMPAT +int Z_EXPORT PREFIX(gzgetc_)(gzFile file) { + return PREFIX(gzgetc)(file); +} +#endif + +/* -- see zlib.h -- */ +z_int32_t Z_EXPORT PREFIX(gzungetc)(z_int32_t c, gzFile file) { + gz_state *state; + + /* get internal structure */ + if (file == NULL) + return -1; + state = (gz_state *)file; + + /* in case this was just opened, set up the input buffer */ + if (state->mode == GZ_READ && state->how == LOOK && state->x.have == 0) + (void)gz_look(state); + + /* check that we're reading and that there's no (serious) error */ + if (state->mode != GZ_READ || (state->err != Z_OK && state->err != Z_BUF_ERROR)) + return -1; + + /* process a skip request */ + if (state->seek) { + state->seek = 0; + if (gz_skip(state, state->skip) == -1) + return -1; + } + + /* can't push EOF */ + if (c < 0) + return -1; + + /* if output buffer empty, put byte at end (allows more pushing) */ + if (state->x.have == 0) { + state->x.have = 1; + state->x.next = state->out + (state->size << 1) - 1; + state->x.next[0] = (unsigned char)c; + state->x.pos--; + state->past = 0; + return c; + } + + /* if no room, give up (must have already done a gzungetc()) */ + if (state->x.have == (state->size << 1)) { + PREFIX(gz_error)(state, Z_DATA_ERROR, "out of room to push characters"); + return -1; + } + + /* slide output data if needed and insert byte before existing data */ + if (state->x.next == state->out) { + unsigned char *src = state->out + state->x.have; + unsigned char *dest = state->out + (state->size << 1); + while (src > state->out) + *--dest = *--src; + state->x.next = dest; + } + state->x.have++; + state->x.next--; + state->x.next[0] = (unsigned char)c; + state->x.pos--; + state->past = 0; + return c; +} + +/* -- see zlib.h -- */ +char * Z_EXPORT PREFIX(gzgets)(gzFile file, char *buf, z_int32_t len) { + unsigned left, n; + char *str; + unsigned char *eol; + gz_state *state; + + /* check parameters and get internal structure */ + if (file == NULL || buf == NULL || len < 1) + return NULL; + state = (gz_state *)file; + + /* check that we're reading and that there's no (serious) error */ + if (state->mode != GZ_READ || (state->err != Z_OK && state->err != Z_BUF_ERROR)) + return NULL; + + /* process a skip request */ + if (state->seek) { + state->seek = 0; + if (gz_skip(state, state->skip) == -1) + return NULL; + } + + /* copy output bytes up to new line or len - 1, whichever comes first -- + append a terminating zero to the string (we don't check for a zero in + the contents, let the user worry about that) */ + str = buf; + left = (unsigned)len - 1; + if (left) { + do { + /* assure that something is in the output buffer */ + if (state->x.have == 0 && gz_fetch(state) == -1) + return NULL; /* error */ + if (state->x.have == 0) { /* end of file */ + state->past = 1; /* read past end */ + break; /* return what we have */ + } + + /* look for end-of-line in current output buffer */ + n = MIN(state->x.have, left); + eol = (unsigned char *)memchr(state->x.next, '\n', n); + if (eol != NULL) + n = (unsigned)(eol - state->x.next) + 1; + + /* copy through end-of-line, or remainder if not found */ + memcpy(buf, state->x.next, n); + state->x.have -= n; + state->x.next += n; + state->x.pos += n; + left -= n; + buf += n; + } while (left && eol == NULL); + } + + /* return terminated string, or if nothing, end of file */ + if (buf == str) + return NULL; + buf[0] = 0; + return str; +} + +/* -- see zlib.h -- */ +z_int32_t Z_EXPORT PREFIX(gzdirect)(gzFile file) { + gz_state *state; + + /* get internal structure */ + if (file == NULL) + return 0; + + state = (gz_state *)file; + + /* if the state is not known, but we can find out, then do so (this is + mainly for right after a gzopen() or gzdopen()) */ + if (state->mode == GZ_READ && state->how == LOOK && state->x.have == 0) + (void)gz_look(state); + + /* return 1 if transparent, 0 if processing a gzip stream */ + return state->direct; +} + +/* -- see zlib.h -- */ +z_int32_t Z_EXPORT PREFIX(gzclose_r)(gzFile file) { + int ret, err; + gz_state *state; + + /* get internal structure */ + if (file == NULL) + return Z_STREAM_ERROR; + + state = (gz_state *)file; + + /* check that we're reading */ + if (state->mode != GZ_READ) + return Z_STREAM_ERROR; + + /* free memory and close file */ + if (state->size) { + PREFIX(inflateEnd)(&(state->strm)); + gz_buffer_free(state); + } + err = state->err == Z_BUF_ERROR ? Z_BUF_ERROR : Z_OK; + PREFIX(gz_error)(state, Z_OK, NULL); + free(state->path); + ret = close(state->fd); + zng_free(state); + return ret ? Z_ERRNO : err; +} |