netcdf-c/libdispatch/dcrc32.c
Dennis Heimbigner 36102e3c32 Improve UTF8 Support On Windows
re: Issue https://github.com/Unidata/netcdf-c/issues/2190

The primary purpose of this PR is to improve the utf8 support
for windows. This is persuant to a change in Windows that
supports utf8 natively (almost). The almost means that it is
still utf16 internally and the set of characters representable
by utf8 is larger than those representable by utf16.

This leaves open the question in the Issue about handling
the Windows 1252 character set.

This required the following changes:

1. Test the Windows build and major version in order to see if
   native utf8 is supported.
2. If native utf8 is supported, Modify dpathmgr.c to call the 8-bit
   version of the windows fopen() and open() functions.
3. In support of this, programs that use XGetOpt (Windows versions)
   need to get the command line as utf8 and then parse to
   arc+argv as utf8. This requires using a homegrown command line parser
   named XCommandLineToArgvA.
4. Add a utility program called "acpget" that prints out the
   current Windows code page and locale.

Additionally, some technical debt was cleaned up as follows:

1. Unify all the places which attempt to read all or a part
   of a file into the dutil.c#NC_readfile code.
2. Similary unify all the code that creates temp files into
   dutil.c#NC_mktmp code.
3. Convert almost all remaining calls to fopen() and open()
   to NCfopen() and NCopen3(). This is to ensure that path management
   is used consistently. This touches a number of files.
4. extern->EXTERNL as needed to get it to work under Windows.
2022-02-08 20:53:30 -07:00

508 lines
16 KiB
C

/* zlib.h -- interface of the 'zlib' general purpose compression library
version 1.2.11, January 15th, 2017
Copyright (C) 1995-2017 Jean-loup Gailly and Mark Adler
This software is provided 'as-is', without any express or implied
warranty. In no event will the authors be held liable for any damages
arising from the use of this software.
Permission is granted to anyone to use this software for any purpose,
including commercial applications, and to alter it and redistribute it
freely, subject to the following restrictions:
1. The origin of this software must not be misrepresented; you must not
claim that you wrote the original software. If you use this software
in a product, an acknowledgment in the product documentation would be
appreciated but is not required.
2. Altered source versions must be plainly marked as such, and must not be
misrepresented as being the original software.
3. This notice may not be removed or altered from any source distribution.
Jean-loup Gailly Mark Adler
jloup@gzip.org madler@alumni.caltech.edu
The data format used by the zlib library is described by RFCs (Request for
Comments) 1950 to 1952 in the files http://tools.ietf.org/html/rfc1950
(zlib format), rfc1951 (deflate format) and rfc1952 (gzip format).
*/
/* crc32.c -- compute the CRC-32 of a data stream
* Copyright (C) 1995-2006, 2010, 2011, 2012, 2016 Mark Adler
* For conditions of distribution and use, see copyright notice in zlib.h
*
* Thanks to Rodney Brown <rbrown64@csc.com.au> for his contribution of faster
* CRC methods: exclusive-oring 32 bits of data at a time, and pre-computing
* tables for updating the shift register in one step with three exclusive-ors
* instead of four steps with four exclusive-ors. This results in about a
* factor of two increase in speed on a Power PC G4 (PPC7455) using gcc -O3.
*/
/**
Modified to make it standalone.
Dennis Heimbigner
UCAR
*/
/* crc32.c -- compute the CRC-32 of a data stream
* Copyright (C) 1995-2006, 2010, 2011, 2012, 2016 Mark Adler
* For conditions of distribution and use, see copyright notice in zlib.h
*
* Thanks to Rodney Brown <rbrown64@csc.com.au> for his contribution of faster
* CRC methods: exclusive-oring 32 bits of data at a time, and pre-computing
* tables for updating the shift register in one step with three exclusive-ors
* instead of four steps with four exclusive-ors. This results in about a
* factor of two increase in speed on a Power PC G4 (PPC7455) using gcc -O3.
*/
/* @(#) $Id$ */
/*
Note on the use of DYNAMIC_CRC_TABLE: there is no mutex or semaphore
protection on the static variables used to control the first-use generation
of the crc tables. Therefore, if you #define DYNAMIC_CRC_TABLE, you should
first call get_crc_table() to initialize the tables before allowing more than
one thread to use crc32().
DYNAMIC_CRC_TABLE and MAKECRCH can be #defined to write out dcrc32.h.
*/
/* Prototype for the crc32 function is defined in include/nccrc.h */
/* Define some of the macros used here */
#define FAR
#define ZEXPORT
#define local static
#define OF(x) x
#define uLong unsigned long
#define uInt unsigned int
#define z_off64_t long long
#define z_off_t long
#define z_crc_t unsigned long
#define z_size_t size_t
#define Z_NULL NULL
#include <stdlib.h>
#ifdef MAKECRCH
# include <stdio.h>
# ifndef DYNAMIC_CRC_TABLE
# define DYNAMIC_CRC_TABLE
# endif /* !DYNAMIC_CRC_TABLE */
#endif /* MAKECRCH */
#include "ncexternl.h"
/* Definitions for doing the crc four data bytes at a time. */
#if !defined(NOBYFOUR) && defined(Z_U4)
# define BYFOUR
#endif
#ifdef BYFOUR
local unsigned long crc32_little OF((unsigned long,
const unsigned char FAR *, z_size_t));
local unsigned long crc32_big OF((unsigned long,
const unsigned char FAR *, z_size_t));
# define TBLS 8
#else
# define TBLS 1
#endif /* BYFOUR */
local const z_crc_t FAR crc_table[TBLS][256];
#ifdef DYNAMIC_CRC_TABLE
local volatile int crc_table_empty = 1;
local z_crc_t FAR crc_table[TBLS][256];
local void make_crc_table OF((void));
#ifdef MAKECRCH
local void write_table OF((FILE *, const z_crc_t FAR *));
#endif /* MAKECRCH */
/*
Generate tables for a byte-wise 32-bit CRC calculation on the polynomial:
x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x+1.
Polynomials over GF(2) are represented in binary, one bit per coefficient,
with the lowest powers in the most significant bit. Then adding polynomials
is just exclusive-or, and multiplying a polynomial by x is a right shift by
one. If we call the above polynomial p, and represent a byte as the
polynomial q, also with the lowest power in the most significant bit (so the
byte 0xb1 is the polynomial x^7+x^3+x+1), then the CRC is (q*x^32) mod p,
where a mod b means the remainder after dividing a by b.
This calculation is done using the shift-register method of multiplying and
taking the remainder. The register is initialized to zero, and for each
incoming bit, x^32 is added mod p to the register if the bit is a one (where
x^32 mod p is p+x^32 = x^26+...+1), and the register is multiplied mod p by
x (which is shifting right by one and adding x^32 mod p if the bit shifted
out is a one). We start with the highest power (least significant bit) of
q and repeat for all eight bits of q.
The first table is simply the CRC of all possible eight bit values. This is
all the information needed to generate CRCs on data a byte at a time for all
combinations of CRC register values and incoming bytes. The remaining tables
allow for word-at-a-time CRC calculation for both big-endian and little-
endian machines, where a word is four bytes.
*/
local void make_crc_table()
{
z_crc_t c;
int n, k;
z_crc_t poly; /* polynomial exclusive-or pattern */
/* terms of polynomial defining this crc (except x^32): */
static volatile int first = 1; /* flag to limit concurrent making */
static const unsigned char p[] = {0,1,2,4,5,7,8,10,11,12,16,22,23,26};
/* See if another task is already doing this (not thread-safe, but better
than nothing -- significantly reduces duration of vulnerability in
case the advice about DYNAMIC_CRC_TABLE is ignored) */
if (first) {
first = 0;
/* make exclusive-or pattern from polynomial (0xedb88320UL) */
poly = 0;
for (n = 0; n < (int)(sizeof(p)/sizeof(unsigned char)); n++)
poly |= (z_crc_t)1 << (31 - p[n]);
/* generate a crc for every 8-bit value */
for (n = 0; n < 256; n++) {
c = (z_crc_t)n;
for (k = 0; k < 8; k++)
c = c & 1 ? poly ^ (c >> 1) : c >> 1;
crc_table[0][n] = c;
}
#ifdef BYFOUR
/* generate crc for each value followed by one, two, and three zeros,
and then the byte reversal of those as well as the first table */
for (n = 0; n < 256; n++) {
c = crc_table[0][n];
crc_table[4][n] = ZSWAP32(c);
for (k = 1; k < 4; k++) {
c = crc_table[0][c & 0xff] ^ (c >> 8);
crc_table[k][n] = c;
crc_table[k + 4][n] = ZSWAP32(c);
}
}
#endif /* BYFOUR */
crc_table_empty = 0;
}
else { /* not first */
/* wait for the other guy to finish (not efficient, but rare) */
while (crc_table_empty)
;
}
#ifdef MAKECRCH
/* write out CRC tables to dcrc32.h */
{
FILE *out;
out = NCfopen("dcrc32.h", "w");
if (out == NULL) return;
fprintf(out, "/* dcrc32.h -- tables for rapid CRC calculation\n");
fprintf(out, " * Generated automatically by dcrc32.c\n */\n\n");
fprintf(out, "local const z_crc_t FAR ");
fprintf(out, "crc_table[TBLS][256] =\n{\n {\n");
write_table(out, crc_table[0]);
# ifdef BYFOUR
fprintf(out, "#ifdef BYFOUR\n");
for (k = 1; k < 8; k++) {
fprintf(out, " },\n {\n");
write_table(out, crc_table[k]);
}
fprintf(out, "#endif\n");
# endif /* BYFOUR */
fprintf(out, " }\n};\n");
fclose(out);
}
#endif /* MAKECRCH */
}
#ifdef MAKECRCH
local void write_table(out, table)
FILE *out;
const z_crc_t FAR *table;
{
int n;
for (n = 0; n < 256; n++)
fprintf(out, "%s0x%08lxUL%s", n % 5 ? "" : " ",
(unsigned long)(table[n]),
n == 255 ? "\n" : (n % 5 == 4 ? ",\n" : ", "));
}
#endif /* MAKECRCH */
#else /* !DYNAMIC_CRC_TABLE */
/* ========================================================================
* Tables of CRC-32s of all single-byte values, made by make_crc_table().
*/
#include "dcrc32.h"
#endif /* DYNAMIC_CRC_TABLE */
/* =========================================================================
* This function can be used by asm versions of crc32()
*/
#if 0 /* Unused */
local const z_crc_t FAR * ZEXPORT get_crc_table()
{
#ifdef DYNAMIC_CRC_TABLE
if (crc_table_empty)
make_crc_table();
#endif /* DYNAMIC_CRC_TABLE */
return (const z_crc_t FAR *)crc_table;
}
#endif
/* ========================================================================= */
#define DO1 crc = crc_table[0][((int)crc ^ (*buf++)) & 0xff] ^ (crc >> 8)
#define DO8 DO1; DO1; DO1; DO1; DO1; DO1; DO1; DO1
/* ========================================================================= */
local unsigned long ZEXPORT crc32_z(crc, buf, len)
unsigned long crc;
const unsigned char FAR *buf;
z_size_t len;
{
if (buf == Z_NULL) return 0UL;
#ifdef DYNAMIC_CRC_TABLE
if (crc_table_empty)
make_crc_table();
#endif /* DYNAMIC_CRC_TABLE */
#ifdef BYFOUR
if (sizeof(void *) == sizeof(ptrdiff_t)) {
z_crc_t endian;
endian = 1;
if (*((unsigned char *)(&endian)))
return crc32_little(crc, buf, len);
else
return crc32_big(crc, buf, len);
}
#endif /* BYFOUR */
crc = crc ^ 0xffffffffUL;
while (len >= 8) {
DO8;
len -= 8;
}
if (len) do {
DO1;
} while (--len);
return crc ^ 0xffffffffUL;
}
/* ========================================================================= */
EXTERNL unsigned int ZEXPORT
NC_crc32(unsigned int crc, const void* buf, unsigned int len)
{
unsigned long value = (unsigned long)crc;
unsigned char* cbuf = (unsigned char*)buf;
value = crc32_z(value, cbuf, len);
return (unsigned int)(value & 0xFFFFFFFF); /* in case |long| is 64 bits */
}
#ifdef BYFOUR
/*
This BYFOUR code accesses the passed unsigned char * buffer with a 32-bit
integer pointer type. This violates the strict aliasing rule, where a
compiler can assume, for optimization purposes, that two pointers to
fundamentally different types won't ever point to the same memory. This can
manifest as a problem only if one of the pointers is written to. This code
only reads from those pointers. So long as this code remains isolated in
this compilation unit, there won't be a problem. For this reason, this code
should not be copied and pasted into a compilation unit in which other code
writes to the buffer that is passed to these routines.
*/
/* ========================================================================= */
#define DOLIT4 c ^= *buf4++; \
c = crc_table[3][c & 0xff] ^ crc_table[2][(c >> 8) & 0xff] ^ \
crc_table[1][(c >> 16) & 0xff] ^ crc_table[0][c >> 24]
#define DOLIT32 DOLIT4; DOLIT4; DOLIT4; DOLIT4; DOLIT4; DOLIT4; DOLIT4; DOLIT4
/* ========================================================================= */
local unsigned long crc32_little(crc, buf, len)
unsigned long crc;
const unsigned char FAR *buf;
z_size_t len;
{
register z_crc_t c;
register const z_crc_t FAR *buf4;
c = (z_crc_t)crc;
c = ~c;
while (len && ((ptrdiff_t)buf & 3)) {
c = crc_table[0][(c ^ *buf++) & 0xff] ^ (c >> 8);
len--;
}
buf4 = (const z_crc_t FAR *)(const void FAR *)buf;
while (len >= 32) {
DOLIT32;
len -= 32;
}
while (len >= 4) {
DOLIT4;
len -= 4;
}
buf = (const unsigned char FAR *)buf4;
if (len) do {
c = crc_table[0][(c ^ *buf++) & 0xff] ^ (c >> 8);
} while (--len);
c = ~c;
return (unsigned long)c;
}
/* ========================================================================= */
#define DOBIG4 c ^= *buf4++; \
c = crc_table[4][c & 0xff] ^ crc_table[5][(c >> 8) & 0xff] ^ \
crc_table[6][(c >> 16) & 0xff] ^ crc_table[7][c >> 24]
#define DOBIG32 DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4
/* ========================================================================= */
local unsigned long crc32_big(crc, buf, len)
unsigned long crc;
const unsigned char FAR *buf;
z_size_t len;
{
register z_crc_t c;
register const z_crc_t FAR *buf4;
c = ZSWAP32((z_crc_t)crc);
c = ~c;
while (len && ((ptrdiff_t)buf & 3)) {
c = crc_table[4][(c >> 24) ^ *buf++] ^ (c << 8);
len--;
}
buf4 = (const z_crc_t FAR *)(const void FAR *)buf;
while (len >= 32) {
DOBIG32;
len -= 32;
}
while (len >= 4) {
DOBIG4;
len -= 4;
}
buf = (const unsigned char FAR *)buf4;
if (len) do {
c = crc_table[4][(c >> 24) ^ *buf++] ^ (c << 8);
} while (--len);
c = ~c;
return (unsigned long)(ZSWAP32(c));
}
#endif /* BYFOUR */
#define GF2_DIM 32 /* dimension of GF(2) vectors (length of CRC) */
/* ========================================================================= */
#if 0 /* Unused */
local unsigned long gf2_matrix_times(mat, vec)
unsigned long *mat;
unsigned long vec;
{
unsigned long sum;
sum = 0;
while (vec) {
if (vec & 1)
sum ^= *mat;
vec >>= 1;
mat++;
}
return sum;
}
/* ========================================================================= */
local void gf2_matrix_square(square, mat)
unsigned long *square;
unsigned long *mat;
{
int n;
for (n = 0; n < GF2_DIM; n++)
square[n] = gf2_matrix_times(mat, mat[n]);
}
/* ========================================================================= */
local uLong crc32_combine_(crc1, crc2, len2)
uLong crc1;
uLong crc2;
z_off64_t len2;
{
int n;
unsigned long row;
unsigned long even[GF2_DIM]; /* even-power-of-two zeros operator */
unsigned long odd[GF2_DIM]; /* odd-power-of-two zeros operator */
/* degenerate case (also disallow negative lengths) */
if (len2 <= 0)
return crc1;
/* put operator for one zero bit in odd */
odd[0] = 0xedb88320UL; /* CRC-32 polynomial */
row = 1;
for (n = 1; n < GF2_DIM; n++) {
odd[n] = row;
row <<= 1;
}
/* put operator for two zero bits in even */
gf2_matrix_square(even, odd);
/* put operator for four zero bits in odd */
gf2_matrix_square(odd, even);
/* apply len2 zeros to crc1 (first square will put the operator for one
zero byte, eight zero bits, in even) */
do {
/* apply zeros operator for this bit of len2 */
gf2_matrix_square(even, odd);
if (len2 & 1)
crc1 = gf2_matrix_times(even, crc1);
len2 >>= 1;
/* if no more bits set, then done */
if (len2 == 0)
break;
/* another iteration of the loop with odd and even swapped */
gf2_matrix_square(odd, even);
if (len2 & 1)
crc1 = gf2_matrix_times(odd, crc1);
len2 >>= 1;
/* if no more bits set, then done */
} while (len2 != 0);
/* return combined crc */
crc1 ^= crc2;
return crc1;
}
/* ========================================================================= */
local uLong ZEXPORT crc32_combine(crc1, crc2, len2)
uLong crc1;
uLong crc2;
z_off_t len2;
{
return crc32_combine_(crc1, crc2, len2);
}
local uLong ZEXPORT crc32_combine64(crc1, crc2, len2)
uLong crc1;
uLong crc2;
z_off64_t len2;
{
return crc32_combine_(crc1, crc2, len2);
}
#endif