zstd/tests/datagencli.c

131 lines
4.4 KiB
C
Raw Normal View History

/*
* Copyright (c) 2015-present, Yann Collet, Facebook, Inc.
2016-08-30 10:04:33 -07:00
* All rights reserved.
*
* This source code is licensed under both the BSD-style license (found in the
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
* in the COPYING file in the root directory of this source tree).
* You may select, at your option, one of the above-listed licenses.
2016-08-30 10:04:33 -07:00
*/
2016-05-11 02:42:51 -07:00
/*-************************************
2016-09-15 08:00:02 -07:00
* Dependencies
**************************************/
2016-05-19 03:16:14 -07:00
#include "util.h" /* Compiler options */
#include <stdio.h> /* fprintf, stderr */
#include "datagen.h" /* RDG_generate */
2016-05-11 02:42:51 -07:00
/*-************************************
* Constants
**************************************/
#define KB *(1 <<10)
#define MB *(1 <<20)
#define GB *(1U<<30)
2016-07-28 10:55:09 -07:00
#define SIZE_DEFAULT ((64 KB) + 1)
#define SEED_DEFAULT 0
#define COMPRESSIBILITY_DEFAULT 50
2016-05-11 02:42:51 -07:00
/*-************************************
* Macros
**************************************/
#define DISPLAY(...) fprintf(stderr, __VA_ARGS__)
#define DISPLAYLEVEL(l, ...) if (displayLevel>=l) { DISPLAY(__VA_ARGS__); }
static unsigned displayLevel = 2;
2016-05-11 02:42:51 -07:00
/*-*******************************************************
* Command line
*********************************************************/
2016-05-11 02:42:51 -07:00
static int usage(const char* programName)
{
DISPLAY( "Compressible data generator\n");
DISPLAY( "Usage :\n");
DISPLAY( " %s [args]\n", programName);
DISPLAY( "\n");
DISPLAY( "Arguments :\n");
DISPLAY( " -g# : generate # data (default:%i)\n", SIZE_DEFAULT);
DISPLAY( " -s# : Select seed (default:%i)\n", SEED_DEFAULT);
2017-05-15 17:15:46 -07:00
DISPLAY( " -P# : Select compressibility in %% (default:%i%%)\n",
COMPRESSIBILITY_DEFAULT);
DISPLAY( " -h : display help and exit\n");
return 0;
}
2016-05-11 02:42:51 -07:00
int main(int argc, const char** argv)
{
2017-05-15 17:15:46 -07:00
unsigned probaU32 = COMPRESSIBILITY_DEFAULT;
2015-02-10 09:15:20 -08:00
double litProba = 0.0;
U64 size = SIZE_DEFAULT;
U32 seed = SEED_DEFAULT;
2016-07-28 10:55:09 -07:00
const char* const programName = argv[0];
2016-07-28 10:55:09 -07:00
int argNb;
2016-05-11 02:42:51 -07:00
for(argNb=1; argNb<argc; argNb++) {
const char* argument = argv[argNb];
if(!argument) continue; /* Protection if argument empty */
/* Handle commands. Aggregated commands are allowed */
2016-05-11 02:42:51 -07:00
if (*argument=='-') {
argument++;
2016-05-11 02:42:51 -07:00
while (*argument!=0) {
switch(*argument)
{
case 'h':
return usage(programName);
case 'g':
argument++;
size=0;
while ((*argument>='0') && (*argument<='9'))
2016-05-11 02:42:51 -07:00
size *= 10, size += *argument++ - '0';
if (*argument=='K') { size <<= 10; argument++; }
if (*argument=='M') { size <<= 20; argument++; }
if (*argument=='G') { size <<= 30; argument++; }
if (*argument=='B') { argument++; }
break;
case 's':
argument++;
seed=0;
while ((*argument>='0') && (*argument<='9'))
2016-05-11 02:42:51 -07:00
seed *= 10, seed += *argument++ - '0';
break;
case 'P':
argument++;
probaU32 = 0;
while ((*argument>='0') && (*argument<='9'))
2017-05-15 17:15:46 -07:00
probaU32 *= 10, probaU32 += *argument++ - '0';
if (probaU32>100) probaU32 = 100;
break;
case 'L': /* hidden argument : Literal distribution probability */
argument++;
litProba=0.;
while ((*argument>='0') && (*argument<='9'))
2016-05-11 02:42:51 -07:00
litProba *= 10, litProba += *argument++ - '0';
if (litProba>100.) litProba=100.;
litProba /= 100.;
break;
case 'v':
displayLevel = 4;
argument++;
break;
default:
return usage(programName);
}
2016-05-11 02:42:51 -07:00
} } } /* for(argNb=1; argNb<argc; argNb++) */
2017-05-15 17:15:46 -07:00
DISPLAYLEVEL(4, "Compressible data Generator \n");
if (probaU32!=COMPRESSIBILITY_DEFAULT)
DISPLAYLEVEL(3, "Compressibility : %i%%\n", probaU32);
fix confusion between unsigned <-> U32 as suggested in #1441. generally U32 and unsigned are the same thing, except when they are not ... case : 32-bit compilation for MIPS (uint32_t == unsigned long) A vast majority of transformation consists in transforming U32 into unsigned. In rare cases, it's the other way around (typically for internal code, such as seeds). Among a few issues this patches solves : - some parameters were declared with type `unsigned` in *.h, but with type `U32` in their implementation *.c . - some parameters have type unsigned*, but the caller user a pointer to U32 instead. These fixes are useful. However, the bulk of changes is about %u formating, which requires unsigned type, but generally receives U32 values instead, often just for brevity (U32 is shorter than unsigned). These changes are generally minor, or even annoying. As a consequence, the amount of code changed is larger than I would expect for such a patch. Testing is also a pain : it requires manually modifying `mem.h`, in order to lie about `U32` and force it to be an `unsigned long` typically. On a 64-bit system, this will break the equivalence unsigned == U32. Unfortunately, it will also break a few static_assert(), controlling structure sizes. So it also requires modifying `debug.h` to make `static_assert()` a noop. And then reverting these changes. So it's inconvenient, and as a consequence, this property is currently not checked during CI tests. Therefore, these problems can emerge again in the future. I wonder if it is worth ensuring proper distinction of U32 != unsigned in CI tests. It's another restriction for coding, adding more frustration during merge tests, since most platforms don't need this distinction (hence contributor will not see it), and while this can matter in theory, the number of platforms impacted seems minimal. Thoughts ?
2018-12-21 16:19:44 -08:00
DISPLAYLEVEL(3, "Seed = %u \n", (unsigned)seed);
2017-05-15 17:15:46 -07:00
RDG_genStdout(size, (double)probaU32/100, litProba, seed);
DISPLAYLEVEL(1, "\n");
return 0;
}