view mercurial/bitmanipulation.h @ 48178:f12a19d03d2c

fix: reduce number of tool executions

By grouping together (path, ctx) pairs according to the inputs they would
provide to fixer tools, we can deduplicate executions of fixer tools to
significantly reduce the amount of time spent running slow tools.

This change does not handle clean files in the working copy, which could still
be deduplicated against the files in the checked out commit. It's a little
harder to do that because the filerev is not available in the workingfilectx
(and it doesn't exist for added files).

Anecdotally, this change makes some real uses cases at Google 10x faster. I
think we were originally hesitant to do this because the benefits weren't
obvious, and implementing it efficiently is kind of tricky. If we simply
memoized the formatter execution function, we would be keeping tons of file
content in memory.

Also included is a regression test for a corner case that I broke with my first
attempt at optimizing this code.

Differential Revision: https://phab.mercurial-scm.org/D11280

#ifndef _HG_BITMANIPULATION_H_
#define _HG_BITMANIPULATION_H_

#include <string.h>

#include "compat.h"

/* Reads a 64 bit integer from big-endian bytes. Assumes that the data is long
 enough */
static inline uint64_t getbe64(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((((uint64_t)d[0]) << 56) | (((uint64_t)d[1]) << 48) |
	        (((uint64_t)d[2]) << 40) | (((uint64_t)d[3]) << 32) |
	        (((uint64_t)d[4]) << 24) | (((uint64_t)d[5]) << 16) |
	        (((uint64_t)d[6]) << 8) | (d[7]));
}

static inline uint32_t getbe32(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((((uint32_t)d[0]) << 24) | (((uint32_t)d[1]) << 16) |
	        (((uint32_t)d[2]) << 8) | (d[3]));
}

static inline int16_t getbeint16(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((d[0] << 8) | (d[1]));
}

static inline uint16_t getbeuint16(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((d[0] << 8) | (d[1]));
}

/* Writes a 64 bit integer to bytes in a big-endian format.
 Assumes that the buffer is long enough */
static inline void putbe64(uint64_t x, char *c)
{
	c[0] = (x >> 56) & 0xff;
	c[1] = (x >> 48) & 0xff;
	c[2] = (x >> 40) & 0xff;
	c[3] = (x >> 32) & 0xff;
	c[4] = (x >> 24) & 0xff;
	c[5] = (x >> 16) & 0xff;
	c[6] = (x >> 8) & 0xff;
	c[7] = (x)&0xff;
}

static inline void putbe32(uint32_t x, char *c)
{
	c[0] = (x >> 24) & 0xff;
	c[1] = (x >> 16) & 0xff;
	c[2] = (x >> 8) & 0xff;
	c[3] = (x)&0xff;
}

static inline double getbefloat64(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;
	double ret;
	int i;
	uint64_t t = 0;
	for (i = 0; i < 8; i++) {
		t = (t << 8) + d[i];
	}
	memcpy(&ret, &t, sizeof(t));
	return ret;
}

#endif