xdiff: load full words in the inner loop of xdl_hash_record

[thirdparty/git.git] / xdiff / xutils.c

/*
 *  LibXDiff by Davide Libenzi ( File Differential Library )
 *  Copyright (C) 2003	Davide Libenzi
 *
 *  This library is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU Lesser General Public
 *  License as published by the Free Software Foundation; either
 *  version 2.1 of the License, or (at your option) any later version.
 *
 *  This library is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 *  Lesser General Public License for more details.
 *
 *  You should have received a copy of the GNU Lesser General Public
 *  License along with this library; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 *  Davide Libenzi <davidel@xmailserver.org>
 *
 */

#include <limits.h>
#include <assert.h>
#include "xinclude.h"




long xdl_bogosqrt(long n) {
	long i;

	/*
	 * Classical integer square root approximation using shifts.
	 */
	for (i = 1; n > 0; n >>= 2)
		i <<= 1;

	return i;
}


int xdl_emit_diffrec(char const *rec, long size, char const *pre, long psize,
		     xdemitcb_t *ecb) {
	int i = 2;
	mmbuffer_t mb[3];

	mb[0].ptr = (char *) pre;
	mb[0].size = psize;
	mb[1].ptr = (char *) rec;
	mb[1].size = size;
	if (size > 0 && rec[size - 1] != '\n') {
		mb[2].ptr = (char *) "\n\\ No newline at end of file\n";
		mb[2].size = strlen(mb[2].ptr);
		i++;
	}
	if (ecb->outf(ecb->priv, mb, i) < 0) {

		return -1;
	}

	return 0;
}

void *xdl_mmfile_first(mmfile_t *mmf, long *size)
{
	*size = mmf->size;
	return mmf->ptr;
}


long xdl_mmfile_size(mmfile_t *mmf)
{
	return mmf->size;
}


int xdl_cha_init(chastore_t *cha, long isize, long icount) {

	cha->head = cha->tail = NULL;
	cha->isize = isize;
	cha->nsize = icount * isize;
	cha->ancur = cha->sncur = NULL;
	cha->scurr = 0;

	return 0;
}


void xdl_cha_free(chastore_t *cha) {
	chanode_t *cur, *tmp;

	for (cur = cha->head; (tmp = cur) != NULL;) {
		cur = cur->next;
		xdl_free(tmp);
	}
}


void *xdl_cha_alloc(chastore_t *cha) {
	chanode_t *ancur;
	void *data;

	if (!(ancur = cha->ancur) || ancur->icurr == cha->nsize) {
		if (!(ancur = (chanode_t *) xdl_malloc(sizeof(chanode_t) + cha->nsize))) {

			return NULL;
		}
		ancur->icurr = 0;
		ancur->next = NULL;
		if (cha->tail)
			cha->tail->next = ancur;
		if (!cha->head)
			cha->head = ancur;
		cha->tail = ancur;
		cha->ancur = ancur;
	}

	data = (char *) ancur + sizeof(chanode_t) + ancur->icurr;
	ancur->icurr += cha->isize;

	return data;
}


void *xdl_cha_first(chastore_t *cha) {
	chanode_t *sncur;

	if (!(cha->sncur = sncur = cha->head))
		return NULL;

	cha->scurr = 0;

	return (char *) sncur + sizeof(chanode_t) + cha->scurr;
}


void *xdl_cha_next(chastore_t *cha) {
	chanode_t *sncur;

	if (!(sncur = cha->sncur))
		return NULL;
	cha->scurr += cha->isize;
	if (cha->scurr == sncur->icurr) {
		if (!(sncur = cha->sncur = sncur->next))
			return NULL;
		cha->scurr = 0;
	}

	return (char *) sncur + sizeof(chanode_t) + cha->scurr;
}


long xdl_guess_lines(mmfile_t *mf, long sample) {
	long nl = 0, size, tsize = 0;
	char const *data, *cur, *top;

	if ((cur = data = xdl_mmfile_first(mf, &size)) != NULL) {
		for (top = data + size; nl < sample && cur < top; ) {
			nl++;
			if (!(cur = memchr(cur, '\n', top - cur)))
				cur = top;
			else
				cur++;
		}
		tsize += (long) (cur - data);
	}

	if (nl && tsize)
		nl = xdl_mmfile_size(mf) / (tsize / nl);

	return nl + 1;
}

int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags)
{
	int i1, i2;

	if (s1 == s2 && !memcmp(l1, l2, s1))
		return 1;
	if (!(flags & XDF_WHITESPACE_FLAGS))
		return 0;

	i1 = 0;
	i2 = 0;

	/*
	 * -w matches everything that matches with -b, and -b in turn
	 * matches everything that matches with --ignore-space-at-eol.
	 *
	 * Each flavor of ignoring needs different logic to skip whitespaces
	 * while we have both sides to compare.
	 */
	if (flags & XDF_IGNORE_WHITESPACE) {
		goto skip_ws;
		while (i1 < s1 && i2 < s2) {
			if (l1[i1++] != l2[i2++])
				return 0;
		skip_ws:
			while (i1 < s1 && XDL_ISSPACE(l1[i1]))
				i1++;
			while (i2 < s2 && XDL_ISSPACE(l2[i2]))
				i2++;
		}
	} else if (flags & XDF_IGNORE_WHITESPACE_CHANGE) {
		while (i1 < s1 && i2 < s2) {
			if (XDL_ISSPACE(l1[i1]) && XDL_ISSPACE(l2[i2])) {
				/* Skip matching spaces and try again */
				while (i1 < s1 && XDL_ISSPACE(l1[i1]))
					i1++;
				while (i2 < s2 && XDL_ISSPACE(l2[i2]))
					i2++;
				continue;
			}
			if (l1[i1++] != l2[i2++])
				return 0;
		}
	} else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL) {
		while (i1 < s1 && i2 < s2 && l1[i1++] == l2[i2++])
			; /* keep going */
	}

	/*
	 * After running out of one side, the remaining side must have
	 * nothing but whitespace for the lines to match.  Note that
	 * ignore-whitespace-at-eol case may break out of the loop
	 * while there still are characters remaining on both lines.
	 */
	if (i1 < s1) {
		while (i1 < s1 && XDL_ISSPACE(l1[i1]))
			i1++;
		if (s1 != i1)
			return 0;
	}
	if (i2 < s2) {
		while (i2 < s2 && XDL_ISSPACE(l2[i2]))
			i2++;
		return (s2 == i2);
	}
	return 1;
}

static unsigned long xdl_hash_record_with_whitespace(char const **data,
		char const *top, long flags) {
	unsigned long ha = 5381;
	char const *ptr = *data;

	for (; ptr < top && *ptr != '\n'; ptr++) {
		if (XDL_ISSPACE(*ptr)) {
			const char *ptr2 = ptr;
			int at_eol;
			while (ptr + 1 < top && XDL_ISSPACE(ptr[1])
					&& ptr[1] != '\n')
				ptr++;
			at_eol = (top <= ptr + 1 || ptr[1] == '\n');
			if (flags & XDF_IGNORE_WHITESPACE)
				; /* already handled */
			else if (flags & XDF_IGNORE_WHITESPACE_CHANGE
				 && !at_eol) {
				ha += (ha << 5);
				ha ^= (unsigned long) ' ';
			}
			else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL
				 && !at_eol) {
				while (ptr2 != ptr + 1) {
					ha += (ha << 5);
					ha ^= (unsigned long) *ptr2;
					ptr2++;
				}
			}
			continue;
		}
		ha += (ha << 5);
		ha ^= (unsigned long) *ptr;
	}
	*data = ptr < top ? ptr + 1: ptr;

	return ha;
}

#ifdef XDL_FAST_HASH

#define ONEBYTES	0x0101010101010101ul
#define NEWLINEBYTES	0x0a0a0a0a0a0a0a0aul
#define HIGHBITS	0x8080808080808080ul

/* Return the high bit set in the first byte that is a zero */
static inline unsigned long has_zero(unsigned long a)
{
	return ((a - ONEBYTES) & ~a) & HIGHBITS;
}

#if __WORDSIZE == 64

/*
 * Jan Achrenius on G+: microoptimized version of
 * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
 * that works for the bytemasks without having to
 * mask them first.
 */
static inline long count_masked_bytes(unsigned long mask)
{
	return mask * 0x0001020304050608 >> 56;
}

#else	/* 32-bit case */

/* Modified Carl Chatfield G+ version for 32-bit */
static inline long count_masked_bytes(long mask)
{
	/*
	 * (a) gives us
	 *   -1 (0, ff), 0 (ffff) or 1 (ffffff)
	 * (b) gives us
	 *   0 for 0, 1 for (ff ffff ffffff)
	 * (a+b+1) gives us
	 *   correct 0-3 bytemask count result
	 */
	long a = (mask - 256) >> 23;
	long b = mask & 1;
	return a + b + 1;
}

#endif

unsigned long xdl_hash_record(char const **data, char const *top, long flags)
{
	unsigned long hash = 5381;
	unsigned long a = 0, mask = 0;
	char const *ptr = *data;
	char const *end = top - sizeof(unsigned long) + 1;

	if (flags & XDF_WHITESPACE_FLAGS)
		return xdl_hash_record_with_whitespace(data, top, flags);

	ptr -= sizeof(unsigned long);
	do {
		hash += hash << 5;
		hash ^= a;
		ptr += sizeof(unsigned long);
		if (ptr >= end)
			break;
		a = *(unsigned long *)ptr;
		/* Do we have any '\n' bytes in this word? */
		mask = has_zero(a ^ NEWLINEBYTES);
	} while (!mask);

	if (ptr >= end) {
		/*
		 * There is only a partial word left at the end of the
		 * buffer. Because we may work with a memory mapping,
		 * we have to grab the rest byte by byte instead of
		 * blindly reading it.
		 *
		 * To avoid problems with masking in a signed value,
		 * we use an unsigned char here.
		 */
		const char *p;
		for (p = top - 1; p >= ptr; p--)
			a = (a << 8) + *((const unsigned char *)p);
		mask = has_zero(a ^ NEWLINEBYTES);
		if (!mask)
			/*
			 * No '\n' found in the partial word.  Make a
			 * mask that matches what we read.
			 */
			mask = 1UL << (8 * (top - ptr) + 7);
	}

	/* The mask *below* the first high bit set */
	mask = (mask - 1) & ~mask;
	mask >>= 7;
	hash += hash << 5;
	hash ^= a & mask;

	/* Advance past the last (possibly partial) word */
	ptr += count_masked_bytes(mask);

	if (ptr < top) {
		assert(*ptr == '\n');
		ptr++;
	}

	*data = ptr;

	return hash;
}

#else /* XDL_FAST_HASH */

unsigned long xdl_hash_record(char const **data, char const *top, long flags) {
	unsigned long ha = 5381;
	char const *ptr = *data;

	if (flags & XDF_WHITESPACE_FLAGS)
		return xdl_hash_record_with_whitespace(data, top, flags);

	for (; ptr < top && *ptr != '\n'; ptr++) {
		ha += (ha << 5);
		ha ^= (unsigned long) *ptr;
	}
	*data = ptr < top ? ptr + 1: ptr;

	return ha;
}

#endif /* XDL_FAST_HASH */

unsigned int xdl_hashbits(unsigned int size) {
	unsigned int val = 1, bits = 0;

	for (; val < size && bits < CHAR_BIT * sizeof(unsigned int); val <<= 1, bits++);
	return bits ? bits: 1;
}


int xdl_num_out(char *out, long val) {
	char *ptr, *str = out;
	char buf[32];

	ptr = buf + sizeof(buf) - 1;
	*ptr = '\0';
	if (val < 0) {
		*--ptr = '-';
		val = -val;
	}
	for (; val && ptr > buf; val /= 10)
		*--ptr = "0123456789"[val % 10];
	if (*ptr)
		for (; *ptr; ptr++, str++)
			*str = *ptr;
	else
		*str++ = '0';
	*str = '\0';

	return str - out;
}


long xdl_atol(char const *str, char const **next) {
	long val, base;
	char const *top;

	for (top = str; XDL_ISDIGIT(*top); top++);
	if (next)
		*next = top;
	for (val = 0, base = 1, top--; top >= str; top--, base *= 10)
		val += base * (long)(*top - '0');
	return val;
}


int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2,
		      const char *func, long funclen, xdemitcb_t *ecb) {
	int nb = 0;
	mmbuffer_t mb;
	char buf[128];

	memcpy(buf, "@@ -", 4);
	nb += 4;

	nb += xdl_num_out(buf + nb, c1 ? s1: s1 - 1);

	if (c1 != 1) {
		memcpy(buf + nb, ",", 1);
		nb += 1;

		nb += xdl_num_out(buf + nb, c1);
	}

	memcpy(buf + nb, " +", 2);
	nb += 2;

	nb += xdl_num_out(buf + nb, c2 ? s2: s2 - 1);

	if (c2 != 1) {
		memcpy(buf + nb, ",", 1);
		nb += 1;

		nb += xdl_num_out(buf + nb, c2);
	}

	memcpy(buf + nb, " @@", 3);
	nb += 3;
	if (func && funclen) {
		buf[nb++] = ' ';
		if (funclen > sizeof(buf) - nb - 1)
			funclen = sizeof(buf) - nb - 1;
		memcpy(buf + nb, func, funclen);
		nb += funclen;
	}
	buf[nb++] = '\n';

	mb.ptr = buf;
	mb.size = nb;
	if (ecb->outf(ecb->priv, &mb, 1) < 0)
		return -1;

	return 0;
}

int xdl_fall_back_diff(xdfenv_t *diff_env, xpparam_t const *xpp,
		int line1, int count1, int line2, int count2)
{
	/*
	 * This probably does not work outside Git, since
	 * we have a very simple mmfile structure.
	 *
	 * Note: ideally, we would reuse the prepared environment, but
	 * the libxdiff interface does not (yet) allow for diffing only
	 * ranges of lines instead of the whole files.
	 */
	mmfile_t subfile1, subfile2;
	xdfenv_t env;

	subfile1.ptr = (char *)diff_env->xdf1.recs[line1 - 1]->ptr;
	subfile1.size = diff_env->xdf1.recs[line1 + count1 - 2]->ptr +
		diff_env->xdf1.recs[line1 + count1 - 2]->size - subfile1.ptr;
	subfile2.ptr = (char *)diff_env->xdf2.recs[line2 - 1]->ptr;
	subfile2.size = diff_env->xdf2.recs[line2 + count2 - 2]->ptr +
		diff_env->xdf2.recs[line2 + count2 - 2]->size - subfile2.ptr;
	if (xdl_do_diff(&subfile1, &subfile2, xpp, &env) < 0)
		return -1;

	memcpy(diff_env->xdf1.rchg + line1 - 1, env.xdf1.rchg, count1);
	memcpy(diff_env->xdf2.rchg + line2 - 1, env.xdf2.rchg, count2);

	xdl_free_env(&env);

	return 0;
}