xdiff: replace {unsigned ,}long with {u,}int64_t

MSVC treats "long" as 4-byte. That could cause overflows since the xdiff
code uses "long" in places where "size_t" or "ssize_t" should be used.
Let's use explicit 8 byte integers to avoid

FWIW git avoids that overflow by limiting diff size to 1GB [1]. After
examining the code, I think the remaining risk (the use of "int") is low
since "int" is only used for return values and hash table size. Although a
wrong hash table size would not affect the correctness of the code, but that
could make the code extremely slow. The next patch will change hash table
size to 8-byte integer so the 1GB limit is unlikely needed.

This patch was done by using `sed`.

[1]: https://github.com/git/git/commit/dcd1742e56ebb944c4ff62346da4548e1e3be67

Differential Revision: https://phab.mercurial-scm.org/D2762

mercurial/thirdparty/xdiff/xdiff.h

@@ -1,83 +1,83 b''
 /*
  *  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, see
  *  <http://www.gnu.org/licenses/>.
  *
  *  Davide Libenzi <[e-mail]>
  *
  */
 
 #if !defined(XDIFF_H)
 #define XDIFF_H
 
 #ifdef __cplusplus
 extern "C" {
 #endif /* #ifdef __cplusplus */
 
 #include <stddef.h> /* size_t */
 
 /* xpparm_t.flags */
 #define XDF_NEED_MINIMAL (1 << 0)
 
 #define XDF_INDENT_HEURISTIC (1 << 23)
 
 /* emit bdiff-style "matched" (a1, a2, b1, b2) hunks instead of "different"
  * (a1, a2 - a1, b1, b2 - b1) hunks */
 #define XDL_EMIT_BDIFFHUNK (1 << 4)
 
 typedef struct s_mmfile {
 	char *ptr;
-	long size;
+	int64_t size;
 } mmfile_t;
 
 typedef struct s_mmbuffer {
 	char *ptr;
-	long size;
+	int64_t size;
 } mmbuffer_t;
 
 typedef struct s_xpparam {
-	unsigned long flags;
+	uint64_t flags;
 } xpparam_t;
 
 typedef struct s_xdemitcb {
 	void *priv;
 } xdemitcb_t;
 
-typedef int (*xdl_emit_hunk_consume_func_t)(long start_a, long count_a,
-					    long start_b, long count_b,
+typedef int (*xdl_emit_hunk_consume_func_t)(int64_t start_a, int64_t count_a,
+					    int64_t start_b, int64_t count_b,
 					    void *cb_data);
 
 typedef struct s_xdemitconf {
-	unsigned long flags;
+	uint64_t flags;
 	xdl_emit_hunk_consume_func_t hunk_func;
 } xdemitconf_t;
 
 
 #define xdl_malloc(x) malloc(x)
 #define xdl_free(ptr) free(ptr)
 #define xdl_realloc(ptr,x) realloc(ptr,x)
 
-void *xdl_mmfile_first(mmfile_t *mmf, long *size);
-long xdl_mmfile_size(mmfile_t *mmf);
+void *xdl_mmfile_first(mmfile_t *mmf, int64_t *size);
+int64_t xdl_mmfile_size(mmfile_t *mmf);
 
 int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 	     xdemitconf_t const *xecfg, xdemitcb_t *ecb);
 
 #ifdef __cplusplus
 }
 #endif /* #ifdef __cplusplus */
 
 #endif /* #if !defined(XDIFF_H) */

mercurial/thirdparty/xdiff/xdiffi.c

@@ -1,1133 +1,1133 b''
 /*
  *  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, see
  *  <http://www.gnu.org/licenses/>.
  *
  *  Davide Libenzi <[e-mail]>
  *
  */
 
 #include "xinclude.h"
 
 
 
 #define XDL_MAX_COST_MIN 256
 #define XDL_HEUR_MIN_COST 256
 #define XDL_LINE_MAX (long)((1UL << (CHAR_BIT * sizeof(long) - 1)) - 1)
 #define XDL_SNAKE_CNT 20
 #define XDL_K_HEUR 4
 
 /* VC 2008 doesn't know about the inline keyword. */
 #if defined(_MSC_VER)
 #define inline __forceinline
 #endif
 
 
 typedef struct s_xdpsplit {
-	long i1, i2;
+	int64_t i1, i2;
 	int min_lo, min_hi;
 } xdpsplit_t;
 
 
 
 
-static long xdl_split(unsigned long const *ha1, long off1, long lim1,
-		      unsigned long const *ha2, long off2, long lim2,
-		      long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl,
+static int64_t xdl_split(uint64_t const *ha1, int64_t off1, int64_t lim1,
+		      uint64_t const *ha2, int64_t off2, int64_t lim2,
+		      int64_t *kvdf, int64_t *kvdb, int need_min, xdpsplit_t *spl,
 		      xdalgoenv_t *xenv);
-static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, long chg2);
+static xdchange_t *xdl_add_change(xdchange_t *xscr, int64_t i1, int64_t i2, int64_t chg1, int64_t chg2);
 
 
 
 
 
 /*
  * See "An O(ND) Difference Algorithm and its Variations", by Eugene Myers.
  * Basically considers a "box" (off1, off2, lim1, lim2) and scan from both
  * the forward diagonal starting from (off1, off2) and the backward diagonal
  * starting from (lim1, lim2). If the K values on the same diagonal crosses
  * returns the furthest point of reach. We might end up having to expensive
  * cases using this algorithm is full, so a little bit of heuristic is needed
  * to cut the search and to return a suboptimal point.
  */
-static long xdl_split(unsigned long const *ha1, long off1, long lim1,
-		      unsigned long const *ha2, long off2, long lim2,
-		      long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl,
+static int64_t xdl_split(uint64_t const *ha1, int64_t off1, int64_t lim1,
+		      uint64_t const *ha2, int64_t off2, int64_t lim2,
+		      int64_t *kvdf, int64_t *kvdb, int need_min, xdpsplit_t *spl,
 		      xdalgoenv_t *xenv) {
-	long dmin = off1 - lim2, dmax = lim1 - off2;
-	long fmid = off1 - off2, bmid = lim1 - lim2;
-	long odd = (fmid - bmid) & 1;
-	long fmin = fmid, fmax = fmid;
-	long bmin = bmid, bmax = bmid;
-	long ec, d, i1, i2, prev1, best, dd, v, k;
+	int64_t dmin = off1 - lim2, dmax = lim1 - off2;
+	int64_t fmid = off1 - off2, bmid = lim1 - lim2;
+	int64_t odd = (fmid - bmid) & 1;
+	int64_t fmin = fmid, fmax = fmid;
+	int64_t bmin = bmid, bmax = bmid;
+	int64_t ec, d, i1, i2, prev1, best, dd, v, k;
 
 	/*
 	 * Set initial diagonal values for both forward and backward path.
 	 */
 	kvdf[fmid] = off1;
 	kvdb[bmid] = lim1;
 
 	for (ec = 1;; ec++) {
 		int got_snake = 0;
 
 		/*
 		 * We need to extent the diagonal "domain" by one. If the next
 		 * values exits the box boundaries we need to change it in the
 		 * opposite direction because (max - min) must be a power of two.
 		 * Also we initialize the external K value to -1 so that we can
 		 * avoid extra conditions check inside the core loop.
 		 */
 		if (fmin > dmin)
 			kvdf[--fmin - 1] = -1;
 		else
 			++fmin;
 		if (fmax < dmax)
 			kvdf[++fmax + 1] = -1;
 		else
 			--fmax;
 
 		for (d = fmax; d >= fmin; d -= 2) {
 			if (kvdf[d - 1] >= kvdf[d + 1])
 				i1 = kvdf[d - 1] + 1;
 			else
 				i1 = kvdf[d + 1];
 			prev1 = i1;
 			i2 = i1 - d;
 			for (; i1 < lim1 && i2 < lim2 && ha1[i1] == ha2[i2]; i1++, i2++);
 			if (i1 - prev1 > xenv->snake_cnt)
 				got_snake = 1;
 			kvdf[d] = i1;
 			if (odd && bmin <= d && d <= bmax && kvdb[d] <= i1) {
 				spl->i1 = i1;
 				spl->i2 = i2;
 				spl->min_lo = spl->min_hi = 1;
 				return ec;
 			}
 		}
 
 		/*
 		 * We need to extent the diagonal "domain" by one. If the next
 		 * values exits the box boundaries we need to change it in the
 		 * opposite direction because (max - min) must be a power of two.
 		 * Also we initialize the external K value to -1 so that we can
 		 * avoid extra conditions check inside the core loop.
 		 */
 		if (bmin > dmin)
 			kvdb[--bmin - 1] = XDL_LINE_MAX;
 		else
 			++bmin;
 		if (bmax < dmax)
 			kvdb[++bmax + 1] = XDL_LINE_MAX;
 		else
 			--bmax;
 
 		for (d = bmax; d >= bmin; d -= 2) {
 			if (kvdb[d - 1] < kvdb[d + 1])
 				i1 = kvdb[d - 1];
 			else
 				i1 = kvdb[d + 1] - 1;
 			prev1 = i1;
 			i2 = i1 - d;
 			for (; i1 > off1 && i2 > off2 && ha1[i1 - 1] == ha2[i2 - 1]; i1--, i2--);
 			if (prev1 - i1 > xenv->snake_cnt)
 				got_snake = 1;
 			kvdb[d] = i1;
 			if (!odd && fmin <= d && d <= fmax && i1 <= kvdf[d]) {
 				spl->i1 = i1;
 				spl->i2 = i2;
 				spl->min_lo = spl->min_hi = 1;
 				return ec;
 			}
 		}
 
 		if (need_min)
 			continue;
 
 		/*
 		 * If the edit cost is above the heuristic trigger and if
 		 * we got a good snake, we sample current diagonals to see
 		 * if some of the, have reached an "interesting" path. Our
 		 * measure is a function of the distance from the diagonal
 		 * corner (i1 + i2) penalized with the distance from the
 		 * mid diagonal itself. If this value is above the current
 		 * edit cost times a magic factor (XDL_K_HEUR) we consider
 		 * it interesting.
 		 */
 		if (got_snake && ec > xenv->heur_min) {
 			for (best = 0, d = fmax; d >= fmin; d -= 2) {
 				dd = d > fmid ? d - fmid: fmid - d;
 				i1 = kvdf[d];
 				i2 = i1 - d;
 				v = (i1 - off1) + (i2 - off2) - dd;
 
 				if (v > XDL_K_HEUR * ec && v > best &&
 				    off1 + xenv->snake_cnt <= i1 && i1 < lim1 &&
 				    off2 + xenv->snake_cnt <= i2 && i2 < lim2) {
 					for (k = 1; ha1[i1 - k] == ha2[i2 - k]; k++)
 						if (k == xenv->snake_cnt) {
 							best = v;
 							spl->i1 = i1;
 							spl->i2 = i2;
 							break;
 						}
 				}
 			}
 			if (best > 0) {
 				spl->min_lo = 1;
 				spl->min_hi = 0;
 				return ec;
 			}
 
 			for (best = 0, d = bmax; d >= bmin; d -= 2) {
 				dd = d > bmid ? d - bmid: bmid - d;
 				i1 = kvdb[d];
 				i2 = i1 - d;
 				v = (lim1 - i1) + (lim2 - i2) - dd;
 
 				if (v > XDL_K_HEUR * ec && v > best &&
 				    off1 < i1 && i1 <= lim1 - xenv->snake_cnt &&
 				    off2 < i2 && i2 <= lim2 - xenv->snake_cnt) {
 					for (k = 0; ha1[i1 + k] == ha2[i2 + k]; k++)
 						if (k == xenv->snake_cnt - 1) {
 							best = v;
 							spl->i1 = i1;
 							spl->i2 = i2;
 							break;
 						}
 				}
 			}
 			if (best > 0) {
 				spl->min_lo = 0;
 				spl->min_hi = 1;
 				return ec;
 			}
 		}
 
 		/*
 		 * Enough is enough. We spent too much time here and now we collect
 		 * the furthest reaching path using the (i1 + i2) measure.
 		 */
 		if (ec >= xenv->mxcost) {
-			long fbest, fbest1, bbest, bbest1;
+			int64_t fbest, fbest1, bbest, bbest1;
 
 			fbest = fbest1 = -1;
 			for (d = fmax; d >= fmin; d -= 2) {
 				i1 = XDL_MIN(kvdf[d], lim1);
 				i2 = i1 - d;
 				if (lim2 < i2)
 					i1 = lim2 + d, i2 = lim2;
 				if (fbest < i1 + i2) {
 					fbest = i1 + i2;
 					fbest1 = i1;
 				}
 			}
 
 			bbest = bbest1 = XDL_LINE_MAX;
 			for (d = bmax; d >= bmin; d -= 2) {
 				i1 = XDL_MAX(off1, kvdb[d]);
 				i2 = i1 - d;
 				if (i2 < off2)
 					i1 = off2 + d, i2 = off2;
 				if (i1 + i2 < bbest) {
 					bbest = i1 + i2;
 					bbest1 = i1;
 				}
 			}
 
 			if ((lim1 + lim2) - bbest < fbest - (off1 + off2)) {
 				spl->i1 = fbest1;
 				spl->i2 = fbest - fbest1;
 				spl->min_lo = 1;
 				spl->min_hi = 0;
 			} else {
 				spl->i1 = bbest1;
 				spl->i2 = bbest - bbest1;
 				spl->min_lo = 0;
 				spl->min_hi = 1;
 			}
 			return ec;
 		}
 	}
 }
 
 
 /*
  * Rule: "Divide et Impera". Recursively split the box in sub-boxes by calling
  * the box splitting function. Note that the real job (marking changed lines)
  * is done in the two boundary reaching checks.
  */
-int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1,
-		 diffdata_t *dd2, long off2, long lim2,
-		 long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv) {
-	unsigned long const *ha1 = dd1->ha, *ha2 = dd2->ha;
+int xdl_recs_cmp(diffdata_t *dd1, int64_t off1, int64_t lim1,
+		 diffdata_t *dd2, int64_t off2, int64_t lim2,
+		 int64_t *kvdf, int64_t *kvdb, int need_min, xdalgoenv_t *xenv) {
+	uint64_t const *ha1 = dd1->ha, *ha2 = dd2->ha;
 
 	/*
 	 * Shrink the box by walking through each diagonal snake (SW and NE).
 	 */
 	for (; off1 < lim1 && off2 < lim2 && ha1[off1] == ha2[off2]; off1++, off2++);
 	for (; off1 < lim1 && off2 < lim2 && ha1[lim1 - 1] == ha2[lim2 - 1]; lim1--, lim2--);
 
 	/*
 	 * If one dimension is empty, then all records on the other one must
 	 * be obviously changed.
 	 */
 	if (off1 == lim1) {
 		char *rchg2 = dd2->rchg;
-		long *rindex2 = dd2->rindex;
+		int64_t *rindex2 = dd2->rindex;
 
 		for (; off2 < lim2; off2++)
 			rchg2[rindex2[off2]] = 1;
 	} else if (off2 == lim2) {
 		char *rchg1 = dd1->rchg;
-		long *rindex1 = dd1->rindex;
+		int64_t *rindex1 = dd1->rindex;
 
 		for (; off1 < lim1; off1++)
 			rchg1[rindex1[off1]] = 1;
 	} else {
 		xdpsplit_t spl;
 		spl.i1 = spl.i2 = 0;
 
 		/*
 		 * Divide ...
 		 */
 		if (xdl_split(ha1, off1, lim1, ha2, off2, lim2, kvdf, kvdb,
 			      need_min, &spl, xenv) < 0) {
 
 			return -1;
 		}
 
 		/*
 		 * ... et Impera.
 		 */
 		if (xdl_recs_cmp(dd1, off1, spl.i1, dd2, off2, spl.i2,
 				 kvdf, kvdb, spl.min_lo, xenv) < 0 ||
 		    xdl_recs_cmp(dd1, spl.i1, lim1, dd2, spl.i2, lim2,
 				 kvdf, kvdb, spl.min_hi, xenv) < 0) {
 
 			return -1;
 		}
 	}
 
 	return 0;
 }
 
 
 int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 		xdfenv_t *xe) {
-	long ndiags;
-	long *kvd, *kvdf, *kvdb;
+	int64_t ndiags;
+	int64_t *kvd, *kvdf, *kvdb;
 	xdalgoenv_t xenv;
 	diffdata_t dd1, dd2;
 
 	if (xdl_prepare_env(mf1, mf2, xpp, xe) < 0) {
 
 		return -1;
 	}
 
 	/*
 	 * Allocate and setup K vectors to be used by the differential algorithm.
 	 * One is to store the forward path and one to store the backward path.
 	 */
 	ndiags = xe->xdf1.nreff + xe->xdf2.nreff + 3;
-	if (!(kvd = (long *) xdl_malloc((2 * ndiags + 2) * sizeof(long)))) {
+	if (!(kvd = (int64_t *) xdl_malloc((2 * ndiags + 2) * sizeof(long)))) {
 
 		xdl_free_env(xe);
 		return -1;
 	}
 	kvdf = kvd;
 	kvdb = kvdf + ndiags;
 	kvdf += xe->xdf2.nreff + 1;
 	kvdb += xe->xdf2.nreff + 1;
 
 	xenv.mxcost = xdl_bogosqrt(ndiags);
 	if (xenv.mxcost < XDL_MAX_COST_MIN)
 		xenv.mxcost = XDL_MAX_COST_MIN;
 	xenv.snake_cnt = XDL_SNAKE_CNT;
 	xenv.heur_min = XDL_HEUR_MIN_COST;
 
 	dd1.nrec = xe->xdf1.nreff;
 	dd1.ha = xe->xdf1.ha;
 	dd1.rchg = xe->xdf1.rchg;
 	dd1.rindex = xe->xdf1.rindex;
 	dd2.nrec = xe->xdf2.nreff;
 	dd2.ha = xe->xdf2.ha;
 	dd2.rchg = xe->xdf2.rchg;
 	dd2.rindex = xe->xdf2.rindex;
 
 	if (xdl_recs_cmp(&dd1, 0, dd1.nrec, &dd2, 0, dd2.nrec,
 			 kvdf, kvdb, (xpp->flags & XDF_NEED_MINIMAL) != 0, &xenv) < 0) {
 
 		xdl_free(kvd);
 		xdl_free_env(xe);
 		return -1;
 	}
 
 	xdl_free(kvd);
 
 	return 0;
 }
 
 
-static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, long chg2) {
+static xdchange_t *xdl_add_change(xdchange_t *xscr, int64_t i1, int64_t i2, int64_t chg1, int64_t chg2) {
 	xdchange_t *xch;
 
 	if (!(xch = (xdchange_t *) xdl_malloc(sizeof(xdchange_t))))
 		return NULL;
 
 	xch->next = xscr;
 	xch->i1 = i1;
 	xch->i2 = i2;
 	xch->chg1 = chg1;
 	xch->chg2 = chg2;
 	xch->ignore = 0;
 
 	return xch;
 }
 
 
-static int recs_match(xrecord_t *rec1, xrecord_t *rec2, long flags)
+static int recs_match(xrecord_t *rec1, xrecord_t *rec2, int64_t flags)
 {
 	return (rec1->ha == rec2->ha &&
 		xdl_recmatch(rec1->ptr, rec1->size,
 			     rec2->ptr, rec2->size,
 			     flags));
 }
 
 /*
  * If a line is indented more than this, get_indent() just returns this value.
  * This avoids having to do absurd amounts of work for data that are not
  * human-readable text, and also ensures that the output of get_indent fits within
  * an int.
  */
 #define MAX_INDENT 200
 
 /*
  * Return the amount of indentation of the specified line, treating TAB as 8
  * columns. Return -1 if line is empty or contains only whitespace. Clamp the
  * output value at MAX_INDENT.
  */
 static int get_indent(xrecord_t *rec)
 {
-	long i;
+	int64_t i;
 	int ret = 0;
 
 	for (i = 0; i < rec->size; i++) {
 		char c = rec->ptr[i];
 
 		if (!XDL_ISSPACE(c))
 			return ret;
 		else if (c == ' ')
 			ret += 1;
 		else if (c == '\t')
 			ret += 8 - ret % 8;
 		/* ignore other whitespace characters */
 
 		if (ret >= MAX_INDENT)
 			return MAX_INDENT;
 	}
 
 	/* The line contains only whitespace. */
 	return -1;
 }
 
 /*
  * If more than this number of consecutive blank rows are found, just return this
  * value. This avoids requiring O(N^2) work for pathological cases, and also
  * ensures that the output of score_split fits in an int.
  */
 #define MAX_BLANKS 20
 
 /* Characteristics measured about a hypothetical split position. */
 struct split_measurement {
 	/*
 	 * Is the split at the end of the file (aside from any blank lines)?
 	 */
 	int end_of_file;
 
 	/*
 	 * How much is the line immediately following the split indented (or -1 if
 	 * the line is blank):
 	 */
 	int indent;
 
 	/*
 	 * How many consecutive lines above the split are blank?
 	 */
 	int pre_blank;
 
 	/*
 	 * How much is the nearest non-blank line above the split indented (or -1
 	 * if there is no such line)?
 	 */
 	int pre_indent;
 
 	/*
 	 * How many lines after the line following the split are blank?
 	 */
 	int post_blank;
 
 	/*
 	 * How much is the nearest non-blank line after the line following the
 	 * split indented (or -1 if there is no such line)?
 	 */
 	int post_indent;
 };
 
 struct split_score {
 	/* The effective indent of this split (smaller is preferred). */
 	int effective_indent;
 
 	/* Penalty for this split (smaller is preferred). */
 	int penalty;
 };
 
 /*
  * Fill m with information about a hypothetical split of xdf above line split.
  */
-static void measure_split(const xdfile_t *xdf, long split,
+static void measure_split(const xdfile_t *xdf, int64_t split,
 			  struct split_measurement *m)
 {
-	long i;
+	int64_t i;
 
 	if (split >= xdf->nrec) {
 		m->end_of_file = 1;
 		m->indent = -1;
 	} else {
 		m->end_of_file = 0;
 		m->indent = get_indent(xdf->recs[split]);
 	}
 
 	m->pre_blank = 0;
 	m->pre_indent = -1;
 	for (i = split - 1; i >= 0; i--) {
 		m->pre_indent = get_indent(xdf->recs[i]);
 		if (m->pre_indent != -1)
 			break;
 		m->pre_blank += 1;
 		if (m->pre_blank == MAX_BLANKS) {
 			m->pre_indent = 0;
 			break;
 		}
 	}
 
 	m->post_blank = 0;
 	m->post_indent = -1;
 	for (i = split + 1; i < xdf->nrec; i++) {
 		m->post_indent = get_indent(xdf->recs[i]);
 		if (m->post_indent != -1)
 			break;
 		m->post_blank += 1;
 		if (m->post_blank == MAX_BLANKS) {
 			m->post_indent = 0;
 			break;
 		}
 	}
 }
 
 /*
  * The empirically-determined weight factors used by score_split() below.
  * Larger values means that the position is a less favorable place to split.
  *
  * Note that scores are only ever compared against each other, so multiplying
  * all of these weight/penalty values by the same factor wouldn't change the
  * heuristic's behavior. Still, we need to set that arbitrary scale *somehow*.
  * In practice, these numbers are chosen to be large enough that they can be
  * adjusted relative to each other with sufficient precision despite using
  * integer math.
  */
 
 /* Penalty if there are no non-blank lines before the split */
 #define START_OF_FILE_PENALTY 1
 
 /* Penalty if there are no non-blank lines after the split */
 #define END_OF_FILE_PENALTY 21
 
 /* Multiplier for the number of blank lines around the split */
 #define TOTAL_BLANK_WEIGHT (-30)
 
 /* Multiplier for the number of blank lines after the split */
 #define POST_BLANK_WEIGHT 6
 
 /*
  * Penalties applied if the line is indented more than its predecessor
  */
 #define RELATIVE_INDENT_PENALTY (-4)
 #define RELATIVE_INDENT_WITH_BLANK_PENALTY 10
 
 /*
  * Penalties applied if the line is indented less than both its predecessor and
  * its successor
  */
 #define RELATIVE_OUTDENT_PENALTY 24
 #define RELATIVE_OUTDENT_WITH_BLANK_PENALTY 17
 
 /*
  * Penalties applied if the line is indented less than its predecessor but not
  * less than its successor
  */
 #define RELATIVE_DEDENT_PENALTY 23
 #define RELATIVE_DEDENT_WITH_BLANK_PENALTY 17
 
 /*
  * We only consider whether the sum of the effective indents for splits are
  * less than (-1), equal to (0), or greater than (+1) each other. The resulting
  * value is multiplied by the following weight and combined with the penalty to
  * determine the better of two scores.
  */
 #define INDENT_WEIGHT 60
 
 /*
  * Compute a badness score for the hypothetical split whose measurements are
  * stored in m. The weight factors were determined empirically using the tools and
  * corpus described in
  *
  *     https://github.com/mhagger/diff-slider-tools
  *
  * Also see that project if you want to improve the weights based on, for example,
  * a larger or more diverse corpus.
  */
 static void score_add_split(const struct split_measurement *m, struct split_score *s)
 {
 	/*
 	 * A place to accumulate penalty factors (positive makes this index more
 	 * favored):
 	 */
 	int post_blank, total_blank, indent, any_blanks;
 
 	if (m->pre_indent == -1 && m->pre_blank == 0)
 		s->penalty += START_OF_FILE_PENALTY;
 
 	if (m->end_of_file)
 		s->penalty += END_OF_FILE_PENALTY;
 
 	/*
 	 * Set post_blank to the number of blank lines following the split,
 	 * including the line immediately after the split:
 	 */
 	post_blank = (m->indent == -1) ? 1 + m->post_blank : 0;
 	total_blank = m->pre_blank + post_blank;
 
 	/* Penalties based on nearby blank lines: */
 	s->penalty += TOTAL_BLANK_WEIGHT * total_blank;
 	s->penalty += POST_BLANK_WEIGHT * post_blank;
 
 	if (m->indent != -1)
 		indent = m->indent;
 	else
 		indent = m->post_indent;
 
 	any_blanks = (total_blank != 0);
 
 	/* Note that the effective indent is -1 at the end of the file: */
 	s->effective_indent += indent;
 
 	if (indent == -1) {
 		/* No additional adjustments needed. */
 	} else if (m->pre_indent == -1) {
 		/* No additional adjustments needed. */
 	} else if (indent > m->pre_indent) {
 		/*
 		 * The line is indented more than its predecessor.
 		 */
 		s->penalty += any_blanks ?
 			RELATIVE_INDENT_WITH_BLANK_PENALTY :
 			RELATIVE_INDENT_PENALTY;
 	} else if (indent == m->pre_indent) {
 		/*
 		 * The line has the same indentation level as its predecessor.
 		 * No additional adjustments needed.
 		 */
 	} else {
 		/*
 		 * The line is indented less than its predecessor. It could be
 		 * the block terminator of the previous block, but it could
 		 * also be the start of a new block (e.g., an "else" block, or
 		 * maybe the previous block didn't have a block terminator).
 		 * Try to distinguish those cases based on what comes next:
 		 */
 		if (m->post_indent != -1 && m->post_indent > indent) {
 			/*
 			 * The following line is indented more. So it is likely
 			 * that this line is the start of a block.
 			 */
 			s->penalty += any_blanks ?
 				RELATIVE_OUTDENT_WITH_BLANK_PENALTY :
 				RELATIVE_OUTDENT_PENALTY;
 		} else {
 			/*
 			 * That was probably the end of a block.
 			 */
 			s->penalty += any_blanks ?
 				RELATIVE_DEDENT_WITH_BLANK_PENALTY :
 				RELATIVE_DEDENT_PENALTY;
 		}
 	}
 }
 
 static int score_cmp(struct split_score *s1, struct split_score *s2)
 {
 	/* -1 if s1.effective_indent < s2->effective_indent, etc. */
 	int cmp_indents = ((s1->effective_indent > s2->effective_indent) -
 			   (s1->effective_indent < s2->effective_indent));
 
 	return INDENT_WEIGHT * cmp_indents + (s1->penalty - s2->penalty);
 }
 
 /*
  * Represent a group of changed lines in an xdfile_t (i.e., a contiguous group
  * of lines that was inserted or deleted from the corresponding version of the
  * file). We consider there to be such a group at the beginning of the file, at
  * the end of the file, and between any two unchanged lines, though most such
  * groups will usually be empty.
  *
  * If the first line in a group is equal to the line following the group, then
  * the group can be slid down. Similarly, if the last line in a group is equal
  * to the line preceding the group, then the group can be slid up. See
  * group_slide_down() and group_slide_up().
  *
  * Note that loops that are testing for changed lines in xdf->rchg do not need
  * index bounding since the array is prepared with a zero at position -1 and N.
  */
 struct xdlgroup {
 	/*
 	 * The index of the first changed line in the group, or the index of
 	 * the unchanged line above which the (empty) group is located.
 	 */
-	long start;
+	int64_t start;
 
 	/*
 	 * The index of the first unchanged line after the group. For an empty
 	 * group, end is equal to start.
 	 */
-	long end;
+	int64_t end;
 };
 
 /*
  * Initialize g to point at the first group in xdf.
  */
 static void group_init(xdfile_t *xdf, struct xdlgroup *g)
 {
 	g->start = g->end = 0;
 	while (xdf->rchg[g->end])
 		g->end++;
 }
 
 /*
  * Move g to describe the next (possibly empty) group in xdf and return 0. If g
  * is already at the end of the file, do nothing and return -1.
  */
 static inline int group_next(xdfile_t *xdf, struct xdlgroup *g)
 {
 	if (g->end == xdf->nrec)
 		return -1;
 
 	g->start = g->end + 1;
 	for (g->end = g->start; xdf->rchg[g->end]; g->end++)
 		;
 
 	return 0;
 }
 
 /*
  * Move g to describe the previous (possibly empty) group in xdf and return 0.
  * If g is already at the beginning of the file, do nothing and return -1.
  */
 static inline int group_previous(xdfile_t *xdf, struct xdlgroup *g)
 {
 	if (g->start == 0)
 		return -1;
 
 	g->end = g->start - 1;
 	for (g->start = g->end; xdf->rchg[g->start - 1]; g->start--)
 		;
 
 	return 0;
 }
 
 /*
  * If g can be slid toward the end of the file, do so, and if it bumps into a
  * following group, expand this group to include it. Return 0 on success or -1
  * if g cannot be slid down.
  */
-static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g, long flags)
+static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g, int64_t flags)
 {
 	if (g->end < xdf->nrec &&
 	    recs_match(xdf->recs[g->start], xdf->recs[g->end], flags)) {
 		xdf->rchg[g->start++] = 0;
 		xdf->rchg[g->end++] = 1;
 
 		while (xdf->rchg[g->end])
 			g->end++;
 
 		return 0;
 	} else {
 		return -1;
 	}
 }
 
 /*
  * If g can be slid toward the beginning of the file, do so, and if it bumps
  * into a previous group, expand this group to include it. Return 0 on success
  * or -1 if g cannot be slid up.
  */
-static int group_slide_up(xdfile_t *xdf, struct xdlgroup *g, long flags)
+static int group_slide_up(xdfile_t *xdf, struct xdlgroup *g, int64_t flags)
 {
 	if (g->start > 0 &&
 	    recs_match(xdf->recs[g->start - 1], xdf->recs[g->end - 1], flags)) {
 		xdf->rchg[--g->start] = 1;
 		xdf->rchg[--g->end] = 0;
 
 		while (xdf->rchg[g->start - 1])
 			g->start--;
 
 		return 0;
 	} else {
 		return -1;
 	}
 }
 
 static void xdl_bug(const char *msg)
 {
 	fprintf(stderr, "BUG: %s\n", msg);
 	exit(1);
 }
 
 /*
  * For indentation heuristic, skip searching for better slide position after
  * checking MAX_BORING lines without finding an improvement. This defends the
  * indentation heuristic logic against pathological cases. The value is not
  * picked scientifically but should be good enough.
  */
 #define MAX_BORING 100
 
 /*
  * Move back and forward change groups for a consistent and pretty diff output.
  * This also helps in finding joinable change groups and reducing the diff
  * size.
  */
-int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
+int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, int64_t flags) {
 	struct xdlgroup g, go;
-	long earliest_end, end_matching_other;
-	long groupsize;
+	int64_t earliest_end, end_matching_other;
+	int64_t groupsize;
 
 	group_init(xdf, &g);
 	group_init(xdfo, &go);
 
 	while (1) {
 		/* If the group is empty in the to-be-compacted file, skip it: */
 		if (g.end == g.start)
 			goto next;
 
 		/*
 		 * Now shift the change up and then down as far as possible in
 		 * each direction. If it bumps into any other changes, merge them.
 		 */
 		do {
 			groupsize = g.end - g.start;
 
 			/*
 			 * Keep track of the last "end" index that causes this
 			 * group to align with a group of changed lines in the
 			 * other file. -1 indicates that we haven't found such
 			 * a match yet:
 			 */
 			end_matching_other = -1;
 
 			/* Shift the group backward as much as possible: */
 			while (!group_slide_up(xdf, &g, flags))
 				if (group_previous(xdfo, &go))
 					xdl_bug("group sync broken sliding up");
 
 			/*
 			 * This is this highest that this group can be shifted.
 			 * Record its end index:
 			 */
 			earliest_end = g.end;
 
 			if (go.end > go.start)
 				end_matching_other = g.end;
 
 			/* Now shift the group forward as far as possible: */
 			while (1) {
 				if (group_slide_down(xdf, &g, flags))
 					break;
 				if (group_next(xdfo, &go))
 					xdl_bug("group sync broken sliding down");
 
 				if (go.end > go.start)
 					end_matching_other = g.end;
 			}
 		} while (groupsize != g.end - g.start);
 
 		/*
 		 * If the group can be shifted, then we can possibly use this
 		 * freedom to produce a more intuitive diff.
 		 *
 		 * The group is currently shifted as far down as possible, so the
 		 * heuristics below only have to handle upwards shifts.
 		 */
 
 		if (g.end == earliest_end) {
 			/* no shifting was possible */
 		} else if (end_matching_other != -1) {
 			/*
 			 * Move the possibly merged group of changes back to line
 			 * up with the last group of changes from the other file
 			 * that it can align with.
 			 */
 			while (go.end == go.start) {
 				if (group_slide_up(xdf, &g, flags))
 					xdl_bug("match disappeared");
 				if (group_previous(xdfo, &go))
 					xdl_bug("group sync broken sliding to match");
 			}
 		} else if (flags & XDF_INDENT_HEURISTIC) {
 			/*
 			 * Indent heuristic: a group of pure add/delete lines
 			 * implies two splits, one between the end of the "before"
 			 * context and the start of the group, and another between
 			 * the end of the group and the beginning of the "after"
 			 * context. Some splits are aesthetically better and some
 			 * are worse. We compute a badness "score" for each split,
 			 * and add the scores for the two splits to define a
 			 * "score" for each position that the group can be shifted
 			 * to. Then we pick the shift with the lowest score.
 			 */
-			long shift, best_shift = -1;
+			int64_t shift, best_shift = -1;
 			struct split_score best_score;
 
 			/*
 			 * This is O(N * MAX_BLANKS) (N = shift-able lines).
 			 * Even with MAX_BLANKS bounded to a small value, a
 			 * large N could still make this loop take several
 			 * times longer than the main diff algorithm. The
 			 * "boring" value is to help cut down N to something
 			 * like (MAX_BORING + groupsize).
 			 *
 			 * Scan from bottom to top. So we can exit the loop
 			 * without compromising the assumption "for a same best
 			 * score, pick the bottommost shift".
 			 */
 			int boring = 0;
 			for (shift = g.end; shift >= earliest_end; shift--) {
 				struct split_measurement m;
 				struct split_score score = {0, 0};
 				int cmp;
 
 				measure_split(xdf, shift, &m);
 				score_add_split(&m, &score);
 				measure_split(xdf, shift - groupsize, &m);
 				score_add_split(&m, &score);
 
 				if (best_shift == -1) {
 					cmp = -1;
 				} else {
 					cmp = score_cmp(&score, &best_score);
 				}
 				if (cmp < 0) {
 					boring = 0;
 					best_score.effective_indent = score.effective_indent;
 					best_score.penalty = score.penalty;
 					best_shift = shift;
 				} else {
 					boring += 1;
 					if (boring >= MAX_BORING)
 						break;
 				}
 			}
 
 			while (g.end > best_shift) {
 				if (group_slide_up(xdf, &g, flags))
 					xdl_bug("best shift unreached");
 				if (group_previous(xdfo, &go))
 					xdl_bug("group sync broken sliding to blank line");
 			}
 		}
 
 	next:
 		/* Move past the just-processed group: */
 		if (group_next(xdf, &g))
 			break;
 		if (group_next(xdfo, &go))
 			xdl_bug("group sync broken moving to next group");
 	}
 
 	if (!group_next(xdfo, &go))
 		xdl_bug("group sync broken at end of file");
 
 	return 0;
 }
 
 
 int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr) {
 	xdchange_t *cscr = NULL, *xch;
 	char *rchg1 = xe->xdf1.rchg, *rchg2 = xe->xdf2.rchg;
-	long i1, i2, l1, l2;
+	int64_t i1, i2, l1, l2;
 
 	/*
 	 * Trivial. Collects "groups" of changes and creates an edit script.
 	 */
 	for (i1 = xe->xdf1.nrec, i2 = xe->xdf2.nrec; i1 >= 0 || i2 >= 0; i1--, i2--)
 		if (rchg1[i1 - 1] || rchg2[i2 - 1]) {
 			for (l1 = i1; rchg1[i1 - 1]; i1--);
 			for (l2 = i2; rchg2[i2 - 1]; i2--);
 
 			if (!(xch = xdl_add_change(cscr, i1, i2, l1 - i1, l2 - i2))) {
 				xdl_free_script(cscr);
 				return -1;
 			}
 			cscr = xch;
 		}
 
 	*xscr = cscr;
 
 	return 0;
 }
 
 
 void xdl_free_script(xdchange_t *xscr) {
 	xdchange_t *xch;
 
 	while ((xch = xscr) != NULL) {
 		xscr = xscr->next;
 		xdl_free(xch);
 	}
 }
 
 
 /*
  * Starting at the passed change atom, find the latest change atom to be included
  * inside the differential hunk according to the specified configuration.
  * Also advance xscr if the first changes must be discarded.
  */
 xdchange_t *xdl_get_hunk(xdchange_t **xscr, xdemitconf_t const *xecfg)
 {
 	xdchange_t *xch, *xchp, *lxch;
-	long max_common = 0;
-	long max_ignorable = 0;
-	unsigned long ignored = 0; /* number of ignored blank lines */
+	int64_t max_common = 0;
+	int64_t max_ignorable = 0;
+	uint64_t ignored = 0; /* number of ignored blank lines */
 
 	/* remove ignorable changes that are too far before other changes */
 	for (xchp = *xscr; xchp && xchp->ignore; xchp = xchp->next) {
 		xch = xchp->next;
 
 		if (xch == NULL ||
 		    xch->i1 - (xchp->i1 + xchp->chg1) >= max_ignorable)
 			*xscr = xch;
 	}
 
 	if (*xscr == NULL)
 		return NULL;
 
 	lxch = *xscr;
 
 	for (xchp = *xscr, xch = xchp->next; xch; xchp = xch, xch = xch->next) {
-		long distance = xch->i1 - (xchp->i1 + xchp->chg1);
+		int64_t distance = xch->i1 - (xchp->i1 + xchp->chg1);
 		if (distance > max_common)
 			break;
 
 		if (distance < max_ignorable && (!xch->ignore || lxch == xchp)) {
 			lxch = xch;
 			ignored = 0;
 		} else if (distance < max_ignorable && xch->ignore) {
 			ignored += xch->chg2;
 		} else if (lxch != xchp &&
 			   xch->i1 + ignored - (lxch->i1 + lxch->chg1) > max_common) {
 			break;
 		} else if (!xch->ignore) {
 			lxch = xch;
 			ignored = 0;
 		} else {
 			ignored += xch->chg2;
 		}
 	}
 
 	return lxch;
 }
 
 
 static int xdl_call_hunk_func(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 			      xdemitconf_t const *xecfg)
 {
-	long p = xe->nprefix, s = xe->nsuffix;
+	int64_t p = xe->nprefix, s = xe->nsuffix;
 	xdchange_t *xch, *xche;
 
 	if (!xecfg->hunk_func)
 		return -1;
 
 	if ((xecfg->flags & XDL_EMIT_BDIFFHUNK) != 0) {
-		long i1 = 0, i2 = 0, n1 = xe->xdf1.nrec, n2 = xe->xdf2.nrec;
+		int64_t i1 = 0, i2 = 0, n1 = xe->xdf1.nrec, n2 = xe->xdf2.nrec;
 		for (xch = xscr; xch; xch = xche->next) {
 			xche = xdl_get_hunk(&xch, xecfg);
 			if (!xch)
 				break;
 			if (xch != xche)
 				xdl_bug("xch != xche");
 			xch->i1 += p;
 			xch->i2 += p;
 			if (xch->i1 > i1 || xch->i2 > i2) {
 				if (xecfg->hunk_func(i1, xch->i1, i2, xch->i2, ecb->priv) < 0)
 					return -1;
 			}
 			i1 = xche->i1 + xche->chg1;
 			i2 = xche->i2 + xche->chg2;
 		}
 		if (xecfg->hunk_func(i1, n1 + p + s, i2, n2 + p + s,
 				     ecb->priv) < 0)
 			return -1;
 	} else {
 		for (xch = xscr; xch; xch = xche->next) {
 			xche = xdl_get_hunk(&xch, xecfg);
 			if (!xch)
 				break;
 			if (xecfg->hunk_func(xch->i1 + p,
 					xche->i1 + xche->chg1 - xch->i1,
 					xch->i2 + p,
 					xche->i2 + xche->chg2 - xch->i2,
 					ecb->priv) < 0)
 				return -1;
 		}
 	}
 	return 0;
 }
 
 int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 	     xdemitconf_t const *xecfg, xdemitcb_t *ecb) {
 	xdchange_t *xscr;
 	xdfenv_t xe;
 
 	if (xdl_do_diff(mf1, mf2, xpp, &xe) < 0) {
 
 		return -1;
 	}
 	if (xdl_change_compact(&xe.xdf1, &xe.xdf2, xpp->flags) < 0 ||
 	    xdl_change_compact(&xe.xdf2, &xe.xdf1, xpp->flags) < 0 ||
 	    xdl_build_script(&xe, &xscr) < 0) {
 
 		xdl_free_env(&xe);
 		return -1;
 	}
 
 	if (xdl_call_hunk_func(&xe, xscr, ecb, xecfg) < 0) {
 		xdl_free_script(xscr);
 		xdl_free_env(&xe);
 		return -1;
 	}
 	xdl_free_script(xscr);
 	xdl_free_env(&xe);
 
 	return 0;
 }

mercurial/thirdparty/xdiff/xdiffi.h

@@ -1,58 +1,58 b''
 /*
  *  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, see
  *  <http://www.gnu.org/licenses/>.
  *
  *  Davide Libenzi <[e-mail]>
  *
  */
 
 #if !defined(XDIFFI_H)
 #define XDIFFI_H
 
 
 typedef struct s_diffdata {
-	long nrec;
-	unsigned long const *ha;
-	long *rindex;
+	int64_t nrec;
+	uint64_t const *ha;
+	int64_t *rindex;
 	char *rchg;
 } diffdata_t;
 
 typedef struct s_xdalgoenv {
-	long mxcost;
-	long snake_cnt;
-	long heur_min;
+	int64_t mxcost;
+	int64_t snake_cnt;
+	int64_t heur_min;
 } xdalgoenv_t;
 
 typedef struct s_xdchange {
 	struct s_xdchange *next;
-	long i1, i2;
-	long chg1, chg2;
+	int64_t i1, i2;
+	int64_t chg1, chg2;
 	int ignore;
 } xdchange_t;
 
 
 
-int xdl_recs_cmp(diffdata_t *dd1, long off1, long lim1,
-		 diffdata_t *dd2, long off2, long lim2,
-		 long *kvdf, long *kvdb, int need_min, xdalgoenv_t *xenv);
+int xdl_recs_cmp(diffdata_t *dd1, int64_t off1, int64_t lim1,
+		 diffdata_t *dd2, int64_t off2, int64_t lim2,
+		 int64_t *kvdf, int64_t *kvdb, int need_min, xdalgoenv_t *xenv);
 int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 		xdfenv_t *xe);
-int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags);
+int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, int64_t flags);
 int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr);
 void xdl_free_script(xdchange_t *xscr);
 
 #endif /* #if !defined(XDIFFI_H) */

mercurial/thirdparty/xdiff/xinclude.h

@@ -1,40 +1,41 b''
 /*
  *  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, see
  *  <http://www.gnu.org/licenses/>.
  *
  *  Davide Libenzi <[e-mail]>
  *
  */
 
 #if !defined(XINCLUDE_H)
 #define XINCLUDE_H
 
 #include <ctype.h>
+#include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <limits.h>
 
 #include "xmacros.h"
 #include "xdiff.h"
 #include "xtypes.h"
 #include "xutils.h"
 #include "xprepare.h"
 #include "xdiffi.h"
 
 
 #endif /* #if !defined(XINCLUDE_H) */

mercurial/thirdparty/xdiff/xprepare.c

@@ -1,552 +1,552 b''
 /*
  *  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, see
  *  <http://www.gnu.org/licenses/>.
  *
  *  Davide Libenzi <[e-mail]>
  *
  */
 
 #include "xinclude.h"
 
 
 #define XDL_KPDIS_RUN 4
 #define XDL_MAX_EQLIMIT 1024
 #define XDL_SIMSCAN_WINDOW 100
 #define XDL_GUESS_NLINES1 256
 
 
 typedef struct s_xdlclass {
 	struct s_xdlclass *next;
-	unsigned long ha;
+	uint64_t ha;
 	char const *line;
-	long size;
-	long idx;
-	long len1, len2;
+	int64_t size;
+	int64_t idx;
+	int64_t len1, len2;
 } xdlclass_t;
 
 typedef struct s_xdlclassifier {
 	unsigned int hbits;
-	long hsize;
+	int64_t hsize;
 	xdlclass_t **rchash;
 	chastore_t ncha;
 	xdlclass_t **rcrecs;
-	long alloc;
-	long count;
-	long flags;
+	int64_t alloc;
+	int64_t count;
+	int64_t flags;
 } xdlclassifier_t;
 
 
 
 
-static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags);
+static int xdl_init_classifier(xdlclassifier_t *cf, int64_t size, int64_t flags);
 static void xdl_free_classifier(xdlclassifier_t *cf);
 static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t **rhash,
 			       unsigned int hbits, xrecord_t *rec);
-static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp,
+static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, int64_t narec, xpparam_t const *xpp,
 			   xdlclassifier_t *cf, xdfile_t *xdf);
 static void xdl_free_ctx(xdfile_t *xdf);
-static int xdl_clean_mmatch(char const *dis, long i, long s, long e);
+static int xdl_clean_mmatch(char const *dis, int64_t i, int64_t s, int64_t e);
 static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2);
 static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2);
 static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2);
 
 
 
 
-static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags) {
+static int xdl_init_classifier(xdlclassifier_t *cf, int64_t size, int64_t flags) {
 	cf->flags = flags;
 
 	cf->hbits = xdl_hashbits((unsigned int) size);
 	cf->hsize = 1 << cf->hbits;
 
 	if (xdl_cha_init(&cf->ncha, sizeof(xdlclass_t), size / 4 + 1) < 0) {
 
 		return -1;
 	}
 	if (!(cf->rchash = (xdlclass_t **) xdl_malloc(cf->hsize * sizeof(xdlclass_t *)))) {
 
 		xdl_cha_free(&cf->ncha);
 		return -1;
 	}
 	memset(cf->rchash, 0, cf->hsize * sizeof(xdlclass_t *));
 
 	cf->alloc = size;
 	if (!(cf->rcrecs = (xdlclass_t **) xdl_malloc(cf->alloc * sizeof(xdlclass_t *)))) {
 
 		xdl_free(cf->rchash);
 		xdl_cha_free(&cf->ncha);
 		return -1;
 	}
 
 	cf->count = 0;
 
 	return 0;
 }
 
 
 static void xdl_free_classifier(xdlclassifier_t *cf) {
 
 	xdl_free(cf->rcrecs);
 	xdl_free(cf->rchash);
 	xdl_cha_free(&cf->ncha);
 }
 
 
 static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t **rhash,
 			       unsigned int hbits, xrecord_t *rec) {
-	long hi;
+	int64_t hi;
 	char const *line;
 	xdlclass_t *rcrec;
 	xdlclass_t **rcrecs;
 
 	line = rec->ptr;
 	hi = (long) XDL_HASHLONG(rec->ha, cf->hbits);
 	for (rcrec = cf->rchash[hi]; rcrec; rcrec = rcrec->next)
 		if (rcrec->ha == rec->ha &&
 				xdl_recmatch(rcrec->line, rcrec->size,
 					rec->ptr, rec->size, cf->flags))
 			break;
 
 	if (!rcrec) {
 		if (!(rcrec = xdl_cha_alloc(&cf->ncha))) {
 
 			return -1;
 		}
 		rcrec->idx = cf->count++;
 		if (cf->count > cf->alloc) {
 			cf->alloc *= 2;
 			if (!(rcrecs = (xdlclass_t **) xdl_realloc(cf->rcrecs, cf->alloc * sizeof(xdlclass_t *)))) {
 
 				return -1;
 			}
 			cf->rcrecs = rcrecs;
 		}
 		cf->rcrecs[rcrec->idx] = rcrec;
 		rcrec->line = line;
 		rcrec->size = rec->size;
 		rcrec->ha = rec->ha;
 		rcrec->len1 = rcrec->len2 = 0;
 		rcrec->next = cf->rchash[hi];
 		cf->rchash[hi] = rcrec;
 	}
 
 	(pass == 1) ? rcrec->len1++ : rcrec->len2++;
 
 	rec->ha = (unsigned long) rcrec->idx;
 
 	hi = (long) XDL_HASHLONG(rec->ha, hbits);
 	rec->next = rhash[hi];
 	rhash[hi] = rec;
 
 	return 0;
 }
 
 
 /*
  * Trim common prefix from files.
  *
  * Note: trimming could affect hunk shifting. But the performance benefit
  * outweighs the shift change. A diff result with suboptimal shifting is still
  * valid.
  */
-static void xdl_trim_files(mmfile_t *mf1, mmfile_t *mf2, long reserved,
+static void xdl_trim_files(mmfile_t *mf1, mmfile_t *mf2, int64_t reserved,
 		xdfenv_t *xe, mmfile_t *out_mf1, mmfile_t *out_mf2) {
 	mmfile_t msmall, mlarge;
 	/* prefix lines, prefix bytes, suffix lines, suffix bytes */
-	long plines = 0, pbytes = 0, slines = 0, sbytes = 0, i;
+	int64_t plines = 0, pbytes = 0, slines = 0, sbytes = 0, i;
 	/* prefix char pointer for msmall and mlarge */
 	const char *pp1, *pp2;
 	/* suffix char pointer for msmall and mlarge */
 	const char *ps1, *ps2;
 
 	/* reserved must >= 0 for the line boundary adjustment to work */
 	if (reserved < 0)
 		reserved = 0;
 
 	if (mf1->size < mf2->size) {
 		memcpy(&msmall, mf1, sizeof(mmfile_t));
 		memcpy(&mlarge, mf2, sizeof(mmfile_t));
 	} else {
 		memcpy(&msmall, mf2, sizeof(mmfile_t));
 		memcpy(&mlarge, mf1, sizeof(mmfile_t));
 	}
 
 	pp1 = msmall.ptr, pp2 = mlarge.ptr;
 	for (i = 0; i < msmall.size && *pp1 == *pp2; ++i) {
 		plines += (*pp1 == '\n');
 		pp1++, pp2++;
 	}
 
 	ps1 = msmall.ptr + msmall.size - 1, ps2 = mlarge.ptr + mlarge.size - 1;
 	while (ps1 > pp1 && *ps1 == *ps2) {
 		slines += (*ps1 == '\n');
 		ps1--, ps2--;
 	}
 
 	/* Retract common prefix and suffix boundaries for reserved lines */
 	if (plines <= reserved + 1) {
 		plines = 0;
 	} else {
 		i = 0;
 		while (i <= reserved) {
 			pp1--;
 			i += (*pp1 == '\n');
 		}
 		/* The new mmfile starts at the next char just after '\n' */
 		pbytes = pp1 - msmall.ptr + 1;
 		plines -= reserved;
 	}
 
 	if (slines <= reserved + 1) {
 		slines = 0;
 	} else {
 		/* Note: with compiler SIMD support (ex. -O3 -mavx2), this
 		 * might perform better than memchr. */
 		i = 0;
 		while (i <= reserved) {
 			ps1++;
 			i += (*ps1 == '\n');
 		}
 		/* The new mmfile includes this '\n' */
 		sbytes = msmall.ptr + msmall.size - ps1 - 1;
 		slines -= reserved;
 		if (msmall.ptr[msmall.size - 1] == '\n')
 			slines -= 1;
 	}
 
 	xe->nprefix = plines;
 	xe->nsuffix = slines;
 	out_mf1->ptr = mf1->ptr + pbytes;
 	out_mf1->size = mf1->size - pbytes - sbytes;
 	out_mf2->ptr = mf2->ptr + pbytes;
 	out_mf2->size = mf2->size - pbytes - sbytes;
 }
 
 
-static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp,
+static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, int64_t narec, xpparam_t const *xpp,
 			   xdlclassifier_t *cf, xdfile_t *xdf) {
 	unsigned int hbits;
-	long nrec, hsize, bsize;
-	unsigned long hav;
+	int64_t nrec, hsize, bsize;
+	uint64_t hav;
 	char const *blk, *cur, *top, *prev;
 	xrecord_t *crec;
 	xrecord_t **recs, **rrecs;
 	xrecord_t **rhash;
-	unsigned long *ha;
+	uint64_t *ha;
 	char *rchg;
-	long *rindex;
+	int64_t *rindex;
 
 	ha = NULL;
 	rindex = NULL;
 	rchg = NULL;
 	rhash = NULL;
 	recs = NULL;
 
 	if (xdl_cha_init(&xdf->rcha, sizeof(xrecord_t), narec / 4 + 1) < 0)
 		goto abort;
 	if (!(recs = (xrecord_t **) xdl_malloc(narec * sizeof(xrecord_t *))))
 		goto abort;
 
 	{
 		hbits = xdl_hashbits((unsigned int) narec);
 		hsize = 1 << hbits;
 		if (!(rhash = (xrecord_t **) xdl_malloc(hsize * sizeof(xrecord_t *))))
 			goto abort;
 		memset(rhash, 0, hsize * sizeof(xrecord_t *));
 	}
 
 	nrec = 0;
 	if ((cur = blk = xdl_mmfile_first(mf, &bsize)) != NULL) {
 		for (top = blk + bsize; cur < top; ) {
 			prev = cur;
 			hav = xdl_hash_record(&cur, top, xpp->flags);
 			if (nrec >= narec) {
 				narec *= 2;
 				if (!(rrecs = (xrecord_t **) xdl_realloc(recs, narec * sizeof(xrecord_t *))))
 					goto abort;
 				recs = rrecs;
 			}
 			if (!(crec = xdl_cha_alloc(&xdf->rcha)))
 				goto abort;
 			crec->ptr = prev;
 			crec->size = (long) (cur - prev);
 			crec->ha = hav;
 			recs[nrec++] = crec;
 
 			if (xdl_classify_record(pass, cf, rhash, hbits, crec) < 0)
 				goto abort;
 		}
 	}
 
 	if (!(rchg = (char *) xdl_malloc((nrec + 2) * sizeof(char))))
 		goto abort;
 	memset(rchg, 0, (nrec + 2) * sizeof(char));
 
-	if (!(rindex = (long *) xdl_malloc((nrec + 1) * sizeof(long))))
+	if (!(rindex = (int64_t *) xdl_malloc((nrec + 1) * sizeof(long))))
 		goto abort;
-	if (!(ha = (unsigned long *) xdl_malloc((nrec + 1) * sizeof(unsigned long))))
+	if (!(ha = (uint64_t *) xdl_malloc((nrec + 1) * sizeof(unsigned long))))
 		goto abort;
 
 	xdf->nrec = nrec;
 	xdf->recs = recs;
 	xdf->hbits = hbits;
 	xdf->rhash = rhash;
 	xdf->rchg = rchg + 1;
 	xdf->rindex = rindex;
 	xdf->nreff = 0;
 	xdf->ha = ha;
 	xdf->dstart = 0;
 	xdf->dend = nrec - 1;
 
 	return 0;
 
 abort:
 	xdl_free(ha);
 	xdl_free(rindex);
 	xdl_free(rchg);
 	xdl_free(rhash);
 	xdl_free(recs);
 	xdl_cha_free(&xdf->rcha);
 	return -1;
 }
 
 
 static void xdl_free_ctx(xdfile_t *xdf) {
 
 	xdl_free(xdf->rhash);
 	xdl_free(xdf->rindex);
 	xdl_free(xdf->rchg - 1);
 	xdl_free(xdf->ha);
 	xdl_free(xdf->recs);
 	xdl_cha_free(&xdf->rcha);
 }
 
 /* Reserved lines for trimming, to leave room for shifting */
 #define TRIM_RESERVED_LINES 100
 
 int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 		    xdfenv_t *xe) {
-	long enl1, enl2, sample;
+	int64_t enl1, enl2, sample;
 	mmfile_t tmf1, tmf2;
 	xdlclassifier_t cf;
 
 	memset(&cf, 0, sizeof(cf));
 
 	sample = XDL_GUESS_NLINES1;
 
 	enl1 = xdl_guess_lines(mf1, sample) + 1;
 	enl2 = xdl_guess_lines(mf2, sample) + 1;
 
 	if (xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0)
 		return -1;
 
 	xdl_trim_files(mf1, mf2, TRIM_RESERVED_LINES, xe, &tmf1, &tmf2);
 
 	if (xdl_prepare_ctx(1, &tmf1, enl1, xpp, &cf, &xe->xdf1) < 0) {
 
 		xdl_free_classifier(&cf);
 		return -1;
 	}
 	if (xdl_prepare_ctx(2, &tmf2, enl2, xpp, &cf, &xe->xdf2) < 0) {
 
 		xdl_free_ctx(&xe->xdf1);
 		xdl_free_classifier(&cf);
 		return -1;
 	}
 
 	if (xdl_optimize_ctxs(&cf, &xe->xdf1, &xe->xdf2) < 0) {
 		xdl_free_ctx(&xe->xdf2);
 		xdl_free_ctx(&xe->xdf1);
 		xdl_free_classifier(&cf);
 		return -1;
 	}
 
 	xdl_free_classifier(&cf);
 
 	return 0;
 }
 
 
 void xdl_free_env(xdfenv_t *xe) {
 
 	xdl_free_ctx(&xe->xdf2);
 	xdl_free_ctx(&xe->xdf1);
 }
 
 
-static int xdl_clean_mmatch(char const *dis, long i, long s, long e) {
-	long r, rdis0, rpdis0, rdis1, rpdis1;
+static int xdl_clean_mmatch(char const *dis, int64_t i, int64_t s, int64_t e) {
+	int64_t r, rdis0, rpdis0, rdis1, rpdis1;
 
 	/*
 	 * Limits the window the is examined during the similar-lines
 	 * scan. The loops below stops when dis[i - r] == 1 (line that
 	 * has no match), but there are corner cases where the loop
 	 * proceed all the way to the extremities by causing huge
 	 * performance penalties in case of big files.
 	 */
 	if (i - s > XDL_SIMSCAN_WINDOW)
 		s = i - XDL_SIMSCAN_WINDOW;
 	if (e - i > XDL_SIMSCAN_WINDOW)
 		e = i + XDL_SIMSCAN_WINDOW;
 
 	/*
 	 * Scans the lines before 'i' to find a run of lines that either
 	 * have no match (dis[j] == 0) or have multiple matches (dis[j] > 1).
 	 * Note that we always call this function with dis[i] > 1, so the
 	 * current line (i) is already a multimatch line.
 	 */
 	for (r = 1, rdis0 = 0, rpdis0 = 1; (i - r) >= s; r++) {
 		if (!dis[i - r])
 			rdis0++;
 		else if (dis[i - r] == 2)
 			rpdis0++;
 		else
 			break;
 	}
 	/*
 	 * If the run before the line 'i' found only multimatch lines, we
 	 * return 0 and hence we don't make the current line (i) discarded.
 	 * We want to discard multimatch lines only when they appear in the
 	 * middle of runs with nomatch lines (dis[j] == 0).
 	 */
 	if (rdis0 == 0)
 		return 0;
 	for (r = 1, rdis1 = 0, rpdis1 = 1; (i + r) <= e; r++) {
 		if (!dis[i + r])
 			rdis1++;
 		else if (dis[i + r] == 2)
 			rpdis1++;
 		else
 			break;
 	}
 	/*
 	 * If the run after the line 'i' found only multimatch lines, we
 	 * return 0 and hence we don't make the current line (i) discarded.
 	 */
 	if (rdis1 == 0)
 		return 0;
 	rdis1 += rdis0;
 	rpdis1 += rpdis0;
 
 	return rpdis1 * XDL_KPDIS_RUN < (rpdis1 + rdis1);
 }
 
 
 /*
  * Try to reduce the problem complexity, discard records that have no
  * matches on the other file. Also, lines that have multiple matches
  * might be potentially discarded if they happear in a run of discardable.
  */
 static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) {
-	long i, nm, nreff, mlim;
+	int64_t i, nm, nreff, mlim;
 	xrecord_t **recs;
 	xdlclass_t *rcrec;
 	char *dis, *dis1, *dis2;
 
 	if (!(dis = (char *) xdl_malloc(xdf1->nrec + xdf2->nrec + 2))) {
 
 		return -1;
 	}
 	memset(dis, 0, xdf1->nrec + xdf2->nrec + 2);
 	dis1 = dis;
 	dis2 = dis1 + xdf1->nrec + 1;
 
 	if ((mlim = xdl_bogosqrt(xdf1->nrec)) > XDL_MAX_EQLIMIT)
 		mlim = XDL_MAX_EQLIMIT;
 	for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; i <= xdf1->dend; i++, recs++) {
 		rcrec = cf->rcrecs[(*recs)->ha];
 		nm = rcrec ? rcrec->len2 : 0;
 		dis1[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1;
 	}
 
 	if ((mlim = xdl_bogosqrt(xdf2->nrec)) > XDL_MAX_EQLIMIT)
 		mlim = XDL_MAX_EQLIMIT;
 	for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; i <= xdf2->dend; i++, recs++) {
 		rcrec = cf->rcrecs[(*recs)->ha];
 		nm = rcrec ? rcrec->len1 : 0;
 		dis2[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1;
 	}
 
 	for (nreff = 0, i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart];
 	     i <= xdf1->dend; i++, recs++) {
 		if (dis1[i] == 1 ||
 		    (dis1[i] == 2 && !xdl_clean_mmatch(dis1, i, xdf1->dstart, xdf1->dend))) {
 			xdf1->rindex[nreff] = i;
 			xdf1->ha[nreff] = (*recs)->ha;
 			nreff++;
 		} else
 			xdf1->rchg[i] = 1;
 	}
 	xdf1->nreff = nreff;
 
 	for (nreff = 0, i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart];
 	     i <= xdf2->dend; i++, recs++) {
 		if (dis2[i] == 1 ||
 		    (dis2[i] == 2 && !xdl_clean_mmatch(dis2, i, xdf2->dstart, xdf2->dend))) {
 			xdf2->rindex[nreff] = i;
 			xdf2->ha[nreff] = (*recs)->ha;
 			nreff++;
 		} else
 			xdf2->rchg[i] = 1;
 	}
 	xdf2->nreff = nreff;
 
 	xdl_free(dis);
 
 	return 0;
 }
 
 
 /*
  * Early trim initial and terminal matching records.
  */
 static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) {
-	long i, lim;
+	int64_t i, lim;
 	xrecord_t **recs1, **recs2;
 
 	recs1 = xdf1->recs;
 	recs2 = xdf2->recs;
 	for (i = 0, lim = XDL_MIN(xdf1->nrec, xdf2->nrec); i < lim;
 	     i++, recs1++, recs2++)
 		if ((*recs1)->ha != (*recs2)->ha)
 			break;
 
 	xdf1->dstart = xdf2->dstart = i;
 
 	recs1 = xdf1->recs + xdf1->nrec - 1;
 	recs2 = xdf2->recs + xdf2->nrec - 1;
 	for (lim -= i, i = 0; i < lim; i++, recs1--, recs2--)
 		if ((*recs1)->ha != (*recs2)->ha)
 			break;
 
 	xdf1->dend = xdf1->nrec - i - 1;
 	xdf2->dend = xdf2->nrec - i - 1;
 
 	return 0;
 }
 
 
 static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) {
 
 	if (xdl_trim_ends(xdf1, xdf2) < 0 ||
 	    xdl_cleanup_records(cf, xdf1, xdf2) < 0) {
 
 		return -1;
 	}
 
 	return 0;
 }

mercurial/thirdparty/xdiff/xtypes.h

@@ -1,105 +1,105 b''
 /*
  *  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, see
  *  <http://www.gnu.org/licenses/>.
  *
  *  Davide Libenzi <[e-mail]>
  *
  */
 
 #if !defined(XTYPES_H)
 #define XTYPES_H
 
 
 
 typedef struct s_chanode {
 	struct s_chanode *next;
-	long icurr;
+	int64_t icurr;
 } chanode_t;
 
 typedef struct s_chastore {
 	chanode_t *head, *tail;
-	long isize, nsize;
+	int64_t isize, nsize;
 	chanode_t *ancur;
 	chanode_t *sncur;
-	long scurr;
+	int64_t scurr;
 } chastore_t;
 
 typedef struct s_xrecord {
 	struct s_xrecord *next;
 	char const *ptr;
-	long size;
-	unsigned long ha;
+	int64_t size;
+	uint64_t ha;
 } xrecord_t;
 
 typedef struct s_xdfile {
 	/* manual memory management */
 	chastore_t rcha;
 
 	/* number of records (lines) */
-	long nrec;
+	int64_t nrec;
 
 	/* hash table size
 	 * the maximum hash value in the table is (1 << hbits) */
 	unsigned int hbits;
 
 	/* hash table, hash value => xrecord_t
 	 * note: xrecord_t is a linked list. */
 	xrecord_t **rhash;
 
 	/* range excluding common prefix and suffix
 	 * [recs[i] for i in range(0, dstart)] are common prefix.
 	 * [recs[i] for i in range(dstart, dend + 1 - dstart)] are interesting
 	 * lines */
-	long dstart, dend;
+	int64_t dstart, dend;
 
 	/* pointer to records (lines) */
 	xrecord_t **recs;
 
 	/* record changed, use original "recs" index
 	 * rchag[i] can be either 0 or 1. 1 means recs[i] (line i) is marked
 	 * "changed". */
 	char *rchg;
 
 	/* cleaned-up record index => original "recs" index
 	 * clean-up means:
 	 *  rule 1. remove common prefix and suffix
 	 *  rule 2. remove records that are only on one side, since they can
 	 *          not match the other side
 	 * rindex[0] is likely dstart, if not removed up by rule 2.
 	 * rindex[nreff - 1] is likely dend, if not removed by rule 2.
 	 */
-	long *rindex;
+	int64_t *rindex;
 
 	/* rindex size */
-	long nreff;
+	int64_t nreff;
 
 	/* cleaned-up record index => hash value
 	 * ha[i] = recs[rindex[i]]->ha */
-	unsigned long *ha;
+	uint64_t *ha;
 } xdfile_t;
 
 typedef struct s_xdfenv {
 	xdfile_t xdf1, xdf2;
 
 	/* number of lines for common prefix and suffix that are removed
 	 * from xdf1 and xdf2 as a preprocessing step */
-	long nprefix, nsuffix;
+	int64_t nprefix, nsuffix;
 } xdfenv_t;
 
 
 
 #endif /* #if !defined(XTYPES_H) */

mercurial/thirdparty/xdiff/xutils.c

@@ -1,149 +1,149 b''
 /*
  *  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, see
  *  <http://www.gnu.org/licenses/>.
  *
  *  Davide Libenzi <[e-mail]>
  *
  */
 
 #include <limits.h>
 #include <assert.h>
 #include "xinclude.h"
 
 
 
 
-long xdl_bogosqrt(long n) {
-	long i;
+int64_t xdl_bogosqrt(int64_t n) {
+	int64_t i;
 
 	/*
 	 * Classical integer square root approximation using shifts.
 	 */
 	for (i = 1; n > 0; n >>= 2)
 		i <<= 1;
 
 	return i;
 }
 
 
-void *xdl_mmfile_first(mmfile_t *mmf, long *size)
+void *xdl_mmfile_first(mmfile_t *mmf, int64_t *size)
 {
 	*size = mmf->size;
 	return mmf->ptr;
 }
 
 
-long xdl_mmfile_size(mmfile_t *mmf)
+int64_t xdl_mmfile_size(mmfile_t *mmf)
 {
 	return mmf->size;
 }
 
 
-int xdl_cha_init(chastore_t *cha, long isize, long icount) {
+int xdl_cha_init(chastore_t *cha, int64_t isize, int64_t 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;
 }
 
-long xdl_guess_lines(mmfile_t *mf, long sample) {
-	long nl = 0, size, tsize = 0;
+int64_t xdl_guess_lines(mmfile_t *mf, int64_t sample) {
+	int64_t 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 xdl_recmatch(const char *l1, int64_t s1, const char *l2, int64_t s2, int64_t flags)
 {
 	if (s1 == s2 && !memcmp(l1, l2, s1))
 		return 1;
 	return 0;
 }
 
-unsigned long xdl_hash_record(char const **data, char const *top, long flags) {
-	unsigned long ha = 5381;
+uint64_t xdl_hash_record(char const **data, char const *top, int64_t flags) {
+	uint64_t ha = 5381;
 	char const *ptr = *data;
 
 	for (; ptr < top && *ptr != '\n'; ptr++) {
 		ha += (ha << 5);
 		ha ^= (unsigned long) *ptr;
 	}
 	*data = ptr < top ? ptr + 1: ptr;
 
 	return ha;
 }
 
 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;
 }

mercurial/thirdparty/xdiff/xutils.h

@@ -1,39 +1,39 b''
 /*
  *  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, see
  *  <http://www.gnu.org/licenses/>.
  *
  *  Davide Libenzi <[e-mail]>
  *
  */
 
 #if !defined(XUTILS_H)
 #define XUTILS_H
 
 
 
-long xdl_bogosqrt(long n);
-int xdl_cha_init(chastore_t *cha, long isize, long icount);
+int64_t xdl_bogosqrt(int64_t n);
+int xdl_cha_init(chastore_t *cha, int64_t isize, int64_t icount);
 void xdl_cha_free(chastore_t *cha);
 void *xdl_cha_alloc(chastore_t *cha);
-long xdl_guess_lines(mmfile_t *mf, long sample);
-int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags);
-unsigned long xdl_hash_record(char const **data, char const *top, long flags);
+int64_t xdl_guess_lines(mmfile_t *mf, int64_t sample);
+int xdl_recmatch(const char *l1, int64_t s1, const char *l2, int64_t s2, int64_t flags);
+uint64_t xdl_hash_record(char const **data, char const *top, int64_t flags);
 unsigned int xdl_hashbits(unsigned int size);
 
 
 
 #endif /* #if !defined(XUTILS_H) */