xdiff: remove whitespace related feature

In Mercurial, whitespace related handling are done at a higher level than
the low-level diff algorithm so "ignore spaces". So it's not used by mdiff.
Some of the upcoming optimizations would be more difficult with whitespace
related features kept. So let's remove them.

Differential Revision: https://phab.mercurial-scm.org/D2683

mercurial/thirdparty/xdiff/xdiff.h

@@ -1,150 +1,139
 /*
  *  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_IGNORE_WHITESPACE (1 << 1)
-#define XDF_IGNORE_WHITESPACE_CHANGE (1 << 2)
-#define XDF_IGNORE_WHITESPACE_AT_EOL (1 << 3)
-#define XDF_IGNORE_CR_AT_EOL (1 << 4)
-#define XDF_WHITESPACE_FLAGS (XDF_IGNORE_WHITESPACE | \
-			      XDF_IGNORE_WHITESPACE_CHANGE | \
-			      XDF_IGNORE_WHITESPACE_AT_EOL | \
-			      XDF_IGNORE_CR_AT_EOL)
-
-#define XDF_IGNORE_BLANK_LINES (1 << 7)
-
 #define XDF_INDENT_HEURISTIC (1 << 23)
 
 /* xdemitconf_t.flags */
 #define XDL_EMIT_FUNCNAMES (1 << 0)
 #define XDL_EMIT_FUNCCONTEXT (1 << 2)
 /* 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)
 
 #define XDL_MMB_READONLY (1 << 0)
 
 #define XDL_MMF_ATOMIC (1 << 0)
 
 #define XDL_BDOP_INS 1
 #define XDL_BDOP_CPY 2
 #define XDL_BDOP_INSB 3
 
 /* merge simplification levels */
 #define XDL_MERGE_MINIMAL 0
 #define XDL_MERGE_EAGER 1
 #define XDL_MERGE_ZEALOUS 2
 #define XDL_MERGE_ZEALOUS_ALNUM 3
 
 /* merge favor modes */
 #define XDL_MERGE_FAVOR_OURS 1
 #define XDL_MERGE_FAVOR_THEIRS 2
 #define XDL_MERGE_FAVOR_UNION 3
 
 /* merge output styles */
 #define XDL_MERGE_DIFF3 1
 
 typedef struct s_mmfile {
 	char *ptr;
 	long size;
 } mmfile_t;
 
 typedef struct s_mmbuffer {
 	char *ptr;
 	long size;
 } mmbuffer_t;
 
 typedef struct s_xpparam {
 	unsigned long flags;
 
 	/* See Documentation/diff-options.txt. */
 	char **anchors;
 	size_t anchors_nr;
 } xpparam_t;
 
 typedef struct s_xdemitcb {
 	void *priv;
 	int (*outf)(void *, mmbuffer_t *, int);
 } xdemitcb_t;
 
 typedef long (*find_func_t)(const char *line, long line_len, char *buffer, long buffer_size, void *priv);
 
 typedef int (*xdl_emit_hunk_consume_func_t)(long start_a, long count_a,
 					    long start_b, long count_b,
 					    void *cb_data);
 
 typedef struct s_xdemitconf {
 	long ctxlen;
 	long interhunkctxlen;
 	unsigned long flags;
 	find_func_t find_func;
 	void *find_func_priv;
 	xdl_emit_hunk_consume_func_t hunk_func;
 } xdemitconf_t;
 
 typedef struct s_bdiffparam {
 	long bsize;
 } bdiffparam_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);
 
 int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 	     xdemitconf_t const *xecfg, xdemitcb_t *ecb);
 
 typedef struct s_xmparam {
 	xpparam_t xpp;
 	int marker_size;
 	int level;
 	int favor;
 	int style;
 	const char *ancestor;	/* label for orig */
 	const char *file1;	/* label for mf1 */
 	const char *file2;	/* label for mf2 */
 } xmparam_t;
 
 #define DEFAULT_CONFLICT_MARKER_SIZE 7
 
 int xdl_merge(mmfile_t *orig, mmfile_t *mf1, mmfile_t *mf2,
 		xmparam_t const *xmp, mmbuffer_t *result);
 
 #ifdef __cplusplus
 }
 #endif /* #ifdef __cplusplus */
 
 #endif /* #if !defined(XDIFF_H) */

mercurial/thirdparty/xdiff/xdiffi.c

@@ -1,1094 +1,1071
 /*
  *  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;
 	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,
 		      xdalgoenv_t *xenv);
 static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, long 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,
 		      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;
 
 	/*
 	 * 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;
 
 			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;
 
 	/*
 	 * 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;
 
 		for (; off2 < lim2; off2++)
 			rchg2[rindex2[off2]] = 1;
 	} else if (off2 == lim2) {
 		char *rchg1 = dd1->rchg;
 		long *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;
 	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)))) {
 
 		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) {
 	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)
 {
 	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;
 	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,
 			  struct split_measurement *m)
 {
 	long 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;
 
 	/*
 	 * The index of the first unchanged line after the group. For an empty
 	 * group, end is equal to start.
 	 */
 	long 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)
 {
 	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)
 {
 	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) {
 	struct xdlgroup g, go;
 	long earliest_end, end_matching_other;
 	long 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;
 			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;
 
 	/*
 	 * 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);
 	}
 }
 
 static int xdl_call_hunk_func(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 			      xdemitconf_t const *xecfg)
 {
 	xdchange_t *xch, *xche;
 	if ((xecfg->flags & XDL_EMIT_BDIFFHUNK) != 0) {
 		long 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->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, i2, n2, 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, xche->i1 + xche->chg1 - xch->i1,
 					xch->i2, xche->i2 + xche->chg2 - xch->i2,
 					ecb->priv) < 0)
 				return -1;
 		}
 	}
 	return 0;
 }
 
-static void xdl_mark_ignorable(xdchange_t *xscr, xdfenv_t *xe, long flags)
-{
-	xdchange_t *xch;
-
-	for (xch = xscr; xch; xch = xch->next) {
-		int ignore = 1;
-		xrecord_t **rec;
-		long i;
-
-		rec = &xe->xdf1.recs[xch->i1];
-		for (i = 0; i < xch->chg1 && ignore; i++)
-			ignore = xdl_blankline(rec[i]->ptr, rec[i]->size, flags);
-
-		rec = &xe->xdf2.recs[xch->i2];
-		for (i = 0; i < xch->chg2 && ignore; i++)
-			ignore = xdl_blankline(rec[i]->ptr, rec[i]->size, flags);
-
-		xch->ignore = ignore;
-	}
-}
-
 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;
 	emit_func_t ef = xecfg->hunk_func ? xdl_call_hunk_func : xdl_emit_diff;
 
 	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 (xpp->flags & XDF_IGNORE_BLANK_LINES)
-		xdl_mark_ignorable(xscr, &xe, xpp->flags);
 	if (ef(&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/xutils.c

@@ -1,425 +1,274
 /*
  *  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;
 
 	/*
 	 * 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;
 }
 
 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_blankline(const char *line, long size, long flags)
-{
-	long i;
-
-	if (!(flags & XDF_WHITESPACE_FLAGS))
-		return (size <= 1);
-
-	for (i = 0; i < size && XDL_ISSPACE(line[i]); i++)
-		;
-
-	return (i == size);
-}
-
-/*
- * Have we eaten everything on the line, except for an optional
- * CR at the very end?
- */
-static int ends_with_optional_cr(const char *l, long s, long i)
-{
-	int complete = s && l[s-1] == '\n';
-
-	if (complete)
-		s--;
-	if (s == i)
-		return 1;
-	/* do not ignore CR at the end of an incomplete line */
-	if (complete && s == i + 1 && l[i] == '\r')
-		return 1;
-	return 0;
-}
-
 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,
-	 * which in turn matches everything that matches with --ignore-cr-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]) {
-			i1++;
-			i2++;
-		}
-	} else if (flags & XDF_IGNORE_CR_AT_EOL) {
-		/* Find the first difference and see how the line ends */
-		while (i1 < s1 && i2 < s2 && l1[i1] == l2[i2]) {
-			i1++;
-			i2++;
-		}
-		return (ends_with_optional_cr(l1, s1, i1) &&
-			ends_with_optional_cr(l2, s2, i2));
-	}
-
-	/*
-	 * 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;
-	int cr_at_eol_only = (flags & XDF_WHITESPACE_FLAGS) == XDF_IGNORE_CR_AT_EOL;
-
-	for (; ptr < top && *ptr != '\n'; ptr++) {
-		if (cr_at_eol_only) {
-			/* do not ignore CR at the end of an incomplete line */
-			if (*ptr == '\r' &&
-			    (ptr + 1 < top && ptr[1] == '\n'))
-				continue;
-		}
-		else 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;
+	return 0;
 }
 
 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;
 }
 
 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;
 }
 
 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;
 }

mercurial/thirdparty/xdiff/xutils.h

@@ -1,47 +1,46
 /*
  *  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_emit_diffrec(char const *rec, long size, char const *pre, long psize,
 		     xdemitcb_t *ecb);
 int xdl_cha_init(chastore_t *cha, long isize, long 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_blankline(const char *line, long size, long flags);
 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);
 unsigned int xdl_hashbits(unsigned int size);
 int xdl_num_out(char *out, long val);
 int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2,
 		      const char *func, long funclen, xdemitcb_t *ecb);
 int xdl_fall_back_diff(xdfenv_t *diff_env, xpparam_t const *xpp,
 		       int line1, int count1, int line2, int count2);
 
 
 
 #endif /* #if !defined(XUTILS_H) */