Patchwork D2686: xdiff: add a preprocessing step that trims files

login
register
mail settings
Submitter phabricator
Date March 9, 2018, 11:24 p.m.
Message ID <eb5c67843198d6fd137c3972511d60cf@localhost.localdomain>
Download mbox | patch
Permalink /patch/29217/
State Not Applicable
Headers show

Comments

phabricator - March 9, 2018, 11:24 p.m.
This revision was automatically updated to reflect the committed changes.
Closed by commit rHG665958f30789: xdiff: add a preprocessing step that trims files (authored by quark, committed by ).

REPOSITORY
  rHG Mercurial

CHANGES SINCE LAST UPDATE
  https://phab.mercurial-scm.org/D2686?vs=6797&id=6804

REVISION DETAIL
  https://phab.mercurial-scm.org/D2686

AFFECTED FILES
  mercurial/thirdparty/xdiff/xdiffi.c
  mercurial/thirdparty/xdiff/xprepare.c
  mercurial/thirdparty/xdiff/xtypes.h

CHANGE DETAILS




To: quark, #hg-reviewers, indygreg
Cc: indygreg, mercurial-devel

Patch

diff --git a/mercurial/thirdparty/xdiff/xtypes.h b/mercurial/thirdparty/xdiff/xtypes.h
--- a/mercurial/thirdparty/xdiff/xtypes.h
+++ b/mercurial/thirdparty/xdiff/xtypes.h
@@ -60,6 +60,10 @@ 
 
 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;
 } xdfenv_t;
 
 
diff --git a/mercurial/thirdparty/xdiff/xprepare.c b/mercurial/thirdparty/xdiff/xprepare.c
--- a/mercurial/thirdparty/xdiff/xprepare.c
+++ b/mercurial/thirdparty/xdiff/xprepare.c
@@ -156,6 +156,87 @@ 
 }
 
 
+/*
+ * 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,
+		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;
+	/* 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,
 			   xdlclassifier_t *cf, xdfile_t *xdf) {
 	unsigned int hbits;
@@ -254,10 +335,13 @@ 
 	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;
+	mmfile_t tmf1, tmf2;
 	xdlclassifier_t cf;
 
 	memset(&cf, 0, sizeof(cf));
@@ -270,12 +354,14 @@ 
 	if (xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0)
 		return -1;
 
-	if (xdl_prepare_ctx(1, mf1, enl1, xpp, &cf, &xe->xdf1) < 0) {
+	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, mf2, enl2, xpp, &cf, &xe->xdf2) < 0) {
+	if (xdl_prepare_ctx(2, &tmf2, enl2, xpp, &cf, &xe->xdf2) < 0) {
 
 		xdl_free_ctx(&xe->xdf1);
 		xdl_free_classifier(&cf);
diff --git a/mercurial/thirdparty/xdiff/xdiffi.c b/mercurial/thirdparty/xdiff/xdiffi.c
--- a/mercurial/thirdparty/xdiff/xdiffi.c
+++ b/mercurial/thirdparty/xdiff/xdiffi.c
@@ -1062,6 +1062,7 @@ 
 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;
 	xdchange_t *xch, *xche;
 
 	if (!xecfg->hunk_func)
@@ -1073,23 +1074,29 @@ 
 			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, i2, n2, ecb->priv) < 0)
+		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, xche->i1 + xche->chg1 - xch->i1,
-					xch->i2, xche->i2 + xche->chg2 - xch->i2,
+			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;
 		}