xdiff: do away with xdl_mmfile_next()

diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c
index 0f571db2d7cc5ac85bd37cfe67d611898f339f0a..620fc9a657e2246d3a382c916c2cdd4f820c0c44 100644 (file)
--- a/xdiff/xprepare.c
+++ b/xdiff/xprepare.c
@@ -26,6 +26,8 @@
 #define XDL_KPDIS_RUN 4
 #define XDL_MAX_EQLIMIT 1024
 #define XDL_SIMSCAN_WINDOW 100
+#define XDL_GUESS_NLINES1 256
+#define XDL_GUESS_NLINES2 20
 
 
 typedef struct s_xdlclass {
@@ -154,20 +156,19 @@ static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp,
        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 *));
+       if (xpp->flags & XDF_HISTOGRAM_DIFF)
+               hbits = hsize = 0;
+       else {
+               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;;) {
-                       if (cur >= top) {
-                               if (!(cur = blk = xdl_mmfile_next(mf, &bsize)))
-                                       break;
-                               top = blk + bsize;
-                       }
+               for (top = blk + bsize; cur < top; ) {
                        prev = cur;
                        hav = xdl_hash_record(&cur, top, xpp->flags);
                        if (nrec >= narec) {
@@ -183,7 +184,8 @@ static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp,
                        crec->ha = hav;
                        recs[nrec++] = crec;
 
-                       if (xdl_classify_record(cf, rhash, hbits, crec) < 0)
+                       if (!(xpp->flags & XDF_HISTOGRAM_DIFF) &&
+                               xdl_classify_record(cf, rhash, hbits, crec) < 0)
                                goto abort;
                }
        }
@@ -234,13 +236,23 @@ static void xdl_free_ctx(xdfile_t *xdf) {
 
 int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
                    xdfenv_t *xe) {
-       long enl1, enl2;
+       long enl1, enl2, sample;
        xdlclassifier_t cf;
 
-       enl1 = xdl_guess_lines(mf1) + 1;
-       enl2 = xdl_guess_lines(mf2) + 1;
+       /*
+        * For histogram diff, we can afford a smaller sample size and
+        * thus a poorer estimate of the number of lines, as the hash
+        * table (rhash) won't be filled up/grown. The number of lines
+        * (nrecs) will be updated correctly anyway by
+        * xdl_prepare_ctx().
+        */
+       sample = xpp->flags & XDF_HISTOGRAM_DIFF ? XDL_GUESS_NLINES2 : 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) {
+       if (!(xpp->flags & XDF_HISTOGRAM_DIFF) &&
+               xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0) {
 
                return -1;
        }
@@ -257,9 +269,11 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
                return -1;
        }
 
-       xdl_free_classifier(&cf);
+       if (!(xpp->flags & XDF_HISTOGRAM_DIFF))
+               xdl_free_classifier(&cf);
 
        if (!(xpp->flags & XDF_PATIENCE_DIFF) &&
+                       !(xpp->flags & XDF_HISTOGRAM_DIFF) &&
                        xdl_optimize_ctxs(&xe->xdf1, &xe->xdf2) < 0) {
 
                xdl_free_ctx(&xe->xdf2);