Performance boost by replacing TRUELENGTH -> STDVEC_TRUELENGTH for strings (no ALTREP strings + algorithms wouldn't work anymore).

Author: SebKrantz

src/chmatch.c

@@ -58,7 +58,7 @@ static SEXP chmatchMain(SEXP x, SEXP table, int nomatch, bool chin, bool chmatch
   savetl_init();
   for (int i=0; i<xlen; i++) {
     SEXP s = xd[i];
-    const int tl = TRULEN(s);
+    const int tl = STDVEC_TRUELENGTH(s);
     if (tl>0) {
       savetl(s);  // R's internal hash (which is positive); save it
       SET_TRULEN(s,0);
@@ -75,7 +75,7 @@ static SEXP chmatchMain(SEXP x, SEXP table, int nomatch, bool chin, bool chmatch
   int nuniq=0;
   for (int i=0; i<tablelen; ++i) {
     const SEXP s = td[i];
-    int tl = TRULEN(s);
+    int tl = STDVEC_TRUELENGTH(s);
     if (tl>0) { savetl(s); tl=0; }
     if (tl==0) SET_TRULEN(s, chmatchdup ? -(++nuniq) : -i-1); // first time seen this string in table
   }
@@ -105,12 +105,12 @@ static SEXP chmatchMain(SEXP x, SEXP table, int nomatch, bool chin, bool chmatch
       error(_("Failed to allocate %"PRIu64" bytes working memory in chmatchdup: length(table)=%d length(unique(table))=%d"), ((uint64_t)tablelen*2+nuniq)*sizeof(int), tablelen, nuniq);
       // # nocov end
     }
-    for (int i=0; i<tablelen; ++i) counts[-TRULEN(td[i])-1]++;
+    for (int i=0; i<tablelen; ++i) counts[-STDVEC_TRUELENGTH(td[i])-1]++;
     for (int i=0, sum=0; i<nuniq; ++i) { int tt=counts[i]; counts[i]=sum; sum+=tt+1; }
-    for (int i=0; i<tablelen; ++i) map[counts[-TRULEN(td[i])-1]++] = i+1;           // 0 is left ending each group thanks to the calloc
+    for (int i=0; i<tablelen; ++i) map[counts[-STDVEC_TRUELENGTH(td[i])-1]++] = i+1;           // 0 is left ending each group thanks to the calloc
     for (int i=0, last=0; i<nuniq; ++i) {int tt=counts[i]+1; counts[i]=last; last=tt;}  // rewind counts to the beginning of each group
     for (int i=0; i<xlen; ++i) {
-      int u = TRULEN(xd[i]);
+      int u = STDVEC_TRUELENGTH(xd[i]);
       if (u<0) {
         const int w = counts[-u-1]++;
         if (map[w]) { ansd[i]=map[w]; continue; }
@@ -123,11 +123,11 @@ static SEXP chmatchMain(SEXP x, SEXP table, int nomatch, bool chin, bool chmatch
     free(map);
   } else if (chin) {
     for (int i=0; i<xlen; i++) {
-      ansd[i] = TRULEN(xd[i])<0;
+      ansd[i] = STDVEC_TRUELENGTH(xd[i])<0;
     }
   } else {
     for (int i=0; i<xlen; i++) {
-      const int m = TRULEN(xd[i]);
+      const int m = STDVEC_TRUELENGTH(xd[i]);
       ansd[i] = (m<0) ? -m : nomatch;
     }
   }

src/forder.c

@@ -307,10 +307,10 @@ static void range_str(const SEXP *x, int n, uint64_t *out_min, uint64_t *out_max
       na_count++;
       continue;
     }
-    if (TRULEN(s)<0) continue;  // seen this group before
+    if (STDVEC_TRUELENGTH(s)<0) continue;  // seen this group before
     #pragma omp critical
-    if (TRULEN(s)>=0) {  // another thread may have set it while I was waiting, so check it again
-      if (TRULEN(s)>0)   // save any of R's own usage of tl (assumed positive, so we can both count and save in one scan), to restore
+    if (STDVEC_TRUELENGTH(s)>=0) {  // another thread may have set it while I was waiting, so check it again
+      if (STDVEC_TRUELENGTH(s)>0)   // save any of R's own usage of tl (assumed positive, so we can both count and save in one scan), to restore
         savetl(s);           // afterwards. From R 2.14.0, tl is initialized to 0, prior to that it was random so this step saved too much.
       // now save unique SEXP in ustr so i) we can loop through them afterwards and reset TRUELENGTH to 0 and ii) sort uniques when sorting too
       if (ustr_alloc<=ustr_n) {
@@ -351,7 +351,7 @@ static void range_str(const SEXP *x, int n, uint64_t *out_min, uint64_t *out_max
     for (int i=0; i<ustr_n; i++) {
       SEXP s = ustr3[i];
       if (LENGTH(s)>ustr_maxlen) ustr_maxlen=LENGTH(s);
-      if (TRULEN(s)>0) savetl(s);
+      if (STDVEC_TRUELENGTH(s)>0) savetl(s);
     }
     cradix(ustr3, ustr_n);  // sort to detect possible duplicates after converting; e.g. two different non-utf8 map to the same utf8
     SET_TRULEN(ustr3[0], -1);
@@ -365,7 +365,7 @@ static void range_str(const SEXP *x, int n, uint64_t *out_min, uint64_t *out_max
     if (!tl)
       STOP(_("Failed to alloc tl when converting strings to UTF8"));  // # nocov
     const SEXP *tt = STRING_PTR_RO(ustr2);
-    for (int i=0; i<ustr_n; i++) tl[i] = TRULEN(tt[i]);   // fetches the o in ustr3 into tl which is ordered by ustr
+    for (int i=0; i<ustr_n; i++) tl[i] = STDVEC_TRUELENGTH(tt[i]);   // fetches the o in ustr3 into tl which is ordered by ustr
     for (int i=0; i<ustr_n; i++) SET_TRULEN(ustr3[i], 0);    // reset to 0 tl of the UTF8 (and possibly non-UTF in ustr too)
     for (int i=0; i<ustr_n; i++) SET_TRULEN(ustr[i], tl[i]); // put back the o into ustr's tl
     free(tl);
@@ -766,7 +766,7 @@ SEXP forder(SEXP DT, SEXP by, SEXP retGrpArg, SEXP retStatsArg, SEXP sortGroupsA
           if (nalast==-1) anso[i]=0;
           elem = naval;
         } else {
-          elem = -TRULEN(xd[i]);
+          elem = -STDVEC_TRUELENGTH(xd[i]);
         }
         WRITE_KEY
       }}