add comments

Author: ben-schwen

inst/tests/tests.Rraw

@@ -19067,6 +19067,7 @@ test(2281.2, fwrite(data.table(a=.POSIXct(0.0001)), dec=',', sep=';'), output="1
 # rbindlist(l, use.names=TRUE) should handle different colnames encodings #5452
 x = data.table(a = 1, b = 2, c = 3)
 y = data.table(x = 4, y = 5, z = 6)
+# a-umlaut, o-umlaut, u-umlaut
 setnames(x , c("\u00e4", "\u00f6", "\u00fc"))
 setnames(y , iconv(c("\u00f6", "\u00fc", "\u00e4"), from = "UTF-8", to = "latin1"))
 test(2282.1, rbindlist(list(x,y), use.names=TRUE), data.table("\u00e4"=c(1,6), "\u00f6"=c(2,4), "\u00fc"=c(3,5)))

src/rbindlist.c

@@ -74,6 +74,7 @@ SEXP rbindlist(SEXP l, SEXP usenamesArg, SEXP fillArg, SEXP idcolArg, SEXP ignor
       error(_("Failed to allocate upper bound of %"PRId64" unique column names [sum(lapply(l,ncol))]"), (int64_t)upperBoundUniqueNames);
     savetl_init();
     int nuniq=0;
+    // first pass - gather unique column names
     for (int i=0; i<LENGTH(l); i++) {
       SEXP li = VECTOR_ELT(l, i);
       int thisncol=LENGTH(li);
@@ -89,11 +90,8 @@ SEXP rbindlist(SEXP l, SEXP usenamesArg, SEXP fillArg, SEXP idcolArg, SEXP ignor
         SET_TRUELENGTH(s,-nuniq);
       }
     }
-    if (nuniq>0) {
-      SEXP *tt = realloc(uniq, nuniq*sizeof(SEXP));  // shrink to only what we need to release the spare
-      if (!tt) free(uniq);  // shrink never fails; just keep codacy happy
-      uniq = tt;
-    }
+    if (nuniq>0) uniq = realloc(uniq, nuniq*sizeof(SEXP));  // shrink to only what we need to release the spare
+
     // now count the dups (if any) and how they're distributed across the items
     int *counts = (int *)calloc(nuniq, sizeof(int)); // counts of names for each colnames
     int *maxdup = (int *)calloc(nuniq, sizeof(int)); // the most number of dups for any name within one colname vector
@@ -105,6 +103,7 @@ SEXP rbindlist(SEXP l, SEXP usenamesArg, SEXP fillArg, SEXP idcolArg, SEXP ignor
       error(_("Failed to allocate nuniq=%d items working memory in rbindlist.c"), nuniq);
       // # nocov end
     }
+    // second pass - count duplicates
     for (int i=0; i<LENGTH(l); i++) {
       SEXP li = VECTOR_ELT(l, i);
       int thisncol=length(li);
@@ -143,6 +142,7 @@ SEXP rbindlist(SEXP l, SEXP usenamesArg, SEXP fillArg, SEXP idcolArg, SEXP ignor
     for (int i=0; i<ncol; ++i) {uniqMap[i] = dupLink[i] = -1;}
     int nextCol=0, lastDup=ncol-1;
 
+    // third pass - create final column mapping colMapRaw
     for (int i=0; i<LENGTH(l); ++i) {
       SEXP li = VECTOR_ELT(l, i);
       int thisncol=length(li);