]> granicus.if.org Git - pdns/commitdiff
add support for quantcast top million list in dnsbulktest
authorKees Monshouwer <mind04@monshouwer.org>
Sun, 8 Sep 2013 15:05:03 +0000 (17:05 +0200)
committermind04 <mind04@monshouwer.org>
Sun, 8 Sep 2013 16:25:42 +0000 (18:25 +0200)
pdns/dnsbulktest.cc
regression-tests/.gitignore

index 527f9807ae47706a9d1a3e6c8b09ffc957ed2bfb..e89c4693649676c76b146e3ff9ea29635738fdd8 100644 (file)
@@ -247,11 +247,17 @@ int main(int argc, char** argv)
   while(stringfgets(stdin, line)) {
     if(limit && domains.size() >= limit)
       break;
-      
+
     trim_right(line);
+    if(line.empty() || line[0] == '#')
+      continue;
     split=splitField(line,',');
+    if (split.second.empty())
+      split=splitField(line,'\t');
+    if(!split.second.find('.')) // skip 'Hidden profile' in quantcast list.
+      continue;
     pos=split.second.find('/');
-    if(pos != string::npos) // alexa has whole urls in the list now..
+    if(pos != string::npos) // alexa has whole urls in the list now.
       split.second.resize(pos);
     if(find_if(split.second.begin(), split.second.end(), isalpha) == split.second.end())
     {
index 42dbd1818381a1da17683e64bfa1b77416bfae21..6df8dbc81022d068b3207eddc497e05658280182 100644 (file)
@@ -26,6 +26,7 @@ real_result
 /recursor-bulktest/
 /recursor.log
 /top-1m.csv
+/Quantcast-Top-Million.txt
 /report.json
 /nsd.*
 /*.nsd