From: Kees Monshouwer Date: Sun, 8 Sep 2013 15:05:03 +0000 (+0200) Subject: add support for quantcast top million list in dnsbulktest X-Git-Tag: rec-3.6.0-rc1~450^2 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=246ccf7b1dd86bff5637598ba58d59853de41231;p=pdns add support for quantcast top million list in dnsbulktest --- diff --git a/pdns/dnsbulktest.cc b/pdns/dnsbulktest.cc index 527f9807a..e89c46936 100644 --- a/pdns/dnsbulktest.cc +++ b/pdns/dnsbulktest.cc @@ -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()) { diff --git a/regression-tests/.gitignore b/regression-tests/.gitignore index 42dbd1818..6df8dbc81 100644 --- a/regression-tests/.gitignore +++ b/regression-tests/.gitignore @@ -26,6 +26,7 @@ real_result /recursor-bulktest/ /recursor.log /top-1m.csv +/Quantcast-Top-Million.txt /report.json /nsd.* /*.nsd