Fix duplicate colon in warcinfo header

commoncrawl · Oct 29, 2021 · fb1c64d · fb1c64d
1 parent 2c62b3c
commit fb1c64d
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/src/main/java/org/commoncrawl/stormcrawler/news/CrawlTopology.java b/src/main/java/org/commoncrawl/stormcrawler/news/CrawlTopology.java
@@ -122,7 +122,7 @@ protected WARCHdfsBolt getWarcBolt(String filePrefix) {
         fileNameFormat.withPrefix(filePrefix);
 
         Map<String, String> fields = new LinkedHashMap<>();
-        fields.put("software:", "StormCrawler 1.17 https://stormcrawler.net/");
+        fields.put("software", "StormCrawler 1.17 https://stormcrawler.net/");
         fields.put("description", "News crawl for Common Crawl");
         String userAgent = AbstractHttpProtocol.getAgentString(getConf());
         fields.put("http-header-user-agent", userAgent);