Better organisation of downloaded logs

This commit is contained in:
Spyros Zoupanos 2020-09-20 12:56:04 +03:00
parent 8a39ec44e0
commit 373f4fdbd8
3 changed files with 39 additions and 30 deletions

View File

@ -115,9 +115,10 @@ public class LaReferenciaDownloadLogs {
String inputLine;
while ((inputLine = in.readLine()) != null) {
response.append(inputLine);
response.append("\n");
// response.append("\n");
}
}
return response.toString();
} catch (Exception e) {
log.error("Failed to get URL: " + e);
@ -177,28 +178,28 @@ public class LaReferenciaDownloadLogs {
.info(
"Downloading logs for LaReferencia repoid " + laReferencialMatomoID + " and for "
+ sdf.format(date));
System.out.println("====> Downloading logs for LaReferencia repoid " + laReferencialMatomoID + " and for "
+ sdf.format(date));
System.out
.println(
"====> Downloading logs for LaReferencia repoid " + laReferencialMatomoID + " and for "
+ sdf.format(date));
String period = "&period=day&date=" + sdf.format(date);
String outFolder = "";
outFolder = repoLogsPath;
FileSystem fs = FileSystem.get(new Configuration());
FSDataOutputStream fin = fs
.create(
new Path(outFolder + "/" + laReferencialMatomoID + "_LaRefPiwiklog" + sdf.format((date)) + ".json"),
true);
String baseApiUrl = getPiwikLogUrl() + APImethod + "&idSite=" + laReferencialMatomoID + period + format
+ "&expanded=5&filter_limit=1000&token_auth=" + tokenAuth;
String content = "";
int i = 0;
while (!content.equals("[]\n")) {
FSDataOutputStream fin = fs
.create(
new Path(outFolder + "/" + laReferencialMatomoID + "_LaRefPiwiklog" + sdf.format((date)) + "_"
+ i + ".json"),
true);
JSONParser parser = new JSONParser();
while (!content.equals("[]")) {
String apiUrl = baseApiUrl;
if (i > 0) {
@ -207,16 +208,22 @@ public class LaReferenciaDownloadLogs {
content = getJson(apiUrl);
fin.write(content.getBytes());
JSONArray jsonArray = (JSONArray) parser.parse(content);
for (Object aJsonArray : jsonArray) {
JSONObject jsonObjectRaw = (JSONObject) aJsonArray;
fin.write(jsonObjectRaw.toJSONString().getBytes());
fin.writeChar('\n');
}
System.out
.println(
"====> Downloaded part " + i + " of logs for LaReferencia repoid " + laReferencialMatomoID
+ " and for "
+ sdf.format(date));
i++;
fin.close();
}
// fin.close();
// out.close();
fin.close();
}
// }
}
}

View File

@ -103,17 +103,18 @@ public class LaReferenciaStats {
public void processLogs() throws Exception {
try {
System.out.println("====> Processing LaReferencia repository logs");
processlaReferenciaLog();
System.out.println("====> LaReferencia repository logs process done");
log.info("LaReferencia repository process done");
removeDoubleClicks();
log.info("LaReferencia removing double clicks done");
viewsStats();
log.info("LaReferencia views done");
downloadsStats();
log.info("LaReferencia downloads done");
updateProdTables();
log.info("LaReferencia update productions tables done");
// removeDoubleClicks();
// log.info("LaReferencia removing double clicks done");
// viewsStats();
// log.info("LaReferencia views done");
// downloadsStats();
// log.info("LaReferencia downloads done");
// updateProdTables();
// log.info("LaReferencia update productions tables done");
} catch (Exception e) {
log.error("Failed to process logs: " + e);

View File

@ -62,8 +62,9 @@ public class UsageStatsExporter {
System.out.println("====> Downloading LaReferencia logs");
lrf.GetLaReferenciaRepos(lareferenciaLogPath);
System.out.println("====> Downloaded LaReferencia logs");
LaReferenciaStats lastats = new LaReferenciaStats(lareferenciaLogPath);
// lastats.processLogs();
LaReferenciaStats lastats = new LaReferenciaStats(lareferenciaLogPath);
System.out.println("====> Processing LaReferencia logs");
lastats.processLogs();
// log.info("LaReferencia logs done");
// IrusStats irusstats = new IrusStats(irusUKBaseURL);