- Exclude empty and null urls in the assignments.

- Update the "getFullTextsImproved"-call to "getFullTexts", now that the "improved" version is stable.
- Update Gradle.
- Code polishing.

README.md

@@ -25,4 +25,4 @@ If you want to build and run the app on a **Docker Container**, then run the scr
 
 Implementation notes:
 - For transferring the full-text files, we use Facebook's [**Zstandard**](https://facebook.github.io/zstd/) compression algorithm, which brings very big benefits in compression rate and speed.
-- The names of the uploaded full-text files ae of the following form: "***datasourceID/recordId::fileHash.pdf***"
+- The uploaded full-text files follow this naming-scheme: "**datasourceID/recordId::fileHash.pdf**"

gradle/wrapper/gradle-wrapper.properties

@@ -1,6 +1,6 @@
 distributionBase=GRADLE_USER_HOME
 distributionPath=wrapper/dists
-distributionUrl=https\://services.gradle.org/distributions/gradle-7.6-bin.zip
+distributionUrl=https\://services.gradle.org/distributions/gradle-8.0-bin.zip
 networkTimeout=10000
 zipStoreBase=GRADLE_USER_HOME
 zipStorePath=wrapper/dists

installAndRun.sh

@@ -26,7 +26,7 @@ if [[ justInstall -eq 1 && shouldRunInDocker -eq 1 ]]; then
   justInstall=0
 fi
 
-gradleVersion="7.6"
+gradleVersion="8.0"
 
 if [[ justInstall -eq 0 ]]; then
 

src/main/java/eu/openaire/urls_controller/controllers/UrlController.java

@@ -94,21 +94,23 @@ public class UrlController {
                             "from " + ImpalaConnector.databaseName + ".publication p\n" +
                         "join " + ImpalaConnector.databaseName + ".publication_urls pu on pu.id=p.id\n" +
                         "join " + ImpalaConnector.databaseName + ".datasource d on d.id=p.datasourceid\n" +
-                        "left outer join (select count(a.id) as counts, a.id from " + ImpalaConnector.databaseName + ".attempt a group by a.id) as attempts on attempts.id=p.id\n" +
+                        "left outer join (select count(a.id) as counts, a.id from " + ImpalaConnector.databaseName + ".attempt a group by a.id) as attempts\n" +
+                                    "on attempts.id=p.id\n" +
                         "left outer join (select a.id, a.original_url from " + ImpalaConnector.databaseName + ".assignment a\n" +
                                             "union all\n" +
-                                            "select pl.id, pl.original_url from " + ImpalaConnector.databaseName + ".payload pl)\n" +
+                                            "select pl.id, pl.original_url from " + ImpalaConnector.databaseName + ".payload pl) as existing\n" +
-                                            "as existing on existing.id=p.id and existing.original_url=pu.url\n" +
+                                        "on existing.id=p.id and existing.original_url=pu.url\n" +
                         "where d.allow_harvest=true and existing.id is null and coalesce(attempts.counts, 0) <= " + maxAttemptsPerRecordAtomic.get() +
                             "\nand not exists (select 1 from " + ImpalaConnector.databaseName + ".attempt a where a.id=p.id and a.error_class = 'noRetry' limit 1)\n" +
-                        "limit " + (assignmentsLimit * 10) + ")\n" +
+                            "and pu.url != '' and pu.url is not null\n" +   // Some IDs have empty-string urls, there are no "null" urls, but keep the relevant check for future-proofing.
-                        "as non_distinct_results\n" +
+                        "limit " + (assignmentsLimit * 10) +
+                    ")\nas non_distinct_results\n" +
                     "order by coalesce(attempt_count, 0), reverse(pubid), url\n" +
-                    "limit " + assignmentsLimit + ")\n" +
+                    "limit " + assignmentsLimit +
-                "as findAssignmentsQuery";
+                "\n) as findAssignmentsQuery";
 
         // The "order by" in the end makes sure the older attempted records will be re-attempted after a long time.
-        //logger.debug(findAssignmentsQuery); // DEBUG!
+        //logger.debug("findAssignmentsQuery:\n" + findAssignmentsQuery); // DEBUG!
 
         String getAssignmentsQuery = "select * from " + ImpalaConnector.databaseName + ".current_assignment";
 

src/main/java/eu/openaire/urls_controller/services/StatsService.java

@@ -67,4 +67,8 @@ public class StatsService {
         }
     }
 
+    // To get the human-friendly timestamp format from the BigInt in the database:
+    // select from_timestamp(CAST(CAST(`date` as decimal(30,0))/1000 AS timestamp), "yyyy-MM-dd HH:mm:ss.SSS") from payload
+
+
 }

src/main/java/eu/openaire/urls_controller/util/FileUtils.java

@@ -237,7 +237,7 @@ public class FileUtils {
             logger.debug("The assignments_" + assignmentsBatchCounter + " have " + numAllFullTexts + " distinct non-already-uploaded fullTexts. Going to request them from the Worker \"" + workerId + "\", in " + numOfBatches + " batches (" + numOfFullTextsPerBatch + " files each).");
 
         // Check if one full text is left out because of the division. Put it int the last batch.
-        String baseUrl = "http://" + remoteAddr + ":1881/api/full-texts/getFullTextsImproved/" + assignmentsBatchCounter + "/" + numOfBatches + "/";
+        String baseUrl = "http://" + remoteAddr + ":1881/api/full-texts/getFullTexts/" + assignmentsBatchCounter + "/" + numOfBatches + "/";
 
         // TODO - The worker should send the port in which it accepts requests, along with the current request.
         // TODO - The least we have to do it to expose the port-assignment somewhere more obvious like inside the "application.properties" file.