Mirror/MarginaliaSearch
1
0
Fork 0
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-02-24 05:18:58 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

(converter) More robust filename resolution

Browse Source
This commit is contained in:
Viktor Lofgren 2023-10-20 14:16:03 +02:00
parent d76d926c38
commit 10fc489822
1 changed files with 10 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
code/process-models/crawling-model/src/main/java/plan/CrawlPlan.java
View File

@ -7,6 +7,7 @@ import nu.marginalia.crawling.io.CrawledDomainReader;
import nu.marginalia.crawling.io.SerializableCrawlDataStream; import nu.marginalia.crawling.io.SerializableCrawlDataStream;
import nu.marginalia.crawling.model.CrawledDomain; import nu.marginalia.crawling.model.CrawledDomain;
import nu.marginalia.process.log.WorkLog; import nu.marginalia.process.log.WorkLog;
import org.apache.logging.log4j.util.Strings;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
@ -23,7 +24,7 @@ public class CrawlPlan {
public WorkDir crawl; public WorkDir crawl;
public WorkDir process; public WorkDir process;
private static String rootDirRewrite = System.getProperty("crawl.rootDirRewrite"); private final static String rootDirRewrite = System.getProperty("crawl.rootDirRewrite");
public Path getJobSpec() { public Path getJobSpec() {
return Path.of(rewrite(jobSpec)); return Path.of(rewrite(jobSpec));
@ -52,25 +53,19 @@ public class CrawlPlan {
} }
public Path getCrawledFilePath(String fileName) { public Path getCrawledFilePath(String fileName) {
int sp = fileName.lastIndexOf('/');
// Normalize the filename
if (sp >= 0 && sp + 1< fileName.length())
fileName = fileName.substring(sp + 1);
if (fileName.length() < 4)
fileName = Strings.repeat("0", 4 - fileName.length()) + fileName;
String sp1 = fileName.substring(0, 2); String sp1 = fileName.substring(0, 2);
String sp2 = fileName.substring(2, 4); String sp2 = fileName.substring(2, 4);
return crawl.getDir().resolve(sp1).resolve(sp2).resolve(fileName); return crawl.getDir().resolve(sp1).resolve(sp2).resolve(fileName);
} }
public Path getProcessedFilePath(String fileName) {
String sp1 = fileName.substring(0, 2);
String sp2 = fileName.substring(2, 4);
return process.getDir().resolve(sp1).resolve(sp2).resolve(fileName);
}
public WorkLog createCrawlWorkLog() throws IOException {
return new WorkLog(crawl.getLogFile());
}
public WorkLog createProcessWorkLog() throws IOException {
return new WorkLog(process.getLogFile());
}
public int countCrawledDomains() { public int countCrawledDomains() {
int count = 0; int count = 0;
for (var ignored : WorkLog.iterable(crawl.getLogFile())) { for (var ignored : WorkLog.iterable(crawl.getLogFile())) {
@ -93,26 +88,6 @@ public class CrawlPlan {
}); });
} }
public Iterable<CrawledDomain> domainsIterable(Predicate<String> idPredicate) {
final CrawledDomainReader reader = new CrawledDomainReader();
return WorkLog.iterableMap(crawl.getLogFile(),
entry -> {
if (!idPredicate.test(entry.id())) {
return Optional.empty();
}
var path = getCrawledFilePath(entry.path());
if (!Files.exists(path)) {
logger.warn("File not found: {}", path);
return Optional.empty();
}
return reader.readOptionally(path);
});
}
public Iterable<SerializableCrawlDataStream> crawlDataIterable(Predicate<String> idPredicate) { public Iterable<SerializableCrawlDataStream> crawlDataIterable(Predicate<String> idPredicate) {
final CrawledDomainReader reader = new CrawledDomainReader(); final CrawledDomainReader reader = new CrawledDomainReader();