refactoring; webapp context set to bioschemas

This commit is contained in:
Enrico Ottonello 2022-06-07 13:38:14 +02:00
parent 079b2506e6
commit 8a18fe11ec
17 changed files with 60 additions and 60 deletions

View File

@ -1,7 +1,7 @@
{
"type_source": "SVN",
"goal": "package -U source:jar",
"url": "http://svn-public.driver.research-infrastructures.eu/driver/dnet50/modules/dnet-bmuse-webapp/trunk/",
"url": "http://svn-public.driver.research-infrastructures.eu/driver/dnet50/modules/dnet-bioschemas-api/trunk/",
"deploy_repository": "dnet5-snapshots",
"version": "5",
"mail": "sandro.labruzzo@isti.cnr.it,michele.artini@isti.cnr.it, claudio.atzori@isti.cnr.it, alessia.bardi@isti.cnr.it, enrico.ottonello@isti.cnr.it",

View File

@ -1,4 +1,4 @@
package eu.dnetlib.bmuse_webapp;
package eu.dnetlib.bioschemas.api;
import org.springframework.context.annotation.Configuration;
import org.springframework.context.annotation.Profile;

View File

@ -1,4 +1,4 @@
package eu.dnetlib.bmuse_webapp;
package eu.dnetlib.bioschemas.api;
import eu.dnetlib.common.app.AbstractDnetApp;
import org.springframework.boot.SpringApplication;

View File

@ -1,10 +1,10 @@
package eu.dnetlib.bmuse_webapp;
package eu.dnetlib.bioschemas.api;
import eu.dnetlib.bmuse_webapp.crawl.CrawlRecord;
import eu.dnetlib.bmuse_webapp.scraper.BMUSEScraper;
import eu.dnetlib.bmuse_webapp.scraper.ScrapeState;
import eu.dnetlib.bmuse_webapp.scraper.ScrapeThread;
import eu.dnetlib.bmuse_webapp.utils.UrlParser;
import eu.dnetlib.bioschemas.api.crawl.CrawlRecord;
import eu.dnetlib.bioschemas.api.scraper.BMUSEScraper;
import eu.dnetlib.bioschemas.api.scraper.ScrapeState;
import eu.dnetlib.bioschemas.api.scraper.ScrapeThread;
import eu.dnetlib.bioschemas.api.utils.UrlParser;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.jsoup.nodes.Element;

View File

@ -1,4 +1,4 @@
package eu.dnetlib.bmuse_webapp.crawl;
package eu.dnetlib.bioschemas.api.crawl;
import java.util.Date;

View File

@ -1,8 +1,8 @@
package eu.dnetlib.bmuse_webapp.crawl;
package eu.dnetlib.bioschemas.api.crawl;
/**
*
* {@link eu.dnetlib.bmuse_webapp.crawl.StatusOfScrape} describes the possible status levels the scrape for each URL/CrawlRecord.
* {@link StatusOfScrape} describes the possible status levels the scrape for each URL/CrawlRecord.
*
* Each URL/CrawlRecord can have one of the following:
* DOES_NOT_EXIST = 404.

View File

@ -1,6 +1,6 @@
package eu.dnetlib.bmuse_webapp.publisher;
package eu.dnetlib.bioschemas.api.publisher;
import eu.dnetlib.bmuse_webapp.ServiceScrapeDriver;
import eu.dnetlib.bioschemas.api.ServiceScrapeDriver;
import eu.dnetlib.common.controller.AbstractDnetController;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.LineIterator;
@ -24,17 +24,17 @@ import java.nio.charset.StandardCharsets;
@RestController
@RequestMapping("/api")
public class BMUSEWebappController extends AbstractDnetController {
public class BioschemasAPIController extends AbstractDnetController {
@Value("${outputFolder}")
private String outputFolder;
@Value("${outputDataPattern}")
private String outputDataPattern;
private static Logger logger = LoggerFactory.getLogger(BMUSEWebappController.class);
private static Logger logger = LoggerFactory.getLogger(BioschemasAPIController.class);
@RequestMapping(value = "/startScraping", method = RequestMethod.GET)
public String startScraping(@RequestParam final String datasourceKey, @RequestParam final String sitemapUrl) throws BMUSEWebappException, IOException {
public String startScraping(@RequestParam final String datasourceKey, @RequestParam final String sitemapUrl) throws BioschemasException, IOException {
logger.info("<STARTSCRAPING> datasourceKey: "+datasourceKey+" sitemapUrl:"+sitemapUrl);
@ -46,7 +46,7 @@ public class BMUSEWebappController extends AbstractDnetController {
}
@RequestMapping(value = "/getNQuads", method = RequestMethod.GET)
public String getNQuads(@RequestParam final String datasourceKey, HttpServletResponse response) throws BMUSEWebappException, IOException {
public String getNQuads(@RequestParam final String datasourceKey, HttpServletResponse response) throws BioschemasException, IOException {
logger.info("<GETNQUADS> datasourceKey: "+datasourceKey);

View File

@ -0,0 +1,28 @@
package eu.dnetlib.bioschemas.api.publisher;
/**
* @author enrico.ottonello
*
*/
public class BioschemasException extends Exception{
public BioschemasException() {
}
public BioschemasException(final String message) {
super(message);
}
public BioschemasException(final String message, final Throwable cause) {
super(message, cause);
}
public BioschemasException(final Throwable cause) {
super(cause);
}
public BioschemasException(final String message, final Throwable cause, final boolean enableSuppression, final boolean writableStackTrace) {
super(message, cause, enableSuppression, writableStackTrace);
}
}

View File

@ -1,4 +1,4 @@
package eu.dnetlib.bmuse_webapp.publisher;
package eu.dnetlib.bioschemas.api.publisher;
import eu.dnetlib.common.controller.AbstractDnetController;
import org.springframework.stereotype.Controller;

View File

@ -1,5 +1,5 @@
package eu.dnetlib.bmuse_webapp.scraper;
package eu.dnetlib.bioschemas.api.scraper;
import hwu.elixir.scrape.exceptions.MissingMarkupException;
import hwu.elixir.scrape.scraper.ScraperFilteredCore;

View File

@ -1,7 +1,7 @@
package eu.dnetlib.bmuse_webapp.scraper;
package eu.dnetlib.bioschemas.api.scraper;
import eu.dnetlib.bmuse_webapp.crawl.CrawlRecord;
import eu.dnetlib.bmuse_webapp.crawl.StatusOfScrape;
import eu.dnetlib.bioschemas.api.crawl.StatusOfScrape;
import eu.dnetlib.bioschemas.api.crawl.CrawlRecord;
import java.util.ArrayList;
import java.util.Collections;

View File

@ -1,7 +1,7 @@
package eu.dnetlib.bmuse_webapp.scraper;
package eu.dnetlib.bioschemas.api.scraper;
import eu.dnetlib.bmuse_webapp.crawl.CrawlRecord;
import eu.dnetlib.bmuse_webapp.utils.CompressorUtil;
import eu.dnetlib.bioschemas.api.crawl.CrawlRecord;
import eu.dnetlib.bioschemas.api.utils.CompressorUtil;
import hwu.elixir.scrape.exceptions.CannotWriteException;
import hwu.elixir.scrape.exceptions.FourZeroFourException;
import hwu.elixir.scrape.exceptions.JsonLDInspectionException;
@ -63,7 +63,7 @@ public class ScrapeThread extends Thread {
try {
String nquads = process.getNQUADSFromUrl(record.getUrl(), true);
logger.info("downloaded "+record.getUrl() + " leftToScrape:" + scrapeState.pagesLeftToScrape());
logger.info("downloaded "+record.getUrl() + " leftToScrape:" + scrapeState.getNumberPagesLeftToScrape());
record.setNquads(CompressorUtil.compressValue(nquads));
if (!nquads.isEmpty()) {
scrapeState.addSuccessfulScrapedURL(record);

View File

@ -1,6 +1,6 @@
package eu.dnetlib.bmuse_webapp.scraper;
package eu.dnetlib.bioschemas.api.scraper;
import eu.dnetlib.bmuse_webapp.crawl.StatusOfScrape;
import eu.dnetlib.bioschemas.api.crawl.StatusOfScrape;
import hwu.elixir.scrape.exceptions.*;
import hwu.elixir.scrape.scraper.ScraperFilteredCore;
import org.slf4j.Logger;

View File

@ -1,4 +1,4 @@
package eu.dnetlib.bmuse_webapp.utils;
package eu.dnetlib.bioschemas.api.utils;
import org.apache.commons.codec.binary.Base64;
import org.apache.commons.io.IOUtils;

View File

@ -1,5 +1,5 @@
package eu.dnetlib.bmuse_webapp.utils;
package eu.dnetlib.bioschemas.api.utils;
import hwu.elixir.utils.Helpers;
import org.jsoup.Jsoup;

View File

@ -1,28 +0,0 @@
package eu.dnetlib.bmuse_webapp.publisher;
/**
* @author enrico.ottonello
*
*/
public class BMUSEWebappException extends Exception{
public BMUSEWebappException() {
}
public BMUSEWebappException(final String message) {
super(message);
}
public BMUSEWebappException(final String message, final Throwable cause) {
super(message, cause);
}
public BMUSEWebappException(final Throwable cause) {
super(cause);
}
public BMUSEWebappException(final String message, final Throwable cause, final boolean enableSuppression, final boolean writableStackTrace) {
super(message, cause, enableSuppression, writableStackTrace);
}
}

View File

@ -1,4 +1,4 @@
server.servlet.context-path=/dnet-bmuse-webapp
server.servlet.context-path=/bioschemas
server.port=8281
spring.profiles.active=garr