X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;ds=sidebyside;f=src%2Fjalview%2Fext%2Fensembl%2FEnsemblRestClient.java;h=ad6c70cb28e99269c963fc78d34c1a257b8d3eb2;hb=b3ad9eb10b8d77634a5dae103fa0d0834e6ffe6a;hp=f8cd0d65aef171e82b72bea8288d6146efd61c72;hpb=e60cc5ef2185356035706a6b7130a4c697674188;p=jalview.git diff --git a/src/jalview/ext/ensembl/EnsemblRestClient.java b/src/jalview/ext/ensembl/EnsemblRestClient.java index f8cd0d6..ad6c70c 100644 --- a/src/jalview/ext/ensembl/EnsemblRestClient.java +++ b/src/jalview/ext/ensembl/EnsemblRestClient.java @@ -1,5 +1,26 @@ +/* + * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$) + * Copyright (C) $$Year-Rel$$ The Jalview Authors + * + * This file is part of Jalview. + * + * Jalview is free software: you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, either version 3 + * of the License, or (at your option) any later version. + * + * Jalview is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR + * PURPOSE. See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with Jalview. If not, see . + * The Jalview Authors are detailed in the 'AUTHORS' file. + */ package jalview.ext.ensembl; +import jalview.io.DataSourceType; import jalview.io.FileParse; import jalview.util.StringUtils; @@ -30,14 +51,19 @@ import com.stevesoft.pat.Regex; */ abstract class EnsemblRestClient extends EnsemblSequenceFetcher { + private static final int DEFAULT_READ_TIMEOUT = 5 * 60 * 1000; // 5 minutes + + private static final int CONNECT_TIMEOUT_MS = 10 * 1000; // 10 seconds + /* * update these constants when Jalview has been checked / updated for - * changes to Ensembl REST API + * changes to Ensembl REST API (ref JAL-2105) * @see https://github.com/Ensembl/ensembl-rest/wiki/Change-log + * @see http://rest.ensembl.org/info/rest?content-type=application/json */ - private static final String LATEST_ENSEMBLGENOMES_REST_VERSION = "4.6"; + private static final String LATEST_ENSEMBLGENOMES_REST_VERSION = "5.0"; - private static final String LATEST_ENSEMBL_REST_VERSION = "4.6"; + private static final String LATEST_ENSEMBL_REST_VERSION = "5.0"; private static final String REST_CHANGE_LOG = "https://github.com/Ensembl/ensembl-rest/wiki/Change-log"; @@ -50,17 +76,20 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher private final static long VERSION_RETEST_INTERVAL = 1000L * 3600; // 1 hr + private static final Regex PROTEIN_REGEX = new Regex( + "(ENS)([A-Z]{3}|)P[0-9]{11}$"); + private static final Regex TRANSCRIPT_REGEX = new Regex( - "(ENS)([A-Z]{3}|)T[0-9]{11}$"); + "(ENS)([A-Z]{3}|)T[0-9]{11}$"); private static final Regex GENE_REGEX = new Regex( - "(ENS)([A-Z]{3}|)G[0-9]{11}$"); + "(ENS)([A-Z]{3}|)G[0-9]{11}$"); static { domainData = new HashMap(); - domainData.put(ENSEMBL_REST, new EnsemblInfo(ENSEMBL_REST, - LATEST_ENSEMBL_REST_VERSION)); + domainData.put(ENSEMBL_REST, + new EnsemblInfo(ENSEMBL_REST, LATEST_ENSEMBL_REST_VERSION)); domainData.put(ENSEMBL_GENOMES_REST, new EnsemblInfo( ENSEMBL_GENOMES_REST, LATEST_ENSEMBLGENOMES_REST_VERSION)); } @@ -99,6 +128,18 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher /** * Answers true if the query matches the regular expression pattern for an + * Ensembl protein stable identifier + * + * @param query + * @return + */ + public boolean isProteinIdentifier(String query) + { + return query == null ? false : PROTEIN_REGEX.search(query); + } + + /** + * Answers true if the query matches the regular expression pattern for an * Ensembl gene stable identifier * * @param query @@ -165,31 +206,38 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher */ private boolean checkEnsembl() { - HttpURLConnection conn = null; + BufferedReader br = null; try { // note this format works for both ensembl and ensemblgenomes // info/ping.json works for ensembl only (March 2016) - URL ping = new URL(getDomain() - + "/info/ping?content-type=application/json"); + URL ping = new URL( + getDomain() + "/info/ping?content-type=application/json"); /* * expect {"ping":1} if ok + * if ping takes more than 2 seconds to respond, treat as if unavailable */ - BufferedReader br = getHttpResponse(ping, null); + br = getHttpResponse(ping, null, 2 * 1000); JSONParser jp = new JSONParser(); JSONObject val = (JSONObject) jp.parse(br); String pingString = val.get("ping").toString(); return pingString != null; } catch (Throwable t) { - System.err.println("Error connecting to " + PING_URL + ": " - + t.getMessage()); + System.err.println( + "Error connecting to " + PING_URL + ": " + t.getMessage()); } finally { - if (conn != null) + if (br != null) { - conn.disconnect(); + try + { + br.close(); + } catch (IOException e) + { + // ignore + } } } return false; @@ -202,39 +250,61 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher * @return * @throws IOException */ - protected FileParse getSequenceReader(List ids) - throws IOException + protected FileParse getSequenceReader(List ids) throws IOException { URL url = getUrl(ids); - + BufferedReader reader = getHttpResponse(url, ids); - FileParse fp = new FileParse(reader, url.toString(), "HTTP_POST"); + if (reader == null) + { + // request failed + return null; + } + FileParse fp = new FileParse(reader, url.toString(), + DataSourceType.URL); return fp; } /** + * Gets a reader to the HTTP response, using the default read timeout of 5 + * minutes + * + * @param url + * @param ids + * @return + * @throws IOException + */ + protected BufferedReader getHttpResponse(URL url, List ids) + throws IOException + { + return getHttpResponse(url, ids, DEFAULT_READ_TIMEOUT); + } + + /** * Writes the HTTP request and gets the response as a reader. * * @param url * @param ids * written as Json POST body if more than one + * @param readTimeout + * in milliseconds * @return * @throws IOException * if response code was not 200, or other I/O error */ - protected BufferedReader getHttpResponse(URL url, List ids) - throws IOException + protected BufferedReader getHttpResponse(URL url, List ids, + int readTimeout) throws IOException { // long now = System.currentTimeMillis(); HttpURLConnection connection = (HttpURLConnection) url.openConnection(); - + /* * POST method allows multiple queries in one request; it is supported for * sequence queries, but not for overlap */ boolean multipleIds = ids != null && ids.size() > 1; - connection.setRequestMethod(multipleIds ? HttpMethod.POST - : HttpMethod.GET); + connection.setRequestMethod( + multipleIds ? HttpMethod.POST : HttpMethod.GET); connection.setRequestProperty("Content-Type", getRequestMimeType(multipleIds)); connection.setRequestProperty("Accept", getResponseMimeType()); @@ -243,22 +313,24 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher connection.setDoInput(true); connection.setDoOutput(multipleIds); + connection.setConnectTimeout(CONNECT_TIMEOUT_MS); + connection.setReadTimeout(readTimeout); + if (multipleIds) { writePostBody(connection, ids); } - + int responseCode = connection.getResponseCode(); - + if (responseCode != 200) { /* * note: a GET request for an invalid id returns an error code e.g. 415 * but POST request returns 200 and an empty Fasta response */ - throw new IOException( - "Response code was not 200. Detected response was " - + responseCode); + System.err.println("Response code " + responseCode + " for " + url); + return null; } // get content InputStream response = connection.getInputStream(); @@ -267,7 +339,7 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher // + (System.currentTimeMillis() - now) + "ms to fetch"); checkRateLimits(connection); - + BufferedReader reader = null; reader = new BufferedReader(new InputStreamReader(response, "UTF-8")); return reader; @@ -307,8 +379,8 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher + (1000 * Integer.valueOf(retryDelay)); } catch (NumberFormatException e) { - System.err.println("Unexpected value for Retry-After: " - + retryDelay); + System.err + .println("Unexpected value for Retry-After: " + retryDelay); } } else @@ -320,7 +392,7 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher // remaining, limit, reset)); } } - + /** * Rechecks if Ensembl is responding, unless the last check was successful and * the retest interval has not yet elapsed. Returns true if Ensembl is up, @@ -352,7 +424,8 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher /* * recheck if Ensembl is up if it was down, or the recheck period has elapsed */ - boolean retestAvailability = (now - info.lastAvailableCheckTime) > AVAILABILITY_RETEST_INTERVAL; + boolean retestAvailability = (now + - info.lastAvailableCheckTime) > AVAILABILITY_RETEST_INTERVAL; if (!info.restAvailable || retestAvailability) { info.restAvailable = checkEnsembl(); @@ -362,7 +435,8 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher /* * refetch Ensembl versions if the recheck period has elapsed */ - boolean refetchVersion = (now - info.lastVersionCheckTime) > VERSION_RETEST_INTERVAL; + boolean refetchVersion = (now + - info.lastVersionCheckTime) > VERSION_RETEST_INTERVAL; if (refetchVersion) { checkEnsemblRestVersion(); @@ -403,7 +477,8 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher byte[] thepostbody = postBody.toString().getBytes(); connection.setRequestProperty("Content-Length", Integer.toString(thepostbody.length)); - DataOutputStream wr = new DataOutputStream(connection.getOutputStream()); + DataOutputStream wr = new DataOutputStream( + connection.getOutputStream()); wr.write(thepostbody); wr.flush(); wr.close(); @@ -422,8 +497,8 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher URL url = null; try { - url = new URL(getDomain() - + "/info/rest?content-type=application/json"); + url = new URL( + getDomain() + "/info/rest?content-type=application/json"); BufferedReader br = getHttpResponse(url, null); JSONObject val = (JSONObject) jp.parse(br); String version = val.get("release").toString(); @@ -453,18 +528,19 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher * if so warn; we don't worry if it is earlier (this indicates Jalview has * been tested in advance against the next pending REST version) */ - boolean laterVersion = StringUtils.compareVersions(version, expected) == 1; + boolean laterVersion = StringUtils.compareVersions(version, + expected) == 1; if (laterVersion) { System.err.println(String.format( - "Expected %s REST version %s but found %s, see %s", + "EnsemblRestClient expected %s REST version %s but found %s, see %s", getDbSource(), expected, version, REST_CHANGE_LOG)); } info.restVersion = version; } catch (Throwable t) { - System.err.println("Error checking Ensembl REST version: " - + t.getMessage()); + System.err.println( + "Error checking Ensembl REST version: " + t.getMessage()); } } @@ -484,16 +560,16 @@ abstract class EnsemblRestClient extends EnsemblSequenceFetcher URL url = null; try { - url = new URL(getDomain() - + "/info/data?content-type=application/json"); + url = new URL( + getDomain() + "/info/data?content-type=application/json"); BufferedReader br = getHttpResponse(url, null); JSONObject val = (JSONObject) jp.parse(br); JSONArray versions = (JSONArray) val.get("releases"); domainData.get(getDomain()).dataVersion = versions.get(0).toString(); } catch (Throwable t) { - System.err.println("Error checking Ensembl data version: " - + t.getMessage()); + System.err.println( + "Error checking Ensembl data version: " + t.getMessage()); } }