Skip to content

Fix NonstandardProteinCompoundTest failure #780

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sbliven merged 1 commit into from
Jun 27, 2018
Merged

Fix NonstandardProteinCompoundTest failure #780

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
63 changes: 58 additions & 5 deletions ...-core/src/main/java/org/biojava/nbio/core/sequence/loader/UniprotProxySequenceReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,7 @@ public class UniprotProxySequenceReader<C extends Compound> implements ProxySequ
private static final String TREMBLID_PATTERN = "[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}";
public static final Pattern UP_AC_PATTERN = Pattern.compile("(" + SPID_PATTERN + "|" + TREMBLID_PATTERN + ")");

private static String uniprotbaseURL = "http://www.uniprot.org"; //"http://pir.uniprot.org";
private static String uniprotbaseURL = "https://www.uniprot.org"; //"http://pir.uniprot.org";
private static String uniprotDirectoryCache = null;
private String sequence;
private CompoundSet<C> compoundSet;
Expand Down Expand Up @@ -414,6 +414,61 @@ private void writeCache(StringBuilder sb, String accession) throws IOException {
fw.write(sb.toString());
fw.close();
}

/**
* Open a URL connection.
*
* Follows redirects.
* @param url
* @throws IOException
*/
private static HttpURLConnection openURLConnection(URL url) throws IOException {
// This method should be moved to a utility class in BioJava 5.0

final int timeout = 5000;
final String useragent = "BioJava";

HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty("User-Agent", useragent);
conn.setInstanceFollowRedirects(true);
conn.setConnectTimeout(timeout);
conn.setReadTimeout(timeout);

int status = conn.getResponseCode();
while (status == HttpURLConnection.HTTP_MOVED_TEMP
|| status == HttpURLConnection.HTTP_MOVED_PERM
|| status == HttpURLConnection.HTTP_SEE_OTHER) {
// Redirect!
String newUrl = conn.getHeaderField("Location");

if(newUrl.equals(url.toString())) {
throw new IOException("Cyclic redirect detected at "+newUrl);
}

// Preserve cookies
String cookies = conn.getHeaderField("Set-Cookie");

// open the new connection again
url = new URL(newUrl);
conn.disconnect();
conn = (HttpURLConnection) url.openConnection();
if(cookies != null) {
conn.setRequestProperty("Cookie", cookies);
}
conn.addRequestProperty("User-Agent", useragent);
conn.setInstanceFollowRedirects(true);
conn.setConnectTimeout(timeout);
conn.setReadTimeout(timeout);
conn.connect();

status = conn.getResponseCode();

logger.info("Redirecting from {} to {}", url, newUrl);
}
conn.connect();

return conn;
}

private StringBuilder fetchUniprotXML(String uniprotURL)
throws IOException, CompoundNotFoundException {
Expand All @@ -423,11 +478,9 @@ private StringBuilder fetchUniprotXML(String uniprotURL)
int attempt = 5;
List<String> errorCodes = new ArrayList<String>();
while(attempt > 0) {
HttpURLConnection uniprotConnection = (HttpURLConnection) uniprot.openConnection();
uniprotConnection.setRequestProperty("User-Agent", "BioJava");
uniprotConnection.connect();
HttpURLConnection uniprotConnection = openURLConnection(uniprot);
int statusCode = uniprotConnection.getResponseCode();
if (statusCode == 200) {
if (statusCode == HttpURLConnection.HTTP_OK) {
BufferedReader in = new BufferedReader(
new InputStreamReader(
uniprotConnection.getInputStream()));
Expand Down