commit 8bd642198cd78c288516a68aa684eafefe86e074 Author: Karsten Loesing karsten.loesing@gmx.net Date: Sat Apr 30 08:24:55 2016 +0200

Resolve a bunch of checkstyle warnings. --- resources/metrics_checks.xml | 8 +- .../bridgedescs/BridgeDescriptorParser.java | 7 +- .../bridgedescs/BridgeSnapshotReader.java | 44 +++-- .../bridgedescs/SanitizedBridgesWriter.java | 173 +++++++++--------- .../BridgePoolAssignmentsProcessor.java | 36 ++-- .../collector/exitlists/ExitListDownloader.java | 33 ++-- .../collector/index/CreateIndexJson.java | 21 ++- .../torproject/collector/main/Configuration.java | 31 +++- src/org/torproject/collector/main/LockFile.java | 3 +- .../collector/main/LoggingConfiguration.java | 1 + .../collector/relaydescs/ArchiveReader.java | 30 ++-- .../collector/relaydescs/ArchiveWriter.java | 135 ++++++++------ .../relaydescs/CachedRelayDescriptorReader.java | 55 +++--- .../collector/relaydescs/ReferenceChecker.java | 64 ++++--- .../relaydescs/RelayDescriptorDownloader.java | 198 +++++++++++++-------- .../relaydescs/RelayDescriptorParser.java | 61 ++++--- .../collector/torperf/TorperfDownloader.java | 62 ++++--- 17 files changed, 564 insertions(+), 398 deletions(-)

diff --git a/resources/metrics_checks.xml b/resources/metrics_checks.xml index 4fa2737..bd1d7ba 100644 --- a/resources/metrics_checks.xml +++ b/resources/metrics_checks.xml @@ -5,7 +5,11 @@

<!-- Checkstyle configuration that checks the Google coding conventions from Google Java Style - that can be found at https://google.github.io/styleguide/javaguide.html. + that can be found at https://google.github.io/styleguide/javaguide.html with the following + modifications: + + - Replaced com.google with org.torproject in import statement ordering + [CustomImportOrder].

Checkstyle is very configurable. Be sure to read the documentation at http://checkstyle.sf.net (or in your downloaded distribution). @@ -159,7 +163,7 @@ <module name="OverloadMethodsDeclarationOrder"/> <module name="VariableDeclarationUsageDistance"/> <module name="CustomImportOrder"> - <property name="specialImportsRegExp" value="com.google"/> + <property name="specialImportsRegExp" value="org.torproject"/> <property name="sortImportsInGroupAlphabetically" value="true"/> <property name="customImportOrderRules" value="STATIC###SPECIAL_IMPORTS###THIRD_PARTY_PACKAGE###STANDARD_JAVA_PACKAGE"/> </module> diff --git a/src/org/torproject/collector/bridgedescs/BridgeDescriptorParser.java b/src/org/torproject/collector/bridgedescs/BridgeDescriptorParser.java index c14875b..f683ea0 100644 --- a/src/org/torproject/collector/bridgedescs/BridgeDescriptorParser.java +++ b/src/org/torproject/collector/bridgedescs/BridgeDescriptorParser.java @@ -1,5 +1,6 @@ -/* Copyright 2010--2012 The Tor Project +/* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.bridgedescs;

import java.io.BufferedReader; @@ -9,13 +10,17 @@ import java.util.logging.Level; import java.util.logging.Logger;

public class BridgeDescriptorParser { + private SanitizedBridgesWriter sbw; + private Logger logger; + public BridgeDescriptorParser(SanitizedBridgesWriter sbw) { this.sbw = sbw; this.logger = Logger.getLogger(BridgeDescriptorParser.class.getName()); } + public void parse(byte[] allData, String dateTime) { try { BufferedReader br = new BufferedReader(new StringReader( diff --git a/src/org/torproject/collector/bridgedescs/BridgeSnapshotReader.java b/src/org/torproject/collector/bridgedescs/BridgeSnapshotReader.java index b16938d..2d41d18 100644 --- a/src/org/torproject/collector/bridgedescs/BridgeSnapshotReader.java +++ b/src/org/torproject/collector/bridgedescs/BridgeSnapshotReader.java @@ -1,7 +1,13 @@ -/* Copyright 2010--2012 The Tor Project +/* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.bridgedescs;

+import org.apache.commons.codec.binary.Hex; +import org.apache.commons.codec.digest.DigestUtils; +import org.apache.commons.compress.archivers.tar.TarArchiveInputStream; +import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream; + import java.io.BufferedInputStream; import java.io.BufferedReader; import java.io.BufferedWriter; @@ -20,11 +26,6 @@ import java.util.TreeSet; import java.util.logging.Level; import java.util.logging.Logger;

-import org.apache.commons.codec.binary.Hex; -import org.apache.commons.codec.digest.DigestUtils; -import org.apache.commons.compress.archivers.tar.TarArchiveInputStream; -import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream; - /** * Reads the half-hourly snapshots of bridge descriptors from Tonga. */ @@ -32,8 +33,8 @@ public class BridgeSnapshotReader { public BridgeSnapshotReader(BridgeDescriptorParser bdp, File bridgeDirectoriesDir, File statsDirectory) {

- if (bdp == null || bridgeDirectoriesDir == null || - statsDirectory == null) { + if (bdp == null || bridgeDirectoriesDir == null + || statsDirectory == null) { throw new IllegalArgumentException(); }

@@ -62,11 +63,15 @@ public class BridgeSnapshotReader { } } logger.fine("Importing files in directory " + bridgeDirectoriesDir - + "/..."); + + "/..."); Set<String> descriptorImportHistory = new HashSet<String>(); - int parsedFiles = 0, skippedFiles = 0, parsedStatuses = 0, - parsedServerDescriptors = 0, skippedServerDescriptors = 0, - parsedExtraInfoDescriptors = 0, skippedExtraInfoDescriptors = 0; + int parsedFiles = 0; + int skippedFiles = 0; + int parsedStatuses = 0; + int parsedServerDescriptors = 0; + int skippedServerDescriptors = 0; + int parsedExtraInfoDescriptors = 0; + int skippedExtraInfoDescriptors = 0; Stack<File> filesInInputDir = new Stack<File>(); filesInInputDir.add(bdDir); while (!filesInInputDir.isEmpty()) { @@ -118,9 +123,9 @@ public class BridgeSnapshotReader { break; } } - if (firstLine.startsWith("published ") || - firstLine.startsWith("flag-thresholds ") || - firstLine.startsWith("r ")) { + if (firstLine.startsWith("published ") + || firstLine.startsWith("flag-thresholds ") + || firstLine.startsWith("r ")) { bdp.parse(allData, dateTime); parsedStatuses++; } else if (descriptorImportHistory.contains(fileDigest)) { @@ -129,10 +134,11 @@ public class BridgeSnapshotReader { skippedFiles++; continue; } else { - int start = -1, sig = -1, end = -1; - String startToken = - firstLine.startsWith("router ") ? - "router " : "extra-info "; + int start = -1; + int sig = -1; + int end = -1; + String startToken = firstLine.startsWith("router ") + ? "router " : "extra-info "; String sigToken = "\nrouter-signature\n"; String endToken = "\n-----END SIGNATURE-----\n"; while (end < ascii.length()) { diff --git a/src/org/torproject/collector/bridgedescs/SanitizedBridgesWriter.java b/src/org/torproject/collector/bridgedescs/SanitizedBridgesWriter.java index 4aa13ea..f8d61c0 100644 --- a/src/org/torproject/collector/bridgedescs/SanitizedBridgesWriter.java +++ b/src/org/torproject/collector/bridgedescs/SanitizedBridgesWriter.java @@ -1,7 +1,17 @@ /* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.bridgedescs;

+import org.torproject.collector.main.Configuration; +import org.torproject.collector.main.LockFile; +import org.torproject.collector.main.LoggingConfiguration; + +import org.apache.commons.codec.DecoderException; +import org.apache.commons.codec.binary.Base64; +import org.apache.commons.codec.binary.Hex; +import org.apache.commons.codec.digest.DigestUtils; + import java.io.BufferedReader; import java.io.BufferedWriter; import java.io.File; @@ -25,14 +35,6 @@ import java.util.TreeMap; import java.util.logging.Level; import java.util.logging.Logger;

-import org.apache.commons.codec.DecoderException; -import org.apache.commons.codec.binary.Base64; -import org.apache.commons.codec.binary.Hex; -import org.apache.commons.codec.digest.DigestUtils; -import org.torproject.collector.main.Configuration; -import org.torproject.collector.main.LockFile; -import org.torproject.collector.main.LoggingConfiguration; - /** * Sanitizes bridge descriptors, i.e., removes all possibly sensitive * information from them, and writes them to a local directory structure. @@ -125,8 +127,8 @@ public class SanitizedBridgesWriter extends Thread { config.getLimitBridgeDescriptorMappings(); File statsDirectory = new File("stats");

- if (bridgeDirectoriesDirectory == null || - sanitizedBridgesDirectory == null || statsDirectory == null) { + if (bridgeDirectoriesDirectory == null + || sanitizedBridgesDirectory == null || statsDirectory == null) { throw new IllegalArgumentException(); }

@@ -169,9 +171,9 @@ public class SanitizedBridgesWriter extends Thread { String line; while ((line = br.readLine()) != null) { String[] parts = line.split(","); - if ((line.length() != ("yyyy-MM,".length() + 31 * 2) && - line.length() != ("yyyy-MM,".length() + 50 * 2)) || - parts.length != 2) { + if ((line.length() != ("yyyy-MM,".length() + 31 * 2) + && line.length() != ("yyyy-MM,".length() + 50 * 2)) + || parts.length != 2) { this.logger.warning("Invalid line in bridge-ip-secrets file " + "starting with '" + line.substring(0, 7) + "'! " + "Not calculating any IP address hashes in this " @@ -364,8 +366,8 @@ public class SanitizedBridgesWriter extends Thread { }

private byte[] getSecretForMonth(String month) throws IOException { - if (!this.secretsForHashingIPAddresses.containsKey(month) || - this.secretsForHashingIPAddresses.get(month).length == 31) { + if (!this.secretsForHashingIPAddresses.containsKey(month) + || this.secretsForHashingIPAddresses.get(month).length == 31) { byte[] secret = new byte[50]; this.secureRandom.nextBytes(secret); if (this.secretsForHashingIPAddresses.containsKey(month)) { @@ -420,8 +422,8 @@ public class SanitizedBridgesWriter extends Thread { maxNetworkStatusPublishedTime = publicationTime; }

- if (this.bridgeSanitizingCutOffTimestamp. - compareTo(publicationTime) > 0) { + if (this.bridgeSanitizingCutOffTimestamp + .compareTo(publicationTime) > 0) { this.logger.log(!this.haveWarnedAboutInterval ? Level.WARNING : Level.FINE, "Sanitizing and storing network status with " + "publication time outside our descriptor sanitizing " @@ -476,9 +478,9 @@ public class SanitizedBridgesWriter extends Thread { String dirPort = parts[8];

/* Determine most recent descriptor publication time. */ - if (descPublicationTime.compareTo(publicationTime) <= 0 && - (mostRecentDescPublished == null || - descPublicationTime.compareTo( + if (descPublicationTime.compareTo(publicationTime) <= 0 + && (mostRecentDescPublished == null + || descPublicationTime.compareTo( mostRecentDescPublished) > 0)) { mostRecentDescPublished = descPublicationTime; } @@ -515,9 +517,9 @@ public class SanitizedBridgesWriter extends Thread { }

/* Nothing special about s, w, and p lines; just copy them. */ - } else if (line.startsWith("s ") || line.equals("s") || - line.startsWith("w ") || line.equals("w") || - line.startsWith("p ") || line.equals("p")) { + } else if (line.startsWith("s ") || line.equals("s") + || line.startsWith("w ") || line.equals("w") + || line.startsWith("p ") || line.equals("p")) { scrubbed.append(line + "\n");

/* There should be nothing else but r, w, p, and s lines in the @@ -541,9 +543,9 @@ public class SanitizedBridgesWriter extends Thread { SimpleDateFormat formatter = new SimpleDateFormat( "yyyy-MM-dd HH:mm:ss"); formatter.setTimeZone(TimeZone.getTimeZone("UTC")); - if (formatter.parse(publicationTime).getTime() - - formatter.parse(mostRecentDescPublished).getTime() > - 60L * 60L * 1000L) { + if (formatter.parse(publicationTime).getTime() + - formatter.parse(mostRecentDescPublished).getTime() + > 60L * 60L * 1000L) { this.logger.warning("The most recent descriptor in the bridge " + "network status published at " + publicationTime + " was " + "published at " + mostRecentDescPublished + " which is " @@ -609,16 +611,21 @@ public class SanitizedBridgesWriter extends Thread { }

/* Parse descriptor to generate a sanitized version. */ - String scrubbedDesc = null, published = null, - masterKeyEd25519FromIdentityEd25519 = null; + String scrubbedDesc = null; + String published = null; + String masterKeyEd25519FromIdentityEd25519 = null; try { BufferedReader br = new BufferedReader(new StringReader( new String(data, "US-ASCII"))); StringBuilder scrubbed = new StringBuilder(); - String line = null, hashedBridgeIdentity = null, address = null, - routerLine = null, scrubbedAddress = null, - masterKeyEd25519 = null; - List<String> orAddresses = null, scrubbedOrAddresses = null; + String line = null; + String hashedBridgeIdentity = null; + String address = null; + String routerLine = null; + String scrubbedAddress = null; + String masterKeyEd25519 = null; + List<String> orAddresses = null; + List<String> scrubbedOrAddresses = null; boolean skipCrypto = false; while ((line = br.readLine()) != null) {

@@ -649,8 +656,8 @@ public class SanitizedBridgesWriter extends Thread { if (published.compareTo(maxServerDescriptorPublishedTime) > 0) { maxServerDescriptorPublishedTime = published; } - if (this.bridgeSanitizingCutOffTimestamp. - compareTo(published) > 0) { + if (this.bridgeSanitizingCutOffTimestamp + .compareTo(published) > 0) { this.logger.log(!this.haveWarnedAboutInterval ? Level.WARNING : Level.FINE, "Sanitizing and storing " + "server descriptor with publication time outside our " @@ -661,15 +668,15 @@ public class SanitizedBridgesWriter extends Thread {

/* Parse the fingerprint to determine the hashed bridge * identity. */ - } else if (line.startsWith("opt fingerprint ") || - line.startsWith("fingerprint ")) { - String fingerprint = line.substring(line.startsWith("opt ") ? - "opt fingerprint".length() : "fingerprint".length()). - replaceAll(" ", "").toLowerCase(); + } else if (line.startsWith("opt fingerprint ") + || line.startsWith("fingerprint ")) { + String fingerprint = line.substring(line.startsWith("opt ") + ? "opt fingerprint".length() : "fingerprint".length()) + .replaceAll(" ", "").toLowerCase(); byte[] fingerprintBytes = Hex.decodeHex( fingerprint.toCharArray()); - hashedBridgeIdentity = DigestUtils.shaHex(fingerprintBytes). - toLowerCase(); + hashedBridgeIdentity = DigestUtils.shaHex(fingerprintBytes) + .toLowerCase(); try { scrubbedAddress = scrubIpv4Address(address, fingerprintBytes, published); @@ -695,9 +702,10 @@ public class SanitizedBridgesWriter extends Thread { } scrubbed.append((line.startsWith("opt ") ? "opt " : "") + "fingerprint"); - for (int i = 0; i < hashedBridgeIdentity.length() / 4; i++) + for (int i = 0; i < hashedBridgeIdentity.length() / 4; i++) { scrubbed.append(" " + hashedBridgeIdentity.substring(4 * i, 4 * (i + 1)).toUpperCase()); + } scrubbed.append("\n");

/* Replace the contact line (if present) with a generic one. */ @@ -722,8 +730,8 @@ public class SanitizedBridgesWriter extends Thread {

/* Replace extra-info digest with the hashed digest of the * non-scrubbed descriptor. */ - } else if (line.startsWith("opt extra-info-digest ") || - line.startsWith("extra-info-digest ")) { + } else if (line.startsWith("opt extra-info-digest ") + || line.startsWith("extra-info-digest ")) { String[] parts = line.split(" "); if (line.startsWith("opt ")) { scrubbed.append("opt "); @@ -733,8 +741,8 @@ public class SanitizedBridgesWriter extends Thread { Hex.decodeHex(parts[1].toCharArray())).toUpperCase()); if (parts.length > 2) { scrubbed.append(" " + Base64.encodeBase64String( - DigestUtils.sha256(Base64.decodeBase64(parts[2]))). - replaceAll("=", "")); + DigestUtils.sha256(Base64.decodeBase64(parts[2]))) + .replaceAll("=", "")); } scrubbed.append("\n");

@@ -752,8 +760,8 @@ public class SanitizedBridgesWriter extends Thread { /* Extract master-key-ed25519 from identity-ed25519. */ } else if (line.equals("identity-ed25519")) { StringBuilder sb = new StringBuilder(); - while ((line = br.readLine()) != null && - !line.equals("-----END ED25519 CERT-----")) { + while ((line = br.readLine()) != null + && !line.equals("-----END ED25519 CERT-----")) { if (line.equals("-----BEGIN ED25519 CERT-----")) { continue; } @@ -764,8 +772,8 @@ public class SanitizedBridgesWriter extends Thread { sb.toString()); String sha256MasterKeyEd25519 = Base64.encodeBase64String( DigestUtils.sha256(Base64.decodeBase64( - masterKeyEd25519FromIdentityEd25519 + "="))). - replaceAll("=", ""); + masterKeyEd25519FromIdentityEd25519 + "="))) + .replaceAll("=", ""); scrubbed.append("master-key-ed25519 " + sha256MasterKeyEd25519 + "\n"); if (masterKeyEd25519 != null && !masterKeyEd25519.equals( @@ -778,8 +786,8 @@ public class SanitizedBridgesWriter extends Thread { /* Verify that identity-ed25519 and master-key-ed25519 match. */ } else if (line.startsWith("master-key-ed25519 ")) { masterKeyEd25519 = line.substring(line.indexOf(" ") + 1); - if (masterKeyEd25519FromIdentityEd25519 != null && - !masterKeyEd25519FromIdentityEd25519.equals( + if (masterKeyEd25519FromIdentityEd25519 != null + && !masterKeyEd25519FromIdentityEd25519.equals( masterKeyEd25519)) { this.logger.warning("Mismatch between identity-ed25519 and " + "master-key-ed25519. Skipping."); @@ -829,9 +837,9 @@ public class SanitizedBridgesWriter extends Thread { /* Skip all crypto parts that might leak the bridge's identity * fingerprint. */ } else if (line.startsWith("-----BEGIN ") - || line.equals("onion-key") || line.equals("signing-key") || - line.equals("onion-key-crosscert") || - line.startsWith("ntor-onion-key-crosscert ")) { + || line.equals("onion-key") || line.equals("signing-key") + || line.equals("onion-key-crosscert") + || line.startsWith("ntor-onion-key-crosscert ")) { skipCrypto = true;

/* Stop skipping lines when the crypto parts are over. */ @@ -893,8 +901,8 @@ public class SanitizedBridgesWriter extends Thread { byte[] forDigest = new byte[sig - start]; System.arraycopy(data, start, forDigest, 0, sig - start); descriptorDigestSha256Base64 = Base64.encodeBase64String( - DigestUtils.sha256(DigestUtils.sha256(forDigest))). - replaceAll("=", ""); + DigestUtils.sha256(DigestUtils.sha256(forDigest))) + .replaceAll("=", ""); } } catch (UnsupportedEncodingException e) { /* Handle below. */ @@ -1010,14 +1018,16 @@ public class SanitizedBridgesWriter extends Thread { public void sanitizeAndStoreExtraInfoDescriptor(byte[] data) {

/* Parse descriptor to generate a sanitized version. */ - String scrubbedDesc = null, published = null, - masterKeyEd25519FromIdentityEd25519 = null; + String scrubbedDesc = null; + String published = null; + String masterKeyEd25519FromIdentityEd25519 = null; try { BufferedReader br = new BufferedReader(new StringReader(new String( data, "US-ASCII"))); String line = null; StringBuilder scrubbed = null; - String hashedBridgeIdentity = null, masterKeyEd25519 = null; + String hashedBridgeIdentity = null; + String masterKeyEd25519 = null; while ((line = br.readLine()) != null) {

/* Parse bridge identity from extra-info line and replace it with @@ -1054,8 +1064,8 @@ public class SanitizedBridgesWriter extends Thread { /* Extract master-key-ed25519 from identity-ed25519. */ } else if (line.equals("identity-ed25519")) { StringBuilder sb = new StringBuilder(); - while ((line = br.readLine()) != null && - !line.equals("-----END ED25519 CERT-----")) { + while ((line = br.readLine()) != null + && !line.equals("-----END ED25519 CERT-----")) { if (line.equals("-----BEGIN ED25519 CERT-----")) { continue; } @@ -1066,8 +1076,8 @@ public class SanitizedBridgesWriter extends Thread { sb.toString()); String sha256MasterKeyEd25519 = Base64.encodeBase64String( DigestUtils.sha256(Base64.decodeBase64( - masterKeyEd25519FromIdentityEd25519 + "="))). - replaceAll("=", ""); + masterKeyEd25519FromIdentityEd25519 + "="))) + .replaceAll("=", ""); scrubbed.append("master-key-ed25519 " + sha256MasterKeyEd25519 + "\n"); if (masterKeyEd25519 != null && !masterKeyEd25519.equals( @@ -1080,8 +1090,8 @@ public class SanitizedBridgesWriter extends Thread { /* Verify that identity-ed25519 and master-key-ed25519 match. */ } else if (line.startsWith("master-key-ed25519 ")) { masterKeyEd25519 = line.substring(line.indexOf(" ") + 1); - if (masterKeyEd25519FromIdentityEd25519 != null && - !masterKeyEd25519FromIdentityEd25519.equals( + if (masterKeyEd25519FromIdentityEd25519 != null + && !masterKeyEd25519FromIdentityEd25519.equals( masterKeyEd25519)) { this.logger.warning("Mismatch between identity-ed25519 and " + "master-key-ed25519. Skipping."); @@ -1169,8 +1179,8 @@ public class SanitizedBridgesWriter extends Thread { byte[] forDigest = new byte[sig - start]; System.arraycopy(data, start, forDigest, 0, sig - start); descriptorDigestSha256Base64 = Base64.encodeBase64String( - DigestUtils.sha256(DigestUtils.sha256(forDigest))). - replaceAll("=", ""); + DigestUtils.sha256(DigestUtils.sha256(forDigest))) + .replaceAll("=", ""); } } catch (UnsupportedEncodingException e) { /* Handle below. */ @@ -1230,11 +1240,12 @@ public class SanitizedBridgesWriter extends Thread { public void finishWriting() {

/* Delete secrets that we don't need anymore. */ - if (!this.secretsForHashingIPAddresses.isEmpty() && - this.secretsForHashingIPAddresses.firstKey().compareTo( + if (!this.secretsForHashingIPAddresses.isEmpty() + && this.secretsForHashingIPAddresses.firstKey().compareTo( this.bridgeSanitizingCutOffTimestamp) < 0) { try { - int kept = 0, deleted = 0; + int kept = 0; + int deleted = 0; BufferedWriter bw = new BufferedWriter(new FileWriter( this.bridgeIpSecretsFile)); for (Map.Entry<String, byte[]> e : @@ -1267,26 +1278,26 @@ public class SanitizedBridgesWriter extends Thread { try { long maxNetworkStatusPublishedMillis = dateTimeFormat.parse(maxNetworkStatusPublishedTime).getTime(); - if (maxNetworkStatusPublishedMillis > 0L && - maxNetworkStatusPublishedMillis < tooOldMillis) { + if (maxNetworkStatusPublishedMillis > 0L + && maxNetworkStatusPublishedMillis < tooOldMillis) { this.logger.warning("The last known bridge network status was " + "published " + maxNetworkStatusPublishedTime + ", which is " + "more than 5:30 hours in the past."); } long maxServerDescriptorPublishedMillis = - dateTimeFormat.parse(maxServerDescriptorPublishedTime). - getTime(); - if (maxServerDescriptorPublishedMillis > 0L && - maxServerDescriptorPublishedMillis < tooOldMillis) { + dateTimeFormat.parse(maxServerDescriptorPublishedTime) + .getTime(); + if (maxServerDescriptorPublishedMillis > 0L + && maxServerDescriptorPublishedMillis < tooOldMillis) { this.logger.warning("The last known bridge server descriptor was " + "published " + maxServerDescriptorPublishedTime + ", which " + "is more than 5:30 hours in the past."); } long maxExtraInfoDescriptorPublishedMillis = - dateTimeFormat.parse(maxExtraInfoDescriptorPublishedTime). - getTime(); - if (maxExtraInfoDescriptorPublishedMillis > 0L && - maxExtraInfoDescriptorPublishedMillis < tooOldMillis) { + dateTimeFormat.parse(maxExtraInfoDescriptorPublishedTime) + .getTime(); + if (maxExtraInfoDescriptorPublishedMillis > 0L + && maxExtraInfoDescriptorPublishedMillis < tooOldMillis) { this.logger.warning("The last known bridge extra-info descriptor " + "was published " + maxExtraInfoDescriptorPublishedTime + ", which is more than 5:30 hours in the past."); diff --git a/src/org/torproject/collector/bridgepools/BridgePoolAssignmentsProcessor.java b/src/org/torproject/collector/bridgepools/BridgePoolAssignmentsProcessor.java index b682316..8afaa43 100644 --- a/src/org/torproject/collector/bridgepools/BridgePoolAssignmentsProcessor.java +++ b/src/org/torproject/collector/bridgepools/BridgePoolAssignmentsProcessor.java @@ -1,7 +1,17 @@ /* Copyright 2011--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.bridgepools;

+import org.torproject.collector.main.Configuration; +import org.torproject.collector.main.LockFile; +import org.torproject.collector.main.LoggingConfiguration; + +import org.apache.commons.codec.DecoderException; +import org.apache.commons.codec.binary.Hex; +import org.apache.commons.codec.digest.DigestUtils; +import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream; + import java.io.BufferedReader; import java.io.BufferedWriter; import java.io.File; @@ -24,14 +34,6 @@ import java.util.TreeSet; import java.util.logging.Level; import java.util.logging.Logger;

-import org.apache.commons.codec.DecoderException; -import org.apache.commons.codec.binary.Hex; -import org.apache.commons.codec.digest.DigestUtils; -import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream; -import org.torproject.collector.main.Configuration; -import org.torproject.collector.main.LockFile; -import org.torproject.collector.main.LoggingConfiguration; - public class BridgePoolAssignmentsProcessor extends Thread {

public static void main(String[] args) { @@ -77,8 +79,8 @@ public class BridgePoolAssignmentsProcessor extends Thread {

Logger logger = Logger.getLogger(BridgePoolAssignmentsProcessor.class.getName()); - if (assignmentsDirectory == null || - sanitizedAssignmentsDirectory == null) { + if (assignmentsDirectory == null + || sanitizedAssignmentsDirectory == null) { IllegalArgumentException e = new IllegalArgumentException("Neither " + "assignmentsDirectory nor sanitizedAssignmentsDirectory may " + "be null!"); @@ -117,9 +119,11 @@ public class BridgePoolAssignmentsProcessor extends Thread { } else { br = new BufferedReader(new FileReader(assignmentFile)); } - String line, bridgePoolAssignmentLine = null; + String line; + String bridgePoolAssignmentLine = null; SortedSet<String> sanitizedAssignments = new TreeSet<String>(); - boolean wroteLastLine = false, skipBefore20120504125947 = true; + boolean wroteLastLine = false; + boolean skipBefore20120504125947 = true; Set<String> hashedFingerprints = null; while ((line = br.readLine()) != null || !wroteLastLine) { if (line != null && line.startsWith("bridge-pool-assignment ")) { @@ -142,8 +146,8 @@ public class BridgePoolAssignmentsProcessor extends Thread { continue; } } - if (line == null || - line.startsWith("bridge-pool-assignment ")) { + if (line == null + || line.startsWith("bridge-pool-assignment ")) { if (bridgePoolAssignmentLine != null) { try { long bridgePoolAssignmentTime = assignmentFormat.parse( @@ -235,8 +239,8 @@ public class BridgePoolAssignmentsProcessor extends Thread { + "starting with '" + duplicateFingerprint + "'."); }

- if (maxBridgePoolAssignmentTime > 0L && - maxBridgePoolAssignmentTime + 330L * 60L * 1000L + if (maxBridgePoolAssignmentTime > 0L + && maxBridgePoolAssignmentTime + 330L * 60L * 1000L < System.currentTimeMillis()) { SimpleDateFormat dateTimeFormat = new SimpleDateFormat( "yyyy-MM-dd HH:mm:ss"); diff --git a/src/org/torproject/collector/exitlists/ExitListDownloader.java b/src/org/torproject/collector/exitlists/ExitListDownloader.java index 7e019b0..d328850 100644 --- a/src/org/torproject/collector/exitlists/ExitListDownloader.java +++ b/src/org/torproject/collector/exitlists/ExitListDownloader.java @@ -1,7 +1,17 @@ /* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.exitlists;

+import org.torproject.collector.main.Configuration; +import org.torproject.collector.main.LockFile; +import org.torproject.collector.main.LoggingConfiguration; +import org.torproject.descriptor.Descriptor; +import org.torproject.descriptor.DescriptorParseException; +import org.torproject.descriptor.DescriptorParser; +import org.torproject.descriptor.DescriptorSourceFactory; +import org.torproject.descriptor.ExitList; + import java.io.BufferedInputStream; import java.io.BufferedWriter; import java.io.File; @@ -20,15 +30,6 @@ import java.util.TreeSet; import java.util.logging.Level; import java.util.logging.Logger;

-import org.torproject.descriptor.Descriptor; -import org.torproject.descriptor.DescriptorParser; -import org.torproject.descriptor.DescriptorSourceFactory; -import org.torproject.descriptor.ExitList; -import org.torproject.descriptor.DescriptorParseException; -import org.torproject.collector.main.Configuration; -import org.torproject.collector.main.LockFile; -import org.torproject.collector.main.LoggingConfiguration; - public class ExitListDownloader extends Thread {

public static void main(String[] args) { @@ -85,8 +86,8 @@ public class ExitListDownloader extends Thread { huc.connect(); int response = huc.getResponseCode(); if (response != 200) { - logger.warning("Could not download exit list. Response code " + - response); + logger.warning("Could not download exit list. Response code " + + response); return; } BufferedInputStream in = new BufferedInputStream( @@ -121,8 +122,8 @@ public class ExitListDownloader extends Thread { List<Descriptor> parsedDescriptors = descriptorParser.parseDescriptors(downloadedExitList.getBytes(), tarballFile.getName()); - if (parsedDescriptors.size() != 1 || - !(parsedDescriptors.get(0) instanceof ExitList)) { + if (parsedDescriptors.size() != 1 + || !(parsedDescriptors.get(0) instanceof ExitList)) { logger.warning("Could not parse downloaded exit list"); return; } @@ -136,12 +137,12 @@ public class ExitListDownloader extends Thread { logger.log(Level.WARNING, "Could not parse downloaded exit list", e); } - if (maxScanMillis > 0L && - maxScanMillis + 330L * 60L * 1000L < System.currentTimeMillis()) { + if (maxScanMillis > 0L + && maxScanMillis + 330L * 60L * 1000L < System.currentTimeMillis()) { logger.warning("The last reported scan in the downloaded exit list " + "took place at " + dateTimeFormat.format(maxScanMillis) + ", which is more than 5:30 hours in the past."); - } + }

/* Write to disk. */ File rsyncFile = new File("recent/exit-lists/" diff --git a/src/org/torproject/collector/index/CreateIndexJson.java b/src/org/torproject/collector/index/CreateIndexJson.java index cf2e0bb..ac5adf5 100644 --- a/src/org/torproject/collector/index/CreateIndexJson.java +++ b/src/org/torproject/collector/index/CreateIndexJson.java @@ -1,7 +1,14 @@ -/* Copyright 2015 The Tor Project +/* Copyright 2015--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.index;

+import com.google.gson.Gson; +import com.google.gson.GsonBuilder; + +import org.apache.commons.compress.compressors.bzip2.BZip2CompressorOutputStream; +import org.apache.commons.compress.compressors.xz.XZCompressorOutputStream; + import java.io.BufferedWriter; import java.io.File; import java.io.FileOutputStream; @@ -17,12 +24,6 @@ import java.util.TimeZone; import java.util.TreeSet; import java.util.zip.GZIPOutputStream;

-import org.apache.commons.compress.compressors.bzip2.BZip2CompressorOutputStream; -import org.apache.commons.compress.compressors.xz.XZCompressorOutputStream; - -import com.google.gson.Gson; -import com.google.gson.GsonBuilder; - /* Create a fresh index.json containing all directories and files in the * archive/ and recent/ directories. * @@ -53,12 +54,14 @@ public class CreateIndexJson { String path; SortedSet<FileNode> files; SortedSet<DirectoryNode> directories; + DirectoryNode(String path, SortedSet<FileNode> files, SortedSet<DirectoryNode> directories) { this.path = path; this.files = files; this.directories = directories; } + public int compareTo(DirectoryNode o) { return this.path.compareTo(o.path); } @@ -69,6 +72,7 @@ public class CreateIndexJson { String path; SortedSet<FileNode> files; SortedSet<DirectoryNode> directories; + IndexNode(String index_created, String path, SortedSet<FileNode> files, SortedSet<DirectoryNode> directories) { @@ -83,17 +87,20 @@ public class CreateIndexJson { String path; long size; String last_modified; + FileNode(String path, long size, String last_modified) { this.path = path; this.size = size; this.last_modified = last_modified; } + public int compareTo(FileNode o) { return this.path.compareTo(o.path); } }

static DateFormat dateTimeFormat; + static { dateTimeFormat = new SimpleDateFormat(dateTimePattern, dateTimeLocale); diff --git a/src/org/torproject/collector/main/Configuration.java b/src/org/torproject/collector/main/Configuration.java index eaf3217..9a511d3 100644 --- a/src/org/torproject/collector/main/Configuration.java +++ b/src/org/torproject/collector/main/Configuration.java @@ -1,5 +1,6 @@ -/* Copyright 2010--2012 The Tor Project +/* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.main;

import java.io.BufferedReader; @@ -67,6 +68,7 @@ public class Configuration { private String torperfOutputDirectory = "out/torperf/"; private SortedMap<String, String> torperfSources = null; private List<String> torperfFiles = null; + public Configuration() {

/* Initialize logger. */ @@ -219,84 +221,111 @@ public class Configuration { System.exit(1); } } + public String getDirectoryArchivesOutputDirectory() { return this.directoryArchivesOutputDirectory; } + public boolean getImportCachedRelayDescriptors() { return this.importCachedRelayDescriptors; } + public List<String> getCachedRelayDescriptorDirectory() { return this.cachedRelayDescriptorsDirectory; } + public boolean getImportDirectoryArchives() { return this.importDirectoryArchives; } + public String getDirectoryArchivesDirectory() { return this.directoryArchivesDirectory; } + public boolean getKeepDirectoryArchiveImportHistory() { return this.keepDirectoryArchiveImportHistory; } + public boolean getReplaceIPAddressesWithHashes() { return this.replaceIPAddressesWithHashes; } + public long getLimitBridgeDescriptorMappings() { return this.limitBridgeDescriptorMappings; } + public String getSanitizedBridgesWriteDirectory() { return this.sanitizedBridgesWriteDirectory; } + public String getBridgeSnapshotsDirectory() { return this.bridgeSnapshotsDirectory; } + public boolean getDownloadRelayDescriptors() { return this.downloadRelayDescriptors; } + public List<String> getDownloadFromDirectoryAuthorities() { return this.downloadFromDirectoryAuthorities; } + public List<String> getDownloadVotesByFingerprint() { return this.downloadVotesByFingerprint; } + public boolean getDownloadCurrentConsensus() { return this.downloadCurrentConsensus; } + public boolean getDownloadCurrentMicrodescConsensus() { return this.downloadCurrentMicrodescConsensus; } + public boolean getDownloadCurrentVotes() { return this.downloadCurrentVotes; } + public boolean getDownloadMissingServerDescriptors() { return this.downloadMissingServerDescriptors; } + public boolean getDownloadMissingExtraInfoDescriptors() { return this.downloadMissingExtraInfoDescriptors; } + public boolean getDownloadMissingMicrodescriptors() { return this.downloadMissingMicrodescriptors; } + public boolean getDownloadAllServerDescriptors() { return this.downloadAllServerDescriptors; } + public boolean getDownloadAllExtraInfoDescriptors() { return this.downloadAllExtraInfoDescriptors; } + public boolean getCompressRelayDescriptorDownloads() { return this.compressRelayDescriptorDownloads; } + public String getAssignmentsDirectory() { return this.assignmentsDirectory; } + public String getSanitizedAssignmentsDirectory() { return this.sanitizedAssignmentsDirectory; } + public String getTorperfOutputDirectory() { return this.torperfOutputDirectory; } + public SortedMap<String, String> getTorperfSources() { return this.torperfSources; } + public List<String> getTorperfFiles() { return this.torperfFiles; } diff --git a/src/org/torproject/collector/main/LockFile.java b/src/org/torproject/collector/main/LockFile.java index cd850bd..b07d4b1 100644 --- a/src/org/torproject/collector/main/LockFile.java +++ b/src/org/torproject/collector/main/LockFile.java @@ -1,5 +1,6 @@ -/* Copyright 2010--2012 The Tor Project +/* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.main;

import java.io.BufferedReader; diff --git a/src/org/torproject/collector/main/LoggingConfiguration.java b/src/org/torproject/collector/main/LoggingConfiguration.java index f3a620c..b8a91c7 100644 --- a/src/org/torproject/collector/main/LoggingConfiguration.java +++ b/src/org/torproject/collector/main/LoggingConfiguration.java @@ -1,5 +1,6 @@ /* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.main;

import java.io.File; diff --git a/src/org/torproject/collector/relaydescs/ArchiveReader.java b/src/org/torproject/collector/relaydescs/ArchiveReader.java index 93bea7f..96409f4 100644 --- a/src/org/torproject/collector/relaydescs/ArchiveReader.java +++ b/src/org/torproject/collector/relaydescs/ArchiveReader.java @@ -1,7 +1,12 @@ -/* Copyright 2010--2014 The Tor Project +/* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.relaydescs;

+import org.apache.commons.codec.binary.Base64; +import org.apache.commons.codec.digest.DigestUtils; +import org.apache.commons.compress.compressors.bzip2.BZip2CompressorInputStream; + import java.io.BufferedInputStream; import java.io.BufferedReader; import java.io.BufferedWriter; @@ -28,10 +33,6 @@ import java.util.TreeSet; import java.util.logging.Level; import java.util.logging.Logger;

-import org.apache.commons.codec.binary.Base64; -import org.apache.commons.codec.digest.DigestUtils; -import org.apache.commons.compress.compressors.bzip2.BZip2CompressorInputStream; - /** * Read in all files in a given directory and pass buffered readers of * them to the relay descriptor parser. @@ -40,13 +41,14 @@ public class ArchiveReader { public ArchiveReader(RelayDescriptorParser rdp, File archivesDirectory, File statsDirectory, boolean keepImportHistory) {

- if (rdp == null || archivesDirectory == null || - statsDirectory == null) { + if (rdp == null || archivesDirectory == null + || statsDirectory == null) { throw new IllegalArgumentException(); }

rdp.setArchiveReader(this); - int parsedFiles = 0, ignoredFiles = 0; + int parsedFiles = 0; + int ignoredFiles = 0; Logger logger = Logger.getLogger(ArchiveReader.class.getName()); SortedSet<String> archivesImportHistory = new TreeSet<String>(); File archivesImportHistoryFile = new File(statsDirectory, @@ -82,8 +84,8 @@ public class ArchiveReader { if (rdp != null) { try { BufferedInputStream bis = null; - if (keepImportHistory && - archivesImportHistory.contains(pop.getName())) { + if (keepImportHistory + && archivesImportHistory.contains(pop.getName())) { ignoredFiles++; continue; } else if (pop.getName().endsWith(".tar.bz2")) { @@ -176,7 +178,8 @@ public class ArchiveReader { } catch (UnsupportedEncodingException e) { /* No way that US-ASCII is not supported. */ } - int start = -1, end = -1; + int start = -1; + int end = -1; String startToken = "onion-key\n"; while (end < ascii.length()) { start = ascii.indexOf(startToken, end); @@ -198,8 +201,8 @@ public class ArchiveReader { if (!this.microdescriptorValidAfterTimes.containsKey( digest256Hex)) { logger.fine("Could not store microdescriptor '" - + digest256Hex + "', which was not contained in a " - + "microdesc consensus."); + + digest256Hex + "', which was not contained in a " + + "microdesc consensus."); continue; } for (String validAfterTime : @@ -265,6 +268,7 @@ public class ArchiveReader {

private Map<String, Set<String>> microdescriptorValidAfterTimes = new HashMap<String, Set<String>>(); + public void haveParsedMicrodescConsensus(String validAfterTime, SortedSet<String> microdescriptorDigests) { for (String microdescriptor : microdescriptorDigests) { diff --git a/src/org/torproject/collector/relaydescs/ArchiveWriter.java b/src/org/torproject/collector/relaydescs/ArchiveWriter.java index a4bddff..370b5ea 100644 --- a/src/org/torproject/collector/relaydescs/ArchiveWriter.java +++ b/src/org/torproject/collector/relaydescs/ArchiveWriter.java @@ -1,7 +1,15 @@ /* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.relaydescs;

+import org.torproject.collector.main.Configuration; +import org.torproject.collector.main.LockFile; +import org.torproject.collector.main.LoggingConfiguration; +import org.torproject.descriptor.DescriptorParseException; +import org.torproject.descriptor.DescriptorParser; +import org.torproject.descriptor.DescriptorSourceFactory; + import java.io.BufferedOutputStream; import java.io.BufferedReader; import java.io.BufferedWriter; @@ -27,13 +35,6 @@ import java.util.TreeMap; import java.util.logging.Level; import java.util.logging.Logger;

-import org.torproject.descriptor.DescriptorParser; -import org.torproject.descriptor.DescriptorSourceFactory; -import org.torproject.descriptor.DescriptorParseException; -import org.torproject.collector.main.Configuration; -import org.torproject.collector.main.LockFile; -import org.torproject.collector.main.LoggingConfiguration; - public class ArchiveWriter extends Thread {

public static void main(String[] args) { @@ -78,11 +79,13 @@ public class ArchiveWriter extends Thread { private File outputDirectory; private String rsyncCatString; private DescriptorParser descriptorParser; - private int storedConsensusesCounter = 0, - storedMicrodescConsensusesCounter = 0, storedVotesCounter = 0, - storedCertsCounter = 0, storedServerDescriptorsCounter = 0, - storedExtraInfoDescriptorsCounter = 0, - storedMicrodescriptorsCounter = 0; + private int storedConsensusesCounter = 0; + private int storedMicrodescConsensusesCounter = 0; + private int storedVotesCounter = 0; + private int storedCertsCounter = 0; + private int storedServerDescriptorsCounter = 0; + private int storedExtraInfoDescriptorsCounter = 0; + private int storedMicrodescriptorsCounter = 0;

private SortedMap<Long, SortedSet<String>> storedConsensuses = new TreeMap<Long, SortedSet<String>>(); @@ -361,6 +364,7 @@ public class ArchiveWriter extends Thread {

private static final byte[] CONSENSUS_ANNOTATION = "@type network-status-consensus-3 1.0\n".getBytes(); + public void storeConsensus(byte[] data, long validAfter, SortedSet<String> dirSources, SortedSet<String> serverDescriptorDigests) { @@ -376,8 +380,8 @@ public class ArchiveWriter extends Thread { if (this.store(CONSENSUS_ANNOTATION, data, outputFiles, null)) { this.storedConsensusesCounter++; } - if (!tarballFileExistedBefore && - this.now - validAfter < 3L * 60L * 60L * 1000L) { + if (!tarballFileExistedBefore + && this.now - validAfter < 3L * 60L * 60L * 1000L) { this.storedConsensuses.put(validAfter, serverDescriptorDigests); this.expectedVotes.put(validAfter, dirSources.size()); } @@ -385,6 +389,7 @@ public class ArchiveWriter extends Thread {

private static final byte[] MICRODESCCONSENSUS_ANNOTATION = "@type network-status-microdesc-consensus-3 1.0\n".getBytes(); + public void storeMicrodescConsensus(byte[] data, long validAfter, SortedSet<String> microdescriptorDigests) { SimpleDateFormat yearMonthDirectoryFormat = new SimpleDateFormat( @@ -406,8 +411,8 @@ public class ArchiveWriter extends Thread { null)) { this.storedMicrodescConsensusesCounter++; } - if (!tarballFileExistedBefore && - this.now - validAfter < 3L * 60L * 60L * 1000L) { + if (!tarballFileExistedBefore + && this.now - validAfter < 3L * 60L * 60L * 1000L) { this.storedMicrodescConsensuses.put(validAfter, microdescriptorDigests); } @@ -415,6 +420,7 @@ public class ArchiveWriter extends Thread {

private static final byte[] VOTE_ANNOTATION = "@type network-status-vote-3 1.0\n".getBytes(); + public void storeVote(byte[] data, long validAfter, String fingerprint, String digest, SortedSet<String> serverDescriptorDigests) { @@ -431,8 +437,8 @@ public class ArchiveWriter extends Thread { if (this.store(VOTE_ANNOTATION, data, outputFiles, null)) { this.storedVotesCounter++; } - if (!tarballFileExistedBefore && - this.now - validAfter < 3L * 60L * 60L * 1000L) { + if (!tarballFileExistedBefore + && this.now - validAfter < 3L * 60L * 60L * 1000L) { if (!this.storedVotes.containsKey(validAfter)) { this.storedVotes.put(validAfter, new TreeMap<String, SortedSet<String>>()); @@ -444,6 +450,7 @@ public class ArchiveWriter extends Thread {

private static final byte[] CERTIFICATE_ANNOTATION = "@type dir-key-certificate-3 1.0\n".getBytes(); + public void storeCertificate(byte[] data, String fingerprint, long published) { SimpleDateFormat printFormat = new SimpleDateFormat( @@ -459,6 +466,7 @@ public class ArchiveWriter extends Thread {

private static final byte[] SERVER_DESCRIPTOR_ANNOTATION = "@type server-descriptor 1.0\n".getBytes(); + public void storeServerDescriptor(byte[] data, String digest, long published, String extraInfoDigest) { SimpleDateFormat printFormat = new SimpleDateFormat("yyyy/MM/"); @@ -477,8 +485,8 @@ public class ArchiveWriter extends Thread { append)) { this.storedServerDescriptorsCounter++; } - if (!tarballFileExistedBefore && - this.now - published < 48L * 60L * 60L * 1000L) { + if (!tarballFileExistedBefore + && this.now - published < 48L * 60L * 60L * 1000L) { if (!this.storedServerDescriptors.containsKey(published)) { this.storedServerDescriptors.put(published, new HashMap<String, String>()); @@ -490,6 +498,7 @@ public class ArchiveWriter extends Thread {

private static final byte[] EXTRA_INFO_ANNOTATION = "@type extra-info 1.0\n".getBytes(); + public void storeExtraInfoDescriptor(byte[] data, String extraInfoDigest, long published) { SimpleDateFormat descriptorFormat = new SimpleDateFormat("yyyy/MM/"); @@ -507,8 +516,8 @@ public class ArchiveWriter extends Thread { if (this.store(EXTRA_INFO_ANNOTATION, data, outputFiles, append)) { this.storedExtraInfoDescriptorsCounter++; } - if (!tarballFileExistedBefore && - this.now - published < 48L * 60L * 60L * 1000L) { + if (!tarballFileExistedBefore + && this.now - published < 48L * 60L * 60L * 1000L) { if (!this.storedExtraInfoDescriptors.containsKey(published)) { this.storedExtraInfoDescriptors.put(published, new HashSet<String>()); @@ -519,6 +528,7 @@ public class ArchiveWriter extends Thread {

private static final byte[] MICRODESCRIPTOR_ANNOTATION = "@type microdescriptor 1.0\n".getBytes(); + public void storeMicrodescriptor(byte[] data, String microdescriptorDigest, long validAfter) { /* TODO We could check here whether we already stored the @@ -545,8 +555,8 @@ public class ArchiveWriter extends Thread { append)) { this.storedMicrodescriptorsCounter++; } - if (!tarballFileExistedBefore && - this.now - validAfter < 40L * 24L * 60L * 60L * 1000L) { + if (!tarballFileExistedBefore + && this.now - validAfter < 40L * 24L * 60L * 60L * 1000L) { if (!this.storedMicrodescriptors.containsKey(validAfter)) { this.storedMicrodescriptors.put(validAfter, new HashSet<String>()); @@ -557,6 +567,7 @@ public class ArchiveWriter extends Thread { }

private StringBuilder intermediateStats = new StringBuilder(); + public void intermediateStats(String event) { intermediateStats.append("While " + event + ", we stored " + this.storedConsensusesCounter + " consensus(es), " @@ -600,8 +611,9 @@ public class ArchiveWriter extends Thread { for (Set<String> descriptors : this.storedMicrodescriptors.values()) { knownMicrodescriptors.addAll(descriptors); } - boolean missingDescriptors = false, missingVotes = false, - missingMicrodescConsensus = false; + boolean missingDescriptors = false; + boolean missingVotes = false; + boolean missingMicrodescConsensus = false; for (Map.Entry<Long, SortedSet<String>> c : this.storedConsensuses.entrySet()) { long validAfterMillis = c.getKey(); @@ -613,8 +625,10 @@ public class ArchiveWriter extends Thread { foundVotes = this.storedVotes.get(validAfterMillis).size(); for (Map.Entry<String, SortedSet<String>> v : this.storedVotes.get(validAfterMillis).entrySet()) { - int voteFoundServerDescs = 0, voteAllServerDescs = 0, - voteFoundExtraInfos = 0, voteAllExtraInfos = 0; + int voteFoundServerDescs = 0; + int voteAllServerDescs = 0; + int voteFoundExtraInfos = 0; + int voteAllExtraInfos = 0; for (String serverDescriptorDigest : v.getValue()) { voteAllServerDescs++; if (knownServerDescriptors.containsKey( @@ -636,32 +650,35 @@ public class ArchiveWriter extends Thread { if (voteAllServerDescs > 0) { sb.append(String.format(", %d/%d S (%.1f%%)", voteFoundServerDescs, voteAllServerDescs, - 100.0D * (double) voteFoundServerDescs / - (double) voteAllServerDescs)); + 100.0D * (double) voteFoundServerDescs + / (double) voteAllServerDescs)); } else { sb.append(", 0/0 S"); } if (voteAllExtraInfos > 0) { sb.append(String.format(", %d/%d E (%.1f%%)", voteFoundExtraInfos, voteAllExtraInfos, - 100.0D * (double) voteFoundExtraInfos / - (double) voteAllExtraInfos)); + 100.0D * (double) voteFoundExtraInfos + / (double) voteAllExtraInfos)); } else { sb.append(", 0/0 E"); } String fingerprint = v.getKey(); /* Ignore turtles when warning about missing descriptors. */ if (!fingerprint.equalsIgnoreCase( - "27B6B5996C426270A5C95488AA5BCEB6BCC86956") && - (voteFoundServerDescs * 1000 < voteAllServerDescs * 995 || - voteFoundExtraInfos * 1000 < voteAllExtraInfos * 995)) { + "27B6B5996C426270A5C95488AA5BCEB6BCC86956") + && (voteFoundServerDescs * 1000 < voteAllServerDescs * 995 + || voteFoundExtraInfos * 1000 < voteAllExtraInfos * 995)) { missingDescriptors = true; } } } - int foundServerDescs = 0, allServerDescs = 0, foundExtraInfos = 0, - allExtraInfos = 0, foundMicrodescriptors = 0, - allMicrodescriptors = 0; + int foundServerDescs = 0; + int allServerDescs = 0; + int foundExtraInfos = 0; + int allExtraInfos = 0; + int foundMicrodescriptors = 0; + int allMicrodescriptors = 0; for (String serverDescriptorDigest : c.getValue()) { allServerDescs++; if (knownServerDescriptors.containsKey( @@ -688,15 +705,15 @@ public class ArchiveWriter extends Thread { } if (allServerDescs > 0) { sb.append(String.format(", %d/%d S (%.1f%%)", foundServerDescs, - allServerDescs, 100.0D * (double) foundServerDescs / - (double) allServerDescs)); + allServerDescs, 100.0D * (double) foundServerDescs + / (double) allServerDescs)); } else { sb.append(", 0/0 S"); } if (allExtraInfos > 0) { sb.append(String.format(", %d/%d E (%.1f%%)", foundExtraInfos, - allExtraInfos, 100.0D * (double) foundExtraInfos / - (double) allExtraInfos)); + allExtraInfos, 100.0D * (double) foundExtraInfos + / (double) allExtraInfos)); } else { sb.append(", 0/0 E"); } @@ -712,17 +729,17 @@ public class ArchiveWriter extends Thread { if (allMicrodescriptors > 0) { sb.append(String.format(", %d/%d M (%.1f%%)", foundMicrodescriptors, allMicrodescriptors, - 100.0D * (double) foundMicrodescriptors / - (double) allMicrodescriptors)); + 100.0D * (double) foundMicrodescriptors + / (double) allMicrodescriptors)); } else { sb.append(", 0/0 M"); } } else { missingMicrodescConsensus = true; } - if (foundServerDescs * 1000 < allServerDescs * 995 || - foundExtraInfos * 1000 < allExtraInfos * 995 || - foundMicrodescriptors * 1000 < allMicrodescriptors * 995) { + if (foundServerDescs * 1000 < allServerDescs * 995 + || foundExtraInfos * 1000 < allExtraInfos * 995 + || foundMicrodescriptors * 1000 < allMicrodescriptors * 995) { missingDescriptors = true; } if (foundVotes < allVotes) { @@ -756,44 +773,44 @@ public class ArchiveWriter extends Thread { "yyyy-MM-dd HH:mm:ss"); dateTimeFormat.setTimeZone(TimeZone.getTimeZone("UTC")); long tooOldMillis = this.now - 330L * 60L * 1000L; - if (!this.storedConsensuses.isEmpty() && - this.storedConsensuses.lastKey() < tooOldMillis) { + if (!this.storedConsensuses.isEmpty() + && this.storedConsensuses.lastKey() < tooOldMillis) { this.logger.warning("The last known relay network status " + "consensus was valid after " + dateTimeFormat.format(this.storedConsensuses.lastKey()) + ", which is more than 5:30 hours in the past."); } - if (!this.storedMicrodescConsensuses.isEmpty() && - this.storedMicrodescConsensuses.lastKey() < tooOldMillis) { + if (!this.storedMicrodescConsensuses.isEmpty() + && this.storedMicrodescConsensuses.lastKey() < tooOldMillis) { this.logger.warning("The last known relay network status " + "microdesc consensus was valid after " + dateTimeFormat.format( this.storedMicrodescConsensuses.lastKey()) + ", which is more than 5:30 hours in the past."); } - if (!this.storedVotes.isEmpty() && - this.storedVotes.lastKey() < tooOldMillis) { + if (!this.storedVotes.isEmpty() + && this.storedVotes.lastKey() < tooOldMillis) { this.logger.warning("The last known relay network status vote " + "was valid after " + dateTimeFormat.format( this.storedVotes.lastKey()) + ", which is more than 5:30 hours " + "in the past."); } - if (!this.storedServerDescriptors.isEmpty() && - this.storedServerDescriptors.lastKey() < tooOldMillis) { + if (!this.storedServerDescriptors.isEmpty() + && this.storedServerDescriptors.lastKey() < tooOldMillis) { this.logger.warning("The last known relay server descriptor was " + "published at " + dateTimeFormat.format(this.storedServerDescriptors.lastKey()) + ", which is more than 5:30 hours in the past."); } - if (!this.storedExtraInfoDescriptors.isEmpty() && - this.storedExtraInfoDescriptors.lastKey() < tooOldMillis) { + if (!this.storedExtraInfoDescriptors.isEmpty() + && this.storedExtraInfoDescriptors.lastKey() < tooOldMillis) { this.logger.warning("The last known relay extra-info descriptor " + "was published at " + dateTimeFormat.format( this.storedExtraInfoDescriptors.lastKey()) + ", which is more than 5:30 hours in the past."); } - if (!this.storedMicrodescriptors.isEmpty() && - this.storedMicrodescriptors.lastKey() < tooOldMillis) { + if (!this.storedMicrodescriptors.isEmpty() + && this.storedMicrodescriptors.lastKey() < tooOldMillis) { this.logger.warning("The last known relay microdescriptor was " + "contained in a microdesc consensus that was valid after " + dateTimeFormat.format(this.storedMicrodescriptors.lastKey()) diff --git a/src/org/torproject/collector/relaydescs/CachedRelayDescriptorReader.java b/src/org/torproject/collector/relaydescs/CachedRelayDescriptorReader.java index de0c060..b9001dd 100644 --- a/src/org/torproject/collector/relaydescs/CachedRelayDescriptorReader.java +++ b/src/org/torproject/collector/relaydescs/CachedRelayDescriptorReader.java @@ -1,7 +1,11 @@ -/* Copyright 2010--2012 The Tor Project +/* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.relaydescs;

+import org.apache.commons.codec.binary.Hex; +import org.apache.commons.codec.digest.DigestUtils; + import java.io.BufferedInputStream; import java.io.BufferedReader; import java.io.BufferedWriter; @@ -25,9 +29,6 @@ import java.util.TreeSet; import java.util.logging.Level; import java.util.logging.Logger;

-import org.apache.commons.codec.binary.Hex; -import org.apache.commons.codec.digest.DigestUtils; - /** * Parses all descriptors in local directory cacheddesc/ and sorts them * into directory structure in directory-archive/. @@ -36,8 +37,8 @@ public class CachedRelayDescriptorReader { public CachedRelayDescriptorReader(RelayDescriptorParser rdp, List<String> inputDirectories, File statsDirectory) {

- if (rdp == null || inputDirectories == null || - inputDirectories.isEmpty() || statsDirectory == null) { + if (rdp == null || inputDirectories == null + || inputDirectories.isEmpty() || statsDirectory == null) { throw new IllegalArgumentException(); }

@@ -48,8 +49,8 @@ public class CachedRelayDescriptorReader {

/* Read import history containing SHA-1 digests of previously parsed * statuses and descriptors, so that we can skip them in this run. */ - Set<String> lastImportHistory = new HashSet<String>(), - currentImportHistory = new HashSet<String>(); + Set<String> lastImportHistory = new HashSet<String>(); + Set<String> currentImportHistory = new HashSet<String>(); File importHistoryFile = new File(statsDirectory, "cacheddesc-import-history"); if (importHistoryFile.exists()) { @@ -114,8 +115,8 @@ public class CachedRelayDescriptorReader { SimpleDateFormat dateTimeFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); dateTimeFormat.setTimeZone(TimeZone.getTimeZone("UTC")); - if (dateTimeFormat.parse(line.substring("valid-after ". - length())).getTime() < System.currentTimeMillis() + if (dateTimeFormat.parse(line.substring("valid-after " + .length())).getTime() < System.currentTimeMillis() - 6L * 60L * 60L * 1000L) { logger.warning("Cached descriptor files in " + cachedDescDir.getAbsolutePath() + " are stale. " @@ -133,8 +134,8 @@ public class CachedRelayDescriptorReader { if (rdp != null) { String digest = Hex.encodeHexString(DigestUtils.sha( allData)); - if (!lastImportHistory.contains(digest) && - !currentImportHistory.contains(digest)) { + if (!lastImportHistory.contains(digest) + && !currentImportHistory.contains(digest)) { rdp.parse(allData); } else { dumpStats.append(" (skipped)"); @@ -142,7 +143,8 @@ public class CachedRelayDescriptorReader { currentImportHistory.add(digest); } } else if (f.getName().equals("v3-status-votes")) { - int parsedNum = 0, skippedNum = 0; + int parsedNum = 0; + int skippedNum = 0; String ascii = new String(allData, "US-ASCII"); String startToken = "network-status-version "; int end = ascii.length(); @@ -159,8 +161,8 @@ public class CachedRelayDescriptorReader { if (rdp != null) { String digest = Hex.encodeHexString(DigestUtils.sha( rawNetworkStatusBytes)); - if (!lastImportHistory.contains(digest) && - !currentImportHistory.contains(digest)) { + if (!lastImportHistory.contains(digest) + && !currentImportHistory.contains(digest)) { rdp.parse(rawNetworkStatusBytes); parsedNum++; } else { @@ -173,16 +175,19 @@ public class CachedRelayDescriptorReader { } dumpStats.append("\n" + f.getName() + ": parsed " + parsedNum + ", skipped " + skippedNum + " votes"); - } else if (f.getName().startsWith("cached-descriptors") || - f.getName().startsWith("cached-extrainfo")) { + } else if (f.getName().startsWith("cached-descriptors") + || f.getName().startsWith("cached-extrainfo")) { String ascii = new String(allData, "US-ASCII"); - int start = -1, sig = -1, end = -1; + int start = -1; + int sig = -1; + int end = -1; String startToken = - f.getName().startsWith("cached-descriptors") ? - "router " : "extra-info "; + f.getName().startsWith("cached-descriptors") + ? "router " : "extra-info "; String sigToken = "\nrouter-signature\n"; String endToken = "\n-----END SIGNATURE-----\n"; - int parsedNum = 0, skippedNum = 0; + int parsedNum = 0; + int skippedNum = 0; while (end < ascii.length()) { start = ascii.indexOf(startToken, end); if (start < 0) { @@ -203,8 +208,8 @@ public class CachedRelayDescriptorReader { if (rdp != null) { String digest = Hex.encodeHexString(DigestUtils.sha( descBytes)); - if (!lastImportHistory.contains(digest) && - !currentImportHistory.contains(digest)) { + if (!lastImportHistory.contains(digest) + && !currentImportHistory.contains(digest)) { rdp.parse(descBytes); parsedNum++; } else { @@ -215,8 +220,8 @@ public class CachedRelayDescriptorReader { } dumpStats.append("\n" + f.getName() + ": parsed " + parsedNum + ", skipped " + skippedNum + " " - + (f.getName().startsWith("cached-descriptors") ? - "server" : "extra-info") + " descriptors"); + + (f.getName().startsWith("cached-descriptors") + ? "server" : "extra-info") + " descriptors"); } } catch (IOException e) { logger.log(Level.WARNING, "Failed reading " diff --git a/src/org/torproject/collector/relaydescs/ReferenceChecker.java b/src/org/torproject/collector/relaydescs/ReferenceChecker.java index b9f36de..485fcea 100644 --- a/src/org/torproject/collector/relaydescs/ReferenceChecker.java +++ b/src/org/torproject/collector/relaydescs/ReferenceChecker.java @@ -1,5 +1,22 @@ +/* Copyright 2016 The Tor Project + * See LICENSE for licensing information */ + package org.torproject.collector.relaydescs;

+import org.torproject.descriptor.Descriptor; +import org.torproject.descriptor.DescriptorFile; +import org.torproject.descriptor.DescriptorReader; +import org.torproject.descriptor.DescriptorSourceFactory; +import org.torproject.descriptor.DirSourceEntry; +import org.torproject.descriptor.ExtraInfoDescriptor; +import org.torproject.descriptor.Microdescriptor; +import org.torproject.descriptor.NetworkStatusEntry; +import org.torproject.descriptor.RelayNetworkStatusConsensus; +import org.torproject.descriptor.RelayNetworkStatusVote; +import org.torproject.descriptor.ServerDescriptor; + +import com.google.gson.Gson; + import java.io.File; import java.io.FileReader; import java.io.FileWriter; @@ -17,20 +34,6 @@ import java.util.TreeSet; import java.util.logging.Level; import java.util.logging.Logger;

-import org.torproject.descriptor.Descriptor; -import org.torproject.descriptor.DescriptorFile; -import org.torproject.descriptor.DescriptorReader; -import org.torproject.descriptor.DescriptorSourceFactory; -import org.torproject.descriptor.DirSourceEntry; -import org.torproject.descriptor.ExtraInfoDescriptor; -import org.torproject.descriptor.Microdescriptor; -import org.torproject.descriptor.NetworkStatusEntry; -import org.torproject.descriptor.RelayNetworkStatusConsensus; -import org.torproject.descriptor.RelayNetworkStatusVote; -import org.torproject.descriptor.ServerDescriptor; - -import com.google.gson.Gson; - public class ReferenceChecker {

private Logger log = Logger.getLogger(ReferenceChecker.class.getName()); @@ -87,8 +90,8 @@ public class ReferenceChecker { return false; } Reference other = (Reference) otherObject; - return this.referencing.equals(other.referencing) && - this.referenced.equals(other.referenced); + return this.referencing.equals(other.referencing) + && this.referenced.equals(other.referenced); }

@Override @@ -168,6 +171,7 @@ public class ReferenceChecker { }

private static DateFormat dateTimeFormat; + static { dateTimeFormat = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss'Z'", Locale.US); @@ -175,9 +179,15 @@ public class ReferenceChecker { dateTimeFormat.setTimeZone(TimeZone.getTimeZone("UTC")); }

- private static final long ONE_HOUR = 60L * 60L * 1000L, - THREE_HOURS = 3L * ONE_HOUR, SIX_HOURS = 6L * ONE_HOUR, - ONE_DAY = 24L * ONE_HOUR, THIRTY_DAYS = 30L * ONE_DAY; + private static final long ONE_HOUR = 60L * 60L * 1000L; + + private static final long THREE_HOURS = 3L * ONE_HOUR; + + private static final long SIX_HOURS = 6L * ONE_HOUR; + + private static final long ONE_DAY = 24L * ONE_HOUR; + + private static final long THIRTY_DAYS = 30L * ONE_DAY;

private void readRelayNetworkStatusConsensusUnflavored( RelayNetworkStatusConsensus consensus) { @@ -194,8 +204,8 @@ public class ReferenceChecker { consensus.getValidAfterMillis() + THREE_HOURS); } } - double entryWeight = 200.0 / - ((double) consensus.getStatusEntries().size()); + double entryWeight = 200.0 + / ((double) consensus.getStatusEntries().size()); for (NetworkStatusEntry entry : consensus.getStatusEntries().values()) { this.addReference(referencing, @@ -212,8 +222,8 @@ public class ReferenceChecker { String referencing = String.format("M-%s", validAfter); this.addReference(referencing, String.format("C-%s", validAfter), 1.0, consensus.getValidAfterMillis() + THREE_HOURS); - double entryWeight = 200.0 / - ((double) consensus.getStatusEntries().size()); + double entryWeight = 200.0 + / ((double) consensus.getStatusEntries().size()); for (NetworkStatusEntry entry : consensus.getStatusEntries().values()) { for (String digest : entry.getMicrodescriptorDigests()) { @@ -227,8 +237,8 @@ public class ReferenceChecker { String validAfter = dateTimeFormat.format(vote.getValidAfterMillis()); String referencing = String.format("V-%s-%s", validAfter, vote.getIdentity()); - double entryWeight = 200.0 / - ((double) vote.getStatusEntries().size()); + double entryWeight = 200.0 + / ((double) vote.getStatusEntries().size()); for (NetworkStatusEntry entry : vote.getStatusEntries().values()) { this.addReference(referencing, String.format("S-%s", entry.getDescriptor()), entryWeight, @@ -277,8 +287,8 @@ public class ReferenceChecker { StringBuilder sb = new StringBuilder("Missing referenced " + "descriptors:"); for (Reference reference : this.references) { - if (reference.referenced.length() > 0 && - !knownDescriptors.contains(reference.referenced)) { + if (reference.referenced.length() > 0 + && !knownDescriptors.contains(reference.referenced)) { if (!missingDescriptors.contains(reference.referenced)) { totalMissingDescriptorsWeight += reference.weight; } diff --git a/src/org/torproject/collector/relaydescs/RelayDescriptorDownloader.java b/src/org/torproject/collector/relaydescs/RelayDescriptorDownloader.java index 8cfbf10..458332a 100644 --- a/src/org/torproject/collector/relaydescs/RelayDescriptorDownloader.java +++ b/src/org/torproject/collector/relaydescs/RelayDescriptorDownloader.java @@ -1,7 +1,11 @@ -/* Copyright 2010--2014 The Tor Project +/* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.relaydescs;

+import org.apache.commons.codec.binary.Base64; +import org.apache.commons.codec.digest.DigestUtils; + import java.io.BufferedInputStream; import java.io.BufferedReader; import java.io.BufferedWriter; @@ -31,9 +35,6 @@ import java.util.logging.Level; import java.util.logging.Logger; import java.util.zip.InflaterInputStream;

-import org.apache.commons.codec.binary.Base64; -import org.apache.commons.codec.digest.DigestUtils; - /** * Downloads relay descriptors from the directory authorities via HTTP. * Keeps a list of missing descriptors that gets updated by parse results @@ -224,25 +225,61 @@ public class RelayDescriptorDownloader { * that we requested, and that we successfully downloaded in this * execution. */ - private int oldMissingConsensuses = 0, - oldMissingMicrodescConsensuses = 0, oldMissingVotes = 0, - oldMissingServerDescriptors = 0, oldMissingExtraInfoDescriptors = 0, - oldMissingMicrodescriptors = 0, newMissingConsensuses = 0, - newMissingMicrodescConsensuses = 0, newMissingVotes = 0, - newMissingServerDescriptors = 0, newMissingExtraInfoDescriptors = 0, - newMissingMicrodescriptors = 0, requestedConsensuses = 0, - requestedMicrodescConsensuses = 0, requestedVotes = 0, - requestedMissingServerDescriptors = 0, - requestedAllServerDescriptors = 0, - requestedMissingExtraInfoDescriptors = 0, - requestedAllExtraInfoDescriptors = 0, - requestedMissingMicrodescriptors = 0, downloadedConsensuses = 0, - downloadedMicrodescConsensuses = 0, downloadedVotes = 0, - downloadedMissingServerDescriptors = 0, - downloadedAllServerDescriptors = 0, - downloadedMissingExtraInfoDescriptors = 0, - downloadedAllExtraInfoDescriptors = 0, - downloadedMissingMicrodescriptors = 0; + private int oldMissingConsensuses = 0; + + private int oldMissingMicrodescConsensuses = 0; + + private int oldMissingVotes = 0; + + private int oldMissingServerDescriptors = 0; + + private int oldMissingExtraInfoDescriptors = 0; + + private int oldMissingMicrodescriptors = 0; + + private int newMissingConsensuses = 0; + + private int newMissingMicrodescConsensuses = 0; + + private int newMissingVotes = 0; + + private int newMissingServerDescriptors = 0; + + private int newMissingExtraInfoDescriptors = 0; + + private int newMissingMicrodescriptors = 0; + + private int requestedConsensuses = 0; + + private int requestedMicrodescConsensuses = 0; + + private int requestedVotes = 0; + + private int requestedMissingServerDescriptors = 0; + + private int requestedAllServerDescriptors = 0; + + private int requestedMissingExtraInfoDescriptors = 0; + + private int requestedAllExtraInfoDescriptors = 0; + + private int requestedMissingMicrodescriptors = 0; + + private int downloadedConsensuses = 0; + + private int downloadedMicrodescConsensuses = 0; + + private int downloadedVotes = 0; + + private int downloadedMissingServerDescriptors = 0; + + private int downloadedAllServerDescriptors = 0; + + private int downloadedMissingExtraInfoDescriptors = 0; + + private int downloadedAllExtraInfoDescriptors = 0; + + private int downloadedMissingMicrodescriptors = 0;

/** * Initializes this class, including reading in missing descriptors from @@ -292,8 +329,8 @@ public class RelayDescriptorDownloader { SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); format.setTimeZone(TimeZone.getTimeZone("UTC")); long now = System.currentTimeMillis(); - this.currentValidAfter = format.format((now / (60L * 60L * 1000L)) * - (60L * 60L * 1000L)); + this.currentValidAfter = format.format((now / (60L * 60L * 1000L)) + * (60L * 60L * 1000L)); this.descriptorCutOff = format.format(now - 24L * 60L * 60L * 1000L); this.currentTimestamp = format.format(now); this.downloadAllDescriptorsCutOff = format.format(now @@ -317,14 +354,14 @@ public class RelayDescriptorDownloader { while ((line = br.readLine()) != null) { if (line.split(",").length > 2) { String published = line.split(",")[1]; - if (((line.startsWith("consensus,") || - line.startsWith("consensus-microdesc,") || - line.startsWith("vote,")) && - this.currentValidAfter.equals(published)) || - ((line.startsWith("server,") || - line.startsWith("extra,") || - line.startsWith("micro,")) && - this.descriptorCutOff.compareTo(published) < 0)) { + if (((line.startsWith("consensus,") + || line.startsWith("consensus-microdesc,") + || line.startsWith("vote,")) + && this.currentValidAfter.equals(published)) + || ((line.startsWith("server,") + || line.startsWith("extra,") + || line.startsWith("micro,")) + && this.descriptorCutOff.compareTo(published) < 0)) { if (!line.endsWith("NA")) { /* Not missing. */ } else if (line.startsWith("consensus,")) { @@ -352,8 +389,8 @@ public class RelayDescriptorDownloader { } this.microdescriptorKeys.get(microdescriptorDigest).add( microdescriptorKey); - if (line.endsWith("NA") && !this.missingMicrodescriptors. - contains(microdescriptorDigest)) { + if (line.endsWith("NA") && !this.missingMicrodescriptors + .contains(microdescriptorDigest)) { this.missingMicrodescriptors.add(microdescriptorDigest); oldMissingMicrodescriptors++; } @@ -418,8 +455,8 @@ public class RelayDescriptorDownloader { * download all server and extra-info descriptors from. */ this.downloadAllDescriptorsFromAuthorities = new HashSet<String>(); for (String authority : this.authorities) { - if (!this.lastDownloadedAllDescriptors.containsKey(authority) || - this.lastDownloadedAllDescriptors.get(authority).compareTo( + if (!this.lastDownloadedAllDescriptors.containsKey(authority) + || this.lastDownloadedAllDescriptors.get(authority).compareTo( this.downloadAllDescriptorsCutOff) < 0) { this.downloadAllDescriptorsFromAuthorities.add(authority); } @@ -523,8 +560,8 @@ public class RelayDescriptorDownloader { this.microdescriptorKeys.get(microdescriptorDigest).add( microdescriptorKey); this.missingDescriptors.put(microdescriptorKey, parsed); - if (parsed.equals("NA") && - !this.missingMicrodescriptors.contains(microdescriptorDigest)) { + if (parsed.equals("NA") + && !this.missingMicrodescriptors.contains(microdescriptorDigest)) { this.missingMicrodescriptors.add(microdescriptorDigest); this.newMissingMicrodescriptors++; } @@ -662,8 +699,8 @@ public class RelayDescriptorDownloader { /* Start with downloading the current consensus, unless we already * have it. */ if (downloadCurrentConsensus) { - if (this.missingDescriptors.containsKey(consensusKey) && - this.missingDescriptors.get(consensusKey).equals("NA")) { + if (this.missingDescriptors.containsKey(consensusKey) + && this.missingDescriptors.get(consensusKey).equals("NA")) { this.requestedConsensuses++; this.downloadedConsensuses += this.downloadResourceFromAuthority(authority, @@ -673,10 +710,9 @@ public class RelayDescriptorDownloader {

/* Then try to download the microdesc consensus. */ if (downloadCurrentMicrodescConsensus) { - if (this.missingDescriptors.containsKey( - microdescConsensusKey) && - this.missingDescriptors.get(microdescConsensusKey). - equals("NA")) { + if (this.missingDescriptors.containsKey(microdescConsensusKey) + && this.missingDescriptors.get(microdescConsensusKey) + .equals("NA")) { this.requestedMicrodescConsensuses++; this.downloadedMicrodescConsensuses += this.downloadResourceFromAuthority(authority, @@ -690,8 +726,8 @@ public class RelayDescriptorDownloader { SortedSet<String> fingerprints = new TreeSet<String>(); for (Map.Entry<String, String> e : this.missingDescriptors.entrySet()) { - if (e.getValue().equals("NA") && - e.getKey().startsWith(voteKeyPrefix)) { + if (e.getValue().equals("NA") + && e.getKey().startsWith(voteKeyPrefix)) { String fingerprint = e.getKey().split(",")[2]; fingerprints.add(fingerprint); } @@ -714,9 +750,9 @@ public class RelayDescriptorDownloader { * authority if we haven't done so for 24 hours and if we're * configured to do so. */ if (this.downloadAllDescriptorsFromAuthorities.contains( - authority) && ((type.equals("server") && - this.downloadAllServerDescriptors) || - (type.equals("extra") && this.downloadAllExtraInfos))) { + authority) && ((type.equals("server") + && this.downloadAllServerDescriptors) + || (type.equals("extra") && this.downloadAllExtraInfos))) { int downloadedAllDescriptors = this.downloadResourceFromAuthority(authority, "/tor/" + type + "/all"); @@ -732,11 +768,11 @@ public class RelayDescriptorDownloader {

/* Download missing server descriptors, extra-info descriptors, * and microdescriptors if we're configured to do so. */ - } else if ((type.equals("server") && - this.downloadMissingServerDescriptors) || - (type.equals("extra") && this.downloadMissingExtraInfos) || - (type.equals("micro") && - this.downloadMissingMicrodescriptors)) { + } else if ((type.equals("server") + && this.downloadMissingServerDescriptors) + || (type.equals("extra") && this.downloadMissingExtraInfos) + || (type.equals("micro") + && this.downloadMissingMicrodescriptors)) {

/* Go through the list of missing descriptors of this type * and combine the descriptor identifiers to a URL of up to @@ -746,23 +782,24 @@ public class RelayDescriptorDownloader { new TreeSet<String>(); for (Map.Entry<String, String> e : this.missingDescriptors.entrySet()) { - if (e.getValue().equals("NA") && - e.getKey().startsWith(type + ",") && - this.descriptorCutOff.compareTo( + if (e.getValue().equals("NA") + && e.getKey().startsWith(type + ",") + && this.descriptorCutOff.compareTo( e.getKey().split(",")[1]) < 0) { String descriptorIdentifier = e.getKey().split(",")[3]; descriptorIdentifiers.add(descriptorIdentifier); } } StringBuilder combinedResource = null; - int descriptorsInCombinedResource = 0, - requestedDescriptors = 0, downloadedDescriptors = 0; + int descriptorsInCombinedResource = 0; + int requestedDescriptors = 0; + int downloadedDescriptors = 0; int maxDescriptorsInCombinedResource = type.equals("micro") ? 92 : 96; String separator = type.equals("micro") ? "-" : "+"; for (String descriptorIdentifier : descriptorIdentifiers) { - if (descriptorsInCombinedResource >= - maxDescriptorsInCombinedResource) { + if (descriptorsInCombinedResource + >= maxDescriptorsInCombinedResource) { requestedDescriptors += descriptorsInCombinedResource; downloadedDescriptors += this.downloadResourceFromAuthority(authority, @@ -836,8 +873,8 @@ public class RelayDescriptorDownloader { huc.connect(); int response = huc.getResponseCode(); if (response == 200) { - BufferedInputStream in = this.downloadCompressed && - !resource.startsWith("/tor/extra/") + BufferedInputStream in = this.downloadCompressed + && !resource.startsWith("/tor/extra/") ? new BufferedInputStream(new InflaterInputStream( huc.getInputStream())) : new BufferedInputStream(huc.getInputStream()); @@ -857,10 +894,10 @@ public class RelayDescriptorDownloader { if (resource.startsWith("/tor/status-vote/current/")) { this.rdp.parse(allData); receivedDescriptors = 1; - } else if (resource.startsWith("/tor/server/") || - resource.startsWith("/tor/extra/")) { - if (resource.equals("/tor/server/all") || - resource.equals("/tor/extra/all")) { + } else if (resource.startsWith("/tor/server/") + || resource.startsWith("/tor/extra/")) { + if (resource.equals("/tor/server/all") + || resource.equals("/tor/extra/all")) { this.lastDownloadedAllDescriptors.put(authority, this.currentTimestamp); } @@ -870,9 +907,11 @@ public class RelayDescriptorDownloader { } catch (UnsupportedEncodingException e) { /* No way that US-ASCII is not supported. */ } - int start = -1, sig = -1, end = -1; - String startToken = resource.startsWith("/tor/server/") ? - "router " : "extra-info "; + int start = -1; + int sig = -1; + int end = -1; + String startToken = resource.startsWith("/tor/server/") + ? "router " : "extra-info "; String sigToken = "\nrouter-signature\n"; String endToken = "\n-----END SIGNATURE-----\n"; while (end < ascii.length()) { @@ -910,7 +949,8 @@ public class RelayDescriptorDownloader { } catch (UnsupportedEncodingException e) { /* No way that US-ASCII is not supported. */ } - int start = -1, end = -1; + int start = -1; + int end = -1; String startToken = "onion-key\n"; while (end < ascii.length()) { start = ascii.indexOf(startToken, end); @@ -961,9 +1001,11 @@ public class RelayDescriptorDownloader { public void writeFile() {

/* Write missing descriptors file to disk. */ - int missingConsensuses = 0, missingMicrodescConsensuses = 0, - missingVotes = 0, missingServerDescriptors = 0, - missingExtraInfoDescriptors = 0; + int missingConsensuses = 0; + int missingMicrodescConsensuses = 0; + int missingVotes = 0; + int missingServerDescriptors = 0; + int missingExtraInfoDescriptors = 0; try { this.logger.fine("Writing file " + this.missingDescriptorsFile.getAbsolutePath() + "..."); @@ -972,7 +1014,8 @@ public class RelayDescriptorDownloader { this.missingDescriptorsFile)); for (Map.Entry<String, String> e : this.missingDescriptors.entrySet()) { - String key = e.getKey(), value = e.getValue(); + String key = e.getKey(); + String value = e.getValue(); if (!value.equals("NA")) { /* Not missing. */ } else if (key.startsWith("consensus,")) { @@ -986,6 +1029,7 @@ public class RelayDescriptorDownloader { } else if (key.startsWith("extra,")) { missingExtraInfoDescriptors++; } else if (key.startsWith("micro,")) { + /* We're counting missing microdescriptors below. */ } bw.write(key + "," + value + "\n"); } @@ -1059,7 +1103,7 @@ public class RelayDescriptorDownloader { StringBuilder sb = new StringBuilder(); for (String authority : this.authorities) { sb.append(" " + authority + "=" - + this.requestsByAuthority.get(authority)); + + this.requestsByAuthority.get(authority)); } this.logger.info("We sent these numbers of requests to the directory " + "authorities:" + sb.toString()); diff --git a/src/org/torproject/collector/relaydescs/RelayDescriptorParser.java b/src/org/torproject/collector/relaydescs/RelayDescriptorParser.java index 4158d52..3f9b912 100644 --- a/src/org/torproject/collector/relaydescs/RelayDescriptorParser.java +++ b/src/org/torproject/collector/relaydescs/RelayDescriptorParser.java @@ -1,7 +1,12 @@ -/* Copyright 2010--2014 The Tor Project +/* Copyright 2010--2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.relaydescs;

+import org.apache.commons.codec.binary.Base64; +import org.apache.commons.codec.binary.Hex; +import org.apache.commons.codec.digest.DigestUtils; + import java.io.BufferedReader; import java.io.IOException; import java.io.StringReader; @@ -13,10 +18,6 @@ import java.util.TreeSet; import java.util.logging.Level; import java.util.logging.Logger;

-import org.apache.commons.codec.binary.Base64; -import org.apache.commons.codec.binary.Hex; -import org.apache.commons.codec.digest.DigestUtils; - /** * Parses relay descriptors including network status consensuses and * votes, server and extra-info descriptors, and passes the results to the @@ -93,9 +94,11 @@ public class RelayDescriptorParser { if (line.equals("network-status-version 3 microdesc")) { statusType = "consensus-microdesc"; } - String validAfterTime = null, fingerprint = null, - dirSource = null; - long validAfter = -1L, dirKeyPublished = -1L; + String validAfterTime = null; + String fingerprint = null; + String dirSource = null; + long validAfter = -1L; + long dirKeyPublished = -1L; SortedSet<String> dirSources = new TreeSet<String>(); SortedSet<String> serverDescriptors = new TreeSet<String>(); SortedSet<String> serverDescriptorDigests = new TreeSet<String>(); @@ -130,8 +133,8 @@ public class RelayDescriptorParser { } else if (line.startsWith("dir-key-published ")) { String dirKeyPublishedTime = line.substring( "dir-key-published ".length()); - dirKeyPublished = parseFormat.parse(dirKeyPublishedTime). - getTime(); + dirKeyPublished = parseFormat.parse(dirKeyPublishedTime) + .getTime(); } else if (line.startsWith("r ")) { String[] parts = line.split(" "); if (parts.length == 8) { @@ -158,12 +161,12 @@ public class RelayDescriptorParser { microdescriptorKeys.add(validAfterTime + "," + lastRelayIdentity + "," + digest256Base64); String digest256Hex = Hex.encodeHexString( - Base64.decodeBase64(digest256Base64 + "=")). - toLowerCase(); + Base64.decodeBase64(digest256Base64 + "=")) + .toLowerCase(); microdescriptorDigests.add(digest256Hex); - } else if (parts.length != 3 || - !parts[2].startsWith("sha256=") || - parts[2].length() != 50) { + } else if (parts.length != 3 + || !parts[2].startsWith("sha256=") + || parts[2].length() != 50) { this.logger.log(Level.WARNING, "Could not parse m line '" + line + "' in descriptor. Skipping."); break; @@ -226,23 +229,24 @@ public class RelayDescriptorParser { } } } else if (line.startsWith("router ")) { - String publishedTime = null, extraInfoDigest = null, - relayIdentifier = null; + String publishedTime = null; + String extraInfoDigest = null; + String relayIdentifier = null; long published = -1L; while ((line = br.readLine()) != null) { if (line.startsWith("published ")) { publishedTime = line.substring("published ".length()); published = parseFormat.parse(publishedTime).getTime(); - } else if (line.startsWith("opt fingerprint") || - line.startsWith("fingerprint")) { - relayIdentifier = line.substring(line.startsWith("opt ") ? - "opt fingerprint".length() : "fingerprint".length()). - replaceAll(" ", "").toLowerCase(); - } else if (line.startsWith("opt extra-info-digest ") || - line.startsWith("extra-info-digest ")) { - extraInfoDigest = line.startsWith("opt ") ? - line.split(" ")[2].toLowerCase() : - line.split(" ")[1].toLowerCase(); + } else if (line.startsWith("opt fingerprint") + || line.startsWith("fingerprint")) { + relayIdentifier = line.substring(line.startsWith("opt ") + ? "opt fingerprint".length() : "fingerprint".length()) + .replaceAll(" ", "").toLowerCase(); + } else if (line.startsWith("opt extra-info-digest ") + || line.startsWith("extra-info-digest ")) { + extraInfoDigest = line.startsWith("opt ") + ? line.split(" ")[2].toLowerCase() + : line.split(" ")[1].toLowerCase(); } } String ascii = new String(data, "US-ASCII"); @@ -266,7 +270,8 @@ public class RelayDescriptorParser { relayIdentifier, digest, extraInfoDigest); } } else if (line.startsWith("extra-info ")) { - String publishedTime = null, relayIdentifier = line.split(" ")[2]; + String publishedTime = null; + String relayIdentifier = line.split(" ")[2]; long published = -1L; while ((line = br.readLine()) != null) { if (line.startsWith("published ")) { diff --git a/src/org/torproject/collector/torperf/TorperfDownloader.java b/src/org/torproject/collector/torperf/TorperfDownloader.java index a1483c2..a2c94ef 100644 --- a/src/org/torproject/collector/torperf/TorperfDownloader.java +++ b/src/org/torproject/collector/torperf/TorperfDownloader.java @@ -1,7 +1,12 @@ /* Copyright 2012-2016 The Tor Project * See LICENSE for licensing information */ + package org.torproject.collector.torperf;

+import org.torproject.collector.main.Configuration; +import org.torproject.collector.main.LockFile; +import org.torproject.collector.main.LoggingConfiguration; + import java.io.BufferedReader; import java.io.BufferedWriter; import java.io.File; @@ -22,10 +27,6 @@ import java.util.TreeMap; import java.util.logging.Level; import java.util.logging.Logger;

-import org.torproject.collector.main.Configuration; -import org.torproject.collector.main.LockFile; -import org.torproject.collector.main.LoggingConfiguration; - /* Download possibly truncated Torperf .data and .extradata files from * configured sources, append them to the files we already have, and merge * the two files into the .tpf format. */ @@ -97,8 +98,10 @@ public class TorperfDownloader extends Thread {

private File torperfLastMergedFile = new File("stats/torperf-last-merged"); + SortedMap<String, String> lastMergedTimestamps = new TreeMap<String, String>(); + private void readLastMergedTimestamps() { if (!this.torperfLastMergedFile.exists()) { return; @@ -109,7 +112,8 @@ public class TorperfDownloader extends Thread { String line; while ((line = br.readLine()) != null) { String[] parts = line.split(" "); - String fileName = null, timestamp = null; + String fileName = null; + String timestamp = null; if (parts.length == 2) { try { Double.parseDouble(parts[1]); @@ -315,11 +319,14 @@ public class TorperfDownloader extends Thread { } this.logger.fine("Merging " + dataFile.getAbsolutePath() + " and " + extradataFile.getAbsolutePath() + " into .tpf format."); - BufferedReader brD = new BufferedReader(new FileReader(dataFile)), - brE = new BufferedReader(new FileReader(extradataFile)); - String lineD = brD.readLine(), lineE = brE.readLine(); - int d = 1, e = 1; - String maxDataComplete = null, maxUsedAt = null; + BufferedReader brD = new BufferedReader(new FileReader(dataFile)); + BufferedReader brE = new BufferedReader(new FileReader(extradataFile)); + String lineD = brD.readLine(); + String lineE = brE.readLine(); + int d = 1; + int e = 1; + String maxDataComplete = null; + String maxUsedAt = null; while (lineD != null) {

/* Parse .data line. Every valid .data line will go into the .tpf @@ -363,8 +370,8 @@ public class TorperfDownloader extends Thread { + e++ + " which is a BUILDTIMEOUT_SET line."); lineE = brE.readLine(); continue; - } else if (lineE.startsWith("ok ") || - lineE.startsWith("error ")) { + } else if (lineE.startsWith("ok ") + || lineE.startsWith("error ")) { this.logger.finer("Skipping " + extradataFile.getName() + ":" + e++ + " which is in the old format."); lineE = brE.readLine(); @@ -446,6 +453,7 @@ public class TorperfDownloader extends Thread { }

private SortedMap<Integer, String> dataTimestamps; + private SortedMap<String, String> parseDataLine(String line) { String[] parts = line.trim().split(" "); if (line.length() == 0 || parts.length < 20) { @@ -504,18 +512,18 @@ public class TorperfDownloader extends Thread { String key = keyAndValue[0]; previousKey = key; String value = keyAndValue[1]; - if (value.contains(".") && value.lastIndexOf(".") == - value.length() - 2) { + if (value.contains(".") && value.lastIndexOf(".") + == value.length() - 2) { /* Make sure that all floats have two trailing digits. */ value += "0"; } extradata.put(key, value); } else if (keyAndValue.length == 1 && previousKey != null) { String value = keyAndValue[0]; - if (previousKey.equals("STREAM_FAIL_REASONS") && - (value.equals("MISC") || value.equals("EXITPOLICY") || - value.equals("RESOURCELIMIT") || - value.equals("RESOLVEFAILED"))) { + if (previousKey.equals("STREAM_FAIL_REASONS") + && (value.equals("MISC") || value.equals("EXITPOLICY") + || value.equals("RESOURCELIMIT") + || value.equals("RESOLVEFAILED"))) { extradata.put(previousKey, extradata.get(previousKey) + ":" + value); } else { @@ -529,9 +537,13 @@ public class TorperfDownloader extends Thread { }

private String cachedSource; + private int cachedFileSize; + private String cachedStartDate; + private SortedMap<String, String> cachedTpfLines; + private void writeTpfLine(String source, int fileSize, SortedMap<String, String> keysAndValues) throws IOException { StringBuilder sb = new StringBuilder(); @@ -547,14 +559,14 @@ public class TorperfDownloader extends Thread { long startMillis = Long.parseLong(startString.substring(0, startString.indexOf("."))) * 1000L; String startDate = dateFormat.format(startMillis); - if (this.cachedTpfLines == null || !source.equals(this.cachedSource) || - fileSize != this.cachedFileSize || - !startDate.equals(this.cachedStartDate)) { + if (this.cachedTpfLines == null || !source.equals(this.cachedSource) + || fileSize != this.cachedFileSize + || !startDate.equals(this.cachedStartDate)) { this.writeCachedTpfLines(); this.readTpfLinesToCache(source, fileSize, startDate); } - if (!this.cachedTpfLines.containsKey(startString) || - line.length() > this.cachedTpfLines.get(startString).length()) { + if (!this.cachedTpfLines.containsKey(startString) + || line.length() > this.cachedTpfLines.get(startString).length()) { this.cachedTpfLines.put(startString, line); } } @@ -588,8 +600,8 @@ public class TorperfDownloader extends Thread { }

private void writeCachedTpfLines() throws IOException { - if (this.cachedSource == null || this.cachedFileSize == 0 || - this.cachedStartDate == null || this.cachedTpfLines == null) { + if (this.cachedSource == null || this.cachedFileSize == 0 + || this.cachedStartDate == null || this.cachedTpfLines == null) { return; } File tarballFile = new File(torperfOutputDirectory,