- tor-commits - lists.torproject.org

[metrics-web/master] Make sure fingerprints and digests are lower-case.
by karsten＠torproject.org 22 Mar '12

22 Mar '12

commit b8067f823c87bfc8c8a4af936922a9d34ee85bb2 Author: Karsten Loesing <karsten.loesing(a)gmx.net> Date: Thu Mar 22 10:00:18 2012 +0100 Make sure fingerprints and digests are lower-case. --- src/org/torproject/ernie/cron/ArchiveReader.java | 14 ++++++++------ 1 files changed, 8 insertions(+), 6 deletions(-) diff --git a/src/org/torproject/ernie/cron/ArchiveReader.java b/src/org/torproject/ernie/cron/ArchiveReader.java index 5703661..4befe51 100644 --- a/src/org/torproject/ernie/cron/ArchiveReader.java +++ b/src/org/torproject/ernie/cron/ArchiveReader.java @@ -109,12 +109,14 @@ public class ArchiveReader { for (NetworkStatusEntry statusEntry : consensus.getStatusEntries().values()) { this.rddi.addStatusEntry(consensus.getValidAfterMillis(), - statusEntry.getNickname(), statusEntry.getFingerprint(), - statusEntry.getDescriptor(), statusEntry.getPublishedMillis(), - statusEntry.getAddress(), statusEntry.getOrPort(), - statusEntry.getDirPort(), statusEntry.getFlags(), - statusEntry.getVersion(), statusEntry.getBandwidth(), - statusEntry.getPortList(), statusEntry.getStatusEntryBytes()); + statusEntry.getNickname(), + statusEntry.getFingerprint().toLowerCase(), + statusEntry.getDescriptor().toLowerCase(), + statusEntry.getPublishedMillis(), statusEntry.getAddress(), + statusEntry.getOrPort(), statusEntry.getDirPort(), + statusEntry.getFlags(), statusEntry.getVersion(), + statusEntry.getBandwidth(), statusEntry.getPortList(), + statusEntry.getStatusEntryBytes()); try { this.bsfh.addHashedRelay(DigestUtils.shaHex(Hex.decodeHex( statusEntry.getFingerprint().toCharArray())).toUpperCase());

1 0

[metrics-web/master] Clean up main method for importing relay descriptors.
by karsten＠torproject.org 22 Mar '12

22 Mar '12

commit ed016c9e3552b72be8f4dc2bb46de259f226d04a Author: Karsten Loesing <karsten.loesing(a)gmx.net> Date: Wed Mar 21 15:18:23 2012 +0100 Clean up main method for importing relay descriptors. --- src/org/torproject/ernie/cron/Main.java | 34 +++++++++++------------------- 1 files changed, 13 insertions(+), 21 deletions(-) diff --git a/src/org/torproject/ernie/cron/Main.java b/src/org/torproject/ernie/cron/Main.java index 1c8ca48..8022fcc 100644 --- a/src/org/torproject/ernie/cron/Main.java +++ b/src/org/torproject/ernie/cron/Main.java @@ -37,28 +37,20 @@ public class Main { new BridgeStatsFileHandler( config.getRelayDescriptorDatabaseJDBC()) : null; - // Prepare writing relay descriptors to database - RelayDescriptorDatabaseImporter rddi = - config.getWriteRelayDescriptorDatabase() || - config.getWriteRelayDescriptorsRawFiles() ? - new RelayDescriptorDatabaseImporter( - config.getWriteRelayDescriptorDatabase() ? - config.getRelayDescriptorDatabaseJDBC() : null, - config.getWriteRelayDescriptorsRawFiles() ? - config.getRelayDescriptorRawFilesDirectory() : null) : null; - // Import relay descriptors - if (rddi != null) { - if (config.getImportDirectoryArchives()) { - new ArchiveReader(rddi, bsfh, - new File(config.getDirectoryArchivesDirectory()), - statsDirectory, - config.getKeepDirectoryArchiveImportHistory()); - } - } - - // Close database connection (if active) - if (rddi != null) { + if (config.getImportDirectoryArchives()) { + RelayDescriptorDatabaseImporter rddi = + config.getWriteRelayDescriptorDatabase() || + config.getWriteRelayDescriptorsRawFiles() ? + new RelayDescriptorDatabaseImporter( + config.getWriteRelayDescriptorDatabase() ? + config.getRelayDescriptorDatabaseJDBC() : null, + config.getWriteRelayDescriptorsRawFiles() ? + config.getRelayDescriptorRawFilesDirectory() : null) : null; + new ArchiveReader(rddi, bsfh, + new File(config.getDirectoryArchivesDirectory()), + statsDirectory, + config.getKeepDirectoryArchiveImportHistory()); rddi.closeConnection(); }

1 0

[metrics-web/master] Use metrics-lib for parsing relay descriptors.
by karsten＠torproject.org 22 Mar '12

22 Mar '12

commit 72c1aee10e13d199a2e604adb47c670c417ab0a0 Author: Karsten Loesing <karsten.loesing(a)gmx.net> Date: Wed Mar 21 14:44:30 2012 +0100 Use metrics-lib for parsing relay descriptors. --- config.template | 2 +- src/org/torproject/ernie/cron/ArchiveReader.java | 573 +++++--------------- src/org/torproject/ernie/cron/Configuration.java | 2 +- .../cron/RelayDescriptorDatabaseImporter.java | 32 +- 4 files changed, 155 insertions(+), 454 deletions(-) diff --git a/config.template b/config.template index 8c56909..ce2dc94 100644 --- a/config.template +++ b/config.template @@ -2,7 +2,7 @@ #ImportDirectoryArchives 0 # ## Relative path to directory to import directory archives from -#DirectoryArchivesDirectory archives/ +#DirectoryArchivesDirectory in/relay-descriptors/ # ## Keep a history of imported directory archive files to know which files ## have been imported before. This history can be useful when importing diff --git a/src/org/torproject/ernie/cron/ArchiveReader.java b/src/org/torproject/ernie/cron/ArchiveReader.java index ed1e505..5703661 100644 --- a/src/org/torproject/ernie/cron/ArchiveReader.java +++ b/src/org/torproject/ernie/cron/ArchiveReader.java @@ -2,34 +2,29 @@ * See LICENSE for licensing information */ package org.torproject.ernie.cron; -import java.io.BufferedInputStream; -import java.io.BufferedReader; -import java.io.BufferedWriter; -import java.io.ByteArrayOutputStream; import java.io.File; -import java.io.FileInputStream; -import java.io.FileReader; -import java.io.FileWriter; -import java.io.IOException; -import java.io.StringReader; -import java.text.ParseException; +import java.io.UnsupportedEncodingException; import java.text.SimpleDateFormat; import java.util.ArrayList; import java.util.HashMap; +import java.util.Iterator; import java.util.List; import java.util.Map; -import java.util.SortedMap; -import java.util.SortedSet; -import java.util.Stack; import java.util.TimeZone; -import java.util.TreeMap; -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.DecoderException; import org.apache.commons.codec.binary.Hex; import org.apache.commons.codec.digest.DigestUtils; +import org.torproject.descriptor.Descriptor; +import org.torproject.descriptor.DescriptorFile; +import org.torproject.descriptor.DescriptorReader; +import org.torproject.descriptor.DescriptorSourceFactory; +import org.torproject.descriptor.ExtraInfoDescriptor; +import org.torproject.descriptor.NetworkStatusEntry; +import org.torproject.descriptor.RelayNetworkStatusConsensus; +import org.torproject.descriptor.RelayNetworkStatusVote; +import org.torproject.descriptor.ServerDescriptor; /** * Read in all files in a given directory and pass buffered readers of @@ -72,439 +67,159 @@ public class ArchiveReader { int parsedFiles = 0, ignoredFiles = 0; this.logger = Logger.getLogger(ArchiveReader.class.getName()); - SortedMap<String, Long> - lastArchivesImportHistory = new TreeMap<String, Long>(), - newArchivesImportHistory = new TreeMap<String, Long>(); - File archivesImportHistoryFile = new File(statsDirectory, - "archives-import-history"); - if (keepImportHistory && archivesImportHistoryFile.exists()) { - try { - BufferedReader br = new BufferedReader(new FileReader( - archivesImportHistoryFile)); - String line = null; - while ((line = br.readLine()) != null) { - String[] parts = line.split(","); - if (parts.length < 2) { - logger.warning("Archives import history file does not " - + "contain timestamps. Skipping."); - break; - } - long lastModified = Long.parseLong(parts[0]); - String filename = parts[1]; - lastArchivesImportHistory.put(filename, lastModified); - } - br.close(); - } catch (IOException e) { - logger.log(Level.WARNING, "Could not read in archives import " - + "history file. Skipping."); - } - } if (archivesDirectory.exists()) { logger.fine("Importing files in directory " + archivesDirectory + "/..."); - Stack<File> filesInInputDir = new Stack<File>(); - filesInInputDir.add(archivesDirectory); - List<File> problems = new ArrayList<File>(); - while (!filesInInputDir.isEmpty()) { - File pop = filesInInputDir.pop(); - if (pop.isDirectory()) { - for (File f : pop.listFiles()) { - filesInInputDir.add(f); - } - } else { - try { - long lastModified = pop.lastModified(); - String filename = pop.getName(); - if (keepImportHistory) { - newArchivesImportHistory.put(filename, lastModified); - } - if (keepImportHistory && - lastArchivesImportHistory.containsKey(filename) && - lastArchivesImportHistory.get(filename) >= lastModified) { - ignoredFiles++; - continue; - } else if (filename.endsWith(".tar.bz2")) { - logger.warning("Cannot parse compressed tarball " - + pop.getAbsolutePath() + ". Skipping."); - continue; - } - FileInputStream fis = new FileInputStream(pop); - BufferedInputStream bis = new BufferedInputStream(fis); - ByteArrayOutputStream baos = new ByteArrayOutputStream(); - int len; - byte[] data = new byte[1024]; - while ((len = bis.read(data, 0, 1024)) >= 0) { - baos.write(data, 0, len); - } - bis.close(); - byte[] allData = baos.toByteArray(); - this.parse(allData); - parsedFiles++; - } catch (IOException e) { - problems.add(pop); - if (problems.size() > 3) { - break; - } - } - } + DescriptorReader reader = + DescriptorSourceFactory.createDescriptorReader(); + reader.addDirectory(archivesDirectory); + if (keepImportHistory) { + reader.setExcludeFiles(new File(statsDirectory, + "relay-descriptor-history")); } - if (problems.isEmpty()) { - logger.fine("Finished importing files in directory " - + archivesDirectory + "/."); - } else { - StringBuilder sb = new StringBuilder("Failed importing files in " - + "directory " + archivesDirectory + "/:"); - int printed = 0; - for (File f : problems) { - sb.append("\n " + f.getAbsolutePath()); - if (++printed >= 3) { - sb.append("\n ... more"); - break; + Iterator<DescriptorFile> descriptorFiles = reader.readDescriptors(); + while (descriptorFiles.hasNext()) { + DescriptorFile descriptorFile = descriptorFiles.next(); + if (descriptorFile.getDescriptors() != null) { + for (Descriptor descriptor : descriptorFile.getDescriptors()) { + if (descriptor instanceof RelayNetworkStatusConsensus) { + this.addRelayNetworkStatusConsensus( + (RelayNetworkStatusConsensus) descriptor); + } else if (descriptor instanceof RelayNetworkStatusVote) { + this.addRelayNetworkStatusVote( + (RelayNetworkStatusVote) descriptor); + } else if (descriptor instanceof ServerDescriptor) { + this.addServerDescriptor((ServerDescriptor) descriptor); + } else if (descriptor instanceof ExtraInfoDescriptor) { + this.addExtraInfoDescriptor( + (ExtraInfoDescriptor) descriptor); + } } } - logger.warning(sb.toString()); - } - } - if (keepImportHistory) { - try { - archivesImportHistoryFile.getParentFile().mkdirs(); - BufferedWriter bw = new BufferedWriter(new FileWriter( - archivesImportHistoryFile)); - for (Map.Entry<String, Long> historyEntry : - newArchivesImportHistory.entrySet()) { - bw.write(String.valueOf(historyEntry.getValue()) + "," - + historyEntry.getKey() + "\n"); - } - bw.close(); - } catch (IOException e) { - logger.log(Level.WARNING, "Could not write archives import " - + "history file."); } } + logger.info("Finished importing relay descriptors from local " + "directory:\nParsed " + parsedFiles + ", ignored " + ignoredFiles + " files."); } - public void parse(byte[] data) { - try { - /* Remove any @ lines at the beginning of the file and parse the - * first non-@ line to find out the descriptor type. */ - BufferedReader br = new BufferedReader(new StringReader(new String( - data, "US-ASCII"))); - String line = br.readLine(); - while (line != null && line.startsWith("@")) { - line = br.readLine(); - } - if (line == null) { - this.logger.fine("We were given a file that doesn't contain a " - + "single descriptor for parsing. Ignoring."); - return; + private void addRelayNetworkStatusConsensus( + RelayNetworkStatusConsensus consensus) { + for (NetworkStatusEntry statusEntry : + consensus.getStatusEntries().values()) { + this.rddi.addStatusEntry(consensus.getValidAfterMillis(), + statusEntry.getNickname(), statusEntry.getFingerprint(), + statusEntry.getDescriptor(), statusEntry.getPublishedMillis(), + statusEntry.getAddress(), statusEntry.getOrPort(), + statusEntry.getDirPort(), statusEntry.getFlags(), + statusEntry.getVersion(), statusEntry.getBandwidth(), + statusEntry.getPortList(), statusEntry.getStatusEntryBytes()); + try { + this.bsfh.addHashedRelay(DigestUtils.shaHex(Hex.decodeHex( + statusEntry.getFingerprint().toCharArray())).toUpperCase()); + } catch (DecoderException e) { } - br.close(); + } + this.rddi.addConsensus(consensus.getValidAfterMillis(), + consensus.getRawDescriptorBytes()); + } - /* Split the byte[] possibly containing multiple descriptors into - * byte[]'s with one descriptor each and parse them. */ - String startToken = null; - if (line.equals("network-status-version 3")) { - startToken = "network-status-version 3"; - } else if (line.startsWith("router ")) { - startToken = "router "; - } else if (line.startsWith("extra-info ")) { - startToken = "extra-info "; - } else if (line.equals("dir-key-certificate-version 3")) { - this.logger.fine("Not parsing dir key certificate."); - return; - } else { - this.logger.warning("Unknown descriptor type. First line is '" - + line + "'. Ignoring."); - return; - } - String splitToken = "\n" + startToken; - String ascii = new String(data, "US-ASCII"); - int length = data.length, start = ascii.indexOf(startToken); - while (start < length) { - int end = ascii.indexOf(splitToken, start); - if (end < 0) { - end = length; - } else { - end += 1; - } - byte[] descBytes = new byte[end - start]; - System.arraycopy(data, start, descBytes, 0, end - start); - parseSingleDescriptor(descBytes); - start = end; + private void addRelayNetworkStatusVote(RelayNetworkStatusVote vote) { + this.rddi.addVote(vote.getValidAfterMillis(), vote.getIdentity(), + vote.getRawDescriptorBytes()); + } + + private void addServerDescriptor(ServerDescriptor descriptor) { + String digest = null; + try { + String ascii = new String(descriptor.getRawDescriptorBytes(), + "US-ASCII"); + String startToken = "router "; + String sigToken = "\nrouter-signature\n"; + int start = ascii.indexOf(startToken); + int sig = ascii.indexOf(sigToken) + sigToken.length(); + if (start >= 0 || sig >= 0 || sig > start) { + byte[] forDigest = new byte[sig - start]; + System.arraycopy(descriptor.getRawDescriptorBytes(), start, + forDigest, 0, sig - start); + digest = DigestUtils.shaHex(forDigest); } - } catch (IOException e) { - this.logger.log(Level.WARNING, "Could not parse descriptor. " - + "Skipping.", e); + } catch (UnsupportedEncodingException e) { + } + if (digest != null) { + this.rddi.addServerDescriptor(digest, descriptor.getNickname(), + descriptor.getAddress(), descriptor.getOrPort(), + descriptor.getDirPort(), descriptor.getFingerprint(), + descriptor.getBandwidthRate(), descriptor.getBandwidthBurst(), + descriptor.getBandwidthObserved(), descriptor.getPlatform(), + descriptor.getPublishedMillis(), descriptor.getUptime(), + descriptor.getExtraInfoDigest(), + descriptor.getRawDescriptorBytes()); } } - private void parseSingleDescriptor(byte[] data) { + private void addExtraInfoDescriptor(ExtraInfoDescriptor descriptor) { + if (descriptor.getDirreqV3Reqs() != null) { + int allUsers = 0; + Map<String, String> obs = new HashMap<String, String>(); + for (Map.Entry<String, Integer> e : + descriptor.getDirreqV3Reqs().entrySet()) { + String country = e.getKey(); + int users = e.getValue() - 4; + allUsers += users; + obs.put(country, "" + users); + } + obs.put("zy", "" + allUsers); + this.rddi.addDirReqStats(descriptor.getFingerprint(), + descriptor.getDirreqStatsEndMillis(), + descriptor.getDirreqStatsIntervalLength(), obs); + } + if (descriptor.getConnBiDirectStatsEndMillis() >= 0L) { + this.rddi.addConnBiDirect(descriptor.getFingerprint(), + descriptor.getConnBiDirectStatsEndMillis(), + descriptor.getConnBiDirectStatsIntervalLength(), + descriptor.getConnBiDirectBelow(), + descriptor.getConnBiDirectRead(), + descriptor.getConnBiDirectWrite(), + descriptor.getConnBiDirectBoth()); + } + List<String> bandwidthHistoryLines = new ArrayList<String>(); + if (descriptor.getWriteHistory() != null) { + bandwidthHistoryLines.add(descriptor.getWriteHistory().getLine()); + } + if (descriptor.getReadHistory() != null) { + bandwidthHistoryLines.add(descriptor.getReadHistory().getLine()); + } + if (descriptor.getDirreqWriteHistory() != null) { + bandwidthHistoryLines.add( + descriptor.getDirreqWriteHistory().getLine()); + } + if (descriptor.getDirreqReadHistory() != null) { + bandwidthHistoryLines.add( + descriptor.getDirreqReadHistory().getLine()); + } + String digest = null; try { - /* Convert descriptor to ASCII for parsing. This means we'll lose - * the non-ASCII chars, but we don't care about them for parsing - * anyway. */ - BufferedReader br = new BufferedReader(new StringReader(new String( - data, "US-ASCII"))); - String line = br.readLine(); - SimpleDateFormat parseFormat = - new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); - parseFormat.setTimeZone(TimeZone.getTimeZone("UTC")); - if (line.equals("network-status-version 3")) { - // TODO when parsing the current consensus, check the fresh-until - // time to see when we switch from hourly to half-hourly - // consensuses - boolean isConsensus = true; - String validAfterTime = null, nickname = null, - relayIdentity = null, serverDesc = null, version = null, - ports = null; - String dirSource = null, address = null; - long validAfter = -1L, published = -1L, bandwidth = -1L, - orPort = 0L, dirPort = 0L; - SortedSet<String> relayFlags = null; - StringBuilder rawStatusEntry = null; - SortedSet<String> hashedRelayIdentities = new TreeSet<String>(); - while ((line = br.readLine()) != null) { - if (line.equals("vote-status vote")) { - isConsensus = false; - } else if (line.startsWith("valid-after ")) { - validAfterTime = line.substring("valid-after ".length()); - validAfter = parseFormat.parse(validAfterTime).getTime(); - } else if (line.startsWith("dir-source ")) { - dirSource = line.split(" ")[2]; - } else if (line.startsWith("r ")) { - if (isConsensus && relayIdentity != null && - this.rddi != null) { - byte[] rawDescriptor = rawStatusEntry.toString().getBytes(); - this.rddi.addStatusEntry(validAfter, nickname, - relayIdentity, serverDesc, published, address, orPort, - dirPort, relayFlags, version, bandwidth, ports, - rawDescriptor); - relayFlags = null; - version = null; - bandwidth = -1L; - ports = null; - } - rawStatusEntry = new StringBuilder(line + "\n"); - String[] parts = line.split(" "); - if (parts.length < 9) { - this.logger.log(Level.WARNING, "Could not parse r line '" - + line + "' in descriptor. Skipping."); - break; - } - nickname = parts[1]; - relayIdentity = Hex.encodeHexString( - Base64.decodeBase64(parts[2] + "=")). - toLowerCase(); - hashedRelayIdentities.add(DigestUtils.shaHex( - Base64.decodeBase64(parts[2] + "=")). - toUpperCase()); - serverDesc = Hex.encodeHexString(Base64.decodeBase64( - parts[3] + "=")).toLowerCase(); - published = parseFormat.parse(parts[4] + " " + parts[5]). - getTime(); - address = parts[6]; - orPort = Long.parseLong(parts[7]); - dirPort = Long.parseLong(parts[8]); - } else if (line.startsWith("s ") || line.equals("s")) { - rawStatusEntry.append(line + "\n"); - relayFlags = new TreeSet<String>(); - if (line.length() > 2) { - for (String flag : line.substring(2).split(" ")) { - relayFlags.add(flag); - } - } - } else if (line.startsWith("v ")) { - rawStatusEntry.append(line + "\n"); - version = line.substring(2); - } else if (line.startsWith("w ")) { - rawStatusEntry.append(line + "\n"); - String[] parts = line.split(" "); - for (String part : parts) { - if (part.startsWith("Bandwidth=")) { - bandwidth = Long.parseLong(part.substring( - "Bandwidth=".length())); - } - } - } else if (line.startsWith("p ")) { - rawStatusEntry.append(line + "\n"); - ports = line.substring(2); - } - } - if (isConsensus) { - if (this.bsfh != null) { - for (String hashedRelayIdentity : hashedRelayIdentities) { - this.bsfh.addHashedRelay(hashedRelayIdentity); - } - } - if (this.rddi != null) { - this.rddi.addConsensus(validAfter, data); - if (relayIdentity != null) { - byte[] rawDescriptor = rawStatusEntry.toString().getBytes(); - this.rddi.addStatusEntry(validAfter, nickname, - relayIdentity, serverDesc, published, address, orPort, - dirPort, relayFlags, version, bandwidth, ports, - rawDescriptor); - } - } - } else { - if (this.rddi != null) { - this.rddi.addVote(validAfter, dirSource, data); - } - } - } else if (line.startsWith("router ")) { - String platformLine = null, bandwidthLine = null, - extraInfoDigest = null, relayIdentifier = null; - String[] parts = line.split(" "); - String nickname = parts[1]; - String address = parts[2]; - int orPort = Integer.parseInt(parts[3]); - int dirPort = Integer.parseInt(parts[4]); - long published = -1L, uptime = -1L; - while ((line = br.readLine()) != null) { - if (line.startsWith("platform ")) { - platformLine = line; - } else if (line.startsWith("published ")) { - String 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("bandwidth ")) { - bandwidthLine = line; - } 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("uptime ")) { - uptime = Long.parseLong(line.substring("uptime ".length())); - } - } - String ascii = new String(data, "US-ASCII"); - String startToken = "router "; - String sigToken = "\nrouter-signature\n"; - int start = ascii.indexOf(startToken); - int sig = ascii.indexOf(sigToken) + sigToken.length(); - String digest = null; - if (start >= 0 || sig >= 0 || sig > start) { - byte[] forDigest = new byte[sig - start]; - System.arraycopy(data, start, forDigest, 0, sig - start); - digest = DigestUtils.shaHex(forDigest); - } - if (this.rddi != null && digest != null) { - String[] bwParts = bandwidthLine.split(" "); - long bandwidthAvg = Long.parseLong(bwParts[1]); - long bandwidthBurst = Long.parseLong(bwParts[2]); - long bandwidthObserved = Long.parseLong(bwParts[3]); - String platform = platformLine.substring("platform ".length()); - this.rddi.addServerDescriptor(digest, nickname, address, orPort, - dirPort, relayIdentifier, bandwidthAvg, bandwidthBurst, - bandwidthObserved, platform, published, uptime, - extraInfoDigest, data); - } - } else if (line.startsWith("extra-info ")) { - String nickname = line.split(" ")[1]; - long published = -1L; - String dir = line.split(" ")[2]; - String statsEnd = null; - long seconds = -1L; - List<String> bandwidthHistory = new ArrayList<String>(); - while ((line = br.readLine()) != null) { - if (line.startsWith("published ")) { - String publishedTime = line.substring("published ".length()); - published = parseFormat.parse(publishedTime).getTime(); - } else if (line.startsWith("read-history ") || - line.startsWith("write-history ") || - line.startsWith("dirreq-read-history ") || - line.startsWith("dirreq-write-history ")) { - bandwidthHistory.add(line); - } else if (line.startsWith("dirreq-stats-end ")) { - String[] parts = line.split(" "); - if (parts.length < 5) { - this.logger.warning("Could not parse dirreq-stats-end " - + "line '" + line + "' in descriptor. Skipping."); - break; - } - statsEnd = parts[1] + " " + parts[2]; - seconds = Long.parseLong(parts[3].substring(1)); - } else if (line.startsWith("dirreq-v3-reqs ") - && line.length() > "dirreq-v3-reqs ".length()) { - if (this.rddi != null) { - try { - int allUsers = 0; - Map<String, String> obs = new HashMap<String, String>(); - String[] parts = line.substring("dirreq-v3-reqs ". - length()).split(","); - for (String p : parts) { - String country = p.substring(0, 2); - int users = Integer.parseInt(p.substring(3)) - 4; - allUsers += users; - obs.put(country, "" + users); - } - obs.put("zy", "" + allUsers); - this.rddi.addDirReqStats(dir, statsEnd, seconds, obs); - } catch (NumberFormatException e) { - this.logger.log(Level.WARNING, "Could not parse " - + "dirreq-v3-reqs line '" + line + "' in descriptor. " - + "Skipping.", e); - break; - } - } - } else if (line.startsWith("conn-bi-direct ")) { - if (this.rddi != null) { - String[] parts = line.split(" "); - if (parts.length == 6 && - parts[5].split(",").length == 4) { - try { - String connBiDirectStatsEnd = parts[1] + " " + parts[2]; - long connBiDirectSeconds = Long.parseLong(parts[3]. - substring(1)); - String[] parts2 = parts[5].split(","); - long below = Long.parseLong(parts2[0]); - long read = Long.parseLong(parts2[1]); - long write = Long.parseLong(parts2[2]); - long both = Long.parseLong(parts2[3]); - this.rddi.addConnBiDirect(dir, connBiDirectStatsEnd, - connBiDirectSeconds, below, read, write, both); - } catch (NumberFormatException e) { - this.logger.log(Level.WARNING, "Number format " - + "exception while parsing conn-bi-direct stats " - + "string '" + line + "'. Skipping.", e); - } - } else { - this.logger.warning("Skipping invalid conn-bi-direct " - + "stats string '" + line + "'."); - } - } - } - } - String ascii = new String(data, "US-ASCII"); - String startToken = "extra-info "; - String sigToken = "\nrouter-signature\n"; - String digest = null; - int start = ascii.indexOf(startToken); - int sig = ascii.indexOf(sigToken) + sigToken.length(); - if (start >= 0 || sig >= 0 || sig > start) { - byte[] forDigest = new byte[sig - start]; - System.arraycopy(data, start, forDigest, 0, sig - start); - digest = DigestUtils.shaHex(forDigest); - } - if (this.rddi != null && digest != null) { - this.rddi.addExtraInfoDescriptor(digest, nickname, - dir.toLowerCase(), published, data, bandwidthHistory); - } + String ascii = new String(descriptor.getRawDescriptorBytes(), + "US-ASCII"); + String startToken = "extra-info "; + String sigToken = "\nrouter-signature\n"; + int start = ascii.indexOf(startToken); + int sig = ascii.indexOf(sigToken) + sigToken.length(); + if (start >= 0 || sig >= 0 || sig > start) { + byte[] forDigest = new byte[sig - start]; + System.arraycopy(descriptor.getRawDescriptorBytes(), start, + forDigest, 0, sig - start); + digest = DigestUtils.shaHex(forDigest); } - } catch (IOException e) { - this.logger.log(Level.WARNING, "Could not parse descriptor. " - + "Skipping.", e); - } catch (ParseException e) { - this.logger.log(Level.WARNING, "Could not parse descriptor. " - + "Skipping.", e); + } catch (UnsupportedEncodingException e) { + } + if (digest != null) { + this.rddi.addExtraInfoDescriptor(digest, descriptor.getNickname(), + descriptor.getFingerprint().toLowerCase(), + descriptor.getPublishedMillis(), + descriptor.getRawDescriptorBytes(), bandwidthHistoryLines); } } } diff --git a/src/org/torproject/ernie/cron/Configuration.java b/src/org/torproject/ernie/cron/Configuration.java index 0a493cb..1f30eb9 100644 --- a/src/org/torproject/ernie/cron/Configuration.java +++ b/src/org/torproject/ernie/cron/Configuration.java @@ -17,7 +17,7 @@ import java.util.logging.Logger; */ public class Configuration { private boolean importDirectoryArchives = false; - private String directoryArchivesDirectory = "archives/"; + private String directoryArchivesDirectory = "in/relay-descriptors/"; private boolean keepDirectoryArchiveImportHistory = false; private boolean importSanitizedBridges = false; private String sanitizedBridgesDirectory = "bridges/"; diff --git a/src/org/torproject/ernie/cron/RelayDescriptorDatabaseImporter.java b/src/org/torproject/ernie/cron/RelayDescriptorDatabaseImporter.java index 35ba90e..3ee7b6b 100644 --- a/src/org/torproject/ernie/cron/RelayDescriptorDatabaseImporter.java +++ b/src/org/torproject/ernie/cron/RelayDescriptorDatabaseImporter.java @@ -1017,21 +1017,14 @@ public final class RelayDescriptorDatabaseImporter { /** * Insert a conn-bi-direct stats string into the database. */ - public void addConnBiDirect(String source, String statsEnd, + public void addConnBiDirect(String source, long statsEndMillis, long seconds, long below, long read, long write, long both) { - long statsEndTime = 0L; - try { - statsEndTime = this.dateTimeFormat.parse(statsEnd).getTime(); - } catch (ParseException e) { - this.logger.log(Level.WARNING, "Could not add conn-bi-direct " - + "stats string with interval ending '" + statsEnd + "'.", e); - return; - } + String statsEnd = this.dateTimeFormat.format(statsEndMillis); if (this.importIntoDatabase) { try { - this.addDateToScheduledUpdates(statsEndTime); + this.addDateToScheduledUpdates(statsEndMillis); Calendar cal = Calendar.getInstance(TimeZone.getTimeZone("UTC")); - Timestamp statsEndTimestamp = new Timestamp(statsEndTime); + Timestamp statsEndTimestamp = new Timestamp(statsEndMillis); this.psBs.setString(1, source); this.psBs.setTimestamp(2, statsEndTimestamp, cal); ResultSet rs = psBs.executeQuery(); @@ -1085,21 +1078,14 @@ public final class RelayDescriptorDatabaseImporter { * Adds observations on the number of directory requests by country as * seen on a directory at a given date to the database. */ - public void addDirReqStats(String source, String statsEnd, long seconds, - Map<String, String> dirReqsPerCountry) { - long statsEndTime = 0L; - try { - statsEndTime = this.dateTimeFormat.parse(statsEnd).getTime(); - } catch (ParseException e) { - this.logger.log(Level.WARNING, "Could not add dirreq stats with " - + "interval ending '" + statsEnd + "'.", e); - return; - } + public void addDirReqStats(String source, long statsEndMillis, + long seconds, Map<String, String> dirReqsPerCountry) { + String statsEnd = this.dateTimeFormat.format(statsEndMillis); if (this.importIntoDatabase) { try { - this.addDateToScheduledUpdates(statsEndTime); + this.addDateToScheduledUpdates(statsEndMillis); Calendar cal = Calendar.getInstance(TimeZone.getTimeZone("UTC")); - Timestamp statsEndTimestamp = new Timestamp(statsEndTime); + Timestamp statsEndTimestamp = new Timestamp(statsEndMillis); this.psQs.setString(1, source); this.psQs.setTimestamp(2, statsEndTimestamp, cal); ResultSet rs = psQs.executeQuery();

1 0

[metrics-web/master] Clean up ArchiveReader a bit.
by karsten＠torproject.org 22 Mar '12

22 Mar '12

commit bfa21af59bdae4ee9c924792e6606a7829d0941c Author: Karsten Loesing <karsten.loesing(a)gmx.net> Date: Wed Mar 21 16:23:37 2012 +0100 Clean up ArchiveReader a bit. --- src/org/torproject/ernie/cron/ArchiveReader.java | 10 +--------- 1 files changed, 1 insertions(+), 9 deletions(-) diff --git a/src/org/torproject/ernie/cron/ArchiveReader.java b/src/org/torproject/ernie/cron/ArchiveReader.java index 4befe51..e4f6b2a 100644 --- a/src/org/torproject/ernie/cron/ArchiveReader.java +++ b/src/org/torproject/ernie/cron/ArchiveReader.java @@ -48,8 +48,6 @@ public class ArchiveReader { */ private Logger logger; - private SimpleDateFormat dateTimeFormat; - public ArchiveReader(RelayDescriptorDatabaseImporter rddi, BridgeStatsFileHandler bsfh, File archivesDirectory, File statsDirectory, boolean keepImportHistory) { @@ -62,10 +60,6 @@ public class ArchiveReader { this.rddi = rddi; this.bsfh = bsfh; - this.dateTimeFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); - this.dateTimeFormat.setTimeZone(TimeZone.getTimeZone("UTC")); - - int parsedFiles = 0, ignoredFiles = 0; this.logger = Logger.getLogger(ArchiveReader.class.getName()); if (archivesDirectory.exists()) { logger.fine("Importing files in directory " + archivesDirectory @@ -99,9 +93,7 @@ public class ArchiveReader { } } - logger.info("Finished importing relay descriptors from local " - + "directory:\nParsed " + parsedFiles + ", ignored " - + ignoredFiles + " files."); + logger.info("Finished importing relay descriptors."); } private void addRelayNetworkStatusConsensus(

1 0

[metrics-web/master] Use metrics-lib for parsing bridge descriptors, too.
by karsten＠torproject.org 22 Mar '12

22 Mar '12

commit 333a9c497b8558d584af7e27d953f50ad800aa11 Author: Karsten Loesing <karsten.loesing(a)gmx.net> Date: Wed Mar 21 16:24:23 2012 +0100 Use metrics-lib for parsing bridge descriptors, too. --- .../ernie/cron/BridgeStatsFileHandler.java | 27 ++- .../ernie/cron/ConsensusStatsFileHandler.java | 8 +- .../ernie/cron/SanitizedBridgesReader.java | 299 ++++++-------------- 3 files changed, 111 insertions(+), 223 deletions(-) diff --git a/src/org/torproject/ernie/cron/BridgeStatsFileHandler.java b/src/org/torproject/ernie/cron/BridgeStatsFileHandler.java index 6e7f4eb..aba7804 100644 --- a/src/org/torproject/ernie/cron/BridgeStatsFileHandler.java +++ b/src/org/torproject/ernie/cron/BridgeStatsFileHandler.java @@ -14,12 +14,15 @@ import java.sql.PreparedStatement; import java.sql.ResultSet; import java.sql.SQLException; import java.sql.Statement; +import java.text.ParseException; +import java.text.SimpleDateFormat; import java.util.ArrayList; import java.util.HashMap; import java.util.List; import java.util.Map; import java.util.SortedMap; import java.util.SortedSet; +import java.util.TimeZone; import java.util.TreeMap; import java.util.TreeSet; import java.util.logging.Level; @@ -95,6 +98,8 @@ public class BridgeStatsFileHandler { /* Database connection string. */ private String connectionURL = null; + private SimpleDateFormat dateTimeFormat; + /** * Initializes this class, including reading in intermediate results * files <code>stats/bridge-stats-raw</code> and @@ -122,6 +127,9 @@ public class BridgeStatsFileHandler { /* Initialize database connection string. */ this.connectionURL = connectionURL; + this.dateTimeFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); + this.dateTimeFormat.setTimeZone(TimeZone.getTimeZone("UTC")); + /* Initialize logger. */ this.logger = Logger.getLogger( BridgeStatsFileHandler.class.getName()); @@ -175,7 +183,9 @@ public class BridgeStatsFileHandler { obs.put(headers[i], parts[i]); } } - this.addObs(hashedBridgeIdentity, date, time, obs); + long dateTimeMillis = dateTimeFormat.parse(date + " " + + time).getTime(); + this.addObs(hashedBridgeIdentity, dateTimeMillis, obs); } } } @@ -185,6 +195,9 @@ public class BridgeStatsFileHandler { } catch (IOException e) { this.logger.log(Level.WARNING, "Failed to read file " + this.bridgeStatsRawFile.getAbsolutePath() + "!", e); + } catch (ParseException e) { + this.logger.log(Level.WARNING, "Failed to read file " + + this.bridgeStatsRawFile.getAbsolutePath() + "!", e); } } @@ -253,9 +266,10 @@ public class BridgeStatsFileHandler { * not included in the results, because stats are very likely broken. */ public void addZeroTwoTwoDescriptor(String hashedBridgeIdentity, - String date, String time) { - String value = hashedBridgeIdentity.toUpperCase() + "," + date + "," - + time; + long publishedMillis) { + String value = hashedBridgeIdentity.toUpperCase() + "," + + this.dateTimeFormat.format(publishedMillis). + replaceAll(" ", ","); if (!this.zeroTwoTwoDescriptors.contains(value)) { this.logger.finer("Adding new bridge 0.2.2.x extra-info " + "descriptor: " + value); @@ -281,11 +295,14 @@ public class BridgeStatsFileHandler { * bridge and day, we keep the one with the later publication time and * discard the other one. */ - public void addObs(String hashedIdentity, String date, String time, + public void addObs(String hashedIdentity, long publishedMillis, Map<String, String> obs) { for (String country : obs.keySet()) { this.countries.add(country); } + String dateTime = this.dateTimeFormat.format(publishedMillis); + String date = dateTime.split(" ")[0]; + String time = dateTime.split(" ")[1]; String shortKey = hashedIdentity + "," + date; String longKey = shortKey + "," + time; SortedMap<String, Map<String, String>> tailMap = diff --git a/src/org/torproject/ernie/cron/ConsensusStatsFileHandler.java b/src/org/torproject/ernie/cron/ConsensusStatsFileHandler.java index 6c83b05..fccb29b 100644 --- a/src/org/torproject/ernie/cron/ConsensusStatsFileHandler.java +++ b/src/org/torproject/ernie/cron/ConsensusStatsFileHandler.java @@ -66,6 +66,8 @@ public class ConsensusStatsFileHandler { /* Database connection string. */ private String connectionURL = null; + private SimpleDateFormat dateTimeFormat; + /** * Initializes this class, including reading in intermediate results * files <code>stats/consensus-stats-raw</code> and @@ -86,6 +88,9 @@ public class ConsensusStatsFileHandler { /* Initialize database connection string. */ this.connectionURL = connectionURL; + this.dateTimeFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); + this.dateTimeFormat.setTimeZone(TimeZone.getTimeZone("UTC")); + /* Initialize logger. */ this.logger = Logger.getLogger( ConsensusStatsFileHandler.class.getName()); @@ -128,7 +133,8 @@ public class ConsensusStatsFileHandler { * Adds the intermediate results of the number of running bridges in a * given bridge status to the existing observations. */ - public void addBridgeConsensusResults(String published, int running) { + public void addBridgeConsensusResults(long publishedMillis, int running) { + String published = dateTimeFormat.format(publishedMillis); String line = published + "," + running; if (!this.bridgesRaw.containsKey(published)) { this.logger.finer("Adding new bridge numbers: " + line); diff --git a/src/org/torproject/ernie/cron/SanitizedBridgesReader.java b/src/org/torproject/ernie/cron/SanitizedBridgesReader.java index 78bd7db..c7199cd 100644 --- a/src/org/torproject/ernie/cron/SanitizedBridgesReader.java +++ b/src/org/torproject/ernie/cron/SanitizedBridgesReader.java @@ -2,30 +2,20 @@ * See LICENSE for licensing information */ package org.torproject.ernie.cron; -import java.io.BufferedInputStream; -import java.io.BufferedReader; -import java.io.BufferedWriter; -import java.io.ByteArrayOutputStream; import java.io.File; -import java.io.FileInputStream; -import java.io.FileReader; -import java.io.FileWriter; -import java.io.IOException; -import java.io.StringReader; -import java.text.ParseException; -import java.text.SimpleDateFormat; -import java.util.ArrayList; import java.util.HashMap; -import java.util.List; +import java.util.Iterator; import java.util.Map; -import java.util.SortedSet; -import java.util.Stack; -import java.util.TimeZone; -import java.util.TreeSet; -import java.util.logging.Level; import java.util.logging.Logger; -import org.apache.commons.codec.digest.DigestUtils; +import org.torproject.descriptor.BridgeNetworkStatus; +import org.torproject.descriptor.Descriptor; +import org.torproject.descriptor.DescriptorFile; +import org.torproject.descriptor.DescriptorReader; +import org.torproject.descriptor.DescriptorSourceFactory; +import org.torproject.descriptor.ExtraInfoDescriptor; +import org.torproject.descriptor.NetworkStatusEntry; +import org.torproject.descriptor.ServerDescriptor; public class SanitizedBridgesReader { private ConsensusStatsFileHandler csfh; @@ -45,217 +35,92 @@ public class SanitizedBridgesReader { this.logger = Logger.getLogger(SanitizedBridgesReader.class.getName()); - SortedSet<String> bridgesImportHistory = new TreeSet<String>(); - File bridgesImportHistoryFile = - new File(statsDirectory, "bridges-import-history"); - if (keepImportHistory && bridgesImportHistoryFile.exists()) { - try { - BufferedReader br = new BufferedReader(new FileReader( - bridgesImportHistoryFile)); - String line = null; - while ((line = br.readLine()) != null) { - bridgesImportHistory.add(line); - } - br.close(); - } catch (IOException e) { - logger.log(Level.WARNING, "Could not read in bridge descriptor " - + "import history file. Skipping."); - } - } if (bridgesDir.exists()) { logger.fine("Importing files in directory " + bridgesDir + "/..."); - Stack<File> filesInInputDir = new Stack<File>(); - filesInInputDir.add(bridgesDir); - List<File> problems = new ArrayList<File>(); - while (!filesInInputDir.isEmpty()) { - File pop = filesInInputDir.pop(); - if (pop.isDirectory()) { - for (File f : pop.listFiles()) { - filesInInputDir.add(f); - } - continue; - } else if (keepImportHistory && bridgesImportHistory.contains( - pop.getName())) { - continue; - } else { - try { - BufferedInputStream bis = new BufferedInputStream( - new FileInputStream(pop)); - ByteArrayOutputStream baos = new ByteArrayOutputStream(); - int len; - byte[] data = new byte[1024]; - while ((len = bis.read(data, 0, 1024)) >= 0) { - baos.write(data, 0, len); - } - bis.close(); - byte[] allData = baos.toByteArray(); - String fn = pop.getName(); - // TODO dateTime extraction doesn't work for sanitized network - // statuses! - String dateTime = fn.substring(0, 4) + "-" + fn.substring(4, 6) - + "-" + fn.substring(6, 8) + " " + fn.substring(9, 11) - + ":" + fn.substring(11, 13) + ":" + fn.substring(13, 15); - this.parse(allData, dateTime, true); - if (keepImportHistory) { - bridgesImportHistory.add(pop.getName()); - } - } catch (IOException e) { - problems.add(pop); - if (problems.size() > 3) { - break; - } - } - } + DescriptorReader reader = + DescriptorSourceFactory.createDescriptorReader(); + reader.addDirectory(bridgesDir); + if (keepImportHistory) { + reader.setExcludeFiles(new File(statsDirectory, + "bridge-descriptor-history")); } - if (problems.isEmpty()) { - logger.fine("Finished importing files in directory " + bridgesDir - + "/."); - } else { - StringBuilder sb = new StringBuilder("Failed importing files in " - + "directory " + bridgesDir + "/:"); - int printed = 0; - for (File f : problems) { - sb.append("\n " + f.getAbsolutePath()); - if (++printed >= 3) { - sb.append("\n ... more"); - break; + Iterator<DescriptorFile> descriptorFiles = reader.readDescriptors(); + while (descriptorFiles.hasNext()) { + DescriptorFile descriptorFile = descriptorFiles.next(); + if (descriptorFile.getDescriptors() != null) { + for (Descriptor descriptor : descriptorFile.getDescriptors()) { + if (descriptor instanceof BridgeNetworkStatus) { + this.addBridgeNetworkStatus( + (BridgeNetworkStatus) descriptor); + } else if (descriptor instanceof ServerDescriptor) { + this.addServerDescriptor((ServerDescriptor) descriptor); + } else if (descriptor instanceof ExtraInfoDescriptor) { + this.addExtraInfoDescriptor( + (ExtraInfoDescriptor) descriptor); + } } } - logger.warning(sb.toString()); } - if (keepImportHistory) { - try { - bridgesImportHistoryFile.getParentFile().mkdirs(); - BufferedWriter bw = new BufferedWriter(new FileWriter( - bridgesImportHistoryFile)); - for (String line : bridgesImportHistory) { - bw.write(line + "\n"); - } - bw.close(); - } catch (IOException e) { - logger.log(Level.WARNING, "Could not write bridge descriptor " - + "import history file."); - } + logger.info("Finished importing bridge descriptors."); + } + } + + private void addBridgeNetworkStatus(BridgeNetworkStatus status) { + int runningBridges = 0; + for (NetworkStatusEntry statusEntry : + status.getStatusEntries().values()) { + if (statusEntry.getFlags().contains("Running")) { + runningBridges++; } } + this.csfh.addBridgeConsensusResults(status.getPublishedMillis(), + runningBridges); } - private void parse(byte[] allData, String dateTime, boolean sanitized) { - try { - BufferedReader br = new BufferedReader(new StringReader( - new String(allData, "US-ASCII"))); - SimpleDateFormat timeFormat = new SimpleDateFormat( - "yyyy-MM-dd HH:mm:ss"); - timeFormat.setTimeZone(TimeZone.getTimeZone("UTC")); - String hashedIdentity = null, platformLine = null, - publishedLine = null, geoipStartTimeLine = null, - bridgeStatsEndLine = null; - boolean skip = false; - String line = null; - while ((line = br.readLine()) != null) { - if (line.startsWith("r ")) { - int runningBridges = 0; - while ((line = br.readLine()) != null) { - if (line.startsWith("s ") && line.contains(" Running")) { - runningBridges++; - } - } - if (this.csfh != null) { - this.csfh.addBridgeConsensusResults(dateTime, runningBridges); - } - } else if (line.startsWith("router ")) { - } else if (line.startsWith("extra-info ")) { - hashedIdentity = sanitized ? line.split(" ")[2] - : DigestUtils.shaHex(line.split(" ")[2]).toUpperCase(); - if (this.bsfh != null) { - skip = this.bsfh.isKnownRelay(hashedIdentity); - } - } else if (!skip && line.startsWith("platform ")) { - platformLine = line; - } else if (!skip && line.startsWith("published ")) { - publishedLine = line; - } else if (line.startsWith("opt fingerprint") || - line.startsWith("fingerprint")) { - String identity = line.substring(line.startsWith("opt ") ? - "opt fingerprint".length() : "fingerprint".length()). - replaceAll(" ", "").toLowerCase(); - hashedIdentity = sanitized ? identity - : DigestUtils.shaHex(identity).toUpperCase(); - } else if (!skip && line.startsWith("geoip-start-time ")) { - geoipStartTimeLine = line; - } else if (!skip && line.startsWith("geoip-client-origins") - && line.split(" ").length > 1) { - if (publishedLine == null || - geoipStartTimeLine == null) { - this.logger.warning("Either published line or " - + "geoip-start-time line is not present in " - + (sanitized ? "sanitized" : "non-sanitized") - + " bridge descriptors from " + dateTime + "."); - break; - } - long published = timeFormat.parse(publishedLine. - substring("published ".length())).getTime(); - long started = timeFormat.parse(geoipStartTimeLine. - substring("geoip-start-time ".length())).getTime(); - long seconds = (published - started) / 1000L; - double allUsers = 0.0D; - Map<String, String> obs = new HashMap<String, String>(); - String[] parts = line.split(" ")[1].split(","); - for (String p : parts) { - String country = p.substring(0, 2); - double users = ((double) Long.parseLong(p.substring(3)) - 4L) - * 86400.0D / ((double) seconds); - allUsers += users; - obs.put(country, String.format("%.2f", users)); - } - obs.put("zy", String.format("%.2f", allUsers)); - String date = publishedLine.split(" ")[1]; - String time = publishedLine.split(" ")[2]; - if (this.bsfh != null) { - this.bsfh.addObs(hashedIdentity, date, time, obs); - } - } else if (!skip && line.startsWith("bridge-stats-end ")) { - bridgeStatsEndLine = line; - } else if (!skip && line.startsWith("bridge-ips") - && line.split(" ").length > 1) { - if (bridgeStatsEndLine == null) { - this.logger.warning("bridge-ips line without preceding " - + "bridge-stats-end line in " - + (sanitized ? "sanitized" : "non-sanitized") - + " bridge descriptor."); - break; - } - double allUsers = 0.0D; - Map<String, String> obs = new HashMap<String, String>(); - String[] parts = line.split(" ")[1].split(","); - for (String p : parts) { - String country = p.substring(0, 2); - double users = (double) Long.parseLong(p.substring(3)) - 4L; - allUsers += users; - obs.put(country, String.format("%.2f", users)); - } - obs.put("zy", String.format("%.2f", allUsers)); - String date = bridgeStatsEndLine.split(" ")[1]; - String time = bridgeStatsEndLine.split(" ")[2]; - if (this.bsfh != null) { - this.bsfh.addObs(hashedIdentity, date, time, obs); - } + private void addServerDescriptor(ServerDescriptor descriptor) { + if (descriptor.getPlatform() != null && + descriptor.getPlatform().startsWith("Tor 0.2.2")) { + this.bsfh.addZeroTwoTwoDescriptor(descriptor.getFingerprint(), + descriptor.getPublishedMillis()); + } + } + + private void addExtraInfoDescriptor(ExtraInfoDescriptor descriptor) { + if (!this.bsfh.isKnownRelay(descriptor.getFingerprint())) { + if (descriptor.getGeoipStartTimeMillis() >= 0 && + descriptor.getGeoipClientOrigins() != null) { + long seconds = (descriptor.getPublishedMillis() + - descriptor.getGeoipStartTimeMillis()) / 1000L; + double allUsers = 0.0D; + Map<String, String> obs = new HashMap<String, String>(); + for (Map.Entry<String, Integer> e : + descriptor.getGeoipClientOrigins().entrySet()) { + String country = e.getKey(); + double users = ((double) e.getValue() - 4) * 86400.0D + / ((double) seconds); + allUsers += users; + obs.put(country, String.format("%.2f", users)); } + obs.put("zy", String.format("%.2f", allUsers)); + this.bsfh.addObs(descriptor.getFingerprint(), + descriptor.getPublishedMillis(), obs); } - if (this.bsfh != null && platformLine != null && - platformLine.startsWith("platform Tor 0.2.2")) { - String date = publishedLine.split(" ")[1]; - String time = publishedLine.split(" ")[2]; - this.bsfh.addZeroTwoTwoDescriptor(hashedIdentity, date, time); + if (descriptor.getBridgeStatsEndMillis() >= 0 && + descriptor.getBridgeIps() != null) { + double allUsers = 0.0D; + Map<String, String> obs = new HashMap<String, String>(); + for (Map.Entry<String, Integer> e : + descriptor.getBridgeIps().entrySet()) { + String country = e.getKey(); + double users = (double) e.getValue() - 4; + allUsers += users; + obs.put(country, String.format("%.2f", users)); + } + obs.put("zy", String.format("%.2f", allUsers)); + this.bsfh.addObs(descriptor.getFingerprint(), + descriptor.getBridgeStatsEndMillis(), obs); } - } catch (IOException e) { - this.logger.log(Level.WARNING, "Could not parse bridge descriptor.", - e); - return; - } catch (ParseException e) { - this.logger.log(Level.WARNING, "Could not parse bridge descriptor.", - e); - return; + } } }

1 0

[metrics-web/master] Change default location of sanitized bridges.
by karsten＠torproject.org 22 Mar '12

22 Mar '12

commit ec61104d8e950bb759a9318f76a6a6afd5ef5fe3 Author: Karsten Loesing <karsten.loesing(a)gmx.net> Date: Thu Mar 22 11:40:22 2012 +0100 Change default location of sanitized bridges. --- config.template | 2 +- src/org/torproject/ernie/cron/Configuration.java | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/config.template b/config.template index ce2dc94..9760b56 100644 --- a/config.template +++ b/config.template @@ -14,7 +14,7 @@ #ImportSanitizedBridges 0 # ## Relative path to directory to import sanitized bridges from -#SanitizedBridgesDirectory bridges/ +#SanitizedBridgesDirectory in/bridge-descriptors/ # ## Keep a history of imported sanitized bridge descriptors. This history ## can be useful when importing from a changing data source to avoid diff --git a/src/org/torproject/ernie/cron/Configuration.java b/src/org/torproject/ernie/cron/Configuration.java index 1f30eb9..82a004b 100644 --- a/src/org/torproject/ernie/cron/Configuration.java +++ b/src/org/torproject/ernie/cron/Configuration.java @@ -20,7 +20,7 @@ public class Configuration { private String directoryArchivesDirectory = "in/relay-descriptors/"; private boolean keepDirectoryArchiveImportHistory = false; private boolean importSanitizedBridges = false; - private String sanitizedBridgesDirectory = "bridges/"; + private String sanitizedBridgesDirectory = "in/bridge-descriptors/"; private boolean keepSanitizedBridgesImportHistory = false; private boolean writeRelayDescriptorDatabase = false; private String relayDescriptorDatabaseJdbc =

1 0

[metrics-web/master] Remove relay descriptor parser.
by karsten＠torproject.org 22 Mar '12

22 Mar '12

commit a2b00950c8b4991e20e3026c04f8b5b49ce530d3 Author: Karsten Loesing <karsten.loesing(a)gmx.net> Date: Wed Mar 21 12:20:01 2012 +0100 Remove relay descriptor parser. The purpose of this commit is to prepare adding metrics-lib as library for descriptor parsing. --- src/org/torproject/ernie/cron/ArchiveReader.java | 367 ++++++++++++++++++- src/org/torproject/ernie/cron/Main.java | 9 +- .../ernie/cron/RelayDescriptorParser.java | 387 -------------------- 3 files changed, 365 insertions(+), 398 deletions(-) diff --git a/src/org/torproject/ernie/cron/ArchiveReader.java b/src/org/torproject/ernie/cron/ArchiveReader.java index 20a0905..ed1e505 100644 --- a/src/org/torproject/ernie/cron/ArchiveReader.java +++ b/src/org/torproject/ernie/cron/ArchiveReader.java @@ -11,30 +11,67 @@ import java.io.FileInputStream; import java.io.FileReader; import java.io.FileWriter; import java.io.IOException; +import java.io.StringReader; +import java.text.ParseException; +import java.text.SimpleDateFormat; import java.util.ArrayList; +import java.util.HashMap; import java.util.List; import java.util.Map; import java.util.SortedMap; +import java.util.SortedSet; import java.util.Stack; +import java.util.TimeZone; import java.util.TreeMap; +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; + /** * Read in all files in a given directory and pass buffered readers of * them to the relay descriptor parser. */ public class ArchiveReader { - public ArchiveReader(RelayDescriptorParser rdp, File archivesDirectory, + + /** + * Stats file handler that accepts parse results for bridge statistics. + */ + private BridgeStatsFileHandler bsfh; + + /** + * Relay descriptor database importer that stores relay descriptor + * contents for later evaluation. + */ + private RelayDescriptorDatabaseImporter rddi; + + /** + * Logger for this class. + */ + private Logger logger; + + private SimpleDateFormat dateTimeFormat; + + public ArchiveReader(RelayDescriptorDatabaseImporter rddi, + BridgeStatsFileHandler bsfh, File archivesDirectory, File statsDirectory, boolean keepImportHistory) { - if (rdp == null || archivesDirectory == null || + if (archivesDirectory == null || statsDirectory == null) { throw new IllegalArgumentException(); } + this.rddi = rddi; + this.bsfh = bsfh; + + this.dateTimeFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); + this.dateTimeFormat.setTimeZone(TimeZone.getTimeZone("UTC")); + int parsedFiles = 0, ignoredFiles = 0; - Logger logger = Logger.getLogger(ArchiveReader.class.getName()); + this.logger = Logger.getLogger(ArchiveReader.class.getName()); SortedMap<String, Long> lastArchivesImportHistory = new TreeMap<String, Long>(), newArchivesImportHistory = new TreeMap<String, Long>(); @@ -101,7 +138,7 @@ public class ArchiveReader { } bis.close(); byte[] allData = baos.toByteArray(); - rdp.parse(allData); + this.parse(allData); parsedFiles++; } catch (IOException e) { problems.add(pop); @@ -148,5 +185,327 @@ public class ArchiveReader { + "directory:\nParsed " + parsedFiles + ", ignored " + ignoredFiles + " files."); } + + public void parse(byte[] data) { + try { + /* Remove any @ lines at the beginning of the file and parse the + * first non-@ line to find out the descriptor type. */ + BufferedReader br = new BufferedReader(new StringReader(new String( + data, "US-ASCII"))); + String line = br.readLine(); + while (line != null && line.startsWith("@")) { + line = br.readLine(); + } + if (line == null) { + this.logger.fine("We were given a file that doesn't contain a " + + "single descriptor for parsing. Ignoring."); + return; + } + br.close(); + + /* Split the byte[] possibly containing multiple descriptors into + * byte[]'s with one descriptor each and parse them. */ + String startToken = null; + if (line.equals("network-status-version 3")) { + startToken = "network-status-version 3"; + } else if (line.startsWith("router ")) { + startToken = "router "; + } else if (line.startsWith("extra-info ")) { + startToken = "extra-info "; + } else if (line.equals("dir-key-certificate-version 3")) { + this.logger.fine("Not parsing dir key certificate."); + return; + } else { + this.logger.warning("Unknown descriptor type. First line is '" + + line + "'. Ignoring."); + return; + } + String splitToken = "\n" + startToken; + String ascii = new String(data, "US-ASCII"); + int length = data.length, start = ascii.indexOf(startToken); + while (start < length) { + int end = ascii.indexOf(splitToken, start); + if (end < 0) { + end = length; + } else { + end += 1; + } + byte[] descBytes = new byte[end - start]; + System.arraycopy(data, start, descBytes, 0, end - start); + parseSingleDescriptor(descBytes); + start = end; + } + } catch (IOException e) { + this.logger.log(Level.WARNING, "Could not parse descriptor. " + + "Skipping.", e); + } + } + + private void parseSingleDescriptor(byte[] data) { + try { + /* Convert descriptor to ASCII for parsing. This means we'll lose + * the non-ASCII chars, but we don't care about them for parsing + * anyway. */ + BufferedReader br = new BufferedReader(new StringReader(new String( + data, "US-ASCII"))); + String line = br.readLine(); + SimpleDateFormat parseFormat = + new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); + parseFormat.setTimeZone(TimeZone.getTimeZone("UTC")); + if (line.equals("network-status-version 3")) { + // TODO when parsing the current consensus, check the fresh-until + // time to see when we switch from hourly to half-hourly + // consensuses + boolean isConsensus = true; + String validAfterTime = null, nickname = null, + relayIdentity = null, serverDesc = null, version = null, + ports = null; + String dirSource = null, address = null; + long validAfter = -1L, published = -1L, bandwidth = -1L, + orPort = 0L, dirPort = 0L; + SortedSet<String> relayFlags = null; + StringBuilder rawStatusEntry = null; + SortedSet<String> hashedRelayIdentities = new TreeSet<String>(); + while ((line = br.readLine()) != null) { + if (line.equals("vote-status vote")) { + isConsensus = false; + } else if (line.startsWith("valid-after ")) { + validAfterTime = line.substring("valid-after ".length()); + validAfter = parseFormat.parse(validAfterTime).getTime(); + } else if (line.startsWith("dir-source ")) { + dirSource = line.split(" ")[2]; + } else if (line.startsWith("r ")) { + if (isConsensus && relayIdentity != null && + this.rddi != null) { + byte[] rawDescriptor = rawStatusEntry.toString().getBytes(); + this.rddi.addStatusEntry(validAfter, nickname, + relayIdentity, serverDesc, published, address, orPort, + dirPort, relayFlags, version, bandwidth, ports, + rawDescriptor); + relayFlags = null; + version = null; + bandwidth = -1L; + ports = null; + } + rawStatusEntry = new StringBuilder(line + "\n"); + String[] parts = line.split(" "); + if (parts.length < 9) { + this.logger.log(Level.WARNING, "Could not parse r line '" + + line + "' in descriptor. Skipping."); + break; + } + nickname = parts[1]; + relayIdentity = Hex.encodeHexString( + Base64.decodeBase64(parts[2] + "=")). + toLowerCase(); + hashedRelayIdentities.add(DigestUtils.shaHex( + Base64.decodeBase64(parts[2] + "=")). + toUpperCase()); + serverDesc = Hex.encodeHexString(Base64.decodeBase64( + parts[3] + "=")).toLowerCase(); + published = parseFormat.parse(parts[4] + " " + parts[5]). + getTime(); + address = parts[6]; + orPort = Long.parseLong(parts[7]); + dirPort = Long.parseLong(parts[8]); + } else if (line.startsWith("s ") || line.equals("s")) { + rawStatusEntry.append(line + "\n"); + relayFlags = new TreeSet<String>(); + if (line.length() > 2) { + for (String flag : line.substring(2).split(" ")) { + relayFlags.add(flag); + } + } + } else if (line.startsWith("v ")) { + rawStatusEntry.append(line + "\n"); + version = line.substring(2); + } else if (line.startsWith("w ")) { + rawStatusEntry.append(line + "\n"); + String[] parts = line.split(" "); + for (String part : parts) { + if (part.startsWith("Bandwidth=")) { + bandwidth = Long.parseLong(part.substring( + "Bandwidth=".length())); + } + } + } else if (line.startsWith("p ")) { + rawStatusEntry.append(line + "\n"); + ports = line.substring(2); + } + } + if (isConsensus) { + if (this.bsfh != null) { + for (String hashedRelayIdentity : hashedRelayIdentities) { + this.bsfh.addHashedRelay(hashedRelayIdentity); + } + } + if (this.rddi != null) { + this.rddi.addConsensus(validAfter, data); + if (relayIdentity != null) { + byte[] rawDescriptor = rawStatusEntry.toString().getBytes(); + this.rddi.addStatusEntry(validAfter, nickname, + relayIdentity, serverDesc, published, address, orPort, + dirPort, relayFlags, version, bandwidth, ports, + rawDescriptor); + } + } + } else { + if (this.rddi != null) { + this.rddi.addVote(validAfter, dirSource, data); + } + } + } else if (line.startsWith("router ")) { + String platformLine = null, bandwidthLine = null, + extraInfoDigest = null, relayIdentifier = null; + String[] parts = line.split(" "); + String nickname = parts[1]; + String address = parts[2]; + int orPort = Integer.parseInt(parts[3]); + int dirPort = Integer.parseInt(parts[4]); + long published = -1L, uptime = -1L; + while ((line = br.readLine()) != null) { + if (line.startsWith("platform ")) { + platformLine = line; + } else if (line.startsWith("published ")) { + String 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("bandwidth ")) { + bandwidthLine = line; + } 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("uptime ")) { + uptime = Long.parseLong(line.substring("uptime ".length())); + } + } + String ascii = new String(data, "US-ASCII"); + String startToken = "router "; + String sigToken = "\nrouter-signature\n"; + int start = ascii.indexOf(startToken); + int sig = ascii.indexOf(sigToken) + sigToken.length(); + String digest = null; + if (start >= 0 || sig >= 0 || sig > start) { + byte[] forDigest = new byte[sig - start]; + System.arraycopy(data, start, forDigest, 0, sig - start); + digest = DigestUtils.shaHex(forDigest); + } + if (this.rddi != null && digest != null) { + String[] bwParts = bandwidthLine.split(" "); + long bandwidthAvg = Long.parseLong(bwParts[1]); + long bandwidthBurst = Long.parseLong(bwParts[2]); + long bandwidthObserved = Long.parseLong(bwParts[3]); + String platform = platformLine.substring("platform ".length()); + this.rddi.addServerDescriptor(digest, nickname, address, orPort, + dirPort, relayIdentifier, bandwidthAvg, bandwidthBurst, + bandwidthObserved, platform, published, uptime, + extraInfoDigest, data); + } + } else if (line.startsWith("extra-info ")) { + String nickname = line.split(" ")[1]; + long published = -1L; + String dir = line.split(" ")[2]; + String statsEnd = null; + long seconds = -1L; + List<String> bandwidthHistory = new ArrayList<String>(); + while ((line = br.readLine()) != null) { + if (line.startsWith("published ")) { + String publishedTime = line.substring("published ".length()); + published = parseFormat.parse(publishedTime).getTime(); + } else if (line.startsWith("read-history ") || + line.startsWith("write-history ") || + line.startsWith("dirreq-read-history ") || + line.startsWith("dirreq-write-history ")) { + bandwidthHistory.add(line); + } else if (line.startsWith("dirreq-stats-end ")) { + String[] parts = line.split(" "); + if (parts.length < 5) { + this.logger.warning("Could not parse dirreq-stats-end " + + "line '" + line + "' in descriptor. Skipping."); + break; + } + statsEnd = parts[1] + " " + parts[2]; + seconds = Long.parseLong(parts[3].substring(1)); + } else if (line.startsWith("dirreq-v3-reqs ") + && line.length() > "dirreq-v3-reqs ".length()) { + if (this.rddi != null) { + try { + int allUsers = 0; + Map<String, String> obs = new HashMap<String, String>(); + String[] parts = line.substring("dirreq-v3-reqs ". + length()).split(","); + for (String p : parts) { + String country = p.substring(0, 2); + int users = Integer.parseInt(p.substring(3)) - 4; + allUsers += users; + obs.put(country, "" + users); + } + obs.put("zy", "" + allUsers); + this.rddi.addDirReqStats(dir, statsEnd, seconds, obs); + } catch (NumberFormatException e) { + this.logger.log(Level.WARNING, "Could not parse " + + "dirreq-v3-reqs line '" + line + "' in descriptor. " + + "Skipping.", e); + break; + } + } + } else if (line.startsWith("conn-bi-direct ")) { + if (this.rddi != null) { + String[] parts = line.split(" "); + if (parts.length == 6 && + parts[5].split(",").length == 4) { + try { + String connBiDirectStatsEnd = parts[1] + " " + parts[2]; + long connBiDirectSeconds = Long.parseLong(parts[3]. + substring(1)); + String[] parts2 = parts[5].split(","); + long below = Long.parseLong(parts2[0]); + long read = Long.parseLong(parts2[1]); + long write = Long.parseLong(parts2[2]); + long both = Long.parseLong(parts2[3]); + this.rddi.addConnBiDirect(dir, connBiDirectStatsEnd, + connBiDirectSeconds, below, read, write, both); + } catch (NumberFormatException e) { + this.logger.log(Level.WARNING, "Number format " + + "exception while parsing conn-bi-direct stats " + + "string '" + line + "'. Skipping.", e); + } + } else { + this.logger.warning("Skipping invalid conn-bi-direct " + + "stats string '" + line + "'."); + } + } + } + } + String ascii = new String(data, "US-ASCII"); + String startToken = "extra-info "; + String sigToken = "\nrouter-signature\n"; + String digest = null; + int start = ascii.indexOf(startToken); + int sig = ascii.indexOf(sigToken) + sigToken.length(); + if (start >= 0 || sig >= 0 || sig > start) { + byte[] forDigest = new byte[sig - start]; + System.arraycopy(data, start, forDigest, 0, sig - start); + digest = DigestUtils.shaHex(forDigest); + } + if (this.rddi != null && digest != null) { + this.rddi.addExtraInfoDescriptor(digest, nickname, + dir.toLowerCase(), published, data, bandwidthHistory); + } + } + } catch (IOException e) { + this.logger.log(Level.WARNING, "Could not parse descriptor. " + + "Skipping.", e); + } catch (ParseException e) { + this.logger.log(Level.WARNING, "Could not parse descriptor. " + + "Skipping.", e); + } + } } diff --git a/src/org/torproject/ernie/cron/Main.java b/src/org/torproject/ernie/cron/Main.java index 57ad804..d631a7b 100644 --- a/src/org/torproject/ernie/cron/Main.java +++ b/src/org/torproject/ernie/cron/Main.java @@ -47,15 +47,10 @@ public class Main { config.getWriteRelayDescriptorsRawFiles() ? config.getRelayDescriptorRawFilesDirectory() : null) : null; - // Prepare relay descriptor parser (only if we are writing the - // consensus-health page to disk) - RelayDescriptorParser rdp = rddi != null ? - new RelayDescriptorParser(rddi, bsfh) : null; - // Import relay descriptors - if (rdp != null) { + if (rddi != null) { if (config.getImportDirectoryArchives()) { - new ArchiveReader(rdp, + new ArchiveReader(rddi, bsfh, new File(config.getDirectoryArchivesDirectory()), statsDirectory, config.getKeepDirectoryArchiveImportHistory()); diff --git a/src/org/torproject/ernie/cron/RelayDescriptorParser.java b/src/org/torproject/ernie/cron/RelayDescriptorParser.java deleted file mode 100644 index ed52d4c..0000000 --- a/src/org/torproject/ernie/cron/RelayDescriptorParser.java +++ /dev/null @@ -1,387 +0,0 @@ -/* Copyright 2011, 2012 The Tor Project - * See LICENSE for licensing information */ -package org.torproject.ernie.cron; - -import java.io.BufferedReader; -import java.io.IOException; -import java.io.StringReader; -import java.text.ParseException; -import java.text.SimpleDateFormat; -import java.util.ArrayList; -import java.util.HashMap; -import java.util.List; -import java.util.Map; -import java.util.SortedSet; -import java.util.TimeZone; -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 - * stats handlers, to the archive writer, or to the relay descriptor - * downloader. - */ -public class RelayDescriptorParser { - - /** - * Stats file handler that accepts parse results for bridge statistics. - */ - private BridgeStatsFileHandler bsfh; - - /** - * Relay descriptor database importer that stores relay descriptor - * contents for later evaluation. - */ - private RelayDescriptorDatabaseImporter rddi; - - /** - * Logger for this class. - */ - private Logger logger; - - private SimpleDateFormat dateTimeFormat; - - /** - * Initializes this class. - */ - public RelayDescriptorParser(RelayDescriptorDatabaseImporter rddi, - BridgeStatsFileHandler bsfh) { - this.rddi = rddi; - this.bsfh = bsfh; - - /* Initialize logger. */ - this.logger = Logger.getLogger(RelayDescriptorParser.class.getName()); - - this.dateTimeFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); - this.dateTimeFormat.setTimeZone(TimeZone.getTimeZone("UTC")); - } - - public void parse(byte[] data) { - try { - /* Remove any @ lines at the beginning of the file and parse the - * first non-@ line to find out the descriptor type. */ - BufferedReader br = new BufferedReader(new StringReader(new String( - data, "US-ASCII"))); - String line = br.readLine(); - while (line != null && line.startsWith("@")) { - line = br.readLine(); - } - if (line == null) { - this.logger.fine("We were given a file that doesn't contain a " - + "single descriptor for parsing. Ignoring."); - return; - } - br.close(); - - /* Split the byte[] possibly containing multiple descriptors into - * byte[]'s with one descriptor each and parse them. */ - String startToken = null; - if (line.equals("network-status-version 3")) { - startToken = "network-status-version 3"; - } else if (line.startsWith("router ")) { - startToken = "router "; - } else if (line.startsWith("extra-info ")) { - startToken = "extra-info "; - } else if (line.equals("dir-key-certificate-version 3")) { - this.logger.fine("Not parsing dir key certificate."); - return; - } else { - this.logger.warning("Unknown descriptor type. First line is '" - + line + "'. Ignoring."); - return; - } - String splitToken = "\n" + startToken; - String ascii = new String(data, "US-ASCII"); - int length = data.length, start = ascii.indexOf(startToken); - while (start < length) { - int end = ascii.indexOf(splitToken, start); - if (end < 0) { - end = length; - } else { - end += 1; - } - byte[] descBytes = new byte[end - start]; - System.arraycopy(data, start, descBytes, 0, end - start); - parseSingleDescriptor(descBytes); - start = end; - } - } catch (IOException e) { - this.logger.log(Level.WARNING, "Could not parse descriptor. " - + "Skipping.", e); - } - } - - private void parseSingleDescriptor(byte[] data) { - try { - /* Convert descriptor to ASCII for parsing. This means we'll lose - * the non-ASCII chars, but we don't care about them for parsing - * anyway. */ - BufferedReader br = new BufferedReader(new StringReader(new String( - data, "US-ASCII"))); - String line = br.readLine(); - SimpleDateFormat parseFormat = - new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); - parseFormat.setTimeZone(TimeZone.getTimeZone("UTC")); - if (line.equals("network-status-version 3")) { - // TODO when parsing the current consensus, check the fresh-until - // time to see when we switch from hourly to half-hourly - // consensuses - boolean isConsensus = true; - String validAfterTime = null, nickname = null, - relayIdentity = null, serverDesc = null, version = null, - ports = null; - String dirSource = null, address = null; - long validAfter = -1L, published = -1L, bandwidth = -1L, - orPort = 0L, dirPort = 0L; - SortedSet<String> relayFlags = null; - StringBuilder rawStatusEntry = null; - SortedSet<String> hashedRelayIdentities = new TreeSet<String>(); - while ((line = br.readLine()) != null) { - if (line.equals("vote-status vote")) { - isConsensus = false; - } else if (line.startsWith("valid-after ")) { - validAfterTime = line.substring("valid-after ".length()); - validAfter = parseFormat.parse(validAfterTime).getTime(); - } else if (line.startsWith("dir-source ")) { - dirSource = line.split(" ")[2]; - } else if (line.startsWith("r ")) { - if (isConsensus && relayIdentity != null && - this.rddi != null) { - byte[] rawDescriptor = rawStatusEntry.toString().getBytes(); - this.rddi.addStatusEntry(validAfter, nickname, - relayIdentity, serverDesc, published, address, orPort, - dirPort, relayFlags, version, bandwidth, ports, - rawDescriptor); - relayFlags = null; - version = null; - bandwidth = -1L; - ports = null; - } - rawStatusEntry = new StringBuilder(line + "\n"); - String[] parts = line.split(" "); - if (parts.length < 9) { - this.logger.log(Level.WARNING, "Could not parse r line '" - + line + "' in descriptor. Skipping."); - break; - } - nickname = parts[1]; - relayIdentity = Hex.encodeHexString( - Base64.decodeBase64(parts[2] + "=")). - toLowerCase(); - hashedRelayIdentities.add(DigestUtils.shaHex( - Base64.decodeBase64(parts[2] + "=")). - toUpperCase()); - serverDesc = Hex.encodeHexString(Base64.decodeBase64( - parts[3] + "=")).toLowerCase(); - published = parseFormat.parse(parts[4] + " " + parts[5]). - getTime(); - address = parts[6]; - orPort = Long.parseLong(parts[7]); - dirPort = Long.parseLong(parts[8]); - } else if (line.startsWith("s ") || line.equals("s")) { - rawStatusEntry.append(line + "\n"); - relayFlags = new TreeSet<String>(); - if (line.length() > 2) { - for (String flag : line.substring(2).split(" ")) { - relayFlags.add(flag); - } - } - } else if (line.startsWith("v ")) { - rawStatusEntry.append(line + "\n"); - version = line.substring(2); - } else if (line.startsWith("w ")) { - rawStatusEntry.append(line + "\n"); - String[] parts = line.split(" "); - for (String part : parts) { - if (part.startsWith("Bandwidth=")) { - bandwidth = Long.parseLong(part.substring( - "Bandwidth=".length())); - } - } - } else if (line.startsWith("p ")) { - rawStatusEntry.append(line + "\n"); - ports = line.substring(2); - } - } - if (isConsensus) { - if (this.bsfh != null) { - for (String hashedRelayIdentity : hashedRelayIdentities) { - this.bsfh.addHashedRelay(hashedRelayIdentity); - } - } - if (this.rddi != null) { - this.rddi.addConsensus(validAfter, data); - if (relayIdentity != null) { - byte[] rawDescriptor = rawStatusEntry.toString().getBytes(); - this.rddi.addStatusEntry(validAfter, nickname, - relayIdentity, serverDesc, published, address, orPort, - dirPort, relayFlags, version, bandwidth, ports, - rawDescriptor); - } - } - } else { - if (this.rddi != null) { - this.rddi.addVote(validAfter, dirSource, data); - } - } - } else if (line.startsWith("router ")) { - String platformLine = null, bandwidthLine = null, - extraInfoDigest = null, relayIdentifier = null; - String[] parts = line.split(" "); - String nickname = parts[1]; - String address = parts[2]; - int orPort = Integer.parseInt(parts[3]); - int dirPort = Integer.parseInt(parts[4]); - long published = -1L, uptime = -1L; - while ((line = br.readLine()) != null) { - if (line.startsWith("platform ")) { - platformLine = line; - } else if (line.startsWith("published ")) { - String 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("bandwidth ")) { - bandwidthLine = line; - } 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("uptime ")) { - uptime = Long.parseLong(line.substring("uptime ".length())); - } - } - String ascii = new String(data, "US-ASCII"); - String startToken = "router "; - String sigToken = "\nrouter-signature\n"; - int start = ascii.indexOf(startToken); - int sig = ascii.indexOf(sigToken) + sigToken.length(); - String digest = null; - if (start >= 0 || sig >= 0 || sig > start) { - byte[] forDigest = new byte[sig - start]; - System.arraycopy(data, start, forDigest, 0, sig - start); - digest = DigestUtils.shaHex(forDigest); - } - if (this.rddi != null && digest != null) { - String[] bwParts = bandwidthLine.split(" "); - long bandwidthAvg = Long.parseLong(bwParts[1]); - long bandwidthBurst = Long.parseLong(bwParts[2]); - long bandwidthObserved = Long.parseLong(bwParts[3]); - String platform = platformLine.substring("platform ".length()); - this.rddi.addServerDescriptor(digest, nickname, address, orPort, - dirPort, relayIdentifier, bandwidthAvg, bandwidthBurst, - bandwidthObserved, platform, published, uptime, - extraInfoDigest, data); - } - } else if (line.startsWith("extra-info ")) { - String nickname = line.split(" ")[1]; - long published = -1L; - String dir = line.split(" ")[2]; - String statsEnd = null; - long seconds = -1L; - List<String> bandwidthHistory = new ArrayList<String>(); - while ((line = br.readLine()) != null) { - if (line.startsWith("published ")) { - String publishedTime = line.substring("published ".length()); - published = parseFormat.parse(publishedTime).getTime(); - } else if (line.startsWith("read-history ") || - line.startsWith("write-history ") || - line.startsWith("dirreq-read-history ") || - line.startsWith("dirreq-write-history ")) { - bandwidthHistory.add(line); - } else if (line.startsWith("dirreq-stats-end ")) { - String[] parts = line.split(" "); - if (parts.length < 5) { - this.logger.warning("Could not parse dirreq-stats-end " - + "line '" + line + "' in descriptor. Skipping."); - break; - } - statsEnd = parts[1] + " " + parts[2]; - seconds = Long.parseLong(parts[3].substring(1)); - } else if (line.startsWith("dirreq-v3-reqs ") - && line.length() > "dirreq-v3-reqs ".length()) { - if (this.rddi != null) { - try { - int allUsers = 0; - Map<String, String> obs = new HashMap<String, String>(); - String[] parts = line.substring("dirreq-v3-reqs ". - length()).split(","); - for (String p : parts) { - String country = p.substring(0, 2); - int users = Integer.parseInt(p.substring(3)) - 4; - allUsers += users; - obs.put(country, "" + users); - } - obs.put("zy", "" + allUsers); - this.rddi.addDirReqStats(dir, statsEnd, seconds, obs); - } catch (NumberFormatException e) { - this.logger.log(Level.WARNING, "Could not parse " - + "dirreq-v3-reqs line '" + line + "' in descriptor. " - + "Skipping.", e); - break; - } - } - } else if (line.startsWith("conn-bi-direct ")) { - if (this.rddi != null) { - String[] parts = line.split(" "); - if (parts.length == 6 && - parts[5].split(",").length == 4) { - try { - String connBiDirectStatsEnd = parts[1] + " " + parts[2]; - long connBiDirectSeconds = Long.parseLong(parts[3]. - substring(1)); - String[] parts2 = parts[5].split(","); - long below = Long.parseLong(parts2[0]); - long read = Long.parseLong(parts2[1]); - long write = Long.parseLong(parts2[2]); - long both = Long.parseLong(parts2[3]); - this.rddi.addConnBiDirect(dir, connBiDirectStatsEnd, - connBiDirectSeconds, below, read, write, both); - } catch (NumberFormatException e) { - this.logger.log(Level.WARNING, "Number format " - + "exception while parsing conn-bi-direct stats " - + "string '" + line + "'. Skipping.", e); - } - } else { - this.logger.warning("Skipping invalid conn-bi-direct " - + "stats string '" + line + "'."); - } - } - } - } - String ascii = new String(data, "US-ASCII"); - String startToken = "extra-info "; - String sigToken = "\nrouter-signature\n"; - String digest = null; - int start = ascii.indexOf(startToken); - int sig = ascii.indexOf(sigToken) + sigToken.length(); - if (start >= 0 || sig >= 0 || sig > start) { - byte[] forDigest = new byte[sig - start]; - System.arraycopy(data, start, forDigest, 0, sig - start); - digest = DigestUtils.shaHex(forDigest); - } - if (this.rddi != null && digest != null) { - this.rddi.addExtraInfoDescriptor(digest, nickname, - dir.toLowerCase(), published, data, bandwidthHistory); - } - } - } catch (IOException e) { - this.logger.log(Level.WARNING, "Could not parse descriptor. " - + "Skipping.", e); - } catch (ParseException e) { - this.logger.log(Level.WARNING, "Could not parse descriptor. " - + "Skipping.", e); - } - } -} -

1 0

[metrics-web/master] Remove bridge descriptor parser.
by karsten＠torproject.org 22 Mar '12

22 Mar '12

commit b4d34b4cb2e90584597d297cddde9aa228ae1c66 Author: Karsten Loesing <karsten.loesing(a)gmx.net> Date: Wed Mar 21 12:30:49 2012 +0100 Remove bridge descriptor parser. The purpose of this commit is to prepare adding metrics-lib as library for descriptor parsing. --- .../ernie/cron/BridgeDescriptorParser.java | 148 -------------------- src/org/torproject/ernie/cron/Main.java | 9 +- .../ernie/cron/SanitizedBridgesReader.java | 145 ++++++++++++++++++- .../ernie/test/SanitizedBridgesReaderTest.java | 33 ----- 4 files changed, 143 insertions(+), 192 deletions(-) diff --git a/src/org/torproject/ernie/cron/BridgeDescriptorParser.java b/src/org/torproject/ernie/cron/BridgeDescriptorParser.java deleted file mode 100644 index 221e896..0000000 --- a/src/org/torproject/ernie/cron/BridgeDescriptorParser.java +++ /dev/null @@ -1,148 +0,0 @@ -/* Copyright 2011, 2012 The Tor Project - * See LICENSE for licensing information */ -package org.torproject.ernie.cron; - -import java.io.BufferedReader; -import java.io.IOException; -import java.io.StringReader; -import java.text.ParseException; -import java.text.SimpleDateFormat; -import java.util.HashMap; -import java.util.Map; -import java.util.TimeZone; -import java.util.logging.Level; -import java.util.logging.Logger; - -import org.apache.commons.codec.digest.DigestUtils; - -public class BridgeDescriptorParser { - private ConsensusStatsFileHandler csfh; - private BridgeStatsFileHandler bsfh; - private Logger logger; - public BridgeDescriptorParser(ConsensusStatsFileHandler csfh, - BridgeStatsFileHandler bsfh) { - this.csfh = csfh; - this.bsfh = bsfh; - this.logger = - Logger.getLogger(BridgeDescriptorParser.class.getName()); - } - public void parse(byte[] allData, String dateTime, boolean sanitized) { - try { - BufferedReader br = new BufferedReader(new StringReader( - new String(allData, "US-ASCII"))); - SimpleDateFormat timeFormat = new SimpleDateFormat( - "yyyy-MM-dd HH:mm:ss"); - timeFormat.setTimeZone(TimeZone.getTimeZone("UTC")); - String hashedIdentity = null, platformLine = null, - publishedLine = null, geoipStartTimeLine = null, - bridgeStatsEndLine = null; - boolean skip = false; - String line = null; - while ((line = br.readLine()) != null) { - if (line.startsWith("r ")) { - int runningBridges = 0; - while ((line = br.readLine()) != null) { - if (line.startsWith("s ") && line.contains(" Running")) { - runningBridges++; - } - } - if (this.csfh != null) { - this.csfh.addBridgeConsensusResults(dateTime, runningBridges); - } - } else if (line.startsWith("router ")) { - } else if (line.startsWith("extra-info ")) { - hashedIdentity = sanitized ? line.split(" ")[2] - : DigestUtils.shaHex(line.split(" ")[2]).toUpperCase(); - if (this.bsfh != null) { - skip = this.bsfh.isKnownRelay(hashedIdentity); - } - } else if (!skip && line.startsWith("platform ")) { - platformLine = line; - } else if (!skip && line.startsWith("published ")) { - publishedLine = line; - } else if (line.startsWith("opt fingerprint") || - line.startsWith("fingerprint")) { - String identity = line.substring(line.startsWith("opt ") ? - "opt fingerprint".length() : "fingerprint".length()). - replaceAll(" ", "").toLowerCase(); - hashedIdentity = sanitized ? identity - : DigestUtils.shaHex(identity).toUpperCase(); - } else if (!skip && line.startsWith("geoip-start-time ")) { - geoipStartTimeLine = line; - } else if (!skip && line.startsWith("geoip-client-origins") - && line.split(" ").length > 1) { - if (publishedLine == null || - geoipStartTimeLine == null) { - this.logger.warning("Either published line or " - + "geoip-start-time line is not present in " - + (sanitized ? "sanitized" : "non-sanitized") - + " bridge descriptors from " + dateTime + "."); - break; - } - long published = timeFormat.parse(publishedLine. - substring("published ".length())).getTime(); - long started = timeFormat.parse(geoipStartTimeLine. - substring("geoip-start-time ".length())).getTime(); - long seconds = (published - started) / 1000L; - double allUsers = 0.0D; - Map<String, String> obs = new HashMap<String, String>(); - String[] parts = line.split(" ")[1].split(","); - for (String p : parts) { - String country = p.substring(0, 2); - double users = ((double) Long.parseLong(p.substring(3)) - 4L) - * 86400.0D / ((double) seconds); - allUsers += users; - obs.put(country, String.format("%.2f", users)); - } - obs.put("zy", String.format("%.2f", allUsers)); - String date = publishedLine.split(" ")[1]; - String time = publishedLine.split(" ")[2]; - if (this.bsfh != null) { - this.bsfh.addObs(hashedIdentity, date, time, obs); - } - } else if (!skip && line.startsWith("bridge-stats-end ")) { - bridgeStatsEndLine = line; - } else if (!skip && line.startsWith("bridge-ips") - && line.split(" ").length > 1) { - if (bridgeStatsEndLine == null) { - this.logger.warning("bridge-ips line without preceding " - + "bridge-stats-end line in " - + (sanitized ? "sanitized" : "non-sanitized") - + " bridge descriptor."); - break; - } - double allUsers = 0.0D; - Map<String, String> obs = new HashMap<String, String>(); - String[] parts = line.split(" ")[1].split(","); - for (String p : parts) { - String country = p.substring(0, 2); - double users = (double) Long.parseLong(p.substring(3)) - 4L; - allUsers += users; - obs.put(country, String.format("%.2f", users)); - } - obs.put("zy", String.format("%.2f", allUsers)); - String date = bridgeStatsEndLine.split(" ")[1]; - String time = bridgeStatsEndLine.split(" ")[2]; - if (this.bsfh != null) { - this.bsfh.addObs(hashedIdentity, date, time, obs); - } - } - } - if (this.bsfh != null && platformLine != null && - platformLine.startsWith("platform Tor 0.2.2")) { - String date = publishedLine.split(" ")[1]; - String time = publishedLine.split(" ")[2]; - this.bsfh.addZeroTwoTwoDescriptor(hashedIdentity, date, time); - } - } catch (IOException e) { - this.logger.log(Level.WARNING, "Could not parse bridge descriptor.", - e); - return; - } catch (ParseException e) { - this.logger.log(Level.WARNING, "Could not parse bridge descriptor.", - e); - return; - } - } -} - diff --git a/src/org/torproject/ernie/cron/Main.java b/src/org/torproject/ernie/cron/Main.java index d631a7b..1c8ca48 100644 --- a/src/org/torproject/ernie/cron/Main.java +++ b/src/org/torproject/ernie/cron/Main.java @@ -68,13 +68,10 @@ public class Main { new ConsensusStatsFileHandler( config.getRelayDescriptorDatabaseJDBC()) : null; - // Prepare bridge descriptor parser - BridgeDescriptorParser bdp = config.getWriteBridgeStats() ? - new BridgeDescriptorParser(csfh, bsfh) : null; - // Import bridge descriptors - if (bdp != null && config.getImportSanitizedBridges()) { - new SanitizedBridgesReader(bdp, + if (config.getWriteBridgeStats() && + config.getImportSanitizedBridges()) { + new SanitizedBridgesReader(csfh, bsfh, new File(config.getSanitizedBridgesDirectory()), statsDirectory, config.getKeepSanitizedBridgesImportHistory()); } diff --git a/src/org/torproject/ernie/cron/SanitizedBridgesReader.java b/src/org/torproject/ernie/cron/SanitizedBridgesReader.java index 09b4983..78bd7db 100644 --- a/src/org/torproject/ernie/cron/SanitizedBridgesReader.java +++ b/src/org/torproject/ernie/cron/SanitizedBridgesReader.java @@ -11,24 +11,40 @@ import java.io.FileInputStream; import java.io.FileReader; import java.io.FileWriter; import java.io.IOException; +import java.io.StringReader; +import java.text.ParseException; +import java.text.SimpleDateFormat; import java.util.ArrayList; +import java.util.HashMap; import java.util.List; +import java.util.Map; import java.util.SortedSet; import java.util.Stack; +import java.util.TimeZone; import java.util.TreeSet; import java.util.logging.Level; import java.util.logging.Logger; +import org.apache.commons.codec.digest.DigestUtils; + public class SanitizedBridgesReader { - public SanitizedBridgesReader(BridgeDescriptorParser bdp, - File bridgesDir, File statsDirectory, boolean keepImportHistory) { + private ConsensusStatsFileHandler csfh; + private BridgeStatsFileHandler bsfh; + private Logger logger; + public SanitizedBridgesReader(ConsensusStatsFileHandler csfh, + BridgeStatsFileHandler bsfh, File bridgesDir, File statsDirectory, + boolean keepImportHistory) { - if (bdp == null || bridgesDir == null || statsDirectory == null) { + if (csfh == null || bsfh == null || bridgesDir == null || + statsDirectory == null) { throw new IllegalArgumentException(); } - Logger logger = + this.csfh = csfh; + this.bsfh = bsfh; + this.logger = Logger.getLogger(SanitizedBridgesReader.class.getName()); + SortedSet<String> bridgesImportHistory = new TreeSet<String>(); File bridgesImportHistoryFile = new File(statsDirectory, "bridges-import-history"); @@ -79,7 +95,7 @@ public class SanitizedBridgesReader { String dateTime = fn.substring(0, 4) + "-" + fn.substring(4, 6) + "-" + fn.substring(6, 8) + " " + fn.substring(9, 11) + ":" + fn.substring(11, 13) + ":" + fn.substring(13, 15); - bdp.parse(allData, dateTime, true); + this.parse(allData, dateTime, true); if (keepImportHistory) { bridgesImportHistory.add(pop.getName()); } @@ -123,5 +139,124 @@ public class SanitizedBridgesReader { } } } + + private void parse(byte[] allData, String dateTime, boolean sanitized) { + try { + BufferedReader br = new BufferedReader(new StringReader( + new String(allData, "US-ASCII"))); + SimpleDateFormat timeFormat = new SimpleDateFormat( + "yyyy-MM-dd HH:mm:ss"); + timeFormat.setTimeZone(TimeZone.getTimeZone("UTC")); + String hashedIdentity = null, platformLine = null, + publishedLine = null, geoipStartTimeLine = null, + bridgeStatsEndLine = null; + boolean skip = false; + String line = null; + while ((line = br.readLine()) != null) { + if (line.startsWith("r ")) { + int runningBridges = 0; + while ((line = br.readLine()) != null) { + if (line.startsWith("s ") && line.contains(" Running")) { + runningBridges++; + } + } + if (this.csfh != null) { + this.csfh.addBridgeConsensusResults(dateTime, runningBridges); + } + } else if (line.startsWith("router ")) { + } else if (line.startsWith("extra-info ")) { + hashedIdentity = sanitized ? line.split(" ")[2] + : DigestUtils.shaHex(line.split(" ")[2]).toUpperCase(); + if (this.bsfh != null) { + skip = this.bsfh.isKnownRelay(hashedIdentity); + } + } else if (!skip && line.startsWith("platform ")) { + platformLine = line; + } else if (!skip && line.startsWith("published ")) { + publishedLine = line; + } else if (line.startsWith("opt fingerprint") || + line.startsWith("fingerprint")) { + String identity = line.substring(line.startsWith("opt ") ? + "opt fingerprint".length() : "fingerprint".length()). + replaceAll(" ", "").toLowerCase(); + hashedIdentity = sanitized ? identity + : DigestUtils.shaHex(identity).toUpperCase(); + } else if (!skip && line.startsWith("geoip-start-time ")) { + geoipStartTimeLine = line; + } else if (!skip && line.startsWith("geoip-client-origins") + && line.split(" ").length > 1) { + if (publishedLine == null || + geoipStartTimeLine == null) { + this.logger.warning("Either published line or " + + "geoip-start-time line is not present in " + + (sanitized ? "sanitized" : "non-sanitized") + + " bridge descriptors from " + dateTime + "."); + break; + } + long published = timeFormat.parse(publishedLine. + substring("published ".length())).getTime(); + long started = timeFormat.parse(geoipStartTimeLine. + substring("geoip-start-time ".length())).getTime(); + long seconds = (published - started) / 1000L; + double allUsers = 0.0D; + Map<String, String> obs = new HashMap<String, String>(); + String[] parts = line.split(" ")[1].split(","); + for (String p : parts) { + String country = p.substring(0, 2); + double users = ((double) Long.parseLong(p.substring(3)) - 4L) + * 86400.0D / ((double) seconds); + allUsers += users; + obs.put(country, String.format("%.2f", users)); + } + obs.put("zy", String.format("%.2f", allUsers)); + String date = publishedLine.split(" ")[1]; + String time = publishedLine.split(" ")[2]; + if (this.bsfh != null) { + this.bsfh.addObs(hashedIdentity, date, time, obs); + } + } else if (!skip && line.startsWith("bridge-stats-end ")) { + bridgeStatsEndLine = line; + } else if (!skip && line.startsWith("bridge-ips") + && line.split(" ").length > 1) { + if (bridgeStatsEndLine == null) { + this.logger.warning("bridge-ips line without preceding " + + "bridge-stats-end line in " + + (sanitized ? "sanitized" : "non-sanitized") + + " bridge descriptor."); + break; + } + double allUsers = 0.0D; + Map<String, String> obs = new HashMap<String, String>(); + String[] parts = line.split(" ")[1].split(","); + for (String p : parts) { + String country = p.substring(0, 2); + double users = (double) Long.parseLong(p.substring(3)) - 4L; + allUsers += users; + obs.put(country, String.format("%.2f", users)); + } + obs.put("zy", String.format("%.2f", allUsers)); + String date = bridgeStatsEndLine.split(" ")[1]; + String time = bridgeStatsEndLine.split(" ")[2]; + if (this.bsfh != null) { + this.bsfh.addObs(hashedIdentity, date, time, obs); + } + } + } + if (this.bsfh != null && platformLine != null && + platformLine.startsWith("platform Tor 0.2.2")) { + String date = publishedLine.split(" ")[1]; + String time = publishedLine.split(" ")[2]; + this.bsfh.addZeroTwoTwoDescriptor(hashedIdentity, date, time); + } + } catch (IOException e) { + this.logger.log(Level.WARNING, "Could not parse bridge descriptor.", + e); + return; + } catch (ParseException e) { + this.logger.log(Level.WARNING, "Could not parse bridge descriptor.", + e); + return; + } + } } diff --git a/src/org/torproject/ernie/test/SanitizedBridgesReaderTest.java b/src/org/torproject/ernie/test/SanitizedBridgesReaderTest.java deleted file mode 100644 index 748894e..0000000 --- a/src/org/torproject/ernie/test/SanitizedBridgesReaderTest.java +++ /dev/null @@ -1,33 +0,0 @@ -/* Copyright 2011, 2012 The Tor Project - * See LICENSE for licensing information */ -package org.torproject.ernie.test; - -import java.io.File; - -import org.junit.Before; -import org.junit.Rule; -import org.junit.Test; -import org.junit.rules.TemporaryFolder; -import org.torproject.ernie.cron.SanitizedBridgesReader; - -public class SanitizedBridgesReaderTest { - - private File tempSanitizedBridgesDirectory; - private File tempStatsDirectory; - - @Rule - public TemporaryFolder folder = new TemporaryFolder(); - - @Before - public void createTempDirectories() { - this.tempSanitizedBridgesDirectory = folder.newFolder("bridges"); - this.tempStatsDirectory = folder.newFolder("stats"); - } - - @Test(expected = IllegalArgumentException.class) - public void testBridgeDescriptorParserNull() { - new SanitizedBridgesReader(null, this.tempSanitizedBridgesDirectory, - this.tempStatsDirectory, false); - } -} -

1 0

[translation/vidalia_alpha] Update translations for vidalia_alpha
by translation＠torproject.org 22 Mar '12

22 Mar '12

commit 412291270c78a1159e5ffb3ca8e56094d15ddc74 Author: Translation commit bot <translation(a)torproject.org> Date: Thu Mar 22 10:45:13 2012 +0000 Update translations for vidalia_alpha --- fa/vidalia_fa.po | 58 +++++++++++++++++++++++++++--------------------------- 1 files changed, 29 insertions(+), 29 deletions(-) diff --git a/fa/vidalia_fa.po b/fa/vidalia_fa.po index 0bac717..4526f87 100644 --- a/fa/vidalia_fa.po +++ b/fa/vidalia_fa.po @@ -8,7 +8,7 @@ msgstr "" "Project-Id-Version: The Tor Project\n" "Report-Msgid-Bugs-To: https://trac.torproject.org/projects/tor\n" "POT-Creation-Date: 2012-03-21 17:46+0000\n" -"PO-Revision-Date: 2012-03-22 10:15+0000\n" +"PO-Revision-Date: 2012-03-22 10:31+0000\n" "Last-Translator: ms2222 <slander_mo(a)hotmail.com>\n" "Language-Team: translations(a)vidalia-project.net\n" "MIME-Version: 1.0\n" @@ -638,31 +638,31 @@ msgstr "" msgctxt "CountryInfo" msgid "Chile" -msgstr "" +msgstr "شیلی" msgctxt "CountryInfo" msgid "China" -msgstr "" +msgstr "چین" msgctxt "CountryInfo" msgid "Colombia" -msgstr "" +msgstr "کلمبیا" msgctxt "CountryInfo" msgid "Comoros" -msgstr "" +msgstr "کامرون" msgctxt "CountryInfo" msgid "Congo, The Democratic Republic of the" -msgstr "" +msgstr "جمهوری دموکرات کنگو" msgctxt "CountryInfo" msgid "Congo" -msgstr "" +msgstr "کنگو" msgctxt "CountryInfo" msgid "Costa Rica" -msgstr "" +msgstr "کاستاریکا" msgctxt "CountryInfo" msgid "Cote dâIvoire" @@ -670,11 +670,11 @@ msgstr "" msgctxt "CountryInfo" msgid "Croatia" -msgstr "" +msgstr "کرواسی" msgctxt "CountryInfo" msgid "Cuba" -msgstr "" +msgstr "کوبا" msgctxt "CountryInfo" msgid "Cyprus" @@ -682,11 +682,11 @@ msgstr "" msgctxt "CountryInfo" msgid "Czech Republic" -msgstr "" +msgstr "جمهوری چک" msgctxt "CountryInfo" msgid "Denmark" -msgstr "" +msgstr "دانمارک" msgctxt "CountryInfo" msgid "Djibouti" @@ -698,19 +698,19 @@ msgstr "" msgctxt "CountryInfo" msgid "Dominican Republic" -msgstr "" +msgstr "جمهوری دومنیکن" msgctxt "CountryInfo" msgid "Ecuador" -msgstr "" +msgstr "اکوادور" msgctxt "CountryInfo" msgid "Egypt" -msgstr "" +msgstr "مصر" msgctxt "CountryInfo" msgid "El Salvador" -msgstr "" +msgstr "السالوادور" msgctxt "CountryInfo" msgid "Equatorial Guinea" @@ -722,15 +722,15 @@ msgstr "" msgctxt "CountryInfo" msgid "Estonia" -msgstr "" +msgstr "استونی" msgctxt "CountryInfo" msgid "France" -msgstr "" +msgstr "فرانسه" msgctxt "CountryInfo" msgid "Gabon" -msgstr "" +msgstr "گابن" msgctxt "CountryInfo" msgid "Gambia" @@ -934,15 +934,15 @@ msgstr "هلند" msgctxt "CountryInfo" msgid "New Zealand" -msgstr "" +msgstr "نیوزلند" msgctxt "CountryInfo" msgid "Nicaragua" -msgstr "" +msgstr "نیکاراگوئه" msgctxt "CountryInfo" msgid "Niger" -msgstr "" +msgstr "نیجر" msgctxt "CountryInfo" msgid "Nigeria" @@ -950,15 +950,15 @@ msgstr "" msgctxt "CountryInfo" msgid "Norway" -msgstr "" +msgstr "نروژ" msgctxt "CountryInfo" msgid "Oman" -msgstr "" +msgstr "عمان" msgctxt "CountryInfo" msgid "Pakistan" -msgstr "" +msgstr "پاکستان" msgctxt "CountryInfo" msgid "Palau" @@ -966,11 +966,11 @@ msgstr "" msgctxt "CountryInfo" msgid "Palestine" -msgstr "" +msgstr "فلسطین" msgctxt "CountryInfo" msgid "Panama" -msgstr "" +msgstr "پاناما" msgctxt "CountryInfo" msgid "Papua New Guinea" @@ -978,11 +978,11 @@ msgstr "" msgctxt "CountryInfo" msgid "Paraguay" -msgstr "" +msgstr "پاراگوئه" msgctxt "CountryInfo" msgid "Peru" -msgstr "" +msgstr "پرو" msgctxt "CountryInfo" msgid "Philippines"

1 0

[translation/vidalia_alpha] Update translations for vidalia_alpha
by translation＠torproject.org 22 Mar '12

22 Mar '12

commit 98632c66b816b0cbfd1f72848c1afb41f2743b3d Author: Translation commit bot <translation(a)torproject.org> Date: Thu Mar 22 10:15:12 2012 +0000 Update translations for vidalia_alpha --- fa/vidalia_fa.po | 11 ++++++----- 1 files changed, 6 insertions(+), 5 deletions(-) diff --git a/fa/vidalia_fa.po b/fa/vidalia_fa.po index 35c8f18..0bac717 100644 --- a/fa/vidalia_fa.po +++ b/fa/vidalia_fa.po @@ -2,13 +2,14 @@ # Translators: # Ardeshir <ardeshir(a)redteam.io>, 2012. # <behravanhamed(a)gmail.com>, 2011. +# <slander_mo(a)hotmail.com>, 2012. msgid "" msgstr "" "Project-Id-Version: The Tor Project\n" "Report-Msgid-Bugs-To: https://trac.torproject.org/projects/tor\n" "POT-Creation-Date: 2012-03-21 17:46+0000\n" -"PO-Revision-Date: 2012-03-22 09:01+0000\n" -"Last-Translator: Ardeshir <ardeshir(a)redteam.io>\n" +"PO-Revision-Date: 2012-03-22 10:15+0000\n" +"Last-Translator: ms2222 <slander_mo(a)hotmail.com>\n" "Language-Team: translations(a)vidalia-project.net\n" "MIME-Version: 1.0\n" "Content-Type: text/plain; charset=UTF-8\n" @@ -593,7 +594,7 @@ msgstr "" msgctxt "CountryInfo" msgid "Brazil" -msgstr "" +msgstr "برزیل" msgctxt "CountryInfo" msgid "Brunei Darussalam" @@ -617,11 +618,11 @@ msgstr "" msgctxt "CountryInfo" msgid "Cameroon" -msgstr "" +msgstr "کامرون" msgctxt "CountryInfo" msgid "Canada" -msgstr "" +msgstr "کانادا" msgctxt "CountryInfo" msgid "Cape Verde"

1 0