commit 1c3bcae76d92781fa7f7de86a3dcb6449bd3579d Author: Karsten Loesing karsten.loesing@gmx.net Date: Thu Apr 30 22:06:53 2020 +0200

Change order of detecting descriptor types.

We are detecting descriptor types of parsed descriptors by either content or file name. In some cases, if we downloaded descriptors from web servers, there is no file name. In other cases the file name can match more than one descriptor type. It seems most robust to move the file name checks to the end, which includes web server access logs and OnionPerf analysis files. --- .../torproject/descriptor/impl/DescriptorParserImpl.java | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/src/main/java/org/torproject/descriptor/impl/DescriptorParserImpl.java b/src/main/java/org/torproject/descriptor/impl/DescriptorParserImpl.java index 7dcd9d2..e008e7a 100644 --- a/src/main/java/org/torproject/descriptor/impl/DescriptorParserImpl.java +++ b/src/main/java/org/torproject/descriptor/impl/DescriptorParserImpl.java @@ -131,9 +131,6 @@ public class DescriptorParserImpl implements DescriptorParser { } else if (firstLines.startsWith("@type torperf 1.")) { return TorperfResultImpl.parseTorperfResults(rawDescriptorBytes, sourceFile); - } else if (fileName.endsWith(".onionperf.analysis.json.xz")) { - return new OnionPerfAnalysisConverter(rawDescriptorBytes, sourceFile) - .asTorperfResults(); } else if (firstLines.startsWith("@type snowflake-stats 1.") || firstLines.startsWith(Key.SNOWFLAKE_STATS_END.keyword + SP) || firstLines.contains(NL + Key.SNOWFLAKE_STATS_END.keyword + SP)) { @@ -144,8 +141,6 @@ public class DescriptorParserImpl implements DescriptorParser { || firstLines.contains(NL + Key.BRIDGEDB_METRICS_END.keyword + SP)) { return this.parseOneOrMoreDescriptors(rawDescriptorBytes, sourceFile, Key.BRIDGEDB_METRICS_END, BridgedbMetricsImpl.class); - } else if (fileName.contains(LogDescriptorImpl.MARKER)) { - return LogDescriptorImpl.parse(rawDescriptorBytes, sourceFile, fileName); } else if (firstLines.startsWith("@type bandwidth-file 1.") || firstLines.matches("(?s)[0-9]{10}\n.*")) { /* Identifying bandwidth files by a 10-digit timestamp in the first line @@ -156,6 +151,14 @@ public class DescriptorParserImpl implements DescriptorParser { parsedDescriptors.add(new BandwidthFileImpl(rawDescriptorBytes, sourceFile)); return parsedDescriptors; + } else if (null != fileName + && fileName.contains(LogDescriptorImpl.MARKER)) { + return LogDescriptorImpl.parse(rawDescriptorBytes, sourceFile, + fileName); + } else if (null != fileName + && fileName.endsWith(".onionperf.analysis.json.xz")) { + return new OnionPerfAnalysisConverter(rawDescriptorBytes, sourceFile) + .asTorperfResults(); } else { throw new DescriptorParseException("Could not detect descriptor " + "type in descriptor starting with '" + firstLines + "'.");