-
-
Save ansell/7c59964cce75f6ad03cc71f2ed7520c4 to your computer and use it in GitHub Desktop.
Logstash config for ingesting Solr logs
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
input { | |
file { | |
path => "/Users/sebastienmuller/comperio/projects/sintef/tmp/logs/indexing_logs_2/solr.log.3" | |
start_position => "beginning" | |
sincedb_path => "/dev/null" | |
} | |
} | |
filter { | |
# Extract event severity and timestamp | |
grok { | |
match => { "message" => "%{WORD:level}.+?- %{DATA:LogTime};" } | |
tag_on_failure => [] | |
} | |
multiline { | |
pattern => "%{WORD}.+?- %{DATA};" | |
negate => true | |
what => "previous" | |
add_tag => [] | |
} | |
# INFO level events treated differently than ERROR | |
if "INFO" in [level] { | |
grok { | |
match => { | |
"message" => ".+?; ((([a-zA-Z]+(\.|;|:))+) )+?\[%{WORD:collection}\].+?path=%{DATA:endpoint} params=\{%{DATA:params}\}.+?\{%{WORD:action}=\[%{DATA:docId}" | |
} | |
tag_on_failure => [] | |
} | |
if [params] { | |
kv { | |
field_split => "&" | |
source => "params" | |
} | |
} else { | |
grok { | |
match => { | |
"message" => ".+?; ((([a-zA-Z]+(\.|;|:))+) )+?commits" | |
} | |
tag_on_failure => [ "drop" ] | |
add_field => { | |
"action" => "commit" | |
} | |
} | |
if "drop" in [tags] { | |
drop {} | |
} | |
} | |
} | |
# Error event implies stack track, which requires multiline parsing | |
if "ERROR" in [level] { | |
grok { | |
match => { | |
"message" => ".+?; ((([a-zA-Z]+(\.|;|:))+) )+%{DATA:reason}(\n\t)((.+?Caused by: ((([a-zA-Z]+(\.|;|:))+) )+)%{DATA:reason}(\n\t))+" | |
} | |
tag_on_failure => [] | |
} | |
grok { | |
match => { | |
"message" => ".+?; ((([a-zA-Z]+(\.|;|:))+) )+?Error: %{GREEDYDATA:reason}" | |
} | |
tag_on_failure => [] | |
} | |
} | |
# Remove intermediate tags, and multiline added randomly by multiline stage | |
mutate { | |
remove_tag => [ "multiline" ] | |
} | |
# Drop empty lines | |
if [message] =~ /^\s*$/ { | |
drop {} | |
} | |
} | |
output { | |
# Send directly to local Elasticsearch | |
elasticsearch_http { | |
host => "localhost" | |
template => "/Users/sebastienmuller/dev/logstash/logstash-1.5.2/bin/template.json" | |
index => "solr-%{+YYYY.MM.dd}" | |
template_overwrite => true | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
input { | |
file { | |
path => "~/solr.log" | |
} | |
} | |
filter { | |
# Extract event severity and timestamp | |
grok { | |
match => { "message" => "%{WORD:level}.+?- %{DATA:LogTime};" } | |
tag_on_failure => [] | |
} | |
# Combine commit events into single message | |
multiline { | |
pattern => "^\t(commit\{)" | |
what => "previous" | |
} | |
# INFO level events treated differently than ERROR | |
if "INFO" in [level] { | |
grok { | |
match => { | |
"message" => ".+?; ((([a-zA-Z]+(\.|;|:))+) )+?\[%{WORD:collection}\].+?path=%{DATA:endpoint} params=\{%{DATA:params}\}.+?\{%{WORD:action}=\[%{DATA:docId}" | |
} | |
tag_on_failure => [] | |
} | |
if [params] { | |
kv { | |
field_split => "&" | |
source => "params" | |
} | |
} else { | |
grok { | |
match => { | |
"message" => ".+?; ((([a-zA-Z]+(\.|;|:))+) )+?commits" | |
} | |
tag_on_failure => [ "drop" ] | |
add_field => { | |
"action" => "commit" | |
} | |
} | |
if "drop" in [tags] { | |
drop {} | |
} | |
} | |
} | |
# Error event implies stack track, which requires multiline parsing | |
if "ERROR" in [level] { | |
multiline { | |
pattern => "^\s" | |
what => "previous" | |
add_tag => [ "multiline_pre" ] | |
} | |
multiline { | |
pattern => "^Caused by" | |
what => "previous" | |
add_tag => [ "multiline_post" ] | |
} | |
if "multiline_post" in [tags] { | |
grok { | |
match => { | |
"message" => ".+?; ((([a-zA-Z]+(\.|;|:))+) )+%{DATA:reason}(\n\t)((.+?Caused by: ((([a-zA-Z]+(\.|;|:))+) )+)%{DATA:reason}(\n\t))+" | |
} | |
tag_on_failure => [] | |
} | |
} | |
} | |
# Remove intermediate tags, and multiline added randomly by multiline stage | |
mutate { | |
remove_tag => [ "multiline_pre", "multiline_post", "multiline" ] | |
} | |
# Drop empty lines | |
if [message] =~ /^\s*$/ { | |
drop {} | |
} | |
} | |
output { | |
# Send directly to local Elasticsearch | |
elasticsearch_http { | |
host => "localhost" | |
template => "~/logstash/bin/logstash_solr_template.json" | |
index => "solr-%{+YYYY.MM.dd}" | |
template_overwrite => true | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"template" : "solr-*", | |
"settings" : { | |
"index.refresh_interval" : "5s" | |
}, | |
"mappings" : { | |
"_default_" : { | |
"_all" : {"enabled" : true}, | |
"dynamic_templates" : [ { | |
"string_fields" : { | |
"match" : "*", | |
"match_mapping_type" : "string", | |
"mapping" : { | |
"type" : "string", "index" : "analyzed", "omit_norms" : true, | |
"fields" : { | |
"raw" : {"type": "string", "index" : "not_analyzed", "ignore_above" : 256} | |
} | |
} | |
} | |
} ], | |
"properties" : { | |
"@version": { "type": "string", "index": "not_analyzed" }, | |
"LogTime" : { | |
"type" : "date", | |
"format" : "yyyy-MM-dd HH:mm:ss.SSS" | |
} | |
} | |
} | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
INFO - 2015-09-21 12:34:23.420; org.apache.solr.core.SolrDeletionPolicy; SolrDeletionPolicy.onCommit: commits: num=2 | |
commit{dir=NRTCachingDirectory(MMapDirectory@D:\solution\solr\sintef_main\data\index lockFactory=NativeFSLockFactory@D:\solution\solr\sintef_main\data\index; maxCacheMB=48.0 maxMergeSizeMB=4.0),segFN=segments_1vj7,generation=87523} | |
commit{dir=NRTCachingDirectory(MMapDirectory@D:\solution\solr\sintef_main\data\index lockFactory=NativeFSLockFactory@D:\solution\solr\sintef_main\data\index; maxCacheMB=48.0 maxMergeSizeMB=4.0),segFN=segments_1vj8,generation=87524} | |
INFO - 2015-09-07 15:40:34.536; org.apache.solr.update.processor.LogUpdateProcessor; [sintef_main] webapp=/ path=/update/extract params={literal.source=epifile&literal.epi_file_title=GOFER+L4.0+Demonstratorer+V1.0.pdf&literal.title=GOFER+L4.0+Demonstratorer+V1.0.pdf&literal.id=epifile_211278&literal.epifileid_s=211278&literal.url=http://www.sintef.no/globalassets/upload/teknologi_samfunn/6060/prosjektfiler/gofer/gofer-l4.0-demonstratorer-v1.0.pdf&stream.url=http://www.sintef.no/globalassets/upload/teknologi_samfunn/6060/prosjektfiler/gofer/gofer-l4.0-demonstratorer-v1.0.pdf&literal.filesource_s=SiteFile} {} 0 65 | |
INFO - 2015-09-07 15:40:07.578; org.apache.solr.update.processor.LogUpdateProcessor; [sintef_main] webapp=/ path=/update/extract params={literal.source=epifile&literal.epi_file_title=A05188_Ungdom+påvirker+ungdom.pdf&literal.title=A05188_Ungdom+påvirker+ungdom.pdf&literal.id=epifile_210994&literal.epifileid_s=210994&literal.url=http://www.sintef.no/globalassets/upload/teknologi_samfunn/5033/a05188_ungdom-pavirker-ungdom.pdf&stream.url=http://www.sintef.no/globalassets/upload/teknologi_samfunn/5033/a05188_ungdom-pavirker-ungdom.pdf&literal.filesource_s=SiteFile} {add=[epifile_210994 (1511661982236803072)]} 0 125 | |
ERROR - 2015-09-07 15:40:34.537; org.apache.solr.common.SolrException; org.apache.solr.common.SolrException: org.apache.tika.exception.TikaException: Unable to extract PDF content | |
at org.apache.solr.handler.extraction.ExtractingDocumentLoader.load(ExtractingDocumentLoader.java:225) | |
at org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(ContentStreamHandlerBase.java:74) | |
at org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBase.java:135) | |
at org.apache.solr.core.RequestHandlers$LazyRequestHandlerWrapper.handleRequest(RequestHandlers.java:246) | |
at org.apache.solr.core.SolrCore.execute(SolrCore.java:1976) | |
at org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java:777) | |
at org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:418) | |
at org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:207) | |
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:241) | |
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:208) | |
at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:220) | |
at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:122) | |
at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:171) | |
at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:103) | |
at org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:950) | |
at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:116) | |
at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:408) | |
at org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Processor.java:1070) | |
at org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(AbstractProtocol.java:611) | |
at org.apache.tomcat.util.net.JIoEndpoint$SocketProcessor.run(JIoEndpoint.java:314) | |
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source) | |
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source) | |
at org.apache.tomcat.util.threads.TaskThread$WrappingRunnable.run(TaskThread.java:61) | |
at java.lang.Thread.run(Unknown Source) | |
Caused by: org.apache.tika.exception.TikaException: Unable to extract PDF content | |
at org.apache.tika.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:88) | |
at org.apache.tika.parser.pdf.PDFParser.parse(PDFParser.java:153) | |
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242) | |
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242) | |
at org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120) | |
at org.apache.solr.handler.extraction.ExtractingDocumentLoader.load(ExtractingDocumentLoader.java:219) | |
... 23 more | |
Caused by: java.io.IOException: javax.crypto.BadPaddingException: Given final block not properly padded | |
at javax.crypto.CipherInputStream.getMoreData(CipherInputStream.java:115) | |
at javax.crypto.CipherInputStream.read(CipherInputStream.java:233) | |
at javax.crypto.CipherInputStream.read(CipherInputStream.java:209) | |
at org.apache.pdfbox.pdmodel.encryption.SecurityHandler.encryptData(SecurityHandler.java:313) | |
at org.apache.pdfbox.pdmodel.encryption.SecurityHandler.decryptStream(SecurityHandler.java:412) | |
at org.apache.pdfbox.pdmodel.encryption.SecurityHandler.decrypt(SecurityHandler.java:384) | |
at org.apache.pdfbox.pdmodel.encryption.SecurityHandler.decryptObject(SecurityHandler.java:358) | |
at org.apache.pdfbox.pdmodel.encryption.SecurityHandler.proceedDecryption(SecurityHandler.java:195) | |
at org.apache.pdfbox.pdmodel.encryption.StandardSecurityHandler.decryptDocument(StandardSecurityHandler.java:156) | |
at org.apache.pdfbox.pdmodel.PDDocument.openProtection(PDDocument.java:1366) | |
at org.apache.pdfbox.pdmodel.PDDocument.decrypt(PDDocument.java:798) | |
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:316) | |
at org.apache.tika.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:72) | |
... 28 more | |
Caused by: javax.crypto.BadPaddingException: Given final block not properly padded | |
at com.sun.crypto.provider.CipherCore.doFinal(CipherCore.java:966) | |
at com.sun.crypto.provider.CipherCore.doFinal(CipherCore.java:824) | |
at com.sun.crypto.provider.AESCipher.engineDoFinal(AESCipher.java:436) | |
at javax.crypto.Cipher.doFinal(Cipher.java:2048) | |
at javax.crypto.CipherInputStream.getMoreData(CipherInputStream.java:112) | |
... 40 more | |
INFO - 2015-09-07 15:40:34.535; org.apache.solr.update.processor.LogUpdateProcessor; [sintef_main] webapp=/ path=/update/extract params={literal.source=epifile&literal.epi_file_title=GOFER+L4.0+Demonstratorer+V1.0.pdf&literal.title=GOFER+L4.0+Demonstratorer+V1.0.pdf&literal.id=epifile_211278&literal.epifileid_s=211278&literal.url=http://www.sintef.no/globalassets/upload/teknologi_samfunn/6060/prosjektfiler/gofer/gofer-l4.0-demonstratorer-v1.0.pdf&stream.url=http://www.sintef.no/globalassets/upload/teknologi_samfunn/6060/prosjektfiler/gofer/gofer-l4.0-demonstratorer-v1.0.pdf&literal.filesource_s=SiteFile} {} 0 65 | |
INFO - 2015-09-07 15:40:17.874; org.apache.solr.core.SolrCore; [sintef_main] Registered new searcher Searcher@5dc4452b[sintef_main] main{StandardDirectoryReader(segments_1jd0:315460:nrt _1f7c(4.10.4):C48803/20864:delGen=4917 _2eyv(4.10.4):C7505 _2e8y(4.10.4):C20758/1:delGen=1 _2f26(4.10.4):C978 _2fc7(4.10.4):C1385 _2f58(4.10.4):C2309 _2f1m(4.10.4):C131 _2f8u(4.10.4):C1093 _2ff9(4.10.4):C642 _2ffj(4.10.4):C28 _2ff2(4.10.4):C6 _2ff5(4.10.4):C5 _2ff6(4.10.4):C2 _2ffc(4.10.4):C4 _2ffe(4.10.4):C4 _2fff(4.10.4):C2 _2ffh(4.10.4):C1 _2ffk(4.10.4):C5 _2ffl(4.10.4):C1 _2ffm(4.10.4):C5 _2ffn(4.10.4):C3 _2ffo(4.10.4):C5 _2ffp(4.10.4):C2 _2ffq(4.10.4):C6 _2ffr(4.10.4):C2 _2ffs(4.10.4):C3)} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment