Skip to content
New issue

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

Sign up for GitHub

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

Already on GitHub? Sign in to your account

Jump to bottom

[ML] Include the "properties" layer in find_file_structure mappings #62158

Merged
merged 2 commits into from
Sep 9, 2020
Merged

[ML] Include the "properties" layer in find_file_structure mappings #62158

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6ddd910
[ML] Include the "properties" layer in find_file_structure mappings
droberts195 Sep 9, 2020
2200512
Fix YAML tests
droberts195 Sep 9, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
192 changes: 100 additions & 92 deletions docs/reference/ml/anomaly-detection/apis/find-file-structure.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -299,21 +299,23 @@ If the request does not encounter errors, you receive the following result:
],
"need_client_timezone" : true, <10>
"mappings" : { <11>
"@timestamp" : {
"type" : "date"
},
"author" : {
"type" : "keyword"
},
"name" : {
"type" : "keyword"
},
"page_count" : {
"type" : "long"
},
"release_date" : {
"type" : "date",
"format" : "iso8601"
"properties" : {
"@timestamp" : {
"type" : "date"
},
"author" : {
"type" : "keyword"
},
"name" : {
"type" : "keyword"
},
"page_count" : {
"type" : "long"
},
"release_date" : {
"type" : "date",
"format" : "iso8601"
}
}
},
"ingest_pipeline" : {
Expand Down Expand Up @@ -622,61 +624,63 @@ If the request does not encounter errors, you receive the following result:
],
"need_client_timezone" : true, <10>
"mappings" : {
"@timestamp" : {
"type" : "date"
},
"DOLocationID" : {
"type" : "long"
},
"PULocationID" : {
"type" : "long"
},
"RatecodeID" : {
"type" : "long"
},
"VendorID" : {
"type" : "long"
},
"extra" : {
"type" : "double"
},
"fare_amount" : {
"type" : "double"
},
"improvement_surcharge" : {
"type" : "double"
},
"mta_tax" : {
"type" : "double"
},
"passenger_count" : {
"type" : "long"
},
"payment_type" : {
"type" : "long"
},
"store_and_fwd_flag" : {
"type" : "keyword"
},
"tip_amount" : {
"type" : "double"
},
"tolls_amount" : {
"type" : "double"
},
"total_amount" : {
"type" : "double"
},
"tpep_dropoff_datetime" : {
"type" : "date",
"format" : "yyyy-MM-dd HH:mm:ss"
},
"tpep_pickup_datetime" : {
"type" : "date",
"format" : "yyyy-MM-dd HH:mm:ss"
},
"trip_distance" : {
"type" : "double"
"properties" : {
"@timestamp" : {
"type" : "date"
},
"DOLocationID" : {
"type" : "long"
},
"PULocationID" : {
"type" : "long"
},
"RatecodeID" : {
"type" : "long"
},
"VendorID" : {
"type" : "long"
},
"extra" : {
"type" : "double"
},
"fare_amount" : {
"type" : "double"
},
"improvement_surcharge" : {
"type" : "double"
},
"mta_tax" : {
"type" : "double"
},
"passenger_count" : {
"type" : "long"
},
"payment_type" : {
"type" : "long"
},
"store_and_fwd_flag" : {
"type" : "keyword"
},
"tip_amount" : {
"type" : "double"
},
"tolls_amount" : {
"type" : "double"
},
"total_amount" : {
"type" : "double"
},
"tpep_dropoff_datetime" : {
"type" : "date",
"format" : "yyyy-MM-dd HH:mm:ss"
},
"tpep_pickup_datetime" : {
"type" : "date",
"format" : "yyyy-MM-dd HH:mm:ss"
},
"trip_distance" : {
"type" : "double"
}
}
},
"ingest_pipeline" : {
Expand Down Expand Up @@ -1560,14 +1564,16 @@ this:
],
"need_client_timezone" : true,
"mappings" : {
"@timestamp" : {
"type" : "date"
},
"loglevel" : {
"type" : "keyword"
},
"message" : {
"type" : "text"
"properties" : {
"@timestamp" : {
"type" : "date"
},
"loglevel" : {
"type" : "keyword"
},
"message" : {
"type" : "text"
}
}
},
"ingest_pipeline" : {
Expand Down Expand Up @@ -1720,20 +1726,22 @@ this:
],
"need_client_timezone" : true,
"mappings" : {
"@timestamp" : {
"type" : "date"
},
"class" : {
"type" : "keyword"
},
"loglevel" : {
"type" : "keyword"
},
"message" : {
"type" : "text"
},
"node" : {
"type" : "keyword"
"properties" : {
"@timestamp" : {
"type" : "date"
},
"class" : {
"type" : "keyword"
},
"loglevel" : {
"type" : "keyword"
},
"message" : {
"type" : "text"
},
"node" : {
"type" : "keyword"
}
}
},
"ingest_pipeline" : {
Expand Down
18 changes: 9 additions & 9 deletions ...ain/java/org/elasticsearch/xpack/ml/filestructurefinder/DelimitedFileStructureFinder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,7 @@ static DelimitedFileStructureFinder makeDelimitedFileStructureFinder(List<String
Tuple<SortedMap<String, Object>, SortedMap<String, FieldStats>> mappingsAndFieldStats =
FileStructureUtils.guessMappingsAndCalculateFieldStats(explanation, sampleRecords, timeoutChecker);

SortedMap<String, Object> mappings = mappingsAndFieldStats.v1();
SortedMap<String, Object> fieldMappings = mappingsAndFieldStats.v1();

List<String> columnNamesList = Arrays.asList(columnNames);
char delimiter = (char) csvPreference.getDelimiterChar();
Expand Down Expand Up @@ -149,25 +149,25 @@ static DelimitedFileStructureFinder makeDelimitedFileStructureFinder(List<String
.setJavaTimestampFormats(timeField.v2().getJavaTimestampFormats())
.setNeedClientTimezone(needClientTimeZone)
.setIngestPipeline(FileStructureUtils.makeIngestPipelineDefinition(null, Collections.emptyMap(), csvProcessorSettings,
mappings, timeField.v1(), timeField.v2().getJavaTimestampFormats(), needClientTimeZone,
fieldMappings, timeField.v1(), timeField.v2().getJavaTimestampFormats(), needClientTimeZone,
timeField.v2().needNanosecondPrecision()))
.setMultilineStartPattern(makeMultilineStartPattern(explanation, columnNamesList, maxLinesPerMessage, delimiterPattern,
quotePattern, mappings, timeField.v1(), timeField.v2()));
quotePattern, fieldMappings, timeField.v1(), timeField.v2()));

mappings.put(FileStructureUtils.DEFAULT_TIMESTAMP_FIELD, timeField.v2().getEsDateMappingTypeWithoutFormat());
fieldMappings.put(FileStructureUtils.DEFAULT_TIMESTAMP_FIELD, timeField.v2().getEsDateMappingTypeWithoutFormat());
} else {
structureBuilder.setIngestPipeline(FileStructureUtils.makeIngestPipelineDefinition(null, Collections.emptyMap(),
csvProcessorSettings, mappings, null, null, false, false));
csvProcessorSettings, fieldMappings, null, null, false, false));
structureBuilder.setMultilineStartPattern(makeMultilineStartPattern(explanation, columnNamesList, maxLinesPerMessage,
delimiterPattern, quotePattern, mappings, null, null));
delimiterPattern, quotePattern, fieldMappings, null, null));
}

if (mappingsAndFieldStats.v2() != null) {
structureBuilder.setFieldStats(mappingsAndFieldStats.v2());
}

FileStructure structure = structureBuilder
.setMappings(mappings)
.setMappings(Collections.singletonMap(FileStructureUtils.MAPPING_PROPERTIES_SETTING, fieldMappings))
.setExplanation(explanation)
.build();

Expand Down Expand Up @@ -628,7 +628,7 @@ static Map<String, Object> makeCsvProcessorSettings(String field, List<String> t
* records.
*/
static String makeMultilineStartPattern(List<String> explanation, List<String> columnNames, int maxLinesPerMessage,
String delimiterPattern, String quotePattern, Map<String, Object> mappings,
String delimiterPattern, String quotePattern, Map<String, Object> fieldMappings,
String timeFieldName, TimestampFormatFinder timeFieldFormat) {

assert columnNames.isEmpty() == false;
Expand All @@ -653,7 +653,7 @@ static String makeMultilineStartPattern(List<String> explanation, List<String> c
explanation.add("Created a multi-line start pattern based on timestamp column [" + columnName + "]");
return builder.toString();
}
Object columnMapping = mappings.get(columnName);
Object columnMapping = fieldMappings.get(columnName);
if (columnMapping instanceof Map) {
String type = (String) ((Map<?, ?>) columnMapping).get(FileStructureUtils.MAPPING_TYPE_SETTING);
if (type != null) {
Expand Down
1 change: 1 addition & 0 deletions ...n/ml/src/main/java/org/elasticsearch/xpack/ml/filestructurefinder/FileStructureUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -393,6 +393,7 @@ static boolean isMoreLikelyTextThanKeyword(String str) {
* @param csvProcessorSettings The CSV processor settings for delimited formats. <code>null</code> for
* non-delimited formats.
* @param mappingsForConversions Mappings (or partial mappings) that will be considered for field type conversions.
* The keys in the map are the top level field names - there is no properties layer.
* @param timestampField The input field containing the timestamp to be parsed into <code>@timestamp</code>.
* <code>null</code> if there is no timestamp.
* @param timestampFormats Timestamp formats to be used for parsing {@code timestampField}.
Expand Down
6 changes: 3 additions & 3 deletions ...c/main/java/org/elasticsearch/xpack/ml/filestructurefinder/NdJsonFileStructureFinder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,17 +71,17 @@ static NdJsonFileStructureFinder makeNdJsonFileStructureFinder(List<String> expl
Tuple<SortedMap<String, Object>, SortedMap<String, FieldStats>> mappingsAndFieldStats =
FileStructureUtils.guessMappingsAndCalculateFieldStats(explanation, sampleRecords, timeoutChecker);

Map<String, Object> mappings = mappingsAndFieldStats.v1();
Map<String, Object> fieldMappings = mappingsAndFieldStats.v1();
if (timeField != null) {
mappings.put(FileStructureUtils.DEFAULT_TIMESTAMP_FIELD, timeField.v2().getEsDateMappingTypeWithoutFormat());
fieldMappings.put(FileStructureUtils.DEFAULT_TIMESTAMP_FIELD, timeField.v2().getEsDateMappingTypeWithoutFormat());
}

if (mappingsAndFieldStats.v2() != null) {
structureBuilder.setFieldStats(mappingsAndFieldStats.v2());
}

FileStructure structure = structureBuilder
.setMappings(mappings)
.setMappings(Collections.singletonMap(FileStructureUtils.MAPPING_PROPERTIES_SETTING, fieldMappings))
.setExplanation(explanation)
.build();

Expand Down
14 changes: 7 additions & 7 deletions .../main/java/org/elasticsearch/xpack/ml/filestructurefinder/TextLogFileStructureFinder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,15 +109,15 @@ static TextLogFileStructureFinder makeTextLogFileStructureFinder(List<String> ex
.setMultilineStartPattern(multiLineRegex);

Map<String, String> messageMapping = Collections.singletonMap(FileStructureUtils.MAPPING_TYPE_SETTING, "text");
SortedMap<String, Object> mappings = new TreeMap<>();
mappings.put("message", messageMapping);
mappings.put(FileStructureUtils.DEFAULT_TIMESTAMP_FIELD, timestampFormatFinder.getEsDateMappingTypeWithoutFormat());
SortedMap<String, Object> fieldMappings = new TreeMap<>();
fieldMappings.put("message", messageMapping);
fieldMappings.put(FileStructureUtils.DEFAULT_TIMESTAMP_FIELD, timestampFormatFinder.getEsDateMappingTypeWithoutFormat());

SortedMap<String, FieldStats> fieldStats = new TreeMap<>();
fieldStats.put("message", FileStructureUtils.calculateFieldStats(messageMapping, sampleMessages, timeoutChecker));

Map<String, String> customGrokPatternDefinitions = timestampFormatFinder.getCustomGrokPatternDefinitions();
GrokPatternCreator grokPatternCreator = new GrokPatternCreator(explanation, sampleMessages, mappings, fieldStats,
GrokPatternCreator grokPatternCreator = new GrokPatternCreator(explanation, sampleMessages, fieldMappings, fieldStats,
customGrokPatternDefinitions, timeoutChecker);
// We can't parse directly into @timestamp using Grok, so parse to some other time field, which the date filter will then remove
String interimTimestampField = overrides.getTimestampField();
Expand Down Expand Up @@ -150,10 +150,10 @@ static TextLogFileStructureFinder makeTextLogFileStructureFinder(List<String> ex
.setJavaTimestampFormats(timestampFormatFinder.getJavaTimestampFormats())
.setNeedClientTimezone(needClientTimeZone)
.setGrokPattern(grokPattern)
.setIngestPipeline(FileStructureUtils.makeIngestPipelineDefinition(grokPattern, customGrokPatternDefinitions, null, mappings,
interimTimestampField, timestampFormatFinder.getJavaTimestampFormats(), needClientTimeZone,
.setIngestPipeline(FileStructureUtils.makeIngestPipelineDefinition(grokPattern, customGrokPatternDefinitions, null,
fieldMappings, interimTimestampField, timestampFormatFinder.getJavaTimestampFormats(), needClientTimeZone,
timestampFormatFinder.needNanosecondPrecision()))
.setMappings(mappings)
.setMappings(Collections.singletonMap(FileStructureUtils.MAPPING_PROPERTIES_SETTING, fieldMappings))
.setFieldStats(fieldStats)
.setExplanation(explanation)
.build();
Expand Down
12 changes: 6 additions & 6 deletions .../src/main/java/org/elasticsearch/xpack/ml/filestructurefinder/XmlFileStructureFinder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,18 +114,18 @@ static XmlFileStructureFinder makeXmlFileStructureFinder(List<String> explanatio
structureBuilder.setFieldStats(mappingsAndFieldStats.v2());
}

Map<String, Object> innerMappings = mappingsAndFieldStats.v1();
Map<String, Object> innerFieldMappings = mappingsAndFieldStats.v1();
Map<String, Object> secondLevelProperties = new LinkedHashMap<>();
secondLevelProperties.put(FileStructureUtils.MAPPING_TYPE_SETTING, "object");
secondLevelProperties.put(FileStructureUtils.MAPPING_PROPERTIES_SETTING, innerMappings);
SortedMap<String, Object> outerMappings = new TreeMap<>();
outerMappings.put(topLevelTag, secondLevelProperties);
secondLevelProperties.put(FileStructureUtils.MAPPING_PROPERTIES_SETTING, innerFieldMappings);
SortedMap<String, Object> outerFieldMappings = new TreeMap<>();
outerFieldMappings.put(topLevelTag, secondLevelProperties);
if (timeField != null) {
outerMappings.put(FileStructureUtils.DEFAULT_TIMESTAMP_FIELD, timeField.v2().getEsDateMappingTypeWithoutFormat());
outerFieldMappings.put(FileStructureUtils.DEFAULT_TIMESTAMP_FIELD, timeField.v2().getEsDateMappingTypeWithoutFormat());
}

FileStructure structure = structureBuilder
.setMappings(outerMappings)
.setMappings(Collections.singletonMap(FileStructureUtils.MAPPING_PROPERTIES_SETTING, outerFieldMappings))
.setExplanation(explanation)
.build();

Expand Down
Loading