├── .gitignore ├── LICENSE.txt ├── README.md ├── pom.xml └── src └── main ├── java └── com │ └── lucidworks │ └── dq │ ├── data │ ├── DateChecker.java │ ├── DeleteByIds.java │ ├── DocCount.java │ ├── DumpIds.java │ ├── EmptyFieldStats.java │ ├── SolrToCsv.java │ ├── SolrToSolr.java │ ├── TermCodepointStats.java │ ├── TermStats.java │ └── TestArgs.java │ ├── diff │ ├── DiffEmptyFieldStats.java │ ├── DiffIds.java │ ├── DiffSchema.java │ └── DiffSolrConfig.java │ ├── logs │ ├── LogEntry.java │ ├── LogEntryBase.java │ ├── LogEntryFromSolr.java │ ├── LogEntryGroup.java │ ├── LogEntryGroupFromSolr.java │ ├── LogEntryReference.java │ ├── LogEntryReferenceBase.java │ ├── LogFile.java │ ├── LogFileBase.java │ ├── LogFileFromSolr.java │ ├── LogFileRepo.java │ └── LogFileRepoBase.java │ ├── schema │ ├── Schema.java │ ├── SchemaBase.java │ ├── SchemaFromLocalCore_broken.java │ ├── SchemaFromRest.java │ ├── SchemaFromRestAdHock.java │ ├── SchemaFromXml.java │ ├── SchemalessPlus.java │ ├── SolrConfig.java │ ├── SolrConfigBase.java │ └── SolrConfigFromXml.java │ ├── util │ ├── CharUtils.java │ ├── CmdLineLauncher.java │ ├── DateUtils.java │ ├── HasDescription.java │ ├── HashAndShard.java │ ├── IO_Utils.java │ ├── LLR.java │ ├── LLR.java-new │ ├── SetUtils.java │ ├── SolrUtils.java │ ├── StatsUtils.java │ ├── StringUtils.java │ └── TupleEntropy.java │ └── zk_experiment │ └── ZkSmartClient.java └── resources ├── DQ-Prototype-and-SolrJ.key ├── DQ-Prototype-and-SolrJ.pdf ├── sample-reports ├── README.txt ├── dates-curve-fitting.txt ├── llr-larger-sample.txt ├── llr-tiny-sample.txt ├── populated-fields-diff.txt ├── populated-fields-single-extended-options.txt ├── populated-fields-single.txt ├── report-terms-via-termsReqHandler.txt ├── schema-info-diff.txt ├── schema-info-single.txt ├── term-counts.txt ├── term-lengths.txt ├── unicode-format1.txt └── unicode-format2.txt ├── schema-461.xml └── schema-481.xml /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/LICENSE.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/README.md -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/pom.xml -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/data/DateChecker.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/data/DateChecker.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/data/DeleteByIds.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/data/DeleteByIds.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/data/DocCount.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/data/DocCount.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/data/DumpIds.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/data/DumpIds.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/data/EmptyFieldStats.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/data/EmptyFieldStats.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/data/SolrToCsv.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/data/SolrToCsv.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/data/SolrToSolr.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/data/SolrToSolr.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/data/TermCodepointStats.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/data/TermCodepointStats.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/data/TermStats.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/data/TermStats.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/data/TestArgs.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/data/TestArgs.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/diff/DiffEmptyFieldStats.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/diff/DiffEmptyFieldStats.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/diff/DiffIds.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/diff/DiffIds.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/diff/DiffSchema.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/diff/DiffSchema.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/diff/DiffSolrConfig.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/diff/DiffSolrConfig.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogEntry.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogEntry.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogEntryBase.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogEntryBase.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogEntryFromSolr.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogEntryFromSolr.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogEntryGroup.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogEntryGroup.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogEntryGroupFromSolr.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogEntryGroupFromSolr.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogEntryReference.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogEntryReference.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogEntryReferenceBase.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogEntryReferenceBase.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogFile.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogFile.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogFileBase.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogFileBase.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogFileFromSolr.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogFileFromSolr.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogFileRepo.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogFileRepo.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/logs/LogFileRepoBase.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/logs/LogFileRepoBase.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/schema/Schema.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/schema/Schema.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/schema/SchemaBase.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/schema/SchemaBase.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/schema/SchemaFromLocalCore_broken.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/schema/SchemaFromLocalCore_broken.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/schema/SchemaFromRest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/schema/SchemaFromRest.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/schema/SchemaFromRestAdHock.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/schema/SchemaFromRestAdHock.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/schema/SchemaFromXml.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/schema/SchemaFromXml.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/schema/SchemalessPlus.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/schema/SchemalessPlus.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/schema/SolrConfig.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/schema/SolrConfig.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/schema/SolrConfigBase.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/schema/SolrConfigBase.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/schema/SolrConfigFromXml.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/schema/SolrConfigFromXml.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/CharUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/CharUtils.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/CmdLineLauncher.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/CmdLineLauncher.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/DateUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/DateUtils.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/HasDescription.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/HasDescription.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/HashAndShard.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/HashAndShard.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/IO_Utils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/IO_Utils.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/LLR.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/LLR.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/LLR.java-new: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/LLR.java-new -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/SetUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/SetUtils.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/SolrUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/SolrUtils.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/StatsUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/StatsUtils.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/StringUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/StringUtils.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/util/TupleEntropy.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/util/TupleEntropy.java -------------------------------------------------------------------------------- /src/main/java/com/lucidworks/dq/zk_experiment/ZkSmartClient.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/java/com/lucidworks/dq/zk_experiment/ZkSmartClient.java -------------------------------------------------------------------------------- /src/main/resources/DQ-Prototype-and-SolrJ.key: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/DQ-Prototype-and-SolrJ.key -------------------------------------------------------------------------------- /src/main/resources/DQ-Prototype-and-SolrJ.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/DQ-Prototype-and-SolrJ.pdf -------------------------------------------------------------------------------- /src/main/resources/sample-reports/README.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/README.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/dates-curve-fitting.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/dates-curve-fitting.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/llr-larger-sample.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/llr-larger-sample.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/llr-tiny-sample.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/llr-tiny-sample.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/populated-fields-diff.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/populated-fields-diff.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/populated-fields-single-extended-options.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/populated-fields-single-extended-options.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/populated-fields-single.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/populated-fields-single.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/report-terms-via-termsReqHandler.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/report-terms-via-termsReqHandler.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/schema-info-diff.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/schema-info-diff.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/schema-info-single.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/schema-info-single.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/term-counts.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/term-counts.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/term-lengths.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/term-lengths.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/unicode-format1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/unicode-format1.txt -------------------------------------------------------------------------------- /src/main/resources/sample-reports/unicode-format2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/sample-reports/unicode-format2.txt -------------------------------------------------------------------------------- /src/main/resources/schema-461.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/schema-461.xml -------------------------------------------------------------------------------- /src/main/resources/schema-481.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucidworks/data-quality/HEAD/src/main/resources/schema-481.xml --------------------------------------------------------------------------------