elasticdump/elasticsearch-dump repository overview

npm install elasticdump
./bin/elasticdump

npm install elasticdump -g
elasticdump

# Copy an index from production to staging with analyzer and mapping:
elasticdump \
  --input=http://production.es.com:9200/my_index \
  --output=http://staging.es.com:9200/my_index \
  --type=analyzer
elasticdump \
  --input=http://production.es.com:9200/my_index \
  --output=http://staging.es.com:9200/my_index \
  --type=mapping
elasticdump \
  --input=http://production.es.com:9200/my_index \
  --output=http://staging.es.com:9200/my_index \
  --type=data

# Backup index data to a file:
elasticdump \
  --input=http://production.es.com:9200/my_index \
  --output=/data/my_index_mapping.json \
  --type=mapping
elasticdump \
  --input=http://production.es.com:9200/my_index \
  --output=/data/my_index.json \
  --type=data

# Backup and index to a gzip using stdout:
elasticdump \
  --input=http://production.es.com:9200/my_index \
  --output=$ \
  | gzip > /data/my_index.json.gz

# Backup the results of a query to a file
elasticdump \
  --input=http://production.es.com:9200/my_index \
  --output=query.json \
  --searchBody="{\"query\":{\"term\":{\"username\": \"admin\"}}}"
  
# Specify searchBody from a file
elasticdump \
  --input=http://production.es.com:9200/my_index \
  --output=query.json \
  --searchBody=@/data/searchbody.json  

# Copy a single shard data:
elasticdump \
  --input=http://es.com:9200/api \
  --output=http://es.com:9200/api2 \
  --input-params="{\"preference\":\"_shards:0\"}"

# Backup aliases to a file
elasticdump \
  --input=http://es.com:9200/index-name/alias-filter \
  --output=alias.json \
  --type=alias

# Import aliases into ES
elasticdump \
  --input=./alias.json \
  --output=http://es.com:9200 \
  --type=alias

# Backup templates to a file
elasticdump \
  --input=http://es.com:9200/template-filter \
  --output=templates.json \
  --type=template

# Import templates into ES
elasticdump \
  --input=./templates.json \
  --output=http://es.com:9200 \
  --type=template

# Split files into multiple parts
elasticdump \
  --input=http://production.es.com:9200/my_index \
  --output=/data/my_index.json \
  --fileSize=10mb

# Import data from S3 into ES (using s3urls)
elasticdump \
  --s3AccessKeyId "${access_key_id}" \
  --s3SecretAccessKey "${access_key_secret}" \
  --input "s3://${bucket_name}/${file_name}.json" \
  --output=http://production.es.com:9200/my_index

# Export ES data to S3 (using s3urls)
elasticdump \
  --s3AccessKeyId "${access_key_id}" \
  --s3SecretAccessKey "${access_key_secret}" \
  --input=http://production.es.com:9200/my_index \
  --output "s3://${bucket_name}/${file_name}.json"

# Import data from MINIO (s3 compatible) into ES (using s3urls)
elasticdump \
  --s3AccessKeyId "${access_key_id}" \
  --s3SecretAccessKey "${access_key_secret}" \
  --input "s3://${bucket_name}/${file_name}.json" \
  --output=http://production.es.com:9200/my_index
  --s3ForcePathStyle true
  --s3Endpoint https://production.minio.co

# Export ES data to MINIO (s3 compatible) (using s3urls)
elasticdump \
  --s3AccessKeyId "${access_key_id}" \
  --s3SecretAccessKey "${access_key_secret}" \
  --input=http://production.es.com:9200/my_index \
  --output "s3://${bucket_name}/${file_name}.json"
  --s3ForcePathStyle true
  --s3Endpoint https://production.minio.co

# Import data from CSV file into ES (using csvurls)
elasticdump \
  # csv:// prefix must be included to allow parsing of csv files
  # --input "csv://${file_path}.csv" \
  --input "csv:///data/cars.csv"
  --output=http://production.es.com:9200/my_index \
  --csvSkipRows 1    # used to skip parsed rows (this does not include the headers row)
  --csvDelimiter ";" # default csvDelimiter is ','

# Copy a single index from a elasticsearch:
elasticdump \
  --input=http://es.com:9200/api/search \
  --input-index=my_index \
  --output=http://es.com:9200/api/search \
  --output-index=my_index \
  --type=mapping

# Copy a single type:
elasticdump \
  --input=http://es.com:9200/api/search \
  --input-index=my_index/my_type \
  --output=http://es.com:9200/api/search \
  --output-index=my_index \
  --type=mapping

docker pull elasticdump/elasticsearch-dump

# Copy an index from production to staging with mappings:
docker run --rm -ti elasticdump/elasticsearch-dump \
  --input=http://production.es.com:9200/my_index \
  --output=http://staging.es.com:9200/my_index \
  --type=mapping
docker run --rm -ti elasticdump/elasticsearch-dump \
  --input=http://production.es.com:9200/my_index \
  --output=http://staging.es.com:9200/my_index \
  --type=data

# Backup index data to a file:
docker run --rm -ti -v /data:/tmp elasticdump/elasticsearch-dump \
  --input=http://production.es.com:9200/my_index \
  --output=/tmp/my_index_mapping.json \
  --type=data

docker run --net=host --rm -ti elasticdump/elasticsearch-dump \
  --input=http://staging.es.com:9200/my_index \
  --output=http://localhost:9200/my_index \
  --type=data

while read LINE; do jsonlint-py "${LINE}" ; done < dump.data.json

elasticdump: Import and export tools for elasticsearch
version: %%version%%

Usage: elasticdump --input SOURCE --output DESTINATION [OPTIONS]

--input
                    Source location (required)
--input-index
                    Source index and type
                    (default: all, example: index/type)
--output
                    Destination location (required)
--output-index
                    Destination index and type
                    (default: all, example: index/type)
--overwrite
                    Overwrite output file if it exists
                    (default: false)                    
--limit
                    How many objects to move in batch per operation
                    limit is approximate for file streams
                    (default: 100)
--size
                    How many objects to retrieve
                    (default: -1 -> no limit)
--concurrency
                    The maximum number of requests the can be made concurrently to a specified transport.
                    (default: 1)       
--concurrencyInterval
                    The length of time in milliseconds in which up to <intervalCap> requests can be made
                    before the interval request count resets. Must be finite.
                    (default: 5000)       
--intervalCap
                    The maximum number of transport requests that can be made within a given <concurrencyInterval>.
                    (default: 5)
--carryoverConcurrencyCount
                    If true, any incomplete requests from a <concurrencyInterval> will be carried over to
                    the next interval, effectively reducing the number of new requests that can be created
                    in that next interval.  If false, up to <intervalCap> requests can be created in the
                    next interval regardless of the number of incomplete requests from the previous interval.
                    (default: true)                                                                                       
--throttleInterval
                    Delay in milliseconds between getting data from an inputTransport and sending it to an
                    outputTransport.
                     (default: 1)
--debug
                    Display the elasticsearch commands being used
                    (default: false)
--quiet
                    Suppress all messages except for errors
                    (default: false)
--type
                    What are we exporting?
                    (default: data, options: [settings, analyzer, data, mapping, policy, alias, template, component_template, index_template])
--filterSystemTemplates
                    Whether to remove metrics-*-* and logs-*-* system templates 
                    (default: true])
--templateRegex
                    Regex used to filter templates before passing to the output transport 
                    (default: ((metrics|logs|\\..+)(-.+)?)
--delete
                    Delete documents one-by-one from the input as they are
                    moved.  Will not delete the source index
                    (default: false)
--searchBody
                    Preform a partial extract based on search results
                    when ES is the input, default values are
                      if ES > 5
                        `'{"query": { "match_all": {} }, "stored_fields": ["*"], "_source": true }'`
                      else
                        `'{"query": { "match_all": {} }, "fields": ["*"], "_source": true }'`
                    [As of 6.68.0] If the searchBody is preceded by a @ symbol, elasticdump will perform a file lookup
                    in the location specified. NB: File must contain valid JSON
--searchWithTemplate
                    Enable to use Search Template when using --searchBody
                    If using Search Template then searchBody has to consist of "id" field and "params" objects
                    If "size" field is defined within Search Template, it will be overridden by --size parameter
                    See https://www.elastic.co/guide/en/elasticsearch/reference/current/search-template.html for 
                    further information
                    (default: false)
--searchBodyTemplate
                    A method/function which can be called to the searchBody
                        doc.searchBody = { query: { match_all: {} }, stored_fields: [], _source: true };
                    May be used multiple times.
                    Additionally, searchBodyTemplate may be performed by a module. See [searchBody Template](#search-template) below.
--headers
                    Add custom headers to Elastisearch requests (helpful when
                    your Elasticsearch instance sits behind a proxy)
                    (default: '{"User-Agent": "elasticdump"}')
                    Type/direction based headers are supported .i.e. input-headers/output-headers 
                    (these will only be added based on the current flow type input/output)
--params
                    Add custom parameters to Elastisearch requests uri. Helpful when you for example
                    want to use elasticsearch preference
                    
                    --input-params is a specific params extension that can be used when fetching data with the scroll api
                    --output-params is a specific params extension that can be used when indexing data with the bulk index api
                    NB : These were added to avoid param pollution problems which occur when an input param is used in an output source
                    (default: null)
--sourceOnly
                    Output only the json contained within the document _source
                    Normal: {"_index":"","_type":"","_id":"", "_source":{SOURCE}}
                    sourceOnly: {SOURCE}
                    (default: false)
--ignore-errors
                    Will continue the read/write loop on write error
                    (default: false)
--scrollId
                    The last scroll Id returned from elasticsearch. 
                    This will allow dumps to be resumed used the last scroll Id &
                    `scrollTime` has not expired.
--scrollTime
                    Time the nodes will hold the requested search in order.
                    (default: 10m)
                    
--scroll-with-post
                    Use a HTTP POST method to perform scrolling instead of the default GET
                    (default: false)
                    
--maxSockets
                    How many simultaneous HTTP requests can we process make?
                    (default:
                      5 [node <= v0.10.x] /
                      Infinity [node >= v0.11.x] )
--timeout
                    Integer containing the number of milliseconds to wait for
                    a request to respond before aborting the request. Passed
                    directly to the request library. Mostly used when you don't
                    care too much if you lose some data when importing
                    but rather have speed.
--offset
                    Integer containing the number of rows you wish to skip
                    ahead from the input transport.  When importing a large
                    index, things can go wrong, be it connectivity, crashes,
                    someone forgets to `screen`, etc.  This allows you
                    to start the dump again from the last known line written
                    (as logged by the `offset` in the output).  Please be
                    advised that since no sorting is specified when the
                    dump is initially created, there's no real way to
                    guarantee that the skipped rows have already been
                    written/parsed.  This is more of an option for when
                    you want to get most data as possible in the index
                    without concern for losing some rows in the process,
                    similar to the `timeout` option.
                    (default: 0)
--noRefresh
                    Disable input index refresh.
                    Positive:
                      1. Much increase index speed
                      2. Much less hardware requirements
                    Negative:
                      1. Recently added data may not be indexed
                    Recommended using with big data indexing,
                    where speed and system health in a higher priority
                    than recently added data.
--inputTransport
                    Provide a custom js file to use as the input transport
--outputTransport
                    Provide a custom js file to use as the output transport
--toLog
                    When using a custom outputTransport, should log lines
                    be appended to the output stream?
                    (default: true, except for `$`)
--transform
                    A method/function which can be called to modify documents
                    before writing to a destination. A global variable 'doc'
                    is available.
                    Example script for computing a new field 'f2' as doubled
                    value of field 'f1':
                        doc._source["f2"] = doc._source.f1 * 2;
                    May be used multiple times.
                    Additionally, transform may be performed by a module. See [Module Transform](#module-transform) below.
--awsChain
                    Use [standard](https://aws.amazon.com/blogs/security/a-new-and-standardized-way-to-manage-credentials-in-the-aws-sdks/) location and ordering for resolving credentials including environment variables, config files, EC2 and ECS metadata locations
                    _Recommended option for use with AWS_
                    Use [standard](https://aws.amazon.com/blogs/security/a-new-and-standardized-way-to-manage-credentials-in-the-aws-sdks/) 
                    location and ordering for resolving credentials including environment variables, 
                    config files, EC2 and ECS metadata locations _Recommended option for use with AWS_
--awsAccessKeyId
--awsSecretAccessKey
                    When using Amazon Elasticsearch Service protected by
                    AWS Identity and Access Management (IAM), provide
                    your Access Key ID and Secret Access Key.
                    --sessionToken can also be optionally provided if using temporary credentials
--awsIniFileProfile
                    Alternative to --awsAccessKeyId and --awsSecretAccessKey,
                    loads credentials from a specified profile in aws ini file.
                    For greater flexibility, consider using --awsChain
                    and setting AWS_PROFILE and AWS_CONFIG_FILE
                    environment variables to override defaults if needed
--awsIniFileName
                    Override the default aws ini file name when using --awsIniFileProfile
                    Filename is relative to ~/.aws/
                    (default: config)
--awsService
                    Sets the AWS service that the signature will be generated for
                    (default: calculated from hostname or host)
--awsRegion
                    Sets the AWS region that the signature will be generated for
                    (default: calculated from hostname or host)
--awsUrlRegex
                    Overrides the default regular expression that is used to validate AWS urls that should be signed
                    (default: ^https?:\/\/.*\.amazonaws\.com.*$)
--support-big-int   
                    Support big integer numbers
--big-int-fields   
                    Sepcifies a comma-seperated list of fields that should be checked for big-int support
                    (default '')
--retryAttempts  
                    Integer indicating the number of times a request should be automatically re-attempted before failing
                    when a connection fails with one of the following errors `ECONNRESET`, `ENOTFOUND`, `ESOCKETTIMEDOUT`,
                    ETIMEDOUT`, `ECONNREFUSED`, `EHOSTUNREACH`, `EPIPE`, `EAI_AGAIN`
                    (default: 0)
                    
--retryDelay   
                    Integer indicating the back-off/break period between retry attempts (milliseconds)
                    (default : 5000)            
--parseExtraFields
                    Comma-separated list of meta-fields to be parsed  
--maxRows
                    supports file splitting.  Files are split by the number of rows specified
--fileSize
                    supports file splitting.  This value must be a string supported by the **bytes** module.     
                    The following abbreviations must be used to signify size in terms of units         
                    b for bytes
                    kb for kilobytes
                    mb for megabytes
                    gb for gigabytes
                    tb for terabytes
                    
                    e.g. 10mb / 1gb / 1tb
                    Partitioning helps to alleviate overflow/out of memory exceptions by efficiently segmenting files
                    into smaller chunks that then be merged if needs be.
--fsCompress
                    gzip data before sending output to file.
                    On import the command is used to inflate a gzipped file
--s3AccessKeyId
                    AWS access key ID
--s3SecretAccessKey
                    AWS secret access key
--s3Region
                    AWS region
--s3Endpoint        
                    AWS endpoint can be used for AWS compatible backends such as
                    OpenStack Swift and OpenStack Ceph
--s3SSLEnabled      
                    Use SSL to connect to AWS [default true]
                    
--s3ForcePathStyle  Force path style URLs for S3 objects [default false]
                    
--s3Compress
                    gzip data before sending to s3  
--s3ServerSideEncryption
                    Enables encrypted uploads
--s3SSEKMSKeyId
                    KMS Id to be used with aws:kms uploads                    
--s3ACL
                    S3 ACL: private | public-read | public-read-write | authenticated-read | aws-exec-read |
                    bucket-owner-read | bucket-owner-full-control [default private]
--s3StorageClass
                    Set the Storage Class used for s3
                    (default: STANDARD)   
--s3Options
                    Set all s3 parameters shown here https://docs.aws.amazon.com/AWSJavaScriptSDK/latest/AWS/S3.html#createMultipartUpload-property
                    A escaped JSON string or file can be supplied. File location must be prefixed with the @ symbol
                    (default: null)
--s3Configs
                    Set all s3 constructor configurations
                    A escaped JSON string or file can be supplied. File location must be prefixed with the @ symbol
                    (default: null)
--retryDelayBase
                    The base number of milliseconds to use in the exponential backoff for operation retries. (s3)
--customBackoff
                    Activate custom customBackoff function. (s3)
--tlsAuth
                    Enable TLS X509 client authentication
--cert, --input-cert, --output-cert
                    Client certificate file. Use --cert if source and destination are identical.
                    Otherwise, use the one prefixed with --input or --output as needed.
--key, --input-key, --o