> ## Documentation Index > Fetch the complete documentation index at: https://doc.lucidworks.com/llms.txt > Use this file to discover all available pages before exploring further. # HDFS V1 > The HDFS V1 connector traverses the Hadoop Distributed File System (HDFS) as it would a regular Unix filesystem. export const schema = { "type": "object", "title": "HDFS", "description": "Connector for HDFS or similar Hadoop filesystems.", "required": ["id", "connector", "type", "pipeline", "properties"], "properties": { "category": { "type": "string", "title": "Category", "default": "Filesystem", "hints": ["hidden", "readonly"] }, "id": { "type": "string", "title": "Datasource ID", "description": "Unique name for this datasource.", "minLength": 1, "pattern": "^[a-zA-Z0-9_-]+$" }, "connector": { "type": "string", "title": "Connector Type", "description": "Connector Type.", "hints": ["hidden"], "minLength": 1 }, "type": { "type": "string", "title": "Datasource Type", "description": "Datasource type supported by the selected connector type.", "hints": ["hidden"], "minLength": 1 }, "pipeline": { "type": "string", "title": "Pipeline ID", "description": "Name of an existing index pipeline for processing documents.", "minLength": 1 }, "description": { "type": "string", "title": "Description", "description": "Optional description for this datasource." }, "type_description": { "type": "string", "title": "Type Description", "default": "Connector for HDFS or similar Hadoop filesystems.", "hints": ["hidden", "readonly"] }, "parserId": { "type": "string", "title": "Parser", "description": "Parser used when parsing raw content. For some connectors, a configuration to 'retry' parsing if an error occurs is available as an advanced setting" }, "properties": { "type": "object", "title": "Properties", "description": "Datasource configuration properties", "required": ["url"], "properties": { "collection": { "type": "string", "title": "Collection", "description": "Collection documents will be indexed to.", "hints": ["hidden"], "pattern": "^[a-zA-Z0-9_-]+$" }, "db": { "type": "object", "title": "Connector DB", "description": "Type and properties for a ConnectorDB implementation to use with this datasource.", "required": ["type"], "properties": { "type": { "type": "string", "title": "Implementation Class Name", "description": "Fully qualified class name of ConnectorDb implementation.", "default": "com.lucidworks.connectors.db.impl.MapDbConnectorDb", "minLength": 1 }, "inlinks": { "type": "boolean", "title": "Process Inlinks?", "description": "Keep track of incoming links. This negatively impacts performance and size of DB.", "default": false }, "aliases": { "type": "boolean", "title": "Process Aliases?", "description": "Keep track of original URI-s that resolved to the current URI. This negatively impacts performance and size of DB.", "default": false }, "inv_aliases": { "type": "boolean", "title": "Process Inverted Aliases?", "description": "Keep track of target URI-s that the current URI resolves to. This negatively impacts performance and size of DB.", "default": false } }, "hints": ["hidden"] }, "url": { "type": "string", "title": "Start link", "description": "The start link is the URI for the HDFS connector. The `namenode` is 8020 by default, e.g., hdfs://hmbrnasnfs2.highmark.com:8020/datalake/hm/phi/refined/UnstructuredData/NEPA", "minLength": 1, "pattern": ".*:.*" }, "max_docs": { "type": "integer", "title": "Max items", "description": "Maximum number of documents to fetch. The default (-1) means no limit.", "default": -1, "minimum": -1, "exclusiveMinimum": false }, "max_bytes": { "type": "integer", "title": "Maximum file size (bytes)", "description": "Maximum size (in bytes) of documents to fetch or -1 for unlimited file size.", "default": 10485760, "minimum": -1, "exclusiveMinimum": false }, "index_directories": { "type": "boolean", "title": "Index directories", "description": "Set to true to add directories to the index as documents. If set to false, directories will not be added to the index, but they will still be traversed for documents.", "default": false }, "max_threads": { "type": "integer", "title": "Fetch threads", "description": "The maximum number of threads to use for fetching data. Note: Each thread will create a new connection to the repository, which may make overall throughput faster, but this also requires more system resources, including CPU and memory.", "default": 1, "hints": ["advanced"] }, "add_failed_docs": { "type": "boolean", "title": "Add failed documents", "description": "Set to true to add documents even if they partially fail processing. Failed documents will be added with as much metadata as available, but may not include all expected fields.", "default": false, "hints": ["advanced"] }, "crawl_item_timeout": { "type": "integer", "title": "Fetch timeout", "description": "Time in milliseconds to fetch any individual document.", "default": 600000, "hints": ["advanced"], "minimum": 0, "exclusiveMinimum": true }, "maximum_connections": { "type": "integer", "title": "Maximum fetch connections", "description": "Maximum number of concurrent connections to the filesystem. A large number of documents could cause a large number of simultaneous connections to the repository and lead to errors or degraded performance. In some cases, reducing this number may help performance issues.", "default": 1000, "hints": ["advanced"] }, "initial_mapping": { "type": "object", "title": "Initial field mapping", "description": "Provides mapping of fields before documents are sent to an index pipeline.", "properties": { "skip": { "type": "boolean", "title": "Skip This Stage", "description": "Set to true to skip this stage.", "default": false, "hints": ["advanced"] }, "label": { "type": "string", "title": "Label", "description": "A unique label for this stage.", "hints": ["advanced"], "maxLength": 255 }, "condition": { "type": "string", "title": "Condition", "description": "Define a conditional script that must result in true or false. This can be used to determine if the stage should process or not.", "hints": ["code", "code/javascript", "advanced"] }, "reservedFieldsMappingAllowed": { "type": "boolean", "title": "Allow System Fields Mapping?", "default": false, "hints": ["advanced"] }, "retentionMappings": { "type": "array", "title": "Field Retention", "description": "Fields that should be kept or deleted", "default": [], "hints": ["advanced"], "items": { "type": "object", "required": ["field"], "properties": { "field": { "type": "string", "title": "Field", "description": "The name of the field to operate on.", "hints": ["advanced"] }, "operation": { "type": "string", "title": "Operation", "description": "The type of operation to perform: keep (default) or delete", "enum": ["keep", "delete"], "default": "keep", "hints": ["advanced"] } } } }, "updateMappings": { "type": "array", "title": "Field Value Updates", "description": "Values that should be added to or set on a field. When a value is added, any values previously on the field will be retained. When a value is set, any values previously on the field will be overwritten.", "default": [], "hints": ["advanced"], "items": { "type": "object", "required": ["field", "value"], "properties": { "field": { "type": "string", "title": "Field", "description": "The name of the field to operate on.", "hints": ["advanced"] }, "value": { "type": "string", "title": "Value", "description": "The value to add to or set on the field.", "hints": ["advanced"] }, "operation": { "type": "string", "title": "Operation", "description": "The type of operation to perform: add (default) or set.", "enum": ["add", "set"], "default": "add", "hints": ["advanced"] } } } }, "translationMappings": { "type": "array", "title": "Field Translations", "description": "Fields that should be moved or copied to another field. When a field is moved, the values from the source field are moved over to the target field and the source field is removed. When a field is copied, the values from the source field are copied over to the target field and the source field is retained.", "default": [{ "source": "fetch_time", "target": "fetch_time_dt", "operation": "move" }, { "source": "ds:description", "target": "description", "operation": "move" }], "hints": ["advanced"], "items": { "type": "object", "required": ["source", "target"], "properties": { "source": { "type": "string", "title": "Source Field", "description": "The name of the field to operate on.", "hints": ["advanced"] }, "target": { "type": "string", "title": "Target Field", "description": "The name of the target field.", "hints": ["advanced"] }, "operation": { "type": "string", "title": "Operation", "description": "The type of operation to perform: copy (default) or move.", "enum": ["copy", "move"], "default": "copy", "hints": ["advanced"] } } } }, "unmappedRule": { "type": "object", "title": "Unmapped Fields", "description": "Fields not mapped by the above rules. By default, any remaining fields will be kept on the document.", "properties": { "keep": { "type": "boolean", "title": "Keep", "description": "Keep all unmapped fields", "default": true, "hints": ["advanced"] }, "delete": { "type": "boolean", "title": "Delete", "description": "Delete all unmapped fields", "default": false, "hints": ["advanced"] }, "fieldToMoveValuesTo": { "type": "string", "title": "Move", "description": "Move all unmapped field values to this field", "hints": ["advanced"] }, "fieldToCopyValuesTo": { "type": "string", "title": "Copy", "description": "Copy all unmapped field values to this field", "hints": ["advanced"] }, "valueToAddToUnmappedFields": { "type": "string", "title": "Add", "description": "Add this value to all unmapped fields", "hints": ["advanced"] }, "valueToSetOnUnmappedFields": { "type": "string", "title": "Set", "description": "Set this value on all unmapped fields", "hints": ["advanced"] } }, "default": { "keep": true, "delete": false, "fieldToMoveValuesTo": "", "fieldToCopyValuesTo": "", "valueToAddToUnmappedFields": "", "valueToSetOnUnmappedFields": "" } } }, "category": "Field Transformation", "categoryPriority": 7, "hints": ["advanced"], "unsafe": false }, "converter": { "type": "string", "title": "Converter", "description": "Fully-qualified classname for a custom converter to produce valid SolrInputDocuments extracted from Hadoop Sequence or MapReduce files.", "hints": ["advanced"] }, "with_kerberos": { "type": "boolean", "title": "Use Kerberos Authentication", "description": "Set to true to use Kerberos to authenticate to HDFS for access to the content.", "default": false, "hints": ["advanced"] }, "kerberos_user": { "type": "string", "title": "Kerberos principal", "description": "Kerberos principal name, i.e., 'username@YOUR-REALM.COM'.", "hints": ["advanced"] }, "kerberos_keytab": { "type": "string", "title": "Kerberos keytab", "description": "Full path to the Kerberos keytab file.", "hints": ["advanced"] }, "crawl_depth": { "type": "integer", "title": "Max crawl depth", "description": "Number of levels in a directory or site tree to descend for documents.", "default": -1, "minimum": -1, "exclusiveMinimum": false }, "bounds": { "type": "string", "title": "Crawl bounds", "description": "Limits the crawl to a specific directory sub-tree, hostname or domain.", "enum": ["tree", "host", "domain", "none"], "default": "tree" }, "include_paths": { "type": "array", "title": "Inclusive regexes", "description": "Regular expressions for URI patterns to include. This will limit this datasource to only URIs that match the regular expression.", "items": { "type": "string" } }, "exclude_paths": { "type": "array", "title": "Exclusive regexes", "description": "Regular expressions for URI patterns to exclude. This will limit this datasource to only URIs that do not match the regular expression.", "items": { "type": "string" } }, "include_extensions": { "type": "array", "title": "Included file extensions", "description": "List the file extensions to be fetched. Note: Files with possible matching MIME types but non-matching file extensions will be skipped. Extensions should be listed without periods, using whitespace to separate items (e.g., 'pdf zip').", "items": { "type": "string" } }, "commit_on_finish": { "type": "boolean", "title": "Solr commit on finish", "description": "Set to true for a request to be sent to Solr after the last batch has been fetched to commit the documents to the index.", "default": true, "hints": ["advanced"] }, "verify_access": { "type": "boolean", "title": "Validate access", "description": "Set to true to require successful connection to the filesystem before saving this datasource.", "default": true, "hints": ["advanced"] } }, "propertyGroups": [{ "label": "Kerberos Authentication", "properties": ["with_kerberos", "kerberos_user", "kerberos_keytab"] }, { "label": "Crawl Performance", "properties": ["max_threads", "add_failed_docs", "crawl_item_timeout", "maximum_connections"] }, { "label": "Limit Documents", "properties": ["max_docs", "max_bytes", "index_directories", "crawl_depth", "bounds", "include_paths", "exclude_paths", "include_extensions"] }, { "label": "Field Mapping", "properties": ["initial_mapping"] }] } }, "category": "Other", "categoryPriority": 1, "unsafe": false }; export const SchemaParamFields = ({schema}) => { const sanitize = str => { if (typeof str !== "string") return str; return str.replace(/^"(.*)"$/s, "$1").replace(/\\/g, "").replace(/"/g, "'"); }; const formatDescription = str => { const s = sanitize(str); return (/[.!?]\)*$/).test(s) ? s : `${s}.`; }; const {description, properties = {}, required: requiredProps = []} = schema; const visibleProps = useMemo(() => Object.entries(properties).filter(([, prop]) => !prop.hints?.includes("hidden")), [properties]); return
{description &&

{formatDescription(description)}

} {visibleProps.map(([name, prop]) => { const isRequired = requiredProps.includes(name); const hasDefault = prop.default !== undefined; const rawDefault = prop.default; const isComplexDefault = hasDefault && (typeof rawDefault === "object" || typeof rawDefault === "string" && (rawDefault.length > 20 || rawDefault.includes('"'))); const fieldProps = { key: name, body: prop.title || name, type: prop.type, ...prop.title && ({ post: [<>API property: {name}] }), ...isRequired && ({ required: true }), ...!isComplexDefault && hasDefault ? { default: sanitize(String(rawDefault)) } : {} }; const isObject = prop.type === "object" && prop.properties; const isArrayOfObjects = prop.type === "array" && prop.items?.type === "object" && prop.items.properties; return {prop.description &&

{formatDescription(prop.description)}

} {isComplexDefault &&

Default: 

                  
                    {JSON.stringify(rawDefault, null, 2)}
} {isArrayOfObjects &&

Object attributes: 

                
                  {'{\n'}
                  {Object.entries(prop.items.properties).map(([iname, iprop]) => <>
                      {`  ${iname}`}
                      {prop.items?.required?.includes(iname) &&  required}
                      {`: {\n    display name: ${sanitize(iprop.title || '')}\n    type: ${iprop.type}\n  }\n`}
                    )}
                  {'}'}
} {isObject && } ; })}
; }; export const LwTemplate = ({title = "Key questions to get you started", icon = "sparkles", cta = "Powered by Agent Studio", linkHref = "https://lucidworks.com/demo/?utm_source=docs&utm_medium=referral&utm_campaign=docs_cta_ai"}) => { const [isLoaded, setIsLoaded] = useState(false); useEffect(() => { const timer = setTimeout(() => { setIsLoaded(true); }, 500); return () => clearTimeout(timer); }, []); return
{isLoaded && ` }} />} Powered by Lucidworks Agent Studio
; }; [localhost link]: http://localhost:3000/docs/fusion-connectors/connectors/v1/hdfs [mintlify link]: https://doc.lucidworks.com/docs/fusion-connectors/connectors/v1/hdfs [old doc.lw link]: https://doc.lucidworks.com/fusion-connectors/55 **Compatible with Fusion version:** 4.0.0 through 5.12.0 V1 deprecation and removal notice All V1 connectors are deprecated in Fusion 5.18.0 and later. This means they are no longer being actively developed and will be removed in Fusion 6. V1 connectors were also previously deprecated in Fusion 5.12.0 but remained available in all versions between 5.12.0 and 5.18.0, including the Fusion 5.9.x long-term support release line, to support customers on those versions. The replacement for this connector is in active development at this time and will be released at a future date. If you are using this connector, you must migrate to the replacement connector or a supported alternative before upgrading to Fusion 6. Migrate to the replacement connector as soon as possible to avoid any disruption to your workflows. **See also the Hadoop connectors, which use [MapReduce](https://hadoop.apache.org/docs/r1.2.1/mapred_tutorial.html) to distribute the crawl processes. For Fusion 4.x, see the following connectors reference pages:** * [Apache Hadoop 2](/docs/fusion-connectors/connectors/v1/hadoop-apache2) * [Cloudera](/docs/fusion-connectors/connectors/v1/hadoop-cloudera) * [Hortonworks](/docs/fusion-connectors/connectors/v1/hadoop-hortonworks) * [MapR](/docs/fusion-connectors/connectors/v1/hadoop-mapr) When there is a lot of content to process, these MapReduce-enabled connectors will be significantly faster. ## Configuration When entering configuration values in the UI, use *unescaped* characters, such as `\t` for the tab character. When entering configuration values in the API, use *escaped* characters, such as `\\t` for the tab character.