Field | Optional | Default | Multiple | Notes | Example |
---|---|---|---|---|---|
type | No | - | No | The value must be " |
smb". | " |
smb" | |||||
description | No | - | No | Name of the connection object. | " |
smbConnection" |
hostname |
No | - | No |
Hostname where the shared directory is located. | "shared.example.com" | ||||
port | No | 445 | No | Port where the SMB protocol is used. | "445" |
properties | No | - | No | Configuration object |
---|
disableFetch |
Yes |
false | No |
Check to disable the connector fetcher, only metadata will be collected. | true / false |
verboseSMBJ |
Yes | false | No |
Check to enable SMBJ logging. (WARNING) Enabling this would decrease performance. | true / false | ||||
stopOnScanError | Yes | true | No | If enabled, the crawl will stop if there is an error on the scan phase. | true / false |
indexContainers | Yes | false | No | Enable to index the directories. | true / false |
scanRecursively | Yes | true | No | Enable to scan discovered directories recursively. | true / false |
include | Yes | [ ] | Yes | Patterns to match against document URL, if any of them match, the document will be included in the crawl. | [ ".*pdf$", ".*docx$" ] |
exclude | Yes | [ ] | Yes | Patterns to match against document URL, if any of them match, the document will be excluded from the crawl. | [ ".*png$", ".*jpeg$" ] |
scanExcludedItems | Yes | false | No | Enable to force the scan of excluded directories, so child items within the scope can be found. | true / false |
fetchACLs | Yes |
true |
No | Check to retrieve owner, group and ACL information. | true / false | |||
resolveSIDs | Yes | true | No | Check to resolve retrieved SIDs from owner, group and ACL. | true / false |
addACLSID | Yes | false | No | Check to include SID value on ACL output. | true / false |
addACLEncodedSID | Yes | false | No | Check to include Encoded SID (Base 32) value on ACL output. | true / false |
addACLFlags | Yes | false | No | Check to include ACL flags on ACL output. | true / false |
addACLType | Yes | false | No | Check to include ACL type on ACL output. | true / false |
addACLAccessMask | Yes | false | No | Check to include ACL access mask on ACL output. | true / false |
enableDFS | Yes | true | No | true /false | |
connectionTimeout | No | 6000 | No | "6000" | |
maxRetries | No | 5 | No | "5" | |
baseBackoff | No | 500 | No | Base time for the backoff sleeps (in ms). | "500" |
backoffMultiplier | No | 2.0 | No | Multiplier factor to be used for the backoff time. | "2.0" |
lastAccessedUpdates | Yes | false | No | Check to restore the last accessed date on the documents processed by the connector. WARNING: Requires a user with permissions for writing. This is not supported by windows. | true /false |
staticAcl | Yes | [ ] | Yes | Static ACL configuration object | |
---|---|---|---|---|---|
name | No | - | No | Name of the static ACL. | "group1" |
domain | Yes | "" | No | Domain of the static ACL. | "testDomain" |
entity | Yes | "user" | No | Entity (user / group) represented by the static ACL. | "user" / "group" |
access | Yes | "allow" | No | Access (allow / deny) granted by the ACL. | "allow" / "deny" |
Code Block | ||||
---|---|---|---|---|
| ||||
{
"type": "smb",
"description": "SMB Test Connector",
"properties": {
| ||||
Code Block | ||||
| ||||
{ "type": "filesystem", "description": "FileSystem Test Connector", "properties": { "url": "C:\\Directory", "ignoreSymLinks": true, "stopOnScanError": true, "indexContainers": true, "scanExcludedItems": true, "ignoreSymLinks": true, "includes": ".*\\.txt", "excludes": ".*\\.png", "staticAcl": [{ "namehost": "test-user192.168.0.80", "domain"port": "test-domain445", "disableFetch": false, "entityverboseSMBJ": "user"false, "stopOnScanError": true, "accessindexContainers": "allow"true, }, {"scanExcludedItems": true, "includes": ".*\\.txt", "nameexcludes": "test-group.*\\.png", "domain": "", "fetchACLs":true, "entityresolveSIDs": "group"true, "access": "deny" "addACLSID": false, "addACLEncodedSID": false, "addACLFlags": false, "addACLType" : false, "addACLAccessMask": false, "enableDFS": true, "connectionTimeout": 60000, "maxRetries": 5, "baseBackoff": 500, "backoffMultiplier": 2.0, "lastAccessedUpdates": false, } "staticAcl": [{ ] } } |
[ ]
"name": "test-user",
"domain": "test-domain",
"entity": "user",
"access": "allow"
}, {
"name": "test-group",
"domain": "",
"entity": "group",
"access": "deny"
}
]
}
} |
Field | Optional | Default | Multiple | Notes | Example |
---|---|---|---|---|---|
Field | Optional | Default | Multiple | Notes | Example |
type | No | - | No | The value must be "smb". | "smb" |
description | No | - | No | Name of the connection object. | "smbConnection" |
hostname | No | - | No | Hostname where the shared directory is located. | "shared.example.com" |
port | No | 445 | No | Port where the SMB protocol is used. | "445" |
properties | No | - | No | Configuration object | |
disableFetch | Yes | false | No | Check to disable the connector fetcher, only metadata will be collected. | true / false |
verboseSMBJ | Yes | false | No | Check to enable SMBJ logging. (WARNING) Enabling this would decrease performance. | true / false |
stopOnScanError | Yes | true | No | If enabled, the crawl will stop if there is an error on the scan phase. | true / false |
indexContainers | Yes | false | No | Enable to index the directories. | true / false |
scanRecursively | Yes | true | No | Enable to scan discovered directories recursively. | true / false |
include | Yes | [ ] | Yes | Patterns to match against document URL, if any of them match, the document will be included in the crawl. | [ ".*pdf$", ".*docx$" ] |
exclude | Yes | [ ] | Yes | Patterns to match against document URL, if any of them match, the document will be excluded from the crawl. | [ ".*png$", ".*jpeg$" ] |
scanExcludedItems | Yes | false | No | Enable to force the scan of excluded directories, so child items within the scope can be found. | true / false |
fetchACLs | Yes | true | No | Check to retrieve owner, group and ACL information. | true / false |
resolveSIDs | Yes | true | No | Check to resolve retrieved SIDs from owner, group and ACL. | true / false |
addACLSID | Yes | false | No | Check to include SID value on ACL output. | true / false |
addACLEncodedSID | Yes | false | No | Check to include Encoded SID (Base 32) value on ACL output. | true / false |
addACLFlags | Yes | false | No | Check to include ACL flags on ACL output. | true / false |
addACLType | Yes | false | No | Check to include ACL type on ACL output. | true / false |
addACLAccessMask | Yes | false | No | Check to include ACL access mask on ACL output. | true / false |
enableDFS | Yes | true | No | true /false | |
connectionTimeout | No | 6000 | No | "6000" | |
maxRetries | No | 5 | No | "5" | |
baseBackoff | No | 500 | No | Base time for the backoff sleeps (in ms). | "500" |
backoffMultiplier | No | 2.0 | No | Multiplier factor to be used for the backoff time. | "2.0" |
lastAccessedUpdates | Yes | false | No | Check to restore the last accessed date on the documents processed by the connector. WARNING: Requires a user with permissions for writing. This is not supported by windows. | true /false |
staticAcl | Yes | [ ] | Yes | Static ACL configuration object | |
name | No | - | No | Name of the static ACL. | "group1" |
domain | Yes | "" | No | Domain of the static ACL. | "testDomain" |
entity | Yes | "user" | No | Entity (user / group) represented by the static ACL. | "user" / "group" |
access | Yes | "allow" | No | Access (allow / deny) granted by the ACL. | "allow" / "deny" |
Code Block | ||||
---|---|---|---|---|
| ||||
{
"type": "smb",
"description": "SMB Test Connector",
"properties": {
"host": "192.168.0.80",
"port":"445",
"disableFetch": false,
"verboseSMBJ": false,
"stopOnScanError": true,
"indexContainers": true,
"scanExcludedItems": true,
"includes": ".*\\.txt",
"excludes": ".*\\.png",
"fetchACLs":true, |
[ ]
Code Block | ||||
---|---|---|---|---|
| ||||
{ "id": "89d6632a-a296-426c-adb0-d442adcab4b0", "type": "filesystem", "description": "FileSystem Test Connector", "properties": { "urlresolveSIDs": true, "addACLSID"C:\\Directory", "ignoreSymLinks": true, "stopOnScanError: false, "addACLEncodedSID": false, "addACLFlags": false, "addACLType" : false, "addACLAccessMask": false, "enableDFS": true, "indexContainers "connectionTimeout": true60000, "scanRecursively "maxRetries": true5, "scanExcludedItems "baseBackoff": true500, "includes "backoffMultiplier": ".*\\.txt", "excludes": ".*\\.png"2.0, "lastAccessedUpdates": false, "staticAcl": [{ "name": "test-user", "domain": "test-domain", "entity": "user", "access": "allow" }, { "name": "test-group", "domain": "", "entity": "group", "access": "deny" } ] } } |
Field | Optional | Default | Multiple | Notes | Example | |
---|---|---|---|---|---|---|
seed | No | - | No | The subdirectory to crawl. This value will be appended to the url of the connection. | Path to the element to be crawled, can be a directory or a file. | "myDirectory/levelTwo"directory" |
type | No | - | No | The value must be "filesystem". | "filesystemsmb" | |
description | No | - | No | Name of the seed object. | "MyFileSystemConnection"MySMB" | |
seedFile | Yes | false | No | If checked the path will be processed as a file instead of a directory. WARNING: The crawler will only process the seed and then will stop. | true /false | |
connector | No | - | No | The id of the connector to be used with this seed. The connector type must match the seed type. | "82f7f0a4-8d28-47ce-8c9d-e3ca414b0d31" | |
connection | No | - | No | The id of the connection to be used with this seed. The connection type must match the seed type. | "602d3700-28dd-4a6a-8b51-e4a663fe9ee6" | |
workflows | Yes | [ ] | Yes | The ids of the workflows that will be executed for the documents crawled. | ["f8c414cb-1f5d-42ef-9cc9-5696c3f0bda4"] | |
throttlePolicy | Yes | - | No | Id of the throttle policy that applies to this connection object. | "f5587cee-9116-4011-b3a9-6b235b333a1b" | |
routingPolicies | Yes | [ ] | Yes | The ids of the routing policies that this seed will use. | ["313de87c-3cb9-4fe0-a2cb-17f75ce7d0c7", "b4d2579f-1a0a-4a8b-9fd4-d42780003b36"] | |
tags | Yes | [ ] | Yes | The tags of the seed. These can be used to filter the seed | ["tag1", "tag2"] |
Code Block | ||||
---|---|---|---|---|
| ||||
{ "type": "filesystemsmb", "seed": "directorymyDirectory/levelTwo", "connector": "82f7f0a4-8d28-47ce-8c9d-e3ca414b0d31", "description": "FileSystem_Test_Seed", "throttlePolicy": "6b8b5f23-fc77-47a1-9b58-106577162e7b", "routingPolicies": ["313de87c-3cb9-4fe0-a2cb-17f75ce7d0c7", "b4d2579f-1a0a-4a8b-9fd4-d42780003b36"], "connection": "602d3700-28dd-4a6a-8b51-e4a663fe9ee6", "workflows": ["f8c414cb-1f5d-42ef-9cc9-5696c3f0bda4"], "tags": ["tag1", "tag2"], "properties": { "seed": "directory"seedFile": false } } |
Field | Optional | Default | Multiple | Notes | Example |
---|---|---|---|---|---|
id | No | - | No | Id of the seed to update. | "2f287669-d163-4e35-ad17-6bbfe9df3778" |
seed | Yes | - | No | The subdirectory to crawl. This value will be appended to the url of the connection. | "directorymyDirectory/levelTwo" |
description | Yes | - | No | Name of the seed object. | "MyFileSystemConnection"MySMB" |
seedFile | Yes | false | No | If checked the path will be processed as a file instead of a directory. WARNING: The crawler will only process the seed and then will stop. | true /false |
connector | Yes | - | No | The id of the connector to be used with this seed. The connector type must match the seed type. | "82f7f0a4-8d28-47ce-8c9d-e3ca414b0d31" |
connection | Yes | - | No | The id of the connection to be used with this seed. The connection type must match the seed type. | "602d3700-28dd-4a6a-8b51-e4a663fe9ee6" |
workflows | Yes | [ ] | Yes | The ids of the workflows that will be executed for the documents crawled. | ["f8c414cb-1f5d-42ef-9cc9-5696c3f0bda4"] |
workflows.add | Yes | [ ] | Yes | The ids of the workflows to add. | ["f8c414cb-1f5d-42ef-9cc9-5696c3f0bda4"] |
workflows.remove | Yes | [ ] | Yes | The ids of the workflows to remove. | ["f8c414cb-1f5d-42ef-9cc9-5696c3f0bda4"] |
throttlePolicy | Yes | - | No | Id of the throttle policy that applies to this connection object. | "f5587cee-9116-4011-b3a9-6b235b333a1b" |
routingPolicies | Yes | [ ] | Yes | The ids of the routing policies that this seed will use. | ["313de87c-3cb9-4fe0-a2cb-17f75ce7d0c7", "b4d2579f-1a0a-4a8b-9fd4-d42780003b36"] |
routingPolicies.add | Yes | [ ] | Yes | The ids of the routingPolicies to add. | ["b4d2579f-1a0a-4a8b-9fd4-d42780003b36"] |
routingPolicies.remove | Yes | [ ] | Yes | The ids of the routingPolicies to remove. | ["313de87c-3cb9-4fe0-a2cb-17f75ce7d0c7"] |
tags | Yes | [ ] | Yes | The tags of the seed. These can be used to filter the seed | ["tag1", "tag3"] |
tags.add | Yes | [ ] | Yes | The tags to add | ["tag4"] |
tags.remove | Yes | [ ] | Yes | The tags to remove | ["tag2"] |
Code Block | ||||
---|---|---|---|---|
| ||||
{ "id": "2f287669-d163-4e35-ad17-6bbfe9df3778", "type": "filesystemsmb", "seed": "directorymyDirectory/levelTwo", "connector": "82f7f0a4-8d28-47ce-8c9d-e3ca414b0d31", "description": "FileSystem_Test_Seed", "throttlePolicy": "6b8b5f23-fc77-47a1-9b58-106577162e7b", "routingPolicies": ["313de87c-3cb9-4fe0-a2cb-17f75ce7d0c7", "b4d2579f-1a0a-4a8b-9fd4-d42780003b36"], "connection": "602d3700-28dd-4a6a-8b51-e4a663fe9ee6", "workflows": ["b255e950-1dac-46dc-8f86-1238b2fbdf27", "f8c414cb-1f5d-42ef-9cc9-5696c3f0bda4"], "tags": ["tag", "tag2"], "properties": { "seedseedFile": "directory"false } } |