# Copy this file and change the following settings: # 1. whitelist # 2. dor fetcher service_url # 3. solr url # 4. harvestdor log_dir, log_nam # whitelist: which objects will you index? # the whitelist can be # 1. an array of druids inline here, e.g. ['druid:oo123oo1234', 'druid:oo234oo2345'] # 2. a filename containing a list of druids (one per line) # if a druid is for a collection record (per the object's identityMetadata at purl page) # then we process all the item druids in that collection (as if they were included individually in the whitelist) # if a druid is for an item object, then we process that druid #whitelist: ['druid:dq441rn2614'] # either give absolute path or path relative to where the command will be executed #whitelist: config/ap_whitelist.txt dor_fetcher: # the baseurl of the DOR Fetcher service from which we get the item druids (per whitelist above) # do not include 'collections' at end. service_url: http://127.0.0.1:3000 # if skip_heartbeat set to true, this will skip a check that the dorfetcher service is alive before making API calls # (useful for testing) skip_heartbeat: true # ----------- SOLR index (that we're writing INTO) parameters ------------ solr: url: https://solr.baseurl.org # timeouts are in seconds; read_timeout -> open/read, open_timeout -> connection open read_timeout: 20 open_timeout: 20 max_retries: 3 harvestdor: # log_name: name of log file (default: STDERR per harvestdor-indexer) log_name: ap-test.log # log_dir: directory for log file (suggest: logs) log_dir: spec/test_logs # purl: url for the DOR purl server (used to get ContentMetadata, etc.) purl: http://purl.stanford.edu # Additional options to pass to Faraday http client (https://github.com/technoweenie/faraday) http_options: ssl: verify: false # timeouts are in seconds; timeout -> open/read, open_timeout -> connection open request: timeout: 180 open_timeout: 180