Configuration of the RDF Server #

---
version: 2                         # format of the configuration file

# optional license configuration
license:
  file: "path to semspect license" # default semspect.lic
  session-keep-alive-minutes: 15   # default 15
  warn-before-session-expiration-minutes: 3 # default 3

semspect.rdf:
  # managed.indicesDirectory
  #
  # storage folder for the SemStore indices that are managed over the REST API
  #
  # default: new folder in the JVM working directory
  managed:
    indicesDirectory: "path/where/indices/are/managed"

semspect.rdf:
  # databases
  #
  # Array of databases that are initialized on startup.
  #
  # default: empty array
  databases:
      # database (required param)
      # 
      # Name of the database - must be unique within configuration. 
      # Allowed characters: 
      # alphanumeric characters '_', '.', '-', '~' 
      # (regex: ^[a-zA-Z0-9_.-~]+$ )
      #
    - database: "database-1" 
      description: "Description of DB 1 example"
      
      # mode (required param)
      # 
      # Startup mode for the specified database
      # (described in more detail in the subsequent sections)
      # 
      # options: 
      # - generate: generate indices to the "indicesDirectory" based
      #   upon the configuration of the "indexing" parameter
      # - load: load indices of "indicesDirectory" and initialize 
      #   them based upon the configuration of the "exploration" parameter
      mode: generate
      indicesDirectory: "path/to/db1-indices"
      indexing:
        ... # indexing configuration - only considered if mode is set to "generate"
      exploration:
        ... # configuration for exploration - considered when indices are loaded into main memory
      
    - database: "database-2"
      mode: load
      description: "Description of DB 2 example"
      indicesDirectory: "path/to/db2-indices"
      indexing:
        ...
      exploration:
        ...

################################
# required generation parameters
################################

# "databases[0]" can be used to specify the first entry in the databases array
# (used here to highlight the full path of the nested YAML parameter)
semspect.rdf.databases[0].database: default-db   # the default
semspect.rdf.databases[0].mode: generate
  
################################
# optional generation parameters
################################

# rdfDataSources
#
# Supported data sources:
# - plain files: *.ttl, *.ttls, *.owl, *.nt, *.n3, *.rdf, *.hdt, *.jsonld,
#   *.brf, *.rj, *.trig, *.trigs,
# - compressed files: *.bz2, *.gz
# - archives: *.zip
# - directories
# - URLs: supports plain files or compressed files (no archives).
#   - Note: The Http content type must indicate the correct RDF format,
#     otherwise it is defaulted to RDF Turtle.
# - Graph store content URLs:
#   - GraphDB (tested with v10.5.1):
#       http://localhost:7200/repositories/some-store/statements
#   - RDFox (works with >= v6.3a):
#      http://localhost:12110/datastores/some-store/content?default
#
# default: empty array
semspect.rdf.databases[0].indexing.rdfDataSources:
  - DATA_SOURCE_1
  - ...
  - DATA_SOURCE_N

# indicesDirectory
#
# storage folder for the SemStore indices
#
# default is a new folder in JVM working directory
semspect.rdf.databases[0].indicesDirectory: "path/to/directory"

# parsingStrategy
#
# options:
# - ONE_PASS (default):
#   - generate base structures (triples, dictionary) in a single pass
#     over the provided RDF datasets
#   - consumes more main memory because uncompressed dictionary and triples
#     are loaded simultaneously into memory
# - TWO_PASS:
#   - generate base structures (triples, dictionary) in two iterations
#     over the provided RDF datasets
#   - dictionary is generated in first pass, triples in second
#   - consumes less main memory since dictionary is compressed during
#     generation on demand
semspect.rdf.databases[0].indexing.parsingStrategy: ONE_PASS

# numberOfThreads
#
# default: available processors of machine
semspect.rdf.databases[0].indexing.numberOfThreads: 4

# terminateAfterIndexing
#
# default: false
semspect.rdf.databases[0].indexing.terminateAfterIndexing: false

# validateParsedResources
#
# default: false
semspect.rdf.databases[0].indexing.validateParsedResources: false

# iriDictionarySectionType
#
# Which type of dictionary section should be used for all IRIs.
# An uncompressed type requires more space but might lead to a higher
# performance when applying string filters.
#
# options:
# - PLAIN_FRONT_CODING (default)
# - UNCOMPRESSED_STRINGS
semspect.rdf.databases[0].indexing.iriDictionarySectionType: PLAIN_FRONT_CODING

# stringLiteralDictionarySectionType
#
# Which type of dictionary section should be used for all string literals.
# An uncompressed type requires more space but might lead to a higher
# performance when applying string filters.
#
# options:
# PLAIN_FRONT_CODING (default)
# UNCOMPRESSED_STRINGS
semspect.rdf.databases[0].indexing.stringLiteralDictionarySectionType: PLAIN_FRONT_CODING

# disableRDFSDomainRangeEntailment
#
# When set to true all entailments implied by rdfs:domain as well as rdfs:range
# are ignored.
#
# default: false
semspect.rdf.databases[0].indexing.disableRDFSDomainRangeEntailment: false

#########################
# experimental features
#########################

# translateSKOSToRDFS
#
# This option introduces a class hierarchy to reflect the SKOS concept
# taxonomy. A concept class is generated for each SKOS concept that has a narrower concept. 
# and each skos:broader, skos:narrower, and skos:exactMatch relation is translated to the
# corresponding rdfs:subClassOf axioms.
# Moreover, all root and leaf concepts of the derived hierarchy are assigned new classes
# "Root Concept" and "Leaf Concept" respectively.
# Example:
#   For ":super-c skos:narrower :sub-c", we derive ":sub-c rdfs:subClassOf :super-c".
#   For ":sub-c skos:broader :super-c", we derive ":sub-c a :super-c".
#
# default: false
semspect.rdf.databases[0].indexing.translateSKOSToRDFS: false

# indexReificationTriples
#
# If set to "true", reification triples that use the RDF or OWL vocabulary, such as "_:xxx rdf:subject :some-subject",
# are indexed and can then be explored. However, as rdf:Statement and owl:Axiom are disabled by default, it may be useful
# to additionally set the parameter "[...].exploration.showStatementClassInTree" (as specified in the load configuration).
# RDF Reification vocabulary: https://www.w3.org/TR/rdf11-mt/#reification
# OWL Annotation vocabular: https://www.w3.org/TR/owl2-quick-reference/#Annotations
#
# default: false
semspect.rdf.databases[0].indexing.indexReificationTriples: false

#############################
# required loading parameters
#############################

# "databases[0]" can be used to specify the first entry in the databases array
# (used here to highlight the full path of the nested YAML parameter)
semspect.rdf.databases[0].database: default-db
semspect.rdf.databases[0].mode: load
semspect.rdf.databases[0].indicesDirectory: "path/to/indices/directory"

##################################
# additional server settings
##################################

# port
#
# default: 8080
server.port: 8080

# x-frame support
# The x-frame functionality is a way of combining and organizing web-based
# documents together on a single webpage through the use of frames (HTML
# elements that allow you to display content from another source, such as
# another webpage or a video). By default, the x-frame functionality is
# disabled by Spring Boot, however, by using the following parameter, it is
# possible to define frame-ancestors to include SemSpect in other HTML pages
# (https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Security-Policy/frame-ancestors) .
#
# default: disabled; below are some examples
server.frame-ancestors:
  # local HTML files are allowed to integrate SemSpect in an x-frame
  - "file://*"
  # any subdomain of "example.org" is allowed to integrate SemSpect in an x-frame
  - "https://www.*.example.org"

# context path
#
# Determines at which context path the content will be served by the server.
# For instance, if it is set to "/dataset-x", SemSpect gets hosted on "localhost:8080/dataset-x".
# This option might be helpful to distinguish different running instances of
# SemSpect not merely by their port.
#
# default: /
server.servlet.context-path: /

# basic auth
#
# Enables Basic HTTP Authentication for a single user. 
# 
# Generate the password_hash via spring-boot cli's encodepassword command.
# Installation and usage see: https://docs.spring.io/spring-boot/cli
# E.g: ./spring encodepassword my_password
#
# default: disabled
#spring.security:
#    user:
#      name: 'username'
#      password: 'password_hash' 

##################################
# additional exploration settings
##################################

# explorationMenuWithoutCount
#
# If enabled, the exploration menu does not show the distinct number of connected
# resources. It only shows whether at least one resource of a particular class is
# connected to the given group (increases performance).
#
# default: false
semspect.rdf.databases[0].exploration.explorationMenuWithoutCount: false

# numberOfThreads
#
# default: number of processors of machine
semspect.rdf.databases[0].exploration.numberOfThreads: 4

# cacheGroups
#
# default: true
semspect.rdf.databases[0].exploration.cacheGroups: true

# showClassesAndPropertiesAsResources
#
# If set to true, rdf:Property and rdfs:Class are shown in the class tree.
#
# default: false
semspect.rdf.databases[0].exploration.showClassesAndPropertiesAsResources: false

# showTopClassInTree
#
# If set to true, the top class rdfs:Resource is shown in the class tree.
#
# default: false
semspect.rdf.databases[0].exploration.showTopClassInTree: false

#
# If set to true, the classes rdf:Statement and owl:Axiom are shown in the class tree.
#
# default: false
semspect.rdf.databases[0].exploration.showStatementClassInTree: false

# logMemoryUsage
#
# Logs the used main memory to the file
# INDICES_DIRECTORY/exploration/log/memoryConsumption.csv
#
# default: false
semspect.rdf.databases[0].exploration.logMemoryUsage: false

# explorationMenuComputationMethod
#
# options:
# - ROARING_BITMAPS_PER_CLASS
# - SORTED_ITERATION_PER_CLASS
# - INDIVIDUAL_QUERIES_PER_CLASS
# - INDIVIDUAL_QUERIES
# - ROARING_BITMAPS
# - DYNAMICALLY_DETERMINED_PER_CLASS
# - DYNAMICALLY_DETERMINED (default)
semspect.rdf.databases[0].exploration.explorationMenuComputationMethod: DYNAMICALLY_DETERMINED

# explorationMenuWithoutCountComputationMethod
#
# options:
# - PER_CLASS
# - GLOBAL
# - DYNAMICALLY_DETERMINED (default)
semspect.rdf.databases[0].exploration.explorationMenuWithoutCountComputationMethod: DYNAMICALLY_DETERMINED

# predecessorCountComputationMethod
#
# options:
# - SORTED_ITERATION
# - HASH_SET
# - DYNAMICALLY_DETERMINED (default)
semspect.rdf.databases[0].exploration.predecessorCountComputationMethod: DYNAMICALLY_DETERMINED

# filterComputationMethod
#
# options:
# - QUERY_PER_INDIVIDUAL
# - INDEX_ITERATION
# - DYNAMICALLY_DETERMINED (default)
semspect.rdf.databases[0].exploration.filterComputationMethod: DYNAMICALLY_DETERMINED

# sortingMethod
#
# options:
# - INDEX_ITERATION
# - SORTING_ON_THE_FLY
# - DYNAMICALLY_DETERMINED (default)
semspect.rdf.databases[0].exploration.sortingMethod: DYNAMICALLY_DETERMINED

@prefix :     <http://www.example.org/> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .

:Company
  a rdfs:Class .

:derivo
  a      :Company ;
  :name  "Derivo" ;
  :image "https://www.derivo.de/fileadmin/externe_websites/ext.derivo/images/layout/logo_deutsch_01.png" ;
  :email "info@derivo.de" ;
  :url   "https://www.derivo.de/home/" .

version: 1
databases:
  - database: default-db
    attributes:
      - id: 'http://www.example.org/image'
        type: 'IMAGE' # images or GIFs
      - id: 'http://www.example.org/url'
        type: 'URL'
      - id: 'http://www.example.org/email'
        type: 'EMAIL'

#!/bin/bash
export SEMSPECT_JDK_OPTIONS=-Dde.derivo.semspect.server.configuration.dossier.path="path/to/dossier-config.yaml"
./semspect-smart.sh run test-data.ttl

@prefix :     <http://www.example.org/> .
@prefix rdf:  <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .

:City rdfs:subClassOf :Place.
:Country rdfs:subClassOf :Place.
:Coordinate rdfs:subClassOf :Place.

:germany a :Country;
  rdfs:label "Germany";
  :countryName "DE".
:coordinate1 a :Coordinate;
  :coordinate "48.398537, 9.992537" ;
  :name "Ulmer Münster" .
:ulm a :City;
  rdfs:label "Ulm";
  :postalCode "89073".

databases:
  - database: default-db
    categories:
      - id: 'semspect::top' # special category 'TOP'. Fallback if no other configuration matches.
        description: 
          regex:
            - "\\Qsemspect::object_id\\E" # semspect::object_id is a special reference for the IRI of a resource
      - id: 'http://www.example.org/Place'
        caption:
          regex:
            - "(?i).*name" #  use some property ending on name
            - "\\Qhttp://www.w3.org/2000/01/rdf-schema#label\\E" # if no such property exists use rdfs:label 
      - id: 'http://www.example.org/City'
        caption: 
          regex:
            - '.*postalCode' # ending with postalCode