| # |
| # Licensed to the Apache Software Foundation (ASF) under one or more |
| # contributor license agreements. See the NOTICE file distributed with |
| # this work for additional information regarding copyright ownership. |
| # The ASF licenses this file to You under the Apache License, Version 2.0 |
| # (the "License"); you may not use this file except in compliance with |
| # the License. You may obtain a copy of the License at |
| # |
| # http://www.apache.org/licenses/LICENSE-2.0 |
| # |
| # Unless required by applicable law or agreed to in writing, software |
| # distributed under the License is distributed on an "AS IS" BASIS, |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| # See the License for the specific language governing permissions and |
| # limitations under the License. |
| # |
| |
| # Any23 Core Version |
| any23.core.version=${project.version} |
| |
| # HTTP Client Configuration. |
| # ---- Default HTTP User Agent if not specified. |
| any23.http.user.agent.default=Any23-CLI |
| # ---- HTTP client timeout in milliseconds. |
| any23.http.client.timeout=10000 |
| # ---- HTTP client max number of connections. |
| any23.http.client.max.connections=5 |
| |
| # RDFa Extractor |
| any23.rdfa.extractor.xslt=rdfa.xslt |
| |
| # Allows to enable(on)/disable(off) addition |
| # of timestamp and size metadata triples. |
| any23.extraction.metadata.timesize=off |
| |
| # Allows to enable(on)/disable(off) addition |
| # of nesting metadata triples. |
| any23.extraction.metadata.nesting=on |
| |
| # Allows to enable(on)/disable(off) |
| # the domain triple for every Microformat entity. |
| any23.extraction.metadata.domain.per.entity=off |
| |
| # Allows to decide which RDFa Extractor to enable. |
| # If 'on' will be activated the programmatic RDFa 1.1 Extractor |
| # (org.apache.any23.extractor.rdfa.RDFa11Extractor) otherwise will be |
| # registered the RDFa 1.0 legacy one (org.apache.any23.extractor.rdfa.RDFaExtractor). |
| any23.extraction.rdfa.programmatic=on |
| |
| # The extraction context IRI to be used by the |
| # SingleDocumentExtraction. If == '?' the document IRI will |
| # be used. It can be overriden by specifying a different |
| # value in ExtractionParameters. |
| any23.extraction.context.iri=? |
| |
| # Any23 Core Plugin Dirs |
| any23.plugin.dirs=./plugins |
| |
| # Microdata Configuration. |
| # ---- Enables(on)/disables(off) strict Microdata extraction. |
| # If turned off, it uses the any23.microdata.ns.default |
| # to build IRIs for anonymous properties |
| any23.microdata.strict=off |
| # ---- Microdata default namespace. |
| any23.microdata.ns.default=http://schema.org/ |
| |
| # Allows to enable(on)/disable(off) the registration |
| # of HTMLMetaExtractor.java to |
| # ExtractionRegistry.java |
| any23.extraction.head.meta=on |
| |
| # Allows to specify a CSV file separator and comment delimeter |
| any23.extraction.csv.field=, |
| any23.extraction.csv.comment=# |
