Is it possible to deactivated the standard solr tags like: currency, phone numbers, Money, law clause,... about open-semantic-search HOT 5 OPEN

# -*- coding: utf-8 -*-

#
# ETL config for connector(s)
#

# print debug messages
#config['verbose'] = True


#
# Languages for language specific index
#
# Each document is analyzed without grammar rules in the index fields like content, additionally it can be added/copied to language specific index fields/analyzers
# Document language is autodetected by default plugin enhance_detect_language_tika_server

# If index support enhanced analytics for specific languages, we can add/copy data to language specific fields/analyzers
# Set which languages are configured and shall be used in index for language specific analysis/stemming/synonyms
# Default / if not set all languages that are supported will be analyzed additionally language specific
#config['languages'] = ['en','de','fr','hu','it','pt','nl','cz','ro','ru','ar','fa']

# force to language specific analysis additional in this language(s) grammar & synonyms, even if language autodetection detects other language
#config['languages_force'] = ['en','de']


# only use language for language specific analysis which are added / uncommented later
#config['languages'] = []

# add English
#config['languages'].append('en')

# add German / Deutsch
#config['languages'].append('de')

# add French / Francais
#config['languages'].append('fr')

# add Hungarian
#config['languages'].append('hu')

# add Spanish
#config['languages'].append('es')

# add Portuguese
#config['languages'].append('pt')

# add Italian
#config['languages'].append('it')

# add Czech
#config['languages'].append('cz')

# add Dutch
#config['languages'].append('nl')

# add Romanian
#config['languages'].append('ro')

# add Russian
#config['languages'].append('ru')



#
# Index/storage
#

#
# Solr URL and port
#

config['export'] = 'export_solr'

# Solr server
config['solr'] = 'http://localhost:8983/solr/'

# Solr core
config['index'] = 'opensemanticsearch'


#
# Elastic Search
#

#config['export'] = 'export_elasticsearch'

# Index
#config['index'] = 'opensemanticsearch'


#
# Tika for text and metadata extraction
#

# Tika server (with tesseract-ocr-cache)
# default: http://localhost:9998

#config['tika_server'] = 'http://localhost:9998'

# Tika server with fake OCR cache of tesseract-ocr-cache used if OCR in later ETL tasks
# default: http://localhost:9999

#config['tika_server_fake_ocr'] = 'http://localhost:9999'


#
# Annotations
#

# add plugin for annotation/tagging/enrichment of documents
config['plugins'].append('enhance_annotations')

# set alternate URL of annotation server
#config['metadata_server'] = 'http://localhost/search-apps/annotate/json'


#
# RDF Knowledge Graph
#

# add RDF Metadata Plugin for granular import of RDF file statements to entities of knowledge graphs
config['plugins'].append('enhance_rdf')


#
# Config for OCR (automatic text recognition of text in images)
#

# Disable OCR for image files (i.e for more performance and/or because you don't need the text within images or have only photos without photographed text)
#config['ocr'] = False

# Option to disable OCR of embedded images in PDF by Tika
# so (if alternate plugin is enabled) OCR will be done only by alternate
# plugin enhance_pdf_ocr (which else works only as fallback, if Tika exceptions)
#config['ocr_pdf_tika'] = False

# Use OCR cache
config['ocr_cache'] = '/var/cache/tesseract'

# Option to disable OCR cache
#config['ocr_cache'] = None

# Do OCR for images embedded in PDF documents (i.e. designed images or scanned or photographed documents)
config['plugins'].append('enhance_pdf_ocr')

#OCR language

#If other than english you have to install package tesseract-XXX (tesseract language support) for your language
#and set ocr_lang to this value (be careful, the tesseract package for english is "eng" (not "en") german is named "deu", not "de"!)

# set OCR language to English/default
#config['ocr_lang'] = 'eng'

# set OCR language to German/Deutsch
#config['ocr_lang'] = 'deu'

# set multiple OCR languages
config['ocr_lang'] = 'eng+deu'


#
# Regex pattern for extraction
#

# Enable Regex plugin
config['plugins'].append('enhance_regex')

# Regex config for IBAN extraction
#config['regex_lists'].append('/etc/opensemanticsearch/regex/iban.tsv')


#
# Email address and email domain extraction
#
#config['plugins'].append('enhance_extract_email')


#
# Phone number extraction
#
#config['plugins'].append('enhance_extract_phone')


#
# Config for Named Entities Recognition (NER) and Named Entity Linking (NEL)
#

# Enable Entity Linking / Normalization and dictionary based Named Entities Extraction from thesaurus and ontologies
config['plugins'].append('enhance_entity_linking')

# Enable SpaCy NER plugin
config['plugins'].append('enhance_ner_spacy')

# Spacy NER Machine learning classifier (for which language and with which/how many classes)

# Default classifier if no classifier for specific language

# disable NER for languages where no classifier defined in config['spacy_ner_classifiers']
config['spacy_ner_classifier_default'] = None

# Set default classifier to English (only if you are sure, that all documents you index are english)
# config['spacy_ner_classifier_default'] = 'en_core_web_sm'

# Set default classifier to German (only if you are sure, that all documents you index are german)
# config['spacy_ner_classifier_default'] = 'de_core_news_sm'

# Language specific classifiers (mapping to autodetected document language to Spacy classifier / language)
#
# You have to download additional language classifiers for example english (en) or german (de) by
# python3 -m spacy download en
# python3 -m spacy download de
# ...

config['spacy_ner_classifiers'] = {
    'da': 'da_core_news_sm',
    'de': 'de_core_news_sm',
    'en': 'en_core_web_sm',
    'es': 'es_core_news_sm',
    'fr': 'fr_core_news_sm',
    'it': 'it_core_news_sm',
    'lt': 'lt_core_news_sm',
    'nb': 'nb_core_news_sm',
    'nl': 'nl_core_news_sm',
    'pl': 'pl_core_news_sm',
    'pt': 'pt_core_news_sm',
    'ro': 'ro_core_news_sm',
}


# Enable Stanford NER plugin
#config['plugins'].append('enhance_ner_stanford')

# Stanford NER Machine learning classifier (for which language and with how many classes, which need more computing time)

# Default classifier if no classifier for specific language

# disable NER for languages where no classifier defined in config['stanford_ner_classifiers']
config['stanford_ner_classifier_default'] = None

# Set default classifier to English (only if you are sure, that all documents you index are english)
#config['stanford_ner_classifier_default'] = '/usr/share/java/stanford-ner/classifiers/english.all.3class.distsim.crf.ser.gz'

# Set default classifier to German (only if you are sure, that all documents you index are german)
#config['stanford_ner_classifier_default'] = '/usr/share/java/stanford-ner/classifiers/german.conll.germeval2014.hgc_175m_600.crf.ser.gz'

# Language specific classifiers (mapping to autodetected document language)
# Before you have to download additional language classifiers to the configured path
config['stanford_ner_classifiers'] = {
    'en': '/usr/share/java/stanford-ner/classifiers/english.all.3class.distsim.crf.ser.gz',
    'es': '/usr/share/java/stanford-ner/classifiers/spanish.ancora.distsim.s512.crf.ser.gz',
    'de': '/usr/share/java/stanford-ner/classifiers/german.conll.germeval2014.hgc_175m_600.crf.ser.gz',
}

# If Stanford NER JAR not in standard path
config['stanford_ner_path_to_jar'] = "/usr/share/java/stanford-ner/stanford-ner.jar"

# Stanford NER Java options like RAM settings
config['stanford_ner_java_options'] = '-mx1000m'


#
# Law clauses extraction
#

#config['plugins'].append('enhance_extract_law')


#
# Money extraction
#

#config['plugins'].append('enhance_extract_money')


#
# Neo4j graph database
#

# exports named entities and relations to Neo4j graph database

# Enable plugin to export entities and connections to Neo4j graph database
#config['plugins'].append('export_neo4j')

# Neo4j server
#config['neo4j_host'] = 'localhost'

# Username & password
#config['neo4j_user'] = 'xxx'
#config['neo4j_password'] = 'xxx'