# -*- coding: utf-8 -*-
from SeaCOW import Query, Nonprocessor
# Create a Query object and set whatever needs to be set.
q = Query()
q.corpus = 'decow16a-nano' # Lower-case name of the corpusto use.
q.string = '[word="Gartenzwerg"]' # A normal CQL string as used in NoSketchEngine.
q.max_hits = -1 # Maximal number of hits to return. Ignored for Nonprocessor.
q.attributes = [] # For counting, you don't need word attributes.
q.structures = [] # ... you don't need structural attributes.
q.references = [] # ... you don't need reference attrs.
q.container = 's' # Which container structure should be used?
# Using the deduplicator would NOT change the outcome. Switch off.
q.set_deduplication(off=True)
# Create a Processor object and attach it to the Query object.
# The Nonprocessor processor does nothing. You can work with the results
# yourself in the finalise method or just get the hits value from the
# query object. It is the concordance as seported by Manatee.
p = Nonprocessor() # Create a processor object of apporpriate type.
q.processor = p # Attach the processor to the query.
q.run() # Run the query.
print('Query was: %s' % (q.string))
print('Corpus used: %s' % (q.corpus))
print('Query returned %d hits.' % (q.hits))
# -*- coding: utf-8 -*-
from SeaCOW import Query, ConcordanceLoader
import json # Just for pretty-printing.
# See sample.py for annotations of these attributes.
q = Query()
q.corpus = 'decow16a-nano'
q.string = '[word="Gartenzwerg"]'
q.max_hits = 10
q.attributes = ['word', 'tag']
q.structures = ['s']
q.references = [
'doc.url', 'doc.bdc', 'doc.tld', 'doc.id', 'div.bpc', 's.idx', 's.type'
]
q.container = 's'
q.set_deduplication()
# The concordance loader has just one settable attribute.
p = ConcordanceLoader()
p.full_structure = True # Convert token attributes to dicts as well, otherwise |-separated.
q.processor = p
q.run()
# Now you have a nice structured Python object in p.concordance.
# The json library just provides a convenient way of displaying the
# resulting structures.
print json.dumps(p.concordance[0:2], sort_keys=False, indent=2)
# -*- coding: utf-8 -*-
from SeaCOW import Query, ConcordanceWriter, DependencyBuilder
# Create a Query object and set whatever needs to be set.
q = Query()
q.corpus = 'decow16a-nano' # Lower-case name of the corpusto use.
q.string = '[word="Motorsäge"]' # A normal CQL string as used in NoSketchEngine.
q.max_hits = 10 # Maximal number of hits to return. Use when testing queries!
q.structures = ['s'] # Structure markup to export from corpus.
q.references = [
'doc.url', 'doc.bdc', 'doc.tld', 'doc.id', 'div.bpc', 's.idx', 's.type'
]
# Which reference attributes (of structures) to export.
q.container = 's' # Which container strutcure should be exported?
q.set_deduplication() # Use deduplication.
# The dependency attributes are needed for DependencyBuilder() to work.
q.attributes = ['word', 'depind', 'dephd', 'deprel', 'tag', 'lemma']
# The dependency builder reconstructs (and outputs) dependency trees.
# If you want to filter structures, create a class which inherits from
# DependencyBuilder and override the filtre() method (NO TYPO there).
p = DependencyBuilder()
# The following five are 0-based indeces into q.attributes as defined above.
p.column_token = 0 # Which column contains the token?
p.column_index = 1 # Which column contains the dependency index?
p.column_head = 2 # Which column contains the dependency head index?
p.column_relation = 3 # Which column contains the dependency relation?
p.attribs = [4,
# -*- coding: utf-8 -*-
from SeaCOW import Query, ConcordanceWriter, DependencyBuilder
from iterated import IterativelyFiltredDependencyBuilder
# FIRST QUERY.
# Create a Query object and set whatever needs to be set.
q = Query()
q.corpus = 'encow16a-nano'
q.string = '[word="give" & tag="VB[ZPD]"]'
q.max_hits = 100
q.attributes = ['word', 'depind', 'dephd', 'deprel', 'tag', 'lemma']
q.structures = ['s']
q.references = [
'doc.url', 'doc.bdc', 'doc.tld', 'doc.id', 'div.bpc', 's.idx', 's.type'
]
q.container = 's'
# This enables an efficient duplicate remover using a scaling Bloom filter.
q.set_deduplication()
p = IterativelyFiltredDependencyBuilder()
p.column_token = 0
p.column_index = 1
p.column_head = 2
p.column_relation = 3
p.attribs = [4, 5]
p.fileprefix = 'give_iterated'
p.savejson = True
p.saveimage = 'png'
# -*- coding: utf-8 -*- # This dumps a very raw concordance format. # It's very efficient, though. # See samply.py for options. from SeaCOW import Query, ConcordanceDumper q = Query() q.corpus = 'decow16b' q.string = '[word="Holzweg"]' q.max_hits = 10 q.attributes = ['word'] q.structures = ['s'] q.references = ['doc.url', 'doc.id', 's.idx'] q.container = 's' q.set_deduplication() p = ConcordanceDumper() p.filename = 'output/holzweg.txt' q.processor = p q.run()
# -*- coding: utf-8 -*- import random from SeaCOW import Query, ConcordanceWriter, DependencyBuilder random.seed(2914) q = Query() q.corpus = 'precox20lda25' q.string = '<doc id="[0-9a-f].+">' q.random_subset = 0.09 q.attributes = ['word'] q.structures = ['s.idx', 'div.bpc', 'doc.bdc', 'doc.url', 'doc.id', 'doc.pregister', 'doc.pregbrob'] q.references = ['doc.url', 'doc.id'] q.container = 'doc' p = ConcordanceWriter() p.filename = 'sample.csv' q.processor = p q.run()
# -*- coding: utf-8 -*- # This dumps a very raw concordance format. # It's very efficient, though. # See samply.py for options. from SeaCOW import Query, ConcordanceDumper q = Query() q.corpus = 'encow16a-nano' q.string = '[tag="N."][word="attention"]' q.max_hits = -1 q.attributes = ['word'] q.structures = ['s'] q.references = ['doc.url', 'doc.id', 's.idx'] q.container = 's' q.set_deduplication() p = ConcordanceDumper() p.filename = 'dump.txt' q.processor = p q.run()