luscenje_struktur/src/match_store.py

from collections import defaultdict

from match import StructureMatch
from representation_assigner import RepresentationAssigner
from progress_bar import progress

class MatchStore:
    def __init__(self, args):
        self.data = {}
        self.min_frequency = args.min_freq
        self.dispersions = {}

    def _add_match(self, key, structure, match):
        if key not in self.data:
            self.data[key] = StructureMatch(str(len(self.data) + 1), structure)
        self.data[key].append(match)

    def get(self, key, n):
        return self.data[key][n]

    def add_matches(self, matches):
        for structure, nms in matches.items():
            for nm in nms:
                self._add_match(nm[1], structure, nm[0])

    def get_matches_for(self, structure):
        for _cid_tup, sm in self.data.items():
            if sm.structure != structure:
                continue

            yield sm

    def set_representations(self, word_renderer):
        for _1, sm in progress(self.data.items(), "representations"):
            RepresentationAssigner.set_representations(sm, word_renderer)

    def determine_colocation_dispersions(self):
        dispersions = defaultdict(int)
        for (structure_id, *word_tups) in self.data.keys():
            for component_id, lemma in word_tups:
                dispersions[(structure_id, component_id, lemma)] += 1
        self.dispersions = dict(dispersions)