How to use _adjust_match method in localstack

Best Python code snippet using localstack_python

generic_proxy.py

Source:generic_proxy.py

...267                return source268        elif not isinstance(source, str):269            # Ignore any other types270            return source271        return self.arn_regex.sub(lambda m: self._adjust_match(m, static_partition), source)272    def _adjust_match(self, match: Match, static_partition: str = None):273        region = match.group("Region")274        partition = self._partition_lookup(region) if static_partition is None else static_partition275        service = match.group("Service")276        account_id = match.group("AccountID")277        resource_path = match.group("ResourcePath")278        return f"arn:{partition}:{service}:{region}:{account_id}:{resource_path}"279    def _partition_lookup(self, region: str):280        try:281            partition = self._get_partition_for_region(region)282        except ArnPartitionRewriteListener.InvalidRegionException:283            try:284                # If the region is not properly set (f.e. because it is set to a wildcard),285                # the partition is determined based on the default region.286                partition = self._get_partition_for_region(config.DEFAULT_REGION)...

TMMatching.py

Source:TMMatching.py

...67      else: break68    return l_best_segments69  # Estimate TER between sources segmets.70  def ter_score(self, src_x, src_y): return pyter.ter(src_x.split(), src_y.split())71  def _adjust_match(self, segment, filter, ter):72    if ter > 1:73      ter = 174    ter = (100 - (ter * 100))75    if filter:76      # Penalize match if segment doesn't match filter77      for fname, fvalues in filter.items():78        if fvalues and not set(fvalues) & set(segment[fname]):79          ter -= 580    return ter81  #Check 100% match82  def _cen_p_match(self, l_best_segments):83    #print(l_best_segments)84    segment = l_best_segments[0][0]85    match = l_best_segments[0][1]86    ter = self.ter_score(self.src_input, segment['source_text'])87    logging.info("initial ter: {}".format(ter))88    if match == 100 and 'Q' not in segment.keys() and ter == 0:  # 100% match --> Return match considering domain89        # logging.info("source: {}, tm_source: {}, tm_target: {}, match: {}".format(src_input, segment['source_text'], segment['target_text'], str(ter)))90       self.dic_match = self._create_dic_match(segment, ter)91    return self.dic_match92  def _create_dic_match(self, segment, ter):93    filter = {'domain': ['Automotive']}94    print(filter)95    self.dic_match['tm_src'] = segment['source_text']96    print(self.dic_match['tm_src'])97    self.dic_match['tm_tgt'] = segment['target_text']98    print(self.dic_match['tm_tgt'])99    self.dic_match['match'] = self._adjust_match(segment, filter, ter)100    print(self.dic_match)101    return self.dic_match102  def fuzzy_match(self, l_best_segments):103    logging.info("Improve Fuzzy match")104    fuzzy_alg = TMFuzzyMatch(self.src_input, self.src_lang, self.tgt_lang, self.dic_match, self.threshold, l_best_segments) #Class to improve fuzzy match105    self.dic_match = fuzzy_alg.process()106    return self.dic_match107  def fuzzy_match_posTagger(self, l_best_segments):108    logging.info("Improve Fuzzy match pos tagger")109    fuzzy_alg = TMFuzzyMatch_PosTagger(self.src_input, self.src_lang, self.tgt_lang, self.dic_match, self.threshold,110                             l_best_segments)  # Class to improve fuzzy match111    self.dic_match = fuzzy_alg.process()112    return self.dic_match113    # ************It is necessary check the domain***************114  #   if (improve_ter <= ter) and (115  #             improve_ter < 0.25):  # Fuzzy Match and was possible improve ter value --> Return match considering domain116  #     print("source: " + src_input + ' tm_target: ' + process_match['reg_exp']['tm_tgt_re'] + ' Match: ' + str(117  #       self._adjust_match(segment, filter, improve_ter)))118  #     break119  #   if (120  #               count == 10 or improve_ter > ter) and ter < 0.25:  # Fuzzy Match, but wasn't improved ter value --> Return elasticsearch match121  #     print("source: " + src_input + ' tm_target: ' + segment['target_text'] + ' Match: ' + str(122  #       self._adjust_match(segment, filter, ter)))123  #     todo_ok = False124  #     break125  #126  # else:127  # todo_ok = False128# ************************************************************************************129class TMFuzzyMatch(TMMatching):130  def __init__(self, src_input, src_lang, tgt_lang, dic_match, threshold, l_best_segments):131    super().__init__(src_input, src_lang, tgt_lang, dic_match, threshold)132    self.l_best_segments = l_best_segments133    #self.pipe = ['tokenizer', 'reg_exp', 'pos_tagger', 'sent_split']134    #self.processor = {'reg_exp': TMRegExpPreprocessor(),135    #                  'sent_split': 'split'}  # TMSplitPreprocessor()136  def pre_process(self, text, lang, preprocess):...

TMDbApi.py

Source:TMDbApi.py

...378        break379      # Adjust match % according to filters380      if ter >= qparams.min_match:381        self.timer.start("adjust_match")382        ter = self._adjust_match(segment, qparams.domains, ter)383        self.timer.stop("adjust_match")384        new_segments.append((segment, ter))385        match = True386      elif qparams.aut_trans and len(segments) == 1: # Mark segment as one needed to machine-translate387        match = False388        new_segments.append((segment, ter))389    new_segments.sort(key = lambda x: (x[1], x[0].tm_change_date) if (x[0].tm_change_date is not None) else (x[1], str(datetime.datetime(1970, 1, 1))), reverse = True)390    logging.info("New match segments: {}".format(new_segments))391    tm_match.timer.print()392    return new_segments, match393  def _add_segments(self, segments):394    batch_status = []395    self.timer.start("add_segments:source")396    batch_status.append(self.ml_index.add_segments(segments, 'source'))397    self.timer.stop("add_segments:source")398    self.timer.start("add_segments:target")399    batch_status.append(self.ml_index.add_segments(segments, 'target'))400    self.timer.stop("add_segments:target")401    self.timer.start("add_segments:map")402    batch_status.append(self.seg_map.add_segments(segments))403    self.timer.stop("add_segments:map")404    logging.info('Added {} segments, status: {}'.format(len(segments), batch_status))405    return batch_status406  def _find_pivot_lang(self, langs):407    langs = [l.lower() for l in langs]408    lang_graph = self.seg_map.get_lang_graph()409    path_len = shortest_path_length(lang_graph, langs[0], langs[1])410    if path_len != 2:411      return None412    # Find shortest path413    path = shortest_path(lang_graph, langs[0], langs[1])414    assert (len(path) == 3)415    # Get a pivot language and scan all pivot segments416    return path[1]417  def _src_id2tgt_id(self, src_id, source_lang, target_lang):418    # Query  mapping segment419    target_id,map_doc = self.seg_map.get(uuid.UUID(src_id), source_lang, target_lang)420    if not target_id:421      logging.warning("Can't find matching segment for {}".format(src_id))422      return None,None423    else:424      assert isinstance(target_id, uuid.UUID)425    return target_id,map_doc426  def _msrc_id2tgt_id(self, src_hits, source_lang, target_lang, return_multiple=False):427    margs = [(uuid.UUID(src_hit.meta.id), source_lang, target_lang) for src_hit in src_hits]428    return self.seg_map.mget(margs, return_multiple=return_multiple)429  def _delete(self, langs, docs, filter, force_delete):430    source_lang, target_lang = langs431    # Delete map doc, returns tuple of 2 lists: deleted source and target ids432    deleted_ids = self.seg_map.delete(langs, docs, filter, force_delete)433    logging.info("After deleting from map: {} source and {} target potential orphan segments".format(len(deleted_ids[0]), len(deleted_ids[1])))434    # Check and delete only orphans (for source and target)435    for lang,ids in zip(langs,deleted_ids):436      ids_exist = self.seg_map.mexist(source_lang, ids)437      ids_to_delete = [id for id,exists in zip(ids, ids_exist) if not exists]438      logging.info("Lang: {}, actual orphans to delete: {}".format(lang.upper(), len(ids_to_delete)))439      self.ml_index.delete(lang, ids_to_delete)440  def _doc2segment(self, md, sd=None, td=None):441    doc = md442    if sd: doc['source_pos'] = sd.get('pos')443    if td: doc['target_pos'] = td.get('pos')444    segment = TMTranslationUnit(doc)445    return segment446  def _adjust_match(self, segment, domains, match):447    if domains:448      if not set(domains) & set(getattr(segment, 'domain')):449        match -= self.QUERY_PENALIZE[0]450    if self._is_dirty(segment):451      match -= self.QUERY_PENALIZE[1]452    return match453  def _is_dirty(self, segment):454    if segment.dirty_score and segment.dirty_score >= self.DIRTY_THRESHOLD:455      return True456    return False457if __name__ == "__main__":458  logging.basicConfig(format='%(levelname)s:%(message)s', level=logging.INFO)459  tmdb = TMDbApi()460  #tmdb.init_db()...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.