X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/c171d881945e8c744e4a4a44c5f33edd0d8468fb..c4f22a42eba499ed1854c5967b2e3932fe9b3896:/nominatim/tokenizer/token_analysis/generic.py?ds=sidebyside diff --git a/nominatim/tokenizer/token_analysis/generic.py b/nominatim/tokenizer/token_analysis/generic.py index f0de0cca..f790dad2 100644 --- a/nominatim/tokenizer/token_analysis/generic.py +++ b/nominatim/tokenizer/token_analysis/generic.py @@ -1,7 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# This file is part of Nominatim. (https://nominatim.org) +# +# Copyright (C) 2022 by the Nominatim developer community. +# For a full list of authors see the git log. """ Generic processor for names that creates abbreviation variants. """ -from collections import defaultdict +from collections import defaultdict, namedtuple import itertools import re @@ -10,41 +16,50 @@ import datrie from nominatim.config import flatten_config_list from nominatim.errors import UsageError -import nominatim.tokenizer.icu_variants as variants ### Configuration section +ICUVariant = namedtuple('ICUVariant', ['source', 'replacement']) + def configure(rules, normalization_rules): """ Extract and preprocess the configuration for this module. """ - return {'variants': _parse_variant_list(rules.get('variants'), - normalization_rules)} + config = {} + + config['replacements'], config['chars'] = _get_variant_config(rules.get('variants'), + normalization_rules) + config['variant_only'] = rules.get('mode', '') == 'variant-only' + return config -def _parse_variant_list(rules, normalization_rules): - vset = set() + +def _get_variant_config(rules, normalization_rules): + """ Convert the variant definition from the configuration into + replacement sets. + """ + immediate = defaultdict(list) + chars = set() if rules: + vset = set() rules = flatten_config_list(rules, 'variants') vmaker = _VariantMaker(normalization_rules) - properties = [] for section in rules: - # Create the property field and deduplicate against existing - # instances. - props = variants.ICUVariantProperties.from_rules(section) - for existing in properties: - if existing == props: - props = existing - break - else: - properties.append(props) - for rule in (section.get('words') or []): - vset.update(vmaker.compute(rule, props)) + vset.update(vmaker.compute(rule)) + + # Intermediate reorder by source. Also compute required character set. + for variant in vset: + if variant.source[-1] == ' ' and variant.replacement[-1] == ' ': + replstr = variant.replacement[:-1] + else: + replstr = variant.replacement + immediate[variant.source].append(replstr) + chars.update(variant.source) - return vset + return list(immediate.items()), ''.join(chars) class _VariantMaker: @@ -58,7 +73,7 @@ class _VariantMaker: norm_rules) - def compute(self, rule, props): + def compute(self, rule): """ Generator for all ICUVariant tuples from a single variant rule. """ parts = re.split(r'(\|)?([=-])>', rule) @@ -67,19 +82,19 @@ class _VariantMaker: decompose = parts[1] is None src_terms = [self._parse_variant_word(t) for t in parts[0].split(',')] - repl_terms = (self.norm.transliterate(t.strip()) for t in parts[3].split(',')) + repl_terms = (self.norm.transliterate(t).strip() for t in parts[3].split(',')) # If the source should be kept, add a 1:1 replacement if parts[2] == '-': for src in src_terms: if src: for froms, tos in _create_variants(*src, src[0], decompose): - yield variants.ICUVariant(froms, tos, props) + yield ICUVariant(froms, tos) for src, repl in itertools.product(src_terms, repl_terms): if src and repl: for froms, tos in _create_variants(*src, repl, decompose): - yield variants.ICUVariant(froms, tos, props) + yield ICUVariant(froms, tos) def _parse_variant_word(self, name): @@ -87,7 +102,7 @@ class _VariantMaker: match = re.fullmatch(r'([~^]?)([^~$^]*)([~$]?)', name) if match is None or (match.group(1) == '~' and match.group(3) == '~'): raise UsageError("Invalid variant word descriptor '{}'".format(name)) - norm_name = self.norm.transliterate(match.group(2)) + norm_name = self.norm.transliterate(match.group(2)).strip() if not norm_name: return None @@ -133,10 +148,10 @@ def _create_variants(src, preflag, postflag, repl, decompose): ### Analysis section -def create(norm_rules, trans_rules, config): +def create(transliterator, config): """ Create a new token analysis instance for this module. """ - return GenericTokenAnalysis(norm_rules, trans_rules, config['variants']) + return GenericTokenAnalysis(transliterator, config) class GenericTokenAnalysis: @@ -144,37 +159,19 @@ class GenericTokenAnalysis: and provides the functions to apply the transformations. """ - def __init__(self, norm_rules, trans_rules, replacements): - self.normalizer = Transliterator.createFromRules("icu_normalization", - norm_rules) - self.to_ascii = Transliterator.createFromRules("icu_to_ascii", - trans_rules + - ";[:Space:]+ > ' '") - self.search = Transliterator.createFromRules("icu_search", - norm_rules + trans_rules) + def __init__(self, to_ascii, config): + self.to_ascii = to_ascii + self.variant_only = config['variant_only'] - # Intermediate reorder by source. Also compute required character set. - immediate = defaultdict(list) - chars = set() - for variant in replacements: - if variant.source[-1] == ' ' and variant.replacement[-1] == ' ': - replstr = variant.replacement[:-1] - else: - replstr = variant.replacement - immediate[variant.source].append(replstr) - chars.update(variant.source) - # Then copy to datrie - self.replacements = datrie.Trie(''.join(chars)) - for src, repllist in immediate.items(): - self.replacements[src] = repllist + # Set up datrie + if config['replacements']: + self.replacements = datrie.Trie(config['chars']) + for src, repllist in config['replacements']: + self.replacements[src] = repllist + else: + self.replacements = None - def get_normalized(self, name): - """ Normalize the given name, i.e. remove all elements not relevant - for search. - """ - return self.normalizer.transliterate(name).strip() - def get_variants_ascii(self, norm_name): """ Compute the spelling variants for the given normalized name and transliterate the result. @@ -183,52 +180,51 @@ class GenericTokenAnalysis: partials = [''] startpos = 0 - pos = 0 - force_space = False - while pos < len(baseform): - full, repl = self.replacements.longest_prefix_item(baseform[pos:], - (None, None)) - if full is not None: - done = baseform[startpos:pos] - partials = [v + done + r - for v, r in itertools.product(partials, repl) - if not force_space or r.startswith(' ')] - if len(partials) > 128: - # If too many variants are produced, they are unlikely - # to be helpful. Only use the original term. - startpos = 0 - break - startpos = pos + len(full) - if full[-1] == ' ': - startpos -= 1 - force_space = True - pos = startpos - else: - pos += 1 - force_space = False + if self.replacements is not None: + pos = 0 + force_space = False + while pos < len(baseform): + full, repl = self.replacements.longest_prefix_item(baseform[pos:], + (None, None)) + if full is not None: + done = baseform[startpos:pos] + partials = [v + done + r + for v, r in itertools.product(partials, repl) + if not force_space or r.startswith(' ')] + if len(partials) > 128: + # If too many variants are produced, they are unlikely + # to be helpful. Only use the original term. + startpos = 0 + break + startpos = pos + len(full) + if full[-1] == ' ': + startpos -= 1 + force_space = True + pos = startpos + else: + pos += 1 + force_space = False # No variants detected? Fast return. if startpos == 0: + if self.variant_only: + return [] + trans_name = self.to_ascii.transliterate(norm_name).strip() return [trans_name] if trans_name else [] - return self._compute_result_set(partials, baseform[startpos:]) + return self._compute_result_set(partials, baseform[startpos:], + norm_name if self.variant_only else '') - def _compute_result_set(self, partials, prefix): + def _compute_result_set(self, partials, prefix, exclude): results = set() for variant in partials: - vname = variant + prefix - trans_name = self.to_ascii.transliterate(vname[1:-1]).strip() - if trans_name: - results.add(trans_name) + vname = (variant + prefix)[1:-1].strip() + if vname != exclude: + trans_name = self.to_ascii.transliterate(vname).strip() + if trans_name: + results.add(trans_name) return list(results) - - - def get_search_normalized(self, name): - """ Return the normalized version of the name (including transliteration) - to be applied at search time. - """ - return self.search.transliterate(' ' + name + ' ').strip()