X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/f70930b1a04629a33241047586bda54bc0176dc7..779ea8ac624187850752544eae0209f811bc1551:/nominatim/tokenizer/icu_rule_loader.py diff --git a/nominatim/tokenizer/icu_rule_loader.py b/nominatim/tokenizer/icu_rule_loader.py index 6bf23201..0e6e40b4 100644 --- a/nominatim/tokenizer/icu_rule_loader.py +++ b/nominatim/tokenizer/icu_rule_loader.py @@ -3,30 +3,55 @@ Helper class to create ICU rules from a configuration file. """ import io import logging -from collections import defaultdict import itertools +import re -import yaml from icu import Transliterator from nominatim.errors import UsageError +import nominatim.tokenizer.icu_variants as variants LOG = logging.getLogger() +def _flatten_config_list(content): + if not content: + return [] + + if not isinstance(content, list): + raise UsageError("List expected in ICU configuration.") + + output = [] + for ele in content: + if isinstance(ele, list): + output.extend(_flatten_config_list(ele)) + else: + output.append(ele) + + return output + + +class VariantRule: + """ Saves a single variant expansion. + + An expansion consists of the normalized replacement term and + a dicitonary of properties that describe when the expansion applies. + """ + + def __init__(self, replacement, properties): + self.replacement = replacement + self.properties = properties or {} + class ICURuleLoader: """ Compiler for ICU rules from a tokenizer configuration file. """ - def __init__(self, configfile): - self.configfile = configfile - self.compound_suffixes = set() - self.abbreviations = defaultdict() + def __init__(self, rules): + self.variants = set() - if configfile.suffix == '.yaml': - self._load_from_yaml() - else: - raise UsageError("Unknown format of tokenizer configuration.") + self.normalization_rules = self._cfg_to_icu_rules(rules, 'normalization') + self.transliteration_rules = self._cfg_to_icu_rules(rules, 'transliteration') + self._parse_variant_list(self._get_section(rules, 'variants')) def get_search_rules(self): @@ -57,53 +82,16 @@ class ICURuleLoader: The result is a list of pairs: the first item is the sequence to replace, the second is a list of replacements. """ - synonyms = defaultdict(set) - - # First add entries for compound decomposition. - for suffix in self.compound_suffixes: - variants = (suffix + ' ', ' ' + suffix + ' ') - for key in variants: - synonyms[key].update(variants) - - for full, abbr in self.abbreviations.items(): - key = ' ' + full + ' ' - # Entries in the abbreviation list always apply to full words: - synonyms[key].update((' ' + a + ' ' for a in abbr)) - # Replacements are optional, so add a noop - synonyms[key].add(key) + return self.variants - if full in self.compound_suffixes: - # Full word abbreviating to compunded version. - synonyms[key].update((a + ' ' for a in abbr)) - key = full + ' ' - # Uncompunded suffix abbrevitating to decompounded version. - synonyms[key].update((' ' + a + ' ' for a in abbr)) - # Uncompunded suffix abbrevitating to compunded version. - synonyms[key].update((a + ' ' for a in abbr)) - - # sort the resulting list by descending length (longer matches are prefered). - sorted_keys = sorted(synonyms.keys(), key=len, reverse=True) - - return [(k, list(synonyms[k])) for k in sorted_keys] - - - def _load_from_yaml(self): - rules = yaml.safe_load(self.configfile.read_text()) - - self.normalization_rules = self._cfg_to_icu_rules(rules, 'normalization') - self.transliteration_rules = self._cfg_to_icu_rules(rules, 'transliteration') - self._parse_compound_suffix_list(self._get_section(rules, 'compound_suffixes')) - self._parse_abbreviation_list(self._get_section(rules, 'abbreviations')) - - - def _get_section(self, rules, section): + @staticmethod + def _get_section(rules, section): """ Get the section named 'section' from the rules. If the section does not exist, raise a usage error with a meaningful message. """ if section not in rules: - LOG.fatal("Section '%s' not found in tokenizer config '%s'.", - section, str(self.configfile)) + LOG.fatal("Section '%s' not found in tokenizer config.", section) raise UsageError("Syntax error in tokenizer configuration file.") return rules[section] @@ -121,43 +109,114 @@ class ICURuleLoader: if content is None: return '' - if isinstance(content, str): - return (self.configfile.parent / content).read_text().replace('\n', ' ') + return ';'.join(_flatten_config_list(content)) + ';' - return ';'.join(content) + ';' + def _parse_variant_list(self, rules): + self.variants.clear() - def _parse_compound_suffix_list(self, rules): if not rules: - self.compound_suffixes = set() return - norm = Transliterator.createFromRules("rule_loader_normalization", - self.normalization_rules) + rules = _flatten_config_list(rules) - # Make sure all suffixes are in their normalised form. - self.compound_suffixes = set((norm.transliterate(s) for s in rules)) + vmaker = _VariantMaker(self.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) - def _parse_abbreviation_list(self, rules): - self.abbreviations = defaultdict(list) + for rule in (section.get('words') or []): + self.variants.update(vmaker.compute(rule, props)) - if not rules: - return - norm = Transliterator.createFromRules("rule_loader_normalization", - self.normalization_rules) +class _VariantMaker: + """ Generater for all necessary ICUVariants from a single variant rule. - for rule in rules: - parts = rule.split('=>') - if len(parts) != 2: - LOG.fatal("Syntax error in abbreviation section, line: %s", rule) - raise UsageError("Syntax error in tokenizer configuration file.") + All text in rules is normalized to make sure the variants match later. + """ + + def __init__(self, norm_rules): + self.norm = Transliterator.createFromRules("rule_loader_normalization", + norm_rules) - # Make sure all terms match the normalised version. - fullterms = (norm.transliterate(t.strip()) for t in parts[0].split(',')) - abbrterms = (norm.transliterate(t.strip()) for t in parts[1].split(',')) - for full, abbr in itertools.product(fullterms, abbrterms): - if full and abbr: - self.abbreviations[full].append(abbr) + def compute(self, rule, props): + """ Generator for all ICUVariant tuples from a single variant rule. + """ + parts = re.split(r'(\|)?([=-])>', rule) + if len(parts) != 4: + raise UsageError("Syntax error in variant rule: " + rule) + + 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(',')) + + # 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) + + 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) + + + def _parse_variant_word(self, name): + name = name.strip() + 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)) + if not norm_name: + return None + + return norm_name, match.group(1), match.group(3) + + +_FLAG_MATCH = {'^': '^ ', + '$': ' ^', + '': ' '} + + +def _create_variants(src, preflag, postflag, repl, decompose): + if preflag == '~': + postfix = _FLAG_MATCH[postflag] + # suffix decomposition + src = src + postfix + repl = repl + postfix + + yield src, repl + yield ' ' + src, ' ' + repl + + if decompose: + yield src, ' ' + repl + yield ' ' + src, repl + elif postflag == '~': + # prefix decomposition + prefix = _FLAG_MATCH[preflag] + src = prefix + src + repl = prefix + repl + + yield src, repl + yield src + ' ', repl + ' ' + + if decompose: + yield src, repl + ' ' + yield src + ' ', repl + else: + prefix = _FLAG_MATCH[preflag] + postfix = _FLAG_MATCH[postflag] + + yield prefix + src + postfix, prefix + repl + postfix