From: Sarah Hoffmann Date: Mon, 4 Oct 2021 15:34:30 +0000 (+0200) Subject: make token analyzers configurable modules X-Git-Tag: v4.0.0~22^2~9 X-Git-Url: https://git.openstreetmap.org./nominatim.git/commitdiff_plain/7cfcbacfc75ab2e39ee7eab6a5cf40e8cbd152f5?hp=52847b61a3e1bc0791dd23809dc3c50fe6810df2 make token analyzers configurable modules Adds a mandatory section 'analyzer' to the token-analysis entries which define, which analyser to use. Currently there is exactly one, generic, which implements the former ICUNameProcessor. --- diff --git a/nominatim/tokenizer/icu_rule_loader.py b/nominatim/tokenizer/icu_rule_loader.py index cf725209..a8bdba93 100644 --- a/nominatim/tokenizer/icu_rule_loader.py +++ b/nominatim/tokenizer/icu_rule_loader.py @@ -1,6 +1,7 @@ """ Helper class to create ICU rules from a configuration file. """ +import importlib import io import json import logging @@ -12,7 +13,6 @@ from icu import Transliterator from nominatim.config import flatten_config_list from nominatim.db.properties import set_property, get_property from nominatim.errors import UsageError -from nominatim.tokenizer.icu_name_processor import ICUNameProcessor from nominatim.tokenizer.place_sanitizer import PlaceSanitizer import nominatim.tokenizer.icu_variants as variants @@ -23,6 +23,17 @@ DBCFG_IMPORT_TRANS_RULES = "tokenizer_import_transliteration" DBCFG_IMPORT_ANALYSIS_RULES = "tokenizer_import_analysis_rules" +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.", section) + raise UsageError("Syntax error in tokenizer configuration file.") + + return rules[section] + + class VariantRule: """ Saves a single variant expansion. @@ -45,7 +56,7 @@ class ICURuleLoader: self.normalization_rules = self._cfg_to_icu_rules(rules, 'normalization') self.transliteration_rules = self._cfg_to_icu_rules(rules, 'transliteration') - self.analysis_rules = self._get_section(rules, 'token-analysis') + self.analysis_rules = _get_section(rules, 'token-analysis') self._setup_analysis() # Load optional sanitizer rule set. @@ -130,25 +141,14 @@ class ICURuleLoader: @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.", section) - raise UsageError("Syntax error in tokenizer configuration file.") - - return rules[section] - - - def _cfg_to_icu_rules(self, rules, section): + def _cfg_to_icu_rules(rules, section): """ Load an ICU ruleset from the given section. If the section is a simple string, it is interpreted as a file name and the rules are loaded verbatim from the given file. The filename is expected to be relative to the tokenizer rule file. If the section is a list then each line is assumed to be a rule. All rules are concatenated and returned. """ - content = self._get_section(rules, section) + content = _get_section(rules, section) if content is None: return '' @@ -162,19 +162,27 @@ class TokenAnalyzerRule: """ def __init__(self, rules, normalization_rules): + # Find the analysis module + module_name = 'nominatim.tokenizer.token_analysis.' \ + + _get_section(rules, 'analyzer').replace('-', '_') + analysis_mod = importlib.import_module(module_name) + self._mod_create = analysis_mod.create + + # Load the configuration. + self.config = {} self._parse_variant_list(rules.get('variants'), normalization_rules) def create(self, normalization_rules, transliteration_rules): """ Create an analyzer from the given rules. """ - return ICUNameProcessor(normalization_rules, + return self._mod_create(normalization_rules, transliteration_rules, - self.variants) + self.config) def _parse_variant_list(self, rules, normalization_rules): - self.variants = set() + vset = set() if not rules: return @@ -196,7 +204,9 @@ class TokenAnalyzerRule: properties.append(props) for rule in (section.get('words') or []): - self.variants.update(vmaker.compute(rule, props)) + vset.update(vmaker.compute(rule, props)) + + self.config['variants'] = vset class _VariantMaker: diff --git a/nominatim/tokenizer/token_analysis/__init__.py b/nominatim/tokenizer/token_analysis/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/nominatim/tokenizer/icu_name_processor.py b/nominatim/tokenizer/token_analysis/generic.py similarity index 92% rename from nominatim/tokenizer/icu_name_processor.py rename to nominatim/tokenizer/token_analysis/generic.py index 544f5ebc..2c720f1d 100644 --- a/nominatim/tokenizer/icu_name_processor.py +++ b/nominatim/tokenizer/token_analysis/generic.py @@ -1,6 +1,5 @@ """ -Processor for names that are imported into the database based on the -ICU library. +Generic processor for names that creates abbreviation variants. """ from collections import defaultdict import itertools @@ -8,8 +7,15 @@ import itertools from icu import Transliterator import datrie +### Analysis section -class ICUNameProcessor: +def create(norm_rules, trans_rules, config): + """ Create a new token analysis instance for this module. + """ + return GenericTokenAnalysis(norm_rules, trans_rules, config['variants']) + + +class GenericTokenAnalysis: """ Collects the different transformation rules for normalisation of names and provides the functions to apply the transformations. """ diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml index f85c33ff..d070adcb 100644 --- a/settings/icu_tokenizer.yaml +++ b/settings/icu_tokenizer.yaml @@ -28,7 +28,8 @@ sanitizers: - step: split-name-list - step: strip-brace-terms token-analysis: - - variants: + - analyzer: generic + variants: - !include icu-rules/variants-bg.yaml - !include icu-rules/variants-ca.yaml - !include icu-rules/variants-cs.yaml diff --git a/test/python/test_tokenizer_icu.py b/test/python/test_tokenizer_icu.py index 16caf3ed..52cca6a7 100644 --- a/test/python/test_tokenizer_icu.py +++ b/test/python/test_tokenizer_icu.py @@ -72,7 +72,8 @@ def analyzer(tokenizer_factory, test_config, monkeypatch, cfgstr = {'normalization': list(norm), 'sanitizers': sanitizers, 'transliteration': list(trans), - 'token-analysis': [{'variants': [{'words': list(variants)}]}]} + 'token-analysis': [{'analyzer': 'generic', + 'variants': [{'words': list(variants)}]}]} (test_config.project_dir / 'icu_tokenizer.yaml').write_text(yaml.dump(cfgstr)) tok.loader = ICURuleLoader(test_config) diff --git a/test/python/test_tokenizer_icu_rule_loader.py b/test/python/test_tokenizer_icu_rule_loader.py index 5d931043..b76eee75 100644 --- a/test/python/test_tokenizer_icu_rule_loader.py +++ b/test/python/test_tokenizer_icu_rule_loader.py @@ -34,7 +34,7 @@ def cfgrules(test_config): - ":: Latin ()" - "[[:Punctuation:][:Space:]]+ > ' '" """) - content += "token-analysis:\n - variants:\n - words:\n" + content += "token-analysis:\n - analyzer: generic\n variants:\n - words:\n" content += '\n'.join((" - " + s for s in variants)) + '\n' for k, v in kwargs: content += " {}: {}\n".format(k, v) @@ -50,7 +50,8 @@ def test_empty_rule_set(test_config): normalization: transliteration: token-analysis: - - variants: + - analyzer: generic + variants: """)) rules = ICURuleLoader(test_config) @@ -108,7 +109,8 @@ def test_transliteration_rules_from_file(test_config): - "'ax' > 'b'" - !include transliteration.yaml token-analysis: - - variants: + - analyzer: generic + variants: """)) transpath = test_config.project_dir / ('transliteration.yaml') transpath.write_text('- "x > y"') @@ -128,7 +130,7 @@ class TestGetReplacements: def get_replacements(self, *variants): loader = ICURuleLoader(self.cfgrules(*variants)) - rules = loader.analysis[None].variants + rules = loader.analysis[None].config['variants'] return set((v.source, v.replacement) for v in rules) diff --git a/test/python/test_tokenizer_icu_name_processor.py b/test/python/tokenizer/token_analysis/test_generic.py similarity index 97% rename from test/python/test_tokenizer_icu_name_processor.py rename to test/python/tokenizer/token_analysis/test_generic.py index 366d2aee..f0ce4208 100644 --- a/test/python/test_tokenizer_icu_name_processor.py +++ b/test/python/tokenizer/token_analysis/test_generic.py @@ -28,7 +28,7 @@ def cfgfile(def_config, tmp_path): - ":: Latin ()" - "'🜵' > ' '" """) - content += "token-analysis:\n - variants:\n - words:\n" + content += "token-analysis:\n - analyzer: generic\n variants:\n - words:\n" content += '\n'.join((" - " + s for s in variants)) + '\n' for k, v in kwargs: content += " {}: {}\n".format(k, v)