Helper class to create ICU rules from a configuration file.
"""
import io
+import json
import logging
import itertools
-from pathlib import Path
import re
-import yaml
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
LOG = logging.getLogger()
-def _flatten_yaml_list(content):
- if not content:
- return []
-
- if not isinstance(content, list):
- raise UsageError("List expected in ICU yaml configuration.")
-
- output = []
- for ele in content:
- if isinstance(ele, list):
- output.extend(_flatten_yaml_list(ele))
- else:
- output.append(ele)
-
- return output
+DBCFG_IMPORT_NORM_RULES = "tokenizer_import_normalisation"
+DBCFG_IMPORT_TRANS_RULES = "tokenizer_import_transliteration"
+DBCFG_IMPORT_ANALYSIS_RULES = "tokenizer_import_analysis_rules"
class VariantRule:
""" Compiler for ICU rules from a tokenizer configuration file.
"""
- def __init__(self, configfile):
- self.configfile = configfile
- self.variants = set()
+ def __init__(self, config):
+ rules = config.load_sub_configuration('icu_tokenizer.yaml',
+ config='TOKENIZER_CONFIG')
+
+ 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._setup_analysis()
+
+ # Load optional sanitizer rule set.
+ self.sanitizer_rules = rules.get('sanitizers', [])
+
+
+ def load_config_from_db(self, conn):
+ """ Get previously saved parts of the configuration from the
+ database.
+ """
+ self.normalization_rules = get_property(conn, DBCFG_IMPORT_NORM_RULES)
+ self.transliteration_rules = get_property(conn, DBCFG_IMPORT_TRANS_RULES)
+ self.analysis_rules = json.loads(get_property(conn, DBCFG_IMPORT_ANALYSIS_RULES))
+ self._setup_analysis()
+
+
+ def save_config_to_db(self, conn):
+ """ Save the part of the configuration that cannot be changed into
+ the database.
+ """
+ set_property(conn, DBCFG_IMPORT_NORM_RULES, self.normalization_rules)
+ set_property(conn, DBCFG_IMPORT_TRANS_RULES, self.transliteration_rules)
+ set_property(conn, DBCFG_IMPORT_ANALYSIS_RULES, json.dumps(self.analysis_rules))
+
+
+ def make_sanitizer(self):
+ """ Create a place sanitizer from the configured rules.
+ """
+ return PlaceSanitizer(self.sanitizer_rules)
+
- if configfile.suffix == '.yaml':
- self._load_from_yaml()
- else:
- raise UsageError("Unknown format of tokenizer configuration.")
+ def make_token_analysis(self):
+ """ Create a token analyser from the reviouly loaded rules.
+ """
+ return self.analysis[None].create(self.normalization_rules,
+ self.transliteration_rules)
def get_search_rules(self):
rules.write(self.transliteration_rules)
return rules.getvalue()
+
def get_normalization_rules(self):
""" Return rules for normalisation of a term.
"""
return self.normalization_rules
+
def get_transliteration_rules(self):
""" Return the rules for converting a string into its asciii representation.
"""
return self.transliteration_rules
- def get_replacement_pairs(self):
- """ Return the list of possible compound decompositions with
- application of abbreviations included.
- The result is a list of pairs: the first item is the sequence to
- replace, the second is a list of replacements.
- """
- return self.variants
-
- def _yaml_include_representer(self, loader, node):
- value = loader.construct_scalar(node)
-
- if Path(value).is_absolute():
- content = Path(value)
- else:
- content = (self.configfile.parent / value)
-
- return yaml.safe_load(content.read_text(encoding='utf-8'))
+ def _setup_analysis(self):
+ """ Process the rules used for creating the various token analyzers.
+ """
+ self.analysis = {}
- def _load_from_yaml(self):
- yaml.add_constructor('!include', self._yaml_include_representer,
- Loader=yaml.SafeLoader)
- rules = yaml.safe_load(self.configfile.read_text(encoding='utf-8'))
+ if not isinstance(self.analysis_rules, list):
+ raise UsageError("Configuration section 'token-analysis' must be a list.")
- 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'))
+ for section in self.analysis_rules:
+ name = section.get('id', None)
+ if name in self.analysis:
+ if name is None:
+ LOG.fatal("ICU tokenizer configuration has two default token analyzers.")
+ else:
+ LOG.fatal("ICU tokenizer configuration has two token "
+ "analyzers with id '%s'.", name)
+ UsageError("Syntax error in ICU tokenizer config.")
+ self.analysis[name] = TokenAnalyzerRule(section, self.normalization_rules)
- 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]
if content is None:
return ''
- return ';'.join(_flatten_yaml_list(content)) + ';'
+ return ';'.join(flatten_config_list(content, section)) + ';'
+
+
+class TokenAnalyzerRule:
+ """ Factory for a single analysis module. The class saves the configuration
+ and creates a new token analyzer on request.
+ """
+
+ def __init__(self, rules, normalization_rules):
+ self._parse_variant_list(rules.get('variants'), normalization_rules)
- def _parse_variant_list(self, rules):
- self.variants.clear()
+ def create(self, normalization_rules, transliteration_rules):
+ """ Create an analyzer from the given rules.
+ """
+ return ICUNameProcessor(normalization_rules,
+ transliteration_rules,
+ self.variants)
+
+
+ def _parse_variant_list(self, rules, normalization_rules):
+ self.variants = set()
if not rules:
return
- rules = _flatten_yaml_list(rules)
+ rules = flatten_config_list(rules, 'variants')
- vmaker = _VariantMaker(self.normalization_rules)
+ vmaker = _VariantMaker(normalization_rules)
properties = []
for section in rules:
projects / nominatim.git / blobdiff