"""
Generic processor for names that creates abbreviation variants.
"""
-from collections import defaultdict, namedtuple
import itertools
-import re
-from icu import Transliterator
import datrie
-from nominatim.config import flatten_config_list
from nominatim.errors import UsageError
+from nominatim.tokenizer.token_analysis.config_variants import get_variant_config
+from nominatim.tokenizer.token_analysis.generic_mutation import MutationVariantGenerator
### Configuration section
-ICUVariant = namedtuple('ICUVariant', ['source', 'replacement'])
-
def configure(rules, normalization_rules):
""" Extract and preprocess the configuration for this module.
"""
config = {}
- config['replacements'], config['chars'] = _get_variant_config(rules.get('variants'),
- normalization_rules)
+ config['replacements'], config['chars'] = get_variant_config(rules.get('variants'),
+ normalization_rules)
config['variant_only'] = rules.get('mode', '') == 'variant-only'
- return config
-
-
-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)
-
- for section in rules:
- for rule in (section.get('words') or []):
- 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 list(immediate.items()), ''.join(chars)
-
-
-class _VariantMaker:
- """ Generater for all necessary ICUVariants from a single variant rule.
-
- 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)
-
-
- def compute(self, rule):
- """ 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 ICUVariant(froms, tos)
+ # parse mutation rules
+ config['mutations'] = []
+ for rule in rules.get('mutations', []):
+ if 'pattern' not in rule:
+ raise UsageError("Missing field 'pattern' in mutation configuration.")
+ if not isinstance(rule['pattern'], str):
+ raise UsageError("Field 'pattern' in mutation configuration "
+ "must be a simple text field.")
+ if 'replacements' not in rule:
+ raise UsageError("Missing field 'replacements' in mutation configuration.")
+ if not isinstance(rule['replacements'], list):
+ raise UsageError("Field 'replacements' in mutation configuration "
+ "must be a list of texts.")
+
+ config['mutations'].append((rule['pattern'], rule['replacements']))
- for src, repl in itertools.product(src_terms, repl_terms):
- if src and repl:
- for froms, tos in _create_variants(*src, repl, decompose):
- yield ICUVariant(froms, tos)
-
-
- 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)).strip()
- 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
+ return config
### Analysis section
else:
self.replacements = None
+ # set up mutation rules
+ self.mutations = [MutationVariantGenerator(*cfg) for cfg in config['mutations']]
+
def get_variants_ascii(self, norm_name):
""" Compute the spelling variants for the given normalized name
and transliterate the result.
"""
- results = set()
- for variant in self._generate_word_variants(norm_name):
- if not self.variant_only or variant.strip() != norm_name:
- trans_name = self.to_ascii.transliterate(variant).strip()
- if trans_name:
- results.add(trans_name)
-
- return list(results)
+ variants = self._generate_word_variants(norm_name)
+
+ for mutation in self.mutations:
+ variants = mutation.generate(variants)
+
+ return [name for name in self._transliterate_unique_list(norm_name, variants) if name]
+
+
+ def _transliterate_unique_list(self, norm_name, iterable):
+ seen = set()
+ if self.variant_only:
+ seen.add(norm_name)
+
+ for variant in map(str.strip, iterable):
+ if variant not in seen:
+ seen.add(variant)
+ yield self.to_ascii.transliterate(variant).strip()
def _generate_word_variants(self, norm_name):
projects / nominatim.git / blobdiff