1 # SPDX-License-Identifier: GPL-2.0-only
3 # This file is part of Nominatim. (https://nominatim.org)
5 # Copyright (C) 2022 by the Nominatim developer community.
6 # For a full list of authors see the git log.
8 This sanitizer sets the `analyzer` property depending on the
9 language of the tag. The language is taken from the suffix of the name.
10 If a name already has an analyzer tagged, then this is kept.
14 filter-kind: Restrict the names the sanitizer should be applied to
15 to the given tags. The parameter expects a list of
16 regular expressions which are matched against 'kind'.
17 Note that a match against the full string is expected.
18 whitelist: Restrict the set of languages that should be tagged.
19 Expects a list of acceptable suffixes. When unset,
20 all 2- and 3-letter lower-case codes are accepted.
21 use-defaults: Configure what happens when the name has no suffix.
22 When set to 'all', a variant is created for
23 each of the default languages in the country
24 the feature is in. When set to 'mono', a variant is
25 only created, when exactly one language is spoken
26 in the country. The default is to do nothing with
27 the default languages of a country.
28 mode: Define how the variants are created and may be 'replace' or
29 'append'. When set to 'append' the original name (without
30 any analyzer tagged) is retained. (default: replace)
35 from nominatim.tools import country_info
36 from nominatim.tokenizer.sanitizers.helpers import create_kind_filter
38 class _AnalyzerByLanguage:
39 """ Processor for tagging the language of names in a place.
42 def __init__(self, config):
43 self.filter_kind = create_kind_filter(config)
44 self.replace = config.get('mode', 'replace') != 'append'
45 self.whitelist = config.get('whitelist')
47 self.__compute_default_languages(config.get('use-defaults', 'no'))
50 def __compute_default_languages(self, use_defaults):
53 if use_defaults in ('mono', 'all'):
54 for ccode, prop in country_info.iterate():
55 clangs = prop['languages']
56 if len(clangs) == 1 or use_defaults == 'all':
58 self.deflangs[ccode] = [l for l in clangs if l in self.whitelist]
60 self.deflangs[ccode] = clangs
63 def _suffix_matches(self, suffix):
64 if self.whitelist is None:
65 return len(suffix) in (2, 3) and suffix.islower()
67 return suffix in self.whitelist
70 def __call__(self, obj):
76 for name in (n for n in obj.names
77 if not n.has_attr('analyzer') and self.filter_kind(n)):
79 langs = [name.suffix] if self._suffix_matches(name.suffix) else None
81 langs = self.deflangs.get(obj.place.country_code)
86 name.set_attr('analyzer', langs[0])
88 more_names.append(name.clone(attr={'analyzer': langs[0]}))
90 more_names.extend(name.clone(attr={'analyzer': l}) for l in langs[1:])
92 obj.names.extend(more_names)
96 """ Create a function that sets the analyzer property depending on the
99 return _AnalyzerByLanguage(config)