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
37 class _AnalyzerByLanguage:
38 """ Processor for tagging the language of names in a place.
41 def __init__(self, config):
42 if 'filter-kind' in config:
43 self.regexes = [re.compile(regex) for regex in config['filter-kind']]
47 self.replace = config.get('mode', 'replace') != 'append'
48 self.whitelist = config.get('whitelist')
50 self.__compute_default_languages(config.get('use-defaults', 'no'))
53 def __compute_default_languages(self, use_defaults):
56 if use_defaults in ('mono', 'all'):
57 for ccode, prop in country_info.iterate():
58 clangs = prop['languages']
59 if len(clangs) == 1 or use_defaults == 'all':
61 self.deflangs[ccode] = [l for l in clangs if l in self.whitelist]
63 self.deflangs[ccode] = clangs
66 def _kind_matches(self, kind):
67 if self.regexes is None:
70 return any(regex.fullmatch(kind) for regex in self.regexes)
73 def _suffix_matches(self, suffix):
74 if self.whitelist is None:
75 return len(suffix) in (2, 3) and suffix.islower()
77 return suffix in self.whitelist
80 def __call__(self, obj):
86 for name in (n for n in obj.names
87 if not n.has_attr('analyzer') and self._kind_matches(n.kind)):
89 langs = [name.suffix] if self._suffix_matches(name.suffix) else None
91 langs = self.deflangs.get(obj.place.country_code)
96 name.set_attr('analyzer', langs[0])
98 more_names.append(name.clone(attr={'analyzer': langs[0]}))
100 more_names.extend(name.clone(attr={'analyzer': l}) for l in langs[1:])
102 obj.names.extend(more_names)
106 """ Create a function that sets the analyzer property depending on the
109 return _AnalyzerByLanguage(config)