add documentation for new refresh command

[nominatim.git] / nominatim / tokenizer / icu_rule_loader.py

diff --git a/nominatim/tokenizer/icu_rule_loader.py b/nominatim/tokenizer/icu_rule_loader.py
index a8bdba933637195b3a62a687142b3c08752a3cc8..8a564355e35c03e4ed715363d505224efac1a6cd 100644 (file)
--- a/nominatim/tokenizer/icu_rule_loader.py
+++ b/nominatim/tokenizer/icu_rule_loader.py
@@ -1,3 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2022 by the Nominatim developer community.
+# For a full list of authors see the git log.

 """
 Helper class to create ICU rules from a configuration file.
 """
 """
 Helper class to create ICU rules from a configuration file.
 """


@@ -5,16 +11,13 @@ import importlib
 import io
 import json
 import logging
 import io
 import json
 import logging

-import itertools
-import re
-
-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.place_sanitizer import PlaceSanitizer
 
 from nominatim.config import flatten_config_list
 from nominatim.db.properties import set_property, get_property
 from nominatim.errors import UsageError
 from nominatim.tokenizer.place_sanitizer import PlaceSanitizer

-import nominatim.tokenizer.icu_variants as variants
+from nominatim.tokenizer.icu_token_analysis import ICUTokenAnalysis
+import nominatim.tools.country_info

 
 LOG = logging.getLogger()
 
 
 LOG = logging.getLogger()
 


@@ -34,18 +37,6 @@ def _get_section(rules, section):
     return rules[section]
 
 
     return rules[section]
 
 

-class VariantRule:
-    """ Saves a single variant expansion.
-
-        An expansion consists of the normalized replacement term and
-        a dicitonary of properties that describe when the expansion applies.
-    """
-
-    def __init__(self, replacement, properties):
-        self.replacement = replacement
-        self.properties = properties or {}
-
-

 class ICURuleLoader:
     """ Compiler for ICU rules from a tokenizer configuration file.
     """
 class ICURuleLoader:
     """ Compiler for ICU rules from a tokenizer configuration file.
     """


@@ -54,6 +45,9 @@ class ICURuleLoader:
         rules = config.load_sub_configuration('icu_tokenizer.yaml',
                                               config='TOKENIZER_CONFIG')
 
         rules = config.load_sub_configuration('icu_tokenizer.yaml',
                                               config='TOKENIZER_CONFIG')
 

+        # Make sure country information is available to analyzers and sanitizers.
+        nominatim.tools.country_info.setup_country_config(config)
+

         self.normalization_rules = self._cfg_to_icu_rules(rules, 'normalization')
         self.transliteration_rules = self._cfg_to_icu_rules(rules, 'transliteration')
         self.analysis_rules = _get_section(rules, 'token-analysis')
         self.normalization_rules = self._cfg_to_icu_rules(rules, 'normalization')
         self.transliteration_rules = self._cfg_to_icu_rules(rules, 'transliteration')
         self.analysis_rules = _get_section(rules, 'token-analysis')


@@ -91,8 +85,8 @@ class ICURuleLoader:
     def make_token_analysis(self):
         """ Create a token analyser from the reviouly loaded rules.
         """
     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)
+        return ICUTokenAnalysis(self.normalization_rules,
+                                self.transliteration_rules, self.analysis)

 
 
     def get_search_rules(self):
 
 
     def get_search_rules(self):


@@ -136,7 +130,7 @@ class ICURuleLoader:
                 else:
                     LOG.fatal("ICU tokenizer configuration has two token "
                               "analyzers with id '%s'.", name)
                 else:
                     LOG.fatal("ICU tokenizer configuration has two token "
                               "analyzers with id '%s'.", name)

-                UsageError("Syntax error in ICU tokenizer config.")
+                raise UsageError("Syntax error in ICU tokenizer config.")

             self.analysis[name] = TokenAnalyzerRule(section, self.normalization_rules)
 
 
             self.analysis[name] = TokenAnalyzerRule(section, self.normalization_rules)
 
 


@@ -166,128 +160,7 @@ class TokenAnalyzerRule:
         module_name = 'nominatim.tokenizer.token_analysis.' \
                       + _get_section(rules, 'analyzer').replace('-', '_')
         analysis_mod = importlib.import_module(module_name)
         module_name = 'nominatim.tokenizer.token_analysis.' \
                       + _get_section(rules, 'analyzer').replace('-', '_')
         analysis_mod = importlib.import_module(module_name)

-        self._mod_create = analysis_mod.create
+        self.create = analysis_mod.create

 
         # Load the configuration.
 
         # 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 self._mod_create(normalization_rules,
-                                transliteration_rules,
-                                self.config)
-
-
-    def _parse_variant_list(self, rules, normalization_rules):
-        vset = set()
-
-        if not rules:
-            return
-
-        rules = flatten_config_list(rules, 'variants')
-
-        vmaker = _VariantMaker(normalization_rules)
-
-        properties = []
-        for section in rules:
-            # Create the property field and deduplicate against existing
-            # instances.
-            props = variants.ICUVariantProperties.from_rules(section)
-            for existing in properties:
-                if existing == props:
-                    props = existing
-                    break
-            else:
-                properties.append(props)
-
-            for rule in (section.get('words') or []):
-                vset.update(vmaker.compute(rule, props))
-
-        self.config['variants'] = vset
-
-
-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, props):
-        """ 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 variants.ICUVariant(froms, tos, props)
-
-        for src, repl in itertools.product(src_terms, repl_terms):
-            if src and repl:
-                for froms, tos in _create_variants(*src, repl, decompose):
-                    yield variants.ICUVariant(froms, tos, props)
-
-
-    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))
-        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
+        self.config = analysis_mod.configure(rules, normalization_rules)