unify ICUNameProcessorRules and ICURuleLoader

[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 d3141bf7341691daba70c57db46ab6ed20256ae5..bd0739f2f40e0b8023a6e45fb8fd2dfe03ad1c2f 100644 (file)
--- a/nominatim/tokenizer/icu_rule_loader.py
+++ b/nominatim/tokenizer/icu_rule_loader.py
@@ -2,30 +2,36 @@
 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.db.properties import set_property, get_property
 from nominatim.errors import UsageError
+from nominatim.tokenizer.icu_name_processor import ICUNameProcessor
 import nominatim.tokenizer.icu_variants as variants
 
 LOG = logging.getLogger()
 
-def _flatten_yaml_list(content):
+DBCFG_IMPORT_NORM_RULES = "tokenizer_import_normalisation"
+DBCFG_IMPORT_TRANS_RULES = "tokenizer_import_transliteration"
+DBCFG_IMPORT_ANALYSIS_RULES = "tokenizer_import_analysis_rules"
+
+
+def _flatten_config_list(content):
     if not content:
         return []
 
     if not isinstance(content, list):
-        raise UsageError("List expected in ICU yaml configuration.")
+        raise UsageError("List expected in ICU configuration.")
 
     output = []
     for ele in content:
         if isinstance(ele, list):
-            output.extend(_flatten_yaml_list(ele))
+            output.extend(_flatten_config_list(ele))
         else:
             output.append(ele)
 
@@ -48,14 +54,43 @@ class ICURuleLoader:
     """ Compiler for ICU rules from a tokenizer configuration file.
     """
 
-    def __init__(self, configfile):
-        self.configfile = configfile
+    def __init__(self, config):
+        rules = config.load_sub_configuration('icu_tokenizer.yaml',
+                                              config='TOKENIZER_CONFIG')
+
         self.variants = set()
 
-        if configfile.suffix == '.yaml':
-            self._load_from_yaml()
-        else:
-            raise UsageError("Unknown format of tokenizer configuration.")
+        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, 'variants')
+        self._parse_variant_list()
+
+
+    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._parse_variant_list()
+
+
+    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_token_analysis(self):
+        """ Create a token analyser from the reviouly loaded rules.
+        """
+        return ICUNameProcessor(self.normalization_rules,
+                                self.transliteration_rules,
+                                self.variants)
 
 
     def get_search_rules(self):
@@ -88,34 +123,14 @@ class ICURuleLoader:
         """
         return self.variants
 
-    def _yaml_include_representer(self, loader, node):
-        value = loader.construct_scalar(node)
-
-        if Path(value).is_absolute():
-            content = Path(value).read_text()
-        else:
-            content = (self.configfile.parent / value).read_text()
-
-        return yaml.safe_load(content)
-
 
-    def _load_from_yaml(self):
-        yaml.add_constructor('!include', self._yaml_include_representer,
-                             Loader=yaml.SafeLoader)
-        rules = yaml.safe_load(self.configfile.read_text())
-
-        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'))
-
-
-    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]
@@ -133,16 +148,18 @@ class ICURuleLoader:
         if content is None:
             return ''
 
-        return ';'.join(_flatten_yaml_list(content)) + ';'
+        return ';'.join(_flatten_config_list(content)) + ';'
+
 
+    def _parse_variant_list(self):
+        rules = self.analysis_rules
 
-    def _parse_variant_list(self, rules):
         self.variants.clear()
 
         if not rules:
             return
 
-        rules = _flatten_yaml_list(rules)
+        rules = _flatten_config_list(rules)
 
         vmaker = _VariantMaker(self.normalization_rules)