move variant configuration reading in separate file

nominatim/tokenizer/token_analysis/config_variants.py

@@ -0,0 +1,134 @@
+# 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.
+"""
+Parser for configuration for variants.
+"""
+from collections import defaultdict, namedtuple
+import itertools
+import re
+
+from icu import Transliterator
+
+from nominatim.config import flatten_config_list
+from nominatim.errors import UsageError
+
+ICUVariant = namedtuple('ICUVariant', ['source', 'replacement'])
+
+def get_variant_config(rules, normalization_rules):
+    """ Convert the variant definition from the configuration into
+        replacement sets.
+
+        Returns a tuple containing the replacement set and the list of characters
+        used in the replacements.
+    """
+    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)
+
+        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

nominatim/tokenizer/token_analysis/generic.py

@@ -7,145 +7,26 @@
 """
 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.tokenizer.token_analysis.config_variants import get_variant_config
-from nominatim.errors import UsageError
 
 ### 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'),
+    config['replacements'], config['chars'] = get_variant_config(rules.get('variants'),
-                                                                  normalization_rules)
+                                                                 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)
-
-        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
-
-
 ### Analysis section
 
 def create(transliterator, config):