Merge remote-tracking branch 'upstream/master'

[nominatim.git] / nominatim / tokenizer / token_analysis / generic.py

diff --git a/nominatim/tokenizer/token_analysis/generic.py b/nominatim/tokenizer/token_analysis/generic.py
index 343534eec8a8778133a512982c38fd0360147959..d4eae312d9dfc4f3407cb915988a41256614565b 100644 (file)
--- a/nominatim/tokenizer/token_analysis/generic.py
+++ b/nominatim/tokenizer/token_analysis/generic.py
@@ -1,150 +1,56 @@
+# 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.

 """
 Generic processor for names that creates abbreviation variants.
 """
 """
 Generic processor for names that creates abbreviation variants.
 """

-from collections import defaultdict

 import itertools
 import itertools

-import re

 
 

-from icu import Transliterator

 import datrie
 
 import datrie
 

-from nominatim.config import flatten_config_list

 from nominatim.errors import UsageError
 from nominatim.errors import UsageError

-import nominatim.tokenizer.icu_variants as variants
+from nominatim.tokenizer.token_analysis.config_variants import get_variant_config
+from nominatim.tokenizer.token_analysis.generic_mutation import MutationVariantGenerator

 
 ### Configuration section
 
 def configure(rules, normalization_rules):
     """ Extract and preprocess the configuration for this module.
     """
 
 ### Configuration section
 
 def configure(rules, normalization_rules):
     """ Extract and preprocess the configuration for this module.
     """

-    rules = rules.get('variants')
-    immediate = defaultdict(list)
-    chars = set()
-
-    if rules:
-        vset = set()
-        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))
-
-        # 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 {'replacements': list(immediate.items()),
-            'chars': ''.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, 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
+    config = {}

 
 

-        yield src, repl
-        yield ' ' + src, ' ' + repl
+    config['replacements'], config['chars'] = get_variant_config(rules.get('variants'),
+                                                                 normalization_rules)
+    config['variant_only'] = rules.get('mode', '') == 'variant-only'

 
 

-        if decompose:
-            yield src, ' ' + repl
-            yield ' ' + src, repl
-    elif postflag == '~':
-        # prefix decomposition
-        prefix = _FLAG_MATCH[preflag]
-        src = prefix + src
-        repl = prefix + repl
+    # parse mutation rules
+    config['mutations'] = []
+    for rule in rules.get('mutations', []):
+        if 'pattern' not in rule:
+            raise UsageError("Missing field 'pattern' in mutation configuration.")
+        if not isinstance(rule['pattern'], str):
+            raise UsageError("Field 'pattern' in mutation configuration "
+                             "must be a simple text field.")
+        if 'replacements' not in rule:
+            raise UsageError("Missing field 'replacements' in mutation configuration.")
+        if not isinstance(rule['replacements'], list):
+            raise UsageError("Field 'replacements' in mutation configuration "
+                             "must be a list of texts.")

 
 

-        yield src, repl
-        yield src + ' ', repl + ' '
+        config['mutations'].append((rule['pattern'], rule['replacements']))

 
 

-        if decompose:
-            yield src, repl + ' '
-            yield src + ' ', repl
-    else:
-        prefix = _FLAG_MATCH[preflag]
-        postfix = _FLAG_MATCH[postflag]
-
-        yield prefix + src + postfix, prefix + repl + postfix
+    return config

 
 
 ### Analysis section
 
 
 
 ### Analysis section
 

-def create(norm_rules, trans_rules, config):
+def create(transliterator, config):

     """ Create a new token analysis instance for this module.
     """
     """ Create a new token analysis instance for this module.
     """

-    return GenericTokenAnalysis(norm_rules, trans_rules, config)
+    return GenericTokenAnalysis(transliterator, config)

 
 
 class GenericTokenAnalysis:
 
 
 class GenericTokenAnalysis:


@@ -152,81 +58,81 @@ class GenericTokenAnalysis:
         and provides the functions to apply the transformations.
     """
 
         and provides the functions to apply the transformations.
     """
 

-    def __init__(self, norm_rules, trans_rules, config):
-        self.normalizer = Transliterator.createFromRules("icu_normalization",
-                                                         norm_rules)
-        self.to_ascii = Transliterator.createFromRules("icu_to_ascii",
-                                                       trans_rules +
-                                                       ";[:Space:]+ > ' '")
-        self.search = Transliterator.createFromRules("icu_search",
-                                                     norm_rules + trans_rules)
+    def __init__(self, to_ascii, config):
+        self.to_ascii = to_ascii
+        self.variant_only = config['variant_only']

 
         # Set up datrie
 
         # Set up datrie

-        self.replacements = datrie.Trie(config['chars'])
-        for src, repllist in config['replacements']:
-            self.replacements[src] = repllist
+        if config['replacements']:
+            self.replacements = datrie.Trie(config['chars'])
+            for src, repllist in config['replacements']:
+                self.replacements[src] = repllist
+        else:
+            self.replacements = None

 
 

+        # set up mutation rules
+        self.mutations = [MutationVariantGenerator(*cfg) for cfg in config['mutations']]

 
 

-    def get_normalized(self, name):
-        """ Normalize the given name, i.e. remove all elements not relevant
-            for search.
-        """
-        return self.normalizer.transliterate(name).strip()

 
     def get_variants_ascii(self, norm_name):
         """ Compute the spelling variants for the given normalized name
             and transliterate the result.
         """
 
     def get_variants_ascii(self, norm_name):
         """ Compute the spelling variants for the given normalized name
             and transliterate the result.
         """

-        baseform = '^ ' + norm_name + ' ^'
-        partials = ['']
+        variants = self._generate_word_variants(norm_name)

 
 

-        startpos = 0
-        pos = 0
-        force_space = False
-        while pos < len(baseform):
-            full, repl = self.replacements.longest_prefix_item(baseform[pos:],
-                                                               (None, None))
-            if full is not None:
-                done = baseform[startpos:pos]
-                partials = [v + done + r
-                            for v, r in itertools.product(partials, repl)
-                            if not force_space or r.startswith(' ')]
-                if len(partials) > 128:
-                    # If too many variants are produced, they are unlikely
-                    # to be helpful. Only use the original term.
-                    startpos = 0
-                    break
-                startpos = pos + len(full)
-                if full[-1] == ' ':
-                    startpos -= 1
-                    force_space = True
-                pos = startpos
-            else:
-                pos += 1
-                force_space = False
+        for mutation in self.mutations:
+            variants = mutation.generate(variants)

 
 

-        # No variants detected? Fast return.
-        if startpos == 0:
-            trans_name = self.to_ascii.transliterate(norm_name).strip()
-            return [trans_name] if trans_name else []
+        return [name for name in self._transliterate_unique_list(norm_name, variants) if name]

 
 

-        return self._compute_result_set(partials, baseform[startpos:])

 
 

+    def _transliterate_unique_list(self, norm_name, iterable):
+        seen = set()
+        if self.variant_only:
+            seen.add(norm_name)

 
 

-    def _compute_result_set(self, partials, prefix):
-        results = set()
+        for variant in map(str.strip, iterable):
+            if variant not in seen:
+                seen.add(variant)
+                yield self.to_ascii.transliterate(variant).strip()

 
 

-        for variant in partials:
-            vname = variant + prefix
-            trans_name = self.to_ascii.transliterate(vname[1:-1]).strip()
-            if trans_name:
-                results.add(trans_name)

 
 

-        return list(results)
+    def _generate_word_variants(self, norm_name):
+        baseform = '^ ' + norm_name + ' ^'
+        baselen = len(baseform)
+        partials = ['']

 
 

+        startpos = 0
+        if self.replacements is not None:
+            pos = 0
+            force_space = False
+            while pos < baselen:
+                full, repl = self.replacements.longest_prefix_item(baseform[pos:],
+                                                                   (None, None))
+                if full is not None:
+                    done = baseform[startpos:pos]
+                    partials = [v + done + r
+                                for v, r in itertools.product(partials, repl)
+                                if not force_space or r.startswith(' ')]
+                    if len(partials) > 128:
+                        # If too many variants are produced, they are unlikely
+                        # to be helpful. Only use the original term.
+                        startpos = 0
+                        break
+                    startpos = pos + len(full)
+                    if full[-1] == ' ':
+                        startpos -= 1
+                        force_space = True
+                    pos = startpos
+                else:
+                    pos += 1
+                    force_space = False

 
 

-    def get_search_normalized(self, name):
-        """ Return the normalized version of the name (including transliteration)
-            to be applied at search time.
-        """
-        return self.search.transliterate(' ' + name + ' ').strip()
+        # No variants detected? Fast return.
+        if startpos == 0:
+            return (norm_name, )
+
+        if startpos < baselen:
+            return (part[1:] + baseform[startpos:-1] for part in partials)
+
+        return (part[1:-1] for part in partials)