safety-screen/Nominatim
1
0
Fork 0
forked from hans/Nominatim
Code Pull Requests Activity

add type annotations for token analysis

Browse Source 
No annotations for ICU types yet.
This commit is contained in:
Sarah Hoffmann
2022-07-13 17:18:53 +02:00
parent 62eedbb8f6
commit d35e3c25b6
6 changed files with 94 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
nominatim/tokenizer/token_analysis/base.py Normal file
View File

@@ -0,0 +1,45 @@
# 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.
"""
Common data types and protocols for analysers.
"""
from typing import TypeVar, Mapping, List, Any
from typing_extensions import Protocol
T_config = TypeVar('T_config') # pylint: disable=invalid-name
class Analyser(Protocol):
""" Instance of the token analyser.
"""
def normalize(self, name: str) -> str:
""" Return the normalized form of the name. This is the standard form
from which possible variants for the name can be derived.
"""
def get_variants_ascii(self, norm_name: str) -> List[str]:
""" Compute the spelling variants for the given normalized name
and transliterate the result.
"""
class AnalysisModule(Protocol[T_config]):
""" Protocol for analysis modules.
"""
def configure(self, rules: Mapping[str, Any], normalization_rules: str) -> T_config:
""" Prepare the configuration of the analysis module.
This function should prepare all data that can be shared
between instances of this analyser.
"""
def create(self, normalizer: Any, transliterator: Any, config: T_config) -> Analyser:
""" Create a new instance of the analyser.
A separate instance of the analyser is created for each thread
when used in multi-threading context.
"""

30
nominatim/tokenizer/token_analysis/config_variants.py
View File

@@ -7,7 +7,8 @@
"""
Parser for configuration for variants.
"""
from collections import defaultdict, namedtuple
from typing import Any, Iterator, Tuple, List, Optional, Set, NamedTuple
from collections import defaultdict
import itertools
import re
@@ -16,9 +17,15 @@ from icu import Transliterator
from nominatim.config import flatten_config_list
from nominatim.errors import UsageError
ICUVariant = namedtuple('ICUVariant', ['source', 'replacement'])
class ICUVariant(NamedTuple):
""" A single replacement rule for variant creation.
"""
source: str
replacement: str
def get_variant_config(rules, normalization_rules):
def get_variant_config(in_rules: Any,
normalization_rules: str) -> Tuple[List[Tuple[str, List[str]]], str]:
""" Convert the variant definition from the configuration into
replacement sets.
@@ -26,11 +33,11 @@ def get_variant_config(rules, normalization_rules):
used in the replacements.
"""
immediate = defaultdict(list)
chars = set()
chars: Set[str] = set()
if rules:
vset = set()
rules = flatten_config_list(rules, 'variants')
if in_rules:
vset: Set[ICUVariant] = set()
rules = flatten_config_list(in_rules, 'variants')
vmaker = _VariantMaker(normalization_rules)
@@ -56,12 +63,12 @@ class _VariantMaker:
All text in rules is normalized to make sure the variants match later.
"""
def __init__(self, norm_rules):
def __init__(self, norm_rules: Any) -> None:
self.norm = Transliterator.createFromRules("rule_loader_normalization",
norm_rules)
def compute(self, rule):
def compute(self, rule: Any) -> Iterator[ICUVariant]:
""" Generator for all ICUVariant tuples from a single variant rule.
"""
parts = re.split(r'(\|)?([=-])>', rule)
@@ -85,7 +92,7 @@ class _VariantMaker:
yield ICUVariant(froms, tos)
def _parse_variant_word(self, name):
def _parse_variant_word(self, name: str) -> Optional[Tuple[str, str, str]]:
name = name.strip()
match = re.fullmatch(r'([~^]?)([^~$^]*)([~$]?)', name)
if match is None or (match.group(1) == '~' and match.group(3) == '~'):
@@ -102,7 +109,8 @@ _FLAG_MATCH = {'^': '^ ',
'': ' '}
def _create_variants(src, preflag, postflag, repl, decompose):
def _create_variants(src: str, preflag: str, postflag: str,
repl: str, decompose: bool) -> Iterator[Tuple[str, str]]:
if preflag == '~':
postfix = _FLAG_MATCH[postflag]
# suffix decomposition

21
nominatim/tokenizer/token_analysis/generic.py
View File

@@ -7,6 +7,7 @@
"""
Generic processor for names that creates abbreviation variants.
"""
from typing import Mapping, Dict, Any, Iterable, Iterator, Optional, List, cast
import itertools
import datrie
@@ -17,10 +18,10 @@ from nominatim.tokenizer.token_analysis.generic_mutation import MutationVariantG
### Configuration section
def configure(rules, normalization_rules):
def configure(rules: Mapping[str, Any], normalization_rules: str) -> Dict[str, Any]:
""" Extract and preprocess the configuration for this module.
"""
config = {}
config: Dict[str, Any] = {}
config['replacements'], config['chars'] = get_variant_config(rules.get('variants'),
normalization_rules)
@@ -47,7 +48,8 @@ def configure(rules, normalization_rules):
### Analysis section
def create(normalizer, transliterator, config):
def create(normalizer: Any, transliterator: Any,
config: Mapping[str, Any]) -> 'GenericTokenAnalysis':
""" Create a new token analysis instance for this module.
"""
return GenericTokenAnalysis(normalizer, transliterator, config)
@@ -58,7 +60,7 @@ class GenericTokenAnalysis:
and provides the functions to apply the transformations.
"""
def __init__(self, norm, to_ascii, config):
def __init__(self, norm: Any, to_ascii: Any, config: Mapping[str, Any]) -> None:
self.norm = norm
self.to_ascii = to_ascii
self.variant_only = config['variant_only']
@@ -75,14 +77,14 @@ class GenericTokenAnalysis:
self.mutations = [MutationVariantGenerator(*cfg) for cfg in config['mutations']]
def normalize(self, name):
def normalize(self, name: str) -> str:
""" Return the normalized form of the name. This is the standard form
from which possible variants for the name can be derived.
"""
return self.norm.transliterate(name).strip()
return cast(str, self.norm.transliterate(name)).strip()
def get_variants_ascii(self, norm_name):
def get_variants_ascii(self, norm_name: str) -> List[str]:
""" Compute the spelling variants for the given normalized name
and transliterate the result.
"""
@@ -94,7 +96,8 @@ class GenericTokenAnalysis:
return [name for name in self._transliterate_unique_list(norm_name, variants) if name]
def _transliterate_unique_list(self, norm_name, iterable):
def _transliterate_unique_list(self, norm_name: str,
iterable: Iterable[str]) -> Iterator[Optional[str]]:
seen = set()
if self.variant_only:
seen.add(norm_name)
@@ -105,7 +108,7 @@ class GenericTokenAnalysis:
yield self.to_ascii.transliterate(variant).strip()
def _generate_word_variants(self, norm_name):
def _generate_word_variants(self, norm_name: str) -> Iterable[str]:
baseform = '^ ' + norm_name + ' ^'
baselen = len(baseform)
partials = ['']

9
nominatim/tokenizer/token_analysis/generic_mutation.py
View File

@@ -7,6 +7,7 @@
"""
Creator for mutation variants for the generic token analysis.
"""
from typing import Sequence, Iterable, Iterator, Tuple
import itertools
import logging
import re
@@ -15,7 +16,7 @@ from nominatim.errors import UsageError
LOG = logging.getLogger()
def _zigzag(outer, inner):
def _zigzag(outer: Iterable[str], inner: Iterable[str]) -> Iterator[str]:
return itertools.chain.from_iterable(itertools.zip_longest(outer, inner, fillvalue=''))
@@ -26,7 +27,7 @@ class MutationVariantGenerator:
patterns.
"""
def __init__(self, pattern, replacements):
def __init__(self, pattern: str, replacements: Sequence[str]):
self.pattern = re.compile(pattern)
self.replacements = replacements
@@ -36,7 +37,7 @@ class MutationVariantGenerator:
raise UsageError("Bad mutation pattern in configuration.")
def generate(self, names):
def generate(self, names: Iterable[str]) -> Iterator[str]:
""" Generator function for the name variants. 'names' is an iterable
over a set of names for which the variants are to be generated.
"""
@@ -49,7 +50,7 @@ class MutationVariantGenerator:
yield ''.join(_zigzag(parts, seps))
def _fillers(self, num_parts):
def _fillers(self, num_parts: int) -> Iterator[Tuple[str, ...]]:
""" Returns a generator for strings to join the given number of string
parts in all possible combinations.
"""

13
nominatim/tokenizer/token_analysis/housenumbers.py
View File

@@ -8,6 +8,7 @@
Specialized processor for housenumbers. Analyses common housenumber patterns
and creates variants for them.
"""
from typing import Mapping, Any, List, cast
import re
from nominatim.tokenizer.token_analysis.generic_mutation import MutationVariantGenerator
@@ -19,14 +20,14 @@ RE_NAMED_PART = re.compile(r'[a-z]{4}')
### Configuration section
def configure(rules, normalization_rules): # pylint: disable=W0613
def configure(rules: Mapping[str, Any], normalization_rules: str) -> None: # pylint: disable=W0613
""" All behaviour is currently hard-coded.
"""
return None
### Analysis section
def create(normalizer, transliterator, config): # pylint: disable=W0613
def create(normalizer: Any, transliterator: Any, config: None) -> 'HousenumberTokenAnalysis': # pylint: disable=W0613
""" Create a new token analysis instance for this module.
"""
return HousenumberTokenAnalysis(normalizer, transliterator)
@@ -35,20 +36,20 @@ def create(normalizer, transliterator, config): # pylint: disable=W0613
class HousenumberTokenAnalysis:
""" Detects common housenumber patterns and normalizes them.
"""
def __init__(self, norm, trans):
def __init__(self, norm: Any, trans: Any) -> None:
self.norm = norm
self.trans = trans
self.mutator = MutationVariantGenerator('␣', (' ', ''))
def normalize(self, name):
def normalize(self, name: str) -> str:
""" Return the normalized form of the housenumber.
"""
# shortcut for number-only numbers, which make up 90% of the data.
if RE_NON_DIGIT.search(name) is None:
return name
norm = self.trans.transliterate(self.norm.transliterate(name))
norm = cast(str, self.trans.transliterate(self.norm.transliterate(name)))
# If there is a significant non-numeric part, use as is.
if RE_NAMED_PART.search(norm) is None:
# Otherwise add optional spaces between digits and letters.
@@ -60,7 +61,7 @@ class HousenumberTokenAnalysis:
return norm
def get_variants_ascii(self, norm_name):
def get_variants_ascii(self, norm_name: str) -> List[str]:
""" Compute the spelling variants for the given normalized housenumber.
Generates variants for optional spaces (marked with '␣').

11
nominatim/tokenizer/token_analysis/postcodes.py
View File

@@ -8,19 +8,20 @@
Specialized processor for postcodes. Supports a 'lookup' variant of the
token, which produces variants with optional spaces.
"""
from typing import Mapping, Any, List
from nominatim.tokenizer.token_analysis.generic_mutation import MutationVariantGenerator
### Configuration section
def configure(rules, normalization_rules): # pylint: disable=W0613
def configure(rules: Mapping[str, Any], normalization_rules: str) -> None: # pylint: disable=W0613
""" All behaviour is currently hard-coded.
"""
return None
### Analysis section
def create(normalizer, transliterator, config): # pylint: disable=W0613
def create(normalizer: Any, transliterator: Any, config: None) -> 'PostcodeTokenAnalysis': # pylint: disable=W0613
""" Create a new token analysis instance for this module.
"""
return PostcodeTokenAnalysis(normalizer, transliterator)
@@ -38,20 +39,20 @@ class PostcodeTokenAnalysis:
and transliteration, so that postcodes are correctly recognised by
the search algorithm.
"""
def __init__(self, norm, trans):
def __init__(self, norm: Any, trans: Any) -> None:
self.norm = norm
self.trans = trans
self.mutator = MutationVariantGenerator(' ', (' ', ''))
def normalize(self, name):
def normalize(self, name: str) -> str:
""" Return the standard form of the postcode.
"""
return name.strip().upper()
def get_variants_ascii(self, norm_name):
def get_variants_ascii(self, norm_name: str) -> List[str]:
""" Compute the spelling variants for the given normalized postcode.
Takes the canonical form of the postcode, normalizes it using the