import sqlalchemy as sa
+from ..errors import UsageError
from ..typing import SaRow
from ..sql.sqlalchemy_types import Json
from ..connection import SearchConnection
from ..logging import log
-from ..search import query as qmod
-from ..search.query_analyzer_factory import AbstractQueryAnalyzer
+from . import query as qmod
+from ..query_preprocessing.config import QueryConfig
+from .query_analyzer_factory import AbstractQueryAnalyzer
DB_TO_TOKEN_TYPE = {
QueryParts = List[QueryPart]
WordDict = Dict[str, List[qmod.TokenRange]]
+
def yield_words(terms: List[QueryPart], start: int) -> Iterator[Tuple[str, qmod.TokenRange]]:
""" Return all combinations of words in the terms list after the
given position.
assert self.info
return self.info.get('class', ''), self.info.get('type', '')
-
def rematch(self, norm: str) -> None:
""" Check how well the token matches the given normalized string
and add a penalty, if necessary.
distance += abs((ato-afrom) - (bto-bfrom))
self.penalty += (distance/len(self.lookup_word))
-
@staticmethod
def from_db_row(row: SaRow) -> 'ICUToken':
""" Create a ICUToken from the row of the word table.
addr_count=max(1, addr_count))
-
class ICUQueryAnalyzer(AbstractQueryAnalyzer):
""" Converter for query strings into a tokenized query
using the tokens created by a ICU tokenizer.
"""
-
def __init__(self, conn: SearchConnection) -> None:
self.conn = conn
-
async def setup(self) -> None:
""" Set up static data structures needed for the analysis.
"""
self.transliterator = await self.conn.get_cached_value('ICUTOK', 'transliterator',
_make_transliterator)
+ await self._setup_preprocessing()
+
if 'word' not in self.conn.t.meta.tables:
sa.Table('word', self.conn.t.meta,
sa.Column('word_id', sa.Integer),
sa.Column('word', sa.Text),
sa.Column('info', Json))
+ async def _setup_preprocessing(self) -> None:
+ """ Load the rules for preprocessing and set up the handlers.
+ """
+
+ rules = self.conn.config.load_sub_configuration('icu_tokenizer.yaml',
+ config='TOKENIZER_CONFIG')
+ preprocessing_rules = rules.get('query-preprocessing', [])
+
+ self.preprocessors = []
+
+ for func in preprocessing_rules:
+ if 'step' not in func:
+ raise UsageError("Preprocessing rule is missing the 'step' attribute.")
+ if not isinstance(func['step'], str):
+ raise UsageError("'step' attribute must be a simple string.")
+
+ module = self.conn.config.load_plugin_module(
+ func['step'], 'nominatim_api.query_preprocessing')
+ self.preprocessors.append(
+ module.create(QueryConfig(func).set_normalizer(self.normalizer)))
async def analyze_query(self, phrases: List[qmod.Phrase]) -> qmod.QueryStruct:
""" Analyze the given list of phrases and return the
tokenized query.
"""
log().section('Analyze query (using ICU tokenizer)')
- normalized = list(filter(lambda p: p.text,
- (qmod.Phrase(p.ptype, self.normalize_text(p.text))
- for p in phrases)))
- query = qmod.QueryStruct(normalized)
+ for func in self.preprocessors:
+ phrases = func(phrases)
+ query = qmod.QueryStruct(phrases)
+
log().var_dump('Normalized query', query.source)
if not query.source:
return query
return query
-
def normalize_text(self, text: str) -> str:
""" Bring the given text into a normalized form. That is the
standardized form search will work with. All information removed
"""
return cast(str, self.normalizer.transliterate(text))
-
def split_query(self, query: qmod.QueryStruct) -> Tuple[QueryParts, WordDict]:
""" Transliterate the phrases and split them into tokens.
return parts, words
-
async def lookup_in_db(self, words: List[str]) -> 'sa.Result[Any]':
""" Return the token information from the database for the
given word tokens.
t = self.conn.t.meta.tables['word']
return await self.conn.execute(t.select().where(t.c.word_token.in_(words)))
-
def add_extra_tokens(self, query: qmod.QueryStruct, parts: QueryParts) -> None:
""" Add tokens to query that are not saved in the database.
"""
count=1, addr_count=1, lookup_word=part.token,
word_token=part.token, info=None))
-
def rerank_tokens(self, query: qmod.QueryStruct, parts: QueryParts) -> None:
""" Add penalties to tokens that depend on presence of other token.
"""
and (repl.ttype != qmod.TokenType.HOUSENUMBER
or len(tlist.tokens[0].lookup_word) > 4):
repl.add_penalty(0.39)
- elif tlist.ttype == qmod.TokenType.HOUSENUMBER \
- and len(tlist.tokens[0].lookup_word) <= 3:
+ elif (tlist.ttype == qmod.TokenType.HOUSENUMBER
+ and len(tlist.tokens[0].lookup_word) <= 3):
if any(c.isdigit() for c in tlist.tokens[0].lookup_word):
for repl in node.starting:
if repl.end == tlist.end and repl.ttype != qmod.TokenType.HOUSENUMBER:
projects / nominatim.git / blobdiff