import itertools
import json
import logging
-import re
from textwrap import dedent
from nominatim.db.connection import connect
from nominatim.db.utils import CopyBuffer
from nominatim.db.sql_preprocessor import SQLPreprocessor
-from nominatim.indexer.place_info import PlaceInfo
+from nominatim.data.place_info import PlaceInfo
from nominatim.tokenizer.icu_rule_loader import ICURuleLoader
from nominatim.tokenizer.base import AbstractAnalyzer, AbstractTokenizer
"""
self.loader = ICURuleLoader(config)
- self._install_php(config.lib_dir.php)
+ self._install_php(config.lib_dir.php, overwrite=True)
self._save_config()
if init_db:
with connect(self.dsn) as conn:
self.loader.load_config_from_db(conn)
+ self._install_php(config.lib_dir.php, overwrite=False)
+
def finalize_import(self, config):
""" Do any required postprocessing to make the tokenizer data ready
self.loader.make_token_analysis())
- def _install_php(self, phpdir):
+ def _install_php(self, phpdir, overwrite=True):
""" Install the php script for the tokenizer.
"""
php_file = self.data_dir / "tokenizer.php"
- php_file.write_text(dedent(f"""\
- <?php
- @define('CONST_Max_Word_Frequency', 10000000);
- @define('CONST_Term_Normalization_Rules', "{self.loader.normalization_rules}");
- @define('CONST_Transliteration', "{self.loader.get_search_rules()}");
- require_once('{phpdir}/tokenizer/icu_tokenizer.php');"""))
+
+ if not php_file.exists() or overwrite:
+ php_file.write_text(dedent(f"""\
+ <?php
+ @define('CONST_Max_Word_Frequency', 10000000);
+ @define('CONST_Term_Normalization_Rules', "{self.loader.normalization_rules}");
+ @define('CONST_Transliteration', "{self.loader.get_search_rules()}");
+ require_once('{phpdir}/tokenizer/icu_tokenizer.php');"""), encoding='utf-8')
def _save_config(self):
+ [(k, v, part_ids.get(v, None)) for k, v in partial_tokens.items()]
- @staticmethod
- def normalize_postcode(postcode):
+ def normalize_postcode(self, postcode):
""" Convert the postcode to a standardized form.
This function must yield exactly the same result as the SQL function
""" Update postcode tokens in the word table from the location_postcode
table.
"""
- to_delete = []
+ analyzer = self.token_analysis.analysis.get('@postcode')
+
with self.conn.cursor() as cur:
- # This finds us the rows in location_postcode and word that are
- # missing in the other table.
- cur.execute("""SELECT * FROM
- (SELECT pc, word FROM
- (SELECT distinct(postcode) as pc FROM location_postcode) p
- FULL JOIN
- (SELECT word FROM word WHERE type = 'P') w
- ON pc = word) x
- WHERE pc is null or word is null""")
-
- with CopyBuffer() as copystr:
- for postcode, word in cur:
- if postcode is None:
- to_delete.append(word)
- else:
- copystr.add(self._search_normalized(postcode),
- 'P', postcode)
-
- if to_delete:
- cur.execute("""DELETE FROM WORD
- WHERE type ='P' and word = any(%s)
- """, (to_delete, ))
-
- copystr.copy_out(cur, 'word',
- columns=['word_token', 'type', 'word'])
+ # First get all postcode names currently in the word table.
+ cur.execute("SELECT DISTINCT word FROM word WHERE type = 'P'")
+ word_entries = set((entry[0] for entry in cur))
+
+ # Then compute the required postcode names from the postcode table.
+ needed_entries = set()
+ cur.execute("SELECT country_code, postcode FROM location_postcode")
+ for cc, postcode in cur:
+ info = PlaceInfo({'country_code': cc,
+ 'class': 'place', 'type': 'postcode',
+ 'address': {'postcode': postcode}})
+ address = self.sanitizer.process_names(info)[1]
+ for place in address:
+ if place.kind == 'postcode':
+ if analyzer is None:
+ postcode_name = place.name.strip().upper()
+ variant_base = None
+ else:
+ postcode_name = analyzer.normalize(place.name)
+ variant_base = place.get_attr("variant")
+
+ if variant_base:
+ needed_entries.add(f'{postcode_name}@{variant_base}')
+ else:
+ needed_entries.add(postcode_name)
+ break
+
+ # Now update the word table.
+ self._delete_unused_postcode_words(word_entries - needed_entries)
+ self._add_missing_postcode_words(needed_entries - word_entries)
+
+ def _delete_unused_postcode_words(self, tokens):
+ if tokens:
+ with self.conn.cursor() as cur:
+ cur.execute("DELETE FROM word WHERE type = 'P' and word = any(%s)",
+ (list(tokens), ))
+
+ def _add_missing_postcode_words(self, tokens):
+ if not tokens:
+ return
+
+ analyzer = self.token_analysis.analysis.get('@postcode')
+ terms = []
+
+ for postcode_name in tokens:
+ if '@' in postcode_name:
+ term, variant = postcode_name.split('@', 2)
+ term = self._search_normalized(term)
+ variants = {term}
+ if analyzer is not None:
+ variants.update(analyzer.get_variants_ascii(variant))
+ variants = list(variants)
+ else:
+ variants = [self._search_normalized(postcode_name)]
+ terms.append((postcode_name, variants))
+
+ if terms:
+ with self.conn.cursor() as cur:
+ cur.execute_values("""SELECT create_postcode_word(pc, var)
+ FROM (VALUES %s) AS v(pc, var)""",
+ terms)
+
+
def update_special_phrases(self, phrases, should_replace):
def _process_place_address(self, token_info, address):
for item in address:
if item.kind == 'postcode':
- self._add_postcode(item.name)
+ token_info.set_postcode(self._add_postcode(item))
elif item.kind == 'housenumber':
token_info.add_housenumber(*self._compute_housenumber_token(item))
elif item.kind == 'street':
if not item.suffix:
token_info.add_place(self._compute_partial_tokens(item.name))
elif not item.kind.startswith('_') and not item.suffix and \
- item.kind not in ('country', 'full'):
+ item.kind not in ('country', 'full', 'inclusion'):
token_info.add_address_term(item.kind, self._compute_partial_tokens(item.name))
return full_tokens, partial_tokens
- def _add_postcode(self, postcode):
+ def _add_postcode(self, item):
""" Make sure the normalized postcode is present in the word table.
"""
- if re.search(r'[:,;]', postcode) is None:
- postcode = self.normalize_postcode(postcode)
+ analyzer = self.token_analysis.analysis.get('@postcode')
+
+ if analyzer is None:
+ postcode_name = item.name.strip().upper()
+ variant_base = None
+ else:
+ postcode_name = analyzer.normalize(item.name)
+ variant_base = item.get_attr("variant")
+
+ if variant_base:
+ postcode = f'{postcode_name}@{variant_base}'
+ else:
+ postcode = postcode_name
- if postcode not in self._cache.postcodes:
- term = self._search_normalized(postcode)
- if not term:
- return
+ if postcode not in self._cache.postcodes:
+ term = self._search_normalized(postcode_name)
+ if not term:
+ return None
- with self.conn.cursor() as cur:
- # no word_id needed for postcodes
- cur.execute("""INSERT INTO word (word_token, type, word)
- (SELECT %s, 'P', pc FROM (VALUES (%s)) as v(pc)
- WHERE NOT EXISTS
- (SELECT * FROM word
- WHERE type = 'P' and word = pc))
- """, (term, postcode))
- self._cache.postcodes.add(postcode)
+ variants = {term}
+ if analyzer is not None and variant_base:
+ variants.update(analyzer.get_variants_ascii(variant_base))
+
+ with self.conn.cursor() as cur:
+ cur.execute("SELECT create_postcode_word(%s, %s)",
+ (postcode, list(variants)))
+ self._cache.postcodes.add(postcode)
+
+ return postcode_name
class _TokenInfo:
self.street_tokens = set()
self.place_tokens = set()
self.address_tokens = {}
+ self.postcode = None
@staticmethod
if self.address_tokens:
out['addr'] = self.address_tokens
+ if self.postcode:
+ out['postcode'] = self.postcode
+
return out
if partials:
self.address_tokens[key] = self._mk_array(partials)
+ def set_postcode(self, postcode):
+ """ Set the postcode to the given one.
+ """
+ self.postcode = postcode
+
class _TokenCache:
""" Cache for token information to avoid repeated database queries.
projects / nominatim.git / blobdiff