hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-03-11 21:34:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

remove remaining references to php code

Browse Source
This commit is contained in:
Sarah Hoffmann
2024-09-15 15:33:59 +02:00
parent 7ba5152493
commit 7717bbf59d
10 changed files with 6 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/nominatim_db/tokenizer/factory.py
View File

@@ -15,9 +15,6 @@ be used consistently when querying and updating the database.
This module provides the functions to create and configure a new tokenizer
as well as instantiating the appropriate tokenizer for updating an existing
database.
A tokenizer usually also includes PHP code for querying. The appropriate PHP
normalizer module is installed, when the tokenizer is created.
"""
from typing import Optional
import logging

20
src/nominatim_db/tokenizer/icu_tokenizer.py
View File

@@ -13,7 +13,6 @@ from typing import Optional, Sequence, List, Tuple, Mapping, Any, cast, \
import itertools
import logging
from pathlib import Path
from textwrap import dedent
from psycopg.types.json import Jsonb
from psycopg import sql as pysql
@@ -64,7 +63,6 @@ class ICUTokenizer(AbstractTokenizer):
"""
self.loader = ICURuleLoader(config)
self._install_php(config.lib_dir.php, overwrite=True)
self._save_config()
if init_db:
@@ -81,8 +79,6 @@ class ICUTokenizer(AbstractTokenizer):
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: Configuration) -> None:
""" Do any required postprocessing to make the tokenizer data ready
@@ -281,22 +277,6 @@ class ICUTokenizer(AbstractTokenizer):
return list(s[0].split('@')[0] for s in cur)
def _install_php(self, phpdir: Optional[Path], overwrite: bool = True) -> None:
""" Install the php script for the tokenizer.
"""
if phpdir is not None:
assert self.loader is not None
php_file = self.data_dir / "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) -> None:
""" Save the configuration that needs to remain stable for the given
database as database properties.

20
src/nominatim_db/tokenizer/legacy_tokenizer.py
View File

@@ -14,7 +14,6 @@ import logging
from pathlib import Path
import re
import shutil
from textwrap import dedent
from icu import Transliterator
import psycopg
@@ -120,8 +119,6 @@ class LegacyTokenizer(AbstractTokenizer):
self.normalization = config.TERM_NORMALIZATION
self._install_php(config, overwrite=True)
with connect(self.dsn) as conn:
_check_module(module_dir, conn)
self._save_config(conn, config)
@@ -145,8 +142,6 @@ class LegacyTokenizer(AbstractTokenizer):
config.lib_dir.module,
config.project_dir / 'module')
self._install_php(config, overwrite=False)
def finalize_import(self, config: Configuration) -> None:
""" Do any required postprocessing to make the tokenizer data ready
for use.
@@ -272,21 +267,6 @@ class LegacyTokenizer(AbstractTokenizer):
return list(s[0] for s in cur)
def _install_php(self, config: Configuration, overwrite: bool = True) -> None:
""" Install the php script for the tokenizer.
"""
if config.lib_dir.php is not None:
php_file = self.data_dir / "tokenizer.php"
if not php_file.exists() or overwrite:
php_file.write_text(dedent(f"""\
<?php
@define('CONST_Max_Word_Frequency', {config.MAX_WORD_FREQUENCY});
@define('CONST_Term_Normalization_Rules', "{config.TERM_NORMALIZATION}");
require_once('{config.lib_dir.php}/tokenizer/legacy_tokenizer.php');
"""), encoding='utf-8')
def _init_db_tables(self, config: Configuration) -> None:
""" Set up the word table and fill it with pre-computed word
frequencies.