convert admin --analyse-indexing to new indexing method

[nominatim.git] / nominatim / tools / postcodes.py

diff --git a/nominatim/tools/postcodes.py b/nominatim/tools/postcodes.py
index d00fc97a8dbb39180b2ca5dae92784a7291bd40e..9c66719b5fe1ce55573985f8a653876c093102c6 100644 (file)
--- a/nominatim/tools/postcodes.py
+++ b/nominatim/tools/postcodes.py
@@ -1,7 +1,14 @@
+# 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.

 """
 Functions for importing, updating and otherwise maintaining the table
 of artificial postcode centroids.
 """
 """
 Functions for importing, updating and otherwise maintaining the table
 of artificial postcode centroids.
 """

+from collections import defaultdict

 import csv
 import gzip
 import logging
 import csv
 import gzip
 import logging


@@ -10,6 +17,8 @@ from math import isfinite
 from psycopg2 import sql as pysql
 
 from nominatim.db.connection import connect
 from psycopg2 import sql as pysql
 
 from nominatim.db.connection import connect

+from nominatim.utils.centroid import PointsCentroid
+from nominatim.data.postcode_format import PostcodeFormatter

 
 LOG = logging.getLogger()
 
 
 LOG = logging.getLogger()
 


@@ -24,20 +33,31 @@ def _to_float(num, max_value):
 
     return num
 
 
     return num
 

-class _CountryPostcodesCollector:
+class _PostcodeCollector:

     """ Collector for postcodes of a single country.
     """
 
     """ Collector for postcodes of a single country.
     """
 

-    def __init__(self, country):
+    def __init__(self, country, matcher):

         self.country = country
         self.country = country

-        self.collected = dict()
+        self.matcher = matcher
+        self.collected = defaultdict(PointsCentroid)
+        self.normalization_cache = None

 
 
     def add(self, postcode, x, y):
         """ Add the given postcode to the collection cache. If the postcode
             already existed, it is overwritten with the new centroid.
         """
 
 
     def add(self, postcode, x, y):
         """ Add the given postcode to the collection cache. If the postcode
             already existed, it is overwritten with the new centroid.
         """

-        self.collected[postcode] = (x, y)
+        if self.matcher is not None:
+            if self.normalization_cache and self.normalization_cache[0] == postcode:
+                normalized = self.normalization_cache[1]
+            else:
+                match = self.matcher.match(postcode)
+                normalized = self.matcher.normalize(match) if match else None
+                self.normalization_cache = (postcode, normalized)
+
+            if normalized:
+                self.collected[normalized] += (x, y)

 
 
     def commit(self, conn, analyzer, project_dir):
 
 
     def commit(self, conn, analyzer, project_dir):


@@ -87,16 +107,16 @@ class _CountryPostcodesCollector:
                            WHERE country_code = %s""",
                         (self.country, ))
             for postcode, x, y in cur:
                            WHERE country_code = %s""",
                         (self.country, ))
             for postcode, x, y in cur:

-                newx, newy = self.collected.pop(postcode, (None, None))
-                if newx is not None:
-                    dist = (x - newx)**2 + (y - newy)**2
-                    if dist > 0.0000001:
+                pcobj = self.collected.pop(postcode, None)
+                if pcobj:
+                    newx, newy = pcobj.centroid()
+                    if (x - newx) > 0.0000001 or (y - newy) > 0.0000001:

                         to_update.append((postcode, newx, newy))
                 else:
                     to_delete.append(postcode)
 
                         to_update.append((postcode, newx, newy))
                 else:
                     to_delete.append(postcode)
 

-        to_add = [(k, v[0], v[1]) for k, v in self.collected.items()]
-        self.collected = []
+        to_add = [(k, *v.centroid()) for k, v in self.collected.items()]
+        self.collected = None

 
         return to_add, to_delete, to_update
 
 
         return to_add, to_delete, to_update
 


@@ -119,8 +139,10 @@ class _CountryPostcodesCollector:
                 postcode = analyzer.normalize_postcode(row['postcode'])
                 if postcode not in self.collected:
                     try:
                 postcode = analyzer.normalize_postcode(row['postcode'])
                 if postcode not in self.collected:
                     try:

-                        self.collected[postcode] = (_to_float(row['lon'], 180),
-                                                    _to_float(row['lat'], 90))
+                        # Do float conversation separately, it might throw
+                        centroid = (_to_float(row['lon'], 180),
+                                    _to_float(row['lat'], 90))
+                        self.collected[postcode] += centroid

                     except ValueError:
                         LOG.warning("Bad coordinates %s, %s in %s country postcode file.",
                                     row['lat'], row['lon'], self.country)
                     except ValueError:
                         LOG.warning("Bad coordinates %s, %s in %s country postcode file.",
                                     row['lat'], row['lon'], self.country)


@@ -130,13 +152,13 @@ class _CountryPostcodesCollector:
 
 
     def _open_external(self, project_dir):
 
 
     def _open_external(self, project_dir):

-        fname = project_dir / '{}_postcodes.csv'.format(self.country)
+        fname = project_dir / f'{self.country}_postcodes.csv'

 
         if fname.is_file():
             LOG.info("Using external postcode file '%s'.", fname)
 
         if fname.is_file():
             LOG.info("Using external postcode file '%s'.", fname)

-            return open(fname, 'r')
+            return open(fname, 'r', encoding='utf-8')

 
 

-        fname = project_dir / '{}_postcodes.csv.gz'.format(self.country)
+        fname = project_dir / f'{self.country}_postcodes.csv.gz'

 
         if fname.is_file():
             LOG.info("Using external postcode file '%s'.", fname)
 
         if fname.is_file():
             LOG.info("Using external postcode file '%s'.", fname)


@@ -152,6 +174,7 @@ def update_postcodes(dsn, project_dir, tokenizer):
         potentially enhances it with external data and then updates the
         postcodes in the table 'location_postcode'.
     """
         potentially enhances it with external data and then updates the
         postcodes in the table 'location_postcode'.
     """

+    matcher = PostcodeFormatter()

     with tokenizer.name_analyzer() as analyzer:
         with connect(dsn) as conn:
             # First get the list of countries that currently have postcodes.
     with tokenizer.name_analyzer() as analyzer:
         with connect(dsn) as conn:
             # First get the list of countries that currently have postcodes.


@@ -163,19 +186,17 @@ def update_postcodes(dsn, project_dir, tokenizer):
             # Recompute the list of valid postcodes from placex.
             with conn.cursor(name="placex_postcodes") as cur:
                 cur.execute("""
             # Recompute the list of valid postcodes from placex.
             with conn.cursor(name="placex_postcodes") as cur:
                 cur.execute("""

-                SELECT cc as country_code, pc, ST_X(centroid), ST_Y(centroid)
+                SELECT cc, pc, ST_X(centroid), ST_Y(centroid)

                 FROM (SELECT
                         COALESCE(plx.country_code,
                                  get_country_code(ST_Centroid(pl.geometry))) as cc,
                 FROM (SELECT
                         COALESCE(plx.country_code,
                                  get_country_code(ST_Centroid(pl.geometry))) as cc,

-                        token_normalized_postcode(pl.address->'postcode') as pc,
-                        ST_Centroid(ST_Collect(COALESCE(plx.centroid,
-                                                        ST_Centroid(pl.geometry)))) as centroid
+                        pl.address->'postcode' as pc,
+                        COALESCE(plx.centroid, ST_Centroid(pl.geometry)) as centroid

                       FROM place AS pl LEFT OUTER JOIN placex AS plx
                              ON pl.osm_id = plx.osm_id AND pl.osm_type = plx.osm_type
                       FROM place AS pl LEFT OUTER JOIN placex AS plx
                              ON pl.osm_id = plx.osm_id AND pl.osm_type = plx.osm_type

-                    WHERE pl.address ? 'postcode' AND pl.geometry IS NOT null
-                    GROUP BY cc, pc) xx
+                    WHERE pl.address ? 'postcode' AND pl.geometry IS NOT null) xx

                 WHERE pc IS NOT null AND cc IS NOT null
                 WHERE pc IS NOT null AND cc IS NOT null

-                ORDER BY country_code, pc""")
+                ORDER BY cc, pc""")

 
                 collector = None
 
 
                 collector = None
 


@@ -183,7 +204,7 @@ def update_postcodes(dsn, project_dir, tokenizer):
                     if collector is None or country != collector.country:
                         if collector is not None:
                             collector.commit(conn, analyzer, project_dir)
                     if collector is None or country != collector.country:
                         if collector is not None:
                             collector.commit(conn, analyzer, project_dir)

-                        collector = _CountryPostcodesCollector(country)
+                        collector = _PostcodeCollector(country, matcher.get_matcher(country))

                         todo_countries.discard(country)
                     collector.add(postcode, x, y)
 
                         todo_countries.discard(country)
                     collector.add(postcode, x, y)
 


@@ -192,7 +213,8 @@ def update_postcodes(dsn, project_dir, tokenizer):
 
             # Now handle any countries that are only in the postcode table.
             for country in todo_countries:
 
             # Now handle any countries that are only in the postcode table.
             for country in todo_countries:

-                _CountryPostcodesCollector(country).commit(conn, analyzer, project_dir)
+                fmt = matcher.get_matcher(country)
+                _PostcodeCollector(country, fmt).commit(conn, analyzer, project_dir)

 
             conn.commit()
 
 
             conn.commit()