From 6fc11be24997c0ed8c61239c41bb88b086651ae2 Mon Sep 17 00:00:00 2001
From: Nate Wessel <nate.wessel@toronto.ca>
Date: Tue, 17 Dec 2024 14:56:21 -0500
Subject: [PATCH] Cache travel time results (#171)

* table for storing cached times

temporarily in personal schema for ease of testing

* store the whole results object

trading space for speed in setting this up, for now

* return cached values

* set up for caching

* store cache

* try all table interactions

just in case something ever breaks, I don't want to be dependent on caching
---
 backend/app/get_travel_time.py       | 45 +++++++++++++++++++++++++---
 backend/app/routes.py                |  7 +----
 backend/tables/travel_time_cache.sql |  8 +++++
 3 files changed, 50 insertions(+), 10 deletions(-)
 create mode 100644 backend/tables/travel_time_cache.sql

diff --git a/backend/app/get_travel_time.py b/backend/app/get_travel_time.py
index 47c2072..67e249f 100644
--- a/backend/app/get_travel_time.py
+++ b/backend/app/get_travel_time.py
@@ -8,6 +8,8 @@
 import math
 import pandas
 import random
+import json
+from app.getGitHash import getGitHash
 
 # the way we currently do it
 def mean_daily_mean(obs):
@@ -20,9 +22,44 @@ def mean_daily_mean(obs):
     # average the days together
     return numpy.mean(daily_means)
 
+def checkCache(uri):
+    query = f'''
+        SELECT results
+        FROM nwessel.cached_travel_times
+        WHERE uri_string = %(uri)s AND commit_hash = %(hash)s
+    '''
+    connection = getConnection()
+    with connection:
+        with connection.cursor() as cursor:
+            try:
+                cursor.execute(query, {'uri': uri, 'hash': getGitHash()})
+                for (record,) in cursor: # will skip if no records
+                    return record # there could only be one
+            except:
+                pass
+
+def cacheAndReturn(obj,uri):
+    query = f'''
+        INSERT INTO nwessel.cached_travel_times (uri_string, commit_hash, results)
+        VALUES (%(uri)s, %(hash)s, %(results)s)
+    '''
+    connection = getConnection()
+    with connection:
+        with connection.cursor() as cursor:
+            try:
+                cursor.execute(query, {'uri': uri, 'hash': getGitHash(), 'results': json.dumps(obj)})
+            finally:
+                return obj
+
 def get_travel_time(start_node, end_node, start_time, end_time, start_date, end_date, include_holidays, dow_list):
     """Function for returning data from the aggregate-travel-times/ endpoint"""
 
+    # first check the cache
+    cacheURI = f'/{start_node}/{end_node}/{start_time}/{end_time}/{start_date}/{end_date}/{str(include_holidays).lower()}/{"".join(map(str,dow_list))}'
+    cachedValue = checkCache(cacheURI)
+    if cachedValue:
+        return cachedValue
+
     holiday_clause = ''
     if not include_holidays:
         holiday_clause = '''AND NOT EXISTS (
@@ -112,7 +149,7 @@ def get_travel_time(start_node, end_node, start_time, end_time, start_date, end_
 
     if len(sample) < 1:
         # no travel times or related info to return here
-        return {
+        return cacheAndReturn({
             'results': {
                 'travel_time': None,
                 'observations': [],
@@ -124,7 +161,7 @@ def get_travel_time(start_node, end_node, start_time, end_time, start_date, end_
                 'corridor': {'links': links, 'map_version': map_version},
                 'query_params': query_params
             }
-        }
+        }, cacheURI)
 
     tt_seconds = mean_daily_mean(sample)
 
@@ -143,7 +180,7 @@ def get_travel_time(start_node, end_node, start_time, end_time, start_date, end_
             }
         }
 
-    return {
+    return cacheAndReturn({
         'results': {
             'travel_time': timeFormats(tt_seconds,1),
             'confidence': {
@@ -156,4 +193,4 @@ def get_travel_time(start_node, end_node, start_time, end_time, start_date, end_
             'corridor': {'links': links, 'map_version': map_version},
             'query_params': query_params
         }
-    }
+    },cacheURI)
diff --git a/backend/app/routes.py b/backend/app/routes.py
index 2c9a4b4..346df02 100644
--- a/backend/app/routes.py
+++ b/backend/app/routes.py
@@ -116,13 +116,8 @@ def get_here_links_between_two_nodes(network, from_node_id, to_node_id):
     })
 
 
-
-
 # test URL /aggregate-travel-times/30310940/30310942/9/12/2020-05-01/2020-06-01/true/2
-@app.route(
-    '/aggregate-travel-times/<start_node>/<end_node>/<start_time>/<end_time>/<start_date>/<end_date>/<include_holidays>/<dow_str>',
-    methods=['GET']
-)
+@app.route('/aggregate-travel-times/<start_node>/<end_node>/<start_time>/<end_time>/<start_date>/<end_date>/<include_holidays>/<dow_str>')
 def aggregate_travel_times(start_node, end_node, start_time, end_time, start_date, end_date, include_holidays, dow_str):
     """
     Return averaged travel times given the specified parameters.
diff --git a/backend/tables/travel_time_cache.sql b/backend/tables/travel_time_cache.sql
new file mode 100644
index 0000000..a030f0e
--- /dev/null
+++ b/backend/tables/travel_time_cache.sql
@@ -0,0 +1,8 @@
+CREATE TABLE nwessel.cached_travel_times (
+    uri_string text CHECK(uri_string ~ '^\/\d+\/\d+\/\d{1,2}\/\d{1,2}\/\d{4}-\d{2}-\d{2}\/\d{4}-\d{2}-\d{2}\/(true|false)\/[1-7]{1,7}$'),
+    commit_hash text,
+    results jsonb NOT NULL,
+    PRIMARY KEY (uri_string, commit_hash)
+);
+
+GRANT SELECT, INSERT ON nwessel.cached_travel_times TO tt_request_bot;