WIP

server/data/search.py

@@ -1,5 +1,5 @@
 import datetime
-import typing as t
+from concurrent.futures import ThreadPoolExecutor
 
 from server.data.contacts import Contact, IContactProvider
 from server.data.manager import DataManager
@@ -34,6 +34,8 @@ def search_and_summarize(
         self, contact: Contact
     ) -> tuple[Contact, ContributionSummary] | None:
         """Search for a contact and summarize their contributions."""
+        # LOGGING
+        # print(f"Searching for {contact}")
         for alternative in self._alternatives_helper.get_alternatives(contact):
             if alternative.duplicate_key in self._seen:
                 continue
@@ -48,9 +50,12 @@ def search_and_summarize(
 
     def search_and_summarize_contacts(
         self, contacts: IContactProvider
-    ) -> t.Iterable[tuple[Contact, ContributionSummary]]:
+    ) -> list[tuple[Contact, ContributionSummary]]:
         """Search for contacts and summarize their contributions."""
-        for contact in contacts.get_contacts():
-            result = self.search_and_summarize(contact)
-            if result is not None:
-                yield result
+        contact_list = list(contacts.get_contacts())
+        with ThreadPoolExecutor() as executor:
+            results = []
+            for result in executor.map(self.search_and_summarize, contact_list):
+                if result is not None:
+                    results.append(result)
+        return results

server/data/summaries.py

@@ -176,21 +176,21 @@ def _contributions(
                 contact.last_name, contact.zip5, related_name_set
             )
 
-    def _summaries_for_contact(
-        self, contact: Contact
-    ) -> t.Iterable[ContributionSummary]:
+    def _summaries_for_contact(self, contact: Contact) -> list[ContributionSummary]:
         """Return all possible contribution summaries for a contact."""
         related_name_sets = list(
             self._names_provider.get_related_names(contact.first_name)
         )
         # No related names? Just use the first name.
         if not related_name_sets:
             related_name_sets = [frozenset([contact.first_name])]
+        summaries = []
         for related_name_set in related_name_sets:
             contributions = self._contributions(contact, related_name_set)
             summary = ContributionSummary(contributions)
             if summary.total > 0:
-                yield summary
+                summaries.append(summary)
+        return summaries
 
     def preferred_summary_for_contact(
         self, contact: Contact
@@ -200,9 +200,11 @@ def preferred_summary_for_contact(
         try_contacts = [contact]
         if contact.has_zip:
             try_contacts.append(contact.without_zip())
-        summaries: list[ContributionSummary] = []
+
+        summaries = []
         for try_contact in try_contacts:
-            summaries.extend(list(self._summaries_for_contact(try_contact)))
+            summaries.extend(self._summaries_for_contact(try_contact))
+
         if not summaries:
             return None
         return max(summaries, key=lambda s: s.total)

server/utils/bq.py

@@ -127,7 +127,6 @@ class BQClient(bigquery.Client):
     def execute(self, statement: Statement):
         """Execute the query."""
         query = statement.build_query()
-        # print("EXECUTING: ", query, "WITH PARAMS: ", statement.params)
         job_config = statement.build_query_job_config()
         job = self.query(query, job_config=job_config)
         return job.result()