From cdbd0183f033b7d34eb9965456d2998f2c277490 Mon Sep 17 00:00:00 2001
From: jules cicurel <180195494+jcicurel-pass@users.noreply.github.com>
Date: Fri, 7 Feb 2025 17:23:52 +0100
Subject: [PATCH] (PC-33878) script: try ApiAdresse with collective offers
 offerVenue field

---
 .../scripts/collective_other_address/main.py  | 44 +++++++++++++++++++
 1 file changed, 44 insertions(+)
 create mode 100644 api/src/pcapi/scripts/collective_other_address/main.py

diff --git a/api/src/pcapi/scripts/collective_other_address/main.py b/api/src/pcapi/scripts/collective_other_address/main.py
new file mode 100644
index 00000000000..2b205aafcac
--- /dev/null
+++ b/api/src/pcapi/scripts/collective_other_address/main.py
@@ -0,0 +1,44 @@
+import csv
+import logging
+import os
+import typing
+
+from sqlalchemy.sql.expression import func
+
+from pcapi.app import app
+from pcapi.connectors import api_adresse
+from pcapi.core.educational import models as educational_models
+from pcapi.models import db
+
+
+logger = logging.getLogger(__name__)
+
+app.app_context().push()
+
+if __name__ == "__main__":
+    # try with a sample of 100 collective offers
+    collective_offers: typing.Iterable[educational_models.CollectiveOffer] = (
+        db.session.query(educational_models.CollectiveOffer)
+        .filter(educational_models.CollectiveOffer.offerVenue.op("->>")("addressType") == "other")
+        .order_by(func.random())
+        .limit(100)
+    )
+
+    lines = []
+    for collective_offer in collective_offers:
+        text = collective_offer.offerVenue["otherAddress"].replace("\n", " ").replace(",", " ")
+        lines.append({"nom": text})
+
+    payload = api_adresse.format_payload(headers=["nom"], lines=lines)
+
+    backend = api_adresse.ApiAdresseBackend()
+    result = backend.search_csv(payload=payload, columns=["nom"])
+
+    with open(f"{os.environ.get('OUTPUT_DIRECTORY')}/result.csv", "w", encoding="utf-8") as result_file:
+        writer = None
+        for row in result:
+            if writer is None:
+                writer = csv.DictWriter(result_file, fieldnames=row.keys(), delimiter=",")
+                writer.writeheader()
+
+            writer.writerow(row)