From 48f694e002a6a71f63ebe8dc68f1c9490b108fab Mon Sep 17 00:00:00 2001
From: Viktor Barzin <vbarzin@gmail.com>
Date: Sun, 11 May 2025 19:06:08 +0000
Subject: [PATCH] [4/n] click-ify add detect floorplan command

run with
poetry run python main.py --step detect_floorplan
---
 crawler/4_detect_floorplan.py | 20 +++++++++++++++-----
 crawler/main.py               |  2 ++
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/crawler/4_detect_floorplan.py b/crawler/4_detect_floorplan.py
index 388f2d4..97dc8d9 100644
--- a/crawler/4_detect_floorplan.py
+++ b/crawler/4_detect_floorplan.py
@@ -1,9 +1,19 @@
 from data_access import Listing
 from tqdm import tqdm
 
-listings = Listing.get_all_listings()
 
-for listing in tqdm(listings):
-    tqdm.write(str(listing.identifier))
-    # listing.calculate_sqm_model() # using google/deplot model. Too slow, rather use tesseract
-    listing.calculate_sqm_ocr(recalculate=False)
+def detect_floorplan():
+    listings = Listing.get_all_listings()
+
+    for listing in tqdm(listings):
+        tqdm.write(str(listing.identifier))
+        # listing.calculate_sqm_model() # using google/deplot model. Too slow, rather use tesseract
+        listing.calculate_sqm_ocr(recalculate=False)
+
+
+def main():
+    detect_floorplan()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/crawler/main.py b/crawler/main.py
index 530a58f..f4a287e 100644
--- a/crawler/main.py
+++ b/crawler/main.py
@@ -4,11 +4,13 @@ import importlib
 dump_listings_module = importlib.import_module('1_dump_listings')
 dump_detail_module = importlib.import_module('2_dump_detail')
 dump_images_module = importlib.import_module('3_dump_images')
+detect_floorplan_module = importlib.import_module('4_detect_floorplan')
 
 steps_to_handlers = {
     'dump_listings': dump_listings_module.dump_listings,
     'dump_detail': dump_detail_module.dump_detail,
     'dump_images': dump_images_module.dump_images,
+    'detect_floorplan': detect_floorplan_module.detect_floorplan,
 }