From beb4195f16d089bf7f4dd56f0933749b6e325cc6 Mon Sep 17 00:00:00 2001
From: Deeman <hendriknote@gmail.com>
Date: Sat, 28 Feb 2026 17:27:16 +0100
Subject: [PATCH] feat(extract): daily tenant snapshots with date-based
 partition

- playtomic_tenants: partition by YYYY/MM/DD instead of ISO week;
  schedule changed from weekly to daily in workflows.toml
- playtomic_availability: _load_tenant_ids now tries 3-level glob
  (*/*/*/tenants.jsonl.gz) first for daily files, falls back to
  2-level for old monthly/weekly data

Alphabetical sort would rank old monthly files above daily ones
('t' > '2' in ASCII), so the explicit fallback chain is required.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 .../src/padelnomics_extract/playtomic_availability.py    | 6 ++++--
 .../src/padelnomics_extract/playtomic_tenants.py         | 9 ++++-----
 infra/supervisor/workflows.toml                          | 2 +-
 3 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/extract/padelnomics_extract/src/padelnomics_extract/playtomic_availability.py b/extract/padelnomics_extract/src/padelnomics_extract/playtomic_availability.py
index d708a61..5274ed1 100644
--- a/extract/padelnomics_extract/src/padelnomics_extract/playtomic_availability.py
+++ b/extract/padelnomics_extract/src/padelnomics_extract/playtomic_availability.py
@@ -76,8 +76,10 @@ def _load_tenant_ids(landing_dir: Path) -> list[str]:
     if not playtomic_dir.exists():
         return []
 
-    # Prefer JSONL (new format), fall back to blob (old format)
-    tenant_files = sorted(playtomic_dir.glob("*/*/tenants.jsonl.gz"), reverse=True)
+    # Prefer daily partition (YYYY/MM/DD), fall back to older monthly/weekly partitions
+    tenant_files = sorted(playtomic_dir.glob("*/*/*/tenants.jsonl.gz"), reverse=True)
+    if not tenant_files:
+        tenant_files = sorted(playtomic_dir.glob("*/*/tenants.jsonl.gz"), reverse=True)
     if not tenant_files:
         tenant_files = sorted(playtomic_dir.glob("*/*/tenants.json.gz"), reverse=True)
     if not tenant_files:
diff --git a/extract/padelnomics_extract/src/padelnomics_extract/playtomic_tenants.py b/extract/padelnomics_extract/src/padelnomics_extract/playtomic_tenants.py
index c4c0d06..e09102b 100644
--- a/extract/padelnomics_extract/src/padelnomics_extract/playtomic_tenants.py
+++ b/extract/padelnomics_extract/src/padelnomics_extract/playtomic_tenants.py
@@ -81,12 +81,11 @@ def extract(
     partitions and picks the most recent one.
     """
     today = datetime.now(UTC)
-    year = today.strftime("%G")   # ISO year (matches ISO week, differs from calendar year on week boundaries)
-    week = today.strftime("W%V")  # ISO week: W01 … W53
-    dest_dir = landing_path(landing_dir, "playtomic", year, week)
+    year, month, day = today.strftime("%Y"), today.strftime("%m"), today.strftime("%d")
+    dest_dir = landing_path(landing_dir, "playtomic", year, month, day)
     dest = dest_dir / "tenants.jsonl.gz"
     if dest.exists():
-        logger.info("Already have tenants for %s/%s — skipping", year, week)
+        logger.info("Already have tenants for %s/%s/%s — skipping", year, month, day)
         return {"files_written": 0, "files_skipped": 1, "bytes_written": 0}
 
     tiers = load_proxy_tiers()
@@ -162,7 +161,7 @@ def extract(
         "files_written": 1,
         "files_skipped": 0,
         "bytes_written": bytes_written,
-        "cursor_value": f"{year}/{week}",
+        "cursor_value": f"{year}/{month}/{day}",
     }
 
 
diff --git a/infra/supervisor/workflows.toml b/infra/supervisor/workflows.toml
index 5f5c43d..3dcf055 100644
--- a/infra/supervisor/workflows.toml
+++ b/infra/supervisor/workflows.toml
@@ -23,7 +23,7 @@ schedule = "monthly"
 
 [playtomic_tenants]
 module = "padelnomics_extract.playtomic_tenants"
-schedule = "weekly"
+schedule = "daily"
 
 [playtomic_availability]
 module = "padelnomics_extract.playtomic_availability"