From 08dc536c9306fda4aa94b1808ebb8f52b44ee2fa Mon Sep 17 00:00:00 2001
From: grabowski <berwn@buildfor.life>
Date: Wed, 22 Jul 2026 14:24:28 +0700
Subject: [PATCH] Add unit tests for RID API response parsing

Cover the previously-untested, highest-risk parsing in
fetch_water_data_for_date by mocking the HTTP call:
- hour 1-23 map to the same day; hour 24 rolls to next-day midnight
- qvalues "***" / None yield discharge None (no crash)
- None water level is skipped
- out-of-range (0, 25) and empty hourlytime rows are skipped
- missing "rows" key returns an empty list

This gives the scraper a safety net before its module is split.
---
 tests/test_scraper_parsing.py | 125 ++++++++++++++++++++++++++++++++++
 1 file changed, 125 insertions(+)
 create mode 100644 tests/test_scraper_parsing.py

diff --git a/tests/test_scraper_parsing.py b/tests/test_scraper_parsing.py
new file mode 100644
index 0000000..b8a28e4
--- /dev/null
+++ b/tests/test_scraper_parsing.py
@@ -0,0 +1,125 @@
+"""Assert-based tests for the RID API response parsing.
+
+The parsing in ``fetch_water_data_for_date`` is the riskiest, previously
+untested code: it maps the API's 1..24 "hourlytime" onto real timestamps
+(hour 24 rolls to next-day midnight) and treats ``"***"``/``None`` discharge as
+missing. These tests mock the HTTP call so no network is touched and stub the
+validator so we assert on the parser's output directly.
+"""
+
+import datetime
+from unittest.mock import MagicMock
+
+import pytest
+
+import src.water_scraper_v3 as scraper_mod
+from src.water_scraper_v3 import EnhancedWaterMonitorScraper as Scraper
+
+TARGET = datetime.datetime(2026, 7, 22)
+
+
+@pytest.fixture
+def make_scraper(monkeypatch):
+    """Return a factory that builds a bare scraper returning the given API rows."""
+
+    def _factory(rows):
+        scraper = Scraper.__new__(Scraper)  # bypass __init__ (no DB/network)
+        scraper.api_url = "https://example.invalid/api"
+        scraper.rate_limiter = MagicMock()
+        scraper.request_tracker = MagicMock()
+        scraper.station_config_path = "/nonexistent/stations.json"
+        scraper.station_mapping = scraper._load_station_mapping()  # bundled defaults
+
+        response = MagicMock()
+        response.json.return_value = {"rows": rows}
+        response.raise_for_status.return_value = None
+        scraper.session = MagicMock()
+        scraper.session.post.return_value = response
+
+        # Isolate parsing from validation.
+        monkeypatch.setattr(
+            scraper_mod.DataValidator,
+            "validate_measurements",
+            staticmethod(lambda m: m),
+        )
+        return scraper
+
+    return _factory
+
+
+def test_parses_water_level_and_discharge(make_scraper):
+    rows = [
+        {
+            "hourlytime": "9.00",
+            "wlvalues1": "3.50",
+            "qvalues1": "120.5",
+            "QPercent1": "45.2",
+        }
+    ]
+    data = make_scraper(rows).fetch_water_data_for_date(TARGET)
+
+    p20 = [d for d in data if d["station_code"] == "P.20"]
+    assert len(p20) == 1
+    m = p20[0]
+    assert m["water_level"] == 3.5
+    assert m["discharge"] == 120.5
+    assert m["discharge_percent"] == 45.2
+    assert m["timestamp"] == datetime.datetime(2026, 7, 22, 9, 0)
+    assert m["station_name_en"] == "Ban Chiang Dao"
+
+
+def test_discharge_asterisks_becomes_none(make_scraper):
+    rows = [{"hourlytime": "10.00", "wlvalues8": "4.20", "qvalues8": "***"}]
+    data = make_scraper(rows).fetch_water_data_for_date(TARGET)
+
+    p1 = [d for d in data if d["station_code"] == "P.1"][0]
+    assert p1["water_level"] == 4.2
+    assert p1["discharge"] is None
+    assert p1["discharge_percent"] is None
+
+
+def test_hour_24_rolls_to_next_day_midnight(make_scraper):
+    rows = [{"hourlytime": "24.00", "wlvalues1": "3.00"}]
+    data = make_scraper(rows).fetch_water_data_for_date(TARGET)
+
+    assert data[0]["timestamp"] == datetime.datetime(2026, 7, 23, 0, 0)
+
+
+def test_hours_1_to_23_stay_same_day(make_scraper):
+    rows = [
+        {"hourlytime": "1.00", "wlvalues1": "3.00"},
+        {"hourlytime": "23.00", "wlvalues1": "3.10"},
+    ]
+    data = make_scraper(rows).fetch_water_data_for_date(TARGET)
+
+    times = sorted(d["timestamp"] for d in data)
+    assert times == [
+        datetime.datetime(2026, 7, 22, 1, 0),
+        datetime.datetime(2026, 7, 22, 23, 0),
+    ]
+
+
+def test_none_water_level_is_skipped(make_scraper):
+    rows = [{"hourlytime": "9.00", "wlvalues1": None, "wlvalues2": "2.5"}]
+    data = make_scraper(rows).fetch_water_data_for_date(TARGET)
+
+    codes = {d["station_code"] for d in data}
+    assert "P.20" not in codes  # station 1 skipped (None water level)
+    assert "P.75" in codes  # station 2 present
+
+
+def test_out_of_range_and_empty_hours_skipped(make_scraper):
+    rows = [
+        {"hourlytime": "25.00", "wlvalues1": "3.0"},
+        {"hourlytime": "0.00", "wlvalues1": "3.0"},
+        {"hourlytime": "", "wlvalues1": "3.0"},
+    ]
+    data = make_scraper(rows).fetch_water_data_for_date(TARGET)
+
+    assert data == []
+
+
+def test_missing_rows_key_returns_empty(make_scraper):
+    scraper = make_scraper([])
+    scraper.session.post.return_value.json.return_value = {"unexpected": True}
+    assert scraper.fetch_water_data_for_date(TARGET) == []