Merge pull request #12 from wagesj45/codex/fix-report-definition-paradigm

Simplify report definitions

README.md

@@ -27,18 +27,21 @@ Reports are written under the `output/` directory. Each command updates the corr
 ### Configuring Reports
 
 Report queries are defined in `reports.yml`. Each entry specifies the `name`,
-`interval`, optional `label` and `chart` type, and a SQL `query` that must return
-`bucket` and `value` columns. When `generate_reports.py` runs, every matching
-definition creates `output/<interval>/<name>.json` and an interval dashboard.
+optional `label` and `chart` type, and a SQL `query` that must return `bucket`
+and `value` columns. The special token `{bucket}` is replaced with the
+appropriate SQLite `strftime` expression for each interval (hourly, daily,
+weekly or monthly) so that a single definition works across all durations.
+When `generate_reports.py` runs, every definition is executed for the requested
+interval and creates `output/<interval>/<name>.json` along with an HTML
+dashboard.
 
 Example snippet:
 
 ```yaml
 - name: hits
-  interval: hourly
   chart: bar
   query: |
-    SELECT strftime('%Y-%m-%d %H:00:00', datetime(time)) AS bucket,
+    SELECT {bucket} AS bucket,
            COUNT(*) AS value
     FROM logs
     GROUP BY bucket

reports.yml

@@ -1,20 +1,18 @@
 - name: hits
-  interval: hourly
   label: Hits
   chart: bar
   query: |
-    SELECT strftime('%Y-%m-%d %H:00:00', datetime(time)) AS bucket,
+    SELECT {bucket} AS bucket,
            COUNT(*) AS value
     FROM logs
     GROUP BY bucket
     ORDER BY bucket
 
 - name: error_rate
-  interval: hourly
   label: Error Rate (%)
   chart: line
   query: |
-    SELECT strftime('%Y-%m-%d %H:00:00', datetime(time)) AS bucket,
+    SELECT {bucket} AS bucket,
            SUM(CASE WHEN status >= 500 THEN 1 ELSE 0 END) * 100.0 / COUNT(*) AS value
     FROM logs
     GROUP BY bucket

scripts/generate_reports.py

@@ -13,6 +13,17 @@ OUTPUT_DIR = Path("output")
 TEMPLATE_DIR = Path("templates")
 REPORT_CONFIG = Path("reports.yml")
 
+# Mapping of interval names to SQLite strftime formats.  These strings are
+# substituted into report queries whenever the special ``{bucket}`` token is
+# present so that a single report definition can be reused for multiple
+# intervals.
+INTERVAL_FORMATS = {
+    "hourly": "%Y-%m-%d %H:00:00",
+    "daily": "%Y-%m-%d",
+    "weekly": "%Y-%W",
+    "monthly": "%Y-%m",
+}
+
 app = typer.Typer(help="Generate aggregated log reports")
 
 def _load_config() -> List[Dict]:
@@ -35,13 +46,23 @@ def _render_html(interval: str, reports: List[Dict], out_path: Path) -> None:
     template = env.get_template("report.html")
     out_path.write_text(template.render(interval=interval, reports=reports))
 
+
+def _bucket_expr(interval: str) -> str:
+    """Return the SQLite strftime expression for the given interval."""
+    fmt = INTERVAL_FORMATS.get(interval)
+    if not fmt:
+        typer.echo(f"Unsupported interval: {interval}")
+        raise typer.Exit(1)
+    return f"strftime('{fmt}', datetime(time))"
+
 def _generate_interval(interval: str) -> None:
     cfg = _load_config()
-    defs = [d for d in cfg if d.get("interval") == interval]
-    if not defs:
-        typer.echo(f"No reports defined for {interval}")
+    if not cfg:
+        typer.echo("No report definitions found")
         return
 
+    bucket = _bucket_expr(interval)
+
     conn = sqlite3.connect(DB_PATH)
     cur = conn.cursor()
 
@@ -49,9 +70,9 @@ def _generate_interval(interval: str) -> None:
     out_dir.mkdir(parents=True, exist_ok=True)
 
     report_list = []
-    for definition in defs:
+    for definition in cfg:
         name = definition["name"]
-        query = definition["query"]
+        query = definition["query"].replace("{bucket}", bucket)
         cur.execute(query)
         rows = cur.fetchall()
         headers = [c[0] for c in cur.description]

tests/test_reports.py

@@ -48,16 +48,14 @@ def sample_reports(tmp_path):
     cfg.write_text(
         """
 - name: hits
-  interval: hourly
   query: |
-    SELECT strftime('%Y-%m-%d %H:00:00', datetime(time)) AS bucket, COUNT(*) AS value
+    SELECT {bucket} AS bucket, COUNT(*) AS value
     FROM logs
     GROUP BY bucket
     ORDER BY bucket
 - name: error_rate
-  interval: hourly
   query: |
-    SELECT strftime('%Y-%m-%d %H:00:00', datetime(time)) AS bucket,
+    SELECT {bucket} AS bucket,
            SUM(CASE WHEN status >= 400 THEN 1 ELSE 0 END) * 100.0 / COUNT(*) AS value
     FROM logs
     GROUP BY bucket