Fix validating docs

README.md

@@ -96,21 +96,21 @@ Recommended practices
 
 ### Queries
 
-- Should be defined in files named as `<project>/<dataset>/<table>_<version>/query.sql` e.g.
+- Should be defined in files named as `sql/<project>/<dataset>/<table>_<version>/query.sql` e.g.
   `sql/moz-fx-data-shared-prod/telemetry_derived/clients_daily_v7/query.sql`
   - Queries that populate tables should always be named with a version suffix;
     we assume that future optimizations to the data representation may require
     schema-incompatible changes such as dropping columns
 - May be generated using a python script that prints the query to stdout
-  - Should save output as `<project>/<dataset>/<table>_<version>/query.sql` as above
-  - Should be named as `<project>/query_type.sql.py` e.g. `sql/moz-fx-data-shared-prod/clients_daily.sql.py`
+  - Should save output as `sql/<project>/<dataset>/<table>_<version>/query.sql` as above
+  - Should be named as `sql/<project>/query_type.sql.py` e.g. `sql/moz-fx-data-shared-prod/clients_daily.sql.py`
   - May use options to generate queries for different destination tables e.g.
     using `--source telemetry_core_parquet_v3` to generate
     `sql/moz-fx-data-shared-prod/telemetry/core_clients_daily_v1/query.sql` and using `--source main_summary_v4` to
     generate `sql/moz-fx-data-shared-prod/telemetry/clients_daily_v7/query.sql`
   - Should output a header indicating options used e.g.
     ```sql
-    -- Query generated by: moz-fx-data-shared-prod/clients_daily.sql.py --source telemetry_core_parquet
+    -- Query generated by: sql/moz-fx-data-shared-prod/clients_daily.sql.py --source telemetry_core_parquet
     ```
 - Should not specify a project or dataset in table names to simplify testing
 - Should be [incremental]
@@ -126,7 +126,7 @@ Recommended practices
 
 ### Views
 
-- Should be defined in files named as `<project>/<dataset>/<table>/view.sql` e.g.
+- Should be defined in files named as `sql/<project>/<dataset>/<table>/view.sql` e.g.
   `sql/moz-fx-data-shared-prod/telemetry/core/view.sql`
   - Views should generally _not_ be named with a version suffix; a view represents a
     stable interface for users and whenever possible should maintain compatibility

bigquery_etl/cli/format.py

@@ -10,7 +10,7 @@ from bigquery_etl.format_sql.format import format as format_sql
 )
 @click.argument(
     "path",
-    default="sql/",  # todo: apply formatting to all projects
+    default="sql/",
     type=click.Path(file_okay=True),
 )
 def format(path):

bigquery_etl/docs/validate_docs.py

@@ -51,7 +51,7 @@ def sql_for_dry_run(file, parsed_udfs, project_dir):
             dry_run_sql = dry_run_sql.replace(udf, udf.replace(".", "_"))
 
         # remove explicit project references
-        dry_run_sql = dry_run_sql.replace(project_dir + ".", "")
+        dry_run_sql = dry_run_sql.replace(os.path.basename(project_dir) + ".", "")
 
     return dry_run_sql
 

bigquery_etl/query_scheduling/task.py

@@ -217,7 +217,7 @@ class Task:
         else:
             raise ValueError(
                 "query_file must be a path with format:"
-                " <project>/<dataset>/<table>_<version>/(query.sql|part1.sql)"
+                " sql/<project>/<dataset>/<table>_<version>/(query.sql|part1.sql)"
                 f" but is {self.query_file}"
             )
 

bigquery_etl/udf/parse_udf.py

@@ -18,7 +18,7 @@ from bigquery_etl.util.common import project_dirs
 
 
 UDF_DIRS = ("udf", "udf_js")
-MOZFUN_DIR = ("mozfun",)
+MOZFUN_DIR = ("sql/mozfun",)
 UDF_CHAR = "[a-zA-z0-9_]"
 UDF_FILE = "udf.sql"
 PROCEDURE_FILE = "stored_procedure.sql"

bigquery_etl/view/generate_views.py

@@ -64,7 +64,6 @@ def main():
         parser.error(f"argument --log-level: {e}")
 
     client = bigquery.Client()
-    # todo: support other projects
     tables = get_tables_matching_patterns(client, args.patterns)
 
     views = {}