Optionally specify * to handle unknown proj-tag-names

aws_project_costs/main.py

@@ -1,3 +1,4 @@
+import logging
 from argparse import ArgumentParser
 
 import yaml
@@ -13,9 +14,12 @@ def main() -> None:
     )
     parser.add_argument("--costs", required=True, help="Project costs CSV")
     parser.add_argument("--output", help="Output file")
+    parser.add_argument("--verbose", "-v", action="store_true", help="Verbose output")
 
     args = parser.parse_args()
 
+    logging.basicConfig(level=logging.DEBUG if args.verbose else logging.INFO)
+
     with open(args.config) as f:
         config = yaml.safe_load(f)
 

aws_project_costs/project-cost-schema.json

@@ -5,7 +5,7 @@
   "type": "object",
   "properties": {
     "proj-tag-names": {
-      "description": "A mapping of AWS project tags to the canonical project name",
+      "description": "A mapping of AWS project tags to the canonical project name. Optionally use '*' to map unknown tags to a defined project name",
       "type": "object",
       "additionalProperties": {
         "type": "string",

aws_project_costs/project_costs.py

@@ -1,10 +1,13 @@
 import json
+import logging
 from enum import Enum
 from operator import itemgetter
 from typing import Any, Hashable, Optional
 
 import pandas as pd
 
+logger = logging.getLogger(__name__)
+
 PROJECT_TAG = "Proj"
 
 
@@ -82,9 +85,15 @@ def _shared_account(
 
         project_tag = costs_tag[5:]
         if project_tagname and project_tag and (project_tag not in shared_tag_values):
-            if project_tag not in proj_tag_names_map:
+            if project_tag in proj_tag_names_map:
+                project_name = proj_tag_names_map[project_tag]
+            elif "*" in proj_tag_names_map:
+                project_name = proj_tag_names_map["*"]
+                logger.warn(
+                    "Project tag %s not found, using %s", project_tag, project_name
+                )
+            else:
                 raise ValueError(f"{project_tag} is not in proj-tag-names")
-            project_name = proj_tag_names_map[project_tag]
             rows.append(
                 (
                     start.date().isoformat(),
@@ -177,7 +186,7 @@ def analyse_costs_csv(
     for start in sorted(df["START"].unique()):
         month_costs = df[df["START"] == start]
         for accountname in month_costs["ACCOUNTNAME"].unique():
-            # print(f"Processing {accountname} {start}")
+            logger.debug(f"Processing {accountname} {start}")
             try:
                 acc_itemised_rows = allocate_costs(
                     accountname=accountname,
@@ -187,7 +196,9 @@ def analyse_costs_csv(
                 )
                 itemised_rows.extend(sorted(acc_itemised_rows, key=itemgetter(1, 2, 0)))
             except Exception as e:
-                print(f"ERROR: Failed to analyse account {accountname} {start} {e}")
+                logger.error(
+                    f"ERROR: Failed to analyse account {accountname} {start} {e}"
+                )
                 raise
 
     if output_csv_filename: