CSV export should respect --fileoutput flag

We now treat CSV output the same as JSON and YAML.
A --fileoutput-dynamic flag was added to support the previous behavior for users who desire it

README.md

@@ -106,15 +106,15 @@ Read more about [how KRR works](#how-krr-works)
 | Resource Recommendations 💡 | ✅ CPU/Memory requests and limits                                                                          | ✅ CPU/Memory requests and limits                           |
 | Installation Location 🌍    | ✅ Not required to be installed inside the cluster, can be used on your own device, connected to a cluster | ❌ Must be installed inside the cluster                     |
 | Workload Configuration 🔧   | ✅ No need to configure a VPA object for each workload                                                     | ❌ Requires VPA object configuration for each workload      |
-| Immediate Results ⚡        | ✅ Gets results immediately (given Prometheus is running)                                                  | ❌ Requires time to gather data and provide recommendations |
-| Reporting 📊                | ✅ Detailed CLI Report, web UI in [Robusta.dev](https://home.robusta.dev/)                                 | ❌ Not supported                                            |
+| Immediate Results ⚡         | ✅ Gets results immediately (given Prometheus is running)                                                  | ❌ Requires time to gather data and provide recommendations |
+| Reporting 📊                | ✅ Json, CSV, Markdown, [Web UI](#free-ui-for-krr-recommendations), and more!                              | ❌ Not supported                                            |
 | Extensibility 🔧            | ✅ Add your own strategies with few lines of Python                                                        | :warning: Limited extensibility                             |
 | Explainability 📖           | ✅ See graphs explaining the recommendations                                                               | ❌ Not supported                                            |
 | Custom Metrics 📏           | 🔄 Support in future versions                                                                              | ❌ Not supported                                            |
 | Custom Resources 🎛️         | 🔄 Support in future versions (e.g., GPU)                                                                  | ❌ Not supported                                            |
 | Autoscaling 🔀              | 🔄 Support in future versions                                                                              | ✅ Automatic application of recommendations                 |
-| Default History 🕒          | 14 days                                                                                                    | 8 days                                             |
-| Supports HPA 🔥          | ✅ Enable using `--allow-hpa` flag                                                                                                 | ❌ Not supported                                         |
+| Default History 🕒          | 14 days                                                                                                    | 8 days                                                     |
+| Supports HPA 🔥             | ✅ Enable using `--allow-hpa` flag                                                                         | ❌ Not supported                                            |
 
 
 <!-- GETTING STARTED -->
@@ -328,7 +328,7 @@ krr simple -c my-cluster-1 -c my-cluster-2
 </details>
 
 <details>
-  <summary>Customize output (JSON, YAML, and more</summary>
+  <summary>Output formats for reporting (JSON, YAML, CSV, and more)</summary>
 
 Currently KRR ships with a few formatters to represent the scan data:
 
@@ -338,22 +338,16 @@ Currently KRR ships with a few formatters to represent the scan data:
 - `pprint` - data representation from python's pprint library
 - `csv` - export data to a csv file in the current directory
 
-To run a strategy with a selected formatter, add a `-f` flag:
+To run a strategy with a selected formatter, add a `-f` flag. Usually this should be combined with `--fileoutput <filename>` to write clean output to file without logs:
 
 ```sh
-krr simple -f json
+krr simple -f json --fileoutput krr-report.json
 ```
 
-For JSON output, add --logtostderr  so no logs go to the result file:
+If you prefer, you can also use `--logtostderr` to get clean formatted output in one file and error logs in another:
 
 ```sh
-krr simple --logtostderr -f json > result.json
-```
-
-For YAML output, do the same:
-
-```sh
-krr simple --logtostderr -f yaml > result.yaml
+krr simple --logtostderr -f json > result.json 2> logs-and-errors.log
 ```
 </details>
 

robusta_krr/core/models/config.py

@@ -59,8 +59,9 @@ class Config(pd.BaseSettings):
     log_to_stderr: bool
     width: Optional[int] = pd.Field(None, ge=1)
 
-    # Outputs Settings
+    # Output Settings
     file_output: Optional[str] = pd.Field(None)
+    file_output_dynamic = bool = pd.Field(False)
     slack_output: Optional[str] = pd.Field(None)
 
     other_args: dict[str, Any]

robusta_krr/core/runner.py

@@ -6,7 +6,7 @@
 import warnings
 from concurrent.futures import ThreadPoolExecutor
 from typing import Optional, Union
-from datetime import timedelta
+from datetime import timedelta, datetime
 from prometrix import PrometheusNotFound
 from rich.console import Console
 from slack_sdk import WebClient
@@ -108,14 +108,23 @@ def _process_result(self, result: Result) -> None:
 
         custom_print(formatted, rich=rich, force=True)
 
-        if settings.file_output or settings.slack_output:
-            if settings.file_output:
+        if settings.file_output_dynamic or settings.file_output or settings.slack_output:
+            if settings.file_output_dynamic:
+                current_datetime = datetime.now().strftime("%Y%m%d%H%M%S")
+                file_name = f"krr-{current_datetime}.{settings.format}"
+                logger.info(f"Writing output to file: {file_name}")
+            elif settings.file_output:
                 file_name = settings.file_output
             elif settings.slack_output:
                 file_name = settings.slack_output
+
             with open(file_name, "w") as target_file:
-                console = Console(file=target_file, width=settings.width)
-                console.print(formatted)
+                # don't use rich when writing a csv to avoid line wrapping etc
+                if settings.format == "csv":
+                    target_file.write(formatted)
+                else:
+                    console = Console(file=target_file, width=settings.width)
+                    console.print(formatted)
             if settings.slack_output:
                 client = WebClient(os.environ["SLACK_BOT_TOKEN"])
                 warnings.filterwarnings("ignore", category=UserWarning)

robusta_krr/formatters/csv.py

@@ -1,8 +1,7 @@
 import itertools
 import csv
-
 import logging
-
+import io
 
 from robusta_krr.core.abstract import formatters
 from robusta_krr.core.models.allocations import RecommendationValue, format_recommendation_value, format_diff, NONE_LITERAL, NAN_LITERAL
@@ -12,7 +11,6 @@
 
 logger = logging.getLogger("krr")
 
-
 def _format_request_str(item: ResourceScan, resource: ResourceType, selector: str) -> str:
     allocated = getattr(item.object.allocations, selector)[resource]
     recommended = getattr(item.recommended, selector)[resource]
@@ -38,11 +36,9 @@ def _format_total_diff(item: ResourceScan, resource: ResourceType, pods_current:
 
     return format_diff(allocated, recommended, selector, pods_current)
 
-
-@formatters.register()
-def csv(result: Result) -> str:
+@formatters.register("csv")
+def csv_exporter(result: Result) -> str:
     current_datetime = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
-    file_path = f"krr-{current_datetime}.csv"
 
     # We need to order the resource columns so that they are in the format of Namespace,Name,Pods,Old Pods,Type,Container,CPU Diff,CPU Requests,CPU Limits,Memory Diff,Memory Requests,Memory Limits
     resource_columns = []
@@ -51,36 +47,34 @@ def csv(result: Result) -> str:
         resource_columns.append(f"{resource.name} Requests")
         resource_columns.append(f"{resource.name} Limits")
 
-    with open(file_path, 'w+', newline='') as csvfile:
-        csv_writer = csv.writer(csvfile)
-        csv_writer.writerow([
-            "Namespace", "Name", "Pods", "Old Pods", "Type", "Container",
-            *resource_columns
-
-        ])
-
-        for _, group in itertools.groupby(
-            enumerate(result.scans), key=lambda x: (x[1].object.cluster, x[1].object.namespace, x[1].object.name)
-        ):
-            group_items = list(group)
-
-            for j, (i, item) in enumerate(group_items):
-                full_info_row = j == 0
-
-                row = [
-                    item.object.namespace if full_info_row else "",
-                    item.object.name if full_info_row else "",
-                    f"{item.object.current_pods_count}" if full_info_row else "",
-                    f"{item.object.deleted_pods_count}" if full_info_row else "",
-                    item.object.kind if full_info_row else "",
-                    item.object.container,
-                ]
-
-                for resource in ResourceType:
-                    row.append(_format_total_diff(item, resource, item.object.current_pods_count))
-                    row += [_format_request_str(item, resource, selector) for selector in ["requests", "limits"]]
-
-                csv_writer.writerow(row)
+    output = io.StringIO()
+    csv_writer = csv.writer(output)
+    csv_writer.writerow([
+        "Namespace", "Name", "Pods", "Old Pods", "Type", "Container",
+        *resource_columns
+    ])
+
+    for _, group in itertools.groupby(
+        enumerate(result.scans), key=lambda x: (x[1].object.cluster, x[1].object.namespace, x[1].object.name)
+    ):
+        group_items = list(group)
+
+        for j, (i, item) in enumerate(group_items):
+            full_info_row = j == 0
+
+            row = [
+                item.object.namespace if full_info_row else "",
+                item.object.name if full_info_row else "",
+                f"{item.object.current_pods_count}" if full_info_row else "",
+                f"{item.object.deleted_pods_count}" if full_info_row else "",
+                item.object.kind if full_info_row else "",
+                item.object.container,
+            ]
+
+            for resource in ResourceType:
+                row.append(_format_total_diff(item, resource, item.object.current_pods_count))
+                row += [_format_request_str(item, resource, selector) for selector in ["requests", "limits"]]
+
+            csv_writer.writerow(row)
 
-    logger.info("CSV File: %s", file_path)
-    return ""
+    return output.getvalue()

robusta_krr/main.py

@@ -236,6 +236,9 @@ def run_strategy(
                 file_output: Optional[str] = typer.Option(
                     None, "--fileoutput", help="Filename to write output to (if not specified, file output is disabled)", rich_help_panel="Output Settings"
                 ),
+                file_output_dynamic: bool = typer.Option(
+                    False, "--fileoutput-dynamic", help="Ignore --fileoutput and write files to the current directory in the format krr-{datetime}.{format} (e.g. krr-20240518223924.csv)", rich_help_panel="Output Settings"
+                ),
                 slack_output: Optional[str] = typer.Option(
                     None,
                     "--slackoutput",
@@ -279,6 +282,7 @@ def run_strategy(
                         log_to_stderr=log_to_stderr,
                         width=width,
                         file_output=file_output,
+                        file_output_dynamic=file_output_dynamic,
                         slack_output=slack_output,
                         strategy=_strategy_name,
                         other_args=strategy_args,