fix: resolve all ruff lint errors (#4)

Co-authored-by: liuxiaotong <liuxiaotong@knowlyr.com>

Author: cerwai

src/datarecipe/cli/tools.py

@@ -1244,7 +1244,7 @@ def pii(dataset_id: str, sample_size: int, pii_types: tuple, as_json: bool, outp
     risk_colors = {"high": "red", "medium": "yellow", "low": "green", "none": "green"}
     color = risk_colors.get(report.risk_level, "white")
 
-    console.print(f"\n[bold]PII Detection Report[/bold]")
+    console.print("\n[bold]PII Detection Report[/bold]")
     console.print(f"  Samples scanned: {report.total_samples}")
     console.print(f"  Samples with PII: {report.samples_with_pii}")
     console.print(f"  PII ratio: {report.pii_ratio * 100:.1f}%")
@@ -1270,7 +1270,7 @@ def pii(dataset_id: str, sample_size: int, pii_types: tuple, as_json: bool, outp
         console.print(table)
 
     if report.recommendations:
-        console.print(f"\n[bold cyan]Recommendations:[/bold cyan]")
+        console.print("\n[bold cyan]Recommendations:[/bold cyan]")
         for rec in report.recommendations:
             console.print(f"  - {rec}")
 
@@ -1328,12 +1328,12 @@ def ira(
 
     with console.status(f"[cyan]Analyzing agreement in {dataset_id}...[/cyan]"):
         try:
-            kwargs = dict(
-                item_field=item_field,
-                annotator_field=annotator_field,
-                label_field=label_field,
-                data_format=data_format,
-            )
+            kwargs = {
+                "item_field": item_field,
+                "annotator_field": annotator_field,
+                "label_field": label_field,
+                "data_format": data_format,
+            }
             if is_local:
                 report = analyzer.analyze_from_file(
                     str(local_path.resolve()), sample_size=sample_size, **kwargs,
@@ -1372,7 +1372,7 @@ def ira(
     }
     color = quality_colors.get(report.quality_level, "white")
 
-    console.print(f"\n[bold]Inter-Rater Agreement Report[/bold]")
+    console.print("\n[bold]Inter-Rater Agreement Report[/bold]")
     console.print(f"  Items analyzed: {report.total_items}")
     console.print(f"  Total annotations: {report.total_annotations}")
     console.print(f"  Annotators: {report.n_annotators}")
@@ -1414,7 +1414,7 @@ def ira(
         console.print(table)
 
     if report.recommendations:
-        console.print(f"\n[bold cyan]Recommendations:[/bold cyan]")
+        console.print("\n[bold cyan]Recommendations:[/bold cyan]")
         for rec in report.recommendations:
             console.print(f"  - {rec}")
 

src/datarecipe/comparator.py

@@ -8,7 +8,6 @@
 from datarecipe.quality_metrics import QualityAnalyzer, QualityReport
 from datarecipe.schema import GenerationType, Recipe, SourceType
 
-
 # ==================== Similarity dataclasses ====================
 
 
@@ -599,7 +598,7 @@ def _quality_similarity(self, a: DatasetMetrics, b: DatasetMetrics) -> float:
             b.quality.complexity.vocabulary_richness,
             b.quality.overall_score / 100.0,
         ]
-        dist = math.sqrt(sum((x - y) ** 2 for x, y in zip(dims_a, dims_b)))
+        dist = math.sqrt(sum((x - y) ** 2 for x, y in zip(dims_a, dims_b, strict=False)))
         max_dist = math.sqrt(len(dims_a))
         return max(0.0, 1.0 - dist / max_dist)
 

src/datarecipe/ira_analyzer.py

@@ -4,7 +4,6 @@
 from dataclasses import dataclass, field
 from itertools import combinations
 
-
 # ==================== Dataclasses ====================
 
 
@@ -389,7 +388,7 @@ def _cohen_kappa(self, labels_a: list[str], labels_b: list[str]) -> float:
         all_labels = sorted(set(labels_a) | set(labels_b))
 
         # Observed agreement
-        po = sum(1 for a, b in zip(labels_a, labels_b) if a == b) / n
+        po = sum(1 for a, b in zip(labels_a, labels_b, strict=False) if a == b) / n
 
         # Expected agreement
         pe = 0.0
@@ -538,7 +537,7 @@ def _compute_pairwise(
 
             kappa = self._cohen_kappa(labels_a, labels_b)
             n = len(common_items)
-            agree = sum(1 for a, b in zip(labels_a, labels_b) if a == b)
+            agree = sum(1 for a, b in zip(labels_a, labels_b, strict=False) if a == b)
             pct = agree / n if n > 0 else 0.0
 
             cm = self._build_confusion_matrix(labels_a, labels_b)
@@ -558,7 +557,7 @@ def _build_confusion_matrix(
     ) -> dict[tuple[str, str], int]:
         """Build confusion matrix as {(label_a, label_b): count}."""
         cm: dict[tuple[str, str], int] = {}
-        for a, b in zip(labels_a, labels_b):
+        for a, b in zip(labels_a, labels_b, strict=False):
             key = (a, b)
             cm[key] = cm.get(key, 0) + 1
         return cm

src/datarecipe/mcp_server.py

@@ -973,7 +973,7 @@ async def _recipe_diff(arguments: dict[str, Any]) -> list[TextContent]:
     if "all" in sections:
         sections = ["schema", "stats", "rubrics", "cost"]
 
-    lines = [f"## 分析对比", "", f"- A: `{os.path.basename(dir_a)}`", f"- B: `{os.path.basename(dir_b)}`", ""]
+    lines = ["## 分析对比", "", f"- A: `{os.path.basename(dir_a)}`", f"- B: `{os.path.basename(dir_b)}`", ""]
 
     def _load_json(base_dir: str, *paths: str) -> dict | None:
         for p in paths:

src/datarecipe/pii_detector.py

@@ -3,7 +3,6 @@
 import re
 from dataclasses import dataclass, field
 
-
 # ==================== Dataclasses ====================
 
 

src/datarecipe/sources/local.py

@@ -1,6 +1,5 @@
 """Extract recipe information from local data files (CSV, Parquet, JSONL)."""
 
-import os
 from pathlib import Path
 
 from datarecipe.schema import (

tests/test_ira_analyzer.py

@@ -5,7 +5,6 @@
 import os
 import tempfile
 import unittest
-from pathlib import Path
 
 from click.testing import CliRunner
 
@@ -18,7 +17,6 @@
     PairwiseAgreement,
 )
 
-
 # ==================== Test data factories ====================
 
 

tests/test_local_source.py

@@ -6,7 +6,6 @@
 import tempfile
 import unittest
 from pathlib import Path
-from unittest.mock import MagicMock, patch
 
 from click.testing import CliRunner
 

tests/test_pii_detector.py

@@ -5,8 +5,6 @@
 import os
 import tempfile
 import unittest
-from pathlib import Path
-from unittest.mock import patch
 
 from click.testing import CliRunner
 
@@ -19,7 +17,6 @@
     _luhn_check,
 )
 
-
 # ==================== Test data factories ====================