fix: resolve CI mypy type checking issues

patternforge/src/patternforge/analyzer.py

@@ -0,0 +1,253 @@
+import re
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any
+
+import tree_sitter
+from tree_sitter_languages import get_language
+
+from patternforge.config import Config
+
+
+@dataclass
+class NamingPattern:
+    convention: str
+    prefixes: list[str] = field(default_factory=list)
+    suffixes: list[str] = field(default_factory=list)
+    examples: list[str] = field(default_factory=list)
+
+
+@dataclass
+class CodeStructure:
+    class_patterns: list[dict[str, Any]] = field(default_factory=list)
+    function_patterns: list[dict[str, Any]] = field(default_factory=list)
+    import_patterns: list[str] = field(default_factory=list)
+    type_definitions: list[dict[str, str]] = field(default_factory=list)
+
+
+@dataclass
+class StylePattern:
+    indent_style: str = "space"
+    indent_size: int = 4
+    line_endings: str = "lf"
+    bracket_style: str = "same-line"
+
+
+class CodeAnalyzer:
+    LANGUAGE_MAP = {
+        "python": "python",
+        "javascript": "javascript",
+        "typescript": "typescript",
+        "java": "java",
+        "cpp": "cpp",
+        "c": "c",
+        "rust": "rust",
+        "go": "go",
+        "ruby": "ruby",
+    }
+
+    def __init__(self, language: str, config: Config) -> None:
+        self.language = self.LANGUAGE_MAP.get(language, language)
+        self.config = config
+        self._parser: tree_sitter.Parser | None = None
+        self._language: Any = None
+        self._try_init_language()
+
+    def _try_init_language(self) -> None:
+        try:
+            self._parser = tree_sitter.Parser()
+            self._language = get_language(self.language)
+            self._parser.language = self._language
+        except Exception:
+            self._parser = None
+            self._language = None
+
+    def _file_extensions(self) -> set[str]:
+        extensions = {
+            "python": [".py", ".pyi"],
+            "javascript": [".js", ".mjs"],
+            "typescript": [".ts", ".tsx"],
+            "java": [".java"],
+            "cpp": [".cpp", ".cc", ".cxx", ".hpp"],
+            "c": [".c", ".h"],
+            "rust": [".rs"],
+            "go": [".go"],
+            "ruby": [".rb"],
+        }
+        return set(extensions.get(self.language, [f".{self.language}"]))
+
+    def _is_code_file(self, path: Path) -> bool:
+        return path.suffix in self._file_extensions()
+
+    def _collect_files(self, path: Path, recursive: bool) -> list[Path]:
+        files: list[Path] = []
+        if path.is_file():
+            if self._is_code_file(path):
+                files.append(path)
+            return files
+        pattern = "**/*" if recursive else "*"
+        for f in path.glob(pattern):
+            if f.is_file() and self._is_code_file(f):
+                files.append(f)
+        return files
+
+    def _extract_naming_conventions(self, content: str) -> dict[str, NamingPattern]:
+        conventions: dict[str, NamingPattern] = {}
+        patterns = {
+            "camelCase": r"[a-z][a-zA-Z0-9]*",
+            "PascalCase": r"[A-Z][a-zA-Z0-9]*",
+            "snake_case": r"[a-z][a-z0-9_]*",
+            "SCREAMING_SNAKE_CASE": r"[A-Z][A-Z0-9_]*",
+        }
+        for name, pattern in patterns.items():
+            matches = re.findall(pattern, content)
+            if matches:
+                conventions[name] = NamingPattern(
+                    convention=name,
+                    examples=list(set(matches))[:10],
+                )
+        return conventions
+
+    def _extract_structure(self, content: str) -> CodeStructure:
+        structure = CodeStructure()
+        class_pattern = r"class\s+(\w+)"
+        func_pattern = r"def\s+(\w+)|function\s+(\w+)|public\s+\w+\s+(\w+)"
+        import_pattern = r"^import\s+.*|^from\s+.*|^#include\s+.*"
+
+        for match in re.finditer(class_pattern, content):
+            structure.class_patterns.append({"name": match.group(1)})
+
+        for match in re.finditer(func_pattern, content):
+            name = match.group(1) or match.group(2) or match.group(3)
+            if name:
+                structure.function_patterns.append({"name": name})
+
+        structure.import_patterns = re.findall(import_pattern, content, re.MULTILINE)[:20]
+
+        return structure
+
+    def _detect_style(self, content: str) -> StylePattern:
+        style = StylePattern()
+        if "\t" in content[:1000]:
+            style.indent_style = "tab"
+            style.indent_size = 1
+        elif " " * 4 in content[:1000]:
+            style.indent_size = 4
+        elif " " * 2 in content[:1000]:
+            style.indent_size = 2
+
+        if "\r\n" in content[:1000]:
+            style.line_endings = "crlf"
+        else:
+            style.line_endings = "lf"
+
+        return style
+
+    def _analyze_file(self, path: Path) -> dict[str, Any]:
+        try:
+            with open(path, encoding="utf-8", errors="ignore") as f:
+                content = f.read()
+        except Exception:
+            return {}
+
+        return {
+            "path": str(path),
+            "naming_conventions": self._extract_naming_conventions(content),
+            "structure": {
+                "classes": self._extract_structure(content).class_patterns,
+                "functions": self._extract_structure(content).function_patterns,
+                "imports": self._extract_structure(content).import_patterns,
+            },
+            "style": self._detect_style(content).__dict__,
+            "size": len(content),
+            "lines": content.count("\n"),
+        }
+
+    def analyze(self, path: str, recursive: bool = True) -> dict[str, Any]:
+        target = Path(path)
+        files = self._collect_files(target, recursive)
+        if not files:
+            return {"error": "No matching files found", "language": self.language}
+
+        file_analyses = []
+        all_naming: dict[str, set[str]] = {}
+        all_classes: list[str] = []
+        all_functions: list[str] = []
+        all_imports: list[str] = []
+        style_votes = {"space": 0, "tab": 0}
+        indent_sizes: dict[int, int] = {}
+
+        for f in files:
+            analysis = self._analyze_file(f)
+            if not analysis:
+                continue
+            file_analyses.append(analysis)
+            for nc in analysis.get("naming_conventions", {}).values():
+                for ex in nc.examples:
+                    if nc.convention not in all_naming:
+                        all_naming[nc.convention] = set()
+                    all_naming[nc.convention].add(ex)
+
+            for cls in analysis.get("structure", {}).get("classes", []):
+                all_classes.append(cls.get("name", ""))
+
+            for func in analysis.get("structure", {}).get("functions", []):
+                all_functions.append(func.get("name", ""))
+
+            all_imports.extend(analysis.get("structure", {}).get("imports", []))
+
+            style = analysis.get("style", {})
+            if style.get("indent_style"):
+                style_votes[style["indent_style"]] += 1
+            indent = style.get("indent_size", 0)
+            if indent > 0:
+                indent_sizes[indent] = indent_sizes.get(indent, 0) + 1
+
+        dominant_style = "space" if style_votes["space"] >= style_votes["tab"] else "tab"
+        dominant_indent = max(indent_sizes.items(), key=lambda x: x[1], default=(4, 0))[0]
+
+        return {
+            "language": self.language,
+            "files_analyzed": len(file_analyses),
+            "file_details": file_analyses[:5],
+            "naming_conventions": {
+                k: list(v)[:20] for k, v in all_naming.items()
+            },
+            "entity_counts": {
+                "classes": len(all_classes),
+                "functions": len(all_functions),
+                "imports": len(all_imports),
+            },
+            "style": {
+                "indent_style": dominant_style,
+                "indent_size": dominant_indent,
+            },
+            "summary": {
+                "files": len(file_analyses),
+                "classes": len(all_classes),
+                "functions": len(all_functions),
+                "primary_naming": list(all_naming.keys())[0] if all_naming else "unknown",
+            },
+        }
+
+    def save_patterns(self, output_path: str, patterns: dict[str, Any]) -> None:
+        import yaml
+
+        def convert_dataclass(obj: Any) -> Any:
+            if hasattr(obj, "__dict__"):
+                return {
+                    k: convert_dataclass(v)
+                    for k, v in obj.__dict__.items()
+                    if not k.startswith("_")
+                }
+            elif isinstance(obj, dict):
+                return {k: convert_dataclass(v) for k, v in obj.items()}
+            elif isinstance(obj, list):
+                return [convert_dataclass(i) for i in obj]
+            return obj
+
+        path = Path(output_path)
+        path.parent.mkdir(parents=True, exist_ok=True)
+        clean_patterns = convert_dataclass(patterns)
+        with open(path, "w") as f:
+            yaml.dump(clean_patterns, f, default_flow_style=False, indent=2)