Add parsers module

src/parsers/javascript.py

@@ -0,0 +1,219 @@
+from pathlib import Path
+import re
+
+from src.parsers.base import BaseParser, ParserResult, Entity, EntityType
+
+
+class JavaScriptParser(BaseParser):
+    SUPPORTED_EXTENSIONS = [".js", ".jsx", ".mjs", ".cjs"]
+
+    def __init__(self):
+        self._use_simple_parsing = True
+
+    def parse(self, file_path: Path, content: str) -> ParserResult:
+        result = ParserResult(file_path=file_path, language="javascript")
+        try:
+            result.entities = self.extract_entities(content, file_path)
+            result.imports = self.extract_imports(content)
+            return result
+        except Exception as e:
+            result.errors.append(f"Parse error: {str(e)}")
+            return result
+
+    def extract_entities(self, content: str, file_path: Path) -> list[Entity]:
+        entities = []
+        entities.extend(self._extract_functions(content, file_path))
+        entities.extend(self._extract_classes(content, file_path))
+        return entities
+
+    def _extract_functions(self, content: str, file_path: Path) -> list[Entity]:
+        functions = []
+        lines = content.split('\n')
+
+        for i, line in enumerate(lines):
+            line = line.strip()
+
+            match = re.match(r'function\s+([a-zA-Z_][a-zA-Z0-9_]*)\s*\(([^)]*)\)\s*\{?', line)
+            if match:
+                func_name = match.group(1)
+                params = match.group(2)
+
+                start_line = i + 1
+                end_line = self._find_braces_end(lines, i)
+
+                code_lines = lines[i:end_line]
+                code = '\n'.join(code_lines)
+
+                entity = Entity(
+                    name=func_name,
+                    entity_type=EntityType.FUNCTION,
+                    file_path=file_path,
+                    start_line=start_line,
+                    end_line=end_line,
+                    code=code,
+                    attributes={"parameters": [p.strip() for p in params.split(',') if p.strip()]},
+                    calls=self._extract_function_calls(code),
+                )
+                functions.append(entity)
+
+            arrow_match = re.match(r'(?:const|let|var)\s+([a-zA-Z_][a-zA-Z0-9_]*)\s*=\s*\(([^)]*)\)\s*=>', line)
+            if arrow_match:
+                func_name = arrow_match.group(1)
+                params = arrow_match.group(2)
+
+                start_line = i + 1
+                end_line = self._find_expression_end(lines, i)
+
+                code_lines = lines[i:end_line]
+                code = '\n'.join(code_lines)
+
+                entity = Entity(
+                    name=func_name,
+                    entity_type=EntityType.FUNCTION,
+                    file_path=file_path,
+                    start_line=start_line,
+                    end_line=end_line,
+                    code=code,
+                    attributes={"parameters": [p.strip() for p in params.split(',') if p.strip()]},
+                    calls=self._extract_function_calls(code),
+                )
+                functions.append(entity)
+
+        return functions
+
+    def _extract_classes(self, content: str, file_path: Path) -> list[Entity]:
+        classes = []
+        lines = content.split('\n')
+
+        for i, line in enumerate(lines):
+            line = line.strip()
+
+            match = re.match(r'class\s+([a-zA-Z_][a-zA-Z0-9_]*)\s*(\{|$)', line)
+            if match:
+                class_name = match.group(1)
+
+                start_line = i + 1
+                end_line = self._find_braces_end(lines, i)
+
+                code_lines = lines[i:end_line]
+                code = '\n'.join(code_lines)
+
+                class_content = '\n'.join(lines[i+1:end_line])
+                methods = self._extract_methods(class_content, file_path, start_line)
+
+                entity = Entity(
+                    name=class_name,
+                    entity_type=EntityType.CLASS,
+                    file_path=file_path,
+                    start_line=start_line,
+                    end_line=end_line,
+                    code=code,
+                    children=methods,
+                )
+                classes.append(entity)
+
+        return classes
+
+    def _extract_methods(self, content: str, file_path: Path, base_line: int) -> list[Entity]:
+        methods = []
+        lines = content.split('\n')
+        method_patterns = [
+            r'(\s*)async\s+([a-zA-Z_][a-zA-Z0-9_]*)\s*\(([^)]*)\)\s*\{?',
+            r'(\s*)([a-zA-Z_][a-zA-Z0-9_]*)\s*\(([^)]*)\)\s*\{?',
+        ]
+
+        for i, line in enumerate(lines):
+            for pattern in method_patterns:
+                match = re.match(pattern, line)
+                if match:
+                    if len(match.groups()) == 3:
+                        _, method_name, params = match.groups()
+                    else:
+                        method_name, params = match.group(2), match.group(3)
+
+                    if method_name in ['if', 'while', 'for', 'switch', 'try', 'catch']:
+                        continue
+
+                    start_line = base_line + i
+                    end_line = base_line + self._find_braces_end(lines, i)
+
+                    code_lines = lines[i:end_line]
+                    code = '\n'.join(code_lines)
+
+                    entity = Entity(
+                        name=method_name,
+                        entity_type=EntityType.METHOD,
+                        file_path=file_path,
+                        start_line=start_line,
+                        end_line=end_line,
+                        code=code,
+                        attributes={"parameters": [p.strip() for p in params.split(',') if p.strip()]},
+                        calls=self._extract_function_calls(code),
+                    )
+                    methods.append(entity)
+                    break
+
+        return methods
+
+    def _extract_function_calls(self, code: str) -> list[str]:
+        calls = []
+        patterns = [
+            r'\b([a-zA-Z_][a-zA-Z0-9_]*)\s*\([^)]*\)\s*;',
+            r'\b([a-zA-Z_][a-zA-Z0-9_]*)\s*\([^)]*\)\s*$',
+        ]
+        for pattern in patterns:
+            for match in re.finditer(pattern, code):
+                func_name = match.group(1)
+                if func_name not in ['if', 'while', 'for', 'return', 'throw', 'new', 'console']:
+                    calls.append(func_name)
+        return list(set(calls))
+
+    def _find_braces_end(self, lines: list[str], start_index: int) -> int:
+        brace_count = 0
+        in_string = False
+        string_char = None
+
+        for i, line in enumerate(lines[start_index:], start_index):
+            for j, char in enumerate(line):
+                if char in ['"', "'"] and (j == 0 or line[j-1] != '\\'):
+                    if not in_string:
+                        in_string = True
+                        string_char = char
+                    elif char == string_char:
+                        in_string = False
+                        string_char = None
+                elif not in_string and char == '{':
+                    brace_count += 1
+                elif not in_string and char == '}':
+                    brace_count -= 1
+                    if brace_count == 0:
+                        return i + 1
+
+        return len(lines)
+
+    def _find_expression_end(self, lines: list[str], start_index: int) -> int:
+        for i in range(start_index + 1, len(lines)):
+            line = lines[i].strip()
+            if line and not line.startswith('//') and not line.startswith('*'):
+                return i
+        return len(lines)
+
+    def extract_imports(self, content: str) -> list[str]:
+        imports = []
+        lines = content.split('\n')
+
+        for line in lines:
+            line = line.strip()
+
+            import_match = re.match(r"import\s+(?:\{[^}]*\}|\*)\s+from\s+['\"]([^'\"]+)['\"жа", line)
+            if import_match:
+                imports.append(import_match.group(1))
+
+            require_match = re.match(r"const\s+([a-zA-Z_][a-zA-Z0-9_]*)\s*=\s*require\(['\"]([^'\"]+)['\"]\)", line)
+            if require_match:
+                imports.append(require_match.group(2))
+
+        return imports
+
+    def extract_calls(self, content: str) -> list[str]:
+        return self._extract_function_calls(content)