bioguider 0.2.21__py3-none-any.whl → 0.2.23__py3-none-any.whl

bioguider/utils/r_file_handler.py

@@ -1,368 +1,549 @@
-import re
 import os
-from typing import List, Tuple, Optional
+import re
+from dataclasses import dataclass
+from typing import List, Optional, Tuple
+
+@dataclass
+class RSymbol:
+    name: str
+    parent: Optional[str]
+    start_line: int
+    end_line: int
+    docstring: Optional[str]
+    params: List[str]
+
 
 class RFileHandler:
+    # only up to "function("
+    FUNC_DEF_HEAD_RE = re.compile(
+        r'(?P<name>[A-Za-z.][\w.]*)\s*<-\s*function\s*\(',
+        re.MULTILINE,
+    )
+    
+    S3_METHOD_HEAD_RE = re.compile(
+        r'(?P<generic>[A-Za-z.][\w.]*)\.(?P<class>[A-Za-z.][\w.]*)\s*<-\s*function\s*\(',
+        re.MULTILINE,
+    )
+    
+    # R6 method head: "name = function("
+    R6_METHOD_HEAD_RE = re.compile(
+        r'(?P<mname>[A-Za-z.][\w.]*)\s*=\s*function\s*\(',
+        re.MULTILINE,
+    )
+    
+    # S4 method head inside setMethod(... function(
+    S4_METHOD_HEAD_RE = re.compile(
+        r'setMethod\s*\(\s*["\'](?P<generic>[^"\']+)["\']\s*,.*?function\s*\(',
+        re.MULTILINE | re.DOTALL,
+    )
+
+    FUNC_DEF_RE = re.compile(
+        # name <- function( ... ) {   with multi-line args allowed
+        r'(?P<name>[A-Za-z.][\w.]*)\s*<-\s*function\s*\((?P<args>[^)]*)\)\s*\{',
+        re.MULTILINE,
+    )
+    S3_METHOD_RE = re.compile(
+        r'(?P<generic>[A-Za-z.][\w.]*)\.(?P<class>[A-Za-z.][\w.]*)\s*<-\s*function\s*\((?P<args>[^)]*)\)\s*\{',
+        re.MULTILINE,
+    )
+    R6_CLASS_RE = re.compile(
+        r'(?P<varname>[A-Za-z.][\w.]*)\s*<-\s*R6Class\s*\(\s*["\'](?P<classname>[^"\']+)["\']',
+        re.MULTILINE | re.DOTALL,
+    )
+    R6_METHOD_RE = re.compile(
+        r'(?P<mname>[A-Za-z.][\w.]*)\s*=\s*function\s*\((?P<args>[^)]*)\)\s*\{',
+        re.MULTILINE,
+    )
+    S4_CLASS_RE = re.compile(
+        r'setClass\s*\(\s*["\'](?P<classname>[^"\']+)["\']',
+        re.MULTILINE,
+    )
+    S4_METHOD_RE = re.compile(
+        r'setMethod\s*\(\s*["\'](?P<generic>[^"\']+)["\']\s*,.*?function\s*\((?P<args>[^)]*)\)\s*\{',
+        re.MULTILINE | re.DOTALL,
+    )
+    S4_SIG_CLASS_RE = re.compile(
+        r'signature\s*=\s*(?:list\s*\(|\()\s*(?:[^)]*class\s*=\s*["\'](?P<classname>[^"\']+)["\']|["\'](?P<classname2>[^"\']+)["\'])',
+        re.MULTILINE,
+    )
+    LIB_REQUIRE_RE = re.compile(
+        r'\b(?:library|require)\s*\(\s*([A-Za-z.][\w.]*)\s*\)',
+        re.MULTILINE,
+    )
+    NS_USE_RE = re.compile(
+        r'(?P<pkg>[A-Za-z.][\w.]*):::{0,2}(?P<sym>[A-Za-z.][\w.]*)',
+        re.MULTILINE,
+    )
+
     def __init__(self, file_path: str):
         self.file_path = file_path
+        with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
+            self.text = f.read()
+        self.lines = self.text.splitlines()
+        self._brace_map = self._build_brace_map_safely()  # FIX: ignore comments/strings
+
+    # ---------------- Public API ----------------
 
     def get_functions_and_classes(self) -> List[Tuple[str, Optional[str], int, int, Optional[str], List[str]]]:
-        """
-        Get the functions and S4 classes in a given R file.
-        Returns a list of tuples, each containing:
-        1. the function or class name,
-        2. parent name (None for R, as R doesn't have nested functions in the same way),
-        3. start line number,
-        4. end line number,
-        5. doc string (roxygen comments),
-        6. params (function parameters).
-        """
-        with open(self.file_path, 'r', encoding='utf-8') as f:
-            lines = f.readlines()
-        
-        functions_and_classes = []
-        i = 0
-        
-        while i < len(lines):
-            line = lines[i].strip()
-            
-            # Skip empty lines and comments (except roxygen)
-            if not line or (line.startswith('#') and not line.startswith('#\'') and not line.startswith('#@')):
-                i += 1
-                continue
-            
-            # Check for function definitions
-            func_match = self._match_function(lines, i)
-            if func_match:
-                name, start_line, end_line, doc_string, params = func_match
-                functions_and_classes.append((name, None, start_line + 1, end_line + 1, doc_string, params))
-                i = end_line + 1
-                continue
-            
-            # Check for S4 class definitions
-            class_match = self._match_s4_class(lines, i)
-            if class_match:
-                name, start_line, end_line, doc_string = class_match
-                functions_and_classes.append((name, None, start_line + 1, end_line + 1, doc_string, []))
-                i = end_line + 1
-                continue
-            
-            # Check for S3 class methods (functions with class-specific naming)
-            s3_match = self._match_s3_method(lines, i)
-            if s3_match:
-                name, start_line, end_line, doc_string, params = s3_match
-                functions_and_classes.append((name, None, start_line + 1, end_line + 1, doc_string, params))
-                i = end_line + 1
-                continue
-            
-            i += 1
-        
-        return functions_and_classes
+        items: List[RSymbol] = []
+        items.extend(self._parse_functions())
+        items.extend(self._parse_s3_methods())
+        items.extend(self._parse_r6())
+        items.extend(self._parse_s4())
+        items.sort(key=lambda s: (s.start_line, s.end_line))
+        return [(i.name, i.parent, i.start_line, i.end_line, i.docstring, i.params) for i in items]
+
+    def get_imports(self) -> List[str]:
+        pkgs = set(self.LIB_REQUIRE_RE.findall(self.text))
+        for m in self.NS_USE_RE.finditer(self.text):
+            pkgs.add(m.group('pkg'))
+        return sorted(pkgs)
+
+    # ---------------- Parsers ----------------
+
+    def _parse_functions(self) -> List[RSymbol]:
+        syms: List[RSymbol] = []
+        for m in self.FUNC_DEF_HEAD_RE.finditer(self.text):
+            name = m.group('name')
+            open_paren = m.end() - 1  # points at '('
+            close_paren = self._matching_paren_pos_global(open_paren)
+            if close_paren is None:
+                continue
+            args_text = self.text[open_paren + 1: close_paren]
+            args = self._parse_params(args_text)
     
-    def _match_function(self, lines: List[str], start_idx: int) -> Optional[Tuple[str, int, int, Optional[str], List[str]]]:
-        """Match function definitions in R code."""
-        # Collect roxygen documentation before function
-        doc_string = self._extract_roxygen_doc(lines, start_idx)
-        doc_start_idx = start_idx
-        
-        # Skip roxygen comments to find function definition
-        while start_idx < len(lines) and (lines[start_idx].strip().startswith('#\'') or 
-                                         lines[start_idx].strip().startswith('#@') or 
-                                         not lines[start_idx].strip()):
-            start_idx += 1
-        
-        if start_idx >= len(lines):
-            return None
-        
-        # Pattern for function definition: name <- function(params) or name = function(params)
-        func_pattern = r'^(\s*)([a-zA-Z_][a-zA-Z0-9_.\$]*)\s*(<-|=)\s*function\s*\('
-        
-        line = lines[start_idx]
-        match = re.match(func_pattern, line)
-        
-        if not match:
-            return None
-        
-        func_name = match.group(2)
-        indent_level = len(match.group(1))
-        
-        # Extract parameters
-        params = self._extract_function_params(lines, start_idx)
-        
-        # Find the end of the function by tracking braces
-        end_idx = self._find_function_end(lines, start_idx, indent_level)
-        
-        return func_name, doc_start_idx, end_idx, doc_string, params
+            block_open = self._find_next_code_brace_after(close_paren + 1)
+            if block_open is None:
+                continue
+            block_close = self._matching_brace_pos(block_open)
     
-    def _match_s4_class(self, lines: List[str], start_idx: int) -> Optional[Tuple[str, int, int, Optional[str]]]:
-        """Match S4 class definitions."""
-        doc_string = self._extract_roxygen_doc(lines, start_idx)
-        doc_start_idx = start_idx
-        
-        # Skip documentation to find class definition
-        while start_idx < len(lines) and (lines[start_idx].strip().startswith('#\'') or 
-                                         lines[start_idx].strip().startswith('#@') or 
-                                         not lines[start_idx].strip()):
-            start_idx += 1
-        
-        if start_idx >= len(lines):
-            return None
-        
-        # Pattern for S4 class: setClass("ClassName", ...)
-        class_pattern = r'setClass\s*\(\s*["\']([^"\']+)["\']'
-        
-        line = lines[start_idx]
-        match = re.search(class_pattern, line)
-        
-        if not match:
-            return None
-        
-        class_name = match.group(1)
-        
-        # Find the end by tracking parentheses
-        end_idx = self._find_parentheses_end(lines, start_idx)
-        
-        return class_name, doc_start_idx, end_idx, doc_string
+            start_line = self._pos_to_line(block_open)
+            end_line = self._pos_to_line(block_close)
+            doc = self._roxygen_before(m.start())
     
-    def _match_s3_method(self, lines: List[str], start_idx: int) -> Optional[Tuple[str, int, int, Optional[str], List[str]]]:
-        """Match S3 method definitions (method.class pattern)."""
-        doc_string = self._extract_roxygen_doc(lines, start_idx)
-        doc_start_idx = start_idx
-        
-        # Skip documentation
-        while start_idx < len(lines) and (lines[start_idx].strip().startswith('#\'') or 
-                                         lines[start_idx].strip().startswith('#@') or 
-                                         not lines[start_idx].strip()):
-            start_idx += 1
-        
-        if start_idx >= len(lines):
-            return None
-        
-        # Pattern for S3 method: method.class <- function(params)
-        s3_pattern = r'^(\s*)([a-zA-Z_][a-zA-Z0-9_]*\.[a-zA-Z_][a-zA-Z0-9_]*)\s*(<-|=)\s*function\s*\('
-        
-        line = lines[start_idx]
-        match = re.match(s3_pattern, line)
-        
-        if not match:
-            return None
-        
-        method_name = match.group(2)
-        indent_level = len(match.group(1))
-        
-        # Extract parameters
-        params = self._extract_function_params(lines, start_idx)
-        
-        # Find the end of the function
-        end_idx = self._find_function_end(lines, start_idx, indent_level)
-        
-        return method_name, doc_start_idx, end_idx, doc_string, params
+            syms.append(RSymbol(name=name, parent=None,
+                                start_line=start_line, end_line=end_line,
+                                docstring=doc, params=args))
     
-    def _extract_roxygen_doc(self, lines: List[str], start_idx: int) -> Optional[str]:
-        """Extract roxygen2 documentation comments."""
-        doc_lines = []
-        i = start_idx
-        
-        # Go backwards to find the start of roxygen comments
-        while i > 0 and (lines[i-1].strip().startswith('#\'') or lines[i-1].strip().startswith('#@') or not lines[i-1].strip()):
-            if lines[i-1].strip().startswith('#\'') or lines[i-1].strip().startswith('#@'):
-                i -= 1
-            elif not lines[i-1].strip():
-                i -= 1
-            else:
-                break
-        
-        # Collect roxygen comments
-        while i < len(lines):
-            line = lines[i].strip()
-            if line.startswith('#\'') or line.startswith('#@'):
-                # Remove the roxygen prefix
-                clean_line = re.sub(r'^#[\'@]\s?', '', line)
-                doc_lines.append(clean_line)
-                i += 1
-            elif not line:  # Empty line
-                i += 1
-            else:
-                break
-        
-        return '\n'.join(doc_lines) if doc_lines else None
+            # nested
+            syms.extend(self._parse_nested_functions(block_open, block_close, parent=name))
+        return syms
+
+    def _parse_nested_functions(self, abs_start: int, abs_end: int, parent: str) -> List[RSymbol]:
+        sub = self.text[abs_start:abs_end+1]
+        syms: List[RSymbol] = []
+        for m in self.FUNC_DEF_HEAD_RE.finditer(sub):
+            open_rel = m.end() - 1
+            close_rel = self._matching_paren_pos_in_text(sub, open_rel)
+            if close_rel is None:
+                continue
+            args_text = sub[open_rel + 1: close_rel]
+            args = self._parse_params(args_text)
     
-    def _extract_function_params(self, lines: List[str], start_idx: int) -> List[str]:
-        """Extract function parameters from function definition."""
-        params = []
-        
-        # Find the function line and extract parameters
-        func_line_complete = ""
-        i = start_idx
-        paren_count = 0
-        found_opening = False
-        
-        while i < len(lines):
-            line = lines[i]
-            func_line_complete += line
-            
-            # Count parentheses to find the complete parameter list
-            for char in line:
-                if char == '(':
-                    paren_count += 1
-                    found_opening = True
-                elif char == ')':
-                    paren_count -= 1
-            
-            if found_opening and paren_count == 0:
-                break
-            i += 1
-        
-        # Extract parameters using regex
-        param_match = re.search(r'function\s*\((.*?)\)', func_line_complete, re.DOTALL)
-        if param_match:
-            param_str = param_match.group(1).strip()
-            if param_str:
-                # Split by comma, but be careful with nested parentheses and quotes
-                params = self._smart_split_params(param_str)
-                # Clean up parameter names (remove default values, whitespace)
-                params = [re.split(r'\s*=\s*', param.strip())[0].strip() for param in params]
-                params = [param for param in params if param and param != '...']
-        
-        return params
+            # brace after ')' within the slice
+            func_open_rel = self._find_next_char_in_text(sub, '{', close_rel + 1)
+            if func_open_rel is None:
+                continue
+            func_close_rel = self._matching_brace_pos_in_text(sub, func_open_rel)
+            if func_close_rel is None:
+                continue
     
-    def _smart_split_params(self, param_str: str) -> List[str]:
-        """Split parameters by comma, handling nested structures."""
-        params = []
-        current_param = ""
-        paren_count = 0
-        quote_char = None
-        
-        for char in param_str:
-            if quote_char:
-                current_param += char
-                if char == quote_char and (len(current_param) == 1 or current_param[-2] != '\\'):
-                    quote_char = None
-            elif char in ['"', "'"]:
-                quote_char = char
-                current_param += char
-            elif char == '(':
-                paren_count += 1
-                current_param += char
-            elif char == ')':
-                paren_count -= 1
-                current_param += char
-            elif char == ',' and paren_count == 0:
-                params.append(current_param.strip())
-                current_param = ""
-            else:
-                current_param += char
-        
-        if current_param.strip():
-            params.append(current_param.strip())
-        
-        return params
+            block_open = abs_start + func_open_rel
+            block_close = abs_start + func_close_rel
+            name = m.group('name')
+            doc = self._roxygen_before(block_open)
+            syms.append(RSymbol(
+                name=name, parent=parent,
+                start_line=self._pos_to_line(block_open),
+                end_line=self._pos_to_line(block_close),
+                docstring=doc, params=args
+            ))
+        return syms
+
+
+    def _parse_s3_methods(self) -> List[RSymbol]:
+        syms: List[RSymbol] = []
+        for m in self.S3_METHOD_HEAD_RE.finditer(self.text):
+            generic = m.group('generic')
+            clazz = m.group('class')
+            name = f"{generic}.{clazz}"
     
-    def _find_function_end(self, lines: List[str], start_idx: int, indent_level: int) -> int:
-        """Find the end of a function by tracking braces and indentation."""
-        brace_count = 0
-        in_function = False
-        i = start_idx
-        
-        while i < len(lines):
-            line = lines[i]
-            
-            # Count braces
-            for char in line:
-                if char == '{':
-                    brace_count += 1
-                    in_function = True
-                elif char == '}':
-                    brace_count -= 1
-            
-            # If we've closed all braces, we're at the end
-            if in_function and brace_count == 0:
-                return i
-            
-            # If no braces are used, look for next function or end of file
-            if not in_function and i > start_idx:
-                stripped = line.strip()
-                if stripped and not stripped.startswith('#'):
-                    # Check if this looks like a new function or assignment at same/higher level
-                    if re.match(r'^(\s*)[a-zA-Z_][a-zA-Z0-9_.\$]*\s*(<-|=)', line):
-                        current_indent = len(re.match(r'^(\s*)', line).group(1))
-                        if current_indent <= indent_level:
-                            return i - 1
-            
-            i += 1
-        
-        return len(lines) - 1
+            open_paren = m.end() - 1
+            close_paren = self._matching_paren_pos_global(open_paren)
+            if close_paren is None:
+                continue
+            args_text = self.text[open_paren + 1: close_paren]
+            args = self._parse_params(args_text)
     
-    def _find_parentheses_end(self, lines: List[str], start_idx: int) -> int:
-        """Find the end of a parenthetical expression."""
-        paren_count = 0
-        i = start_idx
-        
-        while i < len(lines):
-            line = lines[i]
-            for char in line:
-                if char == '(':
-                    paren_count += 1
-                elif char == ')':
-                    paren_count -= 1
-                    if paren_count == 0:
-                        return i
-            i += 1
-        
-        return len(lines) - 1
+            block_open = self._find_next_code_brace_after(close_paren + 1)
+            if block_open is None:
+                continue
+            block_close = self._matching_brace_pos(block_open)
     
-    def get_imports(self) -> List[str]:
+            syms.append(RSymbol(
+                name=name, parent=generic,
+                start_line=self._pos_to_line(block_open),
+                end_line=self._pos_to_line(block_close),
+                docstring=self._roxygen_before(m.start()),
+                params=args
+            ))
+        return syms
+
+
+    def _parse_r6(self) -> List[RSymbol]:
+        syms: List[RSymbol] = []
+        for m in self.R6_CLASS_RE.finditer(self.text):
+            classname = m.group('classname')
+            # Find the first '{' after R6Class( — it's the class call's body brace
+            first_brace = self._find_next_code_brace_after(m.end())
+            if first_brace is None:
+                continue
+            class_end = self._matching_brace_pos(first_brace)
+            syms.append(RSymbol(
+                name=classname, parent=None,
+                start_line=self._pos_to_line(first_brace),
+                end_line=self._pos_to_line(class_end),
+                docstring=self._roxygen_before(m.start()),
+                params=[]
+            ))
+            # Methods within public/private/active lists
+            class_text = self.text[m.start():class_end+1]
+            base = m.start()
+            for sect in ('public', 'private', 'active'):
+                for meth in self._parse_r6_section_methods(class_text, base, sect, classname):
+                    syms.append(meth)
+        return syms
+
+    def _parse_r6_section_methods(self, class_text: str, base: int, section: str, parent_class: str) -> List[RSymbol]:
+        syms: List[RSymbol] = []
+        for sec in re.finditer(rf'{section}\s*=\s*list\s*\(', class_text):
+            lst_open = sec.end() - 1
+            lst_close = self._matching_paren_pos_in_text(class_text, lst_open)
+            if lst_close is None:
+                continue
+            list_text = class_text[lst_open:lst_close+1]
+            for m in self.R6_METHOD_HEAD_RE.finditer(list_text):
+                open_rel = m.end() - 1
+                close_rel = self._matching_paren_pos_in_text(list_text, open_rel)
+                if close_rel is None:
+                    continue
+                args_text = list_text[open_rel + 1: close_rel]
+                args = self._parse_params(args_text)
+    
+                func_open_rel = self._find_next_char_in_text(list_text, '{', close_rel + 1)
+                if func_open_rel is None:
+                    continue
+                func_close_rel = self._matching_brace_pos_in_text(list_text, func_open_rel)
+                if func_close_rel is None:
+                    continue
+    
+                block_open = base + lst_open + func_open_rel
+                block_close = base + lst_open + func_close_rel
+    
+                syms.append(RSymbol(
+                    name=f"{parent_class}${m.group('mname')}",
+                    parent=parent_class,
+                    start_line=self._pos_to_line(block_open),
+                    end_line=self._pos_to_line(block_close),
+                    docstring=self._roxygen_before(block_open),
+                    params=args
+                ))
+        return syms
+
+
+    def _parse_s4(self) -> List[RSymbol]:
+        syms: List[RSymbol] = []
+        for m in self.S4_CLASS_RE.finditer(self.text):
+            syms.append(RSymbol(
+                name=m.group('classname'), parent=None,
+                start_line=self._pos_to_line(m.start()),
+                end_line=self._pos_to_line(m.start()),
+                docstring=self._roxygen_before(m.start()),
+                params=[]
+            ))
+        for m in self.S4_METHOD_HEAD_RE.finditer(self.text):
+            generic = m.group('generic')
+        
+            open_paren = m.end() - 1
+            close_paren = self._matching_paren_pos_global(open_paren)
+            if close_paren is None:
+                continue
+            args_text = self.text[open_paren + 1: close_paren]
+            args = self._parse_params(args_text)
+        
+            block_open = self._find_next_code_brace_after(close_paren + 1)
+            block_close = self._matching_brace_pos(block_open) if block_open is not None else m.end()
+        
+            sig_slice = self.text[m.start(): block_open or m.end()]
+            cm = self.S4_SIG_CLASS_RE.search(sig_slice)
+            clazz = cm.group('classname') if cm and cm.group('classname') else (cm.group('classname2') if cm else None)
+            name = f"{generic}{'<' + clazz + '>' if clazz else ''}"
+        
+            syms.append(RSymbol(
+                name=name, parent=generic,
+                start_line=self._pos_to_line(block_open if block_open is not None else m.start()),
+                end_line=self._pos_to_line(block_close),
+                docstring=self._roxygen_before(m.start()),
+                params=args
+            ))
+
+        return syms
+
+    # ---------------- Utilities ----------------
+
+    def _parse_params(self, arg_str: str) -> List[str]:
+        params = []
+        depth = 0
+        token = []
+        in_s: Optional[str] = None
+        escape = False
+        for ch in arg_str:
+            if in_s:
+                token.append(ch)
+                if escape:
+                    escape = False
+                elif ch == '\\':
+                    escape = True
+                elif ch == in_s:
+                    in_s = None
+                continue
+            if ch in ('"', "'"):
+                in_s = ch
+                token.append(ch)
+                continue
+            if ch in '([{':
+                depth += 1
+                token.append(ch)
+            elif ch in ')]}':
+                depth -= 1
+                token.append(ch)
+            elif ch == ',' and depth == 0:
+                params.append(''.join(token).strip())
+                token = []
+            else:
+                token.append(ch)
+        if token:
+            params.append(''.join(token).strip())
+
+        cleaned = []
+        for p in params:
+            p = p.strip()
+            if not p:
+                continue
+            if p == '...':
+                cleaned.append('...')
+                continue
+            name = p.split('=')[0].strip()
+            if name:
+                cleaned.append(name)
+        return cleaned
+
+    def _roxygen_before(self, pos: int) -> Optional[str]:
+        line_idx = self._pos_to_line(pos) - 2
+        if line_idx < 0:
+            return None
+        buf = []
+        while line_idx >= 0:
+            line = self.lines[line_idx]
+            s = line.lstrip()
+            if s.startswith("#'"):
+                buf.append(s[2:].lstrip())
+                line_idx -= 1
+                continue
+            # stop at first non-roxygen line (don’t cross blank + NULL padding blocks)
+            break
+        if not buf:
+            return None
+        buf.reverse()
+        return '\n'.join(buf).strip() or None
+
+    # -------- Position / brace helpers (comment/string aware) --------
+
+    def _build_brace_map_safely(self):
         """
-        Get library imports and source statements in R code.
-        Returns a list of library names and sourced files.
+        Build a map of '{' -> matching '}' while ignoring braces inside:
+          - comments starting with '#'
+          - single- and double-quoted strings with escapes
         """
-        imports = []
-        
-        with open(self.file_path, 'r', encoding='utf-8') as f:
-            lines = f.readlines()
-        
-        for line in lines:
-            line = line.strip()
-            
-            # Match library() calls
-            lib_match = re.search(r'library\s*\(\s*["\']?([^"\')\s]+)["\']?\s*\)', line)
-            if lib_match:
-                imports.append(f"library({lib_match.group(1)})")
-            
-            # Match require() calls
-            req_match = re.search(r'require\s*\(\s*["\']?([^"\')\s]+)["\']?\s*\)', line)
-            if req_match:
-                imports.append(f"require({req_match.group(1)})")
-            
-            # Match source() calls
-            src_match = re.search(r'source\s*\(\s*["\']([^"\']+)["\']\s*\)', line)
-            if src_match:
-                imports.append(f"source({src_match.group(1)})")
-            
-            # Match :: namespace calls (just collect unique packages)
-            ns_matches = re.findall(r'([a-zA-Z_][a-zA-Z0-9_.]*)::', line)
-            for ns in ns_matches:
-                ns_import = f"{ns}::"
-                if ns_import not in imports:
-                    imports.append(ns_import)
-        
-        return imports
+        stack = []
+        pairs = {}
+        in_string: Optional[str] = None
+        escape = False
+        in_comment = False
 
+        for i, ch in enumerate(self.text):
+            if in_comment:
+                if ch == '\n':
+                    in_comment = False
+                continue
 
-# Example usage:
-if __name__ == "__main__":
-    # Example R file analysis
-    handler = RFileHandler("example.R")
-    
-    # Get functions and classes
-    functions_and_classes = handler.get_functions_and_classes()
-    print("Functions and Classes:")
-    for item in functions_and_classes:
-        name, parent, start, end, doc, params = item
-        print(f"  {name}: lines {start}-{end}, params: {params}")
-        if doc:
-            print(f"    Doc: {doc[:50]}...")
+            if in_string:
+                if escape:
+                    escape = False
+                    continue
+                if ch == '\\':
+                    escape = True
+                    continue
+                if ch == in_string:
+                    in_string = None
+                continue
+
+            # not in string/comment
+            if ch == '#':
+                in_comment = True
+                continue
+            if ch == '"' or ch == "'":
+                in_string = ch
+                continue
+
+            if ch == '{':
+                stack.append(i)
+            elif ch == '}':
+                if stack:
+                    open_i = stack.pop()
+                    pairs[open_i] = i
+        return pairs
+
+    def _matching_brace_pos(self, open_brace_pos: int) -> int:
+        return self._brace_map.get(open_brace_pos, len(self.text) - 1)
+
+    def _find_next_code_brace_after(self, start: int) -> Optional[int]:
+        """Find next '{' after start, skipping ones in comments/strings by scanning forward again."""
+        in_string: Optional[str] = None
+        escape = False
+        in_comment = False
+        for i in range(start, len(self.text)):
+            ch = self.text[i]
+            if in_comment:
+                if ch == '\n':
+                    in_comment = False
+                continue
+            if in_string:
+                if escape:
+                    escape = False
+                    continue
+                if ch == '\\':
+                    escape = True
+                    continue
+                if ch == in_string:
+                    in_string = None
+                continue
+            if ch == '#':
+                in_comment = True
+                continue
+            if ch == '"' or ch == "'":
+                in_string = ch
+                continue
+            if ch == '{':
+                return i
+        return None
+
+    def _pos_to_line(self, pos: int) -> int:
+        return self.text.count('\n', 0, max(0, pos)) + 1
+
+    def _find_next_char_in_text(self, text: str, ch: str, start: int) -> Optional[int]:
+        idx = text.find(ch, start)
+        return idx if idx != -1 else None
+
+    # For nested parsing on a slice (already delimited correctly)
+    def _matching_brace_pos_in_text(self, text: str, open_idx: int) -> Optional[int]:
+        in_string: Optional[str] = None
+        escape = False
+        in_comment = False
+        depth = 0
+        for i in range(open_idx, len(text)):
+            ch = text[i]
+            if in_comment:
+                if ch == '\n':
+                    in_comment = False
+                continue
+            if in_string:
+                if escape:
+                    escape = False
+                elif ch == '\\':
+                    escape = True
+                elif ch == in_string:
+                    in_string = None
+                continue
+            if ch == '#':
+                in_comment = True
+                continue
+            if ch == '"' or ch == "'":
+                in_string = ch
+                continue
+            if ch == '{':
+                depth += 1
+            elif ch == '}':
+                depth -= 1
+                if depth == 0:
+                    return i
+        return None
+
+    def _matching_paren_pos_in_text(self, text: str, open_idx: int) -> Optional[int]:
+        in_string: Optional[str] = None
+        escape = False
+        in_comment = False
+        depth = 0
+        for i in range(open_idx, len(text)):
+            ch = text[i]
+            if in_comment:
+                if ch == '\n':
+                    in_comment = False
+                continue
+            if in_string:
+                if escape:
+                    escape = False
+                elif ch == '\\':
+                    escape = True
+                elif ch == in_string:
+                    in_string = None
+                continue
+            if ch == '#':
+                in_comment = True
+                continue
+            if ch == '"' or ch == "'":
+                in_string = ch
+                continue
+            if ch == '(':
+                depth += 1
+            elif ch == ')':
+                depth -= 1
+                if depth == 0:
+                    return i
+        return None
     
-    # Get imports
-    imports = handler.get_imports()
-    print(f"\nImports: {imports}")
+    def _matching_paren_pos_global(self, open_idx: int) -> Optional[int]:
+        """Given an index of '(' in self.text, return the matching ')' index,
+        ignoring parentheses inside strings/comments."""
+        in_string: Optional[str] = None
+        escape = False
+        in_comment = False
+        depth = 0
+        for i in range(open_idx, len(self.text)):
+            ch = self.text[i]
+            if in_comment:
+                if ch == '\n':
+                    in_comment = False
+                continue
+            if in_string:
+                if escape:
+                    escape = False
+                elif ch == '\\':
+                    escape = True
+                elif ch == in_string:
+                    in_string = None
+                continue
+            if ch == '#':
+                in_comment = True
+                continue
+            if ch == '"' or ch == "'":
+                in_string = ch
+                continue
+            if ch == '(':
+                depth += 1
+            elif ch == ')':
+                depth -= 1
+                if depth == 0:
+                    return i
+        return None
+