I forget
- SHA
99fc848819cd7f81efeb4a52ba8507c766d264c5- Parents
-
15f21e0 - Tree
00b83ee
99fc848
99fc848819cd7f81efeb4a52ba8507c766d264c515f21e0
00b83ee| Status | File | + | - |
|---|---|---|---|
| M |
Makefile
|
9 | 1 |
| A |
src/sultree/arg_definitions.py
|
209 | 0 |
| A |
src/sultree/constants.py
|
106 | 0 |
| A |
src/sultree/tree_renderer.py
|
333 | 0 |
| A |
src/sultree/validators.py
|
228 | 0 |
| M |
sultree.spec
|
5 | 3 |
Makefilemodified@@ -5,12 +5,13 @@ PYTHON = python3 | ||
| 5 | 5 | PACKAGE = sultree |
| 6 | 6 | VERSION = 0.0.8 |
| 7 | 7 | |
| 8 | -.PHONY: help build install test clean dist rpm dev-install check format | |
| 8 | +.PHONY: help build install uninstall test clean dist rpm dev-install check format | |
| 9 | 9 | |
| 10 | 10 | help: |
| 11 | 11 | @echo "Available targets:" |
| 12 | 12 | @echo " build - Build the package" |
| 13 | 13 | @echo " install - Install the package" |
| 14 | + @echo " uninstall - Uninstall the package" | |
| 14 | 15 | @echo " dev-install - Install in development mode" |
| 15 | 16 | @echo " test - Run tests" |
| 16 | 17 | @echo " check - Run code quality checks" |
@@ -25,6 +26,13 @@ build: | ||
| 25 | 26 | install: |
| 26 | 27 | $(PYTHON) -m pip install . |
| 27 | 28 | |
| 29 | +uninstall: | |
| 30 | + @echo "Uninstalling $(PACKAGE)..." | |
| 31 | + $(PYTHON) -m pip uninstall $(PACKAGE) -y || echo "Package not installed via pip" | |
| 32 | + @echo "Removing any remaining executables..." | |
| 33 | + @rm -f ~/.local/bin/$(PACKAGE) 2>/dev/null || true | |
| 34 | + @echo "Uninstall complete!" | |
| 35 | + | |
| 28 | 36 | dev-install: |
| 29 | 37 | $(PYTHON) -m pip install -e .[dev] |
| 30 | 38 | |
src/sultree/arg_definitions.pyadded@@ -0,0 +1,209 @@ | ||
| 1 | +""" | |
| 2 | +Data-driven argument definitions for sultree. | |
| 3 | + | |
| 4 | +This module contains all command-line argument definitions in a clean, | |
| 5 | +table-driven format to eliminate repetitive argparse code. | |
| 6 | +""" | |
| 7 | + | |
| 8 | +from dataclasses import dataclass | |
| 9 | +from typing import List, Optional, Callable, Any, Dict | |
| 10 | + | |
| 11 | +from .validators import ( | |
| 12 | + validate_depth, | |
| 13 | + validate_file_limit, | |
| 14 | + validate_pattern, | |
| 15 | + validate_selinux_pattern, | |
| 16 | + validate_path | |
| 17 | +) | |
| 18 | + | |
| 19 | + | |
| 20 | +@dataclass | |
| 21 | +class ArgumentDefinition: | |
| 22 | + """Defines a command-line argument.""" | |
| 23 | + short_name: Optional[str] = None | |
| 24 | + long_name: str = '' | |
| 25 | + action: str = 'store' | |
| 26 | + type_func: Optional[Callable] = None | |
| 27 | + dest: Optional[str] = None | |
| 28 | + metavar: Optional[str] = None | |
| 29 | + help_text: str = '' | |
| 30 | + default: Any = None | |
| 31 | + nargs: Optional[str] = None | |
| 32 | + | |
| 33 | + | |
| 34 | +# Data-driven argument definitions table | |
| 35 | +ARGUMENT_DEFINITIONS = [ | |
| 36 | + # Positional arguments | |
| 37 | + ArgumentDefinition( | |
| 38 | + long_name='directories', | |
| 39 | + action='store', | |
| 40 | + nargs='*', | |
| 41 | + type_func=validate_path, | |
| 42 | + help_text='directories to tree (default: current directory)', | |
| 43 | + default=None # Will be set to [Path('.')] in parsing | |
| 44 | + ), | |
| 45 | + | |
| 46 | + # Basic listing options | |
| 47 | + ArgumentDefinition( | |
| 48 | + short_name='-a', | |
| 49 | + long_name='--all', | |
| 50 | + action='store_true', | |
| 51 | + help_text='show all files (including hidden files)' | |
| 52 | + ), | |
| 53 | + ArgumentDefinition( | |
| 54 | + short_name='-d', | |
| 55 | + long_name='--dirs-only', | |
| 56 | + action='store_true', | |
| 57 | + help_text='list directories only' | |
| 58 | + ), | |
| 59 | + ArgumentDefinition( | |
| 60 | + short_name='-l', | |
| 61 | + long_name='--follow-links', | |
| 62 | + action='store_true', | |
| 63 | + help_text='follow symbolic links like directories' | |
| 64 | + ), | |
| 65 | + ArgumentDefinition( | |
| 66 | + short_name='-f', | |
| 67 | + long_name='--full-path', | |
| 68 | + action='store_true', | |
| 69 | + help_text='print full path prefix for each file' | |
| 70 | + ), | |
| 71 | + ArgumentDefinition( | |
| 72 | + short_name='-x', | |
| 73 | + long_name='--one-file-system', | |
| 74 | + action='store_true', | |
| 75 | + help_text='stay on current filesystem only' | |
| 76 | + ), | |
| 77 | + | |
| 78 | + # Depth control | |
| 79 | + ArgumentDefinition( | |
| 80 | + short_name='-L', | |
| 81 | + long_name='--level', | |
| 82 | + type_func=validate_depth, | |
| 83 | + metavar='level', | |
| 84 | + help_text='descend only level directories deep' | |
| 85 | + ), | |
| 86 | + | |
| 87 | + # Pattern filtering | |
| 88 | + ArgumentDefinition( | |
| 89 | + short_name='-P', | |
| 90 | + long_name='--pattern', | |
| 91 | + type_func=validate_pattern, | |
| 92 | + action='append', | |
| 93 | + dest='include_patterns', | |
| 94 | + metavar='pattern', | |
| 95 | + help_text='list only files that match the pattern' | |
| 96 | + ), | |
| 97 | + ArgumentDefinition( | |
| 98 | + short_name='-I', | |
| 99 | + long_name='--ignore', | |
| 100 | + type_func=validate_pattern, | |
| 101 | + action='append', | |
| 102 | + dest='exclude_patterns', | |
| 103 | + metavar='pattern', | |
| 104 | + help_text='do not list files that match the pattern' | |
| 105 | + ), | |
| 106 | + ArgumentDefinition( | |
| 107 | + long_name='--match-dirs', | |
| 108 | + action='store_true', | |
| 109 | + help_text='include directory names in pattern matching' | |
| 110 | + ), | |
| 111 | + ArgumentDefinition( | |
| 112 | + long_name='--ignore-case', | |
| 113 | + action='store_true', | |
| 114 | + help_text='ignore case when pattern matching' | |
| 115 | + ), | |
| 116 | + | |
| 117 | + # File limits | |
| 118 | + ArgumentDefinition( | |
| 119 | + long_name='--filelimit', | |
| 120 | + type_func=validate_file_limit, | |
| 121 | + metavar='N', | |
| 122 | + help_text='do not descend dirs with more than N files' | |
| 123 | + ), | |
| 124 | + | |
| 125 | + # SELinux options | |
| 126 | + ArgumentDefinition( | |
| 127 | + short_name='-S', | |
| 128 | + long_name='--selinux', | |
| 129 | + type_func=validate_selinux_pattern, | |
| 130 | + action='append', | |
| 131 | + dest='selinux_patterns', | |
| 132 | + metavar='pattern', | |
| 133 | + help_text='show only files matching SELinux pattern (can be used multiple times)' | |
| 134 | + ), | |
| 135 | + | |
| 136 | + # Output options | |
| 137 | + ArgumentDefinition( | |
| 138 | + long_name='--no-report', | |
| 139 | + action='store_true', | |
| 140 | + help_text='turn off file/directory count at end of tree listing' | |
| 141 | + ), | |
| 142 | + ArgumentDefinition( | |
| 143 | + long_name='--version', | |
| 144 | + action='version', | |
| 145 | + help_text='show version information', | |
| 146 | + # Note: version string will be set dynamically | |
| 147 | + ), | |
| 148 | +] | |
| 149 | + | |
| 150 | + | |
| 151 | +def build_argument_kwargs(arg_def: ArgumentDefinition) -> Dict[str, Any]: | |
| 152 | + """ | |
| 153 | + Convert ArgumentDefinition to kwargs for argparse.add_argument(). | |
| 154 | + | |
| 155 | + Args: | |
| 156 | + arg_def: Argument definition | |
| 157 | + | |
| 158 | + Returns: | |
| 159 | + Dictionary of kwargs for add_argument() | |
| 160 | + """ | |
| 161 | + kwargs = {} | |
| 162 | + | |
| 163 | + # Action | |
| 164 | + if arg_def.action: | |
| 165 | + kwargs['action'] = arg_def.action | |
| 166 | + | |
| 167 | + # Type function | |
| 168 | + if arg_def.type_func: | |
| 169 | + kwargs['type'] = arg_def.type_func | |
| 170 | + | |
| 171 | + # Destination | |
| 172 | + if arg_def.dest: | |
| 173 | + kwargs['dest'] = arg_def.dest | |
| 174 | + | |
| 175 | + # Metavar | |
| 176 | + if arg_def.metavar: | |
| 177 | + kwargs['metavar'] = arg_def.metavar | |
| 178 | + | |
| 179 | + # Help text | |
| 180 | + if arg_def.help_text: | |
| 181 | + kwargs['help'] = arg_def.help_text | |
| 182 | + | |
| 183 | + # Default value | |
| 184 | + if arg_def.default is not None: | |
| 185 | + kwargs['default'] = arg_def.default | |
| 186 | + | |
| 187 | + # Nargs | |
| 188 | + if arg_def.nargs: | |
| 189 | + kwargs['nargs'] = arg_def.nargs | |
| 190 | + | |
| 191 | + return kwargs | |
| 192 | + | |
| 193 | + | |
| 194 | +def get_argument_names(arg_def: ArgumentDefinition) -> List[str]: | |
| 195 | + """ | |
| 196 | + Get the argument names (short and long) for an ArgumentDefinition. | |
| 197 | + | |
| 198 | + Args: | |
| 199 | + arg_def: Argument definition | |
| 200 | + | |
| 201 | + Returns: | |
| 202 | + List of argument names | |
| 203 | + """ | |
| 204 | + names = [] | |
| 205 | + if arg_def.short_name: | |
| 206 | + names.append(arg_def.short_name) | |
| 207 | + if arg_def.long_name: | |
| 208 | + names.append(arg_def.long_name) | |
| 209 | + return names | |
src/sultree/constants.pyadded@@ -0,0 +1,106 @@ | ||
| 1 | +""" | |
| 2 | +Constants and configuration values for sultree. | |
| 3 | + | |
| 4 | +This module centralizes all magic numbers and configuration values, | |
| 5 | +making them data-driven and easier to maintain. | |
| 6 | +""" | |
| 7 | + | |
| 8 | +from typing import Dict, Any | |
| 9 | +import dataclasses | |
| 10 | + | |
| 11 | + | |
| 12 | +@dataclasses.dataclass(frozen=True) | |
| 13 | +class Limits: | |
| 14 | + """Resource and validation limits.""" | |
| 15 | + | |
| 16 | + # Input validation limits | |
| 17 | + MAX_DEPTH: int = 1000 | |
| 18 | + MAX_FILE_LIMIT: int = 100000 | |
| 19 | + MAX_PATTERN_LENGTH: int = 1000 | |
| 20 | + MAX_SELINUX_PATTERN_LENGTH: int = 500 | |
| 21 | + MAX_PATH_LENGTH: int = 4096 | |
| 22 | + | |
| 23 | + # Performance tuning | |
| 24 | + SELINUX_QUERY_TIMEOUT: int = 5 | |
| 25 | + MAX_LINE_LENGTH: int = 2000 | |
| 26 | + MAX_FILE_READ_LINES: int = 2000 | |
| 27 | + | |
| 28 | + # SELinux context fields (allows up to 6 for complex MLS levels) | |
| 29 | + MAX_SELINUX_FIELDS: int = 6 | |
| 30 | + | |
| 31 | + | |
| 32 | +@dataclasses.dataclass(frozen=True) | |
| 33 | +class TreeChars: | |
| 34 | + """Tree drawing characters for different terminal types.""" | |
| 35 | + | |
| 36 | + # Unicode tree characters (default) | |
| 37 | + UNICODE: Dict[str, str] = dataclasses.field(default_factory=lambda: { | |
| 38 | + 'vertical': '│', | |
| 39 | + 'branch': '├──', | |
| 40 | + 'last': '└──', | |
| 41 | + 'space': ' ', | |
| 42 | + 'continuation': '│ ' | |
| 43 | + }) | |
| 44 | + | |
| 45 | + # ASCII fallback characters | |
| 46 | + ASCII: Dict[str, str] = dataclasses.field(default_factory=lambda: { | |
| 47 | + 'vertical': '|', | |
| 48 | + 'branch': '|--', | |
| 49 | + 'last': '`--', | |
| 50 | + 'space': ' ', | |
| 51 | + 'continuation': '| ' | |
| 52 | + }) | |
| 53 | + | |
| 54 | + | |
| 55 | +@dataclasses.dataclass(frozen=True) | |
| 56 | +class Security: | |
| 57 | + """Security-related constants.""" | |
| 58 | + | |
| 59 | + # Dangerous characters to remove from patterns | |
| 60 | + DANGEROUS_CHARS: tuple = (';', '&', '|', '`', '$', '(', ')', '<', '>', '\n', '\r') | |
| 61 | + | |
| 62 | + # Dangerous regex patterns | |
| 63 | + DANGEROUS_REGEX_PATTERNS: tuple = ( | |
| 64 | + r'\(\?\(\?\!', # Catastrophic backtracking | |
| 65 | + r'\(\?\(\?\=', # Catastrophic backtracking | |
| 66 | + r'\*\*\*+', # Excessive repetition | |
| 67 | + ) | |
| 68 | + | |
| 69 | + # SELinux extended attribute name | |
| 70 | + SELINUX_XATTR: str = 'security.selinux' | |
| 71 | + | |
| 72 | + | |
| 73 | +@dataclasses.dataclass(frozen=True) | |
| 74 | +class ExitCodes: | |
| 75 | + """Standard exit codes.""" | |
| 76 | + | |
| 77 | + SUCCESS: int = 0 | |
| 78 | + GENERAL_ERROR: int = 1 | |
| 79 | + INVALID_ARGS: int = 2 | |
| 80 | + PERMISSION_ERROR: int = 3 | |
| 81 | + PARTIAL_SUCCESS: int = 4 # Some directories processed successfully | |
| 82 | + INTERRUPTED: int = 130 # Ctrl+C | |
| 83 | + | |
| 84 | + | |
| 85 | +@dataclasses.dataclass(frozen=True) | |
| 86 | +class Config: | |
| 87 | + """Main configuration object combining all constants.""" | |
| 88 | + | |
| 89 | + limits: Limits = dataclasses.field(default_factory=Limits) | |
| 90 | + tree_chars: TreeChars = dataclasses.field(default_factory=TreeChars) | |
| 91 | + security: Security = dataclasses.field(default_factory=Security) | |
| 92 | + exit_codes: ExitCodes = dataclasses.field(default_factory=ExitCodes) | |
| 93 | + | |
| 94 | + | |
| 95 | +# Global configuration instance | |
| 96 | +CONFIG = Config() | |
| 97 | + | |
| 98 | + | |
| 99 | +def get_config() -> Config: | |
| 100 | + """ | |
| 101 | + Get the global configuration instance. | |
| 102 | + | |
| 103 | + Returns: | |
| 104 | + Configuration object with all constants | |
| 105 | + """ | |
| 106 | + return CONFIG | |
src/sultree/tree_renderer.pyadded@@ -0,0 +1,333 @@ | ||
| 1 | +""" | |
| 2 | +Proper tree rendering module for sultree. | |
| 3 | + | |
| 4 | +This module implements the visual tree structure that makes tree commands useful, | |
| 5 | +with proper indentation, connectors, and hierarchical display. | |
| 6 | +""" | |
| 7 | + | |
| 8 | +import sys | |
| 9 | +from pathlib import Path | |
| 10 | +from typing import List, Dict, Optional, TextIO, Tuple | |
| 11 | +from dataclasses import dataclass | |
| 12 | + | |
| 13 | +from .constants import CONFIG | |
| 14 | +from .traversal import FileEntry | |
| 15 | +from .selinux import get_selinux_context | |
| 16 | + | |
| 17 | + | |
| 18 | +@dataclass | |
| 19 | +class TreeNode: | |
| 20 | + """Represents a node in the tree structure.""" | |
| 21 | + entry: FileEntry | |
| 22 | + children: List['TreeNode'] | |
| 23 | + is_last: bool = False # Is this the last child of its parent? | |
| 24 | + | |
| 25 | + def __post_init__(self): | |
| 26 | + if not hasattr(self, 'children') or self.children is None: | |
| 27 | + self.children = [] | |
| 28 | + | |
| 29 | + | |
| 30 | +class TreeRenderer: | |
| 31 | + """ | |
| 32 | + Renders directory trees with proper visual structure. | |
| 33 | + | |
| 34 | + Handles the tree drawing characters, indentation, and hierarchical display | |
| 35 | + that makes tree commands visually useful. | |
| 36 | + """ | |
| 37 | + | |
| 38 | + def __init__(self, show_full_path: bool = False, | |
| 39 | + show_selinux: bool = False, | |
| 40 | + use_ascii: bool = False, | |
| 41 | + output_file: Optional[TextIO] = None): | |
| 42 | + """ | |
| 43 | + Initialize tree renderer. | |
| 44 | + | |
| 45 | + Args: | |
| 46 | + show_full_path: Show full paths instead of just names | |
| 47 | + show_selinux: Include SELinux contexts in output | |
| 48 | + use_ascii: Use ASCII characters instead of Unicode | |
| 49 | + output_file: Output file (default: stdout) | |
| 50 | + """ | |
| 51 | + self.show_full_path = show_full_path | |
| 52 | + self.show_selinux = show_selinux | |
| 53 | + self.output_file = output_file or sys.stdout | |
| 54 | + | |
| 55 | + # Choose character set based on terminal capabilities | |
| 56 | + if use_ascii or not self._supports_unicode(): | |
| 57 | + self.chars = CONFIG.tree_chars.ASCII | |
| 58 | + else: | |
| 59 | + self.chars = CONFIG.tree_chars.UNICODE | |
| 60 | + | |
| 61 | + # Statistics tracking | |
| 62 | + self.dir_count = 0 | |
| 63 | + self.file_count = 0 | |
| 64 | + | |
| 65 | + def _supports_unicode(self) -> bool: | |
| 66 | + """ | |
| 67 | + Check if terminal supports Unicode characters. | |
| 68 | + | |
| 69 | + Returns: | |
| 70 | + True if Unicode is supported | |
| 71 | + """ | |
| 72 | + try: | |
| 73 | + # Check encoding | |
| 74 | + encoding = self.output_file.encoding or 'ascii' | |
| 75 | + if 'utf' not in encoding.lower(): | |
| 76 | + return False | |
| 77 | + | |
| 78 | + # Check if we can write Unicode characters | |
| 79 | + self.output_file.write('') # Test write access | |
| 80 | + return True | |
| 81 | + | |
| 82 | + except (AttributeError, UnicodeError): | |
| 83 | + return False | |
| 84 | + | |
| 85 | + def render_tree(self, root_path: Path, root_node: TreeNode, show_report: bool = True) -> None: | |
| 86 | + """ | |
| 87 | + Render the complete tree structure. | |
| 88 | + | |
| 89 | + Args: | |
| 90 | + root_path: Root directory path | |
| 91 | + root_node: Root tree node | |
| 92 | + show_report: Whether to show file/directory count at end | |
| 93 | + """ | |
| 94 | + # Print root directory | |
| 95 | + self._print_root(root_path) | |
| 96 | + | |
| 97 | + # Render tree structure | |
| 98 | + self._render_node_children(root_node.children, prefix="", is_root=True) | |
| 99 | + | |
| 100 | + # Print summary report | |
| 101 | + if show_report: | |
| 102 | + self._print_report() | |
| 103 | + | |
| 104 | + def _render_node_children(self, nodes: List[TreeNode], prefix: str, is_root: bool = False) -> None: | |
| 105 | + """ | |
| 106 | + Render a list of child nodes with proper tree structure. | |
| 107 | + | |
| 108 | + Args: | |
| 109 | + nodes: List of child nodes to render | |
| 110 | + prefix: Current prefix for indentation | |
| 111 | + is_root: Whether these are direct children of root | |
| 112 | + """ | |
| 113 | + for i, node in enumerate(nodes): | |
| 114 | + is_last = (i == len(nodes) - 1) | |
| 115 | + self._render_node(node, prefix, is_last, is_root) | |
| 116 | + | |
| 117 | + def _render_node(self, node: TreeNode, prefix: str, is_last: bool, is_root: bool = False) -> None: | |
| 118 | + """ | |
| 119 | + Render a single node with proper tree connectors. | |
| 120 | + | |
| 121 | + Args: | |
| 122 | + node: Node to render | |
| 123 | + prefix: Current prefix for indentation | |
| 124 | + is_last: Whether this is the last child at this level | |
| 125 | + is_root: Whether this is a direct child of root | |
| 126 | + """ | |
| 127 | + # Build the connector | |
| 128 | + if is_root: | |
| 129 | + # Direct children of root | |
| 130 | + connector = self.chars['last'] if is_last else self.chars['branch'] | |
| 131 | + else: | |
| 132 | + connector = self.chars['last'] if is_last else self.chars['branch'] | |
| 133 | + | |
| 134 | + # Get display name | |
| 135 | + display_name = self._get_display_name(node.entry) | |
| 136 | + | |
| 137 | + # Add SELinux context if requested | |
| 138 | + selinux_info = "" | |
| 139 | + if self.show_selinux: | |
| 140 | + selinux_info = self._get_selinux_display(node.entry.path) | |
| 141 | + | |
| 142 | + # Print the node | |
| 143 | + line = f"{prefix}{connector} {display_name}{selinux_info}" | |
| 144 | + self._safe_print(line) | |
| 145 | + | |
| 146 | + # Update statistics | |
| 147 | + if node.entry.is_dir: | |
| 148 | + self.dir_count += 1 | |
| 149 | + else: | |
| 150 | + self.file_count += 1 | |
| 151 | + | |
| 152 | + # Render children if any | |
| 153 | + if node.children: | |
| 154 | + # Build prefix for children | |
| 155 | + if is_last: | |
| 156 | + child_prefix = prefix + self.chars['space'] | |
| 157 | + else: | |
| 158 | + child_prefix = prefix + self.chars['continuation'] | |
| 159 | + | |
| 160 | + self._render_node_children(node.children, child_prefix) | |
| 161 | + | |
| 162 | + def _get_display_name(self, entry: FileEntry) -> str: | |
| 163 | + """ | |
| 164 | + Get the display name for a file entry. | |
| 165 | + | |
| 166 | + Args: | |
| 167 | + entry: FileEntry to get name for | |
| 168 | + | |
| 169 | + Returns: | |
| 170 | + Formatted display name | |
| 171 | + """ | |
| 172 | + if self.show_full_path: | |
| 173 | + display_name = str(entry.path) | |
| 174 | + else: | |
| 175 | + display_name = entry.name | |
| 176 | + | |
| 177 | + # Add symlink target if applicable | |
| 178 | + if entry.is_symlink and entry.symlink_target: | |
| 179 | + safe_target = self._safe_filename(str(entry.symlink_target)) | |
| 180 | + display_name += f" -> {safe_target}" | |
| 181 | + | |
| 182 | + return self._safe_filename(display_name) | |
| 183 | + | |
| 184 | + def _get_selinux_display(self, file_path: Path) -> str: | |
| 185 | + """ | |
| 186 | + Get formatted SELinux context for display. | |
| 187 | + | |
| 188 | + Args: | |
| 189 | + file_path: Path to get context for | |
| 190 | + | |
| 191 | + Returns: | |
| 192 | + Formatted SELinux context string | |
| 193 | + """ | |
| 194 | + try: | |
| 195 | + context = get_selinux_context(file_path) | |
| 196 | + if context: | |
| 197 | + return f" [{context}]" | |
| 198 | + except Exception as e: | |
| 199 | + # Don't let SELinux errors break tree rendering | |
| 200 | + pass | |
| 201 | + | |
| 202 | + return "" | |
| 203 | + | |
| 204 | + def _safe_filename(self, filename: str) -> str: | |
| 205 | + """ | |
| 206 | + Make filename safe for terminal display. | |
| 207 | + | |
| 208 | + Args: | |
| 209 | + filename: Raw filename | |
| 210 | + | |
| 211 | + Returns: | |
| 212 | + Safely escaped filename | |
| 213 | + """ | |
| 214 | + if not filename: | |
| 215 | + return "<empty>" | |
| 216 | + | |
| 217 | + # Replace control characters with visible representations | |
| 218 | + safe_chars = [] | |
| 219 | + for char in filename: | |
| 220 | + # Replace control characters with visible representations | |
| 221 | + if ord(char) < 32 or ord(char) == 127: # Control characters | |
| 222 | + safe_chars.append(f"\\x{ord(char):02x}") | |
| 223 | + elif char in ('\n', '\r', '\t'): # Specific dangerous chars | |
| 224 | + safe_chars.append(repr(char)[1:-1]) # Use repr but remove quotes | |
| 225 | + else: | |
| 226 | + safe_chars.append(char) | |
| 227 | + | |
| 228 | + return ''.join(safe_chars) | |
| 229 | + | |
| 230 | + def _print_root(self, root_path: Path) -> None: | |
| 231 | + """ | |
| 232 | + Print the root directory name. | |
| 233 | + | |
| 234 | + Args: | |
| 235 | + root_path: Root directory to display | |
| 236 | + """ | |
| 237 | + root_display = str(root_path) if self.show_full_path else root_path.name or str(root_path) | |
| 238 | + safe_display = self._safe_filename(root_display) | |
| 239 | + self._safe_print(safe_display) | |
| 240 | + | |
| 241 | + def _safe_print(self, text: str) -> None: | |
| 242 | + """ | |
| 243 | + Safely print text to output, handling encoding issues. | |
| 244 | + | |
| 245 | + Args: | |
| 246 | + text: Text to print | |
| 247 | + """ | |
| 248 | + try: | |
| 249 | + print(text, file=self.output_file) | |
| 250 | + except UnicodeEncodeError: | |
| 251 | + # Fallback for terminals that can't handle the text | |
| 252 | + safe_text = text.encode('ascii', 'replace').decode('ascii') | |
| 253 | + print(safe_text, file=self.output_file) | |
| 254 | + | |
| 255 | + def _print_report(self) -> None: | |
| 256 | + """ | |
| 257 | + Print summary report of files and directories. | |
| 258 | + """ | |
| 259 | + total = self.dir_count + self.file_count | |
| 260 | + | |
| 261 | + report_parts = [] | |
| 262 | + if self.dir_count > 0: | |
| 263 | + dir_word = "directory" if self.dir_count == 1 else "directories" | |
| 264 | + report_parts.append(f"{self.dir_count} {dir_word}") | |
| 265 | + | |
| 266 | + if self.file_count > 0: | |
| 267 | + file_word = "file" if self.file_count == 1 else "files" | |
| 268 | + report_parts.append(f"{self.file_count} {file_word}") | |
| 269 | + | |
| 270 | + if report_parts: | |
| 271 | + report = ", ".join(report_parts) | |
| 272 | + self._safe_print(f"\n{report}") | |
| 273 | + | |
| 274 | + | |
| 275 | +def build_tree_structure(entries: List[FileEntry], root_path: Path) -> TreeNode: | |
| 276 | + """ | |
| 277 | + Build a proper tree structure from a flat list of entries. | |
| 278 | + | |
| 279 | + Args: | |
| 280 | + entries: Flat list of FileEntry objects | |
| 281 | + root_path: The root directory path | |
| 282 | + | |
| 283 | + Returns: | |
| 284 | + Root TreeNode with hierarchical structure | |
| 285 | + """ | |
| 286 | + # Create a mapping from path to node | |
| 287 | + path_to_node: Dict[Path, TreeNode] = {} | |
| 288 | + | |
| 289 | + # Create the root node first | |
| 290 | + root_entry = FileEntry( | |
| 291 | + path=root_path, | |
| 292 | + name=root_path.name or str(root_path), | |
| 293 | + is_dir=True, | |
| 294 | + depth=0 | |
| 295 | + ) | |
| 296 | + root_node = TreeNode(entry=root_entry, children=[]) | |
| 297 | + path_to_node[root_path] = root_node | |
| 298 | + | |
| 299 | + # Sort entries by path depth to ensure parents are processed before children | |
| 300 | + sorted_entries = sorted(entries, key=lambda e: len(e.path.parts)) | |
| 301 | + | |
| 302 | + for entry in sorted_entries: | |
| 303 | + # Create node for this entry | |
| 304 | + node = TreeNode(entry=entry, children=[]) | |
| 305 | + path_to_node[entry.path] = node | |
| 306 | + | |
| 307 | + # Find parent and add as child | |
| 308 | + parent_path = entry.path.parent | |
| 309 | + if parent_path in path_to_node: | |
| 310 | + parent_node = path_to_node[parent_path] | |
| 311 | + parent_node.children.append(node) | |
| 312 | + else: | |
| 313 | + # Parent not in our tree (might be filtered out or permission denied) | |
| 314 | + # Try to find the closest ancestor that exists | |
| 315 | + current_path = parent_path | |
| 316 | + while current_path and current_path != current_path.parent: | |
| 317 | + if current_path in path_to_node: | |
| 318 | + path_to_node[current_path].children.append(node) | |
| 319 | + break | |
| 320 | + current_path = current_path.parent | |
| 321 | + else: | |
| 322 | + # No ancestor found, add to root | |
| 323 | + root_node.children.append(node) | |
| 324 | + | |
| 325 | + # Sort children at each level (directories first, then alphabetical) | |
| 326 | + def sort_children(node: TreeNode): | |
| 327 | + node.children.sort(key=lambda n: (not n.entry.is_dir, n.entry.name.lower())) | |
| 328 | + for child in node.children: | |
| 329 | + sort_children(child) | |
| 330 | + | |
| 331 | + sort_children(root_node) | |
| 332 | + | |
| 333 | + return root_node | |
src/sultree/validators.pyadded@@ -0,0 +1,228 @@ | ||
| 1 | +""" | |
| 2 | +Reusable validation utilities for sultree. | |
| 3 | + | |
| 4 | +This module consolidates validation logic to eliminate duplication | |
| 5 | +and provide consistent error handling. | |
| 6 | +""" | |
| 7 | + | |
| 8 | +import argparse | |
| 9 | +import re | |
| 10 | +from pathlib import Path | |
| 11 | +from typing import Union, List | |
| 12 | + | |
| 13 | +from .constants import CONFIG | |
| 14 | + | |
| 15 | + | |
| 16 | +class ValidationError(Exception): | |
| 17 | + """Base exception for validation errors.""" | |
| 18 | + pass | |
| 19 | + | |
| 20 | + | |
| 21 | +def validate_integer_in_range( | |
| 22 | + value: str, | |
| 23 | + name: str, | |
| 24 | + min_val: int = 0, | |
| 25 | + max_val: Union[int, None] = None | |
| 26 | +) -> int: | |
| 27 | + """ | |
| 28 | + Generic integer validation with range checking. | |
| 29 | + | |
| 30 | + Args: | |
| 31 | + value: String representation of integer | |
| 32 | + name: Human-readable name for error messages | |
| 33 | + min_val: Minimum allowed value (inclusive) | |
| 34 | + max_val: Maximum allowed value (inclusive), None for no limit | |
| 35 | + | |
| 36 | + Returns: | |
| 37 | + Validated integer value | |
| 38 | + | |
| 39 | + Raises: | |
| 40 | + argparse.ArgumentTypeError: If validation fails | |
| 41 | + """ | |
| 42 | + try: | |
| 43 | + int_val = int(value) | |
| 44 | + | |
| 45 | + if int_val < min_val: | |
| 46 | + raise argparse.ArgumentTypeError(f"{name} must be >= {min_val}") | |
| 47 | + | |
| 48 | + if max_val is not None and int_val > max_val: | |
| 49 | + raise argparse.ArgumentTypeError(f"{name} too large (max {max_val})") | |
| 50 | + | |
| 51 | + return int_val | |
| 52 | + | |
| 53 | + except ValueError: | |
| 54 | + raise argparse.ArgumentTypeError(f"{name} must be an integer") | |
| 55 | + | |
| 56 | + | |
| 57 | +def validate_string_length( | |
| 58 | + value: str, | |
| 59 | + name: str, | |
| 60 | + max_length: int, | |
| 61 | + allow_empty: bool = False | |
| 62 | +) -> str: | |
| 63 | + """ | |
| 64 | + Generic string length validation. | |
| 65 | + | |
| 66 | + Args: | |
| 67 | + value: String to validate | |
| 68 | + name: Human-readable name for error messages | |
| 69 | + max_length: Maximum allowed length | |
| 70 | + allow_empty: Whether empty strings are allowed | |
| 71 | + | |
| 72 | + Returns: | |
| 73 | + Validated string | |
| 74 | + | |
| 75 | + Raises: | |
| 76 | + argparse.ArgumentTypeError: If validation fails | |
| 77 | + """ | |
| 78 | + if not value and not allow_empty: | |
| 79 | + raise argparse.ArgumentTypeError(f"{name} cannot be empty") | |
| 80 | + | |
| 81 | + if len(value) > max_length: | |
| 82 | + raise argparse.ArgumentTypeError( | |
| 83 | + f"{name} too long (max {max_length} characters)" | |
| 84 | + ) | |
| 85 | + | |
| 86 | + return value | |
| 87 | + | |
| 88 | + | |
| 89 | +def validate_pattern_safety(pattern: str, name: str) -> str: | |
| 90 | + """ | |
| 91 | + Validate pattern for potentially dangerous constructs. | |
| 92 | + | |
| 93 | + Args: | |
| 94 | + pattern: Pattern to validate | |
| 95 | + name: Human-readable name for error messages | |
| 96 | + | |
| 97 | + Returns: | |
| 98 | + Validated pattern | |
| 99 | + | |
| 100 | + Raises: | |
| 101 | + argparse.ArgumentTypeError: If pattern contains dangerous constructs | |
| 102 | + """ | |
| 103 | + # Check for dangerous regex patterns | |
| 104 | + for dangerous in CONFIG.security.DANGEROUS_REGEX_PATTERNS: | |
| 105 | + if re.search(dangerous, pattern): | |
| 106 | + raise argparse.ArgumentTypeError( | |
| 107 | + f"{name} contains potentially dangerous constructs" | |
| 108 | + ) | |
| 109 | + | |
| 110 | + return pattern | |
| 111 | + | |
| 112 | + | |
| 113 | +def sanitize_selinux_pattern(pattern: str) -> str: | |
| 114 | + """ | |
| 115 | + Sanitize SELinux pattern by removing dangerous characters. | |
| 116 | + | |
| 117 | + Args: | |
| 118 | + pattern: Pattern to sanitize | |
| 119 | + | |
| 120 | + Returns: | |
| 121 | + Sanitized pattern | |
| 122 | + """ | |
| 123 | + # Remove dangerous characters | |
| 124 | + for char in CONFIG.security.DANGEROUS_CHARS: | |
| 125 | + pattern = pattern.replace(char, '') | |
| 126 | + | |
| 127 | + return pattern.strip() | |
| 128 | + | |
| 129 | + | |
| 130 | +def validate_selinux_context_format(pattern: str, name: str) -> str: | |
| 131 | + """ | |
| 132 | + Validate SELinux context pattern format. | |
| 133 | + | |
| 134 | + Args: | |
| 135 | + pattern: SELinux pattern to validate | |
| 136 | + name: Human-readable name for error messages | |
| 137 | + | |
| 138 | + Returns: | |
| 139 | + Validated pattern | |
| 140 | + | |
| 141 | + Raises: | |
| 142 | + argparse.ArgumentTypeError: If format is invalid | |
| 143 | + """ | |
| 144 | + # Basic SELinux context format validation | |
| 145 | + if ':' in pattern: | |
| 146 | + parts = pattern.split(':') | |
| 147 | + if len(parts) > CONFIG.limits.MAX_SELINUX_FIELDS: | |
| 148 | + raise argparse.ArgumentTypeError( | |
| 149 | + f"{name} has too many colon-separated parts" | |
| 150 | + ) | |
| 151 | + | |
| 152 | + return pattern | |
| 153 | + | |
| 154 | + | |
| 155 | +def validate_path_safety(path_str: str, name: str) -> Path: | |
| 156 | + """ | |
| 157 | + Validate path for security issues. | |
| 158 | + | |
| 159 | + Args: | |
| 160 | + path_str: Path string to validate | |
| 161 | + name: Human-readable name for error messages | |
| 162 | + | |
| 163 | + Returns: | |
| 164 | + Validated Path object | |
| 165 | + | |
| 166 | + Raises: | |
| 167 | + argparse.ArgumentTypeError: If path is unsafe | |
| 168 | + """ | |
| 169 | + # Check for null bytes (major security issue) | |
| 170 | + if '\x00' in path_str: | |
| 171 | + raise argparse.ArgumentTypeError(f"{name} contains null bytes") | |
| 172 | + | |
| 173 | + try: | |
| 174 | + path = Path(path_str) | |
| 175 | + return path | |
| 176 | + except (ValueError, OSError) as e: | |
| 177 | + raise argparse.ArgumentTypeError(f"invalid {name}: {e}") | |
| 178 | + | |
| 179 | + | |
| 180 | +# Specialized validators using the generic functions above | |
| 181 | + | |
| 182 | +def validate_depth(value: str) -> int: | |
| 183 | + """Validate depth argument.""" | |
| 184 | + return validate_integer_in_range( | |
| 185 | + value, "depth", 0, CONFIG.limits.MAX_DEPTH | |
| 186 | + ) | |
| 187 | + | |
| 188 | + | |
| 189 | +def validate_file_limit(value: str) -> int: | |
| 190 | + """Validate file limit argument.""" | |
| 191 | + return validate_integer_in_range( | |
| 192 | + value, "file limit", 1, CONFIG.limits.MAX_FILE_LIMIT | |
| 193 | + ) | |
| 194 | + | |
| 195 | + | |
| 196 | +def validate_pattern(pattern: str) -> str: | |
| 197 | + """Validate and sanitize pattern arguments.""" | |
| 198 | + pattern = validate_string_length( | |
| 199 | + pattern, "pattern", CONFIG.limits.MAX_PATTERN_LENGTH | |
| 200 | + ) | |
| 201 | + return validate_pattern_safety(pattern, "pattern") | |
| 202 | + | |
| 203 | + | |
| 204 | +def validate_selinux_pattern(pattern: str) -> str: | |
| 205 | + """Validate SELinux pattern for security.""" | |
| 206 | + pattern = validate_string_length( | |
| 207 | + pattern, "SELinux pattern", CONFIG.limits.MAX_SELINUX_PATTERN_LENGTH | |
| 208 | + ) | |
| 209 | + | |
| 210 | + # Check for dangerous characters | |
| 211 | + for char in CONFIG.security.DANGEROUS_CHARS: | |
| 212 | + if char in pattern: | |
| 213 | + raise argparse.ArgumentTypeError( | |
| 214 | + f"SELinux pattern contains invalid character: '{char}'" | |
| 215 | + ) | |
| 216 | + | |
| 217 | + pattern = validate_selinux_context_format(pattern, "SELinux pattern") | |
| 218 | + | |
| 219 | + return pattern | |
| 220 | + | |
| 221 | + | |
| 222 | +def validate_path(path_str: str) -> Path: | |
| 223 | + """Validate and sanitize path arguments.""" | |
| 224 | + path_str = validate_string_length( | |
| 225 | + path_str, "path", CONFIG.limits.MAX_PATH_LENGTH | |
| 226 | + ) | |
| 227 | + | |
| 228 | + return validate_path_safety(path_str, "path") | |
sultree.specmodified@@ -32,10 +32,12 @@ Features: | ||
| 32 | 32 | %autosetup |
| 33 | 33 | |
| 34 | 34 | %build |
| 35 | -%py3_build | |
| 35 | +export PATH=$PATH:/home/espadon/.local/bin | |
| 36 | +%{python3} -m build --wheel --no-isolation | |
| 36 | 37 | |
| 37 | 38 | %install |
| 38 | -%py3_install | |
| 39 | +export PATH=$PATH:/home/espadon/.local/bin | |
| 40 | +%{python3} -m pip install --root %{buildroot} --no-deps --ignore-installed dist/*.whl | |
| 39 | 41 | |
| 40 | 42 | # Install the standalone script |
| 41 | 43 | install -Dm755 sultree %{buildroot}%{_bindir}/sultree-standalone |
@@ -43,7 +45,7 @@ install -Dm755 sultree %{buildroot}%{_bindir}/sultree-standalone | ||
| 43 | 45 | %files |
| 44 | 46 | %doc README.md |
| 45 | 47 | %{python3_sitelib}/%{name}/ |
| 46 | -%{python3_sitelib}/%{name}-%{version}*.egg-info/ | |
| 48 | +%{python3_sitelib}/%{name}-%{version}*.dist-info/ | |
| 47 | 49 | %{_bindir}/sultree |
| 48 | 50 | %{_bindir}/sultree-standalone |
| 49 | 51 | |