Anarchyphase-Website/file_graph_generator.py

"""
File Graph Generator

Creates a tree-like visualization of files with their content,
respecting .gitignore patterns with proper tree rendering.
"""

import argparse
import fnmatch
import logging
import os
import sys
from dataclasses import dataclass, field
from pathlib import Path
from typing import Iterator, List, Optional

# ───────────────────────────── Logging Setup ──────────────────────────────


def setup_logging(level: int = logging.INFO) -> None:
    """Configure structured logging to stderr (stdout is reserved for output)."""
    logging.basicConfig(
        stream=sys.stderr,
        level=level,
        format="%(asctime)s | %(levelname)-8s | %(message)s",
        datefmt="%H:%M:%S",
    )


logger = logging.getLogger("file_graph")


# ─────────────────────────── Gitignore Engine ─────────────────────────────


@dataclass
class GitignoreRule:
    """A single parsed gitignore rule."""

    pattern: str
    is_negation: bool = False
    is_dir_only: bool = False
    is_anchored: bool = False
    is_relative: bool = False  # contains / (not at start)


class GitignoreParser:
    """Parse a .gitignore file into ordered rules."""

    @staticmethod
    def parse(path: Path) -> List[GitignoreRule]:
        rules = []
        if not path.exists():
            return rules
        try:
            with path.open("r", encoding="utf-8", errors="ignore") as f:
                for line in f:
                    line = line.rstrip("\n\r")
                    # Skip empty lines and comments
                    if not line or line.startswith("#"):
                        continue

                    is_negation = line.startswith("!")
                    if is_negation:
                        line = line[1:]

                    # Handle escaped ! and #
                    if line.startswith("\\!") or line.startswith("\\#"):
                        line = line[1:]

                    line = line.rstrip()
                    if not line:
                        continue

                    is_dir_only = line.endswith("/")
                    if is_dir_only:
                        line = line[:-1]

                    is_anchored = line.startswith("/")
                    if is_anchored:
                        line = line[1:]

                    is_relative = "/" in line

                    rules.append(
                        GitignoreRule(
                            pattern=line,
                            is_negation=is_negation,
                            is_dir_only=is_dir_only,
                            is_anchored=is_anchored,
                            is_relative=is_relative,
                        )
                    )
        except OSError as e:
            logger.warning(f"Could not read {path}: {e}")
        return rules


class GitignoreChecker:
    """Check if paths should be ignored, respecting per-directory .gitignore files."""

    def __init__(self, root: Path):
        self.root = root.resolve()
        self._cache: dict[Path, List[GitignoreRule]] = {}
        self._skip_dirs = {
            ".git",
            "__pycache__",
            ".pytest_cache",
            ".mypy_cache",
            ".tox",
            ".venv",
            "venv",
        }
        self._skip_files = {
            "file_graph_generator.py",
            "file_graph_generator_v2.py",
            "file_graph_generator_v3.py",
            "file_tree.txt",
        }

    def _load(self, directory: Path) -> List[GitignoreRule]:
        """Load rules for a directory (cached)."""
        directory = directory.resolve()
        if directory not in self._cache:
            gitignore_path = directory / ".gitignore"
            if gitignore_path.exists():
                logger.debug(f"Parsing gitignore: {gitignore_path}")
            self._cache[directory] = GitignoreParser.parse(gitignore_path)
        return self._cache[directory]

    def _match_rule(
        self, rule: GitignoreRule, name: str, rel_path: str, is_dir: bool
    ) -> bool:
        """Check if a single rule matches."""
        if rule.is_dir_only and not is_dir:
            return False

        # Anchored pattern: match only at .gitignore level
        if rule.is_anchored:
            return fnmatch.fnmatch(rel_path, rule.pattern) or fnmatch.fnmatch(
                rel_path, rule.pattern + "/"
            )

        # Relative path pattern (contains /): match against rel_path
        if rule.is_relative:
            return fnmatch.fnmatch(rel_path, rule.pattern) or fnmatch.fnmatch(
                rel_path, rule.pattern + "/"
            )

        # Basename pattern: match name at any level
        return fnmatch.fnmatch(name, rule.pattern)

    def is_ignored(self, path: Path, is_dir: bool) -> bool:
        """Check if path should be ignored, walking up to root."""
        name = path.name

        # Fast-path: always skip common VCS/build dirs and script/output files
        if is_dir and name in self._skip_dirs:
            logger.debug(f"Skipping common dir: {name}")
            return True
        if not is_dir and name in self._skip_files:
            logger.debug(f"Skipping script/output file: {name}")
            return True

        # Walk from current directory up to root
        current = path.parent.resolve()
        while True:
            rules = self._load(current)
            if rules:
                rel_path = path.relative_to(current).as_posix()
                ignored = False

                for rule in rules:
                    if self._match_rule(rule, name, rel_path, is_dir):
                        if rule.is_negation:
                            ignored = False
                        else:
                            ignored = True

                if ignored:
                    logger.debug(f"Ignored by gitignore: {path}")
                    return True

            if current == self.root:
                break
            current = current.parent

        return False


# ──────────────────────────── File Reading ────────────────────────────────

MAX_CONTENT_BYTES = 50 * 100  # ~50 lines avg


def is_binary(path: Path) -> bool:
    """Fast binary detection using first 8KB chunk."""
    try:
        with path.open("rb") as f:
            chunk = f.read(8192)
        if not chunk:
            return False
        if b"\x00" in chunk:
            return True
        if chunk[:2] in (b"\xff\xfe", b"\xfe\xff", b"\x1f\x8b"):
            return True
        return False
    except OSError:
        return True


def read_content(path: Path, max_lines: int = 50) -> Iterator[str]:
    """Yield content lines with minimal memory footprint."""
    if is_binary(path):
        yield "[binary file — content skipped]"
        return

    try:
        with path.open("r", encoding="utf-8", errors="replace") as f:
            for i, line in enumerate(f):
                if i >= max_lines:
                    remaining = sum(1 for _ in f)
                    yield f"... ({remaining} more lines)"
                    return
                yield line.rstrip("\n")
    except OSError as e:
        yield f"[Error reading file: {e}]"


# ─────────────────────────── Tree Generator ───────────────────────────────


def get_visible_children(path: Path, checker: GitignoreChecker) -> List[os.DirEntry]:
    """Get sorted, filtered children of a directory."""
    try:
        entries = list(os.scandir(path))
    except PermissionError:
        logger.warning(f"Permission denied: {path}")
        return []
    except OSError as e:
        logger.error(f"Error scanning {path}: {e}")
        return []

    visible = []
    for entry in entries:
        # Skip .gitignore files entirely
        if entry.name == ".gitignore":
            continue

        child_path = Path(entry.path)
        is_dir = entry.is_dir()

        if not checker.is_ignored(child_path, is_dir):
            visible.append(entry)

    # Sort: dirs first, then files, both alphabetically (case-insensitive)
    visible.sort(key=lambda e: (not e.is_dir(), e.name.lower()))
    return visible


def build_tree_lines(
    path: Path,
    checker: GitignoreChecker,
    prefix: str = "",
    max_lines: int = 50,
    max_depth: Optional[int] = None,
    current_depth: int = 0,
) -> Iterator[str]:
    """Recursively yield tree lines. Correctly handles is_last filtering."""

    if path.is_dir():
        if max_depth is not None and current_depth >= max_depth:
            return

        children = get_visible_children(path, checker)
        count = len(children)

        for i, entry in enumerate(children):
            is_last = i == count - 1
            connector = "└── " if is_last else "├── "
            name = entry.name

            if entry.is_dir():
                yield prefix + connector + name + "/"
                extension = "    " if is_last else "│   "
                yield from build_tree_lines(
                    Path(entry.path),
                    checker,
                    prefix + extension,
                    max_lines,
                    max_depth,
                    current_depth + 1,
                )
            else:
                yield prefix + connector + name
                content_prefix = prefix + ("    " if is_last else "│   ") + "    "
                for content_line in read_content(Path(entry.path), max_lines):
                    yield content_prefix + content_line


# ─────────────────────────────── Main ─────────────────────────────────────


def main() -> None:
    parser = argparse.ArgumentParser(
        description="File tree generator with gitignore support",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
Examples:
  %(prog)s                          # Scan current directory
  %(prog)s ./src -o tree.txt        # Scan ./src, write to tree.txt
  %(prog)s --max-depth 3            # Limit depth to 3 levels
  %(prog)s --max-lines 20           # Show only 20 lines per file
  %(prog)s -v                       # Verbose logging
  %(prog)s --no-gitignore           # Ignore all .gitignore files
        """,
    )
    parser.add_argument(
        "directory", nargs="?", default=".", help="Root directory to scan"
    )
    parser.add_argument("-o", "--output", default="file_tree.txt", help="Output file")
    parser.add_argument(
        "--max-depth", type=int, default=None, help="Maximum directory depth"
    )
    parser.add_argument(
        "--max-lines", type=int, default=50, help="Max lines to show per file"
    )
    parser.add_argument(
        "--no-gitignore", action="store_true", help="Disable .gitignore processing"
    )
    parser.add_argument(
        "-v", "--verbose", action="store_true", help="Enable debug logging"
    )

    args = parser.parse_args()
    setup_logging(logging.DEBUG if args.verbose else logging.INFO)

    root = Path(args.directory).resolve()
    if not root.is_dir():
        logger.error(f"Not a directory: {root}")
        sys.exit(1)

    checker = GitignoreChecker(root)
    if args.no_gitignore:
        # Disable by making all paths return empty rules
        checker._cache = {d: [] for d in checker._cache}
        # Also override _load to always return empty
        checker._load = lambda d: []
        logger.info("Gitignore processing disabled")

    try:
        with open(args.output, "w", encoding="utf-8") as f:
            # Print root
            f.write(root.name + "/\n")

            # Print tree
            for line in build_tree_lines(
                root, checker, max_lines=args.max_lines, max_depth=args.max_depth
            ):
                f.write(line + "\n")

        logger.info(f"Output written to: {args.output}")
    except OSError as e:
        logger.error(f"Failed to write output: {e}")
        sys.exit(1)


if __name__ == "__main__":
    main()