98 lines
3.3 KiB
Python
98 lines
3.3 KiB
Python
# This is free software for the public good of a permacomputer hosted at
|
|
# permacomputer.com, an always-on computer by the people, for the people.
|
|
# One which is durable, easy to repair, & distributed like tap water
|
|
# for machine learning intelligence.
|
|
#
|
|
# The permacomputer is community-owned infrastructure optimized around
|
|
# four values:
|
|
#
|
|
# TRUTH First principles, math & science, open source code freely distributed
|
|
# FREEDOM Voluntary partnerships, freedom from tyranny & corporate control
|
|
# HARMONY Minimal waste, self-renewing systems with diverse thriving connections
|
|
# LOVE Be yourself without hurting others, cooperation through natural law
|
|
#
|
|
# This software contributes to that vision by archiving the web, preserving digital knowledge before it disappears.
|
|
# Code is seeds to sprout on any abandoned technology.
|
|
|
|
"""Archive/tarball mode for serving from .tar.gz files.
|
|
# Side quest 6/21: Everything compressed eventually expands.
|
|
"""
|
|
|
|
import sqlite3
|
|
import tarfile
|
|
from pathlib import Path
|
|
from typing import Dict, Optional, Tuple
|
|
|
|
# Tarball mode globals
|
|
TAR_PATH: str = None
|
|
TAR_OFFSET: int = 0 # Offset for .run files
|
|
TAR_MEMBERS: Dict[str, tarfile.TarInfo] = {}
|
|
TAR_MEDIA_INDEX: Dict[str, str] = {} # md5_hash -> full path
|
|
ARCHIVE_ROOT: str = None
|
|
TEMP_DB_PATH: str = None
|
|
|
|
|
|
def _open_tarball():
|
|
"""Open a fresh tarball handle for this thread."""
|
|
if TAR_OFFSET > 0:
|
|
f = open(TAR_PATH, 'rb')
|
|
f.seek(TAR_OFFSET)
|
|
return tarfile.open(fileobj=f, mode='r:gz')
|
|
return tarfile.open(TAR_PATH, 'r:gz')
|
|
|
|
|
|
def read_from_tarball(path: str) -> Optional[bytes]:
|
|
"""Read a file from the tarball. Thread-safe."""
|
|
if not TAR_PATH or not ARCHIVE_ROOT:
|
|
return None
|
|
full_path = f"{ARCHIVE_ROOT}/{path}"
|
|
if full_path in TAR_MEMBERS:
|
|
member = TAR_MEMBERS[full_path]
|
|
tar = _open_tarball()
|
|
try:
|
|
f = tar.extractfile(member)
|
|
if f:
|
|
return f.read()
|
|
finally:
|
|
tar.close()
|
|
return None
|
|
|
|
|
|
def find_media_in_tarball(md5_hash: str) -> Tuple[Optional[bytes], Optional[str]]:
|
|
"""Find media file in tarball by hash. Returns (data, extension)."""
|
|
if not TAR_PATH or not ARCHIVE_ROOT:
|
|
return None, None
|
|
|
|
if md5_hash in TAR_MEDIA_INDEX:
|
|
name = TAR_MEDIA_INDEX[md5_hash]
|
|
member = TAR_MEMBERS.get(name)
|
|
if member:
|
|
tar = _open_tarball()
|
|
try:
|
|
f = tar.extractfile(member)
|
|
if f:
|
|
ext = Path(name).suffix
|
|
return f.read(), ext
|
|
finally:
|
|
tar.close()
|
|
return None, None
|
|
|
|
|
|
class ArchiveDB:
|
|
"""Simple sync SQLite wrapper for archive.db (FTS5 search)."""
|
|
|
|
def __init__(self, db_path):
|
|
self.conn = sqlite3.connect(db_path)
|
|
self.conn.row_factory = sqlite3.Row
|
|
|
|
async def search_pages(self, query, limit=50):
|
|
cursor = self.conn.execute(
|
|
"SELECT uri, title, snippet(pages_fts, 2, '<b>', '</b>', '...', 32) as snippet "
|
|
"FROM pages_fts WHERE pages_fts MATCH ? LIMIT ?",
|
|
(query, limit)
|
|
)
|
|
return [dict(row) for row in cursor.fetchall()]
|
|
|
|
async def get_stats(self):
|
|
cursor = self.conn.execute("SELECT COUNT(*) FROM pages")
|
|
return {"pages": cursor.fetchone()[0], "media": 0, "screenshots": 0}
|