versioning/tests/test_units.py

import asyncio
from pathlib import PurePath

from versiond.db import Database
from versiond.diff import hunks, unified
from versiond.filters import Filters
from versiond.ingest import Coalescer, Repository
from versiond.store import BlobStore


def test_filters_paths():
    f = Filters()
    ok = ["app.py", "src/main.go", ".env", ".env.production", "Makefile", "pkg/package.json", ".gitignore",
          # user data: images, archives, databases, documents (backed up as raw files)
          "photos/vacation.jpg", "img/logo.png", "backup/site.tar.gz", "data/archive.zip",
          "app.db", "app.sqlite3", "report.pdf", "song.mp3", "clip.mp4"]
    for p in ok:
        assert f.path_reason(PurePath(p)) is None, p
    journals = ["app.db-wal", "app.db-shm", "app.sqlite-journal", "data/x-wal"]
    for p in journals:
        assert f.path_reason(PurePath(p)) == "database-journal", p
    rejected = {
        "node_modules/x/index.js": "ignored-directory",
        ".git/config": "ignored-directory",
        "src/__pycache__/a.cpython-312.pyc": "ignored-directory",
        "a.pyc": "ignored-extension",
        ".bashrc_local": "hidden-file",
        "notes.txt~": "temporary-file",
        "main.py.swp": "ignored-extension",
        "draft.temp": "ignored-extension",
        "x.kate-swp": "ignored-extension",
        "~$lock.docx": "temporary-file",
        "#autosave#": "temporary-file",
        "venv/lib/x.py": "ignored-directory",
        "target/debug/build.rs": "ignored-directory",
        "4913": "temporary-file",
        "src/pkg.egg-info/PKG-INFO": "ignored-directory",
    }
    for p, reason in rejected.items():
        assert f.path_reason(PurePath(p)) == reason, p
    assert f.size_reason(10_485_760) is None
    assert f.size_reason(10_485_761) == "file-too-large"


def test_filter_patterns():
    f = Filters(patterns=("*.log", "secret/*"))
    assert f.path_reason(PurePath("x/debug.log")) == "ignored-pattern"
    assert f.path_reason(PurePath("secret/key.txt")) == "ignored-pattern"
    assert f.path_reason(PurePath("src/key.txt")) is None


def test_directory_patterns():
    f = Filters(patterns=("app/data/uploads",))
    assert f.skip_dir("uploads", "app/data/uploads")
    assert not f.skip_dir("uploads", "other/uploads")
    assert f.path_reason(PurePath("app/data/uploads/a/b.txt")) == "ignored-pattern"
    assert f.path_reason(PurePath("app/data/config.json")) is None


def test_diff_unified():
    a = b"one\ntwo\nthree\n"
    b = b"one\n2\nthree\nfour\n"
    out = unified(hunks(a, b), "a", "b")
    assert "-two\n+2\n" in out and "+four\n" in out
    assert hunks(b"x  y\n", b"x y\n", ignore_whitespace=True) == []


def _repo(tmp_path):
    db = Database(tmp_path / "index.sqlite")
    return Repository(db, BlobStore(tmp_path / "spool"), Filters())


def test_coalescer_keeps_first_and_last(tmp_path):
    repo = _repo(tmp_path)
    path = str(tmp_path / "f.py")

    async def run():
        c = Coalescer(repo, window=0.2, max_hold=1.0, per_hour=100)
        statuses = [c.submit(path, f"v{i}\n".encode(), "test", "edit")["status"] for i in range(6)]
        await asyncio.sleep(0.5)
        return statuses

    statuses = asyncio.run(run())
    assert statuses[0] == "committed"
    assert set(statuses[1:]) == {"coalesced"}
    file = repo.db.file_by_path(path)
    contents = [repo.blobs.get(v["blob_sha256"]) for v in reversed(repo.db.history(file["id"]))]
    assert contents == [b"v0\n", b"v5\n"]


def test_coalescer_rate_limit_keeps_newest(tmp_path):
    repo = _repo(tmp_path)
    path = str(tmp_path / "f.py")

    async def run():
        c = Coalescer(repo, window=0.05, max_hold=0.1, per_hour=2)
        c.submit(path, b"a", "t", "e")
        await asyncio.sleep(0.1)
        c.submit(path, b"b", "t", "e")
        await asyncio.sleep(0.2)
        status = c.submit(path, b"c", "t", "e")["status"]
        await asyncio.sleep(0.2)
        flushed = c.flush()
        return status, flushed

    status, flushed = asyncio.run(run())
    assert status == "coalesced"
    assert flushed == 1  # over the limit it waits, and shutdown still stores it
    file = repo.db.file_by_path(path)
    assert repo.blobs.get(repo.db.latest_version(file["id"])["blob_sha256"]) == b"c"


def test_dedupe_unchanged(tmp_path):
    repo = _repo(tmp_path)
    path = str(tmp_path / "f.py")
    assert repo.commit(path, b"x", "t", "e")["status"] == "committed"
    assert repo.commit(path, b"x", "t", "e")["status"] == "unchanged"