feat: Posted-Anniversary Dedup Store

tests/test_run_logging.py

@@ -30,10 +30,9 @@ def _run_lines(buf: io.StringIO) -> list[dict]:
 
 
 def _seed_state(data_dir: Path, ids: list[str]) -> None:
-    from tenbackward.state import save_posted
+    from tenbackward.state import mark_posted_many
 
-    state = {pid: {"posted_at": "2024-01-01T00:00:00+00:00"} for pid in ids}
-    save_posted(data_dir, state)
+    mark_posted_many(list(ids), data_dir)
 
 
 def test_run_emits_one_info_summary_on_success(env_setup, data_dir, capture_logger, monkeypatch) -> None:

tests/test_state.py

@@ -1,31 +1,167 @@
 from __future__ import annotations
 
+import io
+import json
+import logging
+import os
 from pathlib import Path
 
-from tenbackward.state import load_posted, posted_path, save_posted
+from tenbackward.logging_setup import JsonFormatter
+from tenbackward.state import (
+    PostedStore,
+    is_posted,
+    load_posted,
+    mark_posted,
+    mark_posted_many,
+    posted_path,
+)
 
 
-def test_load_posted_creates_empty_when_missing(tmp_path: Path) -> None:
-    state = load_posted(tmp_path)
-    assert state == {}
+def _store(tmp_path: Path) -> PostedStore:
+    return PostedStore(tmp_path)
 
 
-def test_round_trip_persists(tmp_path: Path) -> None:
-    state = {"post-1": {"posted_at": "2024-01-01T00:00:00Z"}}
-    save_posted(tmp_path, state)
+def test_load_creates_empty_file_when_missing(tmp_path: Path) -> None:
+    store = _store(tmp_path)
+    result = store.load()
 
+    assert result == []
     assert posted_path(tmp_path).exists()
-    again = load_posted(tmp_path)
-    assert again == state
+    document = json.loads(posted_path(tmp_path).read_text(encoding="utf-8"))
+    assert document == {"posted": []}
 
 
-def test_load_posted_handles_corrupt_file(tmp_path: Path) -> None:
+def test_load_returns_empty_when_file_missing_no_crash(tmp_path: Path) -> None:
+    assert _store(tmp_path).load() == []
+
+
+def test_load_warns_and_returns_empty_on_malformed_json(
+    tmp_path: Path,
+) -> None:
+    buf = io.StringIO()
+    handler = logging.StreamHandler(buf)
+    handler.setFormatter(JsonFormatter())
+    logger = logging.getLogger("tenbackward")
+    original_handlers = list(logger.handlers)
+    original_propagate = logger.propagate
+    logger.handlers = [handler]
+    logger.setLevel(logging.WARNING)
+    logger.propagate = False
+    try:
+        posted_path(tmp_path).parent.mkdir(parents=True, exist_ok=True)
+        posted_path(tmp_path).write_text("not-json", encoding="utf-8")
+        result = _store(tmp_path).load()
+    finally:
+        logger.handlers = original_handlers
+        logger.propagate = original_propagate
+
+    assert result == []
+    lines = [
+        json.loads(line) for line in buf.getvalue().splitlines() if line.strip()
+    ]
+    events = [line.get("event") for line in lines]
+    assert "posted_store_corrupt" in events
+
+
+def test_mark_posted_writes_relative_path_to_file(tmp_path: Path) -> None:
+    _store(tmp_path).mark_posted("2014/2014-08-04-foo.md")
+
+    document = json.loads(posted_path(tmp_path).read_text(encoding="utf-8"))
+    assert document == {"posted": ["2014/2014-08-04-foo.md"]}
+
+
+def test_is_posted_round_trip(tmp_path: Path) -> None:
+    store = _store(tmp_path)
+    store.mark_posted("2014/2014-08-04-foo.md")
+
+    assert store.is_posted("2014/2014-08-04-foo.md") is True
+    assert store.is_posted("2015/2015-01-01-bar.md") is False
+
+
+def test_mark_posted_is_idempotent(tmp_path: Path) -> None:
+    store = _store(tmp_path)
+    first = store.mark_posted("2014/2014-08-04-foo.md")
+    second = store.mark_posted("2014/2014-08-04-foo.md")
+
+    assert first is True
+    assert second is False
+
+    document = json.loads(posted_path(tmp_path).read_text(encoding="utf-8"))
+    assert document == {"posted": ["2014/2014-08-04-foo.md"]}
+
+
+def test_mark_posted_many_persists_in_one_write(
+    tmp_path: Path, monkeypatch
+) -> None:
+    store = _store(tmp_path)
+    replaces: list[tuple[object, object]] = []
+    real_replace = os.replace
+
+    def counting_replace(src, dst) -> None:
+        replaces.append((src, dst))
+        real_replace(src, dst)
+
+    monkeypatch.setattr("tenbackward.state.os.replace", counting_replace)
+
+    added = store.mark_posted_many(
+        ["2014/2014-08-04-foo.md", "2015/2015-01-01-bar.md"]
+    )
+
+    assert added == ["2014/2014-08-04-foo.md", "2015/2015-01-01-bar.md"]
+    assert len(replaces) == 1
+    assert Path(replaces[0][1]) == posted_path(tmp_path)
+
+
+def test_mark_posted_leaves_no_temp_files(tmp_path: Path) -> None:
+    _store(tmp_path).mark_posted("2014/2014-08-04-foo.md")
+
+    leftovers = [
+        p for p in tmp_path.iterdir() if p.name.startswith("posted.json.tmp.")
+    ]
+    assert leftovers == []
+
+
+def test_mark_posted_many_against_existing_is_no_op(tmp_path: Path) -> None:
+    store = _store(tmp_path)
+    store.mark_posted("2014/2014-08-04-foo.md")
+
+    added = store.mark_posted_many(
+        ["2014/2014-08-04-foo.md", "2015/2015-01-01-bar.md"]
+    )
+
+    assert added == ["2015/2015-01-01-bar.md"]
+    document = json.loads(posted_path(tmp_path).read_text(encoding="utf-8"))
+    assert document == {
+        "posted": ["2014/2014-08-04-foo.md", "2015/2015-01-01-bar.md"]
+    }
+
+
+def test_posted_path_defaults_via_DATA_DIR(
+    monkeypatch, tmp_path: Path
+) -> None:
+    monkeypatch.setenv("DATA_DIR", str(tmp_path))
+    assert posted_path(None) == tmp_path / "posted.json"
+
+
+def test_load_filters_non_string_entries(tmp_path: Path) -> None:
     posted_path(tmp_path).parent.mkdir(parents=True, exist_ok=True)
-    posted_path(tmp_path).write_text("not-json")
-    assert load_posted(tmp_path) == {}
+    posted_path(tmp_path).write_text(
+        json.dumps({"posted": ["good", 42, None, "also-good"]}),
+        encoding="utf-8",
+    )
+
+    assert _store(tmp_path).load() == ["good", "also-good"]
 
 
-def test_save_posted_creates_parent_dirs(tmp_path: Path) -> None:
-    nested = tmp_path / "deep" / "data"
-    save_posted(nested, {"x": 1})
-    assert posted_path(nested).exists()
+def test_module_helpers_round_trip(tmp_path: Path) -> None:
+    assert load_posted(tmp_path) == []
+    assert is_posted("2014/2014-08-04-foo.md", tmp_path) is False
+    assert mark_posted("2014/2014-08-04-foo.md", tmp_path) is True
+    added = mark_posted_many(
+        ["2014/2014-08-04-foo.md", "2015/2015-01-01-bar.md"], tmp_path
+    )
+    assert added == ["2015/2015-01-01-bar.md"]
+    assert load_posted(tmp_path) == [
+        "2014/2014-08-04-foo.md",
+        "2015/2015-01-01-bar.md",
+    ]