alembic/versions/0028_lift_standalone_tags.py

@@ -0,0 +1,168 @@
+"""lift standalone #tags out of note bodies
+
+Revision ID: 0028
+Revises: 0027
+Create Date: 2026-08-26
+
+M311. A `#tag` was being shown twice — once as the text you typed and once as a chip —
+and with the chip moved to the top of the card the text is redundant. This removes it,
+but only from notes where the tag was standing on its own.
+
+## This migration rewrites note bodies
+
+The rule is deliberately narrow, and the same one `notes/tags.py:split_body_tags`
+applies from here on:
+
+  * A line containing nothing but tags and whitespace is REMOVED.
+  * Every other line is left exactly as written.
+
+So `#todo` on its own line goes, and `remember to call #mom tomorrow` does not. The
+looser reading — also stripping a trailing tag off a prose line — was rejected because
+the text does not say which kind it is: `buy milk #grocery` is filing, `remember to
+call #mom` is the sentence's object, and lifting the second leaves "remember to call".
+Rewriting somebody's words to save a duplicate chip is a bad trade, and a migration is
+the worst possible place to make it.
+
+Two guards, both of which cost a note nothing:
+
+  * A line inside a ``` fence is never touched. A `#tag` there is a shell comment in a
+    snippet somebody pasted, and deleting it would eat a line of their example.
+  * A note that is NOTHING but tags keeps its text. Lifting would leave a blank card,
+    which is worse than the duplication this fixes.
+
+## The label rows have to graduate in the same transaction
+
+A `via_tag` row means "this label is backed by text still in the body". Once the text
+is gone that is false, and leaving it true is not cosmetic: `_lift_and_reconcile_tags`
+detaches any `via_tag` row it cannot find a `#tag` for, so the note would lose the tag
+on its very next save. The flip to `via_tag = false` is what makes the label the record
+instead — and what makes the chip's × appear in both editors, which is now the only way
+to remove a tag whose text no longer exists.
+
+## The transform is inlined, like 0027's
+
+`split_body_tags` is deliberately NOT imported. A migration has to keep producing what
+it produced the day it ran; if the app's rule is ever loosened, this file must not
+loosen with it and start eating prose it previously left alone.
+
+`_display_title` is inlined for the same reason, and is only recomputed for a note whose
+body actually moved — a note named after a `#todo` line needs a new name, and reading it
+from the app would couple this migration to a rule that has already changed once (M13).
+
+## `updated_at` is left alone, and that is load-bearing
+
+Raw SQL, so SQLAlchemy's `onupdate` never fires. A client holding an UNPUSHED body edit
+keeps the newer `updated_at`, so when it pulls the migrated note last-write-wins keeps
+its edit instead of the migration silently winning.
+
+The `sync_revision` trigger (migration 0015) does fire, so every rewritten note becomes
+pullable once and clients converge on the server's text. That is wanted here: unlike
+0027, the clients do NOT yet apply this rule locally, so the server's copy is the only
+correct one until they do.
+
+## The downgrade is not a true inverse, and says so
+
+It cannot be. Nothing distinguishes a `#todo` line this migration deleted from one that
+was never there, and putting one back would be guessing at where in the note it went.
+
+Nothing is lost, though, which is why that is acceptable: the tag still exists as a
+label on the note, and the chip still shows it. What a downgrade cannot restore is the
+DUPLICATE — which is the thing this migration set out to remove. Rolling the rows back
+to `via_tag = true` would be actively harmful: the text that flag claims to be backed by
+is gone, so the next save would detach the label and lose the tag for real. So the
+downgrade leaves both alone. The real rollback is a database restore.
+"""
+import re
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = "0028"
+down_revision = "0027"
+branch_labels = None
+depends_on = None
+
+# Frozen copies. See "The transform is inlined" above — these must not follow the app.
+_TAG_RE = re.compile(r"(?:^|(?<=\s))#(\w[\w-]*)")
+_FENCE_RE = re.compile(r"^\s*(?:```|~~~)")
+_TASK_RE = re.compile(r"^(?P<indent>\s*)(?P<bullet>[-*]) +\[(?P<mark>[ xX])\](?: +(?P<text>.*))?$")
+_DISPLAY_TITLE_CAP = 200
+
+
+def _is_tag(name: str) -> bool:
+    """A tag must contain a letter, so #2024 and #_ are not tags — and a line holding
+    only those is therefore not a tag-only line and is left alone."""
+    return any(c.isalpha() for c in name)
+
+
+def _split(body: str) -> tuple[list[str], str]:
+    """(standalone tag names, body with their lines removed)."""
+    standalone: list[str] = []
+    kept: list[str] = []
+    in_fence = False
+    for line in body.split("\n"):
+        if _FENCE_RE.match(line):
+            in_fence = not in_fence
+            kept.append(line)
+            continue
+        matches = [m for m in _TAG_RE.finditer(line) if _is_tag(m.group(1))]
+        remainder = line
+        for m in reversed(matches):
+            remainder = remainder[: m.start()] + remainder[m.end() :]
+        if in_fence or not matches or remainder.strip():
+            kept.append(line)
+        else:
+            standalone.extend(m.group(1) for m in matches)
+    lifted = re.sub(r"\n{3,}", "\n\n", "\n".join(kept)).strip("\n")
+    if body.strip() and not lifted.strip():
+        return [], body  # nothing but tags: keep the note readable
+    # A tag still written in prose somewhere keeps its text, so it stays derived.
+    still_in_prose = {m.group(1).lower() for m in _TAG_RE.finditer(lifted) if _is_tag(m.group(1))}
+    return [n for n in standalone if n.lower() not in still_in_prose], lifted
+
+
+def _display_title(body: str) -> str:
+    for line in body.splitlines():
+        stripped = line.strip()
+        match = _TASK_RE.match(stripped)
+        text = (match.group("text") or "") if match else stripped
+        text = text.strip()
+        if text:
+            return text[:_DISPLAY_TITLE_CAP]
+    return ""
+
+
+def upgrade():
+    bind = op.get_bind()
+    rows = bind.execute(sa.text("SELECT id, body FROM notes WHERE body LIKE '%#%'")).fetchall()
+
+    flip = sa.text(
+        "UPDATE note_labels nl SET via_tag = false "
+        "FROM labels l "
+        "WHERE nl.label_id = l.id AND nl.note_id = :nid AND nl.via_tag = true "
+        "AND lower(l.name) IN :names"
+    ).bindparams(sa.bindparam("names", expanding=True))
+
+    for note_id, body in rows:
+        if not body:
+            continue
+        standalone, lifted = _split(body)
+        if lifted != body:
+            bind.execute(
+                sa.text("UPDATE notes SET body = :body, display_title = :title WHERE id = :id"),
+                {"body": lifted, "title": _display_title(lifted), "id": note_id},
+            )
+        # Even when the body did not move, a tag can be standalone only in the sense
+        # that its line was already removed by an earlier pass — so the flip is driven
+        # by the tag list, not by whether the text changed.
+        if standalone:
+            bind.execute(flip, {"nid": note_id, "names": [n.lower() for n in standalone]})
+
+
+def downgrade():
+    """Deliberately empty — see the module docstring.
+
+    Restoring the deleted lines would be guessing, and flipping the rows back to
+    `via_tag = true` would be worse than doing nothing: the text that flag claims backs
+    them is gone, so the next save would detach the label and lose the tag for real.
+    """

tests/test_notes.py

@@ -220,6 +220,50 @@ def test_split_body_tags_keeps_a_tag_derived_when_prose_still_carries_it():
     assert body == "remember the #todo list"
 
 
+def test_migration_0028_lifts_exactly_what_the_app_lifts_today():
+    """The 0028 data migration rewrites note bodies, and that is not undoable.
+
+    It carries its OWN frozen copy of the rule rather than importing
+    `split_body_tags`, on 0027's principle that a migration must keep producing what
+    it produced the day it ran. This does not assert the two agree — they are allowed
+    to diverge later, which is the entire point of freezing one. It pins the frozen
+    copy against fixed expectations, so nobody can "tidy" it into eating prose.
+    """
+    import importlib.util
+    from pathlib import Path
+
+    path = Path(__file__).resolve().parents[1] / "alembic" / "versions" / "0028_lift_standalone_tags.py"
+    spec = importlib.util.spec_from_file_location("migration_0028", path)
+    mod = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(mod)
+
+    # Lifted: the tag was the whole line.
+    assert mod._split("#todo\nreorganize the homepage") == (["todo"], "reorganize the homepage")
+    assert mod._split("needs a tauri app\n#todo") == (["todo"], "needs a tauri app")
+    assert mod._split("#todo #work\nreal text") == (["todo", "work"], "real text")
+    assert mod._split("foo\n\n#todo\n\nbar") == (["todo"], "foo\n\nbar")
+
+    # Untouched: prose. Getting any of these wrong destroys somebody's words.
+    for prose in ("remember to call #mom tomorrow", "buy milk #grocery", "#2024\nreal"):
+        assert mod._split(prose) == ([], prose), prose
+
+    # Untouched: a tag inside a fence is a shell comment in somebody's snippet.
+    fenced = "code:\n```\n#!/bin/sh\n#deploy\n```\ndone"
+    assert mod._split(fenced) == ([], fenced)
+
+    # Untouched: a note that is nothing but tags would be blanked.
+    assert mod._split("#todo") == ([], "#todo")
+
+    # Not flipped: the tag is still written in prose, so its text still backs it and
+    # it must stay derived — flipping it would be claiming otherwise.
+    assert mod._split("#todo\nremember the #todo list") == ([], "remember the #todo list")
+
+    # The name has to move with the body, or a note is titled after a deleted line.
+    assert mod._display_title("reorganize the homepage") == "reorganize the homepage"
+    assert mod._display_title("- [ ] milk\n- [ ] eggs") == "milk"
+    assert mod._display_title("") == ""
+
+
 def test_parse_tags():
     assert parse_tags("buy milk #groceries and #to-do now") == ["groceries", "to-do"]
     # case-insensitive dedup, first spelling wins