fix(plex): summaries and taglines are stored as plain text

A Plex agent can hand a summary over as HTML (<p> paragraphs, &aacute;
entities); the info page and the hover card showed the tags. One cleaner,
app/plex/plaintext.py, now runs on every summary and tagline the sync, the
Hungarian overlay and the rich-detail fetch store, and migration 0101 cleans
the rows written before through the same function. Paragraph breaks survive
as newlines, which the info page and the hover card now keep.
This commit is contained in:
2026-10-09 00:06:02 +02:00
parent 75f4efde98
commit 6dd82ef5e2
8 changed files with 216 additions and 8 deletions
@@ -0,0 +1,46 @@
"""Plex summaries and taglines as plain text
Revision ID: 0101_plex_text_plain
Revises: 0100_drop_plex_item_markers
Create Date: 2026-10-08
Some Plex agents write a summary as HTML (`<p>…</p>`, `&aacute;`), and the app showed the tags as
text. The sync now stores every summary and tagline through `plain_text` (app/plex/plaintext.py);
this cleans the rows it wrote before, through the same function, so nothing waits for a full resync.
"""
import sqlalchemy as sa
from alembic import op
from app.plex.plaintext import plain_text
revision: str = "0101_plex_text_plain"
down_revision: str | None = "0100_drop_plex_item_markers"
branch_labels: str | None = None
depends_on: str | None = None
_COLUMNS = {
"plex_items": ("summary", "summary_hu", "tagline", "tagline_hu"),
"plex_shows": ("summary", "summary_hu", "tagline", "tagline_hu"),
"plex_collections": ("summary",),
}
def upgrade() -> None:
conn = op.get_bind()
for table, columns in _COLUMNS.items():
for col in columns:
rows = conn.execute(
sa.text(f"SELECT id, {col} FROM {table} WHERE {col} ~ '[<&]'")
).fetchall()
updates = [
{"id": rid, "v": clean}
for rid, value in rows
if (clean := plain_text(value)) != value
]
if updates:
conn.execute(sa.text(f"UPDATE {table} SET {col} = :v WHERE id = :id"), updates)
def downgrade() -> None:
pass # the markup is not wanted back; the next sync would clean it again