Add Postgres store, path safety, and the crawl indexer

Store: crawl generations as the sync cursor. Diffs compare generations
on entity identity plus a content digest, never on upstream timestamps —
GET /course-rooms/{id}/board returns request time as updatedAt for most
elements, so a timestamp cursor would report every board as changed on
every crawl. Identity diffing also yields deletions, which no timestamp
scheme can. A per-course crawl carries the other courses' rows forward
so every completed generation is a complete picture and any two diff
directly; without that a partial crawl reads as a mass deletion.

FTS uses the german dictionary with weighted title/body, plus a pg_trgm
arm because stemming will not match "Datenschutz" inside
"Datenschutzgrundverordnung" and German compounds make that the common
case. file_texts is keyed by file record id and deliberately outlives
generations: records are immutable upstream, so text extracted once is
valid forever and a re-crawl of unchanged content costs nothing.

Store.open returns undefined instead of throwing when Postgres is
unreachable — the index is an accelerator, and a Pi that loses its
database should get slower, not broken.

core/paths.ts is the security boundary for the mirror. Course titles,
card titles and filenames are all user-supplied upstream, so this is
where a hostile name stops being text and becomes a path. Two bugs found
by its own tests: "///" produced "---" instead of falling back, and dot
runs survived mid-component. Now no ".." can survive anywhere, which
makes the invariant checkable rather than a claim about ordering.

Indexer coalesces concurrent refreshes onto one run and enforces a
minimum interval, since a full crawl is ~270 requests from an account
that looks like a student.

9 store tests against a real Postgres (mocks would test nothing here)
and 13 path tests; 47 total.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
2026-09-12 21:10:53 +02:00
parent 81dd633863
commit a18b526267
11 changed files with 1547 additions and 1 deletions

161
package-lock.json generated
View File

@@ -12,6 +12,7 @@
"exceljs": "^4.4.0",
"express": "^5.1.0",
"mammoth": "^1.11.0",
"pg": "^8.23.0",
"unpdf": "^1.3.2",
"unzipper": "^0.12.3",
"zod": "^3.25.76"
@@ -22,6 +23,7 @@
"devDependencies": {
"@types/express": "^5.0.3",
"@types/node": "^22.15.0",
"@types/pg": "^8.23.1",
"@types/unzipper": "^0.10.11",
"typescript": "^5.9.2"
},
@@ -185,6 +187,18 @@
"undici-types": "~6.21.0"
}
},
"node_modules/@types/pg": {
"version": "8.23.1",
"resolved": "https://registry.npmjs.org/@types/pg/-/pg-8.23.1.tgz",
"integrity": "sha512-fKVHpikPdg4GKks3JuLEhvwSyvwzF23hnabPy6DD8ljVbC7+6J5dQzdv4arV6jqq57djnMgs1HKBxX4P8aBI3A==",
"dev": true,
"license": "MIT",
"dependencies": {
"@types/node": "*",
"pg-protocol": "*",
"pg-types": "^2.2.0"
}
},
"node_modules/@types/qs": {
"version": "6.15.1",
"resolved": "https://registry.npmjs.org/@types/qs/-/qs-6.15.1.tgz",
@@ -1854,6 +1868,96 @@
"url": "https://opencollective.com/express"
}
},
"node_modules/pg": {
"version": "8.23.0",
"resolved": "https://registry.npmjs.org/pg/-/pg-8.23.0.tgz",
"integrity": "sha512-Ip2EQCngowJLGOfCwkFhPXU7/ljlhn6Rxlmy4XYfL2Y+vyRM59+8uR2xqRWKdYmbXmxCFOAmKxBuSUCdF34qLg==",
"license": "MIT",
"peer": true,
"dependencies": {
"pg-connection-string": "^2.14.0",
"pg-pool": "^3.14.0",
"pg-protocol": "^1.16.0",
"pg-types": "2.2.0",
"pgpass": "1.0.5"
},
"engines": {
"node": ">= 16.0.0"
},
"optionalDependencies": {
"pg-cloudflare": "^1.4.0"
},
"peerDependencies": {
"pg-native": ">=3.0.1"
},
"peerDependenciesMeta": {
"pg-native": {
"optional": true
}
}
},
"node_modules/pg-cloudflare": {
"version": "1.4.0",
"resolved": "https://registry.npmjs.org/pg-cloudflare/-/pg-cloudflare-1.4.0.tgz",
"integrity": "sha512-Vo7z/6rrQYxpNRylp4Tlob2elzbh+N/MOQbxFVWCxS7oEx6jF53GTJFxK2WWpKuBRkmiin4Mt+xofFDjx09R0A==",
"license": "MIT",
"optional": true
},
"node_modules/pg-connection-string": {
"version": "2.14.0",
"resolved": "https://registry.npmjs.org/pg-connection-string/-/pg-connection-string-2.14.0.tgz",
"integrity": "sha512-XwWDGcLRGCXAR8F/AM5bG7Q+A3Wm2s6QeEjlOKZLlH3UYcguiqCWKyWXVag5TLTIjR7oOJUY8kcADaZgWPyLeg==",
"license": "MIT"
},
"node_modules/pg-int8": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/pg-int8/-/pg-int8-1.0.1.tgz",
"integrity": "sha512-WCtabS6t3c8SkpDBUlb1kjOs7l66xsGdKpIPZsg4wR+B3+u9UAum2odSsF9tnvxg80h4ZxLWMy4pRjOsFIqQpw==",
"license": "ISC",
"engines": {
"node": ">=4.0.0"
}
},
"node_modules/pg-pool": {
"version": "3.14.0",
"resolved": "https://registry.npmjs.org/pg-pool/-/pg-pool-3.14.0.tgz",
"integrity": "sha512-gKtPkFdQPU3DksooVLi9LsjZxrsBUZIpa+7aVx+LV5pNh0KzP4Zleud2po+ConrxbuXGBJ6Hfer6hdgpIBpBaw==",
"license": "MIT",
"peerDependencies": {
"pg": ">=8.0"
}
},
"node_modules/pg-protocol": {
"version": "1.16.0",
"resolved": "https://registry.npmjs.org/pg-protocol/-/pg-protocol-1.16.0.tgz",
"integrity": "sha512-sILXutLVjCLjcDuOmvhX5e2Z4cS5qG/6Bu3VkpFwdf/633ElGLpEh9bgmuI5I4sqKqkifQiGyiCcx1HdtrK7tg==",
"license": "MIT"
},
"node_modules/pg-types": {
"version": "2.2.0",
"resolved": "https://registry.npmjs.org/pg-types/-/pg-types-2.2.0.tgz",
"integrity": "sha512-qTAAlrEsl8s4OiEQY69wDvcMIdQN6wdz5ojQiOy6YRMuynxenON0O5oCpJI6lshc6scgAY8qvJ2On/p+CXY0GA==",
"license": "MIT",
"dependencies": {
"pg-int8": "1.0.1",
"postgres-array": "~2.0.0",
"postgres-bytea": "~1.0.0",
"postgres-date": "~1.0.4",
"postgres-interval": "^1.1.0"
},
"engines": {
"node": ">=4"
}
},
"node_modules/pgpass": {
"version": "1.0.5",
"resolved": "https://registry.npmjs.org/pgpass/-/pgpass-1.0.5.tgz",
"integrity": "sha512-FdW9r/jQZhSeohs1Z3sI1yxFQNFvMcnmfuj4WBMUTxOrAyLMaTcE1aAMBiTlbMNaXvBCQuVi0R7hd8udDSP7ug==",
"license": "MIT",
"dependencies": {
"split2": "^4.1.0"
}
},
"node_modules/pkce-challenge": {
"version": "5.0.1",
"resolved": "https://registry.npmjs.org/pkce-challenge/-/pkce-challenge-5.0.1.tgz",
@@ -1863,6 +1967,45 @@
"node": ">=16.20.0"
}
},
"node_modules/postgres-array": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/postgres-array/-/postgres-array-2.0.0.tgz",
"integrity": "sha512-VpZrUqU5A69eQyW2c5CA1jtLecCsN2U/bD6VilrFDWq5+5UIEVO7nazS3TEcHf1zuPYO/sqGvUvW62g86RXZuA==",
"license": "MIT",
"engines": {
"node": ">=4"
}
},
"node_modules/postgres-bytea": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/postgres-bytea/-/postgres-bytea-1.0.1.tgz",
"integrity": "sha512-5+5HqXnsZPE65IJZSMkZtURARZelel2oXUEO8rH83VS/hxH5vv1uHquPg5wZs8yMAfdv971IU+kcPUczi7NVBQ==",
"license": "MIT",
"engines": {
"node": ">=0.10.0"
}
},
"node_modules/postgres-date": {
"version": "1.0.7",
"resolved": "https://registry.npmjs.org/postgres-date/-/postgres-date-1.0.7.tgz",
"integrity": "sha512-suDmjLVQg78nMK2UZ454hAG+OAW+HQPZ6n++TNDUX+L0+uUlLywnoxJKDou51Zm+zTCjrCl0Nq6J9C5hP9vK/Q==",
"license": "MIT",
"engines": {
"node": ">=0.10.0"
}
},
"node_modules/postgres-interval": {
"version": "1.2.0",
"resolved": "https://registry.npmjs.org/postgres-interval/-/postgres-interval-1.2.0.tgz",
"integrity": "sha512-9ZhXKM/rw350N1ovuWHbGxnGh/SNJ4cnxHiM0rxE4VN41wsg8P8zWn9hv/buK00RP4WvlOyr/RBDiptyxVbkZQ==",
"license": "MIT",
"dependencies": {
"xtend": "^4.0.0"
},
"engines": {
"node": ">=0.10.0"
}
},
"node_modules/process-nextick-args": {
"version": "2.0.1",
"resolved": "https://registry.npmjs.org/process-nextick-args/-/process-nextick-args-2.0.1.tgz",
@@ -2196,6 +2339,15 @@
"url": "https://github.com/sponsors/ljharb"
}
},
"node_modules/split2": {
"version": "4.2.0",
"resolved": "https://registry.npmjs.org/split2/-/split2-4.2.0.tgz",
"integrity": "sha512-UcjcJOWknrNkF6PLX83qcHM6KHgVKNkV62Y8a5uYDVv9ydGQVwAHMKqHdJje1VTWpljG0WYpCDhrCdAOYH4TWg==",
"license": "ISC",
"engines": {
"node": ">= 10.x"
}
},
"node_modules/sprintf-js": {
"version": "1.0.3",
"resolved": "https://registry.npmjs.org/sprintf-js/-/sprintf-js-1.0.3.tgz",
@@ -2436,6 +2588,15 @@
"integrity": "sha512-JZnDKK8B0RCDw84FNdDAIpZK+JuJw+s7Lz8nksI7SIuU3UXJJslUthsi+uWBUYOwPFwW7W7PRLRfUKpxjtjFCw==",
"license": "MIT"
},
"node_modules/xtend": {
"version": "4.0.2",
"resolved": "https://registry.npmjs.org/xtend/-/xtend-4.0.2.tgz",
"integrity": "sha512-LKYU1iAXJXUgAXn9URjiu+MWhyUXHsvfp7mcuYm9dSUKK0/CjtrUwFAxD82/mCWbtLsGjFIad0wIsod4zrTAEQ==",
"license": "MIT",
"engines": {
"node": ">=0.4"
}
},
"node_modules/zip-stream": {
"version": "4.1.1",
"resolved": "https://registry.npmjs.org/zip-stream/-/zip-stream-4.1.1.tgz",