fix: sanitize foreign schemas (#1058)

Arrow-js uses brittle `instanceof` checks throughout the code base.
These fail unless the library instance that produced the object matches
exactly the same instance the vectordb is using. At a minimum, this
means that a user using arrow version 15 (or any version that doesn't
match exactly the version that vectordb is using) will get strange
errors when they try and use vectordb.

However, there are even cases where the versions can be perfectly
identical, and the instanceof check still fails. One such example is
when using `vite` (e.g. https://github.com/vitejs/vite/issues/3910)

This PR solves the problem in a rather brute force, but workable,
fashion. If we encounter a schema that does not pass the `instanceof`
check then we will attempt to sanitize that schema by traversing the
object and, if it has all the correct properties, constructing an
appropriate `Schema` instance via deep cloning.
This commit is contained in:
Weston Pace
2024-03-04 13:06:36 -08:00
parent 785ecfa037
commit c60a193767
11 changed files with 1241 additions and 42 deletions

View File

@@ -23,6 +23,7 @@
"@types/tmp": "^0.2.6",
"@typescript-eslint/eslint-plugin": "^6.19.0",
"@typescript-eslint/parser": "^6.19.0",
"apache-arrow-old": "npm:apache-arrow@13.0.0",
"eslint": "^8.57.0",
"eslint-config-prettier": "^9.1.0",
"jest": "^29.7.0",
@@ -52,7 +53,6 @@
"version": "1.1.1",
"resolved": "https://registry.npmjs.org/@75lb/deep-merge/-/deep-merge-1.1.1.tgz",
"integrity": "sha512-xvgv6pkMGBA6GwdyJbNAnDmfAIR/DfWhrj9jgWh3TY7gRm3KO46x/GPjRg6wJ0nOepwqrNxFfojebh0Df4h4Tw==",
"peer": true,
"dependencies": {
"lodash.assignwith": "^4.2.0",
"typical": "^7.1.1"
@@ -65,7 +65,6 @@
"version": "7.1.1",
"resolved": "https://registry.npmjs.org/typical/-/typical-7.1.1.tgz",
"integrity": "sha512-T+tKVNs6Wu7IWiAce5BgMd7OZfNYUndHwc5MknN+UHOudi7sGZzuHdCadllRuqJ3fPtgFtIH9+lt9qRv6lmpfA==",
"peer": true,
"engines": {
"node": ">=12.17"
}
@@ -1437,8 +1436,7 @@
"node_modules/@types/command-line-usage": {
"version": "5.0.2",
"resolved": "https://registry.npmjs.org/@types/command-line-usage/-/command-line-usage-5.0.2.tgz",
"integrity": "sha512-n7RlEEJ+4x4TS7ZQddTmNSxP+zziEG0TNsMfiRIxcIVXt71ENJ9ojeXmGO3wPoTdn7pJcU2xc3CJYMktNT6DPg==",
"peer": true
"integrity": "sha512-n7RlEEJ+4x4TS7ZQddTmNSxP+zziEG0TNsMfiRIxcIVXt71ENJ9ojeXmGO3wPoTdn7pJcU2xc3CJYMktNT6DPg=="
},
"node_modules/@types/graceful-fs": {
"version": "4.1.9",
@@ -1507,6 +1505,12 @@
"form-data": "^4.0.0"
}
},
"node_modules/@types/pad-left": {
"version": "2.1.1",
"resolved": "https://registry.npmjs.org/@types/pad-left/-/pad-left-2.1.1.tgz",
"integrity": "sha512-Xd22WCRBydkGSApl5Bw0PhAOHKSVjNL3E3AwzKaps96IMraPqy5BvZIsBVK6JLwdybUzjHnuWVwpDd0JjTfHXA==",
"dev": true
},
"node_modules/@types/semver": {
"version": "7.5.6",
"resolved": "https://registry.npmjs.org/@types/semver/-/semver-7.5.6.tgz",
@@ -1910,6 +1914,40 @@
"arrow2csv": "bin/arrow2csv.cjs"
}
},
"node_modules/apache-arrow-old": {
"name": "apache-arrow",
"version": "13.0.0",
"resolved": "https://registry.npmjs.org/apache-arrow/-/apache-arrow-13.0.0.tgz",
"integrity": "sha512-3gvCX0GDawWz6KFNC28p65U+zGh/LZ6ZNKWNu74N6CQlKzxeoWHpi4CgEQsgRSEMuyrIIXi1Ea2syja7dwcHvw==",
"dev": true,
"dependencies": {
"@types/command-line-args": "5.2.0",
"@types/command-line-usage": "5.0.2",
"@types/node": "20.3.0",
"@types/pad-left": "2.1.1",
"command-line-args": "5.2.1",
"command-line-usage": "7.0.1",
"flatbuffers": "23.5.26",
"json-bignum": "^0.0.3",
"pad-left": "^2.1.0",
"tslib": "^2.5.3"
},
"bin": {
"arrow2csv": "bin/arrow2csv.js"
}
},
"node_modules/apache-arrow-old/node_modules/@types/command-line-args": {
"version": "5.2.0",
"resolved": "https://registry.npmjs.org/@types/command-line-args/-/command-line-args-5.2.0.tgz",
"integrity": "sha512-UuKzKpJJ/Ief6ufIaIzr3A/0XnluX7RvFgwkV89Yzvm77wCh1kFaFmqN8XEnGcN62EuHdedQjEMb8mYxFLGPyA==",
"dev": true
},
"node_modules/apache-arrow-old/node_modules/@types/node": {
"version": "20.3.0",
"resolved": "https://registry.npmjs.org/@types/node/-/node-20.3.0.tgz",
"integrity": "sha512-cumHmIAf6On83X7yP+LrsEyUOf/YlociZelmpRYaGFydoaPdxdt80MAbu6vWerQT2COCp2nPvHdsbD7tHn/YlQ==",
"dev": true
},
"node_modules/argparse": {
"version": "1.0.10",
"resolved": "https://registry.npmjs.org/argparse/-/argparse-1.0.10.tgz",
@@ -1923,7 +1961,6 @@
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/array-back/-/array-back-3.1.0.tgz",
"integrity": "sha512-TkuxA4UCOvxuDK6NZYXCalszEzj+TLszyASooky+i742l9TqsOdYCMJJupxRic61hwquNtppB3hgcuq9SVSH1Q==",
"peer": true,
"engines": {
"node": ">=6"
}
@@ -2200,7 +2237,6 @@
"version": "0.4.0",
"resolved": "https://registry.npmjs.org/chalk-template/-/chalk-template-0.4.0.tgz",
"integrity": "sha512-/ghrgmhfY8RaSdeo43hNXxpoHAtxdbskUHjPpfqUWGttFgycUhYPGx3YZBCnUCvOa7Doivn1IZec3DEGFoMgLg==",
"peer": true,
"dependencies": {
"chalk": "^4.1.2"
},
@@ -2297,7 +2333,6 @@
"version": "5.2.1",
"resolved": "https://registry.npmjs.org/command-line-args/-/command-line-args-5.2.1.tgz",
"integrity": "sha512-H4UfQhZyakIjC74I9d34fGYDwk3XpSr17QhEd0Q3I9Xq1CETHo4Hcuo87WyWHpAF1aSLjLRf5lD9ZGX2qStUvg==",
"peer": true,
"dependencies": {
"array-back": "^3.1.0",
"find-replace": "^3.0.0",
@@ -2312,7 +2347,6 @@
"version": "7.0.1",
"resolved": "https://registry.npmjs.org/command-line-usage/-/command-line-usage-7.0.1.tgz",
"integrity": "sha512-NCyznE//MuTjwi3y84QVUGEOT+P5oto1e1Pk/jFPVdPPfsG03qpTIl3yw6etR+v73d0lXsoojRpvbru2sqePxQ==",
"peer": true,
"dependencies": {
"array-back": "^6.2.2",
"chalk-template": "^0.4.0",
@@ -2327,7 +2361,6 @@
"version": "6.2.2",
"resolved": "https://registry.npmjs.org/array-back/-/array-back-6.2.2.tgz",
"integrity": "sha512-gUAZ7HPyb4SJczXAMUXMGAvI976JoK3qEx9v1FTmeYuJj0IBiaKttG1ydtGKdkfqWkIkouke7nG8ufGy77+Cvw==",
"peer": true,
"engines": {
"node": ">=12.17"
}
@@ -2336,7 +2369,6 @@
"version": "7.1.1",
"resolved": "https://registry.npmjs.org/typical/-/typical-7.1.1.tgz",
"integrity": "sha512-T+tKVNs6Wu7IWiAce5BgMd7OZfNYUndHwc5MknN+UHOudi7sGZzuHdCadllRuqJ3fPtgFtIH9+lt9qRv6lmpfA==",
"peer": true,
"engines": {
"node": ">=12.17"
}
@@ -2872,7 +2904,6 @@
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/find-replace/-/find-replace-3.0.0.tgz",
"integrity": "sha512-6Tb2myMioCAgv5kfvP5/PkZZ/ntTpVK39fHY7WkWBgvbeE+VHd/tZuZ4mrC+bxh4cfOZeYKVPaJIZtZXV7GNCQ==",
"peer": true,
"dependencies": {
"array-back": "^3.0.1"
},
@@ -2913,8 +2944,7 @@
"node_modules/flatbuffers": {
"version": "23.5.26",
"resolved": "https://registry.npmjs.org/flatbuffers/-/flatbuffers-23.5.26.tgz",
"integrity": "sha512-vE+SI9vrJDwi1oETtTIFldC/o9GsVKRM+s6EL0nQgxXlYV1Vc4Tk30hj4xGICftInKQKj1F3up2n8UbIVobISQ==",
"peer": true
"integrity": "sha512-vE+SI9vrJDwi1oETtTIFldC/o9GsVKRM+s6EL0nQgxXlYV1Vc4Tk30hj4xGICftInKQKj1F3up2n8UbIVobISQ=="
},
"node_modules/flatted": {
"version": "3.2.9",
@@ -4158,7 +4188,6 @@
"version": "0.0.3",
"resolved": "https://registry.npmjs.org/json-bignum/-/json-bignum-0.0.3.tgz",
"integrity": "sha512-2WHyXj3OfHSgNyuzDbSxI1w2jgw5gkWSWhS7Qg4bWXx1nLk3jnbwfUeS0PSba3IzpTUWdHxBieELUzXRjQB2zg==",
"peer": true,
"engines": {
"node": ">=0.8"
}
@@ -4269,14 +4298,12 @@
"node_modules/lodash.assignwith": {
"version": "4.2.0",
"resolved": "https://registry.npmjs.org/lodash.assignwith/-/lodash.assignwith-4.2.0.tgz",
"integrity": "sha512-ZznplvbvtjK2gMvnQ1BR/zqPFZmS6jbK4p+6Up4xcRYA7yMIwxHCfbTcrYxXKzzqLsQ05eJPVznEW3tuwV7k1g==",
"peer": true
"integrity": "sha512-ZznplvbvtjK2gMvnQ1BR/zqPFZmS6jbK4p+6Up4xcRYA7yMIwxHCfbTcrYxXKzzqLsQ05eJPVznEW3tuwV7k1g=="
},
"node_modules/lodash.camelcase": {
"version": "4.3.0",
"resolved": "https://registry.npmjs.org/lodash.camelcase/-/lodash.camelcase-4.3.0.tgz",
"integrity": "sha512-TwuEnCnxbc3rAvhf/LbG7tJUDzhqXyFnv3dtzLOPgCG/hODL7WFnsbwktkD7yUV0RrreP/l1PALq/YSg6VvjlA==",
"peer": true
"integrity": "sha512-TwuEnCnxbc3rAvhf/LbG7tJUDzhqXyFnv3dtzLOPgCG/hODL7WFnsbwktkD7yUV0RrreP/l1PALq/YSg6VvjlA=="
},
"node_modules/lodash.memoize": {
"version": "4.1.2",
@@ -4588,6 +4615,18 @@
"node": ">=6"
}
},
"node_modules/pad-left": {
"version": "2.1.0",
"resolved": "https://registry.npmjs.org/pad-left/-/pad-left-2.1.0.tgz",
"integrity": "sha512-HJxs9K9AztdIQIAIa/OIazRAUW/L6B9hbQDxO4X07roW3eo9XqZc2ur9bn1StH9CnbbI9EgvejHQX7CBpCF1QA==",
"dev": true,
"dependencies": {
"repeat-string": "^1.5.4"
},
"engines": {
"node": ">=0.10.0"
}
},
"node_modules/parent-module": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/parent-module/-/parent-module-1.0.1.tgz",
@@ -4865,6 +4904,15 @@
"integrity": "sha512-xWGDIW6x921xtzPkhiULtthJHoJvBbF3q26fzloPCK0hsvxtPVelvftw3zjbHWSkR2km9Z+4uxbDDK/6Zw9B8w==",
"dev": true
},
"node_modules/repeat-string": {
"version": "1.6.1",
"resolved": "https://registry.npmjs.org/repeat-string/-/repeat-string-1.6.1.tgz",
"integrity": "sha512-PV0dzCYDNfRi1jCDbJzpW7jNNDRuCOG/jI5ctQcGKt/clZD+YcPS3yIlWuTJMmESC8aevCFmWJy5wjAFgNqN6w==",
"dev": true,
"engines": {
"node": ">=0.10"
}
},
"node_modules/require-directory": {
"version": "2.1.1",
"resolved": "https://registry.npmjs.org/require-directory/-/require-directory-2.1.1.tgz",
@@ -5088,7 +5136,6 @@
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/stream-read-all/-/stream-read-all-3.0.1.tgz",
"integrity": "sha512-EWZT9XOceBPlVJRrYcykW8jyRSZYbkb/0ZK36uLEmoWVO5gxBOnntNTseNzfREsqxqdfEGQrD8SXQ3QWbBmq8A==",
"peer": true,
"engines": {
"node": ">=10"
}
@@ -5180,7 +5227,6 @@
"version": "3.0.2",
"resolved": "https://registry.npmjs.org/table-layout/-/table-layout-3.0.2.tgz",
"integrity": "sha512-rpyNZYRw+/C+dYkcQ3Pr+rLxW4CfHpXjPDnG7lYhdRoUcZTUt+KEsX+94RGp/aVp/MQU35JCITv2T/beY4m+hw==",
"peer": true,
"dependencies": {
"@75lb/deep-merge": "^1.1.1",
"array-back": "^6.2.2",
@@ -5201,7 +5247,6 @@
"version": "6.2.2",
"resolved": "https://registry.npmjs.org/array-back/-/array-back-6.2.2.tgz",
"integrity": "sha512-gUAZ7HPyb4SJczXAMUXMGAvI976JoK3qEx9v1FTmeYuJj0IBiaKttG1ydtGKdkfqWkIkouke7nG8ufGy77+Cvw==",
"peer": true,
"engines": {
"node": ">=12.17"
}
@@ -5210,7 +5255,6 @@
"version": "7.1.1",
"resolved": "https://registry.npmjs.org/typical/-/typical-7.1.1.tgz",
"integrity": "sha512-T+tKVNs6Wu7IWiAce5BgMd7OZfNYUndHwc5MknN+UHOudi7sGZzuHdCadllRuqJ3fPtgFtIH9+lt9qRv6lmpfA==",
"peer": true,
"engines": {
"node": ">=12.17"
}
@@ -5335,8 +5379,7 @@
"node_modules/tslib": {
"version": "2.6.2",
"resolved": "https://registry.npmjs.org/tslib/-/tslib-2.6.2.tgz",
"integrity": "sha512-AEYxH93jGFPn/a2iVAwW87VuUIkR1FVUKB77NwMF7nBTDkDrrT/Hpt/IrCJ0QXhW27jTBDcf5ZY7w6RiqTMw2Q==",
"peer": true
"integrity": "sha512-AEYxH93jGFPn/a2iVAwW87VuUIkR1FVUKB77NwMF7nBTDkDrrT/Hpt/IrCJ0QXhW27jTBDcf5ZY7w6RiqTMw2Q=="
},
"node_modules/type-check": {
"version": "0.4.0",
@@ -5672,7 +5715,6 @@
"version": "4.0.0",
"resolved": "https://registry.npmjs.org/typical/-/typical-4.0.0.tgz",
"integrity": "sha512-VAH4IvQ7BDFYglMd7BPRDfLgxZZX4O4TFcRDA6EN5X7erNJJq+McIEp8np9aVtxrCJ6qx4GTYVfOWNjcqwZgRw==",
"peer": true,
"engines": {
"node": ">=8"
}
@@ -5819,7 +5861,6 @@
"version": "5.1.0",
"resolved": "https://registry.npmjs.org/wordwrapjs/-/wordwrapjs-5.1.0.tgz",
"integrity": "sha512-JNjcULU2e4KJwUNv6CHgI46UvDGitb6dGryHajXTDiLgg1/RiGoPSDw4kZfYnwGtEXf2ZMeIewDQgFGzkCB2Sg==",
"peer": true,
"engines": {
"node": ">=12.17"
}