Document Processor v2 (#442)

* wip: init refactor of document processor to JS

* add NodeJs PDF support

* wip: partity with python processor
feat: add pptx support

* fix: forgot files

* Remove python scripts totally

* wip:update docker to boot new collector

* add package.json support

* update dockerfile for new build

* update gitignore and linting

* add more protections on file lookup

* update package.json

* test build

* update docker commands to use cap-add=SYS_ADMIN so web scraper can run
update all scripts to reflect this
remove docker build for branch
This commit is contained in:
Timothy Carambat
2023-12-14 15:14:56 -08:00
committed by GitHub
parent 5f6a013139
commit 719521c307
69 changed files with 3682 additions and 1925 deletions

View File

@@ -9,10 +9,11 @@
"node": ">=18"
},
"scripts": {
"lint": "cd server && yarn lint && cd .. && cd frontend && yarn lint",
"setup": "cd server && yarn && cd ../frontend && yarn && cd .. && yarn setup:envs && yarn prisma:setup && echo \"Please run yarn dev:server and yarn dev:frontend in separate terminal tabs.\"",
"lint": "cd server && yarn lint && cd ../frontend && yarn lint && cd ../collector && yarn lint",
"setup": "cd server && yarn && cd ../collector && yarn && cd ../frontend && yarn && cd .. && yarn setup:envs && yarn prisma:setup && echo \"Please run yarn dev:server, yarn dev:collector, and yarn dev:frontend in separate terminal tabs.\"",
"setup:envs": "cp -n ./frontend/.env.example ./frontend/.env && cp -n ./server/.env.example ./server/.env.development && cp -n ./collector/.env.example ./collector/.env && cp -n ./docker/.env.example ./docker/.env && echo \"All ENV files copied!\n\"",
"dev:server": "cd server && yarn dev",
"dev:collector": "cd collector && yarn dev",
"dev:frontend": "cd frontend && yarn start",
"prisma:generate": "cd server && npx prisma generate",
"prisma:migrate": "cd server && npx prisma migrate dev --name init",