I want to aggregate Firestore data.

2023-07-09

• I would like to aggregate Firestore data for ChatGPT for middle and high school students.

• Read Firestore data in a local script

I tried to read the data, but couldn’t.

• I did db.collection('users').get() but snapshot.size is zero
• I asked what caused it.
  • Several causes were mentioned, check from above.
  • I thought the rules were wrong.” I was told, so I put up the rules and asked him to check them.
    • How do I allow access to Firestore from my service account?

I couldn’t read the rules after I changed them.

• I created the code to get one specific message, and it was done.
• But db.collection('users').get() but snapshot.size is zero

Thinking again, I realized, “Even if I grant service accounts the same access rights as normal users, I can’t get a list of users.

• snapshot.size is zero. I just noticed that the rule deny traversal. Fix it
• allow list: if request.auth.token.firebase.sign_in_provider == "null";

Still no luck, I asked why the phenomenon of being able to get the terminal object but not being able to traverse the parent occurs.

• No user document: When you fetch a nested sub-collection document directly (as in code A), Firestore doesn’t need the parent document to exist. In other words, even if there’s no document at users/{userId}, you can still fetch a document at users/{userId}/rooms/{roomId}/messages/{messageId}.
• HF8NVT*MTY4ODgyODA1My4xNi4xLjE2ODg4MzM2NDguMC4wLjA.#non-existent_ancestor_documents Managing Cloud Firestore in Firebase console

• A document can exist even if the ancestor does not exist.

• This…

How do I enumerate descendant documents when no ancestor document exists?

• How to get all /users/<user_id>/rooms/<room_id> when /users/<user_id> is not exists.
• There is a way to fetch all rooms from all users using a Firestore feature called Collection Group Queries.
  • db.collectionGroup('rooms').get()
  • It’s done.

How do you know which user the room belongs to?

• Given doc, how can I see its parent <user_id>
• doc.ref.parent.parent.id

All that’s left is to tally the totals! And then it’s over!

---

This page is auto-translated from /nishio/Firestoreのデータを集計したい using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.