Удалить документ со всеми вложенными коллекциями и вложенными вложенными коллекциями в Firestore

Я не знаю, насколько это полезно для вас, но протестируйте его и сравните время выполнения, которое я использую, из документации хранилища огня

  /** Delete a collection in batches to avoid out-of-memory errors.
     * Batch size may be tuned based on document size (atmost 1MB) and application requirements.

    */



 void deleteCollection(CollectionReference collection, int batchSize) {
      try {
        // retrieve a small batch of documents to avoid out-of-memory errors
        ApiFuture<QuerySnapshot> future = collection.limit(batchSize).get();
        int deleted = 0;
        // future.get() blocks on document retrieval
        List<QueryDocumentSnapshot> documents = future.get().getDocuments();
        for (QueryDocumentSnapshot document : documents) {
          document.getReference().delete();
          ++deleted;
        }
        if (deleted >= batchSize) {
          // retrieve and delete another batch
          deleteCollection(collection, batchSize);
        }
      } catch (Exception e) {
        System.err.println("Error deleting collection : " + e.getMessage());
      }
    }

Вы можете вызвать firebase.firestore().doc("whatever").set(), и это удалит все в этом документе.

Единственный способ, которым .set не стирает все, - это установить флаг merge на true.

См. Документация Firestore по добавлению данных

var cityRef = db.collection('cities').doc('BJ');

var setWithMerge = cityRef.set({
    capital: true
}, { merge: true });

К сожалению, ваш анализ верен, и действительно, этот вариант использования требует много церемоний. Согласно официальной документации, нет поддержки глубоких удалений в одном выстрелил в firestore ни через клиентские библиотеки, ни через rest-api, ни через инструмент cli.

cli имеет открытый исходный код, и его реализация находится здесь: https://github.com/firebase/firebase-tools/blob/master/src/firestore/delete.js. В основном они реализовали вариант 1. Вы описали в своем вопросе, так что вы можете почерпнуть оттуда немного вдохновения.

Оба варианта 1. и 2. далеки от идеальной ситуации, и чтобы сделать ваше решение на 100% надежным, вам нужно будет поддерживать очередь настойчивый с задачами удаления, так как любая ошибка в длительной процедуре оставит вашу систему в каком-то неопределенном состоянии. .

Я бы не рекомендовал использовать необработанный вариант 2, поскольку вызовы рекурсивных облачных функций могут очень легко выйти из строя - например, при достижении максимума. пределы.

Если ссылка изменилась, ниже полный источник https://github.com/firebase/firebase-tools/blob/master/src/firestore/delete.js:

"use strict";

var clc = require("cli-color");
var ProgressBar = require("progress");

var api = require("../api");
var firestore = require("../gcp/firestore");
var FirebaseError = require("../error");
var logger = require("../logger");
var utils = require("../utils");

/**
 * Construct a new Firestore delete operation.
 *
 * @constructor
 * @param {string} project the Firestore project ID.
 * @param {string} path path to a document or collection.
 * @param {boolean} options.recursive true if the delete should be recursive.
 * @param {boolean} options.shallow true if the delete should be shallow (non-recursive).
 * @param {boolean} options.allCollections true if the delete should universally remove all collections and docs.
 */
function FirestoreDelete(project, path, options) {
  this.project = project;
  this.path = path;
  this.recursive = Boolean(options.recursive);
  this.shallow = Boolean(options.shallow);
  this.allCollections = Boolean(options.allCollections);

  // Remove any leading or trailing slashes from the path
  if (this.path) {
    this.path = this.path.replace(/(^/+|/+$)/g, "");
  }

  this.isDocumentPath = this._isDocumentPath(this.path);
  this.isCollectionPath = this._isCollectionPath(this.path);

  this.allDescendants = this.recursive;
  this.parent = "projects/" + project + "/databases/(default)/documents";

  // When --all-collections is passed any other flags or arguments are ignored
  if (!options.allCollections) {
    this._validateOptions();
  }
}

/**
 * Validate all options, throwing an exception for any fatal errors.
 */
FirestoreDelete.prototype._validateOptions = function() {
  if (this.recursive && this.shallow) {
    throw new FirebaseError("Cannot pass recursive and shallow options together.");
  }

  if (this.isCollectionPath && !this.recursive && !this.shallow) {
    throw new FirebaseError("Must pass recursive or shallow option when deleting a collection.");
  }

  var pieces = this.path.split("/");

  if (pieces.length === 0) {
    throw new FirebaseError("Path length must be greater than zero.");
  }

  var hasEmptySegment = pieces.some(function(piece) {
    return piece.length === 0;
  });

  if (hasEmptySegment) {
    throw new FirebaseError("Path must not have any empty segments.");
  }
};

/**
 * Determine if a path points to a document.
 *
 * @param {string} path a path to a Firestore document or collection.
 * @return {boolean} true if the path points to a document, false
 * if it points to a collection.
 */
FirestoreDelete.prototype._isDocumentPath = function(path) {
  if (!path) {
    return false;
  }

  var pieces = path.split("/");
  return pieces.length % 2 === 0;
};

/**
 * Determine if a path points to a collection.
 *
 * @param {string} path a path to a Firestore document or collection.
 * @return {boolean} true if the path points to a collection, false
 * if it points to a document.
 */
FirestoreDelete.prototype._isCollectionPath = function(path) {
  if (!path) {
    return false;
  }

  return !this._isDocumentPath(path);
};

/**
 * Construct a StructuredQuery to find descendant documents of a collection.
 *
 * See:
 * https://firebase.google.com/docs/firestore/reference/rest/v1beta1/StructuredQuery
 *
 * @param {boolean} allDescendants true if subcollections should be included.
 * @param {number} batchSize maximum number of documents to target (limit).
 * @param {string=} startAfter document name to start after (optional).
 * @return {object} a StructuredQuery.
 */
FirestoreDelete.prototype._collectionDescendantsQuery = function(
  allDescendants,
  batchSize,
  startAfter
) {
  var nullChar = String.fromCharCode(0);

  var startAt = this.parent + "/" + this.path + "/" + nullChar;
  var endAt = this.parent + "/" + this.path + nullChar + "/" + nullChar;

  var where = {
    compositeFilter: {
      op: "AND",
      filters: [
        {
          fieldFilter: {
            field: {
              fieldPath: "__name__",
            },
            op: "GREATER_THAN_OR_EQUAL",
            value: {
              referenceValue: startAt,
            },
          },
        },
        {
          fieldFilter: {
            field: {
              fieldPath: "__name__",
            },
            op: "LESS_THAN",
            value: {
              referenceValue: endAt,
            },
          },
        },
      ],
    },
  };

  var query = {
    structuredQuery: {
      where: where,
      limit: batchSize,
      from: [
        {
          allDescendants: allDescendants,
        },
      ],
      select: {
        fields: [{ fieldPath: "__name__" }],
      },
      orderBy: [{ field: { fieldPath: "__name__" } }],
    },
  };

  if (startAfter) {
    query.structuredQuery.startAt = {
      values: [{ referenceValue: startAfter }],
      before: false,
    };
  }

  return query;
};

/**
 * Construct a StructuredQuery to find descendant documents of a document.
 * The document itself will not be included
 * among the results.
 *
 * See:
 * https://firebase.google.com/docs/firestore/reference/rest/v1beta1/StructuredQuery
 *
 * @param {boolean} allDescendants true if subcollections should be included.
 * @param {number} batchSize maximum number of documents to target (limit).
 * @param {string=} startAfter document name to start after (optional).
 * @return {object} a StructuredQuery.
 */
FirestoreDelete.prototype._docDescendantsQuery = function(allDescendants, batchSize, startAfter) {
  var query = {
    structuredQuery: {
      limit: batchSize,
      from: [
        {
          allDescendants: allDescendants,
        },
      ],
      select: {
        fields: [{ fieldPath: "__name__" }],
      },
      orderBy: [{ field: { fieldPath: "__name__" } }],
    },
  };

  if (startAfter) {
    query.structuredQuery.startAt = {
      values: [{ referenceValue: startAfter }],
      before: false,
    };
  }

  return query;
};

/**
 * Query for a batch of 'descendants' of a given path.
 *
 * For document format see:
 * https://firebase.google.com/docs/firestore/reference/rest/v1beta1/Document
 *
 * @param {boolean} allDescendants true if subcollections should be included,
 * @param {number} batchSize the maximum size of the batch.
 * @param {string=} startAfter the name of the document to start after (optional).
 * @return {Promise<object[]>} a promise for an array of documents.
 */
FirestoreDelete.prototype._getDescendantBatch = function(allDescendants, batchSize, startAfter) {
  var url;
  var body;
  if (this.isDocumentPath) {
    url = this.parent + "/" + this.path + ":runQuery";
    body = this._docDescendantsQuery(allDescendants, batchSize, startAfter);
  } else {
    url = this.parent + ":runQuery";
    body = this._collectionDescendantsQuery(allDescendants, batchSize, startAfter);
  }

  return api
    .request("POST", "/v1beta1/" + url, {
      auth: true,
      data: body,
      origin: api.firestoreOrigin,
    })
    .then(function(res) {
      // Return the 'document' property for each element in the response,
      // where it exists.
      return res.body
        .filter(function(x) {
          return x.document;
        })
        .map(function(x) {
          return x.document;
        });
    });
};

/**
 * Progress bar shared by the class.
 */
FirestoreDelete.progressBar = new ProgressBar("Deleted :current docs (:rate docs/s)", {
  total: Number.MAX_SAFE_INTEGER,
});

/**
 * Repeatedly query for descendants of a path and delete them in batches
 * until no documents remain.
 *
 * @return {Promise} a promise for the entire operation.
 */
FirestoreDelete.prototype._recursiveBatchDelete = function() {
  var self = this;

  // Tunable deletion parameters
  var readBatchSize = 7500;
  var deleteBatchSize = 250;
  var maxPendingDeletes = 15;
  var maxQueueSize = deleteBatchSize * maxPendingDeletes * 2;

  // All temporary variables for the deletion queue.
  var queue = [];
  var numPendingDeletes = 0;
  var pagesRemaining = true;
  var pageIncoming = false;
  var lastDocName;

  var failures = [];
  var retried = {};

  var queueLoop = function() {
    if (queue.length == 0 && numPendingDeletes == 0 && !pagesRemaining) {
      return true;
    }

    if (failures.length > 0) {
      logger.debug("Found " + failures.length + " failed deletes, failing.");
      return true;
    }

    if (queue.length <= maxQueueSize && pagesRemaining && !pageIncoming) {
      pageIncoming = true;

      self
        ._getDescendantBatch(self.allDescendants, readBatchSize, lastDocName)
        .then(function(docs) {
          pageIncoming = false;

          if (docs.length == 0) {
            pagesRemaining = false;
            return;
          }

          queue = queue.concat(docs);
          lastDocName = docs[docs.length - 1].name;
        })
        .catch(function(e) {
          logger.debug("Failed to fetch page after " + lastDocName, e);
          pageIncoming = false;
        });
    }

    if (numPendingDeletes > maxPendingDeletes) {
      return false;
    }

    if (queue.length == 0) {
      return false;
    }

    var toDelete = [];
    var numToDelete = Math.min(deleteBatchSize, queue.length);

    for (var i = 0; i < numToDelete; i++) {
      toDelete.push(queue.shift());
    }

    numPendingDeletes++;
    firestore
      .deleteDocuments(self.project, toDelete)
      .then(function(numDeleted) {
        FirestoreDelete.progressBar.tick(numDeleted);
        numPendingDeletes--;
      })
      .catch(function(e) {
        // For server errors, retry if the document has not yet been retried.
        if (e.status >= 500 && e.status < 600) {
          logger.debug("Server error deleting doc batch", e);

          // Retry each doc up to one time
          toDelete.forEach(function(doc) {
            if (retried[doc.name]) {
              logger.debug("Failed to delete doc " + doc.name + " multiple times.");
              failures.push(doc.name);
            } else {
              retried[doc.name] = true;
              queue.push(doc);
            }
          });
        } else {
          logger.debug("Fatal error deleting docs ", e);
          failures = failures.concat(toDelete);
        }

        numPendingDeletes--;
      });

    return false;
  };

  return new Promise(function(resolve, reject) {
    var intervalId = setInterval(function() {
      if (queueLoop()) {
        clearInterval(intervalId);

        if (failures.length == 0) {
          resolve();
        } else {
          reject("Failed to delete documents " + failures);
        }
      }
    }, 0);
  });
};

/**
 * Delete everything under a given path. If the path represents
 * a document the document is deleted and then all descendants
 * are deleted.
 *
 * @return {Promise} a promise for the entire operation.
 */
FirestoreDelete.prototype._deletePath = function() {
  var self = this;
  var initialDelete;
  if (this.isDocumentPath) {
    var doc = { name: this.parent + "/" + this.path };
    initialDelete = firestore.deleteDocument(doc).catch(function(err) {
      logger.debug("deletePath:initialDelete:error", err);
      if (self.allDescendants) {
        // On a recursive delete, we are insensitive to
        // failures of the initial delete
        return Promise.resolve();
      }

      // For a shallow delete, this error is fatal.
      return utils.reject("Unable to delete " + clc.cyan(this.path));
    });
  } else {
    initialDelete = Promise.resolve();
  }

  return initialDelete.then(function() {
    return self._recursiveBatchDelete();
  });
};

/**
 * Delete an entire database by finding and deleting each collection.
 *
 * @return {Promise} a promise for all of the operations combined.
 */
FirestoreDelete.prototype.deleteDatabase = function() {
  var self = this;
  return firestore
    .listCollectionIds(this.project)
    .catch(function(err) {
      logger.debug("deleteDatabase:listCollectionIds:error", err);
      return utils.reject("Unable to list collection IDs");
    })
    .then(function(collectionIds) {
      var promises = [];

      logger.info("Deleting the following collections: " + clc.cyan(collectionIds.join(", ")));

      for (var i = 0; i < collectionIds.length; i++) {
        var collectionId = collectionIds[i];
        var deleteOp = new FirestoreDelete(self.project, collectionId, {
          recursive: true,
        });

        promises.push(deleteOp.execute());
      }

      return Promise.all(promises);
    });
};

/**
 * Check if a path has any children. Useful for determining
 * if deleting a path will affect more than one document.
 *
 * @return {Promise<boolean>} a promise that retruns true if the path has
 * children and false otherwise.
 */
FirestoreDelete.prototype.checkHasChildren = function() {
  return this._getDescendantBatch(true, 1).then(function(docs) {
    return docs.length > 0;
  });
};

/**
 * Run the delete operation.
 */
FirestoreDelete.prototype.execute = function() {
  var verifyRecurseSafe;
  if (this.isDocumentPath && !this.recursive && !this.shallow) {
    verifyRecurseSafe = this.checkHasChildren().then(function(multiple) {
      if (multiple) {
        return utils.reject("Document has children, must specify -r or --shallow.", { exit: 1 });
      }
    });
  } else {
    verifyRecurseSafe = Promise.resolve();
  }

  var self = this;
  return verifyRecurseSafe.then(function() {
    return self._deletePath();
  });
};

module.exports = FirestoreDelete;

Как упоминалось выше, для этого вам нужно написать хороший код. Для каждого удаляемого документа необходимо проверить, есть ли в нем одна или несколько коллекций. Если это так, то вам также нужно поставить их в очередь на удаление. Для этого я написал приведенный ниже код. Он не тестировался на возможность масштабирования до больших наборов данных, что меня устраивает, поскольку я использую его для очистки после небольших интеграционных тестов. Если вам нужно что-то более масштабируемое, смело используйте это как отправную точку и поэкспериментируйте с пакетной обработкой.

class FirebaseDeleter {


constructor(database, collections) {
    this._database = database;
    this._pendingCollections = [];
  }

  run() {
    return new Promise((resolve, reject) => {
      this._callback = resolve;
      this._database.getCollections().then(collections => {
        this._pendingCollections = collections;
        this._processNext();
      });
    });
  }

  _processNext() {
    const collections = this._pendingCollections;
    this._pendingCollections = [];
    const promises = collections.map(collection => {
      return this.deleteCollection(collection, 10000);
    });

    Promise.all(promises).then(() => {
      if (this._pendingCollections.length == 0) {
        this._callback();
      } else {
        process.nextTick(() => {
          this._processNext();
        });
      }
    });
  }

  deleteCollection(collectionRef, batchSize) {
    var query = collectionRef;

    return new Promise((resolve, reject) => {
      this.deleteQueryBatch(query, batchSize, resolve, reject);
    });
  }

  deleteQueryBatch(query, batchSize, resolve, reject) {
    query
      .get()
      .then(snapshot => {
        // When there are no documents left, we are done
        if (snapshot.size == 0) {
          return 0;
        }

        // Delete documents in a batch
        var batch = this._database.batch();
        const collectionPromises = [];
        snapshot.docs.forEach(doc => {
          collectionPromises.push(
            doc.ref.getCollections().then(collections => {
              collections.forEach(collection => {
                this._pendingCollections.push(collection);
              });
            })
          );
          batch.delete(doc.ref);
        });

        // Wait until we know if all the documents have collections before deleting them.
        return Promise.all(collectionPromises).then(() => {
          return batch.commit().then(() => {
            return snapshot.size;
          });
        });
      })
      .then(numDeleted => {
        if (numDeleted === 0) {
          resolve();
          return;
        }

        // Recurse on the next process tick, to avoid
        // exploding the stack.
        process.nextTick(() => {
          this.deleteQueryBatch(query, batchSize, resolve, reject);
        });
      })
      .catch(reject);
  }
}

согласно документации firebase:
https://firebase.google.com/docs/firestore/solutions/delete-collections
Удаление коллекции с вложенными вложенными коллекциями может быть выполнено легко и аккуратно с помощью node-JS на стороне сервера.

const client = require('firebase-tools');
await client.firestore
      .delete(collectionPath, {
        project: process.env.GCLOUD_PROJECT,
        recursive: true,
        yes: true
      }); 

// You can add all the collection hierarchy to object
private collectionsHierarchy = { 

    groups: [

        [
        'groups',
        'projects', 
        'files', 
        'assets',
        'urls',
        'members'
      ]

    ]

 };

async deleteDocument(rootDocument: string) {
     // if (!rootDocument.startsWith(`groups/${this.groupId()}`)) {
     //  rootDocument = `groups/${this.groupId()}/${rootDocument}`;
     // }

    const batchSize: number = 100;
    let root = await this.db
      .doc(rootDocument)
      .get()
      .toPromise();

    if (!root.exists) {
      return;
    }

    const segments = rootDocument.split('/');
    const documentCollection = segments[segments.length - 2]; 
    const allHierarchies = this.collectionsHierarchy[documentCollection];

    for (let i = 0; i < allHierarchies.length; i = i + 1) {
      const hierarchy = allHierarchies[i];
      const collectionIndex = hierarchy.indexOf(documentCollection) + 1;
      const nextCollections: [] = hierarchy.slice(collectionIndex);

      const stack = [`${root.ref.path}/${nextCollections.shift()}`];

      while (stack.length) {
        const path = stack.pop();
        const collectionRef = this.db.firestore.collection(path);
        const query = collectionRef.orderBy('__name__').limit(batchSize);
        let deletedIems = await this.deleteQueryBatch(query, batchSize);
        const nextCollection = nextCollections.shift();
        deletedIems = deletedIems.map(di => `${di}/${nextCollection}`);
        stack.push(...deletedIems);
      }
    }

    await root.ref.delete();
  }

  private async deleteQueryBatch(
    query: firebase.firestore.Query,
    batchSize: number
  ) {
    let deletedItems: string[] = [];
    let snapshot = await query.get();

    if (snapshot.size === 0) {
      return deletedItems;
    }

    const batch = this.db.firestore.batch();
    snapshot.docs.forEach(doc => {
      deletedItems.push(doc.ref.path);
      batch.delete(doc.ref);
    });


    await batch.commit();

    if (snapshot.size === 0) {
      return deletedItems;
    }

    const result = await this.deleteQueryBatch(query, batchSize);
    return [...deletedItems, ...result];
  }

Решение с использованием Node.js Admin SDK

export const deleteDocument = async (doc: FirebaseFirestore.DocumentReference) => {
    const collections = await doc.listCollections()
    await Promise.all(collections.map(collection => deleteCollection(collection)))
    await doc.delete()
}

export const deleteCollection = async (collection: FirebaseFirestore.CollectionReference) => {
    const query = collection.limit(100)
    while (true) {
        const snap = await query.get()
        if (snap.empty) {
            return
        }
        await Promise.all(snap.docs.map(doc => deleteDocument(doc.ref)))
    }
}

Вы можете написать обработчик, который будет рекурсивно удалять все вложенные потомки при срабатывании события onDelete Firestore.

Пример обработчика:

const deleteDocumentWithDescendants = async (documentSnap: FirebaseFirestore.QueryDocumentSnapshot) => {
  return documentSnap.ref.listCollections().then((subCollections) => {
    subCollections.forEach((subCollection) => {
      return subCollection.get().then((snap) => {
        snap.forEach((doc) => {
          doc.ref.delete();
          deleteDocumentWithDescendants(doc);
        });
      });
    });
  });
};

// On any document delete
export const onDocumentDelete = async (documentSnap: FirebaseFirestore.QueryDocumentSnapshot) => {
  await deleteDocumentWithDescendants(documentSnap);
};

Свяжите это с событием firestore:

exports.onDeleteDocument = functions.firestore.document('{collectionId}/{docId}')
    .onDelete(onDocumentDelete);