Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions packages/memory-storage/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,7 @@
"fs-extra": "^11.0.0",
"json5": "^2.2.3",
"mime-types": "^2.1.35",
"p-limit": "^3.1.0",
"proper-lockfile": "^4.1.2",
"tslib": "^2.4.0"
}
Expand Down
42 changes: 24 additions & 18 deletions packages/memory-storage/src/resource-clients/key-value-store.ts
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ import type * as storage from '@crawlee/types';
import { s } from '@sapphire/shapeshift';
import { move } from 'fs-extra';
import mime from 'mime-types';
import pLimit from 'p-limit';

import { scheduleBackgroundTask } from '../background-handler';
import { maybeParseBody } from '../body-parser';
Expand All @@ -19,6 +20,7 @@ import { createKeyList, createKeyStringList, isBuffer, isStream } from '../utils
import { BaseClient } from './common/base-client';

const DEFAULT_LOCAL_FILE_EXTENSION = 'bin';
const GET_RECORD_CONCURRENCY = 25;

export interface KeyValueStoreClientOptions {
name?: string;
Expand Down Expand Up @@ -173,15 +175,15 @@ export class KeyValueStoreClient extends BaseClient {

const firstPageValuesPromise = (async () => {
const firstPageKeys = await firstPageKeysPromise;
const values: unknown[] = [];
for (const item of firstPageKeys.items) {
if (limit !== undefined && values.length >= limit) break;
const record = await getRecord(item.key);
if (record) {
values.push(record.value);
}
}
return values;
const keysToFetch = limit !== undefined ? firstPageKeys.items.slice(0, limit) : firstPageKeys.items;
const limiter = pLimit(GET_RECORD_CONCURRENCY);
const results = await Promise.allSettled(keysToFetch.map((item) => limiter(() => getRecord(item.key))));
return results
.filter(
(r): r is PromiseFulfilledResult<storage.KeyValueStoreRecord> =>
r.status === 'fulfilled' && r.value !== undefined,
)
.map((r) => r.value.value);
})();

async function* asyncGenerator(): AsyncGenerator<unknown> {
Expand Down Expand Up @@ -224,15 +226,19 @@ export class KeyValueStoreClient extends BaseClient {

const firstPageEntriesPromise = (async () => {
const firstPageKeys = await firstPageKeysPromise;
const entries: [string, unknown][] = [];
for (const item of firstPageKeys.items) {
if (limit !== undefined && entries.length >= limit) break;
const record = await getRecord(item.key);
if (record) {
entries.push([item.key, record.value]);
}
}
return entries;
const keysToFetch = limit !== undefined ? firstPageKeys.items.slice(0, limit) : firstPageKeys.items;
const limiter = pLimit(GET_RECORD_CONCURRENCY);
const results = await Promise.allSettled(
keysToFetch.map((item) =>
limiter(() => getRecord(item.key).then((record) => ({ key: item.key, record }))),
),
);
return results
.filter(
(r): r is PromiseFulfilledResult<{ key: string; record: storage.KeyValueStoreRecord }> =>
r.status === 'fulfilled' && r.value.record !== undefined,
)
.map((r) => [r.value.key, r.value.record.value] as [string, unknown]);
})();

async function* asyncGenerator(): AsyncGenerator<[string, unknown]> {
Expand Down
1 change: 1 addition & 0 deletions yarn.lock
Original file line number Diff line number Diff line change
Expand Up @@ -991,6 +991,7 @@ __metadata:
fs-extra: "npm:^11.0.0"
json5: "npm:^2.2.3"
mime-types: "npm:^2.1.35"
p-limit: "npm:^3.1.0"
proper-lockfile: "npm:^4.1.2"
tslib: "npm:^2.4.0"
languageName: unknown
Expand Down
Loading