11 KiB
11 KiB
title | id | challengeType | forumTopicId |
---|---|---|---|
Hash join | 5956795bc9e2c415eb244de1 | 5 | 302284 |
Description
- Hash phase: Create a multimap from one of the two tables, mapping from each join column value to all the rows that contain it.
- The multimap must support hash-based lookup which scales better than a simple linear search, because that's the whole point of this algorithm.
- Ideally we should create the multimap for the smaller table, thus minimizing its creation time and memory size.
- Join phase: Scan the other table, and find matching rows by looking in the multimap created before.
let A = the first input table (or ideally, the larger one) let B = the second input table (or ideally, the smaller one) let jA = the join column ID of table A let jB = the join column ID of table B let MB = a multimap for mapping from single values to multiple rows of table B (starts out empty) let C = the output table (starts out empty) for each row b in table B: place b in multimap MB under key b(jB) for each row a in table A: for each row b in multimap MB under key a(jA): let c = the concatenation of row a and row b place row c in table C
Instructions
Input
|
Output
A_age | A_name | B_character | B_nemesis |
---|---|---|---|
27 | Jonah | Jonah | Whales |
27 | Jonah | Jonah | Spiders |
18 | Alan | Alan | Ghosts |
18 | Alan | Alan | Zombies |
28 | Glory | Glory | Buffy |
28 | Alan | Alan | Ghosts |
28 | Alan | Alan | Zombies |
Tests
tests:
- text: <code>hashJoin</code> is a function.
testString: assert(typeof hashJoin === 'function');
- text: '<code>hashJoin([{ age: 27, name: "Jonah" }, { age: 18, name: "Alan" }, { age: 28, name: "Glory" }, { age: 18, name: "Popeye" }, { age: 28, name: "Alan" }], [{ character: "Jonah", nemesis: "Whales" }, { character: "Jonah", nemesis: "Spiders" }, { character: "Alan", nemesis: "Ghosts" }, { character:"Alan", nemesis: "Zombies" }, { character: "Glory", nemesis: "Buffy" }, { character: "Bob", nemesis: "foo" }])</code> should return <code>[{"A_age": 27,"A_name": "Jonah", "B_character": "Jonah", "B_nemesis": "Whales"}, {"A_age": 27,"A_name": "Jonah", "B_character": "Jonah", "B_nemesis": "Spiders"}, {"A_age": 18,"A_name": "Alan", "B_character": "Alan", "B_nemesis": "Ghosts"}, {"A_age": 18,"A_name": "Alan", "B_character": "Alan", "B_nemesis": "Zombies"}, {"A_age": 28,"A_name": "Glory", "B_character": "Glory", "B_nemesis": "Buffy"}, {"A_age": 28,"A_name": "Alan", "B_character": "Alan", "B_nemesis": "Ghosts"}, {"A_age": 28,"A_name": "Alan", "B_character": "Alan", "B_nemesis": "Zombies"}]</code>'
testString: assert.deepEqual(hashJoin(hash1, hash2), res);
Challenge Seed
function hashJoin(hash1, hash2) {
// Good luck!
return [];
}
After Test
const hash1 = [
{ age: 27, name: 'Jonah' },
{ age: 18, name: 'Alan' },
{ age: 28, name: 'Glory' },
{ age: 18, name: 'Popeye' },
{ age: 28, name: 'Alan' }
];
const hash2 = [
{ character: 'Jonah', nemesis: 'Whales' },
{ character: 'Jonah', nemesis: 'Spiders' },
{ character: 'Alan', nemesis: 'Ghosts' },
{ character: 'Alan', nemesis: 'Zombies' },
{ character: 'Glory', nemesis: 'Buffy' },
{ character: 'Bob', nemesis: 'foo' }
];
const res = [
{ A_age: 27, A_name: 'Jonah', B_character: 'Jonah', B_nemesis: 'Whales' },
{ A_age: 27, A_name: 'Jonah', B_character: 'Jonah', B_nemesis: 'Spiders' },
{ A_age: 18, A_name: 'Alan', B_character: 'Alan', B_nemesis: 'Ghosts' },
{ A_age: 18, A_name: 'Alan', B_character: 'Alan', B_nemesis: 'Zombies' },
{ A_age: 28, A_name: 'Glory', B_character: 'Glory', B_nemesis: 'Buffy' },
{ A_age: 28, A_name: 'Alan', B_character: 'Alan', B_nemesis: 'Ghosts' },
{ A_age: 28, A_name: 'Alan', B_character: 'Alan', B_nemesis: 'Zombies' }
];
const bench1 = [{ name: 'u2v7v', num: 1 }, { name: 'n53c8', num: 10 }, { name: 'oysce', num: 9 }, { name: '0mto2s', num: 1 }, { name: 'vkh5id', num: 4 }, { name: '5od0cf', num: 8 }, { name: 'uuulue', num: 10 }, { name: '3rgsbi', num: 9 }, { name: 'kccv35r', num: 4 }, { name: '80un74', num: 9 }, { name: 'h4pp3', num: 6 }, { name: '51bit', num: 7 }, { name: 'j9ndf', num: 8 }, { name: 'vf3u1', num: 10 }, { name: 'g0bw0om', num: 10 }, { name: 'j031x', num: 7 }, { name: 'ij3asc', num: 9 }, { name: 'byv83y', num: 8 }, { name: 'bjzp4k', num: 4 }, { name: 'f3kbnm', num: 10 }];
const bench2 = [{ friend: 'o8b', num: 8 }, { friend: 'ye', num: 2 }, { friend: '32i', num: 5 }, { friend: 'uz', num: 3 }, { friend: 'a5k', num: 4 }, { friend: 'uad', num: 7 }, { friend: '3w5', num: 10 }, { friend: 'vw', num: 10 }, { friend: 'ah', num: 4 }, { friend: 'qv', num: 7 }, { friend: 'ozv', num: 2 }, { friend: '9ri', num: 10 }, { friend: '7nu', num: 4 }, { friend: 'w3', num: 9 }, { friend: 'tgp', num: 8 }, { friend: 'ibs', num: 1 }, { friend: 'ss7', num: 6 }, { friend: 'g44', num: 9 }, { friend: 'tab', num: 9 }, { friend: 'zem', num: 10 }];
Solution
function hashJoin(hash1, hash2) {
const hJoin = (tblA, tblB, strJoin) => {
const [jA, jB] = strJoin.split('=');
const M = tblB.reduce((a, x) => {
const id = x[jB];
return (
a[id] ? a[id].push(x) : (a[id] = [x]),
a
);
}, {});
return tblA.reduce((a, x) => {
const match = M[x[jA]];
return match ? (
a.concat(match.map(row => dictConcat(x, row)))
) : a;
}, []);
};
const dictConcat = (dctA, dctB) => {
const ok = Object.keys;
return ok(dctB).reduce(
(a, k) => (a[`B_${k}`] = dctB[k]) && a,
ok(dctA).reduce(
(a, k) => (a[`A_${k}`] = dctA[k]) && a, {}
)
);
};
return hJoin(hash1, hash2, 'name=character');
}