Skip to content

ARROW-1698: [JS] File reader attempts to load the same dictionary batch more than once #1222

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
TheNeuralBit wants to merge 2 commits into from
Closed

ARROW-1698: [JS] File reader attempts to load the same dictionary batch more than once #1222

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f7b251b
only load a dictionary once
Oct 20, 2017
aec2f6d
readDictionary now returns a single vector or null
Oct 20, 2017
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
10 changes: 7 additions & 3 deletions js/src/reader/arrow.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ import { readFile } from './file';
import { readStream } from './stream';
import { readVector } from './vector';
import { Vector } from '../vector/vector';
import { readDictionaries } from './dictionary';
import { readDictionary } from './dictionary';

import ByteBuffer = flatbuffers.ByteBuffer;
export import Schema = Schema_.org.apache.arrow.flatbuf.Schema;
Expand Down Expand Up @@ -51,9 +51,13 @@ export function* readBuffers(...bytes: Array<Uint8Array | Buffer | string>) {
let state = { nodeIndex: 0, bufferIndex: 0 };
let index = -1, fieldsLength = schema.fieldsLength();
if (batch.id) {
// A dictionary batch only contain a single vector. Traverse each
// field and its children until we find one that uses this dictionary
while (++index < fieldsLength) {
for (let [id, vector] of readDictionaries(schema.fields(index), batch, state, dictionaries)) {
dictionaries[id] = dictionaries[id] && dictionaries[id].concat(vector) || vector;
let vector = readDictionary(schema.fields(index), batch, state, dictionaries);
if (vector) {
dictionaries[batch.id] = dictionaries[batch.id] && dictionaries[batch.id].concat(vector) || vector;
break;
}
}
} else {
Expand Down
18 changes: 7 additions & 11 deletions js/src/reader/dictionary.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,20 +21,16 @@ import * as Schema_ from '../format/Schema_generated';
import { IteratorState, Dictionaries } from './arrow';
import Field = Schema_.org.apache.arrow.flatbuf.Field;

export function* readDictionaries(field: Field | null,
batch: MessageBatch,
iterator: IteratorState,
dictionaries: Dictionaries) {
export function readDictionary(field: Field | null,
batch: MessageBatch,
iterator: IteratorState,
dictionaries: Dictionaries) {
let id: string, encoding = field && field.dictionary();
if (encoding && batch.id === (id = encoding.id().toFloat64().toString())) {
yield [id, readVector(field, batch, iterator, null)];
return;
return readVector(field, batch, iterator, null);
}
for (let i = -1, n = field && field.childrenLength() || 0; ++i < n;) {
// Since a dictionary batch can only contain a single vector, return early after we find it
for (let result of readDictionaries(field.children(i), batch, iterator, dictionaries)) {
yield result;
return;
}
let vector = readDictionary(field.children(i), batch, iterator, dictionaries);
if (vector) return vector;
}
}