Skip to content

Web console: better input format detection #9007

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

Merged
clintropolis merged 1 commit into from
Dec 10, 2019
Merged

Web console: better input format detection #9007

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
55 changes: 27 additions & 28 deletions web-console/src/utils/ingestion-spec.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -334,13 +334,13 @@ const INPUT_FORMAT_FORM_FIELDS: Field<InputFormat>[] = [
defined: (p: InputFormat) =>
((p.type === 'csv' || p.type === 'tsv') && !p.findColumnsFromHeader) || p.type === 'regex',
},
// {
// name: 'delimiter',
// type: 'string',
// defaultValue: '\t',
// defined: (p: InputFormat) => p.type === 'tsv',
// info: <>A custom delimiter for data values.</>,
// },
{
name: 'delimiter',
type: 'string',
defaultValue: '\t',
defined: (p: InputFormat) => p.type === 'tsv',
info: <>A custom delimiter for data values.</>,
},
{
name: 'listDelimiter',
type: 'string',
Expand Down Expand Up @@ -2455,34 +2455,33 @@ export function updateIngestionType(
}

export function fillInputFormat(spec: IngestionSpec, sampleData: string[]): IngestionSpec {
const inputFormat = guessInputFormat(sampleData);
if (!inputFormat) return spec;

return deepSet(spec, 'ioConfig.inputFormat', inputFormat);
return deepSet(spec, 'ioConfig.inputFormat', guessInputFormat(sampleData));
}

function guessInputFormat(sampleData: string[]): InputFormat | undefined {
const sampleDatum = sampleData[0];
if (!sampleDatum) return;
function guessInputFormat(sampleData: string[]): InputFormat {
let sampleDatum = sampleData[0];
if (sampleDatum) {
sampleDatum = String(sampleDatum); // Really ensure it is a string

if (sampleDatum.startsWith('{') && sampleDatum.endsWith('}')) {
return inputFormatFromType('json');
}
if (sampleDatum.startsWith('{') && sampleDatum.endsWith('}')) {
return inputFormatFromType('json');
}

if (sampleDatum.split('\t').length > 3) {
return inputFormatFromType('tsv', !/\t\d+\t/.test(sampleDatum));
}
if (sampleDatum.split('\t').length > 3) {
return inputFormatFromType('tsv', !/\t\d+\t/.test(sampleDatum));
}

if (sampleDatum.split(',').length > 3) {
return inputFormatFromType('csv', !/,\d+,/.test(sampleDatum));
}
if (sampleDatum.split(',').length > 3) {
return inputFormatFromType('csv', !/,\d+,/.test(sampleDatum));
}

if (sampleDatum.startsWith('PAR1')) {
return inputFormatFromType('parquet');
}
if (sampleDatum.startsWith('PAR1')) {
return inputFormatFromType('parquet');
}

if (sampleDatum.startsWith('ORC')) {
return inputFormatFromType('orc');
if (sampleDatum.startsWith('ORC')) {
return inputFormatFromType('orc');
}
}

return inputFormatFromType('regex');
Expand Down
4 changes: 1 addition & 3 deletions web-console/src/views/load-data-view/load-data-view.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1112,9 +1112,7 @@ export class LoadDataView extends React.PureComponent<LoadDataViewProps, LoadDat
const inputData = inputQueryState.data;

if (druidSource) {
let newSpec = fillInputFormat(spec, []);

newSpec = deepSet(newSpec, 'dataSchema.timestampSpec', {
let newSpec = deepSet(spec, 'dataSchema.timestampSpec', {
column: '__time',
format: 'iso',
});
Expand Down