Compare commits

..

12 Commits

Author SHA1 Message Date
Luccas Mateus
0f7d28e02e [flatuitable][m] - add bytes + parsingConfig 2023-09-20 08:12:32 -03:00
Anuar Ustayev (aka Anu)
083d3178cd Merge pull request #999 from igoradamenko/igoradamenko-patch-1
Fix wiki-link regexp to match non-Latin characters
2023-09-12 00:18:23 +06:00
João Demenech
3200dc5ade fix(site,docs): missing mddb command instruction on 'Searching datasets' tutorial 2023-09-11 08:21:35 -03:00
João Demenech
32dce434eb Merge pull request #1017 from datopian/changeset-release/main
Version Packages
2023-08-31 16:13:39 -03:00
github-actions[bot]
37ef29d9a2 Version Packages 2023-08-31 19:09:52 +00:00
João Demenech
98d62532c5 Merge pull request #1018 from datopian/ckan/feat/private-datasets
feat(ckan): makes it possible to search private datasets on the ckan api
2023-08-31 16:06:01 -03:00
João Demenech
50122cd0cb bump: new version of CKAN API 2023-08-30 18:38:35 -03:00
João Demenech
0156e72dd3 feat(ckan): makes it possible to search private datasets on the ckan api 2023-08-30 18:35:40 -03:00
Luccas Mateus
91217f3256 [packanges/ckan][xs] - fix type (#1016) 2023-08-24 16:04:44 -03:00
github-actions[bot]
11f9253709 Version Packages (#1015)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2023-08-24 16:03:42 -03:00
João Demenech
c09c78b015 feat(site,seo): disallow the people/* path to be crawled 2023-08-23 16:33:28 -03:00
Igor Adamenko
3efba6578d Fix wiki-link regexp to match non-Latin characters 2023-08-09 19:02:11 +03:00
19 changed files with 148 additions and 147 deletions

View File

@@ -0,0 +1,5 @@
---
'@portaljs/components': minor
---
FlatUiTables now accepts a bytes param and a parsingConfig param for CSV links

6
package-lock.json generated
View File

@@ -46942,7 +46942,7 @@
},
"packages/ckan": {
"name": "@portaljs/ckan",
"version": "0.0.3",
"version": "0.1.0",
"dependencies": {
"formik": "^2.2.9",
"swr": "^2.1.5",
@@ -47347,7 +47347,7 @@
},
"packages/components": {
"name": "@portaljs/components",
"version": "0.3.1",
"version": "0.3.2",
"dependencies": {
"@githubocto/flat-ui": "^0.14.1",
"@heroicons/react": "^2.0.17",
@@ -47828,7 +47828,7 @@
},
"packages/remark-wiki-link": {
"name": "@portaljs/remark-wiki-link",
"version": "1.0.4",
"version": "1.1.0",
"license": "MIT",
"dependencies": {
"mdast-util-to-markdown": "^1.5.0",

View File

@@ -1,5 +1,15 @@
# @portaljs/ckan
## 0.1.0
### Minor Changes
- [#1018](https://github.com/datopian/portaljs/pull/1018) [`50122cd0`](https://github.com/datopian/portaljs/commit/50122cd0cbbf68bdadc641341279b30b22538cfd) Thanks [@demenech](https://github.com/demenech)! - package_search method now supports custom headers and include_private parameter
### Patch Changes
- [#1016](https://github.com/datopian/portaljs/pull/1016) [`91217f32`](https://github.com/datopian/portaljs/commit/91217f325657e2f298b0e632793ae9bb8b08e870) Thanks [@luccasmmg](https://github.com/luccasmmg)! - remove optional from id in resource interface
## 0.0.5
### Patch Changes

View File

@@ -1,6 +1,6 @@
{
"name": "@portaljs/ckan",
"version": "0.0.5",
"version": "0.1.0",
"type": "module",
"description": "https://portaljs.org",
"keywords": [

View File

@@ -41,7 +41,7 @@ export interface Resource {
description?: string;
format?: string;
hash?: string;
id?: string;
id: string;
last_modified?: string;
metadata_modified?: string;
mimetype?: string;
@@ -69,6 +69,7 @@ export interface PackageSearchOptions {
query?: string;
resFormat?: Array<string>;
sort?: string;
include_private?: boolean;
}
export interface Tag {

View File

@@ -31,11 +31,7 @@ export default class CKAN {
async getDatasetsListWithDetails(options: DatasetListQueryOptions) {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/current_package_list_with_resources?offset=${
options.offset
}&limit=${options.limit}`,
`${this.DMS}/api/3/action/current_package_list_with_resources?offset=${options.offset}&limit=${options.limit}`,
3
);
const responseData = await response.json();
@@ -44,7 +40,8 @@ export default class CKAN {
}
async packageSearch(
options: PackageSearchOptions
options: PackageSearchOptions,
reqOptions: Partial<RequestInit> = {}
): Promise<{ datasets: Dataset[]; count: number }> {
function buildGroupsQuery(groups: Array<string>) {
if (groups.length > 0) {
@@ -99,16 +96,18 @@ export default class CKAN {
options.groups,
options?.resFormat
);
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/package_search?start=${options.offset}&rows=${
options.limit
}${fq ? fq : ''}${options.query ? '&q=' + options.query : ''}${
options.sort ? '&sort=' + options.sort : ''
}`,
3
);
let url = `${this.DMS}/api/3/action/package_search?`;
url += `start=${options.offset}`;
url += `&rows=${options.limit}`;
url += fq ? fq : '';
url += options.query ? '&q=' + options.query : '';
url += options.sort ? '&sort=' + options.sort : '';
url += options.include_private
? '&include_private=' + options.include_private
: '';
const response = await fetchRetry(url, 3, reqOptions);
const responseData = await response.json();
const datasets: Array<Dataset> = responseData.result.results;
return { datasets, count: responseData.result.count };
@@ -116,9 +115,7 @@ export default class CKAN {
async getDatasetDetails(datasetName: string) {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/package_show?id=${datasetName}`,
`${this.DMS}/api/3/action/package_show?id=${datasetName}`,
1
);
const responseData = await response.json();
@@ -131,9 +128,7 @@ export default class CKAN {
async getDatasetActivityStream(datasetName: string) {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/package_activity_list?id=${datasetName}`,
`${this.DMS}/api/3/action/package_activity_list?id=${datasetName}`,
3
);
const responseData = await response.json();
@@ -151,9 +146,7 @@ export default class CKAN {
async getUser(userId: string) {
try {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/user_show?id=${userId}`,
`${this.DMS}/api/3/action/user_show?id=${userId}`,
3
);
const responseData = await response.json();
@@ -166,10 +159,7 @@ export default class CKAN {
}
async getGroupList() {
const response = await fetchRetry(
`${this.DMS}/api/3/action/group_list`,
3
);
const response = await fetchRetry(`${this.DMS}/api/3/action/group_list`, 3);
const responseData = await response.json();
const groups: Array<string> = responseData.result;
return groups;
@@ -177,9 +167,7 @@ export default class CKAN {
async getGroupsWithDetails() {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/group_list?all_fields=True`,
`${this.DMS}/api/3/action/group_list?all_fields=True`,
3
);
const responseData = await response.json();
@@ -189,9 +177,7 @@ export default class CKAN {
async getGroupDetails(groupName: string) {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/group_show?id=${groupName}&include_datasets=True`,
`${this.DMS}/api/3/action/group_show?id=${groupName}&include_datasets=True`,
3
);
const responseData = await response.json();
@@ -201,9 +187,7 @@ export default class CKAN {
async getGroupActivityStream(groupName: string) {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/group_activity_list?id=${groupName}`,
`${this.DMS}/api/3/action/group_activity_list?id=${groupName}`,
3
);
const responseData = await response.json();
@@ -230,9 +214,7 @@ export default class CKAN {
async getOrgsWithDetails(accrossPages?: boolean) {
if (!accrossPages) {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/organization_list?all_fields=True`,
`${this.DMS}/api/3/action/organization_list?all_fields=True`,
3
);
const responseData = await response.json();
@@ -251,9 +233,7 @@ export default class CKAN {
for (let i = 0; i < pages; i++) {
let allOrgListResponse = await fetchRetry(
`${
this.DMS
}/api/3/action/organization_list?all_fields=True&offset=${
`${this.DMS}/api/3/action/organization_list?all_fields=True&offset=${
i * 25
}&limit=25`,
3
@@ -267,9 +247,7 @@ export default class CKAN {
async getOrgDetails(orgName: string) {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/organization_show?id=${orgName}&include_datasets=True`,
`${this.DMS}/api/3/action/organization_show?id=${orgName}&include_datasets=True`,
3
);
const responseData = await response.json();
@@ -279,9 +257,7 @@ export default class CKAN {
async getOrgActivityStream(orgName: string) {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/organization_activity_list?id=${orgName}`,
`${this.DMS}/api/3/action/organization_activity_list?id=${orgName}`,
3
);
const responseData = await response.json();
@@ -297,9 +273,7 @@ export default class CKAN {
async getAllTags() {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/tag_list?all_fields=True`,
`${this.DMS}/api/3/action/tag_list?all_fields=True`,
3
);
const responseData = await response.json();
@@ -308,9 +282,7 @@ export default class CKAN {
}
async getResourcesWithAliasList() {
const response = await fetch(
`${this.DMS}/api/3/action/datastore_search`,
{
const response = await fetch(`${this.DMS}/api/3/action/datastore_search`, {
method: 'POST',
headers: {
Accept: 'application/json',
@@ -320,17 +292,14 @@ export default class CKAN {
id: '_table_metadata',
limit: '32000',
}),
}
);
});
const responseData = await response.json();
const tableMetadata: Array<TableMetadata> = responseData.result.records;
return tableMetadata.filter((item) => item.alias_of);
}
async datastoreSearch(resourceId: string) {
const response = await fetch(
`${this.DMS}/api/3/action/datastore_search`,
{
const response = await fetch(`${this.DMS}/api/3/action/datastore_search`, {
method: 'POST',
headers: {
Accept: 'application/json',
@@ -340,17 +309,14 @@ export default class CKAN {
id: resourceId,
limit: '32000',
}),
}
);
});
const responseData = await response.json();
return responseData.result.records;
}
async getResourceMetadata(resourceId: string) {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/resource_show?id=${resourceId}`,
`${this.DMS}/api/3/action/resource_show?id=${resourceId}`,
3
);
const responseData = await response.json();
@@ -359,17 +325,14 @@ export default class CKAN {
}
async getResourceInfo(resourceId: string) {
const response = await fetch(
`${this.DMS}/api/3/action/datastore_info`,
{
const response = await fetch(`${this.DMS}/api/3/action/datastore_info`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
},
body: JSON.stringify({ resource_id: resourceId }),
}
);
});
const responseData = await response.json();
const resourceInfo: Array<ResourceInfo> = responseData.result;
return resourceInfo;
@@ -377,9 +340,7 @@ export default class CKAN {
async getFacetFields(field: 'res_format' | 'tags') {
const response = await fetchRetry(
`${
this.DMS
}/api/3/action/package_search?facet.field=["${field}"]&rows=0`,
`${this.DMS}/api/3/action/package_search?facet.field=["${field}"]&rows=0`,
3
);
const responseData = await response.json();

View File

@@ -9,10 +9,14 @@ export function getDaysAgo(date: string) {
return (+today - +createdOn) / msInDay;
}
export default async function fetchRetry(url: string, n: number): Promise<any> {
export default async function fetchRetry(
url: string,
n: number,
opts: Partial<RequestInit> = {}
): Promise<any> {
const abortController = new AbortController();
const id = setTimeout(() => abortController.abort(), 30000);
const res = await fetch(url, { signal: abortController.signal });
const res = await fetch(url, { signal: abortController.signal, ...opts });
clearTimeout(id);
if (!res.ok && n && n > 0) {
return await fetchRetry(url, n - 1);
@@ -21,13 +25,13 @@ export default async function fetchRetry(url: string, n: number): Promise<any> {
}
export function removeTag(tag?: string) {
if (tag === "{{description}}" || !tag) {
if (tag === '{{description}}' || !tag) {
return undefined;
}
if (typeof window !== "undefined") {
const div = document.createElement("div");
if (typeof window !== 'undefined') {
const div = document.createElement('div');
div.innerHTML = tag;
return div.textContent || div.innerText || "";
return div.textContent || div.innerText || '';
}
return tag;
}
@@ -38,10 +42,10 @@ export function convertFieldSchema(
) {
function convertToGraphqlString(fieldName: string) {
return fieldName
.replaceAll(" ", "_")
.replaceAll("(", "_")
.replaceAll(")", "_")
.replace(/[^\w\s]|(_)\1/gi, "_");
.replaceAll(' ', '_')
.replaceAll('(', '_')
.replaceAll(')', '_')
.replace(/[^\w\s]|(_)\1/gi, '_');
}
const entries = Object.entries(schema);
return {

View File

@@ -5,22 +5,20 @@ import LoadingSpinner from './LoadingSpinner';
const queryClient = new QueryClient();
export async function getCsv(url: string, corsProxy?: string) {
if (corsProxy) {
url = corsProxy + url;
}
export async function getCsv(url: string, bytes) {
const response = await fetch(url, {
headers: {
Range: 'bytes=0-5132288',
Range: `bytes=0-${bytes}`,
},
});
const data = await response.text();
return data;
}
export async function parseCsv(file: string): Promise<any> {
export async function parseCsv(file: string, parsingConfig): Promise<any> {
return new Promise((resolve, reject) => {
Papa.parse(file, {
...parsingConfig,
header: true,
dynamicTyping: true,
skipEmptyLines: true,
@@ -41,25 +39,28 @@ export interface FlatUiTableProps {
url?: string;
data?: { [key: string]: number | string }[];
rawCsv?: string;
corsProxy?: string;
randomId?: number;
bytes: number;
parsingConfig: any;
}
export const FlatUiTable: React.FC<FlatUiTableProps> = ({
url,
data,
rawCsv,
corsProxy,
bytes = 5132288,
parsingConfig = {},
}) => {
const randomId = Math.random();
return (
// Provide the client to your App
<QueryClientProvider client={queryClient}>
<TableInner
corsProxy={corsProxy}
bytes={bytes}
url={url}
data={data}
rawCsv={rawCsv}
randomId={randomId}
parsingConfig={parsingConfig}
/>
</QueryClientProvider>
);
@@ -69,8 +70,9 @@ const TableInner: React.FC<FlatUiTableProps> = ({
url,
data,
rawCsv,
corsProxy,
randomId,
bytes,
parsingConfig,
}) => {
if (data) {
return (
@@ -81,12 +83,16 @@ const TableInner: React.FC<FlatUiTableProps> = ({
}
const { data: csvString, isLoading: isDownloadingCSV } = useQuery(
['dataCsv', url, randomId],
() => getCsv(url as string, corsProxy),
() => getCsv(url as string, bytes),
{ enabled: !!url }
);
const { data: parsedData, isLoading: isParsing } = useQuery(
['dataPreview', csvString, randomId],
() => parseCsv(rawCsv ? (rawCsv as string) : (csvString as string)),
() =>
parseCsv(
rawCsv ? (rawCsv as string) : (csvString as string),
parsingConfig
),
{ enabled: rawCsv ? true : !!csvString }
);
if (isParsing || isDownloadingCSV)

View File

@@ -9,17 +9,24 @@ const meta: Meta = {
tags: ['autodocs'],
argTypes: {
data: {
description: "Data to be displayed in the table, must be setup as an array of key value pairs"
description:
'Data to be displayed in the table, must be setup as an array of key value pairs',
},
csv: {
description: "CSV data as string.",
description: 'CSV data as string.',
},
url: {
description: "Fetch the data from a CSV file remotely. only the first 5MB of data will be displayed"
description:
'Fetch the data from a CSV file remotely. only the first 5MB of data will be displayed',
},
bytes: {
description:
'Fetch the data from a CSV file remotely. only the first <bytes> of data will be displayed',
},
parsingConfig: {
description:
'Configuration for parsing the CSV data. See https://www.papaparse.com/docs#config for more details',
},
corsProxy: {
description: "Optionally you cant set a CORS Proxy to which all your requests you be redirected"
}
},
};
@@ -29,7 +36,7 @@ type Story = StoryObj<FlatUiTableProps>;
// More on writing stories with args: https://storybook.js.org/docs/react/writing-stories/args
export const FromColumnsAndData: Story = {
name: "Table data",
name: 'Table data',
args: {
data: [
{ id: 1, lastName: 'Snow', firstName: 'Jon', age: 35 },
@@ -44,20 +51,19 @@ export const FromColumnsAndData: Story = {
};
export const FromRawCSV: Story = {
name: "Table from raw CSV",
name: 'Table from raw CSV',
args: {
rawCsv: `
Year,Temp Anomaly
1850,-0.418
2020,0.923
`
}
`,
},
};
export const FromURL: Story = {
name: "Table from URL",
name: 'Table from URL',
args: {
url: "https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv"
}
url: 'https://ckan-dev.sse.datopian.com/datastore/dump/601c9cf0-595e-46d8-88fc-d1ab2904e2db',
},
};

View File

@@ -79,7 +79,7 @@ function fromMarkdown(opts: FromMarkdownOptions = {}) {
data: { isEmbed, target, alias },
} = wikiLink;
// eslint-disable-next-line no-useless-escape
const wikiLinkWithHeadingPattern = /([\w\s\/\.-]*)(#.*)?/;
const wikiLinkWithHeadingPattern = /([\p{Letter}\d\s\/\.-_]*)(#.*)?/u;
const [, path, heading = ""] = target.match(wikiLinkWithHeadingPattern);
const possibleWikiLinkPermalinks = wikiLinkResolver(path);

View File

@@ -101,7 +101,7 @@ List of available datasets:
<Catalog datasets={datasets} facets={['group']}/>
```
You now have a filter in your page with all possible values automatically added to it.
Rerun `npm run mddb`. You now have a filter in your page with all possible values automatically added to it.
![Data catalog with facets built with PortalJS](https://i.imgur.com/p2miSdg.png)

View File

@@ -3,3 +3,4 @@ id: anuveyatsu
name: Anuar Ustayev
avatar: https://avatars.githubusercontent.com/anuveyatsu
---
<NextSeo noindex={true} nofollow={true} />

View File

@@ -3,3 +3,4 @@ id: joaodemenech
name: João Demenech
avatar: https://avatars.githubusercontent.com/demenech
---
<NextSeo noindex={true} nofollow={true} />

View File

@@ -3,3 +3,4 @@ id: luccasmateus
name: Luccas Mateus
avatar: https://avatars.githubusercontent.com/luccasmmg
---
<NextSeo noindex={true} nofollow={true} />

View File

@@ -3,3 +3,4 @@ id: mikanebu
name: Meiran Zhiyenbayev
avatar: https://avatars.githubusercontent.com/mikanebu
---
<NextSeo noindex={true} nofollow={true} />

View File

@@ -3,3 +3,4 @@ id: ola-rubaj
name: Ola Rubaj
avatar: https://avatars.githubusercontent.com/olayway
---
<NextSeo noindex={true} nofollow={true} />

View File

@@ -3,3 +3,4 @@ id: popovayoana
name: Yoana Popova
avatar: https://avatars.githubusercontent.com/popovayoana
---
<NextSeo noindex={true} nofollow={true} />

View File

@@ -3,3 +3,4 @@ id: rufuspollock
name: Rufus Pollock
avatar: https://avatars.githubusercontent.com/rufuspollock
---
<NextSeo noindex={true} nofollow={true} />

View File

@@ -4,6 +4,7 @@ module.exports = {
generateRobotsTxt: true,
robotsTxtOptions: {
policies: [
{ userAgent: '*', disallow: '/people/' },
{ userAgent: '*', disallow: '/people' },
{ userAgent: '*', disallow: '/?amp=1' },
],