Compare commits

...

8 Commits

Author SHA1 Message Date
olayway
adcafc7d6a add whole tutorial content 2023-05-26 15:26:07 +02:00
olayway
e563782dc4 dsf 2023-05-26 12:29:41 +02:00
olayway
730e160951 [site/content/blog][s]: blob post about basic tutorial on markdowndb 2023-05-26 12:24:56 +02:00
olayway
418b4bfe52 [content/config.js][xs]: add howtos to navlinks 2023-05-19 19:03:35 +02:00
Luccas Mateus de Medeiros Gomes
ee6efc7431 [site][xs] - add components tab in navbar 2023-05-19 07:04:16 -03:00
Ola Rubaj
a62addbfbb Dev how-to pages (#890)
Related to #878

## Changes
How-to docs pages:

- /howto/index: home page for guides
- /howto/analytics: "How to add Google Analytics?"
- /howto/seo: "How to customize page metadata for SEO?"
- /howto/sitemap: "How to build a sitemap?"
- /howto/blog: "How to add a simple blog?"
  - blog index page
  - blog layout
  - comments -> link to the page below
- /howto/comments: "How to add user comments?"
- /howto/markdown: "How to add markdown-based content pages?"
- /howto/drd: "How to create data-rich documents with charts and tables?"
2023-05-19 11:15:52 +02:00
João Demenech
adb6d1bb0e Implement dataset page v0.1 + Home improvements (#892)
* [examples/openspending][xl]: implement dataset page v0.1, add pagination to the datasets grid

* [examples/openspending][m] - fix build + add tests

---------

Co-authored-by: Luccas Mateus de Medeiros Gomes <luccasmmg@gmail.com>
2023-05-18 21:19:01 -03:00
Luccas Mateus
2115a3fdb3 [examples/openspending][m] - table preview (#891)
* [examples/openspending][m] - table preview

* [examples/openspending][xs] - fix typo
2023-05-18 15:09:57 -03:00
38 changed files with 4349 additions and 391 deletions

1
.gitignore vendored
View File

@@ -16,6 +16,7 @@ node_modules
*.launch
.settings/
*.sublime-workspace
.obsidian
# IDE - VSCode
.vscode/*

View File

@@ -1,45 +1,138 @@
import { Octokit } from 'octokit';
import { assert, expect, test } from 'vitest'
import { getProjectDataPackage } from '../lib/octokit';
import { expect, test } from 'vitest';
import { getAllProjectsFromOrg, getProjectDataPackage } from '../lib/project';
import { loadDataPackage } from '../lib/loader';
import { getProjectMetadata } from '../lib/project';
import { getCsv, parseCsv } from '../components/Table';
export async function getAllDataPackagesFromOrg(
org: string,
branch?: string,
github_pat?: string
) {
const octokit = new Octokit({ auth: github_pat });
const repos = await octokit.rest.repos.listForOrg({ org, type: 'public', per_page: 100 });
let failedDataPackages = [];
const datapackages = await Promise.all(
repos.data.map(async (_repo) => {
test(
'Test OS-Data',
async () => {
const repos = await getAllProjectsFromOrg(
'os-data',
'main',
process.env.VITE_GITHUB_PAT
);
if (repos.failed.length > 0) console.log(repos.failed);
expect(repos.failed.length).toBe(0);
},
{ timeout: 100000 }
);
test(
'Test Gift-Data',
async () => {
const repos = await getAllProjectsFromOrg(
'gift-data',
'main',
process.env.VITE_GITHUB_PAT
);
if (repos.failed.length > 0) console.log(repos.failed);
expect(repos.failed.length).toBe(0);
},
{ timeout: 100000 }
);
test(
'Test getting one dataset from github',
async () => {
const datapackage = await getProjectDataPackage(
org,
_repo.name,
branch ? branch : 'main',
github_pat
'os-data',
'berlin-berlin',
'main',
process.env.VITE_GITHUB_PAT
);
if (!datapackage) {
failedDataPackages.push(_repo.name)
return null
};
return {...datapackage, repo: _repo.name};
})
const repo = await getProjectMetadata(
'os-data',
'berlin-berlin',
process.env.VITE_GITHUB_PAT
);
return {
datapackages: datapackages.filter((item) => item !== null),
failedDataPackages,
};
}
test('Test OS-Data', async () => {
const repos = await getAllDataPackagesFromOrg('os-data', 'main', process.env.VITE_GITHUB_PAT)
if (repos.failedDataPackages.length > 0) console.log(repos.failedDataPackages)
expect(repos.failedDataPackages.length).toBe(0)
}, {timeout: 100000})
test('Test Gift-Data', async () => {
const repos = await getAllDataPackagesFromOrg('gift-data', 'main', process.env.VITE_GITHUB_PAT)
if (repos.failedDataPackages.length > 0) console.log(repos.failedDataPackages)
expect(repos.failedDataPackages.length).toBe(0)
}, {timeout: 100000})
const project = loadDataPackage(datapackage, repo);
delete project['datapackage'];
delete project.files[0]['dialect'];
delete project.files[0]['schema'];
expect(project).toStrictEqual({
name: 'berlin-berlin',
title: 'Berlin-Berlin',
description: null,
owner: {
name: 'os-data',
logo: 'https://avatars.githubusercontent.com/u/13695166?v=4',
title: 'os-data',
},
repo: {
name: 'berlin-berlin',
full_name: 'os-data/berlin-berlin',
url: 'https://github.com/os-data/berlin-berlin',
},
files: [
{
name: 'berlin-gesamt',
format: 'csv',
path: 'https://storage.openspending.org/berlin-berlin/berlin-gesamt.csv',
mediatype: 'text/csv',
bytes: 81128743,
encoding: 'utf-8',
},
],
author: 'Michael Peters <michael.peters@okfn.de>',
cityCode: 'Berlin',
countryCode: 'DE',
fiscalPeriod: { start: '2014-01-01', end: '2019-12-31' },
readme: '',
});
},
{ timeout: 100000 }
);
test(
'Test getting one section of csv from R2',
async () => {
const rawCsv = await getCsv(
'https://storage.openspending.org/state-of-minas-gerais-brazil-planned-budget/__os_imported__br-mg-ppagloc.csv'
);
const parsedCsv = await parseCsv(rawCsv);
expect(parsedCsv.errors.length).toBe(1);
expect(parsedCsv.data.length).toBe(10165);
expect(parsedCsv.meta.fields).toStrictEqual([
'function_name',
'function_label',
'product_name',
'product_label',
'area_name',
'area_label',
'subaction_name',
'subaction_label',
'region_label_map',
'region_reg_map',
'region_name',
'region_label',
'municipality_map_id',
'municipality_name',
'municipality_map_code',
'municipality_label',
'municipality_map_name_simple',
'municipality_map_name',
'cofog1_label_en',
'cofog1_name',
'cofog1_label',
'amount',
'subprogramme_name',
'subprogramme_label',
'time_name',
'time_year',
'time_month',
'time_day',
'time_week',
'time_yearmonth',
'time_quarter',
'time',
'action_name',
'action_label',
'subfunction_name',
'subfunction_label',
'programme_name',
'programme_label',
]);
},
{ timeout: 100000 }
);

View File

@@ -9,7 +9,7 @@ export default function DatasetCard({ dataset }: { dataset: Project }) {
className="overflow-hidden rounded-xl border border-gray-200"
>
<Link
href=""
href={`/@${dataset.owner.name}/${dataset.repo.name}`}
className="flex items-center gap-x-4 border-b border-gray-900/5 bg-gray-50 p-6"
>
<img
@@ -60,8 +60,8 @@ export default function DatasetCard({ dataset }: { dataset: Project }) {
<dd className="flex items-start gap-x-2">
<div className="font-medium text-gray-900">
<Link
// TODO: where do we get the info needed for this link?
href=""
// TODO: this link may be incorrect for some datasets
href={`https://github.com/${dataset.owner.name}/${dataset.repo.name}/blob/main/datapackage.json`}
target="_blank"
className="flex items-center hover:text-gray-700"
>

View File

@@ -2,9 +2,26 @@ import { useForm } from 'react-hook-form';
import DatasetsGrid from './DatasetsGrid';
import { Project } from '../lib/project.interface';
import { Index } from 'flexsearch';
import {
ChevronDoubleLeftIcon,
ChevronDoubleRightIcon,
ChevronLeftIcon,
ChevronRightIcon,
} from '@heroicons/react/24/solid';
import { useState } from 'react';
export default function DatasetsSearch({
datasets,
availableCountries,
}: {
datasets: Project[];
availableCountries;
}) {
const itemsPerPage = 6;
const [page, setPage] = useState(1);
export default function DatasetsSearch({ datasets }: { datasets: Project[] }) {
const index = new Index({ tokenize: 'full' });
datasets.forEach((dataset: Project) =>
index.add(
dataset.name,
@@ -21,94 +38,7 @@ export default function DatasetsSearch({ datasets }: { datasets: Project[] }) {
},
});
const allCountries = datasets
.map((item) => item.countryCode)
.filter((v) => v) // Filters false values
.filter((v, i, a) => a.indexOf(v) === i) // Remove duplicates
// TODO: title should be the full name
.map((code) => ({ code, title: code }));
return (
<>
<div className="flex flex-col gap-3 sm:flex-row">
<div className="min-w-0 flex-auto">
<br />
<div className="relative">
<input
placeholder="Search datasets"
aria-label="Search datasets"
{...register('searchTerm')}
className="h-[3em] relative w-full rounded-lg bg-white py-2 pl-3 pr-10 text-left shadow-md focus:outline-none focus-visible:border-emerald-500 focus-visible:ring-2 focus-visible:ring-white focus-visible:ring-opacity-75 focus-visible:ring-offset-2 focus-visible:ring-offset-emerald-400 sm:text-sm"
/>
{watch().searchTerm !== '' && (
<button
onClick={() => resetField('searchTerm')}
className="absolute right-3 top-1/2 -translate-y-1/2 text-gray-500"
>
<CloseIcon />
</button>
)}
</div>
</div>
<div className="sm:basis-1/6">
{/* TODO: nicer select e.g. headlessui example */}
<label className="text-sm text-gray-600 font-medium">Country</label>
<select
className="h-[3em] w-full rounded-lg bg-white py-2 pl-3 pr-10 text-left shadow-md focus:outline-none focus-visible:border-emerald-500 focus-visible:ring-2 focus-visible:ring-white focus-visible:ring-opacity-75 focus-visible:ring-offset-2 focus-visible:ring-offset-emerald-400 sm:text-sm"
{...register('country')}
>
<option value="">All</option>
{allCountries.map((country) => {
return (
<option key={country.code} value={country.code}>
{country.title}
</option>
);
})}
</select>
</div>
<div className="sm:basis-1/6">
<label className="text-sm text-gray-600 font-medium">Min. date</label>
<div className="relative">
<input
aria-label="Min. date"
type="date"
{...register('minDate')}
className="h-[3em] w-full rounded-lg bg-white py-2 pl-3 pr-10 text-left shadow-md focus:outline-none focus-visible:border-emerald-500 focus-visible:ring-2 focus-visible:ring-white focus-visible:ring-opacity-75 focus-visible:ring-offset-2 focus-visible:ring-offset-emerald-400 sm:text-sm"
/>
{watch().minDate !== '' && (
<button
onClick={() => resetField('minDate')}
className="absolute right-3 top-1/2 -translate-y-1/2 text-gray-500"
>
<CloseIcon />
</button>
)}
</div>
</div>
<div className="sm:basis-1/6">
<label className="text-sm text-gray-600 font-medium">Max. date</label>
<div className="relative">
<input
aria-label="Max. date"
type="date"
{...register('maxDate')}
className="h-[3em] w-full rounded-lg bg-white py-2 pl-3 pr-10 text-left shadow-md focus:outline-none focus-visible:border-emerald-500 focus-visible:ring-2 focus-visible:ring-white focus-visible:ring-opacity-75 focus-visible:ring-offset-2 focus-visible:ring-offset-emerald-400 sm:text-sm"
/>
{watch().maxDate !== '' && (
<button
onClick={() => resetField('maxDate')}
className="absolute right-3 top-1/2 -translate-y-1/2 text-gray-500"
>
<CloseIcon />
</button>
)}
</div>
</div>
</div>
<div className="min-w-full mt-10 align-middle">
<DatasetsGrid
datasets={datasets
const filteredDatasets = datasets
.filter((dataset: Project) =>
watch().searchTerm && watch().searchTerm !== ''
? index.search(watch().searchTerm).includes(dataset.name)
@@ -132,8 +62,121 @@ export default function DatasetsSearch({ datasets }: { datasets: Project[] }) {
watch().maxDate && watch().maxDate !== ''
? dataset.fiscalPeriod?.end <= watch().maxDate
: true
)}
);
const paginatedDatasets = filteredDatasets.slice(
(page - 1) * itemsPerPage,
(page - 1) * itemsPerPage + itemsPerPage
);
const pageCount = Math.ceil(filteredDatasets.length / itemsPerPage) || 1;
return (
<>
<div className="flex flex-col gap-3 sm:flex-row">
<div className="min-w-0 flex-auto">
<br />
<div className="relative">
<input
placeholder="Search datasets"
aria-label="Search datasets"
{...register('searchTerm', { onChange: () => setPage(1) })}
className="h-[3em] relative w-full rounded-lg bg-white py-2 pl-3 pr-10 text-left shadow-md focus:outline-none focus-visible:border-emerald-500 focus-visible:ring-2 focus-visible:ring-white focus-visible:ring-opacity-75 focus-visible:ring-offset-2 focus-visible:ring-offset-emerald-400 sm:text-sm"
/>
{watch().searchTerm !== '' && (
<button
onClick={() => resetField('searchTerm')}
className="absolute right-3 top-1/2 -translate-y-1/2 text-gray-500"
>
<CloseIcon />
</button>
)}
</div>
</div>
<div className="sm:basis-1/6">
{/* TODO: nicer select e.g. headlessui example */}
<label className="text-sm text-gray-600 font-medium">Country</label>
<select
className="h-[3em] w-full rounded-lg bg-white py-2 pl-3 pr-10 text-left shadow-md focus:outline-none focus-visible:border-emerald-500 focus-visible:ring-2 focus-visible:ring-white focus-visible:ring-opacity-75 focus-visible:ring-offset-2 focus-visible:ring-offset-emerald-400 sm:text-sm"
{...register('country', { onChange: () => setPage(1) })}
>
<option value="">All</option>
{availableCountries.map((country) => {
return (
<option key={country.code} value={country.code}>
{country.title}
</option>
);
})}
</select>
</div>
<div className="sm:basis-1/6">
<label className="text-sm text-gray-600 font-medium">Min. date</label>
<div className="relative">
<input
aria-label="Min. date"
type="date"
{...register('minDate', { onChange: () => setPage(1) })}
className="h-[3em] w-full rounded-lg bg-white py-2 pl-3 pr-10 text-left shadow-md focus:outline-none focus-visible:border-emerald-500 focus-visible:ring-2 focus-visible:ring-white focus-visible:ring-opacity-75 focus-visible:ring-offset-2 focus-visible:ring-offset-emerald-400 sm:text-sm"
/>
</div>
</div>
<div className="sm:basis-1/6">
<label className="text-sm text-gray-600 font-medium">Max. date</label>
<div className="relative">
<input
aria-label="Max. date"
type="date"
{...register('maxDate', { onChange: () => setPage(1) })}
className="h-[3em] w-full rounded-lg bg-white py-2 pl-3 pr-10 text-left shadow-md focus:outline-none focus-visible:border-emerald-500 focus-visible:ring-2 focus-visible:ring-white focus-visible:ring-opacity-75 focus-visible:ring-offset-2 focus-visible:ring-offset-emerald-400 sm:text-sm"
/>
</div>
</div>
</div>
<div className="mt-5 mb-5">
<span className="text-lg font-medium">
{filteredDatasets.length} datasets found
</span>
</div>
<div className="min-w-full align-middle">
<DatasetsGrid datasets={paginatedDatasets} />
<div className="w-full flex justify-center mt-10">
<button
onClick={() => setPage(1)}
disabled={page <= 1}
className="disabled:text-gray-400"
>
<ChevronDoubleLeftIcon className="w-6 h-6" />
</button>
<button
onClick={() => {
if (page > 1) setPage((prev) => --prev);
}}
disabled={page <= 1}
className="disabled:text-gray-400"
>
<ChevronLeftIcon className="w-6 h-6" />
</button>
<span className="mx-5">
Page {page} of {pageCount}
</span>
<button
onClick={() => {
if (page < pageCount) setPage((prev) => ++prev);
}}
disabled={page >= pageCount}
className="disabled:text-gray-400"
>
<ChevronRightIcon className="w-6 h-6" />
</button>
<button
onClick={() => setPage(pageCount)}
disabled={page >= pageCount}
className="disabled:text-gray-400"
>
<ChevronDoubleRightIcon className="w-6 h-6" />
</button>
</div>
</div>
</>
);

View File

@@ -1,53 +1,82 @@
import Image from 'next/image'
import { Button } from './Button'
import { Container } from './Container'
import logo from "../public/logo.svg"
import Link from 'next/link'
import { useRouter } from 'next/router'
import Image from 'next/image';
import { Container } from './Container';
import logo from '../public/logo.svg';
import Link from 'next/link';
import { useRouter } from 'next/router';
import { Bars3Icon } from '@heroicons/react/24/outline';
import { useState } from 'react';
export function Header() {
const [menuOpen, setMenuOpen] = useState<boolean>(false);
const router = useRouter();
const isActive = (navLink) => {
return router.asPath.split("?")[0] == navLink.href;
}
return router.asPath.split('?')[0] == navLink.href;
};
const navLinks = [
{
title: "Home",
href: "/#header"
title: 'Home',
href: '/',
},
{
title: "Datasets",
href: "/#datasets"
title: 'Datasets',
href: '/#datasets',
},
{
title: "Community",
href: "https://community.openspending.org/"
}
]
// {
// title: "Community",
// href: "https://community.openspending.org/"
// }
];
return (
<header className="z-50 pb-5 lg:pt-11 sticky top-0 backdrop-blur" id="header">
<Container className="flex flex-wrap items-center justify-center sm:justify-between lg:flex-nowrap">
<div className="mt-10 lg:mt-0 lg:grow lg:basis-0 flex items-center">
<header className="relative z-50 pb-11 lg:pt-11">
<Container className="flex flex-wrap items-center justify-between lg:flex-nowrap mt-10 lg:mt-0">
<Link href="/" className="lg:mt-0 lg:grow lg:basis-0 flex items-center">
<Image src={logo} alt="OpenSpending" className="h-12 w-auto" />
</div>
<ul className='list-none flex gap-x-5 text-base font-medium'>
</Link>
<ul className="hidden list-none sm:flex gap-x-5 text-base font-medium">
{navLinks.map((link, i) => (
<li key={`nav-link-${i}`}>
<Link
className={`text-emerald-900 hover:text-emerald-600 ${isActive(link) ? "text-emerald-600" : ""}`}
className={`text-emerald-900 hover:text-emerald-600 ${
isActive(link) ? 'text-emerald-600' : ''
}`}
href={link.href}
scroll={false}
>
{link.title}
</Link>
</li>))}
</li>
))}
</ul>
<div className="hidden sm:mt-10 sm:flex lg:mt-0 lg:grow lg:basis-0 lg:justify-end">
<div className="hidden xl:block xl:grow"></div>
<div className="sm:hidden sm:mt-10 lg:mt-0 lg:grow lg:basis-0 lg:justify-end">
<button onClick={() => setMenuOpen(!menuOpen)}>
<Bars3Icon className="w-8 h-8" />
</button>
</div>
{menuOpen && (
<div className={`sm:hidden basis-full mt-5 text-center`}>
<ul className="gap-x-5 text-base font-medium">
{navLinks.map((link, i) => (
<li key={`nav-link-${i}`}>
<Link
className={`text-emerald-900 hover:text-emerald-600 ${
isActive(link) ? 'text-emerald-600' : ''
}`}
href={link.href}
scroll={false}
>
{link.title}
</Link>
</li>
))}
</ul>
</div>
)}
</Container>
</header >
)
</header>
);
}

View File

@@ -1,9 +1,9 @@
import { Button } from './Button'
import { Container } from './Container'
import { Button } from './Button';
import { Container } from './Container';
export function Hero() {
export function Hero({ countriesCount, datasetsCount, filesCount }) {
return (
<div className="relative pb-20 pt-10 sm:py-40">
<div className="relative pb-20 pt-10 sm:py-40" id="hero">
<div className="absolute inset-x-0 -bottom-14 -top-48 overflow-hidden bg-green-50 bg-opacity-50">
<div className="absolute inset-x-0 top-0 h-40 bg-gradient-to-b from-white" />
<div className="absolute inset-x-0 bottom-0 h-40 bg-gradient-to-t from-white" />
@@ -15,12 +15,13 @@ export function Hero() {
</h1>
<div className="mt-6 space-y-6 font-display text-2xl tracking-tight text-emerald-900">
<p>
By understanding how governments spend money in our name can we have a say
in how that money will affect our own lives. The journey starts here.
By understanding how governments spend money in our name can we
have a say in how that money will affect our own lives. The
journey starts here.
</p>
<p>
OpenSpending is a free, open and global platform to search, visualise and analyse
fiscal data in the public sphere.
OpenSpending is a free, open and global platform to search,
visualise and analyse fiscal data in the public sphere.
</p>
</div>
<Button href="#datasets" className="mt-10">
@@ -28,9 +29,11 @@ export function Hero() {
</Button>
<dl className="mt-10 grid grid-cols-2 gap-x-10 gap-y-6 sm:mt-16 sm:gap-x-16 sm:gap-y-10 sm:text-center lg:auto-cols-auto lg:grid-flow-col lg:grid-cols-none lg:justify-start lg:text-left">
{[
['Countries', '75'],
['Datasets', '2091'],
['Files', '9230'],
// Added the plus sign because some datasets do not
// contain defined countries
['Countries', '+' + countriesCount],
['Datasets', datasetsCount],
['Files', filesCount],
].map(([name, value]) => (
<div key={name}>
<dt className="font-mono text-sm text-emerald-600">{name}</dt>
@@ -43,5 +46,5 @@ export function Hero() {
</div>
</Container>
</div>
)
);
}

View File

@@ -0,0 +1,94 @@
import {
QueryClient,
QueryClientProvider,
useQuery,
useQueryClient,
} from 'react-query';
import Papa from 'papaparse';
import { Grid } from '@githubocto/flat-ui';
const queryClient = new QueryClient();
export async function getCsv(url: string) {
const response = await fetch(url, {
headers: {
Range: 'bytes=0-5132288',
},
});
const data = await response.text();
return data;
}
export async function parseCsv(file: string): Promise<any> {
return new Promise((resolve, reject) => {
Papa.parse(file, {
header: true,
dynamicTyping: true,
skipEmptyLines: true,
transform: (value: string): string => {
return value.trim();
},
complete: (results: any) => {
return resolve(results);
},
error: (error: any) => {
return reject(error);
},
});
});
}
const Spinning = () => {
return (
<div role="status w-fit mx-auto">
<svg
aria-hidden="true"
className="w-8 h-8 mr-2 text-gray-200 animate-spin dark:text-gray-600 fill-emerald-600"
viewBox="0 0 100 101"
fill="none"
xmlns="http://www.w3.org/2000/svg"
>
<path
d="M100 50.5908C100 78.2051 77.6142 100.591 50 100.591C22.3858 100.591 0 78.2051 0 50.5908C0 22.9766 22.3858 0.59082 50 0.59082C77.6142 0.59082 100 22.9766 100 50.5908ZM9.08144 50.5908C9.08144 73.1895 27.4013 91.5094 50 91.5094C72.5987 91.5094 90.9186 73.1895 90.9186 50.5908C90.9186 27.9921 72.5987 9.67226 50 9.67226C27.4013 9.67226 9.08144 27.9921 9.08144 50.5908Z"
fill="currentColor"
/>
<path
d="M93.9676 39.0409C96.393 38.4038 97.8624 35.9116 97.0079 33.5539C95.2932 28.8227 92.871 24.3692 89.8167 20.348C85.8452 15.1192 80.8826 10.7238 75.2124 7.41289C69.5422 4.10194 63.2754 1.94025 56.7698 1.05124C51.7666 0.367541 46.6976 0.446843 41.7345 1.27873C39.2613 1.69328 37.813 4.19778 38.4501 6.62326C39.0873 9.04874 41.5694 10.4717 44.0505 10.1071C47.8511 9.54855 51.7191 9.52689 55.5402 10.0491C60.8642 10.7766 65.9928 12.5457 70.6331 15.2552C75.2735 17.9648 79.3347 21.5619 82.5849 25.841C84.9175 28.9121 86.7997 32.2913 88.1811 35.8758C89.083 38.2158 91.5421 39.6781 93.9676 39.0409Z"
fill="currentFill"
/>
</svg>
<span className="sr-only">Loading...</span>
</div>
);
};
export const Table: React.FC<{ url: string }> = ({ url }) => {
return (
// Provide the client to your App
<QueryClientProvider client={queryClient}>
<TableInner url={url} />
</QueryClientProvider>
);
};
const TableInner: React.FC<{ url: string }> = ({ url }) => {
const { data: csvString, isLoading: isDownloadingCSV } = useQuery(
['dataCsv', url],
() => getCsv(url)
);
const { data: parsedData, isLoading: isParsing } = useQuery(
['dataPreview', csvString],
() => parseCsv(csvString),
{ enabled: !!csvString }
);
if (isParsing || isDownloadingCSV)
<div className="w-full">
<Spinning />
</div>;
if (parsedData)
return (
<div className="h-[500px] overflow-scroll">
<Grid data={parsedData.data} />
</div>
);
};

View File

@@ -0,0 +1,10 @@
import { Header } from '../Header';
export default function Layout({ children }) {
return (
<div className="bg-white min-h-screen">
<Header />
{children}
</div>
);
}

View File

@@ -1,27 +0,0 @@
[
{
"owner": "os-data",
"branch": "main",
"name": "mongolia-budget-2016-2017"
},
{
"owner": "os-data",
"branch": "main",
"name": "gb-country-regional-analysis"
},
{
"owner": "os-data",
"branch": "main",
"name": "berlin-berlin"
},
{
"owner": "os-data",
"branch": "main",
"name": "state-of-minas-gerais-brazil-planned-budget"
},
{
"owner": "os-data",
"branch": "main",
"name": "wesel"
}
]

View File

@@ -98,6 +98,7 @@ export interface TabularDataResource {
key?: string;
path?: string;
size?: number;
bytes?: number;
}
export interface Field {

View File

@@ -5,13 +5,14 @@ export function loadDataPackage(datapackage: FiscalDataPackage, repo): Project {
return {
name: datapackage.name,
title: datapackage.title,
description: datapackage.description || null,
owner: {
name: repo.owner.login,
logo: repo.owner.avatar_url,
// TODO: make this title work
title: repo.owner.login,
},
repo: { name: repo, full_name: repo.full_name },
repo: { name: repo.name, full_name: repo.full_name, url: repo.html_url },
files: datapackage.resources,
author: datapackage.author ? datapackage.author : null,
cityCode: datapackage.cityCode ? datapackage.cityCode : null,

View File

@@ -5,10 +5,11 @@ import {
export interface Project {
owner: { name: string; logo?: string; title?: string }; // Info about the owner of the data repo
repo: { name: string; full_name: string }; // Info about the the data repo
repo: { name: string; full_name: string; url: string }; // Info about the the data repo
files: TabularDataResource[];
name: string;
title?: string;
description?: string;
author?: string;
cityCode?: string;
countryCode?: string;

View File

@@ -13,8 +13,7 @@ export interface GithubProject {
export async function getProjectReadme(
owner: string,
repo: string,
branch: string,
readme: string,
branch: string = 'main',
github_pat?: string
) {
const octokit = new Octokit({ auth: github_pat });
@@ -22,7 +21,7 @@ export async function getProjectReadme(
const response = await octokit.rest.repos.getContent({
owner,
repo,
path: readme,
path: 'README.md',
ref: branch,
});
const data = response.data as { content?: string };
@@ -125,7 +124,6 @@ export async function getProject(project: GithubProject, github_pat?: string) {
project.owner,
project.repo,
project.branch,
project.readme,
github_pat
);
@@ -185,8 +183,43 @@ export async function getProjectDataPackage(
}
const decodedContent = Buffer.from(fileContent, 'base64').toString();
const datapackage = JSON.parse(decodedContent);
return {...datapackage, repo };
return { ...datapackage, repo };
} catch (error) {
return null;
}
}
export async function getAllProjectsFromOrg(
org: string,
branch?: string,
github_pat?: string
) {
const octokit = new Octokit({ auth: github_pat });
const repos = await octokit.rest.repos.listForOrg({
org,
type: 'public',
per_page: 100,
});
let failedProjects = [];
const projects = await Promise.all(
repos.data.map(async (_repo) => {
const project = await getProjectDataPackage(
org,
_repo.name,
branch ? branch : 'main',
github_pat
);
if (!project) {
failedProjects.push(_repo.name);
return null;
}
return { datapackage: project, repo: _repo };
})
);
return {
results: projects.filter((item) => item !== null),
failed: failedProjects,
};
}

View File

@@ -0,0 +1,3 @@
[
"os-data"
]

File diff suppressed because it is too large Load Diff

View File

@@ -10,6 +10,8 @@
"test": "vitest"
},
"dependencies": {
"@githubocto/flat-ui": "^0.14.1",
"@heroicons/react": "^2.0.18",
"@octokit/plugin-throttling": "^5.2.2",
"@types/flexsearch": "^0.7.3",
"@types/node": "18.16.0",
@@ -23,17 +25,20 @@
"next": "13.3.1",
"next-seo": "^6.0.0",
"octokit": "^2.0.14",
"papaparse": "^5.4.1",
"prettier": "^2.8.8",
"react": "18.2.0",
"react-dom": "18.2.0",
"react-hook-form": "^7.43.9",
"react-markdown": "^8.0.7",
"react-query": "^3.39.3",
"react-timeago": "^7.1.0",
"remark-gfm": "^3.0.1",
"typescript": "5.0.4"
},
"devDependencies": {
"@tailwindcss/typography": "^0.5.9",
"@types/papaparse": "^5.3.7",
"autoprefixer": "^10.4.14",
"postcss": "^8.4.23",
"tailwindcss": "^3.3.1",

View File

@@ -1,126 +0,0 @@
import { NextSeo } from 'next-seo';
import { promises as fs } from 'fs';
import path from 'path';
import getConfig from 'next/config';
import { getProject, GithubProject } from '../../../lib/octokit';
import ReactMarkdown from 'react-markdown';
import remarkGfm from 'remark-gfm';
import Breadcrumbs from '../../../components/_shared/Breadcrumbs';
export default function ProjectPage({ project }) {
const repoId = `@${project.repo_config.owner}/${project.repo_config.repo}`
return (
<>
<NextSeo title={`${repoId}${project.base_path !== '/' ? '/' + project.base_path : ''} - GitHub Datasets`} />
<main className="prose mx-auto my-8">
<Breadcrumbs links={[{ title: repoId, href: "" }]} />
<h1 className="mb-0 mt-16">{project.repo_config.name || repoId}</h1>
<p className='mb-8'><span className='font-semibold'>Repository:</span> <a target="_blank" href={project.html_url}>{project.html_url}</a></p>
<h2 className="mb-0 mt-10">Files</h2>
<div className="inline-block min-w-full py-2 align-middle">
<table className="min-w-full divide-y divide-gray-300">
<thead>
<tr>
<th
scope="col"
className="px-3 py-3.5 text-left text-sm font-semibold text-gray-900"
>
Name
</th>
<th
scope="col"
className="px-3 py-3.5 text-left text-sm font-semibold text-gray-900"
>
Size
</th>
</tr>
</thead>
<tbody className="divide-y divide-gray-200">
{project.files?.map((file) => (
<tr key={file.download_url}>
<td className="whitespace-nowrap px-3 py-4 text-sm text-gray-500">
<a href={file.download_url}>{file.name}</a>
</td>
<td className="whitespace-nowrap px-3 py-4 text-sm text-gray-500">
{file.size} Bytes
</td>
</tr>
))}
</tbody>
</table>
</div>
{project.readmeContent && <>
<hr />
<h2 className='uppercase font-black'>Readme</h2>
<ReactMarkdown remarkPlugins={[remarkGfm]}>
{project.readmeContent}
</ReactMarkdown>
</>}
</main>
</>
);
}
// Generates `/posts/1` and `/posts/2`
export async function getStaticPaths() {
const jsonDirectory = path.join(
process.cwd(),
'datasets.json'
);
const repos = await fs.readFile(jsonDirectory, 'utf8');
return {
paths: JSON.parse(repos).map((repo) => {
const projectPath =
repo.readme && repo.readme.split('/').length > 1
? repo.readme.split('/').slice(0, -1)
: null;
let path = [repo.name];
if (projectPath) {
projectPath.forEach((element) => {
path.push(element);
});
}
return {
params: { org: repo.owner, path },
};
}),
fallback: false, // can also be true or 'blocking'
};
}
export async function getStaticProps({ params }) {
const jsonDirectory = path.join(
process.cwd(),
'datasets.json'
);
const reposFile = await fs.readFile(jsonDirectory, 'utf8');
const repos: GithubProject[] = JSON.parse(reposFile);
const repo = repos.find((_repo) => {
const projectPath =
_repo.readme && _repo.readme.split('/').length > 1
? _repo.readme.split('/').slice(0, -1)
: null;
let path = [_repo.name];
if (projectPath) {
projectPath.forEach((element) => {
path.push(element);
});
}
return (
_repo.owner == params.org &&
JSON.stringify(path) === JSON.stringify(params.path)
);
});
const github_pat = getConfig().serverRuntimeConfig.github_pat;
const project = await getProject(repo, github_pat);
return {
props: {
project: { ...project, repo_config: repo },
},
};
}

View File

@@ -0,0 +1,234 @@
import { NextSeo } from 'next-seo';
import getConfig from 'next/config';
import {
getAllProjectsFromOrg,
getProjectDataPackage,
getProjectMetadata,
getProjectReadme,
} from '../../../lib/project';
import ReactMarkdown from 'react-markdown';
import remarkGfm from 'remark-gfm';
import { loadDataPackage } from '../../../lib/loader';
import Layout from '../../../components/_shared/Layout';
import Link from 'next/link';
import { Project } from '../../../lib/project.interface';
import ExternalLinkIcon from '../../../components/icons/ExternalLinkIcon';
export default function ProjectPage({
project,
readme,
}: {
project: Project;
readme: string;
}) {
// Get description from datapackage or calculate
// excerpt from README by getting all the content
// up to the first dot.
const description =
project.description || (readme && readme.slice(0, readme.indexOf('.') + 1));
return (
<Layout>
<NextSeo title={`${project.title} - OpenSpending`} />
<main className="prose mx-auto my-8">
<h1 className="mb-1 mt-16">{project.title || project.name}</h1>
<Link target="_blank" href={project.repo.url}>
@{project.repo.full_name}
</Link>
{description && (
<div className="inline-block min-w-full py-2 align-middle mt-5">
{description}
</div>
)}
<div className="inline-block min-w-full py-2 align-middle">
<table className="min-w-full divide-y divide-gray-300">
<thead>
<tr>
<th
scope="col"
className="px-3 py-3.5 text-left text-sm font-semibold text-gray-900"
>
Name
</th>
{project.datapackage.countryCode && (
<th
scope="col"
className="px-3 py-3.5 text-left text-sm font-semibold text-gray-900"
>
Country
</th>
)}
<th
scope="col"
className="px-3 py-3.5 text-left text-sm font-semibold text-gray-900"
>
Metadata
</th>
</tr>
</thead>
<tbody className="divide-y divide-gray-200">
<tr>
<td className="whitespace-nowrap px-3 py-4 text-sm text-gray-500">
{project.name}
</td>
{project.datapackage.countryCode && (
<td className="whitespace-nowrap px-3 py-4 text-sm text-gray-500">
{project.datapackage.countryCode}
</td>
)}
<td className="whitespace-nowrap px-3 py-4 text-sm text-gray-500">
<Link
// TODO: this link may be incorrect for some datasets
href={`https://github.com/${project.owner.name}/${project.repo.name}/blob/main/datapackage.json`}
target="_blank"
className="flex items-center hover:text-gray-700"
>
datapackage.json <ExternalLinkIcon className="ml-1" />
</Link>
</td>
</tr>
</tbody>
</table>
</div>
<h3 className="mb-1 mt-10">Data files</h3>
<p>
This dataset contains {project.files.length} file
{project.files.length != 1 ? '' : 's'}
</p>
<div className="inline-block min-w-full py-2 align-middle">
<table className="mt-0 min-w-full divide-y divide-gray-300">
<thead>
<tr>
<th
scope="col"
className="px-3 py-3.5 text-left text-sm font-semibold text-gray-900"
>
Name
</th>
<th
scope="col"
className="px-3 py-3.5 text-left text-sm font-semibold text-gray-900"
>
Format
</th>
<th
scope="col"
className="px-3 py-3.5 text-left text-sm font-semibold text-gray-900"
>
Size
</th>
</tr>
</thead>
<tbody className="divide-y divide-gray-200">
{project.files?.map((file) => {
let size: number | string = file.size;
if (!size) {
if (file.bytes) {
if (file.bytes > 1000000) {
size = (file.bytes / 1000000).toFixed(2) + ' MB';
} else {
size = (file.bytes / 1000).toFixed(2) + ' kB';
}
}
}
return (
<tr key={file.name}>
<td className="whitespace-nowrap px-3 py-4 text-sm text-gray-500">
{file.name}
</td>
<td className="whitespace-nowrap px-3 py-4 text-sm text-gray-500">
{file.format}
</td>
<td className="whitespace-nowrap px-3 py-4 text-sm text-gray-500">
{size}
</td>
<td className="whitespace-nowrap px-3 py-4 text-sm text-gray-500">
<Link
target="_blank"
href={
file.path.startsWith('http')
? file.path
: `https://raw.githubusercontent.com/${project.owner.name}/${project.repo.name}/main/${file.path}`
}
>
Download
</Link>
</td>
</tr>
);
})}
</tbody>
</table>
</div>
{readme && (
<>
<hr />
<h2 className="uppercase font-black">Readme</h2>
<ReactMarkdown remarkPlugins={[remarkGfm]}>{readme}</ReactMarkdown>
</>
)}
</main>
</Layout>
);
}
// Generates `/posts/1` and `/posts/2`
export async function getStaticPaths() {
const github_pat = getConfig().serverRuntimeConfig.github_pat;
const allProjects = await getAllProjectsFromOrg(
'os-data',
'main',
github_pat
);
console.log(allProjects)
const paths = allProjects.results.map((project) => ({
params: {
// TODO: dynamize the org
org: 'os-data',
project: project.repo.name,
},
}));
return {
paths,
fallback: false, // can also be true or 'blocking'
};
}
export async function getStaticProps({ params }) {
const { org: orgName, project: projectName } = params;
const github_pat = getConfig().serverRuntimeConfig.github_pat;
const datapackage = await getProjectDataPackage(
orgName,
projectName,
'main',
github_pat
);
const repo = await getProjectMetadata(orgName, projectName, github_pat);
const project = loadDataPackage(datapackage, repo);
// TODO: should this be moved to the loader?
const readme = await getProjectReadme(orgName, projectName, 'main', github_pat);
return {
props: {
project,
readme,
},
};
}

View File

@@ -1,13 +1,11 @@
import { AppProps } from 'next/app';
import Head from 'next/head';
import './styles.css';
import { NextSeo } from 'next-seo';
function CustomApp({ Component, pageProps }: AppProps) {
return (
<>
<Head>
<title>GitHub Datasets</title>
</Head>
<NextSeo title="OpenSpending" />
<main className="app">
<Component {...pageProps} />
</main>

View File

@@ -1,65 +1,58 @@
import { promises as fs } from 'fs';
import path from 'path';
import {
GithubProject,
getProjectDataPackage,
getProjectMetadata,
} from '../lib/octokit';
import { getAllProjectsFromOrg } from '../lib/project';
import getConfig from 'next/config';
import ExternalLinkIcon from '../components/icons/ExternalLinkIcon';
import TimeAgo from 'react-timeago';
import Link from 'next/link';
import { Hero } from '../components/Hero';
import { Header } from '../components/Header';
import { Container } from '../components/Container';
import { FiscalDataPackage } from '../lib/datapackage.interface';
import { loadDataPackage } from '../lib/loader';
import DatasetsSearch from '../components/DatasetsSearch';
import Layout from '../components/_shared/Layout';
export async function getStaticProps() {
const jsonDirectory = path.join(process.cwd(), '/datasets.json');
const repos = await fs.readFile(jsonDirectory, 'utf8');
// TODO: support other orgs
// const orgsListPath = path.join(process.cwd(), '/orgs.json');
// const orgs = await fs.readFile(orgsListPath, 'utf8');
const github_pat = getConfig().serverRuntimeConfig.github_pat;
const datapackages = await Promise.all(
JSON.parse(repos).map(async (_repo: GithubProject) => {
const datapackage = await getProjectDataPackage(
_repo.owner,
_repo.name,
const allProjects = await getAllProjectsFromOrg(
'os-data',
'main',
github_pat
);
const repo = await getProjectMetadata(
_repo.owner,
_repo.name,
github_pat
);
return {
datapackage,
repo,
};
})
);
const projects = datapackages.map(
const projects = allProjects.results.map(
(item: { datapackage: FiscalDataPackage & { repo: string }; repo: any }) =>
loadDataPackage(item.datapackage, item.repo)
);
const availableCountries = projects
.map((item) => item.countryCode)
.filter((v) => v) // Filters false values
.filter((v, i, a) => a.indexOf(v) === i) // Remove duplicates
// TODO: title should be the full name
.map((code) => ({ code, title: code }));
return {
props: {
projects: JSON.stringify(projects),
availableCountries,
},
};
}
export function Datasets({ projects }) {
export function Home({ projects, availableCountries }) {
projects = JSON.parse(projects);
return (
<div className="bg-white min-h-screen">
<Header />
<Hero />
<Layout>
<Hero
countriesCount={availableCountries.length}
datasetsCount={projects.length}
filesCount={projects.reduce(
(partialSum, a) => partialSum + a.files.length,
0
)}
/>
<section className="py-20 sm:py-32">
<Container>
<div className="mx-auto max-w-2xl lg:mx-0">
@@ -74,12 +67,15 @@ export function Datasets({ projects }) {
</p>
</div>
<div className="mt-10">
<DatasetsSearch datasets={projects} />
<DatasetsSearch
datasets={projects}
availableCountries={availableCountries}
/>
</div>
</Container>
</section>
</div>
</Layout>
);
}
export default Datasets;
export default Home;

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.4 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 193 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 92 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 18 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 20 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 114 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 23 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 48 KiB

View File

@@ -0,0 +1,270 @@
---
title: Learn how to use MarkdownDB with our First Tutorial!
description: We've just released our first tutorial that covers the fundamentals of MarkdownDB - our new package for treating markdown files as a database. If you've been curious about how to manage your markdown files more effectively, check it out!
date: 2023-05-26
author: Ola Rubaj
---
We've just released our first tutorial that covers the fundamentals of [MarkdownDB](https://github.com/datopian/markdowndb) - our new package for treating markdown files as a database. If you've been curious about how to manage your markdown files more effectively, this tutorial is an excellent starting point!
![Gif](/assets/blog/markdowndb.gif)
## What is MarkdownDB?
MarkdownDB can parse your markdown files, extract structured data (such as frontmatter, tags, back- and forward links and more), and create an index in a local SQLite database. It also provides a lightweight JavaScript API for querying the database and importing files into your application. With MarkdownDB, you have a powerful tool that allows you to efficiently query your markdown data.
[🔍 Click here to learn more!](https://github.com/datopian/markdowndb)
## What you're going to learn
This tutorial guides you through the steps of creating a small project catalog. In our case, we used our open-source projects on GitHub - but you could use anything! We use simple markdown files to describe each project and then display them with the MarkdownDB package.
## Step 1: Create a markdown file for each project
First, let's create a markdown file for each project. You can use real project details or make up some examples. For the sake of this tutorial, we'll create files for some of the projects we've built at Datopian.
```bash
mkdir projects
cd projects
touch markdowndb.md portaljs.md flowershow.md datapipes.md giftless.md data-cli.md
```
In each file we'll write some short info about a given project, like so:
```md
# What is MarkdownDB
MarkdownDB is a javascript library for treating markdown files as a database -- as a "MarkdownDB". Specifically, it:
- Parses your markdown files to extract structured data (frontmatter, tags, etc) and creates an index in a local SQLite database
- Provides a lightweight javascript API for querying the database and importing files into your application
```
## Step 2: Index markdown files into SQLite database
Once we have prepared our markdown files, we can store them (or more precisely - their metadata) in a database, so that we can then query it later for specific project files.
```bash
# npx @flowershow/markdowndb <path-to-folder-with-md-files>
npx @flowershow/markdowndb ./projects
```
The above command will output a `markdown.db` file in the directory where it was executed. So, in our case, the folder structure will look like this:
```
.
├── markdown.db
└── projects
├── data-cli.md
├── ...
└── portaljs.md
```
## Step 3: Explore the SQLite database
Now, let's explore the database. We can do it with any SQLite viewer, e.g. https://sqlitebrowser.org/. When we open the `markdown.db` file in the viewer, we'll see a list of tables:
- `files`: containing metadata of our markdown,
- `file_tags`: containing tags set in the frontmatter of our markdown files,
- `links`: containing wiki links, i.e. links between our markdown files,
- `tags`: containing all tags used in our markdown files.
In our case, the `files` table will look like this:
![[/assets/blog/sqlite-viewer.png]]
You can also explore the database from the command line, e.g.:
```bash
sqlite3 markdown.db
```
And then run SQL queries, e.g.:
```sql
SELECT * FROM files;
```
Which will output:
```bash
27ce406aac24e59af7a9f3c0c0a437c1d024152b|projects/data-cli.md|md|data-cli||{}
26b1b0b06a4f450646f9e22fc18ec069bf577d8c|projects/datapipes.md|md|datapipes||{}
dafdd0daf71a1b06db1988c57848dc36947375f4|projects/flowershow.md|md|flowershow||{}
32c8db33fb8758516bfefb6ab1f22d03b1e53a08|projects/giftless.md|md|giftless||{}
7e01cae193f12f5a4a9be2b89f22b429761bd313|projects/markdowndb.md|md|markdowndb||{}
5445349c6822704d6f531a83c2aca2e4f90de864|projects/portaljs.md|md|portaljs||{}
```
## Step 4: Query the database in the Node.js app
Now, let's write a simple script that will query the database for our projects and display them on the terminal.
First, let's create a new Node.js project:
```bash
mkdir projects-list
cd projects-list
npm init -y
```
Then, let's install the `@flowershow/markdowndb` package:
```bash
npm install @flowershow/markdowndb
```
Now, let's create a new file `index.js` and add the following code:
```js
import { MarkdownDB } from '@flowershow/markdowndb';
// change this to the path to your markdown.db file
const dbPath = 'markdown.db';
const client = new MarkdownDB({
client: 'sqlite3',
connection: {
filename: dbPath,
},
});
const mddb = await client.init();
// get all projects
const projects = await mddb.getFiles();
console.log(JSON.stringify(projects, null, 2));
process.exit(0);
```
Since we're using ES6 modules, we also need to add `"type": "module"` to our `package.json` file.
Before we run the above script, we need to make sure that the `dbPath` variable is pointing to our `markdown.db` file. If you want to store the database outside of your project folder, you can update the `dbPath` variable to point to the correct location. If you want to have it inside your project folder, you can copy it there, or simply re-run the `npx @flowershow/markdowndb <path-to-markdown-folder>` command from within your project folder.
Now, let's run the script:
```bash
node index.js
```
It should output the JSON with all our projects.
```json
[
{
"_id": "7e01cae193f12f5a4a9be2b89f22b429761bd313",
"file_path": "projects/markdowndb.md",
"extension": "md",
"url_path": "markdowndb",
"filetype": null,
"metadata": {}
},
...
]
```
## Step 5: Add metadata to project files
Now, let's add some metadata to our project files. We'll use frontmatter for that. Since we're creating a catalog of our GitHub projects, we'll add the following frontmatter fields to each file:
```md
---
name: markdowndb
description: Javascript library for treating markdown files as a database.
stars: 6
forks: 0
---
```
After adding the metadata, we need to re-index our markdown files into the database:
```bash
npx @flowershow/markdowndb ../projects
```
Now, if we run our script again, we'll see that the `metadata` field in the output contains the metadata we've added to our project files:
```json
[
{
"_id": "7e01cae193f12f5a4a9be2b89f22b429761bd313",
"file_path": "projects/markdowndb.md",
"extension": "md",
"url_path": "markdowndb",
"metadata": {
"name": "markdowndb",
"description": "Javascript library for treating markdown files as a database",
"stars": 6,
"forks": 0
}
},
...
]
```
## Step 6: Pretty print the output
Now, let's make the output a bit more readable. We'll use the `columnify` package for that:
```bash
npm install columnify
```
And then we'll update our `index.js` file:
```js {2,16-38}
import { MarkdownDB } from '@flowershow/markdowndb';
import columnify from 'columnify';
const dbPath = 'markdown.db';
const client = new MarkdownDB({
client: 'sqlite3',
connection: {
filename: dbPath,
},
});
const mddb = await client.init();
const projects = await mddb.getFiles();
// console.log(JSON.stringify(projects, null, 2));
const projects2 = projects.map((project) => {
const { file_path, metadata } = project;
return {
file_path,
...metadata,
};
});
const columns = columnify(projects2, {
truncate: true,
columnSplitter: ' | ',
config: {
description: {
maxWidth: 80,
},
},
});
console.log('\n');
console.log(columns);
console.log('\n');
process.exit(0);
```
The above script will output the following to the terminal:
![[/assets/blog/output.png]]
## Done!
That's it! We've just created a simple catalog of our GitHub projects using markdown files and the MarkdownDB package. You can find the full code for this tutorial [here](https://github.com/datopian/markdowndb/tree/main/examples/basic-example).
We look forward to seeing the amazing applications you'll build with this tool!
Happy coding!

View File

@@ -20,7 +20,9 @@ const config = {
// { name: "Components", href: "/docs/components" },
{ name: "Blog", href: "/blog" },
{ name: "Showcases", href: "/#showcases" },
{ name: "Howtos", href: "/howto" },
{ name: "Examples", href: "https://github.com/datopian/portaljs/tree/main/examples", target: "_blank" },
{ name: "Components", href: "https://storybook.portaljs.org", target: "_blank" },
// { name: "DL Demo", href: "/data-literate/demo" },
// { name: "Excel Viewer", href: "/excel-viewer" },
],

View File

@@ -0,0 +1,77 @@
# How to add Google Analytics?
>[!todo] Prerequisites
>- [Google Analytics account](https://support.google.com/analytics/answer/9304153?hl=en)
>- [Google tag ID](https://support.google.com/analytics/answer/12270356?hl=en#:~:text=A%20Measurement%20ID%20is%20an,same%20as%20your%20destination%20ID.)
The following piece of code adds pageview tracking functionality to the custom Next.js App in `/pages/_app.tsx`, but you can use it only in specific pages if you want.
```tsx
// /pages/_app.tsx
import { useRouter } from "next/router";
import { useEffect } from "react";
import Script from "next/script";
// Step 0:
// Add your Google tag ID to your local .env.local file, e.g. under GA_TRACKING_ID
// Step 1: create the following pageview function
const pageview = ({
url,
analyticsID,
}: {
url: string;
analyticsID: string;
}) => {
if (typeof window.gtag !== undefined) {
window.gtag("config", analyticsID, {
page_path: url,
});
}
};
export default function MyApp({ Component, pageProps }) {
const router = useRouter();
// ... your code
// Step 3: Add the following useEffect to trigger pageview on each route change
useEffect(() => {
const handleRouteChange = (url) => {
pageview(url, GA_TRACKING_ID);
};
router.events.on("routeChangeComplete", handleRouteChange);
return () => {
router.events.off("routeChangeComplete", handleRouteChange);
};
}, [router.events]);
return (
{/* Step 4: Install Google Analytics tag */}
<>
<Script
strategy="afterInteractive"
src={`https://www.googletagmanager.com/gtag/js?id=${GA_TRACKING_ID}`}
/>
<Script
id="gtag-init"
strategy="afterInteractive"
dangerouslySetInnerHTML={{
__html: `
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', '${GA_TRACKING_ID}', {
page_path: window.location.pathname,
});
`,
}}
/>
<Component {...pageProps} />
</>
);
};
```
>[!info]
> For more info on measuring pageviews with Google Analytics see [Google Analytics documentation](https://developers.google.com/analytics/devguides/collection/gtagjs/pages).

View File

@@ -0,0 +1,75 @@
# How to add a simple blog?
## Setup
The following example uses components imported from the [`@flowershow/core` package](https://github.com/datopian/flowershow). If you want to follow along install it too:
```sh
npm i @flowershow/core
```
## Create home page for your blogs
Add the following code to the Next.js page that is going to be your blog home page, e.g. to `/pages/blog/index.tsx`:
```tsx
import { BlogsList, SimpleLayout } from "@flowershow/core";
// pass a list of blogs, home page title and home page description, e.g. from `getStaticProps`
export default function BlogIndex({ blogs, title, description }) {
return (
<SimpleLayout title={title} description={description}>
<BlogsList blogs={blogs} />
</SimpleLayout>
);
}
```
`BlogsList` component has the following API:
```ts
interface BlogsListProps {
blogs: Blog;
}
interface Blog {
title: string;
date: string;
urlPath: string;
description?: string;
authors?: Array<string>;
tags?: Array<string>;
}
```
## Create blog post pages
Add the following code to your blog pages, e.g. to `/pages/blog/[...slug].tsx`:
```tsx
import { BlogLayout } from "@flowershow/core";
export default BlogPost({ content, title, date, authors }) {
return (
<BlogLayout title={title} date={date} authors={authors}
{content}
</BlogLayout>
)
}
```
`BlogLayout` component has the following API:
```ts
interface BlogLayoutProps {
title?: string;
date?: string;
authors?: Array<Author>;
}
interface Author {
name: string;
avatar: string; // avatar image path
urlPath?: string; // author page
}
```

View File

@@ -0,0 +1,106 @@
# How to add user comments?
![[comments-example.png]]
## Setup
Page comments can be setup with any one of the following supported providers:
1. [giscus](https://giscus.app/)
2. [utterances](https://utteranc.es/)
3. [disqus](https://disqus.com/)
Each provider has it's own configuration options that you should add to your `.env` file.
>[!Info]
>If you are hosting your website on hosting providers like Netlify, Vercel or Cloudflare, you will also need to add the environment variables there.
### Giscus
[Giscus](https://giscus.app/) uses your github repo's discussions feature to store your comments and display them on your site.
#### Prerequisites
1. You have a public [github repository](https://docs.github.com/en/get-started/quickstart/create-a-repo) with the [discussions](https://docs.github.com/en/github/administering-a-repository/managing-repository-settings/enabling-or-disabling-github-discussions-for-a-repository) feature activated which will be used to store your comments.
2. The [giscus app](https://github.com/apps/giscus) installed in your repo by following their configuration setup at [https://giscus.app/](https://giscus.app/)
Once the above steps are completed, head over to [https://giscus.app](https://giscus.app/) and follow the steps there by filling out the fields to get your config values.
>[!important]
> Make sure to choose `pathname` under page discussions mapping.
After filling out the fields, you will be provided with a script tag that contains your config values. Add them to your `.env` file, like so:
```
NEXT_PUBLIC_GISCUS_REPO=
NEXT_PUBLIC_GISCUS_REPOSITORY_ID=
NEXT_PUBLIC_GISCUS_CATEGORY=
NEXT_PUBLIC_GISCUS_CATEGORY_ID=
```
When a user visits a web page, Giscus searches for a discussion whose title contains the page's pathname URL component. If there are no matches (i.e., no comments have been made about that page), then a new discussion is created for that page.
By using the pathname for mapping with a page, Giscus ensures that each discussion is unique to a particular page and that comments made on that page are kept together.
More info on how this connection is achieved can be found on their '**how it works**' section in their repo - [https://github.com/giscus/giscus#how-it-works](https://github.com/giscus/giscus#how-it-works) and also in the '**Page Discussions Mapping**' section at [https://giscus.app/](https://giscus.app/)
### Utterances
[Utterances](https://utteranc.es/) uses your github repo's issues to store comments for your pages and display them on your site. To setup comments with utterances, you would need to do the following:
#### Prerequisites
1. You have a public [github repository](https://docs.github.com/en/get-started/quickstart/create-a-repo)
2. The utterances app installed in your repo by following their configuration setup at [https://utteranc.es/](https://utteranc.es/)
Once installed fill in the required fields and you will see a script tag with your repo value which you can add to your `.env` file, like so:
```
NEXT_PUBLIC_UTTERANCES_REPO=
```
### Disqus
[Disqus](https://disqus.com/) is a feature rich provider which can be used to add comments to your site. You can configure flowershow to use disqus by creating an account on their site and following their process. You will be asked to enter a shortname for your site. Once completed, we can use this shortname in our comments configuration as below.
#### Prerequisites
1. Create an account on [Disqus](https://disqus.com/) and follow their setup process.
You will be asked to enter a shortname for your site. Add it to your `.env` file as well, like so:
```
NEXT_PUBLIC_DISQUS_SHORTNAME=
```
## Add comments to your page layout
You can use `@flowershow/core` to import the comments section component. Install it with:
```sh
npm i @flowershow/core
```
Then, add the following to your custom layout (or directly to your pages):
```tsx
import Navbar from './navbar';
import Footer from './footer';
export default function Layout({ children }) {
return (
<>
<Navbar />
<main>{children}</main>
<div>
<Comments commentsConfig={commentsConfig} slug={urlPath} />
</div>
<Footer />
</>
);
}
```
## Add user comments
Learn how to add support for user comments in [[comments|this guide]].

334
site/content/howto/drd.md Normal file
View File

@@ -0,0 +1,334 @@
# How to create data-rich documents with charts and tables?
> [!info] Prerequisites
> If you want to enrich your markdown content with charts and tables, you first need to add support for rendering markdown files in your PortalJS app. Follow [[markdown|this guide]] to learn how to do this.
PortalJS comes with a library of components that provides essential pieces for your data portal. The best way to explore the components is to look at our [Storybook](https://storybook.portaljs.org/) that contains all the details on how to use them. Below is an overview of available components.
You can install the library with:
```sh
npm i @portaljs/components
```
Now, in order to use these components in your markdown files, we need to pass them to our `MDXRemote` component (see [[markdown#Import, parse and render your markdown files|this section in our markdown guide]]):
```tsx
// e.g. /blog/[[...slug]].tsx
import fs from "fs";
import { LineChart, Table, Catalog, Vega, VegaLite } from "@portaljs/components";
import { MdxRemote } from "next-mdx-remote";
import clientPromise from "@/lib/mddb.mjs";
import parse from "@/lib/markdown";
const components = {
Table: Table,
Vega: Vega,
VegaLite: VegaLite,
LineChart: LineChart,
};
export default function Page({ source }) {
source = JSON.parse(source);
return (
<>
<MdxRemote source={source} components={components} />
</>
);
}
// Import metadata of a file matching the static path and return its parsed source and frontmatter object
export const getStaticProps = async ({ params }) => {
const urlPath = params?.slug ? (params.slug as string[]).join("/") : "/";
const mddb = await clientPromise;
const dbFile = await mddb.getFileByUrl(urlPath);
const filePath = dbFile!.file_path;
// const frontMatter = dbFile!.metadata ?? {};
const source = fs.readFileSync(filePath, { encoding: "utf-8" });
const { mdxSource } = await parse(source, "mdx", {});
return {
props: {
source: JSON.stringify(mdxSource),
// frontMatter
},
};
};
```
You can now use these components in your markdown, like so:
```md
### My Data Rich Note
Some markdown here.
<Table csv={`
Year,Temp Anomaly
1850,-0.418
2020,0.923
`} />
Some markdown here.
```
## PortalJS components
### Table
An easy-to-use table component with built-in pagination, search, and sorting. It can be used with raw data, raw CSV strings or with URLs to hosted CSV files.
![[table-example.png]]
Example usage:
```js
<Table
cols={[
{
key: 'id',
name: 'ID'
},
{
key: 'firstName',
name: 'First name'
},
{
key: 'lastName',
name: 'Last name'
},
{
key: 'age',
name: 'Age'
}
]}
data={[
{
age: 35,
firstName: 'Jon',
id: 1,
lastName: 'Snow'
},
{
age: 42,
firstName: 'Cersei',
id: 2,
lastName: 'Lannister'
}
]}
/>
```
>[!info]
> More info on the [storybook page](https://storybook.portaljs.org/?path=/docs/components-table--docs)
### Linechart
A simple component that allows the creation of an opinionated line chart without the need to go deep into charting standards. It can be used with raw data, raw CSV strings or with URLs to hosted CSV files.
![[linechart-example.png]]
Example usage:
```js
<LineChart
data={[
[
'1850',
-0.41765878
],
[
'1851',
-0.2333498
],
[
'1852',
-0.22939907
],
[
'1853',
-0.27035445
],
[
'1854',
-0.29163003
]
]}
/>
```
>[!info]
> More info on the [storybook page](https://storybook.portaljs.org/?path=/docs/components-linechart--docs)
### Vega chart
A wrapper around the [Vega specification](https://vega.github.io/vega/) that allows you to build pretty much any kind of chart imaginable.
Example usage:
![](https://hackmd.io/_uploads/ryN5mYmSh.png)
```js
<Vega
data={{
table: [
{
x: 1850,
y: -0.418
},
{
x: 2020,
y: 0.923
}
]
}}
spec={{
$schema: 'https://vega.github.io/schema/vega-lite/v4.json',
data: {
name: 'table'
},
encoding: {
x: {
field: 'x',
type: 'ordinal'
},
y: {
field: 'y',
type: 'quantitative'
}
},
mark: 'bar'
}}
/>
```
> [!info]
> More info on the [storybook page](https://storybook.portaljs.org/?path=/docs/components-vega--docs)
### VegaLite chart
A wrapper around the [Vega Lite specification](https://vega.github.io/vega-lite/) which allows for a more concise grammar than Vega around the building of charts.
Example usage:
```js
<VegaLite
data={{
table: [
{
x: 1850,
y: -0.418
},
{
x: 2020,
y: 0.923
}
]
}}
spec={{
$schema: 'https://vega.github.io/schema/vega-lite/v4.json',
data: {
name: 'table'
},
encoding: {
x: {
field: 'x',
type: 'ordinal'
},
y: {
field: 'y',
type: 'quantitative'
}
},
mark: 'bar'
}}
/>
```
>[!info]
> More info on the [storybook page](https://storybook.portaljs.org/?path=/docs/components-vegalite--docs)
### Catalog
A searchable catalog that will index a list of datasets and allow for contextual searching + filters.
![[catalog-example.png]]
Example usage:
```js
<Catalog
datasets={[
{
_id: '07026b22d49916754df1dc8ffb9ccd1c31878aae',
metadata: {
'details-of-task': 'Detect and categorise abusive language in social media data',
language: 'Albanian',
'level-of-annotation': [
'Posts'
],
'link-to-data': 'https://doi.org/10.6084/m9.figshare.19333298.v1',
'link-to-publication': 'https://arxiv.org/abs/2107.13592',
medium: [
'Text'
],
'percentage-abusive': 13.2,
platform: [
'Instagram',
'Youtube'
],
reference: 'Nurce, E., Keci, J., Derczynski, L., 2021. Detecting Abusive Albanian. arXiv:2107.13592',
'size-of-dataset': 11874,
'task-description': 'Hierarchical (offensive/not; untargeted/targeted; person/group/other)',
title: 'Detecting Abusive Albanian'
},
url_path: 'dataset-4'
},
]}
/>
```
You can also add facets that are going to act as filters for your metadata.
![[catalog-facets-example.png]]
```js
<Catalog
datasets={[
{
_id: '07026b22d49916754df1dc8ffb9ccd1c31878aae',
metadata: {
'details-of-task': 'Detect and categorise abusive language in social media data',
language: 'Albanian',
'level-of-annotation': [
'Posts'
],
'link-to-data': 'https://doi.org/10.6084/m9.figshare.19333298.v1',
'link-to-publication': 'https://arxiv.org/abs/2107.13592',
medium: [
'Text'
],
'percentage-abusive': 13.2,
platform: [
'Instagram',
'Youtube'
],
reference: 'Nurce, E., Keci, J., Derczynski, L., 2021. Detecting Abusive Albanian. arXiv:2107.13592',
'size-of-dataset': 11874,
'task-description': 'Hierarchical (offensive/not; untargeted/targeted; person/group/other)',
title: 'Detecting Abusive Albanian'
},
url_path: 'dataset-4'
},
]}
facets={['platform', 'language']}
/>
```
>[!info]
> More info on the [storybook page](https://storybook.portaljs.org/?path=/docs/components-catalog--docs)

View File

@@ -0,0 +1,12 @@
# Guides and tutorials
- [[howto/analytics|How to add web analytics?]]
- [[howto/seo|How to customize page metadata for SEO?]]
- [[howto/sitemap|How to build a sitemap?]]
- [[howto/markdown|How to add markdown-based content pages?]]
- [[howto/blog|How to add a simple blog?]]
- [[howto/drd|How to create data-rich documents with charts and tables?]]
- [[howto/comments|How to add user comments?]]
If you have questions about anything related to PortalJS, you're always welcome to ask our community on [GitHub Discussions](https://github.com/datopian/portaljs/discussions) or on [our chat channel on Discord](https://discord.gg/EeyfGrGu4U).

View File

@@ -0,0 +1,169 @@
# How to add markdown-based content pages?
## Add content layer to your app
Create a folder where you'll keep your markdown files and add some markdown files to it.
```sh
cd my-portaljs-project
mkdir content
# touch content/index.md ...
```
Install [MarkdownDB](https://github.com/datopian/markdowndb) package:
```
npm i @flowershow/markdowndb
```
And add the following to your `package.json`:
```json
{
"scripts": {
"mddb": "mddb <path-to-your-content-folder>",
"prebuild": "npm run mddb"
},
}
```
You can give it a go by running `npm run mddb`. You should see a `markdown.db` file created in the root of your project. You can inspect it with any SQLite viewer or in the command line. In the `files` table you should see all your markdown files from your content folder.
Now, once the data is in the database, you can add the following script to your project (e.g. in `/lib` folder). It will allow you to establish a single connection to the database and use it across your app.
```ts
// lib/mddb.ts
import { MarkdownDB } from "@flowershow/markdowndb";
// path to the markdown.db file created by the mddb script
const dbPath = "markdown.db";
const client = new MarkdownDB({
client: "sqlite3",
connection: {
filename: dbPath,
},
});
const clientPromise = client.init();
export default clientPromise;
```
Now you can import it across your project to query the database, e.g.:
```ts
import clientPromise from "@/lib/mddb";
const mddb = await clientPromise;
const blogs = await mddb.getFiles({
folder: "blog",
extensions: ["md", "mdx"],
});
```
## Write a markdown parser
Install [next-mdx-remote](https://github.com/hashicorp/next-mdx-remote) package, which we'll first use to parse markdown files and then to render them in Next.js app.
```sh
npm i next-mdx-remote
```
Create the following basic parser for your markdown files, e.g. in `/lib/markdown.ts`:
```ts
import matter from "gray-matter";
import remarkGfm from "remark-gfm";
import { serialize } from "next-mdx-remote/serialize";
const parse = async function (source) {
const { content } = matter(source);
const mdxSource = await serialize(
{ value: content },
{
mdxOptions: {
remarkPlugins: [
remarkGfm,
// ... your remark plugins
],
rehypePlugins: [
// ... your plugins
],
format,
}
}
);
return {
mdxSource
};
};
export default parse;
```
## Import, parse and render your markdown files
Create a page in the `/pages` folder that will render your markdown content, e.g. `pages/blog/[[...slug]].tsx`:
```tsx
import fs from "fs";
import { MdxRemote } from "next-mdx-remote";
import clientPromise from "@/lib/mddb.mjs";
import parse from "@/lib/markdown";
export default function Page({ source }) {
source = JSON.parse(source);
return (
<>
<MdxRemote source={source} />
</>
);
}
// Import metadata of a file matching the static path and return its parsed source and frontmatter object
export const getStaticProps = async ({ params }) => {
const urlPath = params?.slug ? (params.slug as string[]).join("/") : "/";
const mddb = await clientPromise;
const dbFile = await mddb.getFileByUrl(urlPath);
const filePath = dbFile!.file_path;
// const frontMatter = dbFile!.metadata ?? {};
const source = fs.readFileSync(filePath, { encoding: "utf-8" });
const { mdxSource } = await parse(source, "mdx", {});
return {
props: {
source: JSON.stringify(mdxSource),
// frontMatter
},
};
};
// Import metadata of your markdown files from MarkdownDB and return a list of static paths
export const getStaticPaths = async () => {
const mddb = await clientPromise;
const allDocuments = await mddb.getFiles({ extensions: ["md", "mdx"] });
const paths = allDocuments
.map((page) => {
const url = decodeURI(page.url_path);
const parts = url.split("/");
return { params: { slug: parts } };
});
return {
paths,
fallback: false,
};
};
```

79
site/content/howto/seo.md Normal file
View File

@@ -0,0 +1,79 @@
# How to customize page metadata for SEO?
>[!info]
>See [`next-seo` documentation](https://github.com/garmeeh/next-seo) to learn more.
## Setup
Install `next-seo` package:
```sh
npm i next-seo
```
## Default SEO configuration
Create `next-seo.config` file (e.g. in the root of your project) and add default meta tags values you want to be set up for your pages. For example:
```ts
export default {
openGraph: {
type: 'website',
locale: 'en_IE',
url: 'https://www.my.portaljs.app/',
siteName: 'MyPortalJSApp',
},
twitter: {
handle: '@handle',
site: '@site',
cardType: 'summary_large_image',
},
};
```
Then, in your custom Next.js App, add the following:
```tsx
// /pages/_app.tsx
import { DefaultSeo } from "next-seo";
// import your default seo configuration
import SEO from '../next-seo.config';
export default function MyApp({ Component, pageProps }) {
// ... your code
return (
<>
<DefaultSeo {...SEO} />
<Component {...pageProps} />
</>
);
};
```
>[!info]
>To learn more on default SEO configuration with `next-seo`, see [this docs section](https://github.com/garmeeh/next-seo#default-seo-configuration).
## Per-page SEO configuration
To add page specific meta tag values:
```tsx
import { NextSeo } from 'next-seo';
export default function Page() (
// ...
<>
<NextSeo
title="My Portal JS page"
description="A short description."
/>
<p>My Portal JS page</p>
</>
);
```
>[!info]
> To learn more on per-page SEO configuration with `next-seo`, see [this docs section](https://github.com/garmeeh/next-seo#add-seo-to-page)

View File

@@ -0,0 +1,94 @@
# How to build a sitemap?
## Setup
Install the following packages:
```sh
npm i globby
npm i -D prettier
```
## Add sitemap script
>[!info]
>The following example assumes files list for dynamic Next.js routes is imported from the database created with [MarkdownDB](https://github.com/datopian/markdowndb) package. You need to adjust it to your specific use case.
Add the following script to e.g. `/scripts/sitemap.mjs` and adjust it to work with your app:
```js
// /scripts/sitemap.mjs
import { writeFileSync } from "fs";
import { globby } from "globby";
import prettier from "prettier";
// Change this to import data from your content layer (if needed)
import clientPromise from "../lib/mddb.mjs";
export default async function sitemap() {
const prettierConfig = await prettier.resolveConfig("path-to-your-prettier-config");
// Change this to create a list of page paths
const mddb = await clientPromise;
const allFiles = await mddb.getFiles({ extensions: ["mdx", "md"] });
const contentPages = allFiles
.filter((x) => !x.metadata?.isDraft)
.map((x) => `/${x.url_path}`);
const pages = await globby([
"pages/*.(js|tsx)",
"!pages/_*.(js|tsx)",
"!pages/api",
"!pages/404.(js|tsx)",
"!pages/**/\\[\\[*\\]\\].(js|tsx)", // pages/[[...slug]].tsx
]);
const allPages = pages.concat(contentPages);
// end
// Replace this with your site domain
const siteDomain = "your-site-domain";
const sitemap = `
<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
${allPages
.map((page) => {
const path = page
.replace("pages/", "/")
.replace("public/", "/")
.replace(/\.js|.tsx|.mdx|.md[^\/.]+$/, "")
.replace("/feed.xml", "");
const route = path === "/index" ? "" : path;
return `
<url>
<loc>${siteDomain}${route}</loc>
</url>
`;
})
.join("")}
</urlset>
`;
const formatted = prettier.format(sitemap, {
...prettierConfig,
parser: "html",
});
if (siteUrl) {
writeFileSync("public/sitemap.xml", formatted);
console.log("Sitemap generated...");
}
}
await sitemap();
process.exit();
```
## Execute script before each build
Add this to the scripts section in your `package.json` to regenerate the sitemap before each build.
```json
"prebuild": "node ./scripts/sitemap.mjs",
```