Compare commits

..

10 commits

33 changed files with 206 additions and 1011 deletions

View file

@ -27,6 +27,6 @@ jobs:
B2_BUCKET_KEY_ID: ${{ secrets.B2_BUCKET_KEY_ID }}
B2_BUCKET_KEY: ${{ secrets.B2_BUCKET_KEY }}
run: |
cd sepa/sepa-precios-archiver
cd sepa
bun install --frozen-lockfile
bun index.ts
bun archiver.ts

36
sepa/README.md Normal file
View file

@ -0,0 +1,36 @@
# sepa
## sepa-precios-importer
Importador de [datasets de precios de SEPA](https://datos.produccion.gob.ar/dataset/sepa-precios/archivo/d076720f-a7f0-4af8-b1d6-1b99d5a90c14) a una base de datos PostgreSQL.
Vease [Errores en el formato de los datos SEPA](https://gist.github.com/catdevnull/587d5c63c4bab11b9798861c917db93b)
```bash
bun install
bun run importer.ts ~/carpeta-con-datasets-descomprimidos
```
## sepa-precios-archiver
Archivador del dataset de precios de [Precios Claros - Base SEPA](https://datos.produccion.gob.ar/dataset/sepa-precios). Recomprime para utilizar ~8 veces menos espacio, y resube a un bucket mio de Backblaze B2.
```bash
bun install
bun run archiver.ts
```
## sepa-dataset-validator
un script para validar los datasets de SEPA automaticamente
basado en [la lista de problemas](https://gist.github.com/catdevnull/587d5c63c4bab11b9798861c917db93b) que encontramos
para ejecutar, necesitas [Bun](https://bun.sh)
```bash
bun install
bun run dataset-validator/index.ts [ruta/al/dataset]
```
podes descargar un dump de [nuestro index](https://github.com/catdevnull/sepa-precios-metadata/blob/main/index.md) para analizar (la descarga pesa mucho menos que los oficiales :). para descomprimir, necesitas tener `zstd` y `tar`. después solo tenes que ejecutar `tar xvf ARCHIVO.tar.zst` y listo.

View file

@ -1,11 +1,11 @@
import { z } from "zod";
import { zDatasetInfo } from "ckan/schemas";
import { zDatasetInfo } from "./ckan/schemas";
import { mkdtemp, writeFile, readdir, mkdir, rm } from "fs/promises";
import { basename, extname, join } from "path";
import { $, write } from "bun";
import { $ } from "bun";
import { S3Client, HeadObjectCommand } from "@aws-sdk/client-s3";
import { Upload } from "@aws-sdk/lib-storage";
import { generateMarkdown } from "sepa-index-gen";
import { generateIndexes } from "./index-gen";
function checkEnvVariable(variableName: string) {
const value = process.env[variableName];
@ -162,8 +162,9 @@ for (const resource of datasetInfo.result.resources) {
await uploadToB2Bucket(fileName, response);
}
}
await saveFileIntoRepo("index.md", await generateMarkdown());
const { markdown, jsonIndex } = await generateIndexes();
await saveFileIntoRepo("index.md", markdown);
await saveFileIntoRepo("index.json", JSON.stringify(jsonIndex, null, 2));
if (errored) {
process.exit(1);

Binary file not shown.

View file

@ -1,15 +0,0 @@
# ckan
To install dependencies:
```bash
bun install
```
To run:
```bash
bun run index.ts
```
This project was created using `bun init` in bun v1.1.26. [Bun](https://bun.sh) is a fast all-in-one JavaScript runtime.

View file

@ -1,13 +0,0 @@
{
"name": "ckan",
"type": "module",
"devDependencies": {
"@types/bun": "latest"
},
"peerDependencies": {
"typescript": "^5.0.0"
},
"dependencies": {
"zod": "^3.23.8"
}
}

View file

@ -100,6 +100,27 @@ const checkers: Record<string, (files: Files) => boolean | string> = {
}
return false;
},
["[productos.csv] hay id_productos no numéricos"](files) {
const productos = files["productos.csv"].data;
for (const producto of productos) {
if (!(producto as any).id_producto) continue;
try {
const n = Number((producto as any).id_producto);
if (isNaN(n)) {
console.error(
` El id_producto ${(producto as any).id_producto} parsea a NaN`
);
return true;
}
} catch {
console.error(
` El id_producto ${(producto as any).id_producto} no es un número`
);
return true;
}
}
return false;
},
["Sucursales mencionadas en productos.csv existen en sucursales.csv"](files) {
const productos = new Set(
files["productos.csv"].data.map((row) => (row as any).id_sucursal)

View file

@ -4,7 +4,7 @@ import { basename, join, dirname } from "path";
import postgres from "postgres";
import { Readable } from "stream";
import { pipeline } from "node:stream/promises";
import { Glob } from "bun";
import { $, Glob } from "bun";
import PQueue from "p-queue";
// TODO: verificar que pasa cuando hay varios datasets del mismo día (como los suele haber cuando actualizan el dataset con nuevos comercios)
@ -161,16 +161,13 @@ async function importDataset(dir: string) {
// Alberdi S.A.
file = file.replaceAll(";", "|");
}
if (
["33504047089", "30707429468", "30589621499"].includes(comercioCuit)
) {
if (["30707429468", "30589621499"].includes(comercioCuit)) {
// TODO: si tienen los valores, pero con otros nombres, por ejemplo
// productos_precio_lista seria precio_unitario_bulto_por_unidad_venta_con_iva.
// pero no quiero mentir, asi que por ahora no lo importo
console.error(
throw new Error(
`No voy a importar el dataset ${dir} porque el formato está mal. Pero se podría importar. Pero por ahora no lo voy a hacer. Véase https://gist.github.com/catdevnull/587d5c63c4bab11b9798861c917db93b`
);
return;
}
console.time("parse");
@ -247,15 +244,38 @@ async function importDataset(dir: string) {
}
}
const pQueue = new PQueue({ concurrency: 2 });
try {
async function importDatasetTar(tarPath: string) {
console.log(`importing tar ${tarPath}`);
const dir = await fs.mkdtemp("/tmp/sepa-precios-importer-");
try {
await $`tar -x -C ${dir} -f ${tarPath}`;
await importDump(dir);
} finally {
await fs.rm(dir, { recursive: true });
}
}
async function importDump(dumpDir: string) {
const pQueue = new PQueue({ concurrency: 2 });
const glob = new Glob("**/productos.csv");
for await (const file of glob.scan(process.argv[2])) {
const dir = join(process.argv[2], dirname(file));
for await (const file of glob.scan(dumpDir)) {
const dir = join(dumpDir, dirname(file));
pQueue.add(() => importDataset(dir));
}
} finally {
await pQueue.onIdle();
}
try {
const tarGlob = new Glob("**/*.tar.zst");
let hasTars = false;
for await (const file of tarGlob.scan(process.argv[2])) {
hasTars = true;
const tar = join(process.argv[2], file);
await importDatasetTar(tar);
}
if (!hasTars) {
await importDump(process.argv[2]);
}
} finally {
await sql.end();
}

View file

@ -4,31 +4,42 @@ import {
ListObjectsV2Command,
GetObjectCommand,
} from "@aws-sdk/client-s3";
import { Upload } from "@aws-sdk/lib-storage";
function checkEnvVariable(variableName: string) {
const value = process.env[variableName];
if (value) {
console.log(`${variableName} is set`);
return value;
} else {
console.log(`${variableName} is not set`);
process.exit(1);
}
}
export const B2_BUCKET_NAME = checkEnvVariable("B2_BUCKET_NAME");
const B2_BUCKET_KEY_ID = checkEnvVariable("B2_BUCKET_KEY_ID");
const B2_BUCKET_KEY = checkEnvVariable("B2_BUCKET_KEY");
export const s3 = new S3Client({
endpoint: "https://s3.us-west-004.backblazeb2.com",
region: "us-west-004",
credentials: {
accessKeyId: B2_BUCKET_KEY_ID,
secretAccessKey: B2_BUCKET_KEY,
},
});
function getVariables() {
const B2_BUCKET_NAME = checkEnvVariable("B2_BUCKET_NAME");
const B2_BUCKET_KEY_ID = checkEnvVariable("B2_BUCKET_KEY_ID");
const B2_BUCKET_KEY = checkEnvVariable("B2_BUCKET_KEY");
return {
B2_BUCKET_NAME,
B2_BUCKET_KEY_ID,
B2_BUCKET_KEY,
};
}
function getS3Client() {
const { B2_BUCKET_NAME, B2_BUCKET_KEY_ID, B2_BUCKET_KEY } = getVariables();
return new S3Client({
endpoint: "https://s3.us-west-004.backblazeb2.com",
region: "us-west-004",
credentials: {
accessKeyId: B2_BUCKET_KEY_ID,
secretAccessKey: B2_BUCKET_KEY,
},
});
}
export async function listDirectory(directoryName: string) {
const { B2_BUCKET_NAME } = getVariables();
const s3 = getS3Client();
const command = new ListObjectsV2Command({
Bucket: B2_BUCKET_NAME,
Prefix: directoryName ? `${directoryName}/` : "",
@ -40,6 +51,8 @@ export async function listDirectory(directoryName: string) {
}
export async function getFileContent(fileName: string) {
const { B2_BUCKET_NAME } = getVariables();
const s3 = getS3Client();
const fileContent = await s3.send(
new GetObjectCommand({
Bucket: B2_BUCKET_NAME,
@ -50,6 +63,8 @@ export async function getFileContent(fileName: string) {
}
export async function checkFileExists(fileName: string): Promise<boolean> {
const { B2_BUCKET_NAME } = getVariables();
const s3 = getS3Client();
try {
await s3.send(
new HeadObjectCommand({

View file

@ -1,4 +1,4 @@
import { zDatasetInfo, type DatasetInfo, type Resource } from "ckan/schemas";
import { zDatasetInfo, type DatasetInfo, type Resource } from "../ckan/schemas";
import { getFileContent, listDirectory } from "./b2";
import { basename } from "path";

View file

@ -1,10 +1,22 @@
import { zResource, type Resource } from "ckan/schemas";
import { zResource, type Resource } from "../ckan/schemas";
import { z } from "zod";
import { listDirectory } from "./b2";
import { isSameDay } from "date-fns";
import { indexResources } from "./index-resources";
export async function generateMarkdown() {
export const IndexEntry = z.object({
id: z.string(),
warnings: z.string(),
name: z.string().optional(),
link: z.string().optional(),
firstSeenAt: z.coerce.date(),
});
export type IndexEntry = z.infer<typeof IndexEntry>;
export const IndexJson = z.record(z.string(), z.array(IndexEntry));
export type IndexJson = z.infer<typeof IndexJson>;
export async function generateIndexes() {
const resourcesIndex = await indexResources();
const datasets = z
@ -111,6 +123,9 @@ esto esta automáticamente generado por sepa-index-gen dentro de preciazo.`;
hour: "2-digit",
minute: "2-digit",
});
let jsonIndex: IndexJson = {};
for (const dateStr of dates) {
const date = new Date(dateStr);
markdown += `\n* ${formatter.format(date)}:`;
@ -120,6 +135,7 @@ esto esta automáticamente generado por sepa-index-gen dentro de preciazo.`;
if (!resourcesInDate.length) {
markdown += " ❌ no tengo recursos para esta fecha";
}
jsonIndex[dateStr] = [];
for (const resource of resourcesInDate) {
const id = `${resource.id}-revID-${resource.revision_id}`;
const fileExists = fileList.find((file) => file.startsWith(id));
@ -135,8 +151,16 @@ esto esta automáticamente generado por sepa-index-gen dentro de preciazo.`;
"⁉️⚠️ dia de semana incorrecto, puede haberse subido incorrectamente ";
}
markdown += `\n * ${id} ${warnings} ${fileExists ? `[✅ descargar](${link})` : "❌"} (primera vez visto: ${dateTimeFormatter.format(resource.firstSeenAt)})`;
jsonIndex[dateStr].push({
id,
warnings: warnings.trim(),
name: fileExists,
link,
firstSeenAt: resource.firstSeenAt,
});
}
}
return markdown;
return { markdown, jsonIndex };
}

View file

@ -1,11 +1,22 @@
{
"name": "sepa",
"private": true,
"workspaces": [
"sepa-precios-archiver",
"sepa-precios-importer",
"sepa-index-gen",
"sepa-dataset-validator",
"ckan"
]
"type": "module",
"devDependencies": {
"@types/bun": "^1.1.7",
"@types/papaparse": "^5.3.14"
},
"peerDependencies": {
"typescript": "^5.0.0"
},
"dependencies": {
"@aws-sdk/client-s3": "^3.651.0",
"@aws-sdk/lib-storage": "^3.651.0",
"date-fns": "^3.6.0",
"jschardet": "^3.1.3",
"p-queue": "^8.0.1",
"papaparse": "^5.4.1",
"postgres": "^3.4.4",
"zod": "^3.23.8"
}
}

View file

@ -0,0 +1,35 @@
import PQueue from "p-queue";
import { IndexEntry, IndexJson } from "../index-gen";
import { $ } from "bun";
import { existsSync } from "fs";
async function getIndex() {
const res = await fetch(
"https://raw.githubusercontent.com/catdevnull/sepa-precios-metadata/main/index.json"
);
return IndexJson.parse(await res.json());
}
const index = await getIndex();
const latestResources = Object.values(index)
.filter((a) => a.length > 0)
.map(
(a) =>
a
.filter(
(r): r is IndexEntry & { link: string } => !!(!r.warnings && r.link)
)
.sort((a, b) => +b.firstSeenAt - +a.firstSeenAt)[0]
);
const queue = new PQueue({ concurrency: 10 });
for (const resource of latestResources) {
queue.add(async () => {
const filename = resource.link.split("/").pop()!;
if (existsSync(filename)) return;
await $`curl ${resource.link} -o ${filename}.temp`;
await $`mv ${filename}.temp ${filename}`;
});
}

View file

@ -1,175 +0,0 @@
# Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore
# Logs
logs
_.log
npm-debug.log_
yarn-debug.log*
yarn-error.log*
lerna-debug.log*
.pnpm-debug.log*
# Caches
.cache
# Diagnostic reports (https://nodejs.org/api/report.html)
report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
# Runtime data
pids
_.pid
_.seed
*.pid.lock
# Directory for instrumented libs generated by jscoverage/JSCover
lib-cov
# Coverage directory used by tools like istanbul
coverage
*.lcov
# nyc test coverage
.nyc_output
# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
.grunt
# Bower dependency directory (https://bower.io/)
bower_components
# node-waf configuration
.lock-wscript
# Compiled binary addons (https://nodejs.org/api/addons.html)
build/Release
# Dependency directories
node_modules/
jspm_packages/
# Snowpack dependency directory (https://snowpack.dev/)
web_modules/
# TypeScript cache
*.tsbuildinfo
# Optional npm cache directory
.npm
# Optional eslint cache
.eslintcache
# Optional stylelint cache
.stylelintcache
# Microbundle cache
.rpt2_cache/
.rts2_cache_cjs/
.rts2_cache_es/
.rts2_cache_umd/
# Optional REPL history
.node_repl_history
# Output of 'npm pack'
*.tgz
# Yarn Integrity file
.yarn-integrity
# dotenv environment variable files
.env
.env.development.local
.env.test.local
.env.production.local
.env.local
# parcel-bundler cache (https://parceljs.org/)
.parcel-cache
# Next.js build output
.next
out
# Nuxt.js build / generate output
.nuxt
dist
# Gatsby files
# Comment in the public line in if your project uses Gatsby and not Next.js
# https://nextjs.org/blog/next-9-1#public-directory-support
# public
# vuepress build output
.vuepress/dist
# vuepress v2.x temp and cache directory
.temp
# Docusaurus cache and generated files
.docusaurus
# Serverless directories
.serverless/
# FuseBox cache
.fusebox/
# DynamoDB Local files
.dynamodb/
# TernJS port file
.tern-port
# Stores VSCode versions used for testing VSCode extensions
.vscode-test
# yarn v2
.yarn/cache
.yarn/unplugged
.yarn/build-state.yml
.yarn/install-state.gz
.pnp.*
# IntelliJ based IDEs
.idea
# Finder (MacOS) folder config
.DS_Store

View file

@ -1,14 +0,0 @@
# sepa-dataset-validator
un script para validar los datasets de SEPA automaticamente
basado en [la lista de problemas](https://gist.github.com/catdevnull/587d5c63c4bab11b9798861c917db93b) que encontramos
para ejecutar, necesitas [Bun](https://bun.sh)
```bash
bun install
bun run . [ruta/al/dataset]
```
podes descargar un dump de [nuestro index](https://github.com/catdevnull/sepa-precios-metadata/blob/main/index.md) para analizar (la descarga pesa mucho menos que los oficiales :). para descomprimir, necesitas tener `zstd` y `tar`. después solo tenes que ejecutar `tar xvf ARCHIVO.tar.zst` y listo.

View file

@ -1,16 +0,0 @@
{
"name": "sepa-dataset-validator",
"module": "index.ts",
"type": "module",
"devDependencies": {
"@types/bun": "latest"
},
"peerDependencies": {
"typescript": "^5.5.4"
},
"dependencies": {
"jschardet": "^3.1.3",
"papaparse": "^5.4.1",
"zod": "^3.23.8"
}
}

View file

@ -1,27 +0,0 @@
{
"compilerOptions": {
// Enable latest features
"lib": ["ESNext", "DOM"],
"target": "ESNext",
"module": "ESNext",
"moduleDetection": "force",
"jsx": "react-jsx",
"allowJs": true,
// Bundler mode
"moduleResolution": "bundler",
"allowImportingTsExtensions": true,
"verbatimModuleSyntax": true,
"noEmit": true,
// Best practices
"strict": true,
"skipLibCheck": true,
"noFallthroughCasesInSwitch": true,
// Some stricter flags (disabled by default)
"noUnusedLocals": false,
"noUnusedParameters": false,
"noPropertyAccessFromIndexSignature": false
}
}

View file

@ -1,175 +0,0 @@
# Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore
# Logs
logs
_.log
npm-debug.log_
yarn-debug.log*
yarn-error.log*
lerna-debug.log*
.pnpm-debug.log*
# Caches
.cache
# Diagnostic reports (https://nodejs.org/api/report.html)
report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
# Runtime data
pids
_.pid
_.seed
*.pid.lock
# Directory for instrumented libs generated by jscoverage/JSCover
lib-cov
# Coverage directory used by tools like istanbul
coverage
*.lcov
# nyc test coverage
.nyc_output
# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
.grunt
# Bower dependency directory (https://bower.io/)
bower_components
# node-waf configuration
.lock-wscript
# Compiled binary addons (https://nodejs.org/api/addons.html)
build/Release
# Dependency directories
node_modules/
jspm_packages/
# Snowpack dependency directory (https://snowpack.dev/)
web_modules/
# TypeScript cache
*.tsbuildinfo
# Optional npm cache directory
.npm
# Optional eslint cache
.eslintcache
# Optional stylelint cache
.stylelintcache
# Microbundle cache
.rpt2_cache/
.rts2_cache_cjs/
.rts2_cache_es/
.rts2_cache_umd/
# Optional REPL history
.node_repl_history
# Output of 'npm pack'
*.tgz
# Yarn Integrity file
.yarn-integrity
# dotenv environment variable files
.env
.env.development.local
.env.test.local
.env.production.local
.env.local
# parcel-bundler cache (https://parceljs.org/)
.parcel-cache
# Next.js build output
.next
out
# Nuxt.js build / generate output
.nuxt
dist
# Gatsby files
# Comment in the public line in if your project uses Gatsby and not Next.js
# https://nextjs.org/blog/next-9-1#public-directory-support
# public
# vuepress build output
.vuepress/dist
# vuepress v2.x temp and cache directory
.temp
# Docusaurus cache and generated files
.docusaurus
# Serverless directories
.serverless/
# FuseBox cache
.fusebox/
# DynamoDB Local files
.dynamodb/
# TernJS port file
.tern-port
# Stores VSCode versions used for testing VSCode extensions
.vscode-test
# yarn v2
.yarn/cache
.yarn/unplugged
.yarn/build-state.yml
.yarn/install-state.gz
.pnp.*
# IntelliJ based IDEs
.idea
# Finder (MacOS) folder config
.DS_Store

View file

@ -1,15 +0,0 @@
# sepa-index-gen
To install dependencies:
```bash
bun install
```
To run:
```bash
bun run index.ts
```
This project was created using `bun init` in bun v1.1.26. [Bun](https://bun.sh) is a fast all-in-one JavaScript runtime.

View file

@ -1,19 +0,0 @@
{
"name": "sepa-index-gen",
"module": "index.ts",
"type": "module",
"devDependencies": {
"@types/bun": "latest",
"prettier": "^3.3.3"
},
"peerDependencies": {
"typescript": "^5.0.0"
},
"dependencies": {
"@aws-sdk/client-s3": "^3.637.0",
"@aws-sdk/lib-storage": "^3.637.0",
"ckan": "workspace:*",
"date-fns": "^3.6.0",
"zod": "^3.23.8"
}
}

View file

@ -1,27 +0,0 @@
{
"compilerOptions": {
// Enable latest features
"lib": ["ESNext", "DOM"],
"target": "ESNext",
"module": "ESNext",
"moduleDetection": "force",
"jsx": "react-jsx",
"allowJs": true,
// Bundler mode
"moduleResolution": "bundler",
"allowImportingTsExtensions": true,
"verbatimModuleSyntax": true,
"noEmit": true,
// Best practices
"strict": true,
"skipLibCheck": true,
"noFallthroughCasesInSwitch": true,
// Some stricter flags (disabled by default)
"noUnusedLocals": false,
"noUnusedParameters": false,
"noPropertyAccessFromIndexSignature": false
}
}

View file

@ -1,175 +0,0 @@
# Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore
# Logs
logs
_.log
npm-debug.log_
yarn-debug.log*
yarn-error.log*
lerna-debug.log*
.pnpm-debug.log*
# Caches
.cache
# Diagnostic reports (https://nodejs.org/api/report.html)
report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
# Runtime data
pids
_.pid
_.seed
*.pid.lock
# Directory for instrumented libs generated by jscoverage/JSCover
lib-cov
# Coverage directory used by tools like istanbul
coverage
*.lcov
# nyc test coverage
.nyc_output
# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
.grunt
# Bower dependency directory (https://bower.io/)
bower_components
# node-waf configuration
.lock-wscript
# Compiled binary addons (https://nodejs.org/api/addons.html)
build/Release
# Dependency directories
node_modules/
jspm_packages/
# Snowpack dependency directory (https://snowpack.dev/)
web_modules/
# TypeScript cache
*.tsbuildinfo
# Optional npm cache directory
.npm
# Optional eslint cache
.eslintcache
# Optional stylelint cache
.stylelintcache
# Microbundle cache
.rpt2_cache/
.rts2_cache_cjs/
.rts2_cache_es/
.rts2_cache_umd/
# Optional REPL history
.node_repl_history
# Output of 'npm pack'
*.tgz
# Yarn Integrity file
.yarn-integrity
# dotenv environment variable files
.env
.env.development.local
.env.test.local
.env.production.local
.env.local
# parcel-bundler cache (https://parceljs.org/)
.parcel-cache
# Next.js build output
.next
out
# Nuxt.js build / generate output
.nuxt
dist
# Gatsby files
# Comment in the public line in if your project uses Gatsby and not Next.js
# https://nextjs.org/blog/next-9-1#public-directory-support
# public
# vuepress build output
.vuepress/dist
# vuepress v2.x temp and cache directory
.temp
# Docusaurus cache and generated files
.docusaurus
# Serverless directories
.serverless/
# FuseBox cache
.fusebox/
# DynamoDB Local files
.dynamodb/
# TernJS port file
.tern-port
# Stores VSCode versions used for testing VSCode extensions
.vscode-test
# yarn v2
.yarn/cache
.yarn/unplugged
.yarn/build-state.yml
.yarn/install-state.gz
.pnp.*
# IntelliJ based IDEs
.idea
# Finder (MacOS) folder config
.DS_Store

View file

@ -1,19 +0,0 @@
# sepa-precios-archiver
Archivador del dataset de precios de [Precios Claros - Base SEPA](https://datos.produccion.gob.ar/dataset/sepa-precios). Recomprime para utilizar ~8 veces menos espacio, y resube a un bucket mio de Backblaze B2.
## Instalación
Para instalar las dependencias:
```bash
bun install
```
Para ejecutarlo:
```bash
bun run index.ts
```
This project was created using `bun init` in bun v1.1.25. [Bun](https://bun.sh) is a fast all-in-one JavaScript runtime.

View file

@ -1,17 +0,0 @@
{
"name": "sepa-precios-archiver",
"module": "index.ts",
"type": "module",
"devDependencies": {
"@types/bun": "latest"
},
"peerDependencies": {
"typescript": "^5.5.4"
},
"dependencies": {
"@aws-sdk/client-s3": "^3.637.0",
"@aws-sdk/lib-storage": "^3.637.0",
"zod": "^3.23.8",
"sepa-index-gen": "workspace:*"
}
}

View file

@ -1,27 +0,0 @@
{
"compilerOptions": {
// Enable latest features
"lib": ["ESNext", "DOM"],
"target": "ESNext",
"module": "ESNext",
"moduleDetection": "force",
"jsx": "react-jsx",
"allowJs": true,
// Bundler mode
"moduleResolution": "bundler",
"allowImportingTsExtensions": true,
"verbatimModuleSyntax": true,
"noEmit": true,
// Best practices
"strict": true,
"skipLibCheck": true,
"noFallthroughCasesInSwitch": true,
// Some stricter flags (disabled by default)
"noUnusedLocals": false,
"noUnusedParameters": false,
"noPropertyAccessFromIndexSignature": false
}
}

View file

@ -1,175 +0,0 @@
# Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore
# Logs
logs
_.log
npm-debug.log_
yarn-debug.log*
yarn-error.log*
lerna-debug.log*
.pnpm-debug.log*
# Caches
.cache
# Diagnostic reports (https://nodejs.org/api/report.html)
report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
# Runtime data
pids
_.pid
_.seed
*.pid.lock
# Directory for instrumented libs generated by jscoverage/JSCover
lib-cov
# Coverage directory used by tools like istanbul
coverage
*.lcov
# nyc test coverage
.nyc_output
# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
.grunt
# Bower dependency directory (https://bower.io/)
bower_components
# node-waf configuration
.lock-wscript
# Compiled binary addons (https://nodejs.org/api/addons.html)
build/Release
# Dependency directories
node_modules/
jspm_packages/
# Snowpack dependency directory (https://snowpack.dev/)
web_modules/
# TypeScript cache
*.tsbuildinfo
# Optional npm cache directory
.npm
# Optional eslint cache
.eslintcache
# Optional stylelint cache
.stylelintcache
# Microbundle cache
.rpt2_cache/
.rts2_cache_cjs/
.rts2_cache_es/
.rts2_cache_umd/
# Optional REPL history
.node_repl_history
# Output of 'npm pack'
*.tgz
# Yarn Integrity file
.yarn-integrity
# dotenv environment variable files
.env
.env.development.local
.env.test.local
.env.production.local
.env.local
# parcel-bundler cache (https://parceljs.org/)
.parcel-cache
# Next.js build output
.next
out
# Nuxt.js build / generate output
.nuxt
dist
# Gatsby files
# Comment in the public line in if your project uses Gatsby and not Next.js
# https://nextjs.org/blog/next-9-1#public-directory-support
# public
# vuepress build output
.vuepress/dist
# vuepress v2.x temp and cache directory
.temp
# Docusaurus cache and generated files
.docusaurus
# Serverless directories
.serverless/
# FuseBox cache
.fusebox/
# DynamoDB Local files
.dynamodb/
# TernJS port file
.tern-port
# Stores VSCode versions used for testing VSCode extensions
.vscode-test
# yarn v2
.yarn/cache
.yarn/unplugged
.yarn/build-state.yml
.yarn/install-state.gz
.pnp.*
# IntelliJ based IDEs
.idea
# Finder (MacOS) folder config
.DS_Store

View file

@ -1,14 +0,0 @@
# sepa-precios-importer
Importador de [datasets de precios de SEPA](https://datos.produccion.gob.ar/dataset/sepa-precios/archivo/d076720f-a7f0-4af8-b1d6-1b99d5a90c14) a una base de datos PostgreSQL.
Vease [Errores en el formato de los datos SEPA](https://gist.github.com/catdevnull/587d5c63c4bab11b9798861c917db93b)
To install dependencies:
```bash
bun install
bun run index.ts ~/carpeta-con-datasets-descomprimidos
```
This project was created using `bun init` in bun v1.1.26. [Bun](https://bun.sh) is a fast all-in-one JavaScript runtime.

View file

@ -1,18 +0,0 @@
{
"name": "sepa-precios-importer",
"module": "index.ts",
"type": "module",
"devDependencies": {
"@types/bun": "^1.1.7",
"@types/papaparse": "^5.3.14"
},
"peerDependencies": {
"typescript": "^5.0.0"
},
"dependencies": {
"ckan": "workspace:*",
"p-queue": "^8.0.1",
"papaparse": "^5.4.1",
"postgres": "^3.4.4"
}
}

View file

@ -1,27 +0,0 @@
{
"compilerOptions": {
// Enable latest features
"lib": ["ESNext", "DOM"],
"target": "ESNext",
"module": "ESNext",
"moduleDetection": "force",
"jsx": "react-jsx",
"allowJs": true,
// Bundler mode
"moduleResolution": "bundler",
"allowImportingTsExtensions": true,
"verbatimModuleSyntax": true,
"noEmit": true,
// Best practices
"strict": true,
"skipLibCheck": true,
"noFallthroughCasesInSwitch": true,
// Some stricter flags (disabled by default)
"noUnusedLocals": false,
"noUnusedParameters": false,
"noPropertyAccessFromIndexSignature": false
}
}