fix(cbo): build the table from the MTE's current release, kept in the repository

.gitattributes

@@ -0,0 +1 @@
+scripts/data/*.csv -text

CONTRIBUTING.md

@@ -104,8 +104,12 @@ itself:
 - **Generated from an official source** by a script in `scripts/` (`npm run build:data`, run
   every Monday by the `Update datasets` workflow): banks (Banco Central, `banks.ts`), CBO
   (`cbo.ts`), CFOP (CONFAZ, `cfop.ts`), municipalities and states (IBGE, `cities.ts`,
-  `states.ts`), CNAE (`cnae.ts`), legal natures (CONCLA, `legal-natures.ts`) and NCM (Siscomex,
-  `ncm.ts`). When a run changes a file, the workflow opens a pull request whose description, written
+  `states.ts`), the DDD of every municipality (Anatel, `area-codes.ts`), CNAE (`cnae.ts`), legal
+  natures (CONCLA, `legal-natures.ts`) and NCM (Siscomex, `ncm.ts`). The CBO is the one table
+  read from a file kept in the repository, `scripts/data/cbo2002-ocupacao.csv`: the MTE serves
+  its current release only after a reCAPTCHA, so a new release is downloaded by hand from
+  https://cbo.mte.gov.br/cbosite/pages/downloads.jsf ("Estrutura CBO (CSV)"), reviewed, copied
+  over that file and its digest put in `CBO_CSV_SHA256` of `scripts/cbo.ts`. When a run changes a file, the workflow opens a pull request whose description, written
   by `scripts/data-summary.ts`, lists per table how many entries were added and removed, with a
   sample of each. Never edit these files by hand.
 - **Maintained by hand**, because the source is a law or a regulation with no machine-readable

docs/getting-started.md

@@ -72,7 +72,7 @@ A few utils embed an official dataset and weigh far more than everything else co
 | `getMunicipalitiesByAreaCode` · `getAreaCodeByMunicipalityCode` | 5571 IBGE municipalities, with the DDD of each (Anatel) | 165.0 - 167.8 KB | 52.1 - 52.8 KB |
 | `getMunicipalities` · `getMunicipalityByCode` · `getMunicipality` | 5571 IBGE municipalities, with names and codes | 153.6 - 154.0 KB | 49.4 - 49.7 KB |
 | `getCities` | 5571 IBGE municipality names | 153.4 KB | 49.2 KB |
-| `getCbo` | CBO 2002 occupation titles | 115.7 KB | 29.5 KB |
+| `getCbo` | CBO 2002 occupation titles | 117.3 KB | 29.9 KB |
 | `getCest` | CEST descriptions and segments (Convênio ICMS 142/18) | 115.5 KB | 26.1 KB |
 | `getCnae` | CNAE-Subclasses 2.3 | 91.6 KB | 20.0 KB |
 | `isValidNcm` | NCM (Nomenclatura Comum do Mercosul) codes | 82.6 KB | 22.8 KB |

docs/pt-br/getting-started.md

@@ -72,7 +72,7 @@ Alguns utilitários embutem uma base de dados oficial e pesam muito mais que tod
 | `getMunicipalitiesByAreaCode` · `getAreaCodeByMunicipalityCode` | 5571 municípios do IBGE, com o DDD de cada um (Anatel) | 165,0 - 167,8 KB | 52,1 - 52,8 KB |
 | `getMunicipalities` · `getMunicipalityByCode` · `getMunicipality` | 5571 municípios do IBGE, com nomes e códigos | 153,6 - 154,0 KB | 49,4 - 49,7 KB |
 | `getCities` | nomes dos 5571 municípios do IBGE | 153,4 KB | 49,2 KB |
-| `getCbo` | títulos das ocupações da CBO 2002 | 115,7 KB | 29,5 KB |
+| `getCbo` | títulos das ocupações da CBO 2002 | 117,3 KB | 29,9 KB |
 | `getCest` | descrições e segmentos do CEST (Convênio ICMS 142/18) | 115,5 KB | 26,1 KB |
 | `getCnae` | CNAE-Subclasses 2.3 | 91,6 KB | 20,0 KB |
 | `isValidNcm` | códigos NCM (Nomenclatura Comum do Mercosul) | 82,6 KB | 22,8 KB |

docs/pt-br/utilities.md

@@ -2772,7 +2772,7 @@ isValidCbo('2124abc05'); // false (não é uma forma documentada)
 isValidCbo(-212405); // false (não é um inteiro seguro não negativo)
 ```
 
-Fonte: [tabela de ocupações da CBO 2002 publicada pelo MTE](https://www.gov.br/trabalho-e-emprego/pt-br/assuntos/cbo/servicos/downloads/cbo2002-ocupacao.csv).
+Fonte: [tabelas da CBO 2002 publicadas pelo MTE ("Estrutura CBO (CSV)", arquivos de 10/07/2026, 2.725 ocupações)](https://cbo.mte.gov.br/cbosite/pages/downloads.jsf). Até a 2.4.0 a tabela vinha da versão mais antiga do gov.br (06/06/2025): faltavam 37 ocupações, e 6 que o MTE retirou depois (225142, 322105, 322115, 322120, 322125 e 782820) deixam de ser válidas.
 
 ### parseCbo
 
@@ -2802,7 +2802,7 @@ getCbo('000000'); // null
 getCbo('2124abc05'); // null (não é uma forma documentada)
 ```
 
-Fonte: [tabela de ocupações da CBO 2002 publicada pelo MTE](https://www.gov.br/trabalho-e-emprego/pt-br/assuntos/cbo/servicos/downloads/cbo2002-ocupacao.csv).
+Fonte: [tabelas da CBO 2002 publicadas pelo MTE ("Estrutura CBO (CSV)", arquivos de 10/07/2026, 2.725 ocupações)](https://cbo.mte.gov.br/cbosite/pages/downloads.jsf). Até a 2.4.0 a tabela vinha da versão mais antiga do gov.br (06/06/2025): faltavam 37 ocupações, e 6 que o MTE retirou depois (225142, 322105, 322115, 322120, 322125 e 782820) deixam de ser válidas.
 
 ### isValidCnae
 

docs/utilities.md

@@ -2772,7 +2772,7 @@ isValidCbo('2124abc05'); // false (not a documented form)
 isValidCbo(-212405); // false (not a non-negative safe integer)
 ```
 
-Source: [CBO 2002 occupation table published by the MTE](https://www.gov.br/trabalho-e-emprego/pt-br/assuntos/cbo/servicos/downloads/cbo2002-ocupacao.csv).
+Source: [CBO 2002 tables published by the MTE ("Estrutura CBO (CSV)", files of 10/07/2026, 2,725 occupations)](https://cbo.mte.gov.br/cbosite/pages/downloads.jsf). Up to 2.4.0 the table came from the older gov.br release (06/06/2025): 37 occupations were missing, and 6 the MTE has since dropped (225142, 322105, 322115, 322120, 322125 and 782820) are no longer valid.
 
 ### parseCbo
 
@@ -2802,7 +2802,7 @@ getCbo('000000'); // null
 getCbo('2124abc05'); // null (not a documented form)
 ```
 
-Source: [CBO 2002 occupation table published by the MTE](https://www.gov.br/trabalho-e-emprego/pt-br/assuntos/cbo/servicos/downloads/cbo2002-ocupacao.csv).
+Source: [CBO 2002 tables published by the MTE ("Estrutura CBO (CSV)", files of 10/07/2026, 2,725 occupations)](https://cbo.mte.gov.br/cbosite/pages/downloads.jsf). Up to 2.4.0 the table came from the older gov.br release (06/06/2025): 37 occupations were missing, and 6 the MTE has since dropped (225142, 322105, 322115, 322120, 322125 and 782820) are no longer valid.
 
 ### isValidCnae
 

scripts/cbo.ts

@@ -1,12 +1,28 @@
 #!/usr/bin/env node
 
-import { fetchSortedRecord } from "./fetch-sorted-record.ts";
+import { createHash } from "node:crypto";
+import { readFile } from "node:fs/promises";
+import { resolve } from "node:path";
+
 import {
 	runAsEntryPoint,
 	serializeCodes,
 	splitRecord,
 	writeGeneratedFiles,
 } from "./lookup-table.ts";
+import { sortRecord } from "./sort-record.ts";
+
+/**
+ * The official occupation table, `CBO2002 - Ocupacao.csv` of the "Estrutura CBO (CSV)" archive the
+ * Ministério do Trabalho e Emprego serves at https://cbo.mte.gov.br/cbosite/pages/downloads.jsf
+ * (files dated 10/07/2026, 2,725 occupations), kept byte for byte in the repository. That archive
+ * is only served after a reCAPTCHA, so no script can download it; the CSVs gov.br serves without
+ * one are an older release (updated 06/06/2025, 2,694 occupations). A new release is downloaded by
+ * hand, reviewed, and its digest put in `CBO_CSV_SHA256`.
+ */
+const CBO_CSV_PATH = resolve(import.meta.dirname, "data", "cbo2002-ocupacao.csv");
+
+const CBO_CSV_SHA256 = "ad775f2f0b662cf1b702a9c610ed168a8dbf3a407fc67c81cc3b012e447f9893";
 
 /** The official CSV is published in ISO-8859-1, not UTF-8. */
 const CBO_CSV_DECODER = new TextDecoder("iso-8859-1");
@@ -60,17 +76,20 @@ export const renderCbo = (titles: Record<string, string>): Record<string, string
  * the same index of \`CBO_DESCRIPTIONS\`, a module of its own (\`cbo-descriptions.ts\`) so that
  * checking a code does not bundle the titles.
  *
- * Built from the official \`cbo2002-ocupacao.csv\` the Ministério do Trabalho e Emprego publishes
- * on gov.br, a plain \`CODIGO;TITULO\` CSV in ISO-8859-1 whose codes are already the 6 digit
- * form \`Cbo.code\` accepts, so no normalization is applied to them.
+ * Built from \`CBO2002 - Ocupacao.csv\` of the "Estrutura CBO (CSV)" archive the Ministério do
+ * Trabalho e Emprego serves on the CBO site (files dated 10/07/2026), a plain \`CODIGO;TITULO\`
+ * CSV in ISO-8859-1 whose codes are already the 6 digit form \`Cbo.code\` accepts, so no
+ * normalization is applied to them. The site serves it only after a reCAPTCHA, so the file is
+ * kept in the repository (\`scripts/data/cbo2002-ocupacao.csv\`) and checked against a reviewed
+ * SHA-256. The \`cbo2002-ocupacao.csv\` gov.br serves is an older release (updated 06/06/2025): it
+ * lacks 37 occupations of this one and still lists 6 it no longer does.
  *
  * Generated by \`node ./scripts/cbo.ts\`. Do not edit by hand.
  *
+ * @see Official: https://cbo.mte.gov.br/cbosite/pages/downloads.jsf
+ * "Estrutura CBO (CSV)", the CBO 2002 tables as published by the Ministério do Trabalho e Emprego.
  * @see Official: https://www.gov.br/trabalho-e-emprego/pt-br/assuntos/cbo/servicos/downloads/cbo2002-ocupacao.csv
- * The CBO 2002 occupation table, as published by the Ministério do Trabalho e Emprego.
- * @see Based on: https://raw.githubusercontent.com/lucaashoff/lista-cbo-json/main/cbos.json
- * Community mirror of the same table, the fallback this script was generated from before the
- * official CSV was used.
+ * The older release of the same table on gov.br, used up to 2.4.0.
  */
 export const CBO_CODES = ${serializeCodes(codes)};
 
@@ -86,30 +105,29 @@ export const CBO_FORMAT_REGEX = /^\\d{4}[\\s.\\-/]?\\d{2}$/;
  *
  * Generated by \`node ./scripts/cbo.ts\`. Do not edit by hand.
  *
- * @see Official: https://www.gov.br/trabalho-e-emprego/pt-br/assuntos/cbo/servicos/downloads/cbo2002-ocupacao.csv
- * The CBO 2002 occupation table, as published by the Ministério do Trabalho e Emprego.
+ * @see Official: https://cbo.mte.gov.br/cbosite/pages/downloads.jsf
+ * "Estrutura CBO (CSV)", the CBO 2002 tables as published by the Ministério do Trabalho e Emprego.
  */
 export const CBO_DESCRIPTIONS: readonly string[] = ${JSON.stringify(descriptions)};
 `,
 	};
 };
 
 const main = async (): Promise<void> => {
-	const sorted = await fetchSortedRecord(
-		"https://www.gov.br/trabalho-e-emprego/pt-br/assuntos/cbo/servicos/downloads/cbo2002-ocupacao.csv",
-		"CBO CSV",
-		async (response) => {
-			const data = parseCsv(CBO_CSV_DECODER.decode(await response.arrayBuffer()));
+	const csv = await readFile(CBO_CSV_PATH);
+	const digest = createHash("sha256").update(csv).digest("hex");
+
+	if (digest !== CBO_CSV_SHA256) {
+		throw new Error(
+			`${CBO_CSV_PATH} has SHA-256 ${digest}, not the reviewed ${CBO_CSV_SHA256}: review the new file and update CBO_CSV_SHA256`,
+		);
+	}
 
-			if (Object.keys(data).length === 0) {
-				throw new Error("CBO CSV holds no occupation");
-			}
+	const data = parseCsv(CBO_CSV_DECODER.decode(csv));
 
-			return data;
-		},
-	);
+	if (Object.keys(data).length === 0) throw new Error("CBO CSV holds no occupation");
 
-	await writeGeneratedFiles(renderCbo(sorted));
+	await writeGeneratedFiles(renderCbo(sortRecord(data)));
 };
 
 await runAsEntryPoint(import.meta.filename, main);