@tricoteuses/senat 2.22.3 → 2.22.5

package/lib/scripts/convert_data.d.ts

@@ -0,0 +1 @@
+export {};

package/lib/scripts/convert_data.js

@@ -0,0 +1,354 @@
+import assert from "assert";
+import commandLineArgs from "command-line-args";
+import fs from "fs-extra";
+import path from "path";
+import pLimit from "p-limit";
+import * as git from "../git";
+import { datasets, EnabledDatasets, getEnabledDatasets } from "../datasets";
+import { DATA_ORIGINAL_FOLDER, DATA_TRANSFORMED_FOLDER, DOCUMENT_METADATA_FILE, DOSLEG_DOSSIERS_FOLDER, SCRUTINS_FOLDER, RAPPORT_FOLDER, SENS_CIRCONSCRIPTIONS_FOLDER, SENS_ORGANISMES_FOLDER, SENS_SENATEURS_FOLDER, TEXTE_FOLDER } from "../loaders";
+import { findAllAmendements, findAllCirconscriptions, findAllDebats, findAllDossiers, findAllScrutins, findAllOrganismes, findAllQuestions, findAllSens, findAllTextes, findAllRapports, } from "../model";
+import { processRapport, processTexte } from "./retrieve_documents";
+import { buildActesLegislatifs } from "../model/dosleg";
+import { UNDEFINED_SESSION } from "../types/sessions";
+import { getSessionFromDate, getSessionFromSignet } from "./datautil";
+import { commonOptions } from "./shared/cli_helpers";
+import { ensureAndClearDir } from "./shared/util";
+const optionsDefinitions = [...commonOptions];
+const options = commandLineArgs(optionsDefinitions);
+const SENAT_TEXTE_XML_BASE_URL = "https://www.senat.fr/akomantoso/";
+const SENAT_TEXTE_BASE_URL = "https://www.senat.fr/leg/";
+const SENAT_EXPOSE_DES_MOTIFS_BASE_URL = "https://www.senat.fr/leg/exposes-des-motifs/";
+const SENAT_RAPPORT_BASE_URL = "https://www.senat.fr/rap/";
+function commitGit(datasetDir, options, exitCode) {
+    if (options.commit) {
+        const errorCode = git.commitAndPush(datasetDir, "Nouvelle moisson", options.remote);
+        if ((exitCode === 10 && errorCode !== 10) || (exitCode === 0 && errorCode !== 0 && errorCode !== 10)) {
+            exitCode = errorCode;
+        }
+    }
+    return exitCode;
+}
+async function convertData() {
+    const dataDir = options["dataDir"];
+    assert(dataDir, "Missing argument: data directory");
+    const enabledDatasets = getEnabledDatasets(options["categories"]);
+    console.time("data transformation time");
+    let exitCode = 0;
+    if (enabledDatasets & EnabledDatasets.Ameli) {
+        try {
+            await convertDatasetAmeli(dataDir, options);
+            const ameliDir = path.join(dataDir, datasets.ameli.database);
+            exitCode = commitGit(ameliDir, options, exitCode);
+        }
+        catch (error) {
+            console.error(`Error converting Ameli dataset:`, error);
+        }
+    }
+    if (enabledDatasets & EnabledDatasets.Debats) {
+        try {
+            await convertDatasetDebats(dataDir, options);
+            const debatsDir = path.join(dataDir, datasets.debats.database);
+            exitCode = commitGit(debatsDir, options, exitCode);
+        }
+        catch (error) {
+            console.error(`Error converting Debats dataset:`, error);
+        }
+    }
+    if (enabledDatasets & EnabledDatasets.DosLeg) {
+        try {
+            await convertDatasetDosLeg(dataDir, options);
+            const doslegDir = path.join(dataDir, datasets.dosleg.database);
+            exitCode = commitGit(doslegDir, options, exitCode);
+        }
+        catch (error) {
+            console.error(`Error converting DosLeg dataset:`, error);
+        }
+        try {
+            await convertDatasetScrutins(dataDir, options);
+            const scrutinsDir = path.join(dataDir, SCRUTINS_FOLDER);
+            exitCode = commitGit(scrutinsDir, options, exitCode);
+        }
+        catch (error) {
+            console.error(`Error converting Scrutins dataset:`, error);
+        }
+    }
+    if (enabledDatasets & EnabledDatasets.Questions) {
+        try {
+            await convertDatasetQuestions(dataDir, options);
+            const questionsDir = path.join(dataDir, datasets.questions.database);
+            exitCode = commitGit(questionsDir, options, exitCode);
+        }
+        catch (error) {
+            console.error(`Error converting Questions dataset:`, error);
+        }
+    }
+    if (enabledDatasets & EnabledDatasets.Sens) {
+        try {
+            await convertDatasetSens(dataDir, options);
+            const sensDir = path.join(dataDir, datasets.sens.database);
+            exitCode = commitGit(sensDir, options, exitCode);
+        }
+        catch (error) {
+            console.error(`Error converting Sens dataset:`, error);
+        }
+    }
+    if (!options["silent"]) {
+        console.timeEnd("data transformation time");
+    }
+    return exitCode;
+}
+async function convertDatasetAmeli(dataDir, options) {
+    const dataset = datasets.ameli;
+    if (!options["silent"]) {
+        console.log(`Converting database ${dataset.database} data into files…`);
+    }
+    const ameliReorganizedRootDir = path.join(dataDir, dataset.database);
+    if (!options.keepDir) {
+        ensureAndClearDir(ameliReorganizedRootDir);
+    }
+    for await (const amendement of findAllAmendements(options["fromSession"])) {
+        if (options["verbose"]) {
+            console.log(`Converting ${amendement["numero"]} file…`);
+        }
+        const session = String(amendement["session"]) || UNDEFINED_SESSION;
+        const signetDossierLegislatif = amendement["signet_dossier_legislatif"] ||
+            `${amendement["nature_texte"]}-${amendement["numero_texte"]}`.toLowerCase();
+        const amendementFileName = `${amendement["numero"]}.json`;
+        const filePath = path.join(ameliReorganizedRootDir, String(session), signetDossierLegislatif, amendementFileName);
+        await fs.outputJSON(filePath, amendement, { spaces: 2 });
+    }
+}
+async function convertDatasetDebats(dataDir, options) {
+    const dataset = datasets.debats;
+    if (!options["silent"]) {
+        console.log(`Converting database ${dataset.database} data into files…`);
+    }
+    const debatsReorganizedRootDir = path.join(dataDir, dataset.database);
+    if (!options.keepDir) {
+        ensureAndClearDir(debatsReorganizedRootDir);
+    }
+    for await (const debat of findAllDebats()) {
+        if (options["verbose"]) {
+            console.log(`Converting ${debat.id} file…`);
+        }
+        const session = getSessionFromDate(debat.date_seance);
+        if (options["fromSession"] && session < options["fromSession"]) {
+            continue;
+        }
+        const debatFileName = `${debat.id}.json`;
+        const filePath = path.join(debatsReorganizedRootDir, String(session), debatFileName);
+        await fs.outputJSON(filePath, debat, { spaces: 2 });
+    }
+}
+async function convertDatasetDosLeg(dataDir, options) {
+    const dataset = datasets.dosleg;
+    if (!options["silent"]) {
+        console.log(`Converting database ${dataset.database} data into files…`);
+    }
+    const doslegReorganizedRootDir = path.join(dataDir, dataset.database);
+    const dossiersReorganizedDir = path.join(doslegReorganizedRootDir, DOSLEG_DOSSIERS_FOLDER);
+    if (!options.keepDir) {
+        ensureAndClearDir(doslegReorganizedRootDir);
+        ensureAndClearDir(dossiersReorganizedDir);
+    }
+    for await (const dossier of findAllDossiers()) {
+        if (options["verbose"]) {
+            console.log(`Converting ${dossier["signet"]} file…`);
+        }
+        let dossierReorganizedDir = path.join(dossiersReorganizedDir, String(UNDEFINED_SESSION));
+        const session = getSessionFromSignet(dossier["signet"]) || UNDEFINED_SESSION;
+        if (options["fromSession"] && session < options["fromSession"]) {
+            continue;
+        }
+        dossierReorganizedDir = path.join(dossiersReorganizedDir, String(session));
+        const actesBrutsNormalises = buildActesLegislatifs(dossier);
+        const dossierWithActes = {
+            ...dossier,
+            actes_legislatifs: actesBrutsNormalises
+        };
+        const dossierFile = `${dossier["signet"]}.json`;
+        await fs.outputJSON(path.join(dossierReorganizedDir, dossierFile), dossierWithActes, { spaces: 2 });
+    }
+    await convertTextes(dataDir, options);
+    await convertRapports(dataDir, options);
+}
+async function convertDatasetScrutins(dataDir, options) {
+    const dataset = datasets.dosleg;
+    if (!options["silent"]) {
+        console.log(`Converting database scrutins (${dataset.database}) data into files…`);
+    }
+    const scrutinsReorganizedDir = path.join(dataDir, SCRUTINS_FOLDER);
+    if (!options.keepDir) {
+        ensureAndClearDir(scrutinsReorganizedDir);
+    }
+    for await (const scrutin of findAllScrutins(options["fromSession"])) {
+        if (options["verbose"]) {
+            console.log(`Converting ${scrutin["numero"]} file…`);
+        }
+        let scrutinReorganizedDir = path.join(scrutinsReorganizedDir, String(UNDEFINED_SESSION));
+        const session = scrutin["session"] || UNDEFINED_SESSION;
+        scrutinReorganizedDir = path.join(scrutinsReorganizedDir, String(session));
+        const scrutinFileName = `${scrutin["numero"]}.json`;
+        await fs.outputJSON(path.join(scrutinReorganizedDir, scrutinFileName), scrutin, {
+            spaces: 2,
+        });
+    }
+}
+async function convertDatasetQuestions(dataDir, options) {
+    const dataset = datasets.questions;
+    if (!options["silent"]) {
+        console.log(`Converting database ${dataset.database} data into files…`);
+    }
+    const questionsReorganizedRootDir = path.join(dataDir, dataset.database);
+    if (!options.keepDir) {
+        ensureAndClearDir(questionsReorganizedRootDir);
+    }
+    const limit = pLimit(10);
+    const tasks = [];
+    for await (const question of findAllQuestions()) {
+        tasks.push(limit(async () => {
+            if (options["verbose"]) {
+                console.log(`Converting ${question["reference"]} file…`);
+            }
+            const legislature = question["legislature"] ? question["legislature"] : 0;
+            const questionFileName = `${question["reference"]}.json`;
+            await fs.outputJSON(path.join(questionsReorganizedRootDir, String(legislature), questionFileName), question, {
+                spaces: 2,
+            });
+        }));
+    }
+    await Promise.all(tasks);
+}
+async function convertTextes(dataDir, options) {
+    const originalTextesDir = path.join(dataDir, TEXTE_FOLDER, DATA_ORIGINAL_FOLDER);
+    const transformedTextesDir = path.join(dataDir, TEXTE_FOLDER, DATA_TRANSFORMED_FOLDER);
+    if (!options["silent"]) {
+        console.log(`Converting database textes data into files…`);
+    }
+    for await (const texte of findAllTextes()) {
+        const session = texte["session"] ?? UNDEFINED_SESSION;
+        if (options["fromSession"] && session < options["fromSession"]) {
+            continue;
+        }
+        if (!texte["url"]) {
+            continue;
+        }
+        const texteName = path.parse(texte["url"]).name;
+        const texteDir = path.join(originalTextesDir, `${session}`, texteName);
+        // oritxtcod = 1 corresponds to "Texte de loi déposé au Sénat"
+        const hasExposeDesMotifs = texte["origine"] === 'Sénat' && texte["ordre_origine"] === '1';
+        const metadata = {
+            name: texteName,
+            session: texte["session"],
+            date: texte["date"],
+            url_expose_des_motifs: hasExposeDesMotifs
+                ? new URL(`${texteName}-expose.html`, SENAT_EXPOSE_DES_MOTIFS_BASE_URL)
+                : undefined,
+            url_xml: new URL(`${texteName}.akn.xml`, SENAT_TEXTE_XML_BASE_URL),
+            url_html: new URL(`${texteName}.html`, SENAT_TEXTE_BASE_URL),
+            url_pdf: new URL(`${texteName}.pdf`, SENAT_TEXTE_BASE_URL),
+        };
+        fs.outputJSONSync(path.join(texteDir, `${texteName}.json`), texte, {
+            spaces: 2,
+        });
+        fs.outputJSONSync(path.join(texteDir, DOCUMENT_METADATA_FILE), metadata, {
+            spaces: 2,
+        });
+        if (options.fetchDocuments) {
+            await processTexte(metadata, originalTextesDir, transformedTextesDir, options);
+        }
+    }
+}
+async function convertRapports(dataDir, options) {
+    const originalRapportsDir = path.join(dataDir, RAPPORT_FOLDER, DATA_ORIGINAL_FOLDER);
+    if (!options["silent"]) {
+        console.log(`Converting database rapports data into files…`);
+    }
+    for await (const rapport of findAllRapports()) {
+        const session = rapport["session"] ?? UNDEFINED_SESSION;
+        if (options["fromSession"] && session < options["fromSession"]) {
+            continue;
+        }
+        if (!rapport["url"]) {
+            continue;
+        }
+        const parsedRapportUrl = path.parse(rapport["url"]);
+        const rapportName = parsedRapportUrl.name;
+        const rapportDir = path.join(originalRapportsDir, `${session}`, rapportName);
+        const rapportHtmlUrlBase = `${rapportName}_mono.html`;
+        const rapportHtmlUrl = path.format({
+            dir: parsedRapportUrl.dir,
+            base: rapportHtmlUrlBase,
+        });
+        const rapportPdfUrlBase = `${rapportName}1.pdf`;
+        const rapportPdfUrl = path.format({
+            dir: parsedRapportUrl.dir,
+            base: rapportPdfUrlBase,
+        });
+        const metadata = {
+            name: rapportName,
+            session: rapport["session"],
+            date: rapport["date"],
+            url_html: new URL(rapportHtmlUrl, SENAT_RAPPORT_BASE_URL),
+            url_pdf: new URL(rapportPdfUrl, SENAT_RAPPORT_BASE_URL),
+        };
+        fs.outputJSONSync(path.join(rapportDir, `${rapportName}.json`), rapport, {
+            spaces: 2,
+        });
+        fs.outputJSONSync(path.join(rapportDir, DOCUMENT_METADATA_FILE), metadata, {
+            spaces: 2,
+        });
+        if (options.fetchDocuments) {
+            await processRapport(metadata, originalRapportsDir, options);
+        }
+    }
+}
+async function convertDatasetSens(dataDir, options) {
+    const dataset = datasets.sens;
+    if (!options["silent"]) {
+        console.log(`Converting database ${dataset.database} data into files…`);
+    }
+    const sensReorganizedRootDir = path.join(dataDir, dataset.database);
+    const senateursReorganizedDir = path.join(sensReorganizedRootDir, SENS_SENATEURS_FOLDER);
+    const circonscriptionsReorganizedDir = path.join(sensReorganizedRootDir, SENS_CIRCONSCRIPTIONS_FOLDER);
+    const organismesReorganizedDir = path.join(sensReorganizedRootDir, SENS_ORGANISMES_FOLDER);
+    if (!options.keepDir) {
+        ensureAndClearDir(sensReorganizedRootDir);
+        ensureAndClearDir(senateursReorganizedDir);
+        ensureAndClearDir(circonscriptionsReorganizedDir);
+        ensureAndClearDir(organismesReorganizedDir);
+    }
+    for await (const sen of findAllSens()) {
+        if (options["verbose"]) {
+            console.log(`Converting ${sen["matricule"]} file…`);
+        }
+        const senFileName = `${sen["matricule"]}.json`;
+        fs.outputJSONSync(path.join(senateursReorganizedDir, senFileName), sen, {
+            spaces: 2,
+        });
+    }
+    for await (const circonscription of findAllCirconscriptions()) {
+        if (options["verbose"]) {
+            console.log(`Converting ${circonscription["identifiant"]} file…`);
+        }
+        const circonscriptionFileName = `${circonscription["identifiant"]}.json`;
+        fs.outputJSONSync(path.join(circonscriptionsReorganizedDir, circonscriptionFileName), circonscription, {
+            spaces: 2,
+        });
+    }
+    for await (const organisme of findAllOrganismes()) {
+        if (options["verbose"]) {
+            console.log(`Converting ${organisme["code"]} file…`);
+        }
+        const organismeFileName = `${organisme["code"]}.json`;
+        fs.outputJSONSync(path.join(organismesReorganizedDir, organisme["type_code"], organismeFileName), organisme, {
+            spaces: 2,
+        });
+    }
+}
+convertData()
+    .then((exitCode) => process.exit(exitCode || 0))
+    .catch((error) => {
+    console.log(error);
+    process.exit(1);
+});

package/lib/scripts/convert_data.mjs

@@ -0,0 +1,181 @@
+import assert from "assert";
+import commandLineArgs from "command-line-args";
+import fs from "fs-extra";
+import path from "path";
+import { datasets, EnabledDatasets, getEnabledDatasets } from "../datasets";
+import { DOCUMENT_METADATA_FILE, DOSLEG_DOSSIERS_FOLDER, RAPPORT_FOLDER, SENS_CIRCONSCRIPTIONS_FOLDER, SENS_ORGANISMES_FOLDER, SENS_SENATEURS_FOLDER, TEXTE_FOLDER, TEXTE_ORIGINAL_FOLDER, } from "../loaders";
+import { findAllAmendements, findAllCirconscriptions, findAllLois, findAllOrganismes, findAllQuestions, findAllSens, } from "../model";
+import { findSenatRapportUrls, findSenatTexteUrls } from "../model/dosleg";
+import { formatToFourDigitSession, SIGNET_STRUCTURE_REGEXP, UNDEFINED_SESSION } from "./datautil";
+import { commonOptions } from "./shared/cli_helpers";
+import { ensureAndClearDir } from "./shared/util";
+const optionsDefinitions = [
+    ...commonOptions,
+];
+const options = commandLineArgs(optionsDefinitions);
+const SENAT_TEXTE_XML_BASE_URL = "https://www.senat.fr/akomantoso/";
+const SENAT_TEXTE_BASE_URL = "https://www.senat.fr/leg/";
+const SENAT_EXPOSE_DES_MOTIFS_BASE_URL = "https://www.senat.fr/leg/exposes-des-motifs/";
+const SENAT_RAPPORT_BASE_URL = "https://www.senat.fr/rap/";
+async function convertData() {
+    const enabledDatasets = getEnabledDatasets(options.categories);
+    const dataDir = options.dataDir;
+    assert(dataDir, "Missing argument: data directory");
+    console.time("data transformation time");
+    if (enabledDatasets & EnabledDatasets.Ameli) {
+        const dataset = datasets.ameli;
+        if (!options.silent) {
+            console.log(`Converting database ${dataset.database} data into files…`);
+        }
+        const ameliReorganizedRootDir = path.join(dataDir, dataset.database);
+        ensureAndClearDir(ameliReorganizedRootDir);
+        for await (const amendement of findAllAmendements()) {
+            if (options.verbose) {
+                console.log(`Converting ${amendement.numero} file…`);
+            }
+            const session = String(amendement.session) || UNDEFINED_SESSION;
+            const signetDossierLegislatif = amendement.signet_dossier_legislatif
+                || `${amendement.nature_texte}-${amendement.numero_texte}`.toLowerCase();
+            const ameliReorganizedDir = path.join(ameliReorganizedRootDir, session, signetDossierLegislatif);
+            fs.ensureDirSync(ameliReorganizedDir);
+            const amendementFileName = `${amendement.numero}.json`;
+            fs.writeJSONSync(path.join(ameliReorganizedDir, amendementFileName), amendement, { spaces: 2 });
+        }
+    }
+    if (enabledDatasets & EnabledDatasets.DosLeg) {
+        const dataset = datasets.dosleg;
+        if (!options.silent) {
+            console.log(`Converting database ${dataset.database} data into files…`);
+        }
+        const doslegReorganizedRootDir = path.join(dataDir, dataset.database);
+        const dossiersReorganizedDir = path.join(doslegReorganizedRootDir, DOSLEG_DOSSIERS_FOLDER);
+        ensureAndClearDir(doslegReorganizedRootDir);
+        ensureAndClearDir(dossiersReorganizedDir);
+        for await (const loi of findAllLois()) {
+            if (options.verbose) {
+                console.log(`Converting ${loi.signet} file…`);
+            }
+            let loiReorganizedDir = path.join(dossiersReorganizedDir, UNDEFINED_SESSION);
+            const signetParts = SIGNET_STRUCTURE_REGEXP.exec(loi.signet)?.groups;
+            if (signetParts) {
+                const { session } = signetParts;
+                const formattedSession = formatToFourDigitSession(session);
+                loiReorganizedDir = path.join(dossiersReorganizedDir, formattedSession);
+            }
+            fs.ensureDirSync(loiReorganizedDir);
+            const loiFileName = `${loi.signet}.json`;
+            fs.writeJSONSync(path.join(loiReorganizedDir, loiFileName), loi, { spaces: 2 });
+        }
+        await convertTexteUrls(dataDir);
+        await convertRapportUrls(dataDir);
+    }
+    if (enabledDatasets & EnabledDatasets.Questions) {
+        const dataset = datasets.questions;
+        if (!options.silent) {
+            console.log(`Converting database ${dataset.database} data into files…`);
+        }
+        const questionsReorganizedRootDir = path.join(dataDir, dataset.database);
+        ensureAndClearDir(questionsReorganizedRootDir);
+        for await (const question of findAllQuestions()) {
+            if (options.verbose) {
+                console.log(`Converting ${question.reference} file…`);
+            }
+            const legislature = question.legislature ? question.legislature : 0;
+            const questionReorganizedDir = path.join(questionsReorganizedRootDir, String(legislature));
+            fs.ensureDirSync(questionReorganizedDir);
+            const questionFileName = `${question.reference}.json`;
+            fs.writeJSONSync(path.join(questionReorganizedDir, questionFileName), question, { spaces: 2 });
+        }
+    }
+    if (enabledDatasets & EnabledDatasets.Sens) {
+        const dataset = datasets.sens;
+        if (!options.silent) {
+            console.log(`Converting database ${dataset.database} data into files…`);
+        }
+        const sensReorganizedRootDir = path.join(dataDir, dataset.database);
+        const senateursReorganizedDir = path.join(sensReorganizedRootDir, SENS_SENATEURS_FOLDER);
+        const circonscriptionsReorganizedDir = path.join(sensReorganizedRootDir, SENS_CIRCONSCRIPTIONS_FOLDER);
+        const organismesReorganizedDir = path.join(sensReorganizedRootDir, SENS_ORGANISMES_FOLDER);
+        ensureAndClearDir(sensReorganizedRootDir);
+        ensureAndClearDir(senateursReorganizedDir);
+        ensureAndClearDir(circonscriptionsReorganizedDir);
+        ensureAndClearDir(organismesReorganizedDir);
+        for await (const sen of findAllSens()) {
+            if (options.verbose) {
+                console.log(`Converting ${sen.matricule} file…`);
+            }
+            const senFileName = `${sen.matricule}.json`;
+            fs.writeJSONSync(path.join(senateursReorganizedDir, senFileName), sen, { spaces: 2 });
+        }
+        for await (const circonscription of findAllCirconscriptions()) {
+            if (options.verbose) {
+                console.log(`Converting ${circonscription.identifiant} file…`);
+            }
+            const circonscriptionFileName = `${circonscription.identifiant}.json`;
+            fs.writeJSONSync(path.join(circonscriptionsReorganizedDir, circonscriptionFileName), circonscription, { spaces: 2 });
+        }
+        for await (const organisme of findAllOrganismes()) {
+            if (options.verbose) {
+                console.log(`Converting ${organisme.code} file…`);
+            }
+            const organismeFileName = `${organisme.code}.json`;
+            fs.writeJSONSync(path.join(organismesReorganizedDir, organismeFileName), organisme, { spaces: 2 });
+        }
+    }
+    if (!options.silent) {
+        console.timeEnd("data transformation time");
+    }
+}
+async function convertTexteUrls(dataDir) {
+    const textesDir = path.join(dataDir, TEXTE_FOLDER);
+    fs.ensureDirSync(textesDir);
+    const originalTextesDir = path.join(textesDir, TEXTE_ORIGINAL_FOLDER);
+    for await (const texte of findSenatTexteUrls(options.sessions)) {
+        const texteName = path.parse(texte.url).name;
+        const texteDir = path.join(originalTextesDir, `${texte.session ?? UNDEFINED_SESSION}`, texteName);
+        fs.ensureDirSync(texteDir);
+        const metadata = {
+            name: texteName,
+            session: texte.session,
+            url_expose_des_motifs: texte.hasExposeDesMotifs ?
+                new URL(`${texteName}-expose.html`, SENAT_EXPOSE_DES_MOTIFS_BASE_URL) : undefined,
+            url_xml: new URL(`${texteName}.akn.xml`, SENAT_TEXTE_XML_BASE_URL),
+            url_html: new URL(`${texteName}.html`, SENAT_TEXTE_BASE_URL),
+            url_pdf: new URL(`${texteName}.pdf`, SENAT_TEXTE_BASE_URL),
+        };
+        fs.writeJSONSync(path.join(texteDir, DOCUMENT_METADATA_FILE), metadata, { spaces: 2 });
+    }
+}
+async function convertRapportUrls(dataDir) {
+    const rapportsDir = path.join(dataDir, RAPPORT_FOLDER);
+    fs.ensureDirSync(rapportsDir);
+    for await (const rapport of findSenatRapportUrls(options.sessions)) {
+        const parsedRapportUrl = path.parse(rapport.url);
+        const rapportName = parsedRapportUrl.name;
+        const rapportDir = path.join(rapportsDir, `${rapport.session ?? UNDEFINED_SESSION}`, rapportName);
+        fs.ensureDirSync(rapportDir);
+        const rapportHtmlUrlBase = `${rapportName}_mono.html`;
+        const rapportHtmlUrl = path.format({
+            dir: parsedRapportUrl.dir,
+            base: rapportHtmlUrlBase,
+        });
+        const rapportPdfUrlBase = `${rapportName}1.pdf`;
+        const rapportPdfUrl = path.format({
+            dir: parsedRapportUrl.dir,
+            base: rapportPdfUrlBase,
+        });
+        const metadata = {
+            name: rapportName,
+            session: rapport.session,
+            url_html: new URL(rapportHtmlUrl, SENAT_RAPPORT_BASE_URL),
+            url_pdf: new URL(rapportPdfUrl, SENAT_RAPPORT_BASE_URL),
+        };
+        fs.writeJSONSync(path.join(rapportDir, DOCUMENT_METADATA_FILE), metadata, { spaces: 2 });
+    }
+}
+convertData()
+    .then(() => process.exit(0))
+    .catch((error) => {
+    console.log(error);
+    process.exit(1);
+});