@tricoteuses/senat 1.4.1 → 2.1.1

package/README.md

@@ -43,19 +43,22 @@ npm run data:download ../senat-data -- [--categories All]
 
 Data from other sources is also available :
 ```bash
-# Retrieval of sénateurs' pictures from Sénat's website
-npm run data:retrieve_senateurs_photos ../senat-data
-
 # Retrieval of textes and rapports from Sénat's website
 # Available options for optional `formats` parameter : xml, html, pdf
 # Available options for optional `types` parameter : textes, rapports
-npm run data:retrieve_documents ../senat-data -- --sessions 2024 2025 [--formats xml pdf] [--types textes]
+npm run data:retrieve_documents ../senat-data -- --fromSession 2023 [--formats xml pdf] [--types textes]
 
 # Retrieval & parsing (textes in xml format only for now)
-npm run data:retrieve_documents ../senat-data -- --sessions 2024 2025 --parseDocuments
+npm run data:retrieve_documents ../senat-data -- --fromSession 2023 --parseDocuments
 
 # Parsing only
 npm run data:parse_textes_lois ../senat-data
+
+# Retrieval of agenda from Sénat's website
+npm run data:retrieve_agenda ../senat-data -- --fromSession 2023
+
+# Retrieval of sénateurs' pictures from Sénat's website
+npm run data:retrieve_senateurs_photos ../senat-data
 ```
 
 ## Data download using Docker
@@ -67,7 +70,7 @@ docker volume create senat-data # Create a volume to download the data
 docker run --name tricoteuses-senat -v senat-data:/app/senat-data -d registry.en-root.org/tricoteuses/tricoteuses-senat:latest
 ```
 
-Use the environment variable `CATEGORIES` and `SESSIONS` if needed.
+Use the environment variable `CATEGORIES` and `FROM_SESSION` if needed.
 
 ## Using the data
 

package/lib/datasets.d.ts

@@ -21,8 +21,9 @@ export declare enum EnabledDatasets {
     Questions = 8,
     Sens = 16,
     PhotosSenateurs = 32,
-    All = 63
+    Agenda = 64,
+    All = 127
 }
 export declare const datasets: Datasets;
-export declare function getEnabledDatasets(categories: any): EnabledDatasets;
-export declare function getChosenFromEnabledDatasets(categories: any): Dataset[];
+export declare function getEnabledDatasets(categories: string[]): EnabledDatasets;
+export declare function getChosenDatasets(enabledDatasets: EnabledDatasets): Dataset[];

package/lib/datasets.js

@@ -10,7 +10,8 @@ export var EnabledDatasets;
     EnabledDatasets[EnabledDatasets["Questions"] = 8] = "Questions";
     EnabledDatasets[EnabledDatasets["Sens"] = 16] = "Sens";
     EnabledDatasets[EnabledDatasets["PhotosSenateurs"] = 32] = "PhotosSenateurs";
-    EnabledDatasets[EnabledDatasets["All"] = 63] = "All";
+    EnabledDatasets[EnabledDatasets["Agenda"] = 64] = "Agenda";
+    EnabledDatasets[EnabledDatasets["All"] = 127] = "All";
 })(EnabledDatasets || (EnabledDatasets = {}));
 export const datasets = {
     ameli: {
@@ -68,8 +69,7 @@ export function getEnabledDatasets(categories) {
         return enabledDatasets | (enabledDataset || EnabledDatasets.None);
     }, EnabledDatasets.None);
 }
-export function getChosenFromEnabledDatasets(categories) {
-    const enabledDatasets = getEnabledDatasets(categories);
+export function getChosenDatasets(enabledDatasets) {
     return [
         enabledDatasets & EnabledDatasets.Ameli ? datasets.ameli : null,
         enabledDatasets & EnabledDatasets.Debats ? datasets.debats : null,

package/lib/index.d.ts

@@ -6,5 +6,5 @@ export type { Ses, Sub, TxtAmeli } from "./types/ameli";
 export type { Debat, LecAssDeb } from "./types/debats";
 export type { Ass, Aud, Auteur, DateSeance, DecCoc, DenRap, DocAtt, Ecr, EtaLoi, LecAss, LecAssRap, Lecture, Loi, Org, OriTxt, Qua, Rap, RapOrg, Scr, Texte, TypAtt, TypLec, TypLoi, TypTxt, TypUrl, } from "./types/dosleg";
 export type { Photo, Sen } from "./types/sens";
-export { Session } from "./types/sessions";
+export type { UNDEFINED_SESSION, Session, getSessionsFromStart } from "./types/sessions";
 export type { Alinea, Article, Division, DivisionTag, FlatTexte } from "./types/texte";

package/lib/index.js

@@ -1 +1 @@
-export { Session } from "./types/sessions";
+export {};

package/lib/loaders.d.ts

@@ -4,15 +4,16 @@ import { QuestionResult } from "./model/questions";
 import { CirconscriptionResult, OrganismeResult, SenateurResult } from "./model/sens";
 import { FlatTexte } from "./types/texte";
 export { EnabledDatasets } from "./datasets";
+export declare const AGENDA_FOLDER = "agenda";
 export declare const DOSLEG_DOSSIERS_FOLDER = "dossiers";
+export declare const RAPPORT_FOLDER = "rap";
 export declare const SENS_CIRCONSCRIPTIONS_FOLDER = "circonscriptions";
 export declare const SENS_ORGANISMES_FOLDER = "organismes";
 export declare const SENS_SENATEURS_FOLDER = "senateurs";
 export declare const TEXTE_FOLDER = "leg";
-export declare const TEXTE_ORIGINAL_FOLDER = "original";
-export declare const TEXTE_TRANSFORMED_FOLDER = "transformed";
+export declare const DATA_ORIGINAL_FOLDER = "original";
+export declare const DATA_TRANSFORMED_FOLDER = "transformed";
 export declare const DOCUMENT_METADATA_FILE = "metadata.json";
-export declare const RAPPORT_FOLDER = "rap";
 type IterItem<T> = {
     item: T;
     filePathFromDataset?: string;

package/lib/loaders.js

@@ -2,17 +2,18 @@ import fs from "fs";
 import path from "path";
 import legislatures from "./legislatures.json";
 import { datasets } from "./datasets";
-import { UNDEFINED_SESSION } from "./scripts/datautil";
+import { UNDEFINED_SESSION } from "./types/sessions";
 export { EnabledDatasets } from "./datasets";
+export const AGENDA_FOLDER = "agenda";
 export const DOSLEG_DOSSIERS_FOLDER = "dossiers";
+export const RAPPORT_FOLDER = "rap";
 export const SENS_CIRCONSCRIPTIONS_FOLDER = "circonscriptions";
 export const SENS_ORGANISMES_FOLDER = "organismes";
 export const SENS_SENATEURS_FOLDER = "senateurs";
 export const TEXTE_FOLDER = "leg";
-export const TEXTE_ORIGINAL_FOLDER = "original";
-export const TEXTE_TRANSFORMED_FOLDER = "transformed";
+export const DATA_ORIGINAL_FOLDER = "original";
+export const DATA_TRANSFORMED_FOLDER = "transformed";
 export const DOCUMENT_METADATA_FILE = "metadata.json";
-export const RAPPORT_FOLDER = "rap";
 export function* iterFilePaths(dirPath) {
     if (dirPath && fs.existsSync(dirPath)) {
         const files = fs.readdirSync(dirPath, {
@@ -59,7 +60,7 @@ export function* iterLoadSenatDossiersLegislatifs(dataDir, session, options = {}
     }
 }
 export function* iterLoadSenatDossiersLegislatifsTexteUrls(dataDir, session) {
-    let itemsDir = path.join(dataDir, TEXTE_FOLDER, TEXTE_ORIGINAL_FOLDER);
+    let itemsDir = path.join(dataDir, TEXTE_FOLDER, DATA_ORIGINAL_FOLDER);
     if (session) {
         itemsDir = path.join(itemsDir, session.toString());
     }
@@ -121,7 +122,7 @@ export function* iterLoadSenatDossiersLegislatifsTextes(dataDir, session, option
 export function loadSenatTexteContent(dataDir, textePathFromDataset) {
     const parsedTextePath = path.parse(textePathFromDataset);
     const jsonTexteName = `${parsedTextePath.name}.json`;
-    const fullTextePath = path.join(dataDir, TEXTE_FOLDER, TEXTE_TRANSFORMED_FOLDER, parsedTextePath.dir, jsonTexteName);
+    const fullTextePath = path.join(dataDir, TEXTE_FOLDER, DATA_TRANSFORMED_FOLDER, parsedTextePath.dir, jsonTexteName);
     if (!fs.existsSync(fullTextePath)) {
         return { item: null };
     }

package/lib/model/agenda.d.ts

@@ -0,0 +1,2 @@
+import { AgendaEvent } from "../types/agenda";
+export declare function parseAgendaFromFile(htmlFilePath: string): Promise<AgendaEvent[] | null>;

package/lib/model/agenda.js

@@ -0,0 +1,85 @@
+import { JSDOM } from "jsdom";
+import { DateTime } from "luxon";
+function getEventType(eventClasses) {
+    const typeClass = [...eventClasses]
+        .find(className => className.startsWith("evt-"))
+        || null;
+    switch (typeClass) {
+        case "evt-seance":
+            return "Séance publique";
+        case "evt-instanz":
+            return "Commissions";
+        case "evt-cemi":
+            return "Mission de contrôle";
+        case "evt-deleg":
+            return "Offices et délégations";
+        case "evt-bureau":
+            return "Instances décisionnelles";
+    }
+    return null;
+}
+function getUrlDossierSenat(lienElements) {
+    const urlElement = [...lienElements]
+        .find(lienElement => lienElement.textContent?.includes("dossier législatif"));
+    return urlElement ? urlElement.getAttribute("href") : null;
+}
+function getHeuresDebutFin(timeStr) {
+    const normalizedHeureDebut = timeStr
+        ?.replace(/^À l'issue de l'espace réservé .* et au plus tard\s/i, "") // Must be first
+        ?.replace(/^(?:le )?matin/i, "10h00")
+        ?.replace(/^(?:l')?après-midi/i, "16h00")
+        ?.replace(/^(?:le )?soir/i, "20h00")
+        ?.replace(/^(?:la )?nuit/i, "22h00")
+        ?.replace(/^à\s/ig, "")
+        ?.replace(/heures/ig, "h00")
+        ?.replace(/\set.*/i, "")
+        ?.replace(/,.*/, "")
+        ?.replace(/\s\(hors hémicycle\)/i, "")
+        ?.replace(/\s*h\s*/ig, "h");
+    console.dir(`${timeStr};${normalizedHeureDebut}`);
+    const heureDebut = timeStr
+        ? DateTime.fromFormat(timeStr, "H'h'mm").toISOTime()
+        : null;
+    return {
+        heureDebut,
+        heureFin: null
+    };
+}
+function transformAgenda(document) {
+    const agendaEvents = [];
+    const eventElements = document.querySelectorAll(".evt");
+    for (const eventElement of eventElements) {
+        const type = getEventType(eventElement.classList);
+        const timeOriginal = eventElement.querySelector(".time")?.textContent || null;
+        const { heureDebut, heureFin } = getHeuresDebutFin(timeOriginal);
+        const titre = eventElement.querySelector(".titre")?.textContent || null;
+        const organe = eventElement.querySelector(".organe")?.textContent || null;
+        const objet = eventElement.querySelector(".objet")?.textContent || null;
+        const lieu = eventElement.querySelector(".lieu")?.textContent || null;
+        const url_dossier_senat = getUrlDossierSenat(eventElement.querySelectorAll(".lien a"));
+        const url_video = eventElement.querySelector(".video a")?.getAttribute("href") || null;
+        agendaEvents.push({
+            type,
+            heureDebut,
+            heureFin,
+            timeOriginal,
+            titre,
+            organe,
+            objet,
+            lieu,
+            url_dossier_senat,
+            url_video,
+        });
+    }
+    return agendaEvents;
+}
+export async function parseAgendaFromFile(htmlFilePath) {
+    try {
+        const { document } = (await JSDOM.fromFile(htmlFilePath, { contentType: "text/html" })).window;
+        return transformAgenda(document);
+    }
+    catch (error) {
+        console.error(`Could not parse texte with error ${error}`);
+    }
+    return null;
+}

package/lib/model/dosleg.d.ts

@@ -214,12 +214,12 @@ export declare function findAll(): AsyncIterableIterator<{
     numero_JO: string | null;
     url_JO: string | null;
 }>;
-export declare function findSenatTexteUrls(sessions?: string[]): AsyncIterableIterator<{
+export declare function findSenatTexteUrls(sessions?: number[]): AsyncIterableIterator<{
     session: string | null | undefined;
     url: string;
     hasExposeDesMotifs: boolean;
 }>;
-export declare function findSenatRapportUrls(sessions?: string[]): AsyncIterableIterator<{
+export declare function findSenatRapportUrls(sessions?: number[]): AsyncIterableIterator<{
     url: string;
     session: string | null | undefined;
 }>;

package/lib/model/dosleg.js

@@ -170,11 +170,12 @@ export function findAll() {
     return findAllQuery.stream();
 }
 export function findSenatTexteUrls(sessions = []) {
+    const sessionsStr = sessions.map(session => String(session));
     return dbDosleg
         .selectFrom("texte")
         .where("texurl", "is not", null)
         .where("typurl", "=", "I")
-        .$if(sessions.length > 0, (qb) => qb.where("sesann", "in", sessions))
+        .$if(sessions.length > 0, (qb) => qb.where("sesann", "in", sessionsStr))
         .select(({ eb, ref }) => [
         "sesann as session",
         rtrim(ref("texurl")).as("url"),
@@ -190,11 +191,12 @@ export function findSenatTexteUrls(sessions = []) {
         .stream();
 }
 export function findSenatRapportUrls(sessions = []) {
+    const sessionsStr = sessions.map(session => String(session));
     return dbDosleg
         .selectFrom("rap")
         .where("rapurl", "is not", null)
         .where("typurl", "=", "I")
-        .$if(sessions.length > 0, (qb) => qb.where("sesann", "in", sessions))
+        .$if(sessions.length > 0, (qb) => qb.where("sesann", "in", sessionsStr))
         .select(({ ref }) => [rtrim(ref("rapurl")).as("url"), "sesann as session"])
         .$narrowType()
         .stream();

package/lib/scripts/convert_data.js

@@ -3,10 +3,11 @@ 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 { DOCUMENT_METADATA_FILE, DOSLEG_DOSSIERS_FOLDER, RAPPORT_FOLDER, SENS_CIRCONSCRIPTIONS_FOLDER, SENS_ORGANISMES_FOLDER, SENS_SENATEURS_FOLDER, TEXTE_FOLDER, DATA_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 { getSessionsFromStart, UNDEFINED_SESSION } from "../types/sessions";
+import { formatToFourDigitSession, SIGNET_STRUCTURE_REGEXP, } from "./datautil";
 import { commonOptions } from "./shared/cli_helpers";
 import { ensureAndClearDir } from "./shared/util";
 const optionsDefinitions = [...commonOptions];
@@ -16,123 +17,99 @@ 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");
+    const enabledDatasets = getEnabledDatasets(options["categories"]);
+    const sessions = getSessionsFromStart(options["fromSession"]);
     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 });
-        }
+        await convertDatasetAmeli(dataDir);
     }
     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 ${loi.signet} file…`);
-            }
-            let loiReorganizedDir = path.join(dossiersReorganizedDir, UNDEFINED_SESSION);
-            const signetParts = SIGNET_STRUCTURE_REGEXP.exec(loi.signet)?.groups;
-            if (signetParts && "session" in signetParts) {
-                const { session } = signetParts;
-                const formattedSession = formatToFourDigitSession(session);
-                loiReorganizedDir = path.join(dossiersReorganizedDir, formattedSession);
-            }
-            fs.ensureDirSync(loiReorganizedDir);
-            const loiFileName = `${loi.signet}.json`;
-            fs.writeJSONSync(path.join(loiReorganizedDir, loiFileName), loi, {
-                spaces: 2,
-            });
-        }
-        await convertTexteUrls(dataDir);
-        await convertRapportUrls(dataDir);
+        await convertDatasetDosLeg(dataDir, sessions);
     }
     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 });
-        }
+        await convertDatasetQuestions(dataDir);
     }
     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,
-            });
+        await convertDatasetSens(dataDir);
+    }
+    if (!options["silent"]) {
+        console.timeEnd("data transformation time");
+    }
+}
+async function convertDatasetAmeli(dataDir) {
+    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…`);
         }
-        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 });
+        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, String(session), signetDossierLegislatif);
+        fs.ensureDirSync(ameliReorganizedDir);
+        const amendementFileName = `${amendement.numero}.json`;
+        fs.writeJSONSync(path.join(ameliReorganizedDir, amendementFileName), amendement, { spaces: 2 });
+    }
+}
+async function convertDatasetDosLeg(dataDir, sessions) {
+    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…`);
         }
-        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 });
+        let loiReorganizedDir = path.join(dossiersReorganizedDir, String(UNDEFINED_SESSION));
+        const signetParts = SIGNET_STRUCTURE_REGEXP.exec(loi.signet)?.groups;
+        if (signetParts && "session" in signetParts) {
+            const { session } = signetParts;
+            const formattedSession = formatToFourDigitSession(session);
+            loiReorganizedDir = path.join(dossiersReorganizedDir, String(formattedSession));
         }
+        fs.ensureDirSync(loiReorganizedDir);
+        const loiFileName = `${loi.signet}.json`;
+        fs.writeJSONSync(path.join(loiReorganizedDir, loiFileName), loi, {
+            spaces: 2,
+        });
     }
+    await convertTexteUrls(dataDir, sessions);
+    await convertRapportUrls(dataDir, sessions);
+}
+async function convertDatasetQuestions(dataDir) {
+    const dataset = datasets.questions;
     if (!options["silent"]) {
-        console.timeEnd("data transformation time");
+        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 });
     }
 }
-async function convertTexteUrls(dataDir) {
+async function convertTexteUrls(dataDir, sessions) {
     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 originalTextesDir = path.join(textesDir, DATA_ORIGINAL_FOLDER);
+    for await (const texte of findSenatTexteUrls(sessions)) {
         const texteName = path.parse(texte.url).name;
         const texteDir = path.join(originalTextesDir, `${texte.session ?? UNDEFINED_SESSION}`, texteName);
         fs.ensureDirSync(texteDir);
@@ -151,10 +128,10 @@ async function convertTexteUrls(dataDir) {
         });
     }
 }
-async function convertRapportUrls(dataDir) {
+async function convertRapportUrls(dataDir, sessions) {
     const rapportsDir = path.join(dataDir, RAPPORT_FOLDER);
     fs.ensureDirSync(rapportsDir);
-    for await (const rapport of findSenatRapportUrls(options["sessions"])) {
+    for await (const rapport of findSenatRapportUrls(sessions)) {
         const parsedRapportUrl = path.parse(rapport.url);
         const rapportName = parsedRapportUrl.name;
         const rapportDir = path.join(rapportsDir, `${rapport.session ?? UNDEFINED_SESSION}`, rapportName);
@@ -180,6 +157,43 @@ async function convertRapportUrls(dataDir) {
         });
     }
 }
+async function convertDatasetSens(dataDir) {
+    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 });
+    }
+}
 convertData()
     .then(() => process.exit(0))
     .catch((error) => {

package/lib/scripts/datautil.d.ts

@@ -1,5 +1,4 @@
 export declare const SIGNET_STRUCTURE_REGEXP: RegExp;
 export declare const AKN_IDENTIFICATION_STRUCTURE_REGEXP: RegExp;
 export declare const AKN_WORKFLOW_IDENTIFICATION_STRUCTURE_REGEXP: RegExp;
-export declare const UNDEFINED_SESSION = "0";
-export declare function formatToFourDigitSession(session: string): string;
+export declare function formatToFourDigitSession(session: string): string | 0;

package/lib/scripts/datautil.js

@@ -1,9 +1,9 @@
 import { DateTime, Settings } from "luxon";
+import { UNDEFINED_SESSION } from "../types/sessions";
 Settings.twoDigitCutoffYear = 50;
 export const SIGNET_STRUCTURE_REGEXP = /^(?<type>[a-z]+)(?<session>\d{2,4})-?(?<numTexte>\d+)?/;
 export const AKN_IDENTIFICATION_STRUCTURE_REGEXP = /^\/akn\/fr\/(?<type>[a-z]+)\/(?<session>\d{4}-\d{4})\/?(?<numTexte>\d+)\/fr@(?<version>\b(?:RECT|RECT_BIS|RECT_TER|RECT_QUATER|RECT_QUINQUIES)\b)?/;
 export const AKN_WORKFLOW_IDENTIFICATION_STRUCTURE_REGEXP = /^\/akn\/fr\/(?<type>[a-z]+)\/(?<session>\d{2,4})\/?(?<numTexte>[a-zA-Z0-9]+)\/fr@(?<version>\b(?:RECT|RECT_BIS|RECT_TER|RECT_QUATER|RECT_QUINQUIES)\b)?/;
-export const UNDEFINED_SESSION = "0";
 export function formatToFourDigitSession(session) {
     if (session.length >= 2) {
         const sessionFirstTwoDigits = session.substring(0, 2);

package/lib/scripts/parse_textes.js

@@ -2,7 +2,7 @@ import assert from "assert";
 import commandLineArgs from "command-line-args";
 import fs from "fs-extra";
 import path from "path";
-import { iterFilePaths, TEXTE_FOLDER, TEXTE_ORIGINAL_FOLDER, TEXTE_TRANSFORMED_FOLDER, } from "../loaders";
+import { iterFilePaths, TEXTE_FOLDER, DATA_ORIGINAL_FOLDER, DATA_TRANSFORMED_FOLDER, } from "../loaders";
 import { parseExposeDesMotifsFromFile, parseTexteFromFile, } from "../model/texte";
 import { commonOptions } from "./shared/cli_helpers";
 import { ensureAndClearDir } from "./shared/util";
@@ -11,14 +11,14 @@ const options = commandLineArgs(optionsDefinitions);
 async function main() {
     const dataDir = options["dataDir"];
     assert(dataDir, "Missing argument: data directory");
-    const transformedTextesDir = path.join(options["dataDir"], TEXTE_FOLDER, TEXTE_TRANSFORMED_FOLDER);
+    const transformedTextesDir = path.join(options["dataDir"], TEXTE_FOLDER, DATA_TRANSFORMED_FOLDER);
     ensureAndClearDir(transformedTextesDir);
-    for (const filePath of iterFilePaths(path.join(dataDir, TEXTE_FOLDER, TEXTE_ORIGINAL_FOLDER))) {
+    for (const filePath of iterFilePaths(path.join(dataDir, TEXTE_FOLDER, DATA_ORIGINAL_FOLDER))) {
         const parsedFilePath = path.parse(filePath);
         if (parsedFilePath.ext !== ".xml") {
             continue;
         }
-        const texteDirFromOriginal = parsedFilePath.dir.substring(filePath.indexOf(TEXTE_ORIGINAL_FOLDER) + TEXTE_ORIGINAL_FOLDER.length);
+        const texteDirFromOriginal = parsedFilePath.dir.substring(filePath.indexOf(DATA_ORIGINAL_FOLDER) + DATA_ORIGINAL_FOLDER.length);
         const transformedTexteDir = path.join(transformedTextesDir, texteDirFromOriginal);
         fs.ensureDirSync(transformedTexteDir);
         if (!options["silent"]) {

package/lib/scripts/retrieve_agenda.d.ts

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

package/lib/scripts/retrieve_agenda.js

@@ -0,0 +1,73 @@
+import assert from "assert";
+import commandLineArgs from "command-line-args";
+import fs from "fs-extra";
+import { DateTime } from "luxon";
+import path from "path";
+import { AGENDA_FOLDER, DATA_ORIGINAL_FOLDER } from "../loaders";
+import { getSessionsFromStart } from "../types/sessions";
+import { commonOptions } from "./shared/cli_helpers";
+import { ensureAndClearDir } from "./shared/util";
+const optionsDefinitions = [
+    ...commonOptions,
+    {
+        help: "parse and convert documents into JSON (textes only for now, requires format xml)",
+        name: "parseDocuments",
+        type: Boolean,
+    },
+];
+const options = commandLineArgs(optionsDefinitions);
+const SENAT_GLOBAL_AGENDA_URL_ROOT = "https://www.senat.fr/aglae/Global";
+async function retrieveAgenda(dataDir, sessions) {
+    const agendaRootDir = path.join(dataDir, AGENDA_FOLDER);
+    ensureAndClearDir(agendaRootDir);
+    const originalAgendaDir = path.join(agendaRootDir, DATA_ORIGINAL_FOLDER);
+    fs.ensureDirSync(originalAgendaDir);
+    for (const session of sessions) {
+        if (!options["silent"]) {
+            console.log(`Retrieving Agenda for session ${session}…`);
+        }
+        const agendaSessionDir = path.join(originalAgendaDir, `${session}`);
+        fs.ensureDirSync(agendaSessionDir);
+        const fifteenDaysFromNow = new Date();
+        fifteenDaysFromNow.setDate(fifteenDaysFromNow.getDate() + 15);
+        for (const date = new Date(session, 0, 1); date <= new Date(session, 11, 31) && date <= fifteenDaysFromNow; date.setDate(date.getDate() + 1)) {
+            const agendaName = DateTime.fromJSDate(date).toFormat("ddMMyyyy");
+            try {
+                const response = await fetch(`${SENAT_GLOBAL_AGENDA_URL_ROOT}/agl${agendaName}.html`);
+                if (!response.ok) {
+                    if (response.status === 404) {
+                        console.warn(`Agenda ${agendaName} not found`);
+                    }
+                    else {
+                        console.error(`An error occurred while retrieving Agenda ${agendaName}: ${response.status}`);
+                    }
+                    return;
+                }
+                const agendaContent = await response.arrayBuffer();
+                if (!agendaContent) {
+                    return;
+                }
+                fs.writeFileSync(path.join(agendaSessionDir, agendaName), Buffer.from(agendaContent));
+            }
+            catch (error) {
+                console.error(error.message);
+            }
+        }
+    }
+}
+async function main() {
+    const dataDir = options["dataDir"];
+    assert(dataDir, "Missing argument: data directory");
+    const sessions = getSessionsFromStart(options["fromSession"]);
+    console.time("agenda processing time");
+    await retrieveAgenda(dataDir, sessions);
+    if (!options["silent"]) {
+        console.timeEnd("agenda processing time");
+    }
+}
+main()
+    .then(() => process.exit(0))
+    .catch((error) => {
+    console.log(error);
+    process.exit(1);
+});

package/lib/scripts/retrieve_documents.js

@@ -2,19 +2,13 @@ import assert from "assert";
 import commandLineArgs from "command-line-args";
 import fs from "fs-extra";
 import path from "path";
-import { iterLoadSenatDossiersLegislatifsRapportUrls, iterLoadSenatDossiersLegislatifsTexteUrls, RAPPORT_FOLDER, TEXTE_FOLDER, TEXTE_ORIGINAL_FOLDER, TEXTE_TRANSFORMED_FOLDER, } from "../loaders";
+import { iterLoadSenatDossiersLegislatifsRapportUrls, iterLoadSenatDossiersLegislatifsTexteUrls, RAPPORT_FOLDER, TEXTE_FOLDER, DATA_ORIGINAL_FOLDER, DATA_TRANSFORMED_FOLDER, } from "../loaders";
 import { parseExposeDesMotifs, parseTexte, parseTexteFromFile, } from "../model/texte";
-import { UNDEFINED_SESSION } from "./datautil";
+import { getSessionsFromStart, UNDEFINED_SESSION } from "../types/sessions";
 import { commonOptions } from "./shared/cli_helpers";
 import { ensureAndClearDir, fetchWithRetry, isOptionEmptyOrHasValue, } from "./shared/util";
 const optionsDefinitions = [
     ...commonOptions,
-    {
-        help: "sessions of textes to retrieve; leave empty for all",
-        multiple: true,
-        name: "sessions",
-        type: String,
-    },
     {
         help: "parse and convert documents into JSON (textes only for now, requires format xml)",
         name: "parseDocuments",
@@ -63,18 +57,18 @@ async function retrieveDocument(documentUrl) {
         return null;
     }
 }
-async function retrieveTextes(dataDir) {
+async function retrieveTextes(dataDir, sessions) {
     const textesDir = path.join(dataDir, TEXTE_FOLDER);
     fs.ensureDirSync(textesDir);
-    const originalTextesDir = path.join(textesDir, TEXTE_ORIGINAL_FOLDER);
-    const transformedTextesDir = path.join(textesDir, TEXTE_TRANSFORMED_FOLDER);
+    const originalTextesDir = path.join(textesDir, DATA_ORIGINAL_FOLDER);
+    const transformedTextesDir = path.join(textesDir, DATA_TRANSFORMED_FOLDER);
     if (options["parseDocuments"]) {
         ensureAndClearDir(transformedTextesDir);
     }
     let retrievedTextesCount = 0;
     const texteUrlsNotFoundOrError = [];
     const texteUrlsParseError = [];
-    for (const session of options["sessions"]) {
+    for (const session of sessions) {
         for (const { item: texteMetadata, } of iterLoadSenatDossiersLegislatifsTexteUrls(dataDir, session)) {
             const texteDir = path.join(originalTextesDir, `${texteMetadata.session ?? UNDEFINED_SESSION}`, texteMetadata.name);
             fs.ensureDirSync(texteDir);
@@ -180,12 +174,12 @@ async function retrieveTextes(dataDir) {
         }
     }
 }
-async function retrieveRapports(dataDir) {
+async function retrieveRapports(dataDir, sessions) {
     const rapportsDir = path.join(dataDir, RAPPORT_FOLDER);
     fs.ensureDirSync(rapportsDir);
     let retrievedRapportsCount = 0;
     const rapportUrlsNotFoundOrError = [];
-    for (const session of options["sessions"]) {
+    for (const session of sessions) {
         for (const { item: rapportMetadata, } of iterLoadSenatDossiersLegislatifsRapportUrls(dataDir, session)) {
             const rapportDir = path.join(rapportsDir, `${rapportMetadata.session ?? UNDEFINED_SESSION}`, rapportMetadata.name);
             fs.ensureDirSync(rapportDir);
@@ -231,12 +225,13 @@ async function retrieveRapports(dataDir) {
 async function main() {
     const dataDir = options["dataDir"];
     assert(dataDir, "Missing argument: data directory");
+    const sessions = getSessionsFromStart(options["fromSession"]);
     console.time("documents processing time");
     if (isOptionEmptyOrHasValue(options["types"], "textes")) {
-        await retrieveTextes(dataDir);
+        await retrieveTextes(dataDir, sessions);
     }
     if (isOptionEmptyOrHasValue(options["types"], "rapports")) {
-        await retrieveRapports(dataDir);
+        await retrieveRapports(dataDir, sessions);
     }
     if (!options["silent"]) {
         console.timeEnd("documents processing time");

package/lib/scripts/retrieve_open_data.js

@@ -10,7 +10,7 @@ import readline from "readline";
 // import util from "util"
 import windows1252 from "windows-1252";
 import config from "../config";
-import { datasets, getChosenFromEnabledDatasets } from "../datasets";
+import { datasets, getChosenDatasets, getEnabledDatasets } from "../datasets";
 import { commonOptions } from "./shared/cli_helpers";
 const badWindows1252CharacterRegex = /[\u0080-\u009f]/g;
 const optionsDefinitions = [
@@ -201,8 +201,9 @@ async function retrieveOpenData() {
             encoding: "utf-8",
         });
     }
-    const choosenDatasets = getChosenFromEnabledDatasets(options["categories"]);
-    for (const dataset of choosenDatasets) {
+    const enabledDatasets = getEnabledDatasets(options["categories"]);
+    const chosenDatasets = getChosenDatasets(enabledDatasets);
+    for (const dataset of chosenDatasets) {
         await retrieveDataset(dataDir, dataset);
     }
     if (!options["silent"]) {

package/lib/scripts/shared/cli_helpers.d.ts

@@ -12,6 +12,12 @@ export declare const dataDirDefaultOption: {
     name: string;
     type: StringConstructor;
 };
+export declare const fromSessionOption: {
+    defaultValue: number;
+    help: string;
+    name: string;
+    type: NumberConstructor;
+};
 export declare const silentOption: {
     alias: string;
     help: string;
@@ -36,6 +42,11 @@ export declare const commonOptions: ({
     help: string;
     name: string;
     type: StringConstructor;
+} | {
+    defaultValue: number;
+    help: string;
+    name: string;
+    type: NumberConstructor;
 } | {
     alias: string;
     help: string;

package/lib/scripts/shared/cli_helpers.js

@@ -1,7 +1,7 @@
 export const categoriesOption = {
     alias: "k",
     defaultValue: ["All"],
-    help: "categories of datasets to reorganize",
+    help: "categories of datasets to reorganize; default All",
     multiple: true,
     name: "categories",
     type: String,
@@ -12,6 +12,12 @@ export const dataDirDefaultOption = {
     name: "dataDir",
     type: String,
 };
+export const fromSessionOption = {
+    defaultValue: 2023,
+    help: "session year to retrieve data from; default 2023",
+    name: "fromSession",
+    type: Number,
+};
 export const silentOption = {
     alias: "s",
     help: "don't log anything",
@@ -27,6 +33,7 @@ export const verboseOption = {
 export const commonOptions = [
     categoriesOption,
     dataDirDefaultOption,
+    fromSessionOption,
     silentOption,
     verboseOption,
 ];

package/lib/types/agenda.d.ts

@@ -0,0 +1,12 @@
+export interface AgendaEvent {
+    type: string | null;
+    heureDebut: string | null;
+    heureFin: string | null;
+    timeOriginal: string | null;
+    titre: string | null;
+    organe: string | null;
+    objet: string | null;
+    lieu: string | null;
+    url_dossier_senat: string | null;
+    url_video: string | null;
+}

package/lib/types/agenda.js

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

package/lib/types/sessions.d.ts

@@ -1,42 +1,5 @@
-export declare enum Session {
-    "2012-2013" = 2012,
-    "2013-2014" = 2013,
-    "2014-2015" = 2014,
-    "2015-2016" = 2015,
-    "2016-2017" = 2016,
-    "2017-2018" = 2017,
-    "2018-2019" = 2018,
-    "2019-2020" = 2019,
-    "2020-2021" = 2020,
-    "2021-2022" = 2021,
-    "2022-2023" = 2022,
-    "2023-2024" = 2023,
-    "2024-2025" = 2024,
-    "2025-2026" = 2025,
-    "2026-2027" = 2026,
-    "2027-2028" = 2027,
-    "2028-2029" = 2028,
-    "2029-2030" = 2029,
-    "2030-2031" = 2030,
-    "2031-2032" = 2031,
-    "2032-2033" = 2032,
-    "2033-2034" = 2033,
-    "2034-2035" = 2034,
-    "2035-2036" = 2035,
-    "2036-2037" = 2036,
-    "2037-2038" = 2037,
-    "2038-2039" = 2038,
-    "2039-2040" = 2039,
-    "2040-2041" = 2040,
-    "2041-2042" = 2041,
-    "2042-2043" = 2042,
-    "2043-2044" = 2043,
-    "2044-2045" = 2044,
-    "2045-2046" = 2045,
-    "2046-2047" = 2046,
-    "2047-2048" = 2047,
-    "2048-2049" = 2048,
-    "2049-2050" = 2049,
-    "2050-2051" = 2050,
-    "All" = 0
-}
+export declare const UNDEFINED_SESSION = 0;
+declare const sessions: readonly [0, 1958, 1959, 1960, 1961, 1962, 1963, 1964, 1965, 1966, 1967, 1968, 1969, 1970, 1971, 1972, 1973, 1974, 1975, 1976, 1977, 1978, 1979, 1980, 1981, 1982, 1983, 1984, 1985, 1986, 1987, 1988, 1989, 1990, 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024, 2025, 2026];
+export type Session = typeof sessions[number];
+export declare function getSessionsFromStart(startSession: Session): (0 | 1958 | 1959 | 1960 | 1961 | 1962 | 1963 | 1964 | 1965 | 1966 | 1967 | 1968 | 1969 | 1970 | 1971 | 1972 | 1973 | 1974 | 1975 | 1976 | 1977 | 1978 | 1979 | 1980 | 1981 | 1982 | 1983 | 1984 | 1985 | 1986 | 1987 | 1988 | 1989 | 1990 | 1991 | 1992 | 1993 | 1994 | 1995 | 1996 | 1997 | 1998 | 1999 | 2000 | 2001 | 2002 | 2003 | 2004 | 2005 | 2006 | 2007 | 2008 | 2009 | 2010 | 2011 | 2012 | 2013 | 2014 | 2015 | 2016 | 2017 | 2018 | 2019 | 2020 | 2021 | 2022 | 2023 | 2024 | 2025 | 2026)[];
+export {};

package/lib/types/sessions.js

@@ -1,43 +1,84 @@
-export var Session;
-(function (Session) {
-    Session[Session["2012-2013"] = 2012] = "2012-2013";
-    Session[Session["2013-2014"] = 2013] = "2013-2014";
-    Session[Session["2014-2015"] = 2014] = "2014-2015";
-    Session[Session["2015-2016"] = 2015] = "2015-2016";
-    Session[Session["2016-2017"] = 2016] = "2016-2017";
-    Session[Session["2017-2018"] = 2017] = "2017-2018";
-    Session[Session["2018-2019"] = 2018] = "2018-2019";
-    Session[Session["2019-2020"] = 2019] = "2019-2020";
-    Session[Session["2020-2021"] = 2020] = "2020-2021";
-    Session[Session["2021-2022"] = 2021] = "2021-2022";
-    Session[Session["2022-2023"] = 2022] = "2022-2023";
-    Session[Session["2023-2024"] = 2023] = "2023-2024";
-    Session[Session["2024-2025"] = 2024] = "2024-2025";
-    Session[Session["2025-2026"] = 2025] = "2025-2026";
-    Session[Session["2026-2027"] = 2026] = "2026-2027";
-    Session[Session["2027-2028"] = 2027] = "2027-2028";
-    Session[Session["2028-2029"] = 2028] = "2028-2029";
-    Session[Session["2029-2030"] = 2029] = "2029-2030";
-    Session[Session["2030-2031"] = 2030] = "2030-2031";
-    Session[Session["2031-2032"] = 2031] = "2031-2032";
-    Session[Session["2032-2033"] = 2032] = "2032-2033";
-    Session[Session["2033-2034"] = 2033] = "2033-2034";
-    Session[Session["2034-2035"] = 2034] = "2034-2035";
-    Session[Session["2035-2036"] = 2035] = "2035-2036";
-    Session[Session["2036-2037"] = 2036] = "2036-2037";
-    Session[Session["2037-2038"] = 2037] = "2037-2038";
-    Session[Session["2038-2039"] = 2038] = "2038-2039";
-    Session[Session["2039-2040"] = 2039] = "2039-2040";
-    Session[Session["2040-2041"] = 2040] = "2040-2041";
-    Session[Session["2041-2042"] = 2041] = "2041-2042";
-    Session[Session["2042-2043"] = 2042] = "2042-2043";
-    Session[Session["2043-2044"] = 2043] = "2043-2044";
-    Session[Session["2044-2045"] = 2044] = "2044-2045";
-    Session[Session["2045-2046"] = 2045] = "2045-2046";
-    Session[Session["2046-2047"] = 2046] = "2046-2047";
-    Session[Session["2047-2048"] = 2047] = "2047-2048";
-    Session[Session["2048-2049"] = 2048] = "2048-2049";
-    Session[Session["2049-2050"] = 2049] = "2049-2050";
-    Session[Session["2050-2051"] = 2050] = "2050-2051";
-    Session[Session["All"] = 0] = "All";
-})(Session || (Session = {}));
+export const UNDEFINED_SESSION = 0;
+const sessions = [
+    UNDEFINED_SESSION,
+    1958,
+    1959,
+    1960,
+    1961,
+    1962,
+    1963,
+    1964,
+    1965,
+    1966,
+    1967,
+    1968,
+    1969,
+    1970,
+    1971,
+    1972,
+    1973,
+    1974,
+    1975,
+    1976,
+    1977,
+    1978,
+    1979,
+    1980,
+    1981,
+    1982,
+    1983,
+    1984,
+    1985,
+    1986,
+    1987,
+    1988,
+    1989,
+    1990,
+    1991,
+    1992,
+    1993,
+    1994,
+    1995,
+    1996,
+    1997,
+    1998,
+    1999,
+    2000,
+    2001,
+    2002,
+    2003,
+    2004,
+    2005,
+    2006,
+    2007,
+    2008,
+    2009,
+    2010,
+    2011,
+    2012,
+    2013,
+    2014,
+    2015,
+    2016,
+    2017,
+    2018,
+    2019,
+    2020,
+    2021,
+    2022,
+    2023,
+    2024,
+    2025,
+    2026,
+    // TO COMPLETE EVERY YEAR :)
+];
+export function getSessionsFromStart(startSession) {
+    if (startSession === 0) {
+        return Array.from(sessions);
+    }
+    const sessionIndex = sessions.findIndex(session => startSession === session);
+    if (sessionIndex >= 0) {
+        return sessions.slice(sessionIndex);
+    }
+    return [];
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tricoteuses/senat",
-  "version": "1.4.1",
+  "version": "2.1.1",
   "description": "Handle French Sénat's open data",
   "keywords": [
     "France",
@@ -45,9 +45,10 @@
     "data:convert_data": "tsx src/scripts/convert_data.ts",
     "data:download": "bash -c 'npm run data:retrieve_open_data -- $@ && npm run data:convert_data -- $@' bash",
     "data:generate_schemas": "tsx src/scripts/retrieve_open_data.ts --schema",
+    "data:retrieve_agenda": "tsx src/scripts/retrieve_agenda.ts",
+    "data:retrieve_documents": "tsx src/scripts/retrieve_documents.ts",
     "data:retrieve_open_data": "tsx src/scripts/retrieve_open_data.ts --all",
     "data:retrieve_senateurs_photos": "tsx src/scripts/retrieve_senateurs_photos.ts --fetch",
-    "data:retrieve_documents": "tsx src/scripts/retrieve_documents.ts",
     "data:parse_textes_lois": "tsx src/scripts/parse_textes.ts",
     "prepare": "npm run build",
     "prepublishOnly": "npm run build",