@tricoteuses/senat 1.3.5 → 2.1.0

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
@@ -67,21 +70,19 @@ 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
 
 Once the data is downloaded, you can use loaders to retrieve it.
 To use loaders in your project, you can install the _@tricoteuses/senat_ package, and import the iterator functions that you need.
 
-_Only iterator for Questions, Sénateurs and Circonscriptions available for now_
-
 ```bash
 npm install @tricoteuses/senat
 ```
 
 ```js
-import { iterLoadSenatQuestions } from "@tricoteuses/senat/lib/loaders"
+import { iterLoadSenatQuestions } from "@tricoteuses/senat/loaders"
 
 // Pass data directory and legislature as arguments
 for (const { item: question } of iterLoadSenatQuestions("../senat-data", 17)) {

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

@@ -2,12 +2,9 @@ export type { AmendementResult, } from "./model/ameli";
 export type { DossierLegislatifResult, } from "./model/dosleg";
 export type { QuestionResult, } from "./model/questions";
 export type { CirconscriptionResult, OrganismeResult, SenateurResult, } from "./model/sens";
-export { sesFieldsToParseInt, sesFieldsToTrim, subFieldsToParseInt, subFieldsToTrim, txtAmeliFieldsToTrim, } from "./types/ameli";
 export type { Ses, Sub, TxtAmeli } from "./types/ameli";
-export { debatsFieldsToTrim, lecassdebFieldsToTrim } from "./types/debats";
 export type { Debat, LecAssDeb } from "./types/debats";
-export { assFieldsToTrim, audFieldsToTrim, auteurFieldsToTrim, dateSeanceFieldsToTrim, deccocFieldsToTrim, denrapFieldsToTrim, docattFieldsToParseInt, docattFieldsToTrim, ecrFieldsToTrim, etaloiFieldsToTrim, lecassFieldsToTrim, lecassrapFieldsToTrim, lectureFieldsToTrim, loiFieldsToTrim, orgFieldsToTrim, oritxtFieldsToTrim, quaFieldsToTrim, rapFieldsToParseInt, rapFieldsToTrim, raporgFieldsToTrim, scrFieldsToTrim, texteFieldsToParseInt, texteFieldsToTrim, typattFieldsToTrim, typlecFieldsToTrim, typloiFieldsToTrim, typtxtFieldsToTrim, typurlFieldsToTrim, } from "./types/dosleg";
 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 { Session } from "./types/sessions";
 export type { Alinea, Article, Division, DivisionTag, FlatTexte } from "./types/texte";

package/lib/index.js

@@ -1,4 +1 @@
-export { sesFieldsToParseInt, sesFieldsToTrim, subFieldsToParseInt, subFieldsToTrim, txtAmeliFieldsToTrim, } from "./types/ameli";
-export { debatsFieldsToTrim, lecassdebFieldsToTrim } from "./types/debats";
-export { assFieldsToTrim, audFieldsToTrim, auteurFieldsToTrim, dateSeanceFieldsToTrim, deccocFieldsToTrim, denrapFieldsToTrim, docattFieldsToParseInt, docattFieldsToTrim, ecrFieldsToTrim, etaloiFieldsToTrim, lecassFieldsToTrim, lecassrapFieldsToTrim, lectureFieldsToTrim, loiFieldsToTrim, orgFieldsToTrim, oritxtFieldsToTrim, quaFieldsToTrim, rapFieldsToParseInt, rapFieldsToTrim, raporgFieldsToTrim, scrFieldsToTrim, texteFieldsToParseInt, texteFieldsToTrim, typattFieldsToTrim, typlecFieldsToTrim, typloiFieldsToTrim, typtxtFieldsToTrim, typurlFieldsToTrim, } from "./types/dosleg";
-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/ameli.d.ts

@@ -49,7 +49,7 @@ declare const findAllQuery: import("kysely").SelectQueryBuilder<{
     date_depot: string;
     dispositif: string | null;
     objet: string | null;
-    etat_id: number;
+    etat: string;
     avis_commission: string | null;
     avis_gouvernement: string | null;
     sort: string | null;
@@ -86,7 +86,7 @@ export declare function findAll(): AsyncIterableIterator<{
     date_depot: string;
     dispositif: string | null;
     objet: string | null;
-    etat_id: number;
+    etat: string;
     avis_commission: string | null;
     avis_gouvernement: string | null;
     sort: string | null;

package/lib/model/ameli.js

@@ -43,7 +43,7 @@ const findAllQuery = dbAmeli
         .then(val("Motion"))
         .when("amd.typ", "=", "S")
         .then(val("Sous-amendement"))
-        .else("'")
+        .else("")
         .end()
         .as("nature"),
     "amd.id as id",
@@ -56,15 +56,23 @@ const findAllQuery = dbAmeli
     "typsub.lib as subdivision_type",
     "amd.alinea as alinea",
     toDateString(ref("amd.datdep")).as("date_depot"),
+    "amd.dis as dispositif",
+    "amd.obj as objet",
     eb
         .case()
+        .when("amd.etaid", "=", 7)
+        .then(val("Diffusé"))
         .when("amd.etaid", "=", 8)
-        .then(val("Cet amendement a été retiré avant séance."))
-        .else(ref("amd.dis"))
+        .then(val("Retiré avant réunion ou séance"))
+        .when("amd.etaid", "=", 9)
+        .then(val("Examiné en commission ou séance"))
+        .when("amd.etaid", "=", 10)
+        .then(val("Irrecevable"))
+        .when("amd.etaid", "=", 11)
+        .then(val("Irrecevable"))
+        .else("")
         .end()
-        .as("dispositif"),
-    "amd.obj as objet",
-    "amd.etaid as etat_id",
+        .as("etat"),
     "avicom.lib as avis_commission",
     "avigvt.lib as avis_gouvernement",
     eb.fn.coalesce("sor.lib", "irr.libirr").as("sort"),

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;