@tricoteuses/senat 3.0.1 → 3.1.0

package/lib/src/scrutins.d.ts

@@ -0,0 +1,47 @@
+export interface VoteScrutinRow {
+    groupe_politique_code: string | null;
+    groupe_politique_id: string | null;
+    matricule_delegant: string | null;
+    matricule_votant: string;
+    position: string | null;
+    statut_votant: string | null;
+    titre_votant: string | null;
+}
+export interface GroupeVotantRow {
+    groupe_politique_code: string | null;
+    nombre_abstentions: string;
+    nombre_contre: string;
+    nombre_non_votants: string;
+    nombre_pour: string;
+    nombre_votants: string;
+}
+export interface MiseAuPointRow {
+    ordre: string | null;
+    texte: string;
+    url: string | null;
+}
+export interface ScrutinResult {
+    date_scrutin: string | null;
+    date_scrutin_effective: string | null;
+    groupes_votants: GroupeVotantRow[];
+    intitule: string | null;
+    lecture_id: string | null;
+    lecture_libelle: string | null;
+    mises_au_point: MiseAuPointRow[];
+    nombre_contre: string | null;
+    nombre_contre_seance: string | null;
+    nombre_majorite: string | null;
+    nombre_majorite_seance: string | null;
+    nombre_pour: string | null;
+    nombre_pour_seance: string | null;
+    nombre_suffrages: string | null;
+    nombre_suffrages_seance: string | null;
+    nombre_votants: string | null;
+    nombre_votants_seance: string | null;
+    note: string | null;
+    numero: string;
+    session: string;
+    signet_dossier: string | null;
+    type_lecture: string | null;
+    votes: VoteScrutinRow[];
+}

package/lib/src/scrutins.js

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

package/lib/src/sens.d.ts

@@ -0,0 +1,104 @@
+export interface FonctionRow {
+    date_debut: string | null;
+    date_fin: string | null;
+    libelle: string | null;
+}
+export interface MandatSenateurRow {
+    code_circonscription: string | null;
+    date_debut: string | null;
+    date_fin: string | null;
+    etat: string | null;
+    etat_debut: string | null;
+    etat_fin: string | null;
+}
+export interface MandatOrganismeRow {
+    code_organisme: string;
+    date_debut: string | null;
+    date_fin: string | null;
+    etat: string | null;
+    fonctions: FonctionRow[];
+    libelle: string | null;
+    type_code_organisme: string | null;
+    type_organisme: string | null;
+}
+export interface AdressePointContactRow {
+    bureau_distributeur: string | null;
+    code_cedex: string | null;
+    code_postal: string | null;
+    commune: string | null;
+    complement: string | null;
+    complement2: string | null;
+    libelle_cedex: string | null;
+    nom_voie: string | null;
+    numero_voie: string | null;
+}
+export interface TelephonePointContactRow {
+    numero: string | null;
+    type: string;
+}
+export interface PointContactRow {
+    adresses: AdressePointContactRow[];
+    id: string;
+    libelle: string | null;
+    telephones: TelephonePointContactRow[];
+    type: string;
+}
+export interface UrlRow {
+    code_url: string;
+    url: string;
+}
+export interface SenateurResult {
+    PCS_INSEE: string | null;
+    PCS_INSEE_24: string | null;
+    PCS_INSEE_42: string | null;
+    PCS_INSEE_8: string | null;
+    circonscription: string | null;
+    code_circonscription: string | null;
+    code_commission_permanente: string | null;
+    code_groupe_politique: string | null;
+    commission_permanente: string | null;
+    commissions: MandatOrganismeRow[];
+    courrier_electronique: string | null;
+    date_deces: string | null;
+    date_naissance: string | null;
+    delegations: MandatOrganismeRow[];
+    description_profession: string | null;
+    etat: string;
+    fonction_bureau_senat: string | null;
+    fonctions_bureau: FonctionRow[];
+    groupe_politique: string | null;
+    groupes: MandatOrganismeRow[];
+    mandats_senateur: MandatSenateurRow[];
+    matricule: string;
+    nom_usuel: string | null;
+    points_contact: PointContactRow[];
+    prenom_usuel: string;
+    qualite: string;
+    siege: string | null;
+    url_hatvp: string | null;
+    urls: UrlRow[];
+}
+export interface CirconscriptionResult {
+    article: string | null;
+    code: string;
+    date_debut: string | null;
+    date_fin: string | null;
+    etat: string | null;
+    identifiant: string;
+    libelle_departement: string;
+    libelle_region: string;
+    nombre_senateurs: string | null;
+    url: string | null;
+}
+export interface OrganismeResult {
+    code: string;
+    date_debut: string | null;
+    date_fin: string | null;
+    etat: string | null;
+    libelle: string | null;
+    libelle_court: string | null;
+    libelle_long: string | null;
+    type_code: string;
+    type_libelle: string | null;
+    url: string | null;
+}

package/lib/src/sens.js

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

package/lib/src/server/agenda.d.ts

@@ -0,0 +1,6 @@
+import { AgendaEvent } from "../other_types/agenda.js";
+export declare function getStartAndEndTimes(timeStr: string | null | undefined, dateISO: string): {
+    startTime: string | null;
+    endTime: string | null;
+};
+export declare function parseAgendaFromFile(htmlFilePath: string): Promise<AgendaEvent[] | null>;

package/lib/src/server/agenda.js

@@ -0,0 +1,148 @@
+import { JSDOM } from "jsdom";
+import { DateTime } from "luxon";
+import path from "path";
+import { ID_DATE_FORMAT, STANDARD_DATE_FORMAT } from "../scripts/datautil.js";
+const FR_TZ = "Europe/Paris";
+function eventIsSeance(eventElement) {
+    return eventElement.classList.contains("evt-seance");
+}
+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 getQuantieme(eventElement, seancesElements) {
+    const seanceIndex = seancesElements.indexOf(eventElement);
+    if (seancesElements.length === 1 && seanceIndex === 0) {
+        return "Unique";
+    }
+    else {
+        switch (seanceIndex) {
+            case 0:
+                return "Première";
+            case 1:
+                return "Deuxième";
+            case 2:
+                return "Troisième";
+            case 3:
+                return "Quatrième";
+            case 4:
+                return "Cinquième";
+        }
+    }
+    return "Non défini";
+}
+/**
+ * Normalize time string to become a simple start time ("H'h'mm") or a duration ("'de 'H'h'mm' à 'H'h'mm").
+ */
+function normalizeTime(timeStr) {
+    return timeStr
+        ?.replace(/^À l'issue de l'espace réservé .* et au plus tard\s/i, "") // Must be processed first
+        ?.replace(/^(?:le )?matin/i, "10h00") // We chose "matin" to mean 10h00
+        ?.replace(/^(?:l')?après-midi/i, "16h00") // We chose "après-midi" to mean 16h00
+        ?.replace(/^(?:le )?soir/i, "20h00") // We chose "soir" to mean 20h00
+        ?.replace(/^(?:la )?nuit/i, "22h00") // We chose "nuit" to mean 22h00
+        ?.replace(/^à\s/gi, "")
+        ?.replace(/heures/gi, "h00")
+        ?.replace(/\set.*/i, "")
+        ?.replace(/,.*/, "")
+        ?.replace(/\s\(hors hémicycle\)/i, "")
+        ?.replace(/\s*h\s*/gi, "h");
+}
+export function getStartAndEndTimes(timeStr, dateISO) {
+    const normalizedTime = normalizeTime(timeStr);
+    if (!normalizedTime) {
+        return { startTime: null, endTime: null };
+    }
+    const rangeMatch = normalizedTime.match(/^de (?<start>\d{1,2}h\d{2}) à (?<end>\d{1,2}h\d{2})$/i);
+    const toUtcTimeOnly = (value) => {
+        if (!value)
+            return null;
+        const time = DateTime.fromFormat(value, "H'h'mm", { zone: FR_TZ });
+        if (!time.isValid)
+            return null;
+        const local = DateTime.fromISO(dateISO, { zone: FR_TZ }).set({
+            hour: time.hour,
+            minute: time.minute,
+            second: 0,
+            millisecond: 0,
+        });
+        if (!local.isValid)
+            return null;
+        return local.toUTC().toFormat("HH:mm:ss.SSS'Z'");
+    };
+    if (rangeMatch?.groups) {
+        const { start, end } = rangeMatch.groups;
+        return {
+            startTime: toUtcTimeOnly(start),
+            endTime: toUtcTimeOnly(end),
+        };
+    }
+    return {
+        startTime: toUtcTimeOnly(normalizedTime),
+        endTime: null,
+    };
+}
+function transformAgenda(document, fileName) {
+    const agendaEvents = [];
+    const eventElements = document.querySelectorAll(".evt");
+    const seanceElements = Array.from(eventElements).filter((eventElement) => eventIsSeance(eventElement));
+    for (const eventElement of eventElements) {
+        const id = eventElement.previousElementSibling?.getAttribute("name") || null;
+        if (!id) {
+            continue;
+        }
+        const type = getEventType(eventElement.classList);
+        const date = DateTime.fromFormat(fileName, ID_DATE_FORMAT).toFormat(STANDARD_DATE_FORMAT);
+        const timeOriginal = eventElement.querySelector(".time")?.textContent || null;
+        const { startTime, endTime } = getStartAndEndTimes(timeOriginal, date);
+        const titre = eventElement.querySelector(".titre")?.textContent?.trim() || "";
+        const organe = eventElement.querySelector(".organe")?.textContent?.trim() || null;
+        const objet = eventElement.querySelector(".objet")?.textContent?.trim()?.replace(/^- /, "") || null;
+        const lieu = eventElement.querySelector(".lieu")?.textContent || null;
+        const videoElement = eventElement.querySelector(".video");
+        const urlDossierSenat = getUrlDossierSenat(eventElement.querySelectorAll(".lien a"));
+        agendaEvents.push({
+            id,
+            type,
+            date,
+            startTime,
+            endTime,
+            timeOriginal,
+            titre,
+            organe,
+            objet,
+            lieu,
+            captationVideo: videoElement !== null,
+            urlDossierSenat: urlDossierSenat,
+            quantieme: eventIsSeance(eventElement) ? getQuantieme(eventElement, seanceElements) : null,
+        });
+    }
+    return agendaEvents;
+}
+export async function parseAgendaFromFile(htmlFilePath) {
+    try {
+        const { document } = (await JSDOM.fromFile(htmlFilePath, { contentType: "text/html" })).window;
+        const fileName = path.parse(htmlFilePath).name;
+        return transformAgenda(document, fileName);
+    }
+    catch (error) {
+        console.error(`Could not parse texte with error ${error.message}`);
+    }
+    return null;
+}

package/lib/src/server/ameli.d.ts

@@ -0,0 +1,2 @@
+import type { AmendementResult } from "../rich_types/ameli.js";
+export declare function findAllAmendements(fromSession?: number): AsyncGenerator<AmendementResult, void, unknown>;

package/lib/src/server/ameli.js

@@ -0,0 +1,153 @@
+import { sql } from "kysely";
+import { jsonArrayFrom } from "kysely/helpers/postgres";
+import { db, streamRawQuery } from "./databases_postgres.js";
+export async function* findAllAmendements(fromSession) {
+    const baseQuery = db
+        .withSchema("senat")
+        .selectFrom("ameli_amd as amd")
+        .leftJoin("ameli_sub as sub", "sub.id", "amd.subid")
+        .leftJoin("ameli_typsub as typsub", "typsub.id", "sub.typid")
+        .leftJoin("ameli_typrect as typrect", "typrect.id", "amd.typrectid")
+        .leftJoin("ameli_txt_ameli as txt_ameli", "txt_ameli.id", "amd.txtid")
+        .leftJoin("ameli_etatxt as etatxt", "etatxt.id", "txt_ameli.txtetaid")
+        .leftJoin("ameli_ses as ses", "ses.id", "txt_ameli.sesdepid")
+        .leftJoin("ameli_typses as typses", "typses.id", "ses.typid")
+        .leftJoin("ameli_nat as nat", "nat.id", "txt_ameli.natid")
+        .leftJoin("ameli_lec_ameli as lec_ameli", "lec_ameli.id", "txt_ameli.lecid")
+        .leftJoin("dosleg_texte as texte", (join) => join.onRef("ses.ann", "=", "texte.sesann").onRef("txt_ameli.numabs", "=", "texte.texnum"))
+        .leftJoin("dosleg_lecass as lecass", "lecass.lecassidt", "texte.lecassidt")
+        .leftJoin("ameli_mot as mot", "mot.id", "amd.motid")
+        .leftJoin("ameli_avicom as avicom", "avicom.id", "amd.avcid")
+        .leftJoin("ameli_avigvt as avigvt", "avigvt.id", "amd.avgid")
+        .leftJoin("ameli_sor as sor", "sor.id", "amd.sorid")
+        .leftJoin("ameli_irr as irr", "irr.id", "amd.irrid")
+        .leftJoin("ameli_grppol_ameli as grppol_ameli", "grppol_ameli.entid", "amd.nomentid")
+        .leftJoin("ameli_com_ameli as com_ameli", "com_ameli.entid", "amd.nomentid")
+        .leftJoin("ameli_cab as cab", "cab.entid", "amd.nomentid")
+        .select((eb) => [
+        sql `${eb.ref("ses.ann")}::text`.as("session"),
+        "ses.lil as session_libelle",
+        "typses.lib as type_session",
+        "txt_ameli.doslegsignet as signet_dossier_legislatif",
+        "nat.libcourt as nature_texte",
+        "nat.lib as nature_texte_libelle",
+        "txt_ameli.numabs as numero_texte",
+        "txt_ameli.numado as numero_adoption_texte",
+        "txt_ameli.int as intitule_texte",
+        "etatxt.lic as etat_texte",
+        "etatxt.lib as etat_texte_libelle",
+        "etatxt.txttyp as type_texte",
+        "lec_ameli.lib as lecture",
+        eb
+            .case()
+            .when("amd.typ", "=", "A")
+            .then("Amendement")
+            .when("amd.typ", "=", "M")
+            .then("Motion")
+            .when("amd.typ", "=", "S")
+            .then("Sous-amendement")
+            .else("")
+            .end()
+            .as("nature"),
+        "amd.id",
+        "amd.amdperid as parent_id",
+        "amd.ideid as identique_id",
+        "amd.discomid as discussion_commune_id",
+        sql `${eb.ref("amd.num")}`.as("numero"),
+        "amd.numabs as numero_absolu",
+        "amd.ord as ordre",
+        "amd.accgou as accepte_gouvernement",
+        "amd.txtid as texte_id",
+        "sub.lib as subdivision_libelle",
+        "sub.lic as subdivision_libelle_court",
+        "sub.pos as subdivision_position_texte",
+        "sub.posder as subdivision_position_discussion",
+        "sub.merid as subdivision_mere_id",
+        "sub.sig as subdivision_signet",
+        "sub.comdelid as subdivision_commission_id",
+        "sub.dupl as subdivision_dupliquee",
+        "typsub.lib as subdivision_type",
+        "amd.alinea",
+        "amd.obs as observations",
+        "amd.mot as observations_additionnelles",
+        sql `to_char(${eb.ref("amd.datdep")}, 'YYYY-MM-DD')`.as("date_depot"),
+        "amd.dis as dispositif",
+        "amd.obj as objet",
+        "typrect.lib as type_rectification",
+        "mot.lib as motion_libelle",
+        eb
+            .case()
+            .when("amd.etaid", "=", 7)
+            .then("Diffusé")
+            .when("amd.etaid", "=", 8)
+            .then("Retiré avant réunion ou séance")
+            .when("amd.etaid", "=", 9)
+            .then("Examiné en commission ou séance")
+            .when("amd.etaid", "=", 10)
+            .then("Irrecevable")
+            .when("amd.etaid", "=", 11)
+            .then("Irrecevable")
+            .else("")
+            .end()
+            .as("etat"),
+        "avicom.lib as avis_commission",
+        "avigvt.lib as avis_gouvernement",
+        eb.fn.coalesce("sor.lib", "irr.libirr").as("sort"),
+        "amd.rev as revision",
+        sql `
+        (
+          case
+            when ${eb.ref("amd.num")} like '%COM%' then 'https://www.senat.fr/amendements/commissions/'
+            else 'https://www.senat.fr/amendements/'
+          end ||
+          ${eb.ref("ses.ann")}::text || '-' ||
+          (${eb.ref("ses.ann")}::integer + 1)::text || '/' ||
+          ${eb.ref("txt_ameli.numabs")} || '/Amdt_' ||
+          ${eb.ref("amd.num")} || '.html'
+        )
+      `.as("url"),
+        "grppol_ameli.lilcou as au_nom_de_groupe_politique",
+        sql `rtrim(${eb.ref("com_ameli.lil")})`.as("au_nom_de_commission"),
+        sql `rtrim(${eb.ref("com_ameli.cod")})`.as("code_commission"),
+        sql `(${eb.ref("cab.entid")} is not null)`.as("auteur_est_gouvernement"),
+        // Sous-requête scalaire: numéro de scrutin
+        eb
+            .withSchema("senat")
+            .selectFrom("dosleg_amescr as amescr")
+            .leftJoin("dosleg_scr as scr", (join) => join.onRef("amescr.scrnum", "=", "scr.scrnum").onRef("amescr.sesann", "=", "scr.sesann"))
+            .leftJoin("dosleg_date_seance as date_seance", "date_seance.code", "scr.code")
+            .select(sql `amescr.scrnum::text`.as("scrnum"))
+            .whereRef("amescr.amescrnum", "=", "amd.num")
+            .whereRef("amescr.sesann", "=", "ses.ann")
+            .whereRef("date_seance.lecidt", "=", "texte.lecassidt")
+            .limit(1)
+            .as("scrutin_num"),
+        // Sous-requête pour les auteurs
+        jsonArrayFrom(eb
+            .withSchema("senat")
+            .selectFrom("ameli_amdsen as amdsen")
+            .leftJoin("ameli_sen_ameli as sen_ameli", "sen_ameli.entid", "amdsen.senid")
+            .leftJoin("ameli_grppol_ameli as grppol_ameli2", "grppol_ameli2.entid", "amdsen.grpid")
+            .select([
+            "amdsen.prenomuse as prenom",
+            "amdsen.hom as homonyme",
+            "amdsen.nomuse as nom",
+            "amdsen.qua as qualite",
+            sql `amdsen.rng::text`.as("rang"),
+            "sen_ameli.mat as matricule",
+            "amdsen.grpid as groupe_politique_id",
+            "grppol_ameli2.cod as group_politique_code",
+            "grppol_ameli2.libcou as groupe_politique_libelle_court",
+            "grppol_ameli2.lilcou as groupe_politique_libelle",
+        ])
+            .whereRef("amdsen.amdid", "=", "amd.id")
+            .orderBy("amdsen.rng", "asc")).as("auteurs"),
+    ]);
+    const compiledQuery = (fromSession === undefined ? baseQuery : baseQuery.where("ses.ann", ">=", String(fromSession))).compile();
+    for await (const row of streamRawQuery(compiledQuery)) {
+        yield {
+            ...row,
+            auteurs: row.auteurs ?? [],
+        };
+    }
+}

package/lib/src/server/commission.d.ts

@@ -0,0 +1,19 @@
+import * as cheerio from "cheerio";
+import type { AnyNode } from "domhandler";
+import { CompteRendu } from "../other_types/compte_rendu.js";
+import { Reunion } from "../other_types/agenda.js";
+export declare function getRemainingTextAfterSpeakerHeader($: cheerio.CheerioAPI, $p: cheerio.Cheerio<AnyNode>): string;
+export type DaySection = {
+    title: string;
+    $start: cheerio.Cheerio<AnyNode>;
+    time?: string;
+};
+export declare function cleanTitle(t: string): string;
+export declare function extractDayH3Sections($: cheerio.CheerioAPI, dateISO: string): DaySection[];
+export declare function parseCommissionCRSectionFromDom($: cheerio.CheerioAPI, htmlFilePath: string, opts: {
+    dateISO: string;
+    hourShort: string | null;
+    organe?: string | null;
+    section: DaySection;
+    matched?: Reunion;
+}): CompteRendu | null;