@tricoteuses/senat 2.22.5 → 2.22.7

package/lib/config.d.ts

@@ -1,10 +1,21 @@
 import "dotenv/config";
+import { z } from "zod";
+export declare const configSchema: z.ZodObject<{
+    db: z.ZodObject<{
+        host: z.ZodString;
+        name: z.ZodString;
+        password: z.ZodString;
+        port: z.ZodCoercedNumber<unknown>;
+        user: z.ZodString;
+    }, z.core.$strip>;
+}, z.core.$strip>;
 declare const _default: {
     db: {
         host: string;
+        name: string;
         password: string;
-        user: string;
         port: number;
+        user: string;
     };
 };
 export default _default;

package/lib/config.js

@@ -1,8 +1,19 @@
 import "dotenv/config";
-import { configSchema } from "./validators/config";
+import { z } from "zod";
+const dbSchema = z.object({
+    host: z.string().trim().min(1, "Must not be empty"),
+    name: z.string().trim().min(1, "Must not be empty"),
+    password: z.string().trim().min(1, "Must not be empty"),
+    port: z.coerce.number().int().min(0).max(65535),
+    user: z.string().trim().min(1, "Must not be empty"),
+});
+export const configSchema = z.object({
+    db: dbSchema,
+});
 const config = {
     db: {
         host: process.env["TRICOTEUSES_SENAT_DB_HOST"] || "localhost",
+        name: process.env["TRICOTEUSES_SENAT_DB_NAME"] || "postgres",
         password: process.env["TRICOTEUSES_SENAT_DB_PASSWORD"] || "opendata",
         port: process.env["TRICOTEUSES_SENAT_DB_PORT"] || 5432,
         user: process.env["TRICOTEUSES_SENAT_DB_USER"] || "opendata",

package/lib/loaders.js

@@ -193,7 +193,7 @@ export function* iterLoadSenatDocuments(dataDir, session, documentType, options
                         ...document,
                     };
                     const documentItem = {
-                        item: enrichedDocument
+                        item: enrichedDocument,
                     };
                     if (document.url) {
                         const documentName = path.parse(document.url).name;

package/lib/model/ameli.js

@@ -47,9 +47,7 @@ const findAllAmendementsQuery = dbSenat
     .leftJoin("ameli.typses", "ameli.typses.id", "ameli.ses.typid")
     .leftJoin("ameli.nat", "ameli.txt_ameli.natid", "ameli.nat.id")
     .leftJoin("ameli.lec_ameli", "ameli.txt_ameli.lecid", "ameli.lec_ameli.id")
-    .leftJoin("dosleg.texte", (join) => join
-    .onRef("ameli.ses.ann", "=", "dosleg.texte.sesann")
-    .onRef("ameli.txt_ameli.numabs", "=", "dosleg.texte.texnum"))
+    .leftJoin("dosleg.texte", (join) => join.onRef("ameli.ses.ann", "=", "dosleg.texte.sesann").onRef("ameli.txt_ameli.numabs", "=", "dosleg.texte.texnum"))
     .leftJoin("dosleg.lecass", "dosleg.texte.lecassidt", "dosleg.lecass.lecassidt")
     .leftJoin("ameli.mot", "ameli.amd.motid", "ameli.mot.id")
     .leftJoin("ameli.avicom", "ameli.amd.avcid", "ameli.avicom.id")

package/lib/model/documents.js

@@ -28,10 +28,7 @@ function documentsAttaches(rapportId) {
         .selectFrom("docatt")
         .leftJoin("typatt", "docatt.typattcod", "typatt.typattcod")
         .where("docatt.rapcod", "=", rapportId)
-        .select([
-        "docatt.docatturl as url",
-        "typatt.typattlib as type_document"
-    ]));
+        .select(["docatt.docatturl as url", "typatt.typattlib as type_document"]));
 }
 function selectRapportAttributes({ eb, ref, val }) {
     return [
@@ -70,14 +67,9 @@ const queryRapports = baseQueryRapports
     .leftJoin("lecass", "lecass.lecassidt", "lecassrap.lecassidt")
     .leftJoin("lecture", "lecture.lecidt", "lecass.lecidt")
     .leftJoin("loi", "loi.loicod", "lecture.loicod")
-    .select((args) => [
-    "loi.signet as signet_dossier",
-    ...selectRapportAttributes(args),
-]);
+    .select((args) => ["loi.signet as signet_dossier", ...selectRapportAttributes(args)]);
 export function rapports(lectureAssembleeId) {
-    return jsonArrayFrom(baseQueryRapports
-        .select(selectRapportAttributes)
-        .where("lecassrap.lecassidt", "=", lectureAssembleeId));
+    return jsonArrayFrom(baseQueryRapports.select(selectRapportAttributes).where("lecassrap.lecassidt", "=", lectureAssembleeId));
 }
 function auteursTexte(texteId) {
     return jsonArrayFrom(dbSenat
@@ -134,14 +126,9 @@ const queryTextes = baseQueryTextes
     .leftJoin("lecass", "lecass.lecassidt", "texte.lecassidt")
     .leftJoin("lecture", "lecture.lecidt", "lecass.lecidt")
     .leftJoin("loi", "loi.loicod", "lecture.loicod")
-    .select((args) => [
-    "loi.signet as signet_dossier",
-    ...selectTexteAttributes(args),
-]);
+    .select((args) => ["loi.signet as signet_dossier", ...selectTexteAttributes(args)]);
 export function textes(lectureAssembleeId) {
-    return jsonArrayFrom(baseQueryTextes
-        .select(selectTexteAttributes)
-        .where("texte.lecassidt", "=", lectureAssembleeId));
+    return jsonArrayFrom(baseQueryTextes.select(selectTexteAttributes).where("texte.lecassidt", "=", lectureAssembleeId));
 }
 export function findAllTextes() {
     return queryTextes.stream();

package/lib/model/dosleg.js

@@ -203,10 +203,10 @@ export function buildActesLegislatifs(dossier) {
                     numero: depotTexte.numero,
                     uid: `${loiSignet}-${phasePrefix}-DEPOT`,
                     session: lecAss.session,
-                    chambre: 'SN',
+                    chambre: "SN",
                     signet_dossier: loiSignet,
                     texte_url: depotTexte.url,
-                    code_organisme: null
+                    code_organisme: null,
                 });
             }
             // =================================================================
@@ -225,7 +225,7 @@ export function buildActesLegislatifs(dossier) {
                         adoption: rap.adoption,
                         uid: `${loiSignet}-${phasePrefix}-COM`,
                         session: lecAss.session,
-                        chambre: 'SN',
+                        chambre: "SN",
                         signet_dossier: loiSignet,
                         texte_url: rap.url,
                     });
@@ -247,9 +247,9 @@ export function buildActesLegislatifs(dossier) {
                         libelle: `Discussion en séance publique`,
                         uid: `${loiSignet}-${phasePrefix}-DEBATS-SEANCE`,
                         session: lecAss.session,
-                        chambre: 'SN',
+                        chambre: "SN",
                         signet_dossier: loiSignet,
-                        code_organisme: null
+                        code_organisme: null,
                     });
                 }
             }
@@ -281,10 +281,10 @@ export function buildActesLegislatifs(dossier) {
                     adoption: libelleStatut,
                     uid: `${loiSignet}-DEC-${texteFinal.numero}`,
                     session: lecAss.session,
-                    chambre: 'SN',
+                    chambre: "SN",
                     signet_dossier: loiSignet,
                     texte_url: texteFinal.url,
-                    code_organisme: null
+                    code_organisme: null,
                 });
             }
         }
@@ -294,19 +294,19 @@ export function buildActesLegislatifs(dossier) {
     // =================================================================
     if (dossier.date_decision_CoC) {
         actes.push({
-            code_acte: 'CC',
+            code_acte: "CC",
             date: dossier.date_decision_CoC,
             libelle: `Décision du Conseil constitutionnel`,
             id: dossier.url_decision_CoC,
             uid: `${loiSignet}-CC`,
-            chambre: 'AN',
+            chambre: "AN",
             signet_dossier: loiSignet,
             texte_url: dossier.url_decision_CoC || dossier.url_dossier_CoC,
         });
     }
     if (dossier.date_promulgation) {
         actes.push({
-            code_acte: 'PROM',
+            code_acte: "PROM",
             date: dossier.date_promulgation,
             libelle: `Promulgation de la loi`,
             date_publication_JO: dossier.date_publication_JO,
@@ -314,7 +314,7 @@ export function buildActesLegislatifs(dossier) {
             url_legifrance: dossier.url_JO,
             id: dossier.url_JO,
             uid: `${loiSignet}-PROM`,
-            chambre: 'AN',
+            chambre: "AN",
             signet_dossier: loiSignet,
         });
     }

package/lib/model/texte.js

@@ -9,15 +9,11 @@ function buildWorklow(metaElement) {
         const identificationParts = AKN_WORKFLOW_IDENTIFICATION_STRUCTURE_REGEXP.exec(identification)?.groups;
         steps.push({
             eId: stepElement.getAttribute("eId"),
-            date: stepElement.getAttribute("date")
-                ? new Date(stepElement.getAttribute("date") ?? "")
-                : null,
+            date: stepElement.getAttribute("date") ? new Date(stepElement.getAttribute("date") ?? "") : null,
             type: identificationParts?.["type"] || null,
             session: identificationParts?.["session"] || null,
             numero: identificationParts?.["numTexte"] || null,
-            version: identificationParts?.["version"]
-                ? identificationParts["version"]
-                : null,
+            version: identificationParts?.["version"] ? identificationParts["version"] : null,
             outcome: stepElement.getAttribute("outcome"),
         });
     }
@@ -131,48 +127,26 @@ function flattenTexte(texteContentRoot) {
 export function transformTexte(document) {
     const metaElement = document.querySelector("meta");
     const preambleElement = document.querySelector("preamble");
-    const identification = metaElement
-        ?.querySelector("FRBRExpression FRBRuri")
-        ?.getAttribute("value") ?? "";
+    const identification = metaElement?.querySelector("FRBRExpression FRBRuri")?.getAttribute("value") ?? "";
     const identificationParts = AKN_IDENTIFICATION_STRUCTURE_REGEXP.exec(identification)?.groups;
     const bodyElement = document.querySelector("body");
     const sessionYears = identificationParts?.["session"]?.split("-") || null;
-    const datePresentation = metaElement
-        ?.querySelector("FRBRdate[name='#presentation']")
-        ?.getAttribute("date");
-    const dateDepot = metaElement
-        ?.querySelector("FRBRdate[name='#depot']")
-        ?.getAttribute("date");
-    const datePublicationXml = metaElement
-        ?.querySelector("FRBRdate[name='#publication-xml']")
-        ?.getAttribute("date");
+    const datePresentation = metaElement?.querySelector("FRBRdate[name='#presentation']")?.getAttribute("date");
+    const dateDepot = metaElement?.querySelector("FRBRdate[name='#depot']")?.getAttribute("date");
+    const datePublicationXml = metaElement?.querySelector("FRBRdate[name='#publication-xml']")?.getAttribute("date");
     return {
         titre: preambleElement?.querySelector("docTitle")?.textContent || null,
-        titreCourt: metaElement
-            ?.querySelector("FRBRalias[name='intitule-court']")
-            ?.getAttribute("value") || null,
-        signetDossier: metaElement
-            ?.querySelector("FRBRalias[name='signet-dossier-legislatif-senat']")
-            ?.getAttribute("value") || null,
-        urlDossierSenat: metaElement
-            ?.querySelector("FRBRalias[name='url-senat']")
-            ?.getAttribute("value") || null,
-        urlDossierAssemblee: metaElement
-            ?.querySelector("FRBRalias[name='url-AN']")
-            ?.getAttribute("value") || null,
+        titreCourt: metaElement?.querySelector("FRBRalias[name='intitule-court']")?.getAttribute("value") || null,
+        signetDossier: metaElement?.querySelector("FRBRalias[name='signet-dossier-legislatif-senat']")?.getAttribute("value") || null,
+        urlDossierSenat: metaElement?.querySelector("FRBRalias[name='url-senat']")?.getAttribute("value") || null,
+        urlDossierAssemblee: metaElement?.querySelector("FRBRalias[name='url-AN']")?.getAttribute("value") || null,
         type: identificationParts?.["type"] || null,
         session: sessionYears && sessionYears.length > 0 ? sessionYears[0] : null,
-        numero: identificationParts?.["numTexte"]
-            ? parseInt(identificationParts["numTexte"])
-            : null,
+        numero: identificationParts?.["numTexte"] ? parseInt(identificationParts["numTexte"]) : null,
         datePresentation: datePresentation ? new Date(datePresentation) : null,
         dateDepot: dateDepot ? new Date(dateDepot) : null,
-        datePublicationXml: datePublicationXml
-            ? new Date(datePublicationXml)
-            : null,
-        version: identificationParts?.["version"]
-            ? identificationParts["version"]
-            : null,
+        datePublicationXml: datePublicationXml ? new Date(datePublicationXml) : null,
+        version: identificationParts?.["version"] ? identificationParts["version"] : null,
         workflow: metaElement ? buildWorklow(metaElement) : [],
         divisions: bodyElement ? flattenTexte(bodyElement) : [],
     };
@@ -188,10 +162,8 @@ export function transformExposeDesMotifs(document) {
         }
         const firstParagraphContent = firstParagraph.textContent;
         const secondParagraphContent = secondParagraph?.textContent;
-        if (!firstParagraphContent ||
-            !exposeDesMotifsRegexp.test(firstParagraphContent.toUpperCase())) {
-            if (!secondParagraphContent ||
-                !exposeDesMotifsRegexp.test(secondParagraphContent.toUpperCase())) {
+        if (!firstParagraphContent || !exposeDesMotifsRegexp.test(firstParagraphContent.toUpperCase())) {
+            if (!secondParagraphContent || !exposeDesMotifsRegexp.test(secondParagraphContent.toUpperCase())) {
                 continue;
             }
             else {

package/lib/raw_types/questions.d.ts

@@ -113,6 +113,10 @@ export interface TamMinisteres {
     titreministre: string | null;
 }
 export interface TamQuestions {
+    /**
+     * Question caduque redéposée
+     */
+    caduque_redeposee: string | null;
     /**
      * Libellé de la circonscription
      */

package/lib/raw_types/senat.d.ts

@@ -2735,6 +2735,10 @@ export interface QuestionsTamMinisteres {
     titreministre: string | null;
 }
 export interface QuestionsTamQuestions {
+    /**
+     * Question caduque redéposée
+     */
+    caduque_redeposee: string | null;
     /**
      * Libellé de la circonscription
      */

package/lib/raw_types_schemats/ameli.d.ts

@@ -1,7 +1,7 @@
 /**
  * AUTO-GENERATED FILE - DO NOT EDIT!
  *
- * This file was automatically generated by schemats v.2.19.6
+ * This file was automatically generated by schemats v.2.20.33
  * $ schemats generate -c postgres://username:password@localhost:5432/senat -t amd -t amdsen -t avicom -t avigvt -t cab -t com_ameli -t ent -t etatxt -t fbu -t grppol_ameli -t gvt -t intora -t irr -t lec_ameli -t mot -t nat -t orarol -t sai -t saisen -t sea -t sen_ameli -t ses -t sor -t sub -t txt_ameli -t typrect -t typses -t typsub -t w_nivrec -s ameli
  *
  */

package/lib/raw_types_schemats/debats.d.ts

@@ -1,7 +1,7 @@
 /**
  * AUTO-GENERATED FILE - DO NOT EDIT!
  *
- * This file was automatically generated by schemats v.2.19.6
+ * This file was automatically generated by schemats v.2.20.33
  * $ schemats generate -c postgres://username:password@localhost:5432/senat -t debats -t intdivers -t intpjl -t lecassdeb -t secdis -t secdivers -t syndeb -t typsec -s debats
  *
  */

package/lib/raw_types_schemats/dosleg.d.ts

@@ -1,7 +1,7 @@
 /**
  * AUTO-GENERATED FILE - DO NOT EDIT!
  *
- * This file was automatically generated by schemats v.2.19.6
+ * This file was automatically generated by schemats v.2.20.33
  * $ schemats generate -c postgres://username:password@localhost:5432/senat -t amescr -t ass -t aud -t auteur -t ble -t catrap -t corscr -t date_seance -t deccoc -t denrap -t doc -t docatt -t docsea -t ecr -t etaloi -t evtsea -t forpub -t gen -t lecass -t lecassrap -t lecture -t lnkrap -t loi -t loithe -t natloi -t org -t orgnomhis -t orippr -t oritxt -t posvot -t qua -t rap -t raporg -t rapthe -t rolsig -t scr -t ses -t stavot -t texte -t texte_ancien -t the -t titsen -t typatt -t typaut -t typdoc -t typevtsea -t typlec -t typloi -t typorg -t typrap -t typtxt -t typurl -t votsen -s dosleg
  *
  */

package/lib/raw_types_schemats/questions.d.ts

@@ -1,7 +1,7 @@
 /**
  * AUTO-GENERATED FILE - DO NOT EDIT!
  *
- * This file was automatically generated by schemats v.2.19.6
+ * This file was automatically generated by schemats v.2.20.33
  * $ schemats generate -c postgres://username:password@localhost:5432/senat -t etatquestion -t legquestion -t naturequestion -t sortquestion -t tam_ministeres -t tam_questions -t tam_reponses -t the -s questions
  *
  */
@@ -76,6 +76,7 @@ export interface tam_ministeres {
     titreministre: tam_ministeresFields.titreministre;
 }
 export declare namespace tam_questionsFields {
+    type caduque_redeposee = string | null;
     type circonscription = string | null;
     type cirnum = number | null;
     type codequalite = string | null;
@@ -135,6 +136,7 @@ export declare namespace tam_questionsFields {
     type version = number | null;
 }
 export interface tam_questions {
+    caduque_redeposee: tam_questionsFields.caduque_redeposee;
     circonscription: tam_questionsFields.circonscription;
     cirnum: tam_questionsFields.cirnum;
     codequalite: tam_questionsFields.codequalite;

package/lib/raw_types_schemats/sens.d.ts

@@ -1,7 +1,7 @@
 /**
  * AUTO-GENERATED FILE - DO NOT EDIT!
  *
- * This file was automatically generated by schemats v.2.19.6
+ * This file was automatically generated by schemats v.2.20.33
  * $ schemats generate -c postgres://username:password@localhost:5432/senat -t acr -t activite -t activite_audit -t activite_delegation -t activite_delegation_audit -t activite_loi -t activite_loi_audit -t activite_obligatoire -t activite_participant -t activite_participant_audit -t activite_senateur -t activite_senateur_audit -t activite_senateur_params -t activite_senateur_params_audit -t activites_liees -t activites_liees_audit -t actpro -t adhgrpsen -t adr -t adresse -t adrsen -t app -t assparint -t asster -t autgrpsen -t autorisation_profil -t autorisations -t avis_nomination_art13 -t basdes -t bur -t bur3r -t bur4r -t cad -t candid -t candidat -t candtodelete -t categorie_activite -t catpro -t catpro2e -t catterrit -t cible_categorie_periode -t cirdep -t com -t con -t cotgip -t csp -t cspfam -t databasechangelog -t databasechangeloglock -t delega -t derogation -t derogation_audit -t derogation_senateur -t derogation_senateur_audit -t design -t designoep -t designorg -t discou -t div -t dpt -t dpt_seuil_presence -t dptele -t dptele_files -t dptele_processing -t dptele_processing_type -t dpttypman -t droits_acces -t droits_acces_audit -t droits_type_derogation -t ele -t eleloc -t elucan -t eludep -t eludiv -t elueur -t elueur_apf -t elumet -t elureg -t elusen -t elusen2e -t elusen3r -t elusen4r -t elusencommu -t elusenpair -t eluter -t elutit -t eluvil -t etadebman -t etadebman3r -t etadebman4r -t etafinman -t etafinman3r -t etafinman4r -t etaprr -t etarpm -t etasen -t ext2e_bio -t ext2e_csp -t ext2e_mandats -t ext2e_minist -t extsencom_identite -t extsencom_mandat -t fonact_participant -t foncandid -t foncom -t fondelega -t fongrppol -t fongrpsen -t fonmemcom -t fonmemdelega -t fonmemextpar -t fonmemgrppol -t fonmemgrpsen -t fonmemorg -t fonorg -t grppol -t grppol4r -t grpsenami -t grpsenamiadh -t grpsenamiadhreq -t grpsenamiadhreqeta -t grpsenamiunadh -t grpsim -t gvt -t insee_pays2008 -t jhi_authority -t jhi_user -t jhi_user_authority -t lanetr -t libcom -t libdelega -t libgrppol -t libgrpsen -t liborg -t lisdptele -t mel -t memcom -t memcomsea -t memdelega -t memextpar -t memgrppol -t memgrpsen -t memorg -t met -t minind -t minist -t mis -t misetafin -t mismin -t misrapeta -t missen -t moddes -t mode_acces_elusenpair -t nation -t nationgrpsen -t nivlan -t org -t orgext -t orgextpres -t orgthe -t pairie_elusenpair -t parpol -t parpolglo -t participa -t pcs -t pcs24 -t pcs42 -t pcs8 -t pcscatpro -t per -t per_sen -t perapp -t periode_presence -t perpolglo -t perrol -t pj_justificatif -t pj_justificatif_audit -t plaind -t plan_table -t plsql_profiler_runs -t plsql_profiler_units -t poicon -t posvot -t presences_scrutin_surcharge -t presencesrevisionentity -t profil_applicatif -t qua -t rap_the -t reg -t reladr -t requetes_profil -t reslis -t resultat -t reu -t revchanges -t rne_mandat -t rne_mandat_diff -t rne_sen -t rne_sen_diff -t rne_type_mandat -t rol -t sal -t scr -t scrusoldelega -t sea -t sec -t sec2e -t secexe -t sen -t senbur -t senbur3r -t senbur4r -t sennom -t senpj -t sensim -t sentablenom -t senurl -t seuil_presence -t sirpas_elusen -t sirpas_fonmemcom -t sirpas_fonmemdelega -t sirpas_fonmemgrppol -t sirpas_memcom -t sirpas_memdelega -t sirpas_memgrppol -t sirpas_mvt -t sirpas_mvtcm -t sirpas_mvttri -t sirpas_sen -t sirpas_senbur -t sirpas_trf -t srv -t stajur -t stavot -t suspensiontravaux -t suspensiontravaux_audit -t sysage -t syscognos -t sysevt -t sysvar -t sysvar_sendev -t sysvar_senprod -t tapsenrevchanges -t tapsenrevisionentity -t telephone -t temval -t tenpol -t territ -t testoracle -t titele -t titelerne -t titmin -t titnob -t tmpsd -t toutes -t turelu -t typadr -t typapppol -t typbister -t typcandid -t type_activite -t type_activite_participant -t type_activite_rol -t type_activite_senateur -t type_categorie -t type_derogation -t type_droit_acces -t type_pj_justificatif -t type_rne_diff -t type_type_derogation -t typele -t typgrpsen -t typman -t typmin -t typmoddes -t typorg -t typorgext -t typparpol -t typpoicon -t typprs -t typprssta -t typscr -t typtel -t typurl -t typvoi -t uploaded_file -t uploaded_file_type -t validation -t validation_defview_profil -t validation_profil -t vercand -t verres -t votes -t zongeo -s sens
  *
  */

package/lib/scripts/convert_data.js

@@ -5,7 +5,7 @@ import path from "path";
 import pLimit from "p-limit";
 import * as git from "../git";
 import { datasets, EnabledDatasets, getEnabledDatasets } from "../datasets";
-import { DATA_ORIGINAL_FOLDER, DATA_TRANSFORMED_FOLDER, DOCUMENT_METADATA_FILE, DOSLEG_DOSSIERS_FOLDER, SCRUTINS_FOLDER, RAPPORT_FOLDER, SENS_CIRCONSCRIPTIONS_FOLDER, SENS_ORGANISMES_FOLDER, SENS_SENATEURS_FOLDER, TEXTE_FOLDER } from "../loaders";
+import { DATA_ORIGINAL_FOLDER, DATA_TRANSFORMED_FOLDER, DOCUMENT_METADATA_FILE, DOSLEG_DOSSIERS_FOLDER, SCRUTINS_FOLDER, RAPPORT_FOLDER, SENS_CIRCONSCRIPTIONS_FOLDER, SENS_ORGANISMES_FOLDER, SENS_SENATEURS_FOLDER, TEXTE_FOLDER, } from "../loaders";
 import { findAllAmendements, findAllCirconscriptions, findAllDebats, findAllDossiers, findAllScrutins, findAllOrganismes, findAllQuestions, findAllSens, findAllTextes, findAllRapports, } from "../model";
 import { processRapport, processTexte } from "./retrieve_documents";
 import { buildActesLegislatifs } from "../model/dosleg";
@@ -164,7 +164,7 @@ async function convertDatasetDosLeg(dataDir, options) {
         const actesBrutsNormalises = buildActesLegislatifs(dossier);
         const dossierWithActes = {
             ...dossier,
-            actes_legislatifs: actesBrutsNormalises
+            actes_legislatifs: actesBrutsNormalises,
         };
         const dossierFile = `${dossier["signet"]}.json`;
         await fs.outputJSON(path.join(dossierReorganizedDir, dossierFile), dossierWithActes, { spaces: 2 });
@@ -236,7 +236,7 @@ async function convertTextes(dataDir, options) {
         const texteName = path.parse(texte["url"]).name;
         const texteDir = path.join(originalTextesDir, `${session}`, texteName);
         // oritxtcod = 1 corresponds to "Texte de loi déposé au Sénat"
-        const hasExposeDesMotifs = texte["origine"] === 'Sénat' && texte["ordre_origine"] === '1';
+        const hasExposeDesMotifs = texte["origine"] === "Sénat" && texte["ordre_origine"] === "1";
         const metadata = {
             name: texteName,
             session: texte["session"],

package/lib/scripts/parse_textes.js

@@ -2,8 +2,8 @@ import assert from "assert";
 import commandLineArgs from "command-line-args";
 import fs from "fs-extra";
 import path from "path";
-import { iterFilePaths, TEXTE_FOLDER, DATA_ORIGINAL_FOLDER, DATA_TRANSFORMED_FOLDER, } from "../loaders";
-import { parseExposeDesMotifsFromFile, parseTexteFromFile, } from "../model/texte";
+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";
 const optionsDefinitions = [...commonOptions];

package/lib/scripts/retrieve_open_data.js

@@ -272,6 +272,7 @@ async function retrieveOpenData() {
         ...process.env,
         PGHOST: process.env["PGHOST"] || config.db.host,
         PGPORT: process.env["PGPORT"] || String(config.db.port),
+        PGDATABASE: process.env["PGDATABASE"] || config.db.name,
         PGUSER: process.env["PGUSER"] || config.db.user,
         PGPASSWORD: process.env["PGPASSWORD"] || config.db.password,
     };

package/lib/scripts/test_iter_load.js

@@ -1,4 +1,4 @@
-import { iterLoadSenatRapports } from "../loaders";
+import { iterLoadSenatRapports, } from "../loaders";
 import commandLineArgs from "command-line-args";
 import { dataDirDefaultOption } from "./shared/cli_helpers";
 const optionsDefinitions = [dataDirDefaultOption];

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

@@ -11,6 +11,8 @@ declare const findAllAmendementsQuery: import("kysely").SelectQueryBuilder<{
     etat: string;
     sort: any;
     url: string;
+    au_nom_de_commission: string;
+    code_commission: string;
     auteur_est_gouvernement: boolean;
     scrutin_num: any;
     auteurs: {
@@ -33,6 +35,8 @@ export declare function findAllAmendements(fromSession?: number): AsyncIterableI
     etat: string;
     sort: any;
     url: string;
+    au_nom_de_commission: string;
+    code_commission: string;
     auteur_est_gouvernement: boolean;
     scrutin_num: any;
     auteurs: {

package/lib/src/model/ameli.js

@@ -1,7 +1,7 @@
 import { sql } from "kysely";
 import { jsonArrayFrom } from "kysely/helpers/postgres";
 import { dbSenat } from "../databases";
-import { concat, toDateString } from "./util";
+import { concat, rtrim, toDateString } from "./util";
 function auteurs(amendementId) {
     return jsonArrayFrom(dbSenat
         .selectFrom("ameli.amdsen")
@@ -134,8 +134,8 @@ const findAllAmendementsQuery = dbSenat
         .else(val("https://www.senat.fr/amendements/"))
         .end(), ref("ameli.ses.ann"), val("-"), sql `(ameli.ses.ann + 1)`, val("/"), ref("ameli.txt_ameli.numabs"), val("/Amdt_"), ref("ameli.amd.num"), val(".html")).as("url"),
     "ameli.grppol_ameli.lilcou as au_nom_de_groupe_politique",
-    "ameli.com_ameli.lil as au_nom_de_commission",
-    "ameli.com_ameli.cod as code_commission",
+    rtrim(ref("ameli.com_ameli.lil")).as("au_nom_de_commission"),
+    rtrim(ref("ameli.com_ameli.cod")).as("code_commission"),
     eb.case().when("ameli.cab.entid", "is not", null).then(true).else(false).end().as("auteur_est_gouvernement"),
     scrutin(ref("ameli.amd.num"), ref("ameli.ses.ann"), ref("dosleg.texte.lecassidt")),
     auteurs(ref("ameli.amd.id")).as("auteurs"),

package/lib/src/scripts/retrieve_videos.js

@@ -132,6 +132,7 @@ async function processGroupedReunion(agenda, session, dataDir, lastByVideo) {
     // 3) Always update BEST agenda JSON from local NVS
     await processOneReunionMatch({
         agenda,
+        best,
         baseDir: ctx.baseDir,
         dataDir: ctx.dataDir,
         session: ctx.session,

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

@@ -30,6 +30,7 @@ export interface Reunion {
     compteRenduRefUid?: string;
     transcriptionRef?: string;
     urlVideo?: string;
+    urlPageVideo?: string;
     timecodeDebutVideo?: number;
     timecodeFinVideo?: number;
     odj?: ReunionOdj;

package/lib/src/utils/nvs-timecode.d.ts

@@ -0,0 +1,17 @@
+export type L1Chapter = {
+    id: string;
+    label: string;
+    index: number;
+};
+export declare function getLevel1Chapters(dataNvs: string): L1Chapter[];
+export declare function pickBestLevel1ChapterForAgenda(chapters: L1Chapter[], agendaTitle: string): {
+    chapter: L1Chapter;
+    score: number;
+} | null;
+export declare function getAgendaSegmentTimecodes(dataNvs: string, finalPlayerNvs: string, agendaTitleOrObjet: string): {
+    start: number;
+    end: number | null;
+    chapterId: string;
+    nextChapterId: string | null;
+    score: number;
+} | null;

package/lib/src/utils/nvs-timecode.js

@@ -0,0 +1,79 @@
+import { XMLParser } from "fast-xml-parser";
+import { dice, normalize } from "./scoring";
+import { decodeHtmlEntities } from "./string_cleaning";
+const CHAPTER_MATCH_THRESHOLD = 0.5;
+const xmlParser = new XMLParser({
+    ignoreAttributes: false,
+    attributeNamePrefix: "@_",
+});
+function getTimecodeForChapterId(finalPlayerNvs, chapterId) {
+    const xml = xmlParser.parse(finalPlayerNvs);
+    const synchros = xml?.player?.synchro;
+    if (!synchros)
+        return null;
+    const synchsArray = Array.isArray(synchros) ? synchros : [synchros];
+    const match = synchsArray.find((s) => String(s["@_id"]) === String(chapterId));
+    if (!match)
+        return null;
+    const rawTimecode = match["@_timecode"];
+    if (rawTimecode == null)
+        return null;
+    const ms = Number(rawTimecode);
+    if (Number.isNaN(ms))
+        return null;
+    return Math.floor(ms / 1000);
+}
+function toArray(v) {
+    if (!v)
+        return [];
+    return Array.isArray(v) ? v : [v];
+}
+export function getLevel1Chapters(dataNvs) {
+    const xml = xmlParser.parse(dataNvs);
+    const root = xml?.data?.chapters?.chapter ?? xml?.chapters?.chapter;
+    const roots = toArray(root);
+    return roots
+        .map((ch, i) => {
+        const id = ch?.id ?? ch?.["@_id"];
+        const labelRaw = ch?.label ?? ch?.["@_label"] ?? "";
+        return {
+            id: String(id),
+            label: decodeHtmlEntities(String(labelRaw)).trim(),
+            index: i,
+        };
+    })
+        .filter((c) => c.id && c.label);
+}
+export function pickBestLevel1ChapterForAgenda(chapters, agendaTitle) {
+    const q = normalize(agendaTitle);
+    let best = null;
+    for (const ch of chapters) {
+        const s = dice(q, ch.label);
+        if (!best || s > best.score)
+            best = { chapter: ch, score: s };
+    }
+    if (!best || best.score < CHAPTER_MATCH_THRESHOLD)
+        return { chapter: chapters[0], score: 0 };
+    return best;
+}
+export function getAgendaSegmentTimecodes(dataNvs, finalPlayerNvs, agendaTitleOrObjet) {
+    const l1 = getLevel1Chapters(dataNvs);
+    if (!l1.length)
+        return null;
+    const best = pickBestLevel1ChapterForAgenda(l1, agendaTitleOrObjet);
+    if (!best)
+        return null;
+    const chapter = best.chapter;
+    const next = l1[chapter.index + 1] ?? null;
+    const start = getTimecodeForChapterId(finalPlayerNvs, chapter.id);
+    if (start == null)
+        return null;
+    const end = next ? getTimecodeForChapterId(finalPlayerNvs, next.id) : null;
+    return {
+        start,
+        end,
+        chapterId: chapter.id,
+        nextChapterId: next?.id ?? null,
+        score: best.score,
+    };
+}

package/lib/src/utils/weights_scoring_config.d.ts

@@ -0,0 +1,2 @@
+import { MatchWeights } from "./scoring";
+export declare const weights: MatchWeights;

package/lib/src/utils/weights_scoring_config.js

@@ -0,0 +1,15 @@
+// BASED ON TESTS RESULTS
+// these weights yield good results in the benchmark test suite
+// aiming at 0 WRONG matches while maximizing HITs
+export const weights = {
+    wTitle: 0.7,
+    wOrg: 0.1,
+    wSalle: 0,
+    wTime: 0.2,
+    sameOrgBonus: 0.2,
+    minAccept: 0.5,
+    margin: 0.1,
+    titleMin: 0.2,
+    titleDominance: 0,
+    orgUncertainPenalty: 0.8,
+};

package/lib/src/videos/pipeline.d.ts

@@ -3,6 +3,7 @@ import { BestMatch, LastForVideo, MatchContext } from "./types";
 import { CommandLineOptions } from "command-line-args";
 export declare function processOneReunionMatch(args: {
     agenda: Reunion;
+    best: BestMatch | null;
     baseDir: string;
     dataDir: string;
     session: number;
@@ -29,6 +30,7 @@ export declare function processBisIfNeeded(args: {
     writeIfChanged: (p: string, content: string) => Promise<void>;
     processOneReunionMatch: (args: {
         agenda: Reunion;
+        best: BestMatch | null;
         baseDir: string;
         dataDir: string;
         session: number;