Improv algo (#48)

* suppression du badge de build status de Travis CI * Rewrite tests to be more demanding * Fix test and bahevior when there is no CodNatJurBenefCA to anonymize the LibOrgaBenef * bump xmldom * Change occultation string to something more generic Also, make it a argument to the anonymize function with a default value * PJRef > NomPJ elements are anonymized * Occultation of all Champ_Editeurs * anonymise all <Proprietaire>s in all <MEMBREASA>s * 1.2.0
dtc-innovation · Apr 7, 2021 · 2302188 · 2302188
1 parent 07eb4f2
commit 2302188
Show file tree

Hide file tree

Showing 5 changed files with 130 additions and 31 deletions.
diff --git a/README.md b/README.md
@@ -1,4 +1,4 @@
-# anonymisation-document-budgetaire [![Build Status](https://travis-ci.org/dtc-innovation/anonymisation-document-budgetaire.svg?branch=master)](https://travis-ci.org/dtc-innovation/anonymisation-document-budgetaire)
+# anonymisation-document-budgetaire
 
 Outil d'anonymisation de fichiers DocumentBudgetaire
 

diff --git a/index.js b/index.js
@@ -1,27 +1,47 @@
-const ANONYMIZED_NAME = "Nom anonymisé";
-
 // http://odm-budgetaire.org/doc-schema/CommunAnnexe_xsd_Complex_Type_ATCodNatJurBenef.html#ATCodNatJurBenef_V
 const CodNatJurBenefPersonnesPhysiques = 'P3';
 
-export default function(doc){
+export default function(doc, OCCULTATION_STRING = "Occultation Article L311-7 CRPA"){
     const concours = Array.from(doc.getElementsByTagName('CONCOURS'));
-
     concours.forEach(c => {
         const natJurEl = c.getElementsByTagName('CodNatJurBenefCA')[0];
 
-        if(natJurEl && natJurEl.getAttribute('V') === CodNatJurBenefPersonnesPhysiques){
+        if(!natJurEl || natJurEl.getAttribute('V') === CodNatJurBenefPersonnesPhysiques){
             const libOrgaBenef = c.getElementsByTagName('LibOrgaBenef')[0];
-            libOrgaBenef.setAttribute('V', ANONYMIZED_NAME);
+            libOrgaBenef.setAttribute('V', OCCULTATION_STRING);
         }
     })
 
     const prets = Array.from(doc.getElementsByTagName('PRET'))
-
     prets.forEach(c => {
         const nomBenefPret = c.getElementsByTagName('NomBenefPret')[0];
 
         if(nomBenefPret){
-            nomBenefPret.setAttribute('V', ANONYMIZED_NAME);
+            nomBenefPret.setAttribute('V', OCCULTATION_STRING);
+        }
+    })
+
+    const BlocBudget = doc.getElementsByTagName('BlocBudget')[0];
+    const PJRefs = Array.from(BlocBudget.getElementsByTagName('PJRef'));
+    PJRefs.forEach(pjref => {
+        const NomPJ = pjref.getElementsByTagName('NomPJ')[0];
+
+        if(NomPJ){
+            NomPJ.setAttribute('V', OCCULTATION_STRING);
+        }
+    })
+
+    const Champ_Editeurs = Array.from(doc.getElementsByTagName('Champ_Editeur'));
+    Champ_Editeurs.forEach(ce => {
+        ce.setAttribute('V', OCCULTATION_STRING);
+    })
+
+    const MEMBREASAs = Array.from(doc.getElementsByTagName('MEMBREASA'))
+    MEMBREASAs.forEach(masa => {
+        const Proprietaire = masa.getElementsByTagName('Proprietaire')[0];
+
+        if(Proprietaire){
+            Proprietaire.setAttribute('V', OCCULTATION_STRING);
         }
     })
 }
diff --git a/package-lock.json b/package-lock.json
diff --git a/package.json b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "anon-doc-budg",
-  "version": "1.1.1",
+  "version": "1.2.0",
   "description": "Outil d'anonymisation de fichiers DocumentBudgetaire",
   "type": "module",
   "engines": {
@@ -23,7 +23,7 @@
     "fs-extra": "^7.0.1",
     "p-limit": "^3.1.0",
     "xml-buffer-tostring": "^0.2.0",
-    "xmldom": "^0.1.27"
+    "xmldom": "^0.5.0"
   },
   "devDependencies": {
     "babel-core": "^6.26.3",

diff --git a/test/index.js b/test/index.js
@@ -4,8 +4,17 @@ import {DOMParser, XMLSerializer} from 'xmldom';
 
 import anonymize from '../index.js';
 
+const defaultBlocBudget = `<BlocBudget>
+    <NatDec V="09"/>
+    <Exer V="2016"/>
+    <BudgPrec V="1"/>
+    <ReprRes V="1"/>
+    <NatFonc V="3"/>
+    <CodTypBud V="P"/>
+</BlocBudget>`
 
-function makeDocBudg(annexes){
+
+function makeDocBudg(annexes = '', blocBudget = defaultBlocBudget){
     const xmlStr = `<?xml version="1.0" encoding="UTF-8"?>
     <DocumentBudgetaire xsi:schemaLocation="http://www.minefi.gouv.fr/cp/demat/docbudgetaire Actes_budgetaires___Schema_Annexes_Bull_V15\DocumentBudgetaire.xsd" xmlns="http://www.minefi.gouv.fr/cp/demat/docbudgetaire" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
        <VersionSchema V="81"/>
@@ -23,14 +32,7 @@ function makeDocBudg(annexes){
              <CodBud V="00"/>
              <Nomenclature V="M14-M14_COM_500_3500"/>
           </EnTeteBudget>
-          <BlocBudget>
-             <NatDec V="09"/>
-             <Exer V="2016"/>
-             <BudgPrec V="1"/>
-             <ReprRes V="1"/>
-             <NatFonc V="3"/>
-             <CodTypBud V="P"/>
-          </BlocBudget>
+          ${blocBudget}
           <InformationsGenerales/>
           <LigneBudget>
             <CodRD V="D"/>
@@ -76,7 +78,7 @@ describe('anonymize', () => {
 
         anonymize(doc);
 
-        expect( doc.getElementsByTagName('LibOrgaBenef')[0].getAttribute('V') ).to.not.equal(NAME);
+        expect( (new XMLSerializer()).serializeToString(doc) ).to.not.include(NAME);
     })
 
     it('should anonymize the document if there are several physical person names', () => {
@@ -105,10 +107,10 @@ describe('anonymize', () => {
         const libOrgaBenefs = doc.getElementsByTagName('LibOrgaBenef');
 
         expect( libOrgaBenefs[0].getAttribute('V') ).to.equal( libOrgaBenefs[1].getAttribute('V') );
-        expect( libOrgaBenefs[0].getAttribute('V') ).to.not.equal( NAME_1 );
+        expect( (new XMLSerializer()).serializeToString(doc) ).to.not.include(NAME_1);
     })
 
-    it('should not do anything if there is no <CodNatJurBenefCA> in the <CONCOURS>', () => {
+    it('should anonymize if there is no <CodNatJurBenefCA> in the <CONCOURS>', () => {
         const NAME = "Asso dtc";
 
         const annexes = `<Annexes>
@@ -124,7 +126,7 @@ describe('anonymize', () => {
 
         anonymize(doc);
 
-        expect( doc.getElementsByTagName('LibOrgaBenef')[0].getAttribute('V') ).to.equal(NAME);
+        expect( (new XMLSerializer()).serializeToString(doc) ).to.not.include(NAME);
     })
 
     it('should not do anything if there are subs, but no physical person', () => {
@@ -187,7 +189,7 @@ describe('anonymize', () => {
 
     })
 
-    it(`should anonimize all <NomBenefPret>s in all <PRET>s`, () => {
+    it(`should anonymize all <NomBenefPret>s in all <PRET>s`, () => {
         const NAME = 'David Bruant';
 
         const annexes = `<Annexes>
@@ -207,9 +209,86 @@ describe('anonymize', () => {
 
         anonymize(doc);
 
-        const nomBenefPret = doc.getElementsByTagName('NomBenefPret')[0].getAttribute('V')
+        expect( (new XMLSerializer()).serializeToString(doc) ).to.not.include(NAME);
+    })
+
+
+    it('should occult all Budget > BlocBudget > PJRef > NomPJ[V]', () => {
+        const PJ_NAME_1 = "Yo.pdf";
+        const PJ_NAME_2 = "Document joint";
+
+        const blocBudget = `<BlocBudget>
+            <NatDec V="09"/>
+            <Exer V="2016"/>
+            <BudgPrec V="1"/>
+            <ReprRes V="1"/>
+            <NatFonc V="3"/>
+            <CodTypBud V="P"/>
+            <PJRef>
+                <NomPJ V="${PJ_NAME_1}"/>
+            </PJRef>
+            <PJRef>
+                <NomPJ V="${PJ_NAME_2}"/>
+            </PJRef>
+        </BlocBudget>`
+
+        const doc = makeDocBudg(undefined, blocBudget);
+
+        anonymize(doc);
+
+        expect( (new XMLSerializer()).serializeToString(doc) ).to.not.include(PJ_NAME_1);
+        expect( (new XMLSerializer()).serializeToString(doc) ).to.not.include(PJ_NAME_2);
+    })
+
+
+    it('should occult all Champ_Editeur[V]', () => {
+        const CHAMP_EDITEUR_1 = "srbdtyndu,yu";
+        const CHAMP_EDITEUR_2 = "16151651681653";
+        const CHAMP_EDITEUR_3 = "ù$*ù*ù$";
+
+        const annexes = `<Annexes>
+            <DATA_EMPRUNT>
+                <EMPRUNT>
+                    <Champ_Editeur V="${CHAMP_EDITEUR_1}"/>
+                </EMPRUNT>
+            </DATA_EMPRUNT>
+            <DATA_TRESORERIE>
+                <TRESORERIE>
+                    <Champ_Editeur V="${CHAMP_EDITEUR_2}"/>
+                </TRESORERIE>
+            </DATA_TRESORERIE>
+            <DATA_CHARGE>
+                <CHARGE>
+                    <Champ_Editeur V="${CHAMP_EDITEUR_3}"/>
+                </CHARGE>
+            </DATA_CHARGE>
+        </Annexes>`;
+
+        const doc = makeDocBudg(annexes);
+
+        anonymize(doc);
+
+        expect( (new XMLSerializer()).serializeToString(doc) ).to.not.include(CHAMP_EDITEUR_1);
+        expect( (new XMLSerializer()).serializeToString(doc) ).to.not.include(CHAMP_EDITEUR_2);
+        expect( (new XMLSerializer()).serializeToString(doc) ).to.not.include(CHAMP_EDITEUR_3);
+    })
+
+    it(`should anonymize all <Proprietaire>s in all <MEMBREASA>s`, () => {
+        const NAME = 'David Bruant';
+
+        const annexes = `<Annexes>
+            <DATA_MEMBRESASA>
+                <MEMBREASA>
+                    <Proprietaire V="${NAME}"/>
+                </MEMBREASA>
+            </DATA_MEMBRESASA>
+        </Annexes>`;
+
+        const doc = makeDocBudg(annexes);
+
+        anonymize(doc);
 
-        expect( nomBenefPret ).to.not.equal(NAME);
+        expect( (new XMLSerializer()).serializeToString(doc) ).to.not.include(NAME);
     })
 
 });