[ENH] Impemented validation for output JSON (#602)

* [FIX] test to use explicit file loading

Previously we relied on a files position in the list of downloaded files.
That's brittle. If we look for the correct file instead, it's not brittle.
Not brittle is better.

* Enabled cypress studio experimental feature

* Aligned terms and output with schema and examples

* Added `ajv` as a dependency

* Added example output json

* Added neurobagel schema to the fixtures

* Added example files

* Implemented validate-output test

* Renamed example files

* Added example file

* Updated example files

* Removed dead code

* Renamed and expanded previously `my_happy_annotation_page_tests`


* Fixed simple-e2e test

* Changed test

* Fixed test

* Added a comment on the filename fix for download-pagetest

* Capitalized `Other` option for `Sex` category

* Removed `example_synthetic copy_annotated_*` file

---------

Co-authored-by: Sebastian Urchs <[email protected]>
Co-authored-by: Arman Jahanpour <[email protected]>

cypress.config.js

@@ -26,7 +26,8 @@ module.exports = defineConfig({
                 findFiles,
                 isFileExist
             });
-        }
+        },
+        experimentalStudio: true
     },
 
     component: {

cypress/e2e/app/simple-e2etest.cy.js

@@ -146,7 +146,7 @@ describe("End to end test using a simple UI path through the app", () => {
                             expect(fileContent.iq.Annotations.IsAbout.Label).to.eq("Assessment tool");
                             expect(fileContent.iq.Annotations.IsAbout.TermURL).to.eq("nb:Assessment");
                             expect(fileContent.iq.Annotations.IsPartOf.Label).to.eq("Wechsler Abbreviated Scale of Intelligence");
-                            expect(fileContent.iq.Annotations.IsPartOf.TermURL).to.eq("cogAtlas:trm_4b94affc43245");
+                            expect(fileContent.iq.Annotations.IsPartOf.TermURL).to.eq("cogatlas:trm_4b94affc43245");
                           });
                     });
 

cypress/e2e/app/validate-output-example-synthetic-e2etest.cy.js

@@ -0,0 +1,114 @@
+describe("to annotate an assessment ", () => {
+    it("sets up some stuff", () => {
+        // Load some data
+        cy.visit('/');
+        cy.get('[data-cy="data-table-selector"]').get('input').selectFile('cypress/fixtures/examples/good/example_synthetic.tsv', { force: true });
+
+        /* ==== Generated with Cypress Studio ==== */
+        cy.get('[data-cy="data-dictionary-selector"] > .row > form > .file-selector-button').click();
+        cy.get('[data-cy="data-dictionary-selector"] > .row > form > .file-selector-button > input').selectFile('cypress/fixtures/examples/good/example_synthetic.json', { force: true });
+        /* ==== End Cypress Studio ==== */
+        cy.get("[data-cy='button-nextpage']").click();
+
+        // Categorize some columns
+        const desiredColumnMappings = [
+            {
+                "column": "participant_id",
+                "category": "Subject ID"
+            },
+            {
+                "column": "pheno_age",
+                "category": "Age"
+
+            },
+            {
+                "column": "pheno_sex",
+                "category": "Sex"
+            },
+            {
+                "column": "pheno_group",
+                "category": "Diagnosis"
+            },
+            {
+                "column": "tool1_item1",
+                "category": "Assessment Tool"
+            },
+            {
+                "column": "tool1_item2",
+                "category": "Assessment Tool"
+            },
+            {
+                "column": "tool2_item1",
+                "category": "Assessment Tool"
+            }
+        ];
+        desiredColumnMappings.forEach(desiredColumnMapping => {
+            cy.get("[data-cy='categorization-table']").contains(desiredColumnMapping.category).click();
+            cy.get("[data-cy='column-linking-table']").contains(desiredColumnMapping.column).click();
+        });
+        // Create two tools
+        cy.get("[data-cy='toolgroup-select']").type("Montreal Cognitive Assessment{enter}");
+        cy.get("[data-cy='toolgroup-select']").type("Unified Parkinson's Disease Rating Scale{enter}");
+        // Map columns to tools
+        const desiredColumnToolMappings = [
+            {
+                "column": "tool1_item1",
+                "tool": "Montreal Cognitive Assessment"
+            },
+            {
+                "column": "tool1_item2",
+                "tool": "Montreal Cognitive Assessment"
+            },
+            {
+                "column": "tool2_item1",
+                "tool": "Unified Parkinson's Disease Rating Scale"
+            }
+        ];
+        desiredColumnToolMappings.forEach(desiredColumnToolMapping => {
+            cy.get("[data-cy='assessment-tool-table']").contains(desiredColumnToolMapping.tool).click();
+            cy.get("[data-cy='assessment-column-table']").contains(desiredColumnToolMapping.column).click();
+        });
+
+        cy.get("[data-cy='button-nextpage']").click();
+
+        /* ==== Generated with Cypress Studio ==== */
+        cy.get('#vs2__combobox > .vs__selected-options > .vs__search').click();
+        cy.get('#vs2__option-1').click();
+        cy.get('[data-cy="dataTable-pheno_age"] > tbody > :nth-child(3) > [aria-colindex="3"] > [data-cy="missingValueButton_2"]').click();
+        cy.get("[data-cy='annotation-category-tabs'] ul").contains("li", "Sex").click();
+        cy.get('#vs3__combobox > .vs__selected-options > .vs__search').click();
+        cy.get('#vs3__option-1').click();
+        cy.get('#vs4__combobox > .vs__selected-options > .vs__search').click();
+        cy.get('#vs4__option-0').click();
+        cy.get('[data-cy="annot-categorical-Sex"] > .card > .card-body > [data-cy="categoricalTable"] > tbody > :nth-child(3) > [aria-colindex="5"] > [data-cy="missingValueButton_2"]').click();
+        cy.get("[data-cy='annotation-category-tabs'] ul").contains("li", "Diagnosis").click();
+        cy.get('#vs6__combobox > .vs__selected-options > .vs__search').click();
+        cy.get('thead > tr > [aria-colindex="6"]').click();
+        cy.get('[data-cy="isControlButton_0"]').click();
+        cy.get('#vs7__combobox > .vs__selected-options > .vs__search').click();
+        cy.get('#vs7__combobox > .vs__selected-options > .vs__search').clear('a');
+        cy.get('#vs7__combobox > .vs__selected-options > .vs__search').type('attention');
+        cy.get('#vs7__combobox').click();
+        cy.get('#vs7__combobox > .vs__selected-options > .vs__search').clear();
+        cy.get('#vs7__combobox > .vs__selected-options > .vs__search').type('Attention deficit hyperactivity disorder');
+        cy.get('#vs7__option-2').click();
+        cy.get('[aria-colindex="5"] > [data-cy="missingValueButton_2"]').click();
+        cy.get("[data-cy='annotation-category-tabs'] ul").contains("li", "Assessment Tool").click();
+        cy.get('[data-cy="tool-annotation-for-cogatlas:tsk_4a57abb949ece"] > tbody > :nth-child(4) > [aria-colindex="3"] > [data-cy="missingValueButton_3"]').click();
+        cy.get('[data-cy="Assessment Tool"]').contains("Montreal Cognitive Assessment").click();
+        cy.get('[data-cy="tool-annotation-for-cogatlas:trm_57964b8a66aed"] > tbody > :nth-child(7) > [aria-colindex="3"] > [data-cy="missingValueButton_6"]').click();
+        cy.get('[data-cy="tool-annotation-for-cogatlas:trm_57964b8a66aed"] > tbody > :nth-child(4) > [aria-colindex="3"] > [data-cy="missingValueButton_3"]').click();
+        cy.get('[data-cy="button-nextpage"]').click();
+        cy.get('[data-cy="download-button"]').click();
+        /* ==== End Cypress Studio ==== */
+
+        cy.task("downloads", "cypress/downloads").then(folderStateAfter => {
+            cy.readFile('cypress/downloads/' + folderStateAfter[folderStateAfter.length - 1]).then((outputContent) => {
+
+                const expectedOutput = require('../../fixtures/examples/good/example_synthetic_expected_output.json');
+                expect(outputContent).to.deep.equal(expectedOutput);
+              });
+        });
+    });
+
+});

cypress/e2e/page/download-pagetests.cy.js

@@ -67,22 +67,26 @@ describe("tests on download page ui via programmatic state loading and store int
                     // 2. Check contents of downloads folder
                     cy.task("downloads", "cypress/downloads").then(folderStateAfter => {
 
-                        // A. Check number of files in downloads folder has increased by one
+                        // Check that we actually downloaded a file
                         expect(folderStateAfter.length).to.be.eq(folderStateBefore.length + 1);
 
-                        // B. Check that the last file retrieved by fs.readdirSync contains the data dictionary input file prefix
-                        // as stored in dataDictionary.filename
+
                         cy.getVuexStoreValue("dataDictionary").then(dataDictionary => {
 
+                            // Using the datadictionary name to locate the file downloaded by test for further verification
+                            // may not be a foolproof solution since if another test ends up using the same data dictionary
+                            // as input this approach may grab the wrong file and lead to test(s) failing
                             const dataDictionaryFilenameNoExt = dataDictionary.filename.split(".").slice(0, -1).join(".");
-
-                            expect(folderStateAfter[folderStateAfter.length - 1]).to.contain(dataDictionaryFilenameNoExt);
+                            expect(folderStateAfter.some(filename => filename.includes(dataDictionaryFilenameNoExt))).to.be.true;
+
+                            // Because we only have access to dataDictionary within the scope of this promise,
+                            // we need to run our next assertion in here
+                            const targetFile = folderStateAfter.filter(filename => filename.includes(dataDictionaryFilenameNoExt))[0];
+                            cy.readFile('cypress/downloads/' + targetFile).then((fileContent) => {
+                                expect(fileContent.participant_id.Annotations).to.have.property("Identifies");
+                                expect(fileContent.participant_id.Annotations.Identifies).to.eq("participant");
+                              });
                         });
-                        // C. Check if the last file retrieved contains the Identifies property and its value under the participant_id key
-                        cy.readFile('cypress/downloads/' + folderStateAfter[folderStateAfter.length - 1]).then((fileContent) => {
-                            expect(fileContent.participant_id.Annotations).to.have.property("Identifies");
-                            expect(fileContent.participant_id.Annotations.Identifies).to.eq("participant");
-                          });
                     });
                 });
             });

cypress/e2e/validate-output.cy.js

@@ -0,0 +1,33 @@
+const Ajv = require('ajv');
+
+const outputJSONFilePath = 'cypress/fixtures/examples/good/ds003653_participant_annotated_1698934398962.json';
+
+const schemaPath = 'cypress/fixtures/schema/neurobagel_data_dictionary.schema.json';
+
+
+describe('Validate Output', () => {
+  it('Validates example output against the schema', () => {
+
+    const ajv = new Ajv();
+
+    cy.readFile(schemaPath)
+          .then((schema) => {
+
+            const validate = ajv.compile(schema);
+
+            cy.readFile(outputJSONFilePath)
+              .then((outputJSONData) => {
+
+                const isValid = validate(outputJSONData);
+
+                if (isValid) {
+                  cy.log('JSON is valid according to the schema');
+                } else {
+                  cy.log('JSON is not valid according to the schema');
+                  cy.log(validate.errors);
+                }
+                cy.expect(isValid).to.be.true;
+      });
+    });
+  });
+});

cypress/fixtures/examples/good/ds003653_participant_annotated_1698934398962.json

@@ -0,0 +1,123 @@
+{
+    "participant_id": {
+        "Description": "A participant ID",
+        "Annotations": {
+            "IsAbout": {
+                "Label": "Subject Unique Identifier",
+                "TermURL": "nb:ParticipantID"
+            },
+            "Identifies": "participant"
+        }
+    },
+    "age": {
+        "Annotations": {
+            "IsAbout": {
+                "Label": "Age",
+                "TermURL": "nb:Age"
+            },
+            "Transformation": {
+                "Label": "integer value",
+                "TermURL": "nb:FromInt"
+            },
+            "MissingValues": []
+        },
+        "Description": "age of the participant",
+        "Units": "years"
+    },
+    "sex": {
+        "Annotations": {
+            "IsAbout": {
+                "Label": "Sex",
+                "TermURL": "nb:Sex"
+            },
+            "Levels": {
+                "M": {
+                    "Label": "male",
+                    "TermURL": "bids:male"
+                },
+                "F": {
+                    "Label": "female",
+                    "TermURL": "bids:female"
+                }
+            },
+            "MissingValues": []
+        },
+        "Description": "sex of the participant as reported by the participant",
+        "Levels": {
+            "M": "male",
+            "F": "female"
+        }
+    },
+    "group": {
+        "Annotations": {
+            "IsAbout": {
+                "Label": "Diagnosis",
+                "TermURL": "nb:Diagnosis"
+            },
+            "Levels": {
+                "UD": {
+                    "Label": "Acute depression",
+                    "TermURL": "snomed:712823008"
+                },
+                "HC": {
+                    "Label": "Healthy Control",
+                    "TermURL": "ncit:C94342"
+                },
+                "HCconvertedMDD": {
+                    "Label": "Borderline personality disorder",
+                    "TermURL": "snomed:20010003"
+                }
+            },
+            "MissingValues": []
+        },
+        "Description": "diagnostic status determined by the study clinician at baseline",
+        "Levels": {
+            "UD": "individuals with unipolar depression including those diagnosed with MDD and PDD",
+            "HC": "healthy controls",
+            "HCconvertedMDD": "individual that presented as HC at baseline, but converted to MDD during the course of the study"
+        }
+    },
+    "group_dx": {
+        "Description": "specific diagnosis determined by the study clinician at baseline",
+        "missingValues": [],
+        "Levels": {
+            "MDD": "major depressive disorder",
+            "PDD": "persistent depressive disorder",
+            "HC": "healthy controls",
+            "HCconvertedMDD": "individual that presented as HC at baseline, but converted to MDD during the course of the study"
+        }
+    },
+    "number_comorbid_dx": {
+        "Description": "a number of diagnoses comorbid with UD (e.g., GAD, PTSD)",
+        "missingValues": [],
+        "Units": "number"
+    },
+    "medload": {
+        "Description": "reflects the number of dosage of psychotropic medications taken by participants. Higher numbers correspond to more medications and/or higher medication dosage ",
+        "missingValues": [],
+        "Units": "arbitrary units"
+    },
+    "iq": {
+        "Annotations": {
+            "IsAbout": {
+                "TermURL": "nb:Assessment",
+                "Label": "Assessment tool"
+            },
+            "IsPartOf": {
+                "TermURL": "cogAtlas:trm_4b94affc43245",
+                "Label": "Wechsler Abbreviated Scale of Intelligence"
+            },
+            "MissingValues": []
+        },
+        "Description": "IQ derived based on the NART assessment.",
+        "Units": "arbitrary units"
+    },
+    "session": {
+        "Description": "scanning session",
+        "missingValues": [],
+        "Levels": {
+            "1": "baseline",
+            "2": "6 months follow-up scan"
+        }
+    }
+}