Parse ontologies and generate publishable directory structure

.gitignore

@@ -0,0 +1,5 @@
+node_modules/*
+.idea
+.rpt2*
+coverage/**
+ontologies/*

package.json

@@ -0,0 +1,31 @@
+{
+  "name": "ontologies",
+  "version": "1.0.0",
+  "description": "",
+  "main": "index.js",
+  "scripts": {
+    "clean": "rm -rf packages/",
+    "generate": "ts-node src/index.ts",
+    "rebuild": "yarn clean && yarn generate",
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/ontola/ontologies.git"
+  },
+  "author": "Fletcher91 <[email protected]>",
+  "license": "GPL-3.0-or-later",
+  "bugs": {
+    "url": "https://github.com/ontola/ontologies/issues"
+  },
+  "homepage": "https://github.com/ontola/ontologies#readme",
+  "dependencies": {
+    "@types/glob": "^7.1.1",
+    "glob": "^7.1.4",
+    "npm-registry-client": "^8.6.0",
+    "rdflib": "npm:[email protected]",
+    "ts-morph": "^3.1.3",
+    "ts-node": "^8.3.0",
+    "typescript": "^3.5.3"
+  }
+}

src/defaults.package.json

@@ -0,0 +1,5 @@
+{
+  "license": "GPL-3.0-or-later",
+  "main": "index.js",
+  "version": "1.0.0"
+}

src/generate.ts

@@ -0,0 +1,38 @@
+import { Project } from "ts-morph"
+import {
+  Ontology,
+  OntologyItem,
+  OntologyItemPropType,
+} from './types'
+import defaults from './defaults.package.json';
+
+const firstValue = (obj: OntologyItem, property: string): OntologyItemPropType => {
+  if (obj && Object.prototype.hasOwnProperty.call(obj, property)) {
+    const prop = obj[property]
+
+    return Array.isArray(prop) ? prop[0] : prop
+  }
+
+  return undefined
+}
+
+export async function generate(ontologies: Ontology[]) {
+  const packages = new Project()
+
+  for (const ontology of ontologies) {
+    const packageJSON = Object.assign(
+      {},
+      defaults,
+      {
+        name: `@ontologies/${ontology.symbol}`,
+        description: firstValue(ontology, 'label'),
+      }
+    )
+    packages.createSourceFile(
+      `packages/${ontology.symbol}/package.json`,
+      JSON.stringify(packageJSON, null, 2)
+    )
+  }
+
+  await packages.save()
+}

src/index.ts

@@ -0,0 +1,5 @@
+import { generate } from './generate'
+import { parse } from "./parse"
+
+console.log("Starting process")
+parse().then(generate);

src/parse.ts

@@ -0,0 +1,107 @@
+import * as  fs from "fs"
+import * as path from 'path'
+
+import glob from "glob"
+import {
+  parse as parseRDF,
+  IndexedFormula,
+  Namespace,
+  SomeTerm,
+  Statement,
+  NamedNode,
+} from 'rdflib'
+import {
+  Ontology,
+  OntologyClass,
+  OntologyInfo,
+  OntologyProperty,
+} from './types'
+
+const rdf = Namespace("http://www.w3.org/1999/02/22-rdf-syntax-ns#")
+const rdfs = Namespace("http://www.w3.org/2000/01/rdf-schema#")
+const owl = Namespace("http://www.w3.org/2002/07/owl#")
+const classTypes: SomeTerm[] = [
+  rdfs("Class"),
+  owl("Class"),
+];
+const propertyTypes: SomeTerm[] = [
+  rdf("Property"),
+  owl("ObjectProperty"),
+];
+
+function parseOntology(file: string, ontologyInfo: OntologyInfo): Promise<IndexedFormula> {
+  return new Promise((resolve) => {
+    const ontology = new IndexedFormula()
+
+    parseRDF(file, ontology, ontologyInfo.ns, "text/turtle", () => {
+      resolve(ontology)
+    })
+  })
+}
+
+function getClasses(ontologyData: IndexedFormula): OntologyClass[] {
+  const getProperty = (st: Statement, prop: NamedNode): SomeTerm[] =>
+    ontologyData.match(st.subject, prop).map(s => s.object);
+
+  return ontologyData
+    .statements
+    .filter((st) => st.predicate === rdf("type") && classTypes.includes(st.object))
+    .map((property) => ({
+      iri: property.subject,
+      label: getProperty(property, rdfs("label")),
+      comment: getProperty(property, rdfs("comment")),
+      isDefinedBy: getProperty(property, rdfs("isDefinedBy")),
+      seeAlso: getProperty(property, rdfs("seeAlso")),
+      subClassOf: getProperty(property, rdfs("subClassOf")).filter(term => term.termType === "NamedNode") as NamedNode[],
+    }))
+}
+
+function getProperties(ontologyData: IndexedFormula): OntologyProperty[] {
+  const getProperty = (st: Statement, prop: NamedNode): SomeTerm[] =>
+    ontologyData.match(st.subject, prop).map(s => s.object);
+
+  return ontologyData
+    .statements
+    .filter((st) => st.predicate === rdf("type") && propertyTypes.includes(st.object))
+    .map((property) => ({
+      iri: property.subject,
+      label: getProperty(property, rdfs("label")),
+      comment: getProperty(property, rdfs("comment")),
+      isDefinedBy: getProperty(property, rdfs("isDefinedBy")),
+      seeAlso: getProperty(property, rdfs("seeAlso")),
+      domain: getProperty(property, rdfs("domain")).filter(term => term.termType === "NamedNode") as NamedNode[],
+      range: getProperty(property, rdfs("range")).filter(term => term.termType === "NamedNode") as NamedNode[],
+    }))
+}
+
+export function parse(): Promise<Ontology[]> {
+  return new Promise(async (resolve, reject) => {
+    glob("./ontologies/**/index.json", async (err: Error | null, files: string[]) => {
+      if (err) {
+        return reject(err)
+      }
+
+      const ontologies: Ontology[] = []
+
+      for (const file of files) {
+        const infoFile = fs.readFileSync(file, "utf8")
+        const ontologyInfo = JSON.parse(infoFile) as OntologyInfo;
+        const ontologyFile = fs.readFileSync(path.resolve(file, '../ontology.ttl'), "utf8")
+
+        const ontologyData = await parseOntology(ontologyFile, ontologyInfo)
+
+        const ontology = {
+          name: ontologyInfo.name,
+          ns: new NamedNode(ontologyInfo.ns),
+          symbol: ontologyInfo.symbol,
+          classes: getClasses(ontologyData),
+          properties: getProperties(ontologyData),
+        };
+
+        ontologies.push(ontology)
+      }
+
+      return resolve(ontologies)
+    })
+  })
+}

src/types.ts

@@ -0,0 +1,42 @@
+import { NamedNode, SomeTerm } from 'rdflib'
+
+export interface OntologyInfo {
+  /** Human readable name */
+  name: string
+  /** The namespace IRI */
+  ns: string
+  /** Location where the ontology can be fetched */
+  source: string
+  /** Preferred shortening symbol for the namespace */
+  symbol: string
+}
+
+export type OntologyItemPropType = undefined | string | SomeTerm | OntologyClass | OntologyProperty
+export type OntologyItemProp = OntologyItemPropType | Array<OntologyItemPropType>
+
+export interface OntologyItem {
+  [k: string]: OntologyItemProp
+  name?: string
+  iri?: SomeTerm
+  label?: SomeTerm[]
+  comment?: SomeTerm[]
+  isDefinedBy?: SomeTerm[]
+  seeAlso?: SomeTerm[]
+}
+
+export interface Ontology extends OntologyItem {
+  classes: OntologyClass[]
+  name: string
+  properties: OntologyProperty[]
+  symbol: string
+  ns: NamedNode
+}
+
+export interface OntologyProperty extends OntologyItem {
+  domain: NamedNode[]
+  range: NamedNode[]
+}
+
+export interface OntologyClass extends OntologyItem {
+  subClassOf: NamedNode[]
+}

tsconfig.json

@@ -0,0 +1,47 @@
+{
+  "compilerOptions": {
+    /* Basic Options */
+    "incremental": true,                   /* Enable incremental compilation */
+    "target": "es5",                          /* Specify ECMAScript target version: 'ES3' (default), 'ES5', 'ES2015', 'ES2016', 'ES2017', 'ES2018', 'ES2019' or 'ESNEXT'. */
+    "module": "commonjs",                     /* Specify module code generation: 'none', 'commonjs', 'amd', 'system', 'umd', 'es2015', or 'ESNext'. */
+    "lib": [
+      "es2019"
+    ],
+    // "allowJs": true,                       /* Allow javascript files to be compiled. */
+    "resolveJsonModule": true,
+    // "checkJs": true,                       /* Report errors in .js files. */
+    // "declaration": true,                   /* Generates corresponding '.d.ts' file. */
+    // "declarationMap": true,                /* Generates a sourcemap for each corresponding '.d.ts' file. */
+    // "sourceMap": true,                     /* Generates corresponding '.map' file. */
+    // "outFile": "./",                       /* Concatenate and emit output to single file. */
+    // "outDir": "./",                        /* Redirect output structure to the directory. */
+    // "rootDir": "./",                       /* Specify the root directory of input files. Use to control the output directory structure with --outDir. */
+    // "composite": true,                     /* Enable project compilation */
+    // "tsBuildInfoFile": "./",               /* Specify file to store incremental compilation information */
+    // "removeComments": true,                /* Do not emit comments to output. */
+    "noEmit": true,                        /* Do not emit outputs. */
+    // "importHelpers": true,                 /* Import emit helpers from 'tslib'. */
+    // "downlevelIteration": true,            /* Provide full support for iterables in 'for-of', spread, and destructuring when targeting 'ES5' or 'ES3'. */
+    // "isolatedModules": true,               /* Transpile each file as a separate module (similar to 'ts.transpileModule'). */
+
+    /* Strict Type-Checking Options */
+    "strict": true,                           /* Enable all strict type-checking options. */
+
+    /* Additional Checks */
+    "noUnusedLocals": true,                /* Report errors on unused locals. */
+    "noUnusedParameters": true,            /* Report errors on unused parameters. */
+    "noImplicitReturns": true,             /* Report error when not all code paths in function return a value. */
+    "noFallthroughCasesInSwitch": true,    /* Report errors for fallthrough cases in switch statement. */
+
+    /* Module Resolution Options */
+    // "baseUrl": "./",                       /* Base directory to resolve non-absolute module names. */
+    // "paths": {},                           /* A series of entries which re-map imports to lookup locations relative to the 'baseUrl'. */
+    // "rootDirs": [],                        /* List of root folders whose combined content represents the structure of the project at runtime. */
+    // "typeRoots": [],                       /* List of folders to include type definitions from. */
+    // "types": [],                           /* Type declaration files to be included in compilation. */
+    // "allowSyntheticDefaultImports": true,  /* Allow default imports from modules with no default export. This does not affect code emit, just typechecking. */
+    "esModuleInterop": true                   /* Enables emit interoperability between CommonJS and ES Modules via creation of namespace objects for all imports. Implies 'allowSyntheticDefaultImports'. */
+    // "preserveSymlinks": true,              /* Do not resolve the real path of symlinks. */
+    // "allowUmdGlobalAccess": true,          /* Allow accessing UMD globals from modules. */
+  }
+}