import { describe, it, expect, vitest } from "vitest"; import * as entities from "./decode.js"; describe("Decode test", () => { const testcases = [ { input: "&amp;", output: "&" }, { input: "&#38;", output: "&" }, { input: "&#x26;", output: "&" }, { input: "&#X26;", output: "&" }, { input: "&#38;", output: "&" }, { input: "&#38;", output: "&" }, { input: "&#38;", output: "&" }, { input: ":", output: ":" }, { input: ":", output: ":" }, { input: ":", output: ":" }, { input: ":", output: ":" }, { input: "&#", output: "&#" }, { input: "&>", output: "&>" }, { input: "id=770&#anchor", output: "id=770&#anchor" }, ]; for (const { input, output } of testcases) { it(`should XML decode ${input}`, () => expect(entities.decodeXML(input)).toBe(output)); it(`should HTML decode ${input}`, () => expect(entities.decodeHTML(input)).toBe(output)); } it("should HTML decode partial legacy entity", () => { expect(entities.decodeHTMLStrict("×bar")).toBe("×bar"); expect(entities.decodeHTML("×bar")).toBe("×bar"); }); it("should HTML decode legacy entities according to spec", () => expect(entities.decodeHTML("?&image_uri=1&ℑ=2&image=3")).toBe( "?&image_uri=1&ℑ=2&image=3", )); it("should back out of legacy entities", () => expect(entities.decodeHTML("&a")).toBe("&a")); it("should not parse numeric entities in strict mode", () => expect(entities.decodeHTMLStrict("7")).toBe("7")); it("should parse   followed by < (#852)", () => expect(entities.decodeHTML(" <")).toBe("\u00A0<")); it("should decode trailing legacy entities", () => { expect(entities.decodeHTML("⨱×bar")).toBe("⨱×bar"); }); it("should decode multi-byte entities", () => { expect(entities.decodeHTML("≧̸")).toBe("≧̸"); }); it("should not decode legacy entities followed by text in attribute mode", () => { expect( entities.decodeHTML("¬", entities.DecodingMode.Attribute), ).toBe("¬"); expect( entities.decodeHTML("¬i", entities.DecodingMode.Attribute), ).toBe("¬i"); expect( entities.decodeHTML("¬=", entities.DecodingMode.Attribute), ).toBe("¬="); expect(entities.decodeHTMLAttribute("¬p")).toBe("¬p"); expect(entities.decodeHTMLAttribute("¬P")).toBe("¬P"); expect(entities.decodeHTMLAttribute("¬3")).toBe("¬3"); }); }); describe("EntityDecoder", () => { it("should decode decimal entities", () => { const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, ); expect(decoder.write("", 1)).toBe(-1); expect(decoder.write("8;", 0)).toBe(5); expect(callback).toHaveBeenCalledTimes(1); expect(callback).toHaveBeenCalledWith(":".charCodeAt(0), 5); }); it("should decode hex entities", () => { const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, ); expect(decoder.write(":", 1)).toBe(6); expect(callback).toHaveBeenCalledTimes(1); expect(callback).toHaveBeenCalledWith(":".charCodeAt(0), 6); }); it("should decode named entities", () => { const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, ); expect(decoder.write("&", 1)).toBe(5); expect(callback).toHaveBeenCalledTimes(1); expect(callback).toHaveBeenCalledWith("&".charCodeAt(0), 5); }); it("should decode legacy entities", () => { const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, ); decoder.startEntity(entities.DecodingMode.Legacy); expect(decoder.write("&", 1)).toBe(-1); expect(callback).toHaveBeenCalledTimes(0); expect(decoder.end()).toBe(4); expect(callback).toHaveBeenCalledTimes(1); expect(callback).toHaveBeenCalledWith("&".charCodeAt(0), 4); }); it("should decode named entity written character by character", () => { const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, ); for (const c of "amp") { expect(decoder.write(c, 0)).toBe(-1); } expect(decoder.write(";", 0)).toBe(5); expect(callback).toHaveBeenCalledTimes(1); expect(callback).toHaveBeenCalledWith("&".charCodeAt(0), 5); }); it("should decode numeric entity written character by character", () => { const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, ); for (const c of "#x3a") { expect(decoder.write(c, 0)).toBe(-1); } expect(decoder.write(";", 0)).toBe(6); expect(callback).toHaveBeenCalledTimes(1); expect(callback).toHaveBeenCalledWith(":".charCodeAt(0), 6); }); it("should decode hex entities across several chunks", () => { const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, ); for (const chunk of ["#x", "cf", "ff", "d"]) { expect(decoder.write(chunk, 0)).toBe(-1); } expect(decoder.write(";", 0)).toBe(9); expect(callback).toHaveBeenCalledTimes(1); expect(callback).toHaveBeenCalledWith(0xc_ff_fd, 9); }); it("should not fail if nothing is written", () => { const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, ); expect(decoder.end()).toBe(0); expect(callback).toHaveBeenCalledTimes(0); }); describe("errors", () => { it("should produce an error for a named entity without a semicolon", () => { const errorHandlers = { missingSemicolonAfterCharacterReference: vitest.fn(), absenceOfDigitsInNumericCharacterReference: vitest.fn(), validateNumericCharacterReference: vitest.fn(), }; const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, errorHandlers, ); decoder.startEntity(entities.DecodingMode.Legacy); expect(decoder.write("&", 1)).toBe(5); expect(callback).toHaveBeenCalledTimes(1); expect(callback).toHaveBeenCalledWith("&".charCodeAt(0), 5); expect( errorHandlers.missingSemicolonAfterCharacterReference, ).toHaveBeenCalledTimes(0); decoder.startEntity(entities.DecodingMode.Legacy); expect(decoder.write("&", 1)).toBe(-1); expect(decoder.end()).toBe(4); expect(callback).toHaveBeenCalledTimes(2); expect(callback).toHaveBeenLastCalledWith("&".charCodeAt(0), 4); expect( errorHandlers.missingSemicolonAfterCharacterReference, ).toHaveBeenCalledTimes(1); }); it("should produce an error for a numeric entity without a semicolon", () => { const errorHandlers = { missingSemicolonAfterCharacterReference: vitest.fn(), absenceOfDigitsInNumericCharacterReference: vitest.fn(), validateNumericCharacterReference: vitest.fn(), }; const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, errorHandlers, ); decoder.startEntity(entities.DecodingMode.Legacy); expect(decoder.write(":", 1)).toBe(-1); expect(decoder.end()).toBe(5); expect(callback).toHaveBeenCalledTimes(1); expect(callback).toHaveBeenCalledWith(0x3a, 5); expect( errorHandlers.missingSemicolonAfterCharacterReference, ).toHaveBeenCalledTimes(1); expect( errorHandlers.absenceOfDigitsInNumericCharacterReference, ).toHaveBeenCalledTimes(0); expect( errorHandlers.validateNumericCharacterReference, ).toHaveBeenCalledTimes(1); expect( errorHandlers.validateNumericCharacterReference, ).toHaveBeenCalledWith(0x3a); }); it("should produce an error for numeric entities without digits", () => { const errorHandlers = { missingSemicolonAfterCharacterReference: vitest.fn(), absenceOfDigitsInNumericCharacterReference: vitest.fn(), validateNumericCharacterReference: vitest.fn(), }; const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, errorHandlers, ); decoder.startEntity(entities.DecodingMode.Legacy); expect(decoder.write("&#", 1)).toBe(-1); expect(decoder.end()).toBe(0); expect(callback).toHaveBeenCalledTimes(0); expect( errorHandlers.missingSemicolonAfterCharacterReference, ).toHaveBeenCalledTimes(0); expect( errorHandlers.absenceOfDigitsInNumericCharacterReference, ).toHaveBeenCalledTimes(1); expect( errorHandlers.absenceOfDigitsInNumericCharacterReference, ).toHaveBeenCalledWith(2); expect( errorHandlers.validateNumericCharacterReference, ).toHaveBeenCalledTimes(0); }); it("should produce an error for hex entities without digits", () => { const errorHandlers = { missingSemicolonAfterCharacterReference: vitest.fn(), absenceOfDigitsInNumericCharacterReference: vitest.fn(), validateNumericCharacterReference: vitest.fn(), }; const callback = vitest.fn(); const decoder = new entities.EntityDecoder( entities.htmlDecodeTree, callback, errorHandlers, ); decoder.startEntity(entities.DecodingMode.Legacy); expect(decoder.write("&#x", 1)).toBe(-1); expect(decoder.end()).toBe(0); expect(callback).toHaveBeenCalledTimes(0); expect( errorHandlers.missingSemicolonAfterCharacterReference, ).toHaveBeenCalledTimes(0); expect( errorHandlers.absenceOfDigitsInNumericCharacterReference, ).toHaveBeenCalledTimes(1); expect( errorHandlers.validateNumericCharacterReference, ).toHaveBeenCalledTimes(0); }); }); });