feat: add the XMLNS_1_0 namespace

src/xmlchars.ts

@@ -211,3 +211,87 @@ export namespace XML_1_0 {
     }
   }
 }
+
+/**
+ * Character class utilities for XML NS 1.0.
+ */
+export namespace XMLNS_1_0 {
+
+  /**
+   * Third edition.
+   */
+  export namespace ED3 {
+    /**
+     * Regular expression fragments. These fragments are designed to be included
+     * inside square brackets in a regular expression.
+     */
+    export namespace fragments {
+      // tslint:disable-next-line:max-line-length
+      export const NC_NAME_START_CHAR = "A-Z_a-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD\u{10000}-\u{EFFFF}";
+
+      export const NC_NAME_CHAR =
+        `-${NC_NAME_START_CHAR}.0-9\u00B7\u0300-\u036F\u203F-\u2040`;
+    }
+
+    /**
+     * Regular expression. These correspond to the productions of the same name
+     * in the specification.
+     */
+    export namespace regexes {
+      export const NC_NAME_START_CHAR =
+        new RegExp(`^[${fragments.NC_NAME_START_CHAR}]$`, "u");
+
+      export const NC_NAME_CHAR =
+        new RegExp(`^[${fragments.NC_NAME_CHAR}]$`, "u");
+
+      export const NC_NAME =
+        new RegExp(
+          `^[${fragments.NC_NAME_START_CHAR}][${fragments.NC_NAME_CHAR}]*$`,
+          "u");
+    }
+
+    /**
+     * Determines whether a codepoint matches
+     * [[regexes.NC_NAME_START_CHAR]].
+     *
+     * @param c The code point.
+     *
+     * @returns ``true`` if the codepoint matches.
+     */
+    // tslint:disable-next-line:cyclomatic-complexity
+    export function isNCNameStartChar(c: number): boolean {
+      return ((c >= 0x41 && c <= 0x5A) ||
+              c === 0x5F ||
+              (c >= 0x61 && c <= 0x7A) ||
+              (c >= 0xC0 && c <= 0xD6) ||
+              (c >= 0xD8 && c <= 0xF6) ||
+              (c >= 0x00F8 && c <= 0x02FF) ||
+              (c >= 0x0370 && c <= 0x037D) ||
+              (c >= 0x037F && c <= 0x1FFF) ||
+              (c >= 0x200C && c <= 0x200D) ||
+              (c >= 0x2070 && c <= 0x218F) ||
+              (c >= 0x2C00 && c <= 0x2FEF) ||
+              (c >= 0x3001 && c <= 0xD7FF) ||
+              (c >= 0xF900 && c <= 0xFDCF) ||
+              (c >= 0xFDF0 && c <= 0xFFFD) ||
+              (c >= 0x10000 && c <= 0xEFFFF));
+    }
+
+    /**
+     * Determines whether a codepoint matches [[regexes.NC_NAME_CHAR]].
+     *
+     * @param c The code point.
+     *
+     * @returns ``true`` if the codepoint matches.
+     */
+    export function isNCNameChar(c: number): boolean {
+      return isNCNameStartChar(c) ||
+        (c === 0x2D ||
+         c === 0x2E ||
+         (c >= 0x30 && c <= 0x39) ||
+         c === 0x00B7 ||
+         (c >= 0x0300 && c <= 0x036F) ||
+         (c >= 0x203F && c <= 0x2040));
+    }
+  }
+}

test/xmlchars.spec.ts

@@ -1,6 +1,6 @@
 // tslint:disable-next-line:missing-jsdoc
 import { expect } from "chai";
-import { XML_1_0 } from "../src/xmlchars";
+import { XML_1_0, XMLNS_1_0 } from "../src/xmlchars";
 
 interface Fixture {
   name: string;
@@ -22,6 +22,11 @@ const poo: Fixture = {
   data: "\u{1F4A9}",
 };
 
+const colon: Fixture = {
+  name: "colon",
+  data: ":",
+};
+
 const space: Fixture = {
   name: "space",
   data: " ",
@@ -92,6 +97,7 @@ const ALL_FIXTURES = new Set([
   x,
   abc,
   poo,
+  colon,
   space,
   tab,
   newline,
@@ -111,9 +117,6 @@ interface Case {
   matching: Fixture[];
 }
 
-type ED4_REGEX_NAMES = keyof typeof XML_1_0.ED4.regexes;
-type ED5_REGEX_NAMES = keyof typeof XML_1_0.ED5.regexes;
-
 function makeTests(re: RegExp, testCase: Case): void {
   describe("matches", () => {
     for (const matchingCase of testCase.matching) {
@@ -172,26 +175,26 @@ function makeCodePointTestTests(codePointTest: (c: number) => boolean,
 describe("XML_1_0", () => {
   describe("ED5", () => {
     // tslint:disable-next-line:mocha-no-side-effect-code
-    const cases: Record<ED5_REGEX_NAMES, Case> = {
+    const cases: Record<keyof typeof XML_1_0.ED5.regexes, Case> = {
       CHAR: {
-        matching: [x, poo, space, tab, newline, cr, ideographic, combining,
-                   digit, extender],
+        matching: [x, poo, colon, space, tab, newline, cr, ideographic,
+                   combining, digit, extender],
       },
       S: {
         matching: [space, tab, newline, cr],
       },
       NAME_START_CHAR: {
-        matching: [x, ideographic, poo],
+        matching: [x, ideographic, poo, colon],
       },
       NAME_CHAR: {
-        matching: [x, ideographic, poo, combining, extender, digit],
+        matching: [x, ideographic, poo, colon, combining, extender, digit],
       },
       NAME: {
-        matching: [x, abc, ideographic, nameWithColon, poo],
+        matching: [x, abc, ideographic, colon, nameWithColon, poo],
       },
       NMTOKEN: {
-        matching: [x, abc, ideographic, nameWithColon, leadingDot, leadingDash,
-                   leadingDigit, combining, extender, digit, poo],
+        matching: [x, abc, ideographic, colon, nameWithColon, leadingDot,
+                   leadingDash, leadingDigit, combining, extender, digit, poo],
       },
       // tslint:disable-next-line:no-any
     } as any;
@@ -229,10 +232,10 @@ describe("XML_1_0", () => {
 
   describe("ED4.regexes", () => {
     // tslint:disable-next-line:mocha-no-side-effect-code
-    const cases: Record<ED4_REGEX_NAMES, Case> = {
+    const cases: Record<keyof typeof XML_1_0.ED4.regexes, Case> = {
       CHAR: {
-        matching: [x, poo, space, tab, newline, cr, ideographic, combining,
-                   digit, extender],
+        matching: [x, poo, colon, space, tab, newline, cr, ideographic,
+                   combining, digit, extender],
       },
       S: {
         matching: [space, tab, newline, cr],
@@ -256,14 +259,14 @@ describe("XML_1_0", () => {
         matching: [x, ideographic],
       },
       NAME_CHAR: {
-        matching: [x, ideographic, digit, extender, combining],
+        matching: [x, ideographic, colon, digit, extender, combining],
       },
       NAME: {
-        matching: [x, abc, ideographic, nameWithColon],
+        matching: [x, abc, ideographic, colon, nameWithColon],
       },
       NMTOKEN: {
-        matching: [x, abc, ideographic, nameWithColon, leadingDot, leadingDash,
-                   leadingDigit, combining, extender, digit],
+        matching: [x, abc, ideographic, colon, nameWithColon, leadingDot,
+                   leadingDash, leadingDigit, combining, extender, digit],
       },
       // tslint:disable-next-line:no-any
     } as any;
@@ -277,3 +280,42 @@ describe("XML_1_0", () => {
     }
   });
 });
+
+describe("XML_NS_1_0", () => {
+  describe("ED3", () => {
+    // tslint:disable-next-line:mocha-no-side-effect-code
+    const cases: Record<keyof typeof XMLNS_1_0.ED3.regexes, Case> = {
+      NC_NAME_START_CHAR: {
+        matching: [x, ideographic, poo],
+      },
+      NC_NAME_CHAR: {
+        matching: [x, ideographic, poo, combining, extender, digit],
+      },
+      NC_NAME: {
+        matching: [x, abc, ideographic, poo],
+      },
+      // tslint:disable-next-line:no-any
+    } as any;
+
+    describe(".regexes", () => {
+      // tslint:disable-next-line:mocha-no-side-effect-code
+      for (const name of (Object.keys(cases) as (keyof typeof cases)[])) {
+        describe(name, () => {
+          // tslint:disable-next-line:mocha-no-side-effect-code
+          makeTests(XMLNS_1_0.ED3.regexes[name], cases[name]);
+        });
+      }
+    });
+
+    describe(".isNCNameStartChar", () => {
+      // tslint:disable-next-line:mocha-no-side-effect-code
+      makeCodePointTestTests(XMLNS_1_0.ED3.isNCNameStartChar,
+                             cases.NC_NAME_START_CHAR);
+    });
+
+    describe(".isNCNameChar", () => {
+      // tslint:disable-next-line:mocha-no-side-effect-code
+      makeCodePointTestTests(XMLNS_1_0.ED3.isNCNameChar, cases.NC_NAME_CHAR);
+    });
+  });
+});