add encoding/hex module (#434)

encoding/hex.ts

@@ -0,0 +1,137 @@
+// Ported from Go
+// https://github.com/golang/go/blob/go1.12.5/src/encoding/hex/hex.go
+// Copyright 2009 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+// Copyright 2018-2019 the Deno authors. All rights reserved. MIT license.
+
+const hextable = new TextEncoder().encode("0123456789abcdef");
+
+export function errInvalidByte(byte: number): Error {
+  return new Error(
+    "encoding/hex: invalid byte: " +
+      new TextDecoder().decode(new Uint8Array([byte]))
+  );
+}
+
+export function errLength(): Error {
+  return new Error("encoding/hex: odd length hex string");
+}
+
+// fromHexChar converts a hex character into its value and a success flag.
+function fromHexChar(byte: number): [number, boolean] {
+  switch (true) {
+    case 48 <= byte && byte <= 57: // '0' <= byte && byte <= '9'
+      return [byte - 48, true];
+    case 97 <= byte && byte <= 102: // 'a' <= byte && byte <= 'f'
+      return [byte - 97 + 10, true];
+    case 65 <= byte && byte <= 70: // 'A' <= byte && byte <= 'F'
+      return [byte - 65 + 10, true];
+  }
+  return [0, false];
+}
+
+/**
+ * EncodedLen returns the length of an encoding of n source bytes. Specifically, it returns n * 2.
+ * @param n
+ */
+export function encodedLen(n: number): number {
+  return n * 2;
+}
+
+/**
+ * Encode encodes `src` into `encodedLen(src.length)` bytes of `dst`.
+ * As a convenience, it returns the number of bytes written to `dst`
+ * but this value is always `encodedLen(src.length)`.
+ * Encode implements hexadecimal encoding.
+ * @param dst
+ * @param src
+ */
+export function encode(dst: Uint8Array, src: Uint8Array): number {
+  const srcLength = encodedLen(src.length);
+  if (dst.length !== srcLength) {
+    throw new Error("Out of index.");
+  }
+  for (let i = 0; i < src.length; i++) {
+    const v = src[i];
+    dst[i * 2] = hextable[v >> 4];
+    dst[i * 2 + 1] = hextable[v & 0x0f];
+  }
+  return srcLength;
+}
+
+/**
+ * EncodeToString returns the hexadecimal encoding of `src`.
+ * @param src
+ */
+export function encodeToString(src: Uint8Array): string {
+  const dest = new Uint8Array(encodedLen(src.length));
+  encode(dest, src);
+  return new TextDecoder().decode(dest);
+}
+
+/**
+ * Decode decodes `src` into `decodedLen(src.length)` bytes
+ * returning the actual number of bytes written to `dst`.
+ * Decode expects that `src` contains only hexadecimal characters and that `src` has even length.
+ * If the input is malformed, Decode returns the number of bytes decoded before the error.
+ * @param dst
+ * @param src
+ */
+export function decode(
+  dst: Uint8Array,
+  src: Uint8Array
+): [number, Error | void] {
+  var i = 0;
+  for (; i < Math.floor(src.length / 2); i++) {
+    const [a, aOK] = fromHexChar(src[i * 2]);
+    if (!aOK) {
+      return [i, errInvalidByte(src[i * 2])];
+    }
+    const [b, bOK] = fromHexChar(src[i * 2 + 1]);
+    if (!bOK) {
+      return [i, errInvalidByte(src[i * 2 + 1])];
+    }
+
+    dst[i] = (a << 4) | b;
+  }
+
+  if (src.length % 2 == 1) {
+    // Check for invalid char before reporting bad length,
+    // since the invalid char (if present) is an earlier problem.
+    const [, ok] = fromHexChar(src[i * 2]);
+    if (!ok) {
+      return [i, errInvalidByte(src[i * 2])];
+    }
+    return [i, errLength()];
+  }
+
+  return [i, undefined];
+}
+
+/**
+ * DecodedLen returns the length of a decoding of `x` source bytes. Specifically, it returns `x / 2`.
+ * @param x
+ */
+export function decodedLen(x: number): number {
+  return Math.floor(x / 2);
+}
+
+/**
+ * DecodeString returns the bytes represented by the hexadecimal string `s`.
+ * DecodeString expects that src contains only hexadecimal characters and that src has even length.
+ * If the input is malformed, DecodeString will throws an error.
+ * @param s the `string` need to decode to `Uint8Array`
+ */
+export function decodeString(s: string): Uint8Array {
+  const src = new TextEncoder().encode(s);
+  // We can use the source slice itself as the destination
+  // because the decode loop increments by one and then the 'seen' byte is not used anymore.
+  const [n, err] = decode(src, src);
+
+  if (err) {
+    throw err;
+  }
+
+  return src.slice(0, n);
+}

encoding/hex_test.ts

@@ -0,0 +1,182 @@
+// Ported from Go
+// https://github.com/golang/go/blob/go1.12.5/src/encoding/hex/hex.go
+// Copyright 2009 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+// Copyright 2018-2019 the Deno authors. All rights reserved. MIT license.
+import { test, runIfMain } from "../testing/mod.ts";
+import { assertEquals, assertThrows } from "../testing/asserts.ts";
+
+import {
+  encodedLen,
+  encode,
+  encodeToString,
+  decodedLen,
+  decode,
+  decodeString,
+  errLength,
+  errInvalidByte
+} from "./hex.ts";
+
+function toByte(s: string): number {
+  return new TextEncoder().encode(s)[0];
+}
+
+const testCases = [
+  // encoded(hex) / decoded(Uint8Array)
+  ["", []],
+  ["0001020304050607", [0, 1, 2, 3, 4, 5, 6, 7]],
+  ["08090a0b0c0d0e0f", [8, 9, 10, 11, 12, 13, 14, 15]],
+  ["f0f1f2f3f4f5f6f7", [0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7]],
+  ["f8f9fafbfcfdfeff", [0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff]],
+  ["67", Array.from(new TextEncoder().encode("g"))],
+  ["e3a1", [0xe3, 0xa1]]
+];
+
+const errCases = [
+  // encoded(hex) / error
+  ["", "", undefined],
+  ["0", "", errLength()],
+  ["zd4aa", "", errInvalidByte(toByte("z"))],
+  ["d4aaz", "\xd4\xaa", errInvalidByte(toByte("z"))],
+  ["30313", "01", errLength()],
+  ["0g", "", errInvalidByte(new TextEncoder().encode("g")[0])],
+  ["00gg", "\x00", errInvalidByte(new TextEncoder().encode("g")[0])],
+  ["0\x01", "", errInvalidByte(new TextEncoder().encode("\x01")[0])],
+  ["ffeed", "\xff\xee", errLength()]
+];
+
+test({
+  name: "[encoding.hex] encodedLen",
+  fn(): void {
+    assertEquals(encodedLen(0), 0);
+    assertEquals(encodedLen(1), 2);
+    assertEquals(encodedLen(2), 4);
+    assertEquals(encodedLen(3), 6);
+    assertEquals(encodedLen(4), 8);
+  }
+});
+
+test({
+  name: "[encoding.hex] encode",
+  fn(): void {
+    {
+      const srcStr = "abc";
+      const src = new TextEncoder().encode(srcStr);
+      const dest = new Uint8Array(encodedLen(src.length));
+      const int = encode(dest, src);
+      assertEquals(src, new Uint8Array([97, 98, 99]));
+      assertEquals(int, 6);
+    }
+
+    {
+      const srcStr = "abc";
+      const src = new TextEncoder().encode(srcStr);
+      const dest = new Uint8Array(2); // out of index
+      assertThrows(
+        (): void => {
+          encode(dest, src);
+        },
+        Error,
+        "Out of index."
+      );
+    }
+
+    for (const [enc, dec] of testCases) {
+      const dest = new Uint8Array(encodedLen(dec.length));
+      const src = new Uint8Array(dec as number[]);
+      const n = encode(dest, src);
+      assertEquals(dest.length, n);
+      assertEquals(new TextDecoder().decode(dest), enc);
+    }
+  }
+});
+
+test({
+  name: "[encoding.hex] encodeToString",
+  fn(): void {
+    for (const [enc, dec] of testCases) {
+      assertEquals(encodeToString(new Uint8Array(dec as number[])), enc);
+    }
+  }
+});
+
+test({
+  name: "[encoding.hex] decodedLen",
+  fn(): void {
+    assertEquals(decodedLen(0), 0);
+    assertEquals(decodedLen(2), 1);
+    assertEquals(decodedLen(4), 2);
+    assertEquals(decodedLen(6), 3);
+    assertEquals(decodedLen(8), 4);
+  }
+});
+
+test({
+  name: "[encoding.hex] decode",
+  fn(): void {
+    // Case for decoding uppercase hex characters, since
+    // Encode always uses lowercase.
+    const extraTestcase = [
+      ["F8F9FAFBFCFDFEFF", [0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff]]
+    ];
+
+    const cases = testCases.concat(extraTestcase);
+
+    for (const [enc, dec] of cases) {
+      const dest = new Uint8Array(decodedLen(enc.length));
+      const src = new TextEncoder().encode(enc as string);
+      const [, err] = decode(dest, src);
+      assertEquals(err, undefined);
+      assertEquals(Array.from(dest), Array.from(dec as number[]));
+    }
+  }
+});
+
+test({
+  name: "[encoding.hex] decodeString",
+  fn(): void {
+    for (const [enc, dec] of testCases) {
+      const dst = decodeString(enc as string);
+
+      assertEquals(dec, Array.from(dst));
+    }
+  }
+});
+
+test({
+  name: "[encoding.hex] decode error",
+  fn(): void {
+    for (const [input, output, expectedErr] of errCases) {
+      const out = new Uint8Array((input as string).length + 10);
+      const [n, err] = decode(out, new TextEncoder().encode(input as string));
+      assertEquals(
+        new TextDecoder("ascii").decode(out.slice(0, n)),
+        output as string
+      );
+      assertEquals(err, expectedErr);
+    }
+  }
+});
+
+test({
+  name: "[encoding.hex] decodeString error",
+  fn(): void {
+    for (const [input, output, expectedErr] of errCases) {
+      if (expectedErr) {
+        assertThrows(
+          (): void => {
+            decodeString(input as string);
+          },
+          Error,
+          (expectedErr as Error).message
+        );
+      } else {
+        const out = decodeString(input as string);
+        assertEquals(new TextDecoder("ascii").decode(out), output as string);
+      }
+    }
+  }
+});
+
+runIfMain(import.meta);

encoding/test.ts

@@ -1,3 +1,4 @@
 // Copyright 2018-2019 the Deno authors. All rights reserved. MIT license.
+import "./hex_test.ts";
 import "./toml_test.ts";
 import "./csv_test.ts";

test.ts

@@ -22,6 +22,7 @@ import "./testing/test.ts";
 import "./textproto/test.ts";
 import "./util/test.ts";
 import "./ws/test.ts";
+import "./encoding/test.ts";
 
 import { xrun } from "./prettier/util.ts";
 import { red, green } from "./colors/mod.ts";