zapdb-kv/src/packages/orderable-varint/index.js

"use strict";

const log2 = require("@extra-bigint/log2"); // TODO: Do we not need this anymore?
const assert = require("assert");

const countBits = require("../../storage-encoder/bitwise/count-bits");
const generateMask = require("../../storage-encoder/bitwise/generate-mask");
const invertBits = require("../../storage-encoder/bitwise/invert");
const invertBits1Byte = require("../../storage-encoder/bitwise/invert-1byte");
const truncateLeftBits = require("../../storage-encoder/bitwise/truncate-left-bits");
const bigintBuffer = require("../../storage-encoder/bigint/buffer");
const absBigInt = require("../../storage-encoder/bigint/abs");

function isNegativeHeaderByte(value) {
	return (value & 128) === 0;
}

function calculateEncodedSize(value) {
	let valueBitsNeeded = countBits(value);
	let valueBytesNeeded = Math.ceil(valueBitsNeeded / 8);
	let sizeBitsNeeded = valueBytesNeeded + 1;

	// We loop here because the addition of a header can actually bump up the needed amount of bits in some cases. It should never be needed more than 3 times, though.
	// FIXME: Add a limit and an error when it's exceeded
	while (true) {
		let totalBitsNeeded = valueBitsNeeded + sizeBitsNeeded;
		let totalBytesNeeded = Math.ceil(totalBitsNeeded / 8);

		if (sizeBitsNeeded === totalBytesNeeded + 1) {
			return {
				totalBytes: BigInt(totalBytesNeeded),
				valueBits: BigInt(valueBitsNeeded)
			};
		} else {
			sizeBitsNeeded = totalBytesNeeded + 1;
		}
	}
}

function readByteCount(value) {
	if (value < 128) {
		// 0xxxxxxx, this should never happen in the first byte!
		return 0;
	} else if (value & 128 && value < 192) {
		// 10xxxxxx
		return 1;
	} else if (value & 192 && value < 224) {
		// 110xxxxx
		return 2;
	} else if (value & 224 && value < 240) {
		// 1110xxxx
		return 3;
	} else if (value & 240 && value < 248) {
		// 11110xxx
		return 4;
	} else if (value & 248 && value < 252) {
		// 111110xx
		return 5;
	} else if (value & 252 && value < 254) {
		// 1111110x
		return 6;
	} else if (value === 254) {
		// 11111110
		return 7;
	} else {
		// 11111111
		return 8;
	}
}

function readBytes(bytes) {
	assert(bytes.length > 0);
	let negative = isNegativeHeaderByte(bytes[0]);
	let headerRead = false;
	let i = 0;
	let totalByteCount = 0;
	let value = 0n;

	while (!headerRead || (i < totalByteCount)) {
		let byte = bytes[i];

		// If the first byte has a negative sign bit, invert the bits so that we can use the same byte count parsing logic for both negative and positive values
		let normalizedByte = (negative)
			? invertBits1Byte(byte)
			: byte;

		let byteValue;

		if (!headerRead) {
			let byteCount = readByteCount(normalizedByte);
			totalByteCount += byteCount;

			if (byteCount === 8) {
				// Continue reading header bytes
				continue;
			} else {
				if (totalByteCount === 0) {
					throw new Error(`Found a 0-byte value, this should never happen`);
				}

				headerRead = true;
				byteValue = truncateLeftBits(normalizedByte, byteCount + 1); // truncate the byteCount bits and the terminator bit
			}
		} else {
			value <<= 8n;
			byteValue = normalizedByte;
		}

		if (negative) {
			value -= BigInt(byteValue);
		} else {
			value += BigInt(byteValue);
		}

		i++;
	}

	if (!headerRead) {
		throw new Error(`Reached end of value while reading header`);
	}

	return {
		value: value,
		bytesRead: totalByteCount
	};
}

module.exports = {
	encode: function encodeOrderableVarint(value) {
		let valueN = BigInt(value);
		let absoluteValue = absBigInt(valueN);

		// NOTE: totalBytes represents both the total size in bytes of the encoded value, *and* the amount of header bits (minus the terminator)
		let { totalBytes, valueBits } = calculateEncodedSize(absoluteValue);
		let headerBits = generateMask(totalBytes);
		
		// Since the terminator bit is already accounted for in the size calculation, we don't need to do anything special for it here - it'll be void space between the header and the value by definition
		let header = headerBits << (totalBytes * 7n);
		let encodedValue = header + absoluteValue;

		if (valueN < 0) {
			encodedValue = invertBits(encodedValue);
		}

		return bigintBuffer.toBuffer(encodedValue);
	},
	decode: function decodeOrderableVarint(bytes) {
		return readBytes(bytes);
	}
};