如何转义不可打印字符？Zig语言TLV编码问题求助

问题描述 #

我用Zig编写了TLV编码代码，但运行后长度字段是不可打印的二进制字节（比如\x15对应数值21），而非预期的十进制字符串形式（比如长度3就写03）。

原代码 #

const std = @import("std");

fn getTLVForValue(writer: anytype, tagNum: []const u8, tagValue: []const u8) !void {
    _ = try writer.write(tagNum);;
    _ = try writer.writeByte(@intCast(tagValue.len));
    _ = try writer.write(tagValue);
}

pub fn main() !void {
    var arena = std.heap.ArenaAllocator.init(std.heap.page_allocator);
    const allocator = arena.allocator();
    var qrCodeBuf = std.ArrayList(u8).init(allocator);
    defer qrCodeBuf.deinit();
    const writer = qrCodeBuf.writer();

    //1. Seller Name
    try getTLVForValue(writer, "01", "Bobs Basement Records");

    //2. VAT Registration
    try getTLVForValue(writer, "02", "312345678901233");

    //3. Time stamp
    try getTLVForValue(writer, "03", "12-12-2023");

    //4. tax Total
    try getTLVForValue(writer, "04", "1000");

    //5. Vat Total
    try getTLVForValue(writer, "05", "115");

    //6. Hashed XML
    try getTLVForValue(writer, "06", "dsds");

    //7. key
    try getTLVForValue(writer, "07", "125");

    //8. Signature
    try getTLVForValue(writer, "08", "dsfsd");

    std.debug.print("{any}\n", .{qrCodeBuf.items});

    std.debug.print("Hex string: {s}\n", .{std.fmt.fmtSliceHexUpper(qrCodeBuf.items)});

    const output_buffer = try allocator.alloc(u8, std.base64.standard.Encoder.calcSize(qrCodeBuf.items.len));
    defer allocator.free(output_buffer);
    const data = std.base64.standard.Encoder.encode(output_buffer, qrCodeBuf.items);
    std.debug.print("{s}\n", .{data});

    const decode_buf = try allocator.alloc(u8, try std.base64.standard.Decoder.calcSizeForSlice(data));
    try std.base64.standard.Decoder.decode(decode_buf, data);
    std.debug.print("{s}\n", .{decode_buf});
    std.debug.print("{}\n", .{std.zig.fmtEscapes(decode_buf)});

    try std.testing.expectEqualStrings(qrCodeBuf.items, decode_buf);
}

当前问题输出 #

01\x15Bobs Basement Records02\x0f31234567890123303\n12-12-202304\x04100005\x0311506\x04dsds07\x0312508\x05dsfsd

需求 #

生成0103xxxx格式的TLV数据：标签（字符串）+ 十进制字符串形式的长度 + 值，比如长度为3时，长度字段写03而非二进制字节0x03。

解决方案 #

问题核心是原代码直接写入了长度的二进制字节值，我们需要改为写入长度的十进制字符串表示。只需修改getTLVForValue函数，用writer.print替代writeByte，将长度格式化为字符串写入即可。

修改后的代码 #

const std = @import("std");

fn getTLVForValue(writer: anytype, tagNum: []const u8, tagValue: []const u8) !void {
    _ = try writer.write(tagNum);
    // 将长度格式化为两位十进制字符串，不足补0；若需可变位数，改用{d}即可
    try writer.print("{d:0>2}", .{tagValue.len});
    _ = try writer.write(tagValue);
}

pub fn main() !void {
    var arena = std.heap.ArenaAllocator.init(std.heap.page_allocator);
    defer arena.deinit();
    const allocator = arena.allocator();
    var qrCodeBuf = std.ArrayList(u8).init(allocator);
    defer qrCodeBuf.deinit();
    const writer = qrCodeBuf.writer();

    //1. Seller Name
    try getTLVForValue(writer, "01", "Bobs Basement Records");

    //2. VAT Registration
    try getTLVForValue(writer, "02", "312345678901233");

    //3. Time stamp
    try getTLVForValue(writer, "03", "12-12-2023");

    //4. tax Total
    try getTLVForValue(writer, "04", "1000");

    //5. Vat Total
    try getTLVForValue(writer, "05", "115");

    //6. Hashed XML
    try getTLVForValue(writer, "06", "dsds");

    //7. key
    try getTLVForValue(writer, "07", "125");

    //8. Signature
    try getTLVForValue(writer, "08", "dsfsd");

    std.debug.print("{s}\n", .{qrCodeBuf.items});
    std.debug.print("Hex string: {s}\n", .{std.fmt.fmtSliceHexUpper(qrCodeBuf.items)});

    const output_buffer = try allocator.alloc(u8, std.base64.standard.Encoder.calcSize(qrCodeBuf.items.len));
    defer allocator.free(output_buffer);
    const data = std.base64.standard.Encoder.encode(output_buffer, qrCodeBuf.items);
    std.debug.print("{s}\n", .{data});

    const decode_buf = try allocator.alloc(u8, try std.base64.standard.Decoder.calcSizeForSlice(data));
    defer allocator.free(decode_buf);
    try std.base64.standard.Decoder.decode(decode_buf, data);
    std.debug.print("{s}\n", .{decode_buf});

    try std.testing.expectEqualStrings(qrCodeBuf.items, decode_buf);
}

关键改动说明 #

1. 替换长度写入逻辑：将writeByte写入二进制字节的操作，改为用writer.print("{d:0>2}", .{tagValue.len})写入格式化后的十进制字符串。
   • {d:0>2}表示将长度转为十进制整数，固定占两位，不足时左侧补0；如果你的场景允许长度为可变位数（比如长度100写100），可以直接用{d}作为格式化指令。

修改后输出示例 #

0121Bobs Basement Records0215312345678901233031012-12-20230404100005031150604dsds07031250805dsfsd

此时长度字段均为可读的十进制字符串，完全符合0103xxxx的格式要求。

内容的提问来源于stack exchange，提问作者Hasan A Yousef