c++ - 使用 C++ 和 BOOST 读取 JSON 文件

Question

HTTP 服务器向我发送一个 JSON 响应(字符串)，如下所示:

{
    "folders" :
    [{
            "id" : 109,
            "parent_id" : 110,
            "path" : "\/1\/105\/110\/"
        },
        {
            "id" : 110,
            "parent_id" : 105,
            "path" : "\/1\/105\/"
        }
    ],

    "files" :
    [{
            "id" : 26,
            "parent_id" : 105,
            "name" : "picture.png",
            "hash" : "md5_hash",
            "path" : "\/1\/105\/"
        },
        {
            "id" : 25,
            "parent_id" : 110,
            "name" : "another_picture.jpg",
            "hash" : "md5_hash",
            "path" : "\/1\/105\/110\/"
        }
    ]
}

我想将这个“远程文件夹树”与本地文件夹树(例如包含本地文件位置的字符串 vector )进行比较，所以我想在(字符串， vector ( map(string, string) ) ) (我不知道这是否可能)。

我正在开发一种在本地文件夹和远程文件夹之间同步文件的工具，因此我使用 boost 来列出本地文件夹，我想将本地列表与远程列表(JSON 响应)进行比较生成操作(下载本地文件夹中不存在的丢失文件，上传远程文件夹中不存在的文件)。

我在另一个问题上发现了这个功能:

void print(boost::property_tree::ptree const& pt)
{
    using boost::property_tree::ptree;
    ptree::const_iterator end = pt.end();
    for (ptree::const_iterator it = pt.begin(); it != end; ++it)
    {
        std::cout << it->first << ": " << it->second.get_value<std::string>() << std::endl;
        print(it->second);
    }
}

我成功打印了这样的东西:

folders:
:
id: 109
parent_id: 110
name: 2011_pictures
:
id: 110
parent_id: 105
name: Aminos
files:
id: 26
parent_id: 105
name: logo.png
:
id: 5
parent_id: 109
name: me.jpg

我想知道是否可以用这个结果生成 map<string, vector <map<string,string> > > ，它将有 2 个键:“文件夹”和"file"，通过这 2 个键，我们可以访问包含每个对象(文件或文件夹)信息的映射类型 vector 。如果这是可行的，它将降低任务的复杂性(比较两个文件夹列表)

示例:T["folder"][0]["id"] 将返回“109”； T["files"][0]["name"] 会返回 "logo.png"

更新:这个问题很老，但我想给出一个建议:只要你想在 C++ 下处理 Json，就使用 RAPIDJSON。

Answer 1

因为其他答案中的数据结构was deemed "very complex"目标数据结构是suggested to be :

struct Data {
    struct Folder { int id, parent_id; std::string path; };
    struct File   { int id, parent_id; std::string path, name, md5_hash; };

    using Folders = std::vector<Folder>;
    using Files   = std::vector<File>;

    Folders folders;
    Files   files;
};

我最终编写了从通用“JSON”到该数据结构的转换(参见其他答案: Reading JSON file with C++ and BOOST )。

但是，如果我们“跳过中间人”并将 JSON 专门解析为显示的 Data 结构，OP 可能会更高兴。这“简化”了语法，使其仅针对此类文档:

start    = '{' >> 
           (folders_ >> commasep) ^
           (files_ >> commasep)
         >> '}';

folders_ = prop_key(+"folders") >> '[' >> -(folder_ % ',') >> ']';
files_   = prop_key(+"files")   >> '[' >> -(file_   % ',') >> ']';

folder_  = '{' >> (
                (prop_key(+"id")        >> int_  >> commasep) ^
                (prop_key(+"parent_id") >> int_  >> commasep) ^
                (prop_key(+"path")      >> text_ >> commasep)
            ) >> '}';
file_    = '{' >> (
                (prop_key(+"id")        >> int_  >> commasep) ^
                (prop_key(+"parent_id") >> int_  >> commasep) ^
                (prop_key(+"path")      >> text_ >> commasep) ^
                (prop_key(+"name")      >> text_ >> commasep) ^
                (prop_key(+"hash")      >> text_ >> commasep)
            ) >> '}';

prop_key = lexeme ['"' >> lazy(_r1) >> '"'] >> ':';
commasep = &char_('}') | ',';

这个语法允许

• 无意义的空格，
• 对象内属性的重新排序
• 和省略的对象属性

好处:

• 早期检查属性值类型
• 缩短编译时间
• 确实减少了代码:减少了 37 个 LoC(不包括约 22% 的示例 JSON 行)

That last benefit has a flip side: if ever you want to read slightly different JSON, now you need to muck with the grammar instead of just writing a different extraction/transform. At 37 lines of code, my preference is with the other answer but I'll leave it to you to decide.

下面是直接使用该语法的同一个演示程序:

Live On Coliru

//#define BOOST_SPIRIT_DEBUG
#include <boost/fusion/adapted.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>

namespace qi = boost::spirit::qi;

static std::string const sample = R"(
    {
        "folders" :
        [{
                "id" : 109,
                "parent_id" : 110,
                "path" : "\/1\/105\/110\/"
            },
            {
                "id" : 110,
                "parent_id" : 105,
                "path" : "\/1\/105\/"
            }
        ],

        "files" :
        [{
                "id" : 26,
                "parent_id" : 105,
                "name" : "picture.png",
                "hash" : "md5_hash",
                "path" : "\/1\/105\/"
            },
            {
                "id" : 25,
                "parent_id" : 110,
                "name" : "another_picture.jpg",
                "hash" : "md5_hash",
                "path" : "\/1\/105\/110\/"
            }
        ]
    })";

struct Data {
    struct Folder { int id, parent_id; std::string path; };
    struct File   { int id, parent_id; std::string path, name, md5_hash; };

    using Folders = std::vector<Folder>;
    using Files   = std::vector<File>;

    Folders folders;
    Files   files;
};

BOOST_FUSION_ADAPT_STRUCT(Data::Folder, (int,id)(int,parent_id)(std::string,path))
BOOST_FUSION_ADAPT_STRUCT(Data::File,   (int,id)(int,parent_id)(std::string,path)(std::string,name)(std::string,md5_hash))
BOOST_FUSION_ADAPT_STRUCT(Data,         (Data::Folders,folders)(Data::Files,files))

namespace folder_info { // adhoc JSON parser

    template <typename It, typename Skipper = qi::space_type>
    struct grammar : qi::grammar<It, Data(), Skipper>
    {
        grammar() : grammar::base_type(start) {
            using namespace qi;

            start    = '{' >> 
                       (folders_ >> commasep) ^
                       (files_ >> commasep)
                     >> '}';

            folders_ = prop_key(+"folders") >> '[' >> -(folder_ % ',') >> ']';
            files_   = prop_key(+"files")   >> '[' >> -(file_   % ',') >> ']';

            folder_  = '{' >> (
                            (prop_key(+"id")        >> int_  >> commasep) ^
                            (prop_key(+"parent_id") >> int_  >> commasep) ^
                            (prop_key(+"path")      >> text_ >> commasep)
                        ) >> '}';
            file_    = '{' >> (
                            (prop_key(+"id")        >> int_  >> commasep) ^
                            (prop_key(+"parent_id") >> int_  >> commasep) ^
                            (prop_key(+"path")      >> text_ >> commasep) ^
                            (prop_key(+"name")      >> text_ >> commasep) ^
                            (prop_key(+"hash")      >> text_ >> commasep)
                        ) >> '}';

            prop_key = lexeme ['"' >> lazy(_r1) >> '"'] >> ':';
            commasep = &char_('}') | ',';

            ////////////////////////////////////////
            // Bonus: properly decoding the string:
            text_   = '"' >> *ch_ >> '"';

            ch_ = +(
                    ~char_("\"\\")) [ _val += _1 ] |
                       qi::lit("\x5C") >> (               // \ (reverse solidus)
                       qi::lit("\x22") [ _val += '"'  ] | // "    quotation mark  U+0022
                       qi::lit("\x5C") [ _val += '\\' ] | // \    reverse solidus U+005C
                       qi::lit("\x2F") [ _val += '/'  ] | // /    solidus         U+002F
                       qi::lit("\x62") [ _val += '\b' ] | // b    backspace       U+0008
                       qi::lit("\x66") [ _val += '\f' ] | // f    form feed       U+000C
                       qi::lit("\x6E") [ _val += '\n' ] | // n    line feed       U+000A
                       qi::lit("\x72") [ _val += '\r' ] | // r    carriage return U+000D
                       qi::lit("\x74") [ _val += '\t' ] | // t    tab             U+0009
                       qi::lit("\x75")                    // uXXXX                U+XXXX
                            >> _4HEXDIG [ append_utf8(qi::_val, qi::_1) ]
                    );

            BOOST_SPIRIT_DEBUG_NODES((files_)(folders_)(file_)(folder_)(start)(text_))
        }
    private:
        qi::rule<It, Data(),            Skipper> start;
        qi::rule<It, Data::Files(),     Skipper> files_;
        qi::rule<It, Data::Folders(),   Skipper> folders_;
        qi::rule<It, Data::File(),      Skipper> file_;
        qi::rule<It, Data::Folder(),    Skipper> folder_;
        qi::rule<It, void(const char*), Skipper> prop_key;

        qi::rule<It, std::string()> text_, ch_;
        qi::rule<It> commasep;

        struct append_utf8_f {
            template <typename...> struct result { typedef void type; };
            template <typename String, typename Codepoint>
            void operator()(String& to, Codepoint codepoint) const {
                auto out = std::back_inserter(to);
                boost::utf8_output_iterator<decltype(out)> convert(out);
                *convert++ = codepoint;
            }
        };
        boost::phoenix::function<append_utf8_f> append_utf8;
        qi::uint_parser<uint32_t, 16, 4, 4> _4HEXDIG;
    };

    template <typename Range, typename It = typename boost::range_iterator<Range const>::type>
    Data parse(Range const& input) {
        grammar<It> g;

        It first(boost::begin(input)), last(boost::end(input));
        Data parsed;
        bool ok = qi::phrase_parse(first, last, g, qi::space, parsed);

        if (ok && (first == last))
            return parsed;

        throw std::runtime_error("Remaining unparsed: '" + std::string(first, last) + "'");
    }
}

int main()
{
    auto parsed = folder_info::parse(sample);

    for (auto& e : parsed.folders) 
        std::cout << "folder:\t" << e.id << "\t" << e.path << "\n";
    for (auto& e : parsed.files) 
        std::cout << "file:\t"   << e.id << "\t" << e.path << "\t" << e.name << "\n";
}

输出:

folder: 109 /1/105/110/
folder: 110 /1/105/
file:   26  /1/105/ picture.png
file:   25  /1/105/110/ another_picture.jpg