1

I want to replace rare words with _RARE_ in a JSON tree using JAVA.

My rareWords list contains

late  
populate
convicts

So for JSON below 

["S", ["PP", ["ADP", "In"], ["NP", ["DET", "the"], ["NP", ["ADJ", "late"], ["NOUN", "1700<s"]]]], ["S", ["NP", ["ADJ", "British"], ["NOUN", "convicts"]], ["S", ["VP", ["VERB", "were"], ["VP", ["VERB", "used"], ["S+VP", ["PRT", "to"], ["VP", ["VERB", "populate"], ["WHNP", ["DET", "which"], ["NOUN", "colony"]]]]]], [".", "?"]]]]

I should get

["S", ["PP", ["ADP", "In"], ["NP", ["DET", "the"], ["NP", ["ADJ", "_RARE_"], ["NOUN", "1700<s"]]]], ["S", ["NP", ["ADJ", "British"], ["NOUN", "_RARE_"]], ["S", ["VP", ["VERB", "were"], ["VP", ["VERB", "used"], ["S+VP", ["PRT", "to"], ["VP", ["VERB", "populate"], ["WHNP", ["DET", "which"], ["NOUN", "colony"]]]]]], [".", "?"]]]]

Notice how

["ADJ","late"]

was replaced by

["ADJ","_RARE_"]

My code so far is like below:

I recursively iterate over the tree and as soon as rare word is found, I create a new JSON array and try to replace the existing tree's node with it. See // this Doesn't work in below, that is where I got stuck. The tree remains unchanged outside of this function.

public static void traverseTreeAndReplaceWithRare(JsonArray tree){   

        //System.out.println(tree.getAsJsonArray()); 

        for (int x = 0; x < tree.getAsJsonArray().size(); x++)
        {
            if(!tree.get(x).isJsonArray())
            {
                if(tree.size()==2)
                {   
                //beware it will get here twice for same word
                 String word= tree.get(1).toString();  
                 word=word.replaceAll("\"", ""); // removing double quotes

                 if(rareWords.contains(word))
                 {
                 JsonParser parser = new JsonParser();                   

                             //This works perfectly 
                             System.out.println("Orig:"+tree);
                 JsonElement jsonElement = parser.parse("["+tree.get(0)+","+"_RARE_"+"]");

                 JsonArray newRareArray = jsonElement.getAsJsonArray();

                             //This works perfectly 
                             System.out.println("New:"+newRareArray);

                 tree=newRareArray; // this Doesn't work
                 }                 

                }               
                continue;   
            }
            traverseTreeAndReplaceWithRare(tree.get(x).getAsJsonArray());
        }
    }

code for calling above, I use google's gson

JsonParser parser = new JsonParser();
JsonElement jsonElement = parser.parse(strJSON);
JsonArray tree = jsonElement.getAsJsonArray();
4

1 回答 1

6

这是 C++ 中的一种直接方法：

#include <fstream>
#include "JSON.hpp"
#include <boost/algorithm/string/regex.hpp>
#include <boost/range/adaptors.hpp>
#include <boost/phoenix.hpp>

static std::vector<std::wstring> readRareWordList()
{
    std::vector<std::wstring> result;

    std::wifstream ifs("testcases/rarewords.txt");
    std::wstring line;
    while (std::getline(ifs, line))
        result.push_back(std::move(line));

    return result;
}

struct RareWords : boost::static_visitor<> {

    /////////////////////////////////////
    // do nothing by default
    template <typename T> void operator()(T&&) const { /* leave all other things unchanged */ }

    /////////////////////////////////////
    // recurse arrays and objects
    void operator()(JSON::Object& obj) const { 
        for(auto& v : obj.values) {
            //RareWords::operator()(v.first); /* to replace in field names (?!) */
            boost::apply_visitor(*this, v.second);
        }
    }

    void operator()(JSON::Array& arr) const {
        int i = 0;
        for(auto& v : arr.values) {
            if (i++) // skip the first element in all arrays
                boost::apply_visitor(*this, v);
        }
    }

    /////////////////////////////////////
    // do replacements on strings
    void operator()(JSON::String& s) const {
        using namespace boost;

        const static std::vector<std::wstring> rareWords = readRareWordList();
        const static std::wstring replacement = L"__RARE__";

        for (auto&& word : rareWords)
            if (word == s.value)
                s.value = replacement;
    }
};

int main()
{
    auto document = JSON::readFrom(std::ifstream("testcases/test3.json"));

    boost::apply_visitor(RareWords(), document);

    std::cout << document;
}

这假设您想要对所有字符串值进行替换，并且只匹配整个字符串。您可以通过更改正则表达式或正则表达式标志轻松地使这种情况不区分大小写、匹配字符串中的单词等。根据评论稍作调整。

包含 JSON.hpp/cpp 的完整代码在这里：https ://github.com/sehe/spirit-v2-json/tree/16093940

于 2013-04-19T02:08:50.670 回答