如何解析R中的嵌套键值对

我试图解析一个日志文件，其中包含键值对形式的结构

log <-  c("name:praveen,age:23,place:UP,address:,dob:, site: {site_name:something , site_url: http://something.com, description:}")  

请帮我解析这个文件谢谢

我已经更新了实际的日志文件格式

{
    "username": "lavita",
    "host": "10.105.22.32",
    "event_source": "server",
    "event_type": "/courses/IITB/CS101/2014_T1/xblock/i4x:;_;_IITB;_CS101;_video;_d333fa637a074b41996dc2fd5e675818/handler/xmodule_handler/save_user_state",
    "context": {
        "course_id": "IITB/CS101/2014_T1",
        "course_user_tags": {},
        "user_id": 42,
        "org_id": "IITB"
    },
    "time": "2014-06-20T05:49:10.468638+00:00",
    "ip": "127.0.0.1",
    "event": "{\"POST\": {\"saved_video_position\": [\"00:02:10\"]}, \"GET\": {}}",
    "agent": "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:18.0) Gecko/20100101 Firefox/18.0",
    "page": null
}

{
    "username": "raeha",
    "host": "10.105.22.32",
    "event_source": "server",
    "event_type": "problem_check",
    "context": {
        "course_id": "IITB/CS101/2014_T1",
        "course_user_tags": {},
        "user_id": 40,
        "org_id": "IITB",
        "module": {
            "display_name": ""
        }
    },
    "time": "2014-06-20T06:43:52.716455+00:00",
    "ip": "127.0.0.1",
    "event": {
        "submission": {
            "i4x-IITB-CS101-problem-33e4aac93dc84f368c93b1d08fa984fc_2_1": {
                "input_type": "choicegroup",
                "question": "",
                "response_type": "multiplechoiceresponse",
                "answer": "MenuInflater.inflate()",
                "variant": "",
                "correct": true
            }
        },
        "success": "correct",
        "grade": 1,
        "correct_map": {
            "i4x-IITB-CS101-problem-33e4aac93dc84f368c93b1d08fa984fc_2_1": {
                "hint": "",
                "hintmode": null,
                "correctness": "correct",
                "npoints": null,
                "msg": "",
                "queuestate": null
            }
        },
        "state": {
            "student_answers": {},
            "seed": 1,
            "done": null,
            "correct_map": {},
            "input_state": {
                "i4x-IITB-CS101-problem-33e4aac93dc84f368c93b1d08fa984fc_2_1": {}
            }
        },
        "answers": {
            "i4x-IITB-CS101-problem-33e4aac93dc84f368c93b1d08fa984fc_2_1": "choice_0"
        },
        "attempts": 1,
        "max_grade": 1,
        "problem_id": "i4x://IITB/CS101/problem/33e4aac93dc84f368c93b1d08fa984fc"
    },
    "agent": "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:29.0) Gecko/20100101 Firefox/29.0",
    "page": "x_module"
}


{
    "username": "tushars",
    "host": "localhost",
    "event_source": "server",
    "event_type": "/courses/IITB/CS101/2014_T1/instructor_dashboard/api/list_instructor_tasks",
    "context": {
        "course_id": "IITB/CS101/2014_T1",
        "course_user_tags": {},
        "user_id": 6,
        "org_id": "IITB"
    },
    "time": "2014-06-20T05:49:26.780244+00:00",
    "ip": "127.0.0.1",
    "event": "{\"POST\": {}, \"GET\": {}}",
    "agent": "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:29.0) Gecko/20100101 Firefox/29.0",
    "page": null
}

---

这是一个相当丑陋的格式。True

json

会引用字符串和非空值，因此它不是真正的标准格式。这里有一个同样丑陋的方法，但它可以处理多个嵌套元素

我将使用它作为测试用例

log <-  paste0("name:{first:praveen,last:smith},age:23,place:UP,address:,",
"dob:, site: {site_name:something , site_url: http://something.com, ",
"description:{english:woot,spanish:wooto}}")

---

如果您的数据是JSON格式，请查看

rjson

包。我尝试使用rjson，但不知道如何处理嵌套的键值对。我会小心使用

名称（名称）

。您可能需要重命名

名称

向量。此外，您还可以将

split_by_逗号/冒号

与

strsplit（log，，|：”

组合在一起，感谢Flick先生的回复。我会尝试一下，如果有任何问题，我会返回给你。我已经添加了实际的文件格式。请检查它。如果你有时间。它稍微不那么难看：）我看不出有任何添加。您无法检查它有什么原因吗？我把你贴的样品放在一起。我希望这能代表你的实际数据。请再检查一遍，我没有节省时间。好吧，那不酷。我花了很多时间制作了一个解析器来处理类似json但不是真正的格式，这里有一个真正的json格式。您只需要在空白处分割数据并解析每个JSON块。你的样本数据很容易引起误解。

log <-  paste0("name:{first:praveen,last:smith},age:23,place:UP,address:,",
"dob:, site: {site_name:something , site_url: http://something.com, ",
"description:{english:woot,spanish:wooto}}")

parseString<-function(log) {
    nested<-c()
    #find {} blocks and replace
    m<-regexec("\\{[^}{]+?\\}", log)
    while(sapply(m, `[`, 1)!=-1) {
        s <- gsub("^\\{|\\}$","",sapply(regmatches(log,m), `[`, 1))
        regmatches(log,m)<-paste0("~~", length(nested)+seq_along(s), "~~")
        nested<-c(nested,s)
        m<-gregexpr("\\{([^}{]+)\\}", log)
    }
    nested<-c(nested, log)

    #turn elements into list
    nestedl<-vector("list", length(nested))
    for(i in seq_along(nested)) {
        kv<-strsplit(nested[i], "\\s*,\\s*")[[1]]
        kv<-lapply(strsplit(kv, ":"), function(x) 
            c(x[1], paste(x[-1],collapse=":")))
        names <- gsub("\\s+","", sapply(kv, `[`,1))
        vals <- gsub("\\s+","", sapply(kv, `[`,2))
        valsl <- setNames(as.list(vals), names)
        m <- regexec("~~(\\d+)~~", vals)
        for(j in which(sapply(m, `[`, 1) != -1)) {
            valsl[[j]]<-nestedl[[as.numeric(regmatches(vals[j], m[j])[[1]][2])]]
        }
        nestedl[[i]]<-valsl
    }
    nestedl[[length(nestedl)]]
}

#parseString(log)
$name
    $name$first
    [1] "praveen"
    $name$last
    [1] "smith"
$age
[1] "23"
$place
[1] "UP"
$address
[1] ""
$dob
[1] ""
$site
    $site$site_name
    [1] "something"
    $site$site_url
    [1] "http://something.com"
    $site$description
        $site$description$english
        [1] "woot"
        $site$description$spanish
        [1] "wooto"