简体   繁体   中英

Deserializing twitter stream json string F#, how to define 'null' as a proper value?

I leave the below in case anybody wants the record types, but my question can be asked as following. Suppose one needs to write to a file a record type that can be null, what is the best way to achieve that, considering the below yields: "The type 'Basic' does not have 'null' as a proper value":

type Basic = {Toto:string}

let basicToString b = function
    |null -> "null"
    |record->record.Toto

Thanks a lot


I have the following code to deserialize tweets from twitter stream:

open System.Runtime.Serialization
open System.Runtime.Serialization.Json
open System
open System.Text
open System.IO  


  let  makeString numFields = 
    if numFields>1 then 
                seq[for i in 1..(numFields-1)->","]
                |> Seq.fold(fun elem res-> elem+res) ""
    else
        ""



[<DataContract>]
type boundingbox = {
    [<field: DataMember(Name = "type")>]
    t:string
    [<field: DataMember(Name = "coordinates")>]
    coordinates:float array array array
    }
    with 
        member this.ToCsv() = let temp =  string this
                              if temp ="" then 
                                  makeString 2
                              else
                                  this.t+","+"coordinates"




[<DataContract>]
type attributes = {
 [<field: DataMember(Name = "street_adress")>]
 street_adress:string
 }
    with 
        member this.ToCsv() = let temp =  string this
                              if temp ="" then 
                                  makeString 1
                              else
                                  this.street_adress



[<DataContract>]
type place = {
    [<field: DataMember(Name = "country")>]
    country:string
    [<field: DataMember(Name = "url")>]
    url:string
    [<field: DataMember(Name = "attributes")>]
    attributes:attributes 
    [<field: DataMember(Name = "country_code")>]
    country_code:string
    [<field: DataMember(Name = "full_name")>]
    full_name:string
    [<field: DataMember(Name = "name")>]
    name:string
    [<field: DataMember(Name = "id")>]
    id:string
    [<field: DataMember(Name = "bounding_box")>]
    bounding_box:boundingbox
    [<field: DataMember(Name = "pldace_type")>]
    place_type:string
    }
    with 
        member this.toCsv() = let temp =  string this
                              if temp ="" then 
                                  makeString 10
                              else
                                  this.country+","+this.url+","+this.attributes.ToCsv()+","+this.country_code+","+this.full_name+","+this.name+","+this.bounding_box.ToCsv()+","+this.place_type



[<DataContract>]
type geo = {
    [<field: DataMember(Name = "type")>]
    t:string
    [<field: DataMember(Name = "coordinates")>]
    coordinates:float array
    }

[<DataContract>]
type url = {
    [<field: DataMember(Name = "url")>]
    url:string
    [<field: DataMember(Name = "indices")>]
    indices:int array
    }

[<DataContract>]
type hashtag = {
    [<field: DataMember(Name = "text")>]
    text:string
    [<field: DataMember(Name = "indices")>]
    indices:int array
    }


[<DataContract>]
type user_mention = {
    [<field: DataMember(Name = "indices")>]
    indices:int array
    [<field: DataMember(Name = "screen_name")>]
    screen_name:string
    [<field: DataMember(Name = "name")>]
    name:string
    [<field: DataMember(Name = "id")>]
    id:string
    }

[<DataContract>]
type entities = {
    [<field: DataMember(Name = "urls")>]
    urls:url array
    [<field: DataMember(Name = "hashtags")>]
    hashtags:hashtag array
    [<field: DataMember(Name = "user_mentions")>]
    user_mentions:user_mention array
    }

[<DataContract>]
type user = {
    [<field: DataMember(Name = "time_zone")>]
     time_zone:string
    [<field: DataMember(Name = "profile_sidebar_border_color")>]
     profile_sidebar_border_color:string
    [<field: DataMember(Name = "screen_name")>]
    screen_name:string
    [<field: DataMember(Name = "notifications")>]
     notifications:string
    [<field: DataMember(Name = "listed_count")>]
     listed_count:string
    [<field: DataMember(Name = "profile_background_image_url")>]
     profile_background_image_url:string
    [<field: DataMember(Name = "location")>]
    location:string
    [<field: DataMember(Name = "statuses_count")>]
     statuses_count:string
    [<field: DataMember(Name = "profile_background_color")>]
    profile_background_color:string
    [<field: DataMember(Name = "description")>]
     description:string
    [<field: DataMember(Name = "show_all_inline_media")>]
     show_all_inline_media:string
    [<field: DataMember(Name = "profile_background_tile")>]
     profile_background_tile:string
    [<field: DataMember(Name = "contributors_enabled")>]
     contributors_enabled:string
    [<field: DataMember(Name = "geo_enabled")>]
     geo_enabled:string
    [<field: DataMember(Name = "created_at")>]
     created_at:string
    [<field: DataMember(Name = "profile_text_color")>]
     profile_text_color:string
    [<field: DataMember(Name = "followers_count")>]
    followers_count:string
    [<field: DataMember(Name = "profile_use_background_image")>]
    profile_use_background_image:string
    [<field: DataMember(Name = "url")>]
     url:string
    [<field: DataMember(Name = "friends_count")>]
     friends_count:string
    [<field: DataMember(Name = "profile_link_color")>]
    profile_link_color:string
    [<field: DataMember(Name = "protected")>]
     Protected:string
    [<field: DataMember(Name = "lang")>]
     lang:string
    [<field: DataMember(Name = "verified")>]
     verified:string
    [<field: DataMember(Name = "name")>]
     name:string
    [<field: DataMember(Name = "follow_request_sent")>]
     follow_request_sent:string
    [<field: DataMember(Name = "following")>]
     following:string
    [<field: DataMember(Name = "favourites_count")>]
     favourites_count:string
    [<field: DataMember(Name = "profile_sidebar_fill_color")>]
     profile_sidebar_fill_color:string
    [<field: DataMember(Name = "profile_image_url")>]
    profile_image_url:string
    [<field: DataMember(Name = "id")>]
    id:string
    [<field: DataMember(Name = "utc_offset")>]
     utc_offset:string
}




[<DataContract>]
type tweet = {
    [<field: DataMember(Name = "place")>]
     place:place
    [<field: DataMember(Name = "geo")>]
     geo:geo
    [<field: DataMember(Name = "text")>]
    text:string
    [<field: DataMember(Name = "coordinates")>]
    coordinates:geo
    [<field: DataMember(Name = "retweet_count")>]
     retweet_count:string
    [<field: DataMember(Name = "favorited")>]
     favorited:string
    [<field: DataMember(Name = "source")>]
    source:string
    [<field: DataMember(Name = "contributors")>]
     contributors:int array
    [<field: DataMember(Name = "created_at")>]
    created_at:string
    [<field: DataMember(Name = "in_reply_to_status_id")>]
    in_reply_to_status_id:string
    [<field: DataMember(Name = "in_reply_to_screen_name")>]
    in_reply_to_screen_name:string
    [<field: DataMember(Name = "user")>]
     user:user
    [<field: DataMember(Name = "retweeted")>]
    retweeted:string
    [<field: DataMember(Name = "in_reply_to_user_id")>]
    in_reply_to_user_id:string
    [<field: DataMember(Name = "truncated")>]
     truncated:string
    [<field: DataMember(Name = "id")>]
    tweet_id:string
    [<field: DataMember(Name = "entities")>]
    entities:entities
    }



[<DataContract>]
type fullTweet = {
    [<field: DataMember(Name = "place")>]
     place:place
    [<field: DataMember(Name = "geo")>]
     geo:geo
    [<field: DataMember(Name = "text")>]
    text:string
    [<field: DataMember(Name = "coordinates")>]
    coordinates:geo
    [<field: DataMember(Name = "retweet_count")>]
     retweet_count:string
    [<field: DataMember(Name = "favorited")>]
     favorited:string
    [<field: DataMember(Name = "source")>]
    source:string
    [<field: DataMember(Name = "contributors")>]
     contributors:int array
    [<field: DataMember(Name = "created_at")>]
    created_at:string
    [<field: DataMember(Name = "in_reply_to_status_id")>]
    in_reply_to_status_id:string
    [<field: DataMember(Name="retweeted_status")>]
    retweeted_status:tweet
    [<field: DataMember(Name = "in_reply_to_screen_name")>]
    in_reply_to_screen_name:string
    [<field: DataMember(Name = "user")>]
     user:user
    [<field: DataMember(Name = "retweeted")>]
    retweeted:string
    [<field: DataMember(Name = "in_reply_to_user_id")>]
    in_reply_to_user_id:string
    [<field: DataMember(Name = "truncated")>]
     truncated:string
    [<field: DataMember(Name = "id")>]
    tweet_id:string
    [<field: DataMember(Name = "entities")>]
    entities:entities
    }



let decodeFullTweet (s:string)  = 
    let json = new DataContractJsonSerializer(typeof<fullTweet>)
    let byteArray = Encoding.UTF8.GetBytes(s)
    let stream = new MemoryStream(byteArray)
    json.ReadObject(stream) :?>fullTweet

let decodeUser (s:string)  = 
    let json = new DataContractJsonSerializer(typeof<user>)
    let byteArray = Encoding.UTF8.GetBytes(s)
    let stream = new MemoryStream(byteArray)
    json.ReadObject(stream) :?>user

The next step I need to get done is to write each fullTweet record to a csv file, the issue is that sometimes some of the fields of the record type are null. For example when decoding the json string (the below is just a small part of the string ):

rel=\\\\"nofollow\\\\">TweetDeck\\",\\"favorited\\":false,\\"in_reply_to_status_id\\":null,\\"entities\\":{\\"hashtags\\":[{\\"text\\":\\"frac1\\",\\"indices\\":[117,123]}],\\"user_mentions\\":[],\\"urls\\":[]},\\"place\\":null,\\"coordinates\\":null,\\"geo\\":null,\\"in_reply_to_user_id\\":null,\\"

The fields "place" and "in_reply_to_user_id" will be null.

How can I handle this so that when a field is null (for example places), the csv line reads "null" ( for each field of the record type place) ? Or if you have a better way to handle this ?

Thanks a lot !!!

(Hope some will enjoy all the record types :) )

If I understand what you are asking, you just need a function which will take a string and return the string if it is not null and return "null" if it is null:

let fieldToString = function
    | null -> "null"
    | field -> field

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM