com.fasterxml.jackson.core.JsonParseException：意外的字符（'\\'（代码92））[Java]

Question

I am deeply sorry for this messy title, but I am completly lost on why this can happen.

I am trying to parse a JSON String using Jackson. My code is simple:

import com.fasterxml.jackson.databind.ObjectMapper;
import formatter.Tweet;
import com.fasterxml.jackson.databind.DeserializationFeature;
public class FormatterTester {


static String tweet = "{\"created_at\":\"Fri May 03 11:43:17 +0000 2019\",\"id\":1124278249620566017,\"id_str\":\"1124278249620566017\",\"text\":\"RT @entkom: '\\u0e40\\u0e0b\\u0e49\\u0e19\\u0e15\\u0e4c-\\u0e28\\u0e38\\u0e20\\u0e1e\\u0e07\\u0e29\\u0e4c' \\u0e41\\u0e08\\u0e01\\u0e04\\u0e27\\u0e32\\u0e21\\u0e19\\u0e48\\u0e32\\u0e23\\u0e31\\u0e01 \\u0e21\\u0e2d\\u0e1a\\u0e04\\u0e27\\u0e32\\u0e21\\u0e2a\\u0e38\\u0e02\\u0e43\\u0e2b\\u0e49\\u0e41\\u0e1f\\u0e19\\u0e04\\u0e25\\u0e31\\u0e1a https:\\/\\/t.co\\/hBbi5hzEH8\",\"source\":\"\\u003ca href=\\\"http:\\/\\/twitter.com\\/download\\/android\\\" rel=\\\"nofollow\\\"\\u003eTwitter for Android\\u003c\\/a\\u003e\",\"truncated\":false,\"in_reply_to_status_id\":null,\"in_reply_to_status_id_str\":null,\"in_reply_to_user_id\":null,\"in_reply_to_user_id_str\":null,\"in_reply_to_screen_name\":null,\"user\":{\"id\":1062336001941504001,\"id_str\":\"1062336001941504001\",\"name\":\"\\ud83d\\udc0a\\u26bd\\ud83d\\udc2f\\ud83c\\udfb8\\ud83d\\udc99sugajin\\/\\/\\ud83d\\udc9a\\ud83d\\udc7b\\ud83d\\udc32\\ud83d\\udc0a\",\"screen_name\":\"sugajinBTS1\",\"location\":null,\"url\":null,\"description\":\"#BTS\\u597d\\u304d\\ud83d\\udc95\\u30b8\\u30f3\\u30cb\\u30e0\\u3088\\u308a\\u306e\\uff75\\uff99\\uff8d\\uff9f\\uff9d\\n#LGBTQ\\u304c\\u3082\\u3063\\u3068\\u7406\\u89e3\\u3055\\u308c\\u3066\\u6b32\\u3057\\u3044\\n#lovebychance\\u306e\\u6cbc\\u306b\\u30cf\\u30de\\u308a\\u4e2d\\n#season2\\u3068\\u3063\\u3066\\u3082\\u671f\\u5f85\\uff01\\uff01\\n#PinSon\\u2665SonPin\\n#2wish\\ud83d\\udc99\\ud83d\\udc9a\\n#Magus\\n#TeamReal\\n#LBCForever\\n\\u7121\\u8a00\\u30d5\\u30a9\\u30ed\\u30fc\\u5931\\u793c\\u3057\\u307e\\u3059\\ud83d\\ude47\",\"translator_type\":\"none\",\"protected\":false,\"verified\":false,\"followers_count\":61,\"friends_count\":224,\"listed_count\":0,\"favourites_count\":37785,\"statuses_count\":11611,\"created_at\":\"Tue Nov 13 13:26:54 +0000 2018\",\"utc_offset\":null,\"time_zone\":null,\"geo_enabled\":false,\"lang\":\"ja\",\"contributors_enabled\":false,\"is_translator\":false,\"profile_background_color\":\"F5F8FA\",\"profile_background_image_url\":\"\",\"profile_background_image_url_https\":\"\",\"profile_background_tile\":false,\"profile_link_color\":\"1DA1F2\",\"profile_sidebar_border_color\":\"C0DEED\",\"profile_sidebar_fill_color\":\"DDEEF6\",\"profile_text_color\":\"333333\",\"profile_use_background_image\":true,\"profile_image_url\":\"http:\\/\\/pbs.twimg.com\\/profile_images\\/1062337509701513216\\/5HFkKxoi_normal.jpg\",\"profile_image_url_https\":\"https:\\/\\/pbs.twimg.com\\/profile_images\\/1062337509701513216\\/5HFkKxoi_normal.jpg\",\"profile_banner_url\":\"https:\\/\\/pbs.twimg.com\\/profile_banners\\/1062336001941504001\\/1543643861\",\"default_profile\":true,\"default_profile_image\":false,\"following\":null,\"follow_request_sent\":null,\"notifications\":null},\"geo\":null,\"coordinates\":null,\"place\":null,\"contributors\":null,\"retweeted_status\":{\"created_at\":\"Fri May 03 01:29:52 +0000 2019\",\"id\":1124123879654301696,\"id_str\":\"1124123879654301696\",\"text\":\"'\\u0e40\\u0e0b\\u0e49\\u0e19\\u0e15\\u0e4c-\\u0e28\\u0e38\\u0e20\\u0e1e\\u0e07\\u0e29\\u0e4c' \\u0e41\\u0e08\\u0e01\\u0e04\\u0e27\\u0e32\\u0e21\\u0e19\\u0e48\\u0e32\\u0e23\\u0e31\\u0e01 \\u0e21\\u0e2d\\u0e1a\\u0e04\\u0e27\\u0e32\\u0e21\\u0e2a\\u0e38\\u0e02\\u0e43\\u0e2b\\u0e49\\u0e41\\u0e1f\\u0e19\\u0e04\\u0e25\\u0e31\\u0e1a https:\\/\\/t.co\\/hBbi5hzEH8\",\"source\":\"\\u003ca href=\\\"http:\\/\\/twitter.com\\\" rel=\\\"nofollow\\\"\\u003eTwitter Web Client\\u003c\\/a\\u003e\",\"truncated\":false,\"in_reply_to_status_id\":null,\"in_reply_to_status_id_str\":null,\"in_reply_to_user_id\":null,\"in_reply_to_user_id_str\":null,\"in_reply_to_screen_name\":null,\"user\":{\"id\":69565234,\"id_str\":\"69565234\",\"name\":\"ent_komchadluek\",\"screen_name\":\"entkom\",\"location\":null,\"url\":null,\"description\":null,\"translator_type\":\"none\",\"protected\":false,\"verified\":false,\"followers_count\":6684,\"friends_count\":1115,\"listed_count\":86,\"favourites_count\":14,\"statuses_count\":31813,\"created_at\":\"Fri Aug 28 11:28:17 +0000 2009\",\"utc_offset\":null,\"time_zone\":null,\"geo_enabled\":false,\"lang\":\"en\",\"contributors_enabled\":false,\"is_translator\":false,\"profile_background_color\":\"FF6699\",\"profile_background_image_url\":\"http:\\/\\/abs.twimg.com\\/images\\/themes\\/theme11\\/bg.gif\",\"profile_background_image_url_https\":\"https:\\/\\/abs.twimg.com\\/images\\/themes\\/theme11\\/bg.gif\",\"profile_background_tile\":true,\"profile_link_color\":\"B40B43\",\"profile_sidebar_border_color\":\"CC3366\",\"profile_sidebar_fill_color\":\"E5507E\",\"profile_text_color\":\"362720\",\"profile_use_background_image\":true,\"profile_image_url\":\"http:\\/\\/pbs.twimg.com\\/profile_images\\/471687167\\/ent1_normal.jpg\",\"profile_image_url_https\":\"https:\\/\\/pbs.twimg.com\\/profile_images\\/471687167\\/ent1_normal.jpg\",\"default_profile\":false,\"default_profile_image\":false,\"following\":null,\"follow_request_sent\":null,\"notifications\":null},\"geo\":null,\"coordinates\":null,\"place\":null,\"contributors\":null,\"is_quote_status\":false,\"quote_count\":9,\"reply_count\":33,\"retweet_count\":584,\"favorite_count\":505,\"entities\":{\"hashtags\":[],\"urls\":[{\"url\":\"https:\\/\\/t.co\\/hBbi5hzEH8\",\"expanded_url\":\"http:\\/\\/www.komchadluek.net\\/news\\/ent\\/370511#.XMuZj_HCjrY.twitter\",\"display_url\":\"komchadluek.net\\/news\\/ent\\/37051\\u2026\",\"indices\":[52,75]}],\"user_mentions\":[],\"symbols\":[]},\"favorited\":false,\"retweeted\":false,\"possibly_sensitive\":false,\"filter_level\":\"low\",\"lang\":\"th\"},\"is_quote_status\":false,\"quote_count\":0,\"reply_count\":0,\"retweet_count\":0,\"favorite_count\":0,\"entities\":{\"hashtags\":[],\"urls\":[{\"url\":\"https:\\/\\/t.co\\/hBbi5hzEH8\",\"expanded_url\":\"http:\\/\\/www.komchadluek.net\\/news\\/ent\\/370511#.XMuZj_HCjrY.twitter\",\"display_url\":\"komchadluek.net\\/news\\/ent\\/37051\\u2026\",\"indices\":[64,87]}],\"user_mentions\":[{\"screen_name\":\"entkom\",\"name\":\"ent_komchadluek\",\"id\":69565234,\"id_str\":\"69565234\",\"indices\":[3,10]}],\"symbols\":[]},\"favorited\":false,\"retweeted\":false,\"possibly_sensitive\":false,\"filter_level\":\"low\",\"lang\":\"th\",\"timestamp_ms\":\"1556883797446\"}";

public static void main(String[]args) {

    String valor_retorno= null;
    Tweet tw;

    try {

        ObjectMapper objectMapper = new ObjectMapper();
        objectMapper.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);

        tw = objectMapper.readValue(tweet, Tweet.class);

        System.out.println("Check 3 - El formatter retorna:\n"+tw.toString());

        valor_retorno = tw.toString();
    }  catch (Exception e) {
        e.printStackTrace();
        System.out.println("\nException " + e.getClass() + ": " + e.getMessage());
    } finally {
        System.out.println("\nReturn: Valor_retorno = "+valor_retorno);
    }

}

} If you run the code you'll see it works fine. Where is the problem then? I have to do this same operation on an Oracle NoSQL database. It's not important to know any of the parts related to the data retrieval since they work fine, I've tested them. The code is quite similar:

String data = new String(value.toByteArray(),StandardCharsets.UTF_8);
ObjectMapper objectMapper = new ObjectMapper();
objectMapper.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
objectMapper.configure(Feature.ALLOW_UNQUOTED_CONTROL_CHARS, true);
tw = objectMapper.readValue(data, Tweet.class);

My objective is to obtain exactly the same result as in the first code. A String of values separated by '|' according of the attributes of my class Tweet.

However, this code is compressed in a Jar file, and run internally by the database over all the Tweets recorded. I can't see what happens nor debug it, but it produces the following exception:

com.fasterxml.jackson.core.JsonParseException: Illegal character ((CTRL-CHAR, code 0)): only regular white space (\\r, \\n, \\t) is allowed between tokens

I've tried scaping the string "data" with StringEscapeUtils.escapeJava(data); what then produces the following exception:

com.fasterxml.jackson.core.JsonParseException: Unexpected character ('\\' (code 92)): expected a valid value (number, String, array, object, 'true', 'false' or 'null') I've also tried scaping the string like this data.replace('\\'', ' '); without success.

I can't understand after many tests, why it runs well on the demo I put here first and not on the actual project, having exactly the same dependencies.

Answer 1

For some reason, Jackson can't parse what I retrieve from the DataBase. This is most likely due to a problem of codification or decodification in the CentOS that my Docker container uses to hold the DB and where the script is invoqued and executed.

In the end, using Gson for the parsing was the best option, though it would still produce errors if you don't trim() the String. Apparently, for some reason the JSON came quoted twice. This is, ""JSON text"".

The code:

package formatter;

import java.io.*;
import java.lang.String;
import java.nio.charset.StandardCharsets;
import java.util.List;

import oracle.kv.*;
import com.google.gson.Gson;
import oracle.kv.KeyValueVersion;
import oracle.kv.exttab.Formatter;

public class TweetFormatter implements Formatter {

    public TweetFormatter() {
        super();
    }

    public String toOracleLoaderFormat(final KeyValueVersion kvv, final KVStore kvStore){

        String valor_retorno= null;

        Tweet tw; //antes sin null

        BufferedWriter bf = FormatterUtils.getInstance().getWriter();

        try {
            final Key key = kvv.getKey();
            final Value value = kvv.getValue();
            Value.Format format = value.getFormat();

            FormatterUtils.getInstance().writeLine(bf,"[Key: "+ key + ", Value:" +value.toByteArray()+ "]" + ". Format= "+ format.toString());

            //Filtrar Clave
            List<String> major = key.getMajorPath();

            FormatterUtils.getInstance().writeLine(bf,"Check 1:\n Key is: "+key + "\n Key length is: "+major.size()
                    + "\n Values are: "+major.toString() + "\n contains: "+major.contains("TweeterStream"));

            Boolean contains = false;

            for(String x : major) {
                if(x.equals("TweeterStream")||x.equals("/TweeterStream")||x.equals("/TweeterStream/")) {
                    contains = true;
                    break;
                }
            }

            //Parsear
            if(contains){

                String data = new String(value.toByteArray(),StandardCharsets.UTF_8);

                data = data.trim();
                tw = new Gson().fromJson(data,Tweet.class); //FUNCIONA

                FormatterUtils.getInstance().writeLine(bf,"Check 3 - El formatter retorna:\n"+tw.toString());
                valor_retorno = tw.toString();
            }else{
                FormatterUtils.getInstance().writeLine(bf,"\nEstoy en else");
            }
            FormatterUtils.getInstance().writeLine(bf,"\nestoy fuera del if-else");
        }  catch (Exception e) {
            e.printStackTrace();
            FormatterUtils.getInstance().writeLine(bf, "\nException " + e.getClass() + ": " + e.getMessage());
        } finally {
            FormatterUtils.getInstance().writeLine(bf,"\nReturn: Valor_retorno = "+valor_retorno);
            FormatterUtils.getInstance().generateLog(bf);
        }
        return valor_retorno;
    }