Trouble with getting codes for Huffman Tree - recursion

I need to create the codes to compress a Huffman Tree. (O if you traverse left 1 if you traverse right.)
Right now the codes array will get the correct first code, but afterwards will only return null.
I am not allowed to use any instance/global variables or any predefined java classes besides array and arrayList
public static String compress(final BinaryNodeInterface<Character> root, final String message)
{
String[] codes;
ArrayList<Character> letter = new ArrayList<Character>();
String codeString = "";
boolean addChar=true;
for(int i =0; i<message.length();i++)
{
for(int j=0;j<letter.size();j++)
if(message.charAt(i)==letter.get(j))
addChar=false;
else
addChar=true;
if(addChar)
letter.add(message.charAt(i));
}
codes = new String[letter.size()];
for(int i=0;i<letter.size();i++)
codes[i]=(getPath(root,letter.get(i),""));
return ""; // Do not forget to change this line!!!
}
private static String getPath(final BinaryNodeInterface<Character> root, char toFind, String path)
{
String result;
if (! root.isLeaf()) {
if ((result = getPath(root.getLeftChild(),toFind, path + '0')) == null) {
result = getPath(root.getLeftChild(),toFind, path + '1');
}
}
else {
result = (toFind == root.getData()) ? path : null;
}
return result;
}

You don't seem to be visiting the right sub child. Change
result = getPath(root.getLeftChild(),toFind, path + '1');
to
result = getPath(root.getRightChild(),toFind, path + '1');

Related

Xunit CSV streamReader.ReadToEnd returns System.ArgumentOutOfRangeException

I would like to evaluate a CSV data series with Xunit.
For this I need to read in a string consisting of int, bool, double and others.
With the following code, the transfer basically works for one row.
But since I want to test for predecessor values, I need a whole CSV file for evaluation.
My [Theory] works with InlineData without errors.
But when I read in a CSV file, the CSVDataHandler gives a System.ArgumentOutOfRangeException!
I can't find a solution for the error and ask for support.
Thanks a lot!
[Theory, CSVDataHandler(false, "C:\\MyTestData.txt", Skip = "")]
public void TestData(int[] newLine, int[] GetInt, bool[] GetBool)
{
for (int i = 0; i < newLine.Length; i++)
{
output.WriteLine("newLine {0}", newLine[i]);
output.WriteLine("GetInt {0}", GetInt[i]);
output.WriteLine("GetBool {0}", GetBool[i]);
}
}
[DataDiscoverer("Xunit.Sdk.DataDiscoverer", "xunit.core")]
[AttributeUsage(AttributeTargets.Method, AllowMultiple = true, Inherited = true)]
public abstract class DataArribute : Attribute
{
public abstract IEnumerable<object> GetData(MethodInfo methodInfo);
public virtual string? Skip { get; set; }
}
[AttributeUsage(AttributeTargets.Method, AllowMultiple = false, Inherited = false)]
public class CSVDataHandler : DataAttribute
{
public CSVDataHandler(bool hasHeaders, string pathCSV)
{
this.hasHeaders = hasHeaders;
this.pathCSV = pathCSV;
}
public override IEnumerable<object[]> GetData(MethodInfo methodInfo)
{
var methodParameters = methodInfo.GetParameters();
var paramterTypes = methodParameters.Select(p => p.ParameterType).ToArray();
using (var streamReader = new StreamReader(pathCSV))
{
if (hasHeaders) { streamReader.ReadLine(); }
string csvLine = string.Empty;
// ReadLine ++
//while ((csvLine = streamReader.ReadLine()) != null)
//{
// var csvRow = csvLine.Split(',');
// yield return ConvertCsv((object[])csvRow, paramterTypes);
//}
// ReadToEnd ??
while ((csvLine = streamReader.ReadToEnd()) != null)
{
if (Environment.NewLine != null)
{
var csvRow = csvLine.Split(',');
yield return ConvertCsv((object[])csvRow, paramterTypes); // System.ArgumentOutOfRangeException
}
}
}
}
private static object[] ConvertCsv(IReadOnlyList<object> cswRow, IReadOnlyList<Type> parameterTypes)
{
var convertedObject = new object[parameterTypes.Count];
for (int i = 0; i < parameterTypes.Count; i++)
{
convertedObject[i] = (parameterTypes[i] == typeof(int)) ? Convert.ToInt32(cswRow[i]) : cswRow[i]; // System.ArgumentOutOfRangeException
convertedObject[i] = (parameterTypes[i] == typeof(double)) ? Convert.ToDouble(cswRow[i]) : cswRow[i];
convertedObject[i] = (parameterTypes[i] == typeof(bool)) ? Convert.ToBoolean(cswRow[i]) : cswRow[i];
}
return convertedObject;
}
}
MyTestData.txt
1,2,true,
2,3,false,
3,10,true,
The first call to streamReader.ReadToEnd() will return the entire contents of the file in a string, not just one line. When you call csvLine.Split(',') you will get an array of 12 elements.
The second call to streamReader.ReadToEnd() will not return null as your while statement appears to expect, but an empty string. See the docu at
https://learn.microsoft.com/en-us/dotnet/api/system.io.streamreader.readtoend?view=net-7.0
If the current position is at the end of the stream, returns an empty
string ("").
With the empty string, the call to call csvLine.Split(',') will return an array of length 0, which causes your exception when its first element (index 0) is accessed.
All of this could have been easily discovered by simply starting the test in a debugger.
It looks like you have some other issues here as well.
I don't understand what your if (Environment.NewLine != null) is intended to do, the NewLine property will never be null but should have one of the values "\r\n" or "\n" so the if will always be taken.
The parameters of your test method are arrays int[] and bool[], but you are checking against the types int, double and bool in your ConvertCsv method, so the alternative cswRow[i] will always be returned. You'll wind up passing strings to your method expecting int[] and bool[] and will at latest get an error there.
This method reads a data series from several rows and columns and returns it as an array for testing purposes.
The conversion of the columns can be adjusted according to existing pattern.
Thanks to Christopher!
[AttributeUsage(AttributeTargets.Method, AllowMultiple = false, Inherited = false)]
public class CSVDataHandler : Xunit.Sdk.DataAttribute
{
public CSVDataHandler(string pathCSV)
{
this.pathCSV = pathCSV;
}
public override IEnumerable<object[]> GetData(MethodInfo methodInfo)
{
List<int> newLine = new();
List<int> GetInt = new();
List<bool> GetBool = new();
var reader = new StreamReader(pathCSV);
string readData = string.Empty;
while ((readData = reader.ReadLine()) != null)
{
string[] split = readData.Split(new char[] { ',' });
newLine.Add(int.Parse(split[0]));
GetInt.Add(int.Parse(split[1]));
GetBool.Add(bool.Parse(split[2]));
// Add more objects ...
}
yield return new object[] { newLine.ToArray(), GetInt.ToArray(), GetBool.ToArray() };
}
}

How to use GUID as Primary Key with System.Data.Sqlite

I'm not saying it's advisable, but sometimes you inherit something which just needs to work. In this case it's Guids for Primary Keys...
Out of the box, you'll get an error about System.Guid not working with byte[] (or String if you're using BinaryGUID=False).
To fix this, you need to intercept byte[] arrays (or strings) and instead return Guid type. This is possible with the System.Data.Sqlite provider.
First
using System.Data.SQLite;
Then, put this in the constructor of your code-first db context:
var con = (SQLiteConnection)base.Database.Connection;
var bind = System.Data.SQLite.SQLiteTypeCallbacks.Create(
null,
new SQLiteReadValueCallback(GuidInterceptor), null, null);
con.SetTypeCallbacks("uniqueidentifier", bind);
con.SetTypeCallbacks("", bind); //Sometimes, the system just doesn't know
con.Flags |= SQLiteConnectionFlags.UseConnectionReadValueCallbacks;
And then this is the magic function:
private void GuidInterceptor(SQLiteConvert convert, SQLiteDataReader reader, SQLiteConnectionFlags flags, SQLiteReadEventArgs args, string typename, int index, object userdata, out bool complete)
{
complete = false;
if (typename == "uniqueidentifier")
{
var e = (SQLiteReadValueEventArgs)args;
var o = reader.GetGuid(index);
e.Value.Value = o;
e.Value.GuidValue = o;
complete = true;
}
else
{
var o = reader.GetValue(index);
if (o is byte[])
{
var b = (byte[])o;
if (b.Length == 16)
{
var e = (SQLiteReadValueEventArgs)args;
var g = new Guid(b);
e.Value.Value = g;
e.Value.GuidValue = g;
complete = true;
}
}
else if (o is string)
{
var s = (string)o;
if (s.Length == 36)
{
var e = (SQLiteReadValueEventArgs)args;
var goGuid = (e.MethodName == "GetGuid");
if (!goGuid)
goGuid = (s[8] == '-' && s[13] == '-' && s[18] == '-' && s[23] == '-');
Guid g;
if (goGuid && Guid.TryParse(s, out g))
{
e.Value.Value = g;
e.Value.GuidValue = g;
complete = true;
}
else
{
}
}
}
}
}
That only fixes reading in of data. If you try to .Where() on a Guid member, and you're using BinaryGUID=True no rows will be returned (when there should be). For now, you'll need BinaryGUID=False, which does take up more space, but it's a simple solution.
If you can help it, try and define your Guid properties instead as:
[Key]
[MaxLength(16)]
[MinLength(16)]
public byte[] AccountUserId { get; set; }
You'll be forced to call guidValue.ToByteArray() in your application layer. You might be able to create some helpers to you're not having to call that function. Having your own custom function proxy for creating and parsing Guids may help, so you can easily change the implementation.
In my case, I don't have the luxury of time to convert all the Guid properties and usages to byte[]

Wikipedia page parsing program caught in endless graph cycle

My program is caught in a cycle that never ends, and I can't see how it get into this trap, or how to avoid it.
It's parsing Wikipedia data and I think it's just following a connected component around and around.
Maybe I can store the pages I've visited already in a set and if a page is in that set I won't go back to it?
This is my project, its quite small, only three short classes.
This is a link to the data it generates, I stopped it short, otherwise it would have gone on and on.
This is the laughably small toy input that generated that mess.
It's the same project I was working on when I asked this question.
What follows is the entirety of the code.
The main class:
public static void main(String[] args) throws Exception
{
String name_list_file = "/home/matthias/Workbench/SUTD/nytimes_corpus/NYTimesCorpus/2005/01/02/test/people_test.txt";
String single_name;
try (
// read in the original file, list of names, w/e
InputStream stream_for_name_list_file = new FileInputStream( name_list_file );
InputStreamReader stream_reader = new InputStreamReader( stream_for_name_list_file , Charset.forName("UTF-8"));
BufferedReader line_reader = new BufferedReader( stream_reader );
)
{
while (( single_name = line_reader.readLine() ) != null)
{
//replace this by a URL encoder
//String associated_alias = single_name.replace(' ', '+');
String associated_alias = URLEncoder.encode( single_name , "UTF-8");
String platonic_key = single_name;
System.out.println("now processing: " + platonic_key);
Wikidata_Q_Reader.getQ( platonic_key, associated_alias );
}
}
//print the struc
Wikidata_Q_Reader.print_data();
}
The Wikipedia reader / value grabber:
static Map<String, HashSet<String> > q_valMap = new HashMap<String, HashSet<String> >();
//public static String[] getQ(String variable_entity) throws Exception
public static void getQ( String platonic_key, String associated_alias ) throws Exception
{
//get the corresponding wikidata page
//check the validity of the URL
String URL_czech = "https://www.wikidata.org/wiki/Special:ItemByTitle?site=en&page=" + associated_alias + "&submit=Search";
URL wikidata_page = new URL(URL_czech);
HttpURLConnection wiki_connection = (HttpURLConnection)wikidata_page.openConnection();
InputStream wikiInputStream = null;
try
{
// try to connect and use the input stream
wiki_connection.connect();
wikiInputStream = wiki_connection.getInputStream();
}
catch(IOException e)
{
// failed, try using the error stream
wikiInputStream = wiki_connection.getErrorStream();
}
BufferedReader wiki_data_pagecontent = new BufferedReader(
new InputStreamReader(
wikiInputStream ));
String line_by_line;
while ((line_by_line = wiki_data_pagecontent.readLine()) != null)
{
// if we can determine it's a disambig page we need to send it off to get all
// the possible senses in which it can be used.
Pattern disambig_pattern = Pattern.compile("<div class=\"wikibase-entitytermsview-heading-description \">Wikipedia disambiguation page</div>");
Matcher disambig_indicator = disambig_pattern.matcher(line_by_line);
if (disambig_indicator.matches())
{
//off to get the different usages
Wikipedia_Disambig_Fetcher.all_possibilities( platonic_key, associated_alias );
}
else
{
//get the Q value off the page by matching
Pattern q_page_pattern = Pattern.compile("<!-- wikibase-toolbar --><span class=\"wikibase-toolbar-container\"><span class=\"wikibase-toolbar-item " +
"wikibase-toolbar \">\\[<span class=\"wikibase-toolbar-item wikibase-toolbar-button wikibase-toolbar-button-edit\"><a " +
"href=\"/wiki/Special:SetSiteLink/(.*?)\">edit</a></span>\\]</span></span>");
Matcher match_Q_component = q_page_pattern.matcher(line_by_line);
if ( match_Q_component.matches() )
{
String Q = match_Q_component.group(1);
// 'Q' should be appended to an array, since each entity can hold multiple
// Q values on that basis of disambig
put_to_hash( platonic_key, Q );
}
}
}
wiki_data_pagecontent.close();
// \\ // ! PRINT IT ! // \\ // \\ // \\ // \\ // \\ // \\
for (Map.Entry<String, HashSet<String> > entry : q_valMap.entrySet())
{
System.out.println(entry.getKey()+" : " + Arrays.deepToString(q_valMap.entrySet().toArray()) );
}
}
// add Q values to their arrayList in the hash map at the index of the appropriate entity
public static HashSet<String> put_to_hash(String key, String value )
{
HashSet<String> valSet;
if (q_valMap.containsKey(key)) {
valSet = q_valMap.get(key);
} else {
valSet = new HashSet<String>();
q_valMap.put(key, valSet);
}
valSet.add(value);
return valSet;
}
// add Q values to their arrayList in the hash map at the index of the appropriate entity
public static void print_data()
{
System.out.println("THIS IS THE FINAL DATA SET!!!");
// \\ // ! PRINT IT ! // \\ // \\ // \\ // \\ // \\ // \\
for (Map.Entry<String, HashSet<String> > entry : q_valMap.entrySet())
{
System.out.println(entry.getKey()+" : " + Arrays.deepToString(q_valMap.entrySet().toArray()) );
}
}
Dealing with disambiguation pages:
public static void all_possibilities( String platonic_key, String associated_alias ) throws Exception
{
System.out.println("this is a disambig page");
//if it's a disambig page we know we can go right to the Wikipedia
//get it's normal wiki disambig page
String URL_czech = "https://en.wikipedia.org/wiki/" + associated_alias;
URL wikidata_page = new URL(URL_czech);
HttpURLConnection wiki_connection = (HttpURLConnection)wikidata_page.openConnection();
InputStream wikiInputStream = null;
try
{
// try to connect and use the input stream
wiki_connection.connect();
wikiInputStream = wiki_connection.getInputStream();
}
catch(IOException e)
{
// failed, try using the error stream
wikiInputStream = wiki_connection.getErrorStream();
}
// parse the input stream using Jsoup
Document docx = Jsoup.parse(wikiInputStream, null, wikidata_page.getProtocol()+"://"+wikidata_page.getHost()+"/");
//this can handle the less structured ones.
Elements linx = docx.select( "p:contains(" + associated_alias + ") ~ ul a:eq(0)" );
for (Element linq : linx)
{
System.out.println(linq.text());
String linq_nospace = URLEncoder.encode( linq.text() , "UTF-8");
Wikidata_Q_Reader.getQ( platonic_key, linq_nospace );
}
}

programming logic problem

I need a function that can give me all possible combinations of a array back.
Example:
$source = array('a', 'b', 'c');
$target = thisiswhatisearch($source);
Now the $target should look like:
array('a','b','c','ab','ac','cb','abc')
I dont need the aa, bb, cc.
I also dont need the the ba, ca, acb.. because the order isn't important to me.
Thanks for any help.
Tried to be language agnostic but i guess its C like:
function combinations(array arr)
{
combos = array();
for (int i=1; i<2**arr.size(); i++)
{
int x = i;
int c = 0;
str = "";
while(x>0)
{
int rem = x % 2;
if(rem == 1)
str += arr[c];
x = x / 2;
c++;
}
combos.add(str);
}
return combos;
}
The Wikipedia entry for Combination has a link to C code that does this.
That's an out of the mind solution. It is probably not the fastest and cleanest one, but it kind of works. It's in Java, because I had it open:
public class Combination {
public static void main(String[] args) {
String[] source = {"a","b","c"};
List<String> result = combineMe(new ArrayList<String>(Arrays.asList(source)));
for (String string : result) {
System.out.println(string);
}
}
public static List<String> combineMe(List<String> source) {
List<String> result = new ArrayList<String>();
if (source.size()==0) {
result.add("");
return result;
}else{
String tmp = source.remove(0);
source = combineMe(source);
for (String string : source) {
result.add(("" + string).trim());
result.add(tmp + string);
}
}
return result;
}
}
The first entry in the resulting list is a fake one, and needs to be removed at the end

Use MatchPattern property of FindMatchingFiles workflow activity

I'm customizing the default workflow of build process template using TFS 2010 Team Build. There is an activity named FindMatchingFiles allows to search for specific files with a pattern defined in MatchPattern property. It works if I only specify one file extension. Example:
String.Format("{0}\\**\\\*.msi", SourcesDirectory)
But I would like to include *.exe as well. Trying following pattern but it doesn't work:
String.Format("{0}\\**\\\*.(msi|exe)", SourcesDirectory)
Anyone could show me how to correct it?
You can use String.Format("{0}\**\*.msi;{0}\**\*.exe", SourcesDirectory)
The FindMatchingFiles activity's MatchPattern property uses the
Syntax that is supported by the searchPattern argument of the Directory.GetFiles(String, String) method.
That means that you can't combine multiple extensions. You'll need to call the FindMatchingFiles activity twice. You can then combine the results of those two calls when you use them (i.e. if your results are msiFiles and exeFiles, you can use msiFiles.Concat(exeFiles) as the input to a ForEach).
However, as you can see with #antwoord's answer, the activity does actually seem to accept a semi-colon delimited list of patterns, unlike Directory.GetFiles.
FindMatchingFiles has some strange search pattern. Here is the code (decompiled using ILSpy) so you can test your search patterns without having to kick off a new build.
It contains a hardcoded root dir at the following location (Z:)
List<string> matchingDirectories = GetMatchingDirectories(#"Z:", matchPattern.Substring(0, num), 0);
Code:
using System;
using System.Collections.Generic;
using System.IO;
namespace DirectoryGetFiles
{
//// Use the FindMatchingFiles activity to find files. Specify the search criteria in the MatchPattern (String) property.
//// In this property, you can specify an argument that includes the following elements:
//// Syntax that is supported by the searchPattern argument of the Directory GetFiles(String, String) method.
////
//// ** to specify a recursive search. For example:
//// To search the sources directory for text files, you could specify something that resembles the following
//// value for the MatchPattern property: String.Format("{0}\**\*.txt", SourcesDirectory).
////
//// To search the sources directory for text files in one or more subdirectories that are called txtfiles,
//// you could specify something that resembles the following value for the MatchPattern property:
//// String.Format("{0}\**\txtfiles\*.txt", SourcesDirectory).
class Program
{
static void Main(string[] args)
{
string searchPattern = #"_PublishedWebsites\Web\Scripts\jasmine-specs**\*.js";
var results = Execute(searchPattern);
foreach (var i in results)
{
Console.WriteLine("found: {0}", i);
}
Console.WriteLine("Done...");
Console.ReadLine();
}
private static IEnumerable<string> Execute(string pattern)
{
string text = pattern;
text = text.Replace(";;", "\0");
var hashSet = new HashSet<string>(StringComparer.OrdinalIgnoreCase);
string[] array = text.Split(new char[]
{
';'
}, StringSplitOptions.RemoveEmptyEntries);
for (int i = 0; i < array.Length; i++)
{
string text2 = array[i];
string text3 = text2.Replace("\0", ";");
if (IsValidPattern(text3))
{
List<string> list = ComputeMatchingPaths(text3);
if (list.Count > 0)
{
using (List<string>.Enumerator enumerator = list.GetEnumerator())
{
while (enumerator.MoveNext())
{
string current = enumerator.Current;
hashSet.Add(current);
}
goto IL_15C;
}
}
////Message = ActivitiesResources.Format("NoMatchesForSearchPattern", new object[]
}
else
{
//// Message = ActivitiesResources.Format("InvalidSearchPattern", new object[]
}
IL_15C: ;
}
return hashSet;//.OrderBy((string x) => x, FileSpec.TopDownComparer);
}
private static bool IsValidPattern(string pattern)
{
string text = "**" + Path.DirectorySeparatorChar;
int num = pattern.IndexOf(text, StringComparison.Ordinal);
return (num < 0 || (pattern.IndexOf(text, num + text.Length, StringComparison.OrdinalIgnoreCase) <= 0 && pattern.IndexOf(Path.DirectorySeparatorChar, num + text.Length) <= 0)) && pattern[pattern.Length - 1] != Path.DirectorySeparatorChar;
}
private static List<string> ComputeMatchingPaths(string matchPattern)
{
List<string> list = new List<string>();
string text = "**" + Path.DirectorySeparatorChar;
int num = matchPattern.IndexOf(text, 0, StringComparison.OrdinalIgnoreCase);
if (num >= 0)
{
List<string> matchingDirectories = GetMatchingDirectories(#"Z:", matchPattern.Substring(0, num), 0);
string searchPattern = matchPattern.Substring(num + text.Length);
using (List<string>.Enumerator enumerator = matchingDirectories.GetEnumerator())
{
while (enumerator.MoveNext())
{
string current = enumerator.Current;
list.AddRange(Directory.GetFiles(current, searchPattern, SearchOption.AllDirectories));
}
return list;
}
}
int num2 = matchPattern.LastIndexOf(Path.DirectorySeparatorChar);
if (num2 >= 0)
{
List<string> matchingDirectories2 = GetMatchingDirectories(string.Empty, matchPattern.Substring(0, num2 + 1), 0);
string searchPattern2 = matchPattern.Substring(num2 + 1);
using (List<string>.Enumerator enumerator2 = matchingDirectories2.GetEnumerator())
{
while (enumerator2.MoveNext())
{
string current2 = enumerator2.Current;
try
{
list.AddRange(Directory.GetFiles(current2, searchPattern2, SearchOption.TopDirectoryOnly));
}
catch
{
}
}
return list;
}
}
try
{
list.AddRange(Directory.GetFiles(Directory.GetCurrentDirectory(), matchPattern, SearchOption.TopDirectoryOnly));
}
catch
{
}
return list;
}
private static List<string> GetMatchingDirectories(string rootDir, string pattern, int level)
{
if (level > 129)
{
return new List<string>();
}
List<string> list = new List<string>();
int num = pattern.IndexOf('*');
if (num >= 0)
{
int num2 = pattern.Substring(0, num).LastIndexOf(Path.DirectorySeparatorChar);
string text = (num2 >= 0) ? Path.Combine(rootDir, pattern.Substring(0, num2 + 1)) : rootDir;
if (text.Equals(string.Empty))
{
text = Directory.GetCurrentDirectory();
}
int num3 = pattern.IndexOf(Path.DirectorySeparatorChar, num);
if (num3 < 0)
{
num3 = pattern.Length;
}
string searchPattern = pattern.Substring(num2 + 1, num3 - num2 - 1);
try
{
string[] directories = Directory.GetDirectories(text, searchPattern, SearchOption.TopDirectoryOnly);
if (num3 < pattern.Length - 1)
{
string pattern2 = pattern.Substring(num3 + 1);
string[] array = directories;
for (int i = 0; i < array.Length; i++)
{
string rootDir2 = array[i];
list.AddRange(GetMatchingDirectories(rootDir2, pattern2, level + 1));
}
}
else
{
list.AddRange(directories);
}
return list;
}
catch
{
return list;
}
}
string text2 = Path.Combine(rootDir, pattern);
if (text2.Equals(string.Empty))
{
list.Add(Directory.GetCurrentDirectory());
}
else
{
if (Directory.Exists(text2))
{
list.Add(Path.GetFullPath(text2));
}
}
return list;
}
}
}

Resources