Hi,

This is an InputRange and RandomAccessRange combined; it's also the placement of wchar in possible null parts of dchar.

Please criticize this code. Each element of a UTF string is matched to its counterparts as dchar and used as wchar. The code is self-explanatory, do you think it's useful?

import std.stdio, std.algorithm;
import std.range, std.conv;

enum alphabets
{
  u = "ÂABCÇDEFGHIJKLMNOPQRSTUVĞİWXYZÖŞÜÇÎÛ",
  l = "âabcçdefghıjklmnopqrstuvğiwxyzöşüçîû",

  ASCII65_95 = "AABCCDEFGHIJKLMNOPQRSTUVGIWXYZOSUCIU",
  ASCII96_127 = "aabccdefghijklmnopqrstuvgiwxyzosuciu",
  ASCII65_127 = ASCII65_95 ~ ASCII96_127
}

//enum dictU = alphabets.u.to!(wchar[]);
enum dictU = "ÂABCÇDEFGHIJKLMNOPQRSTUVĞİWXYZÖŞÜÇÎÛ".to!(wchar[]);
enum dictL = alphabets.l.to!(wchar[]);

struct MixString(T, T[] leftLiterals)
{
  size_t index;
  dchar[] dict;

  this(string d)
  {
    // load dictionary
    foreach(dchar c; d) dict ~= c;

    // place counterparts
    foreach(i, wchar c; leftLiterals)
    {
      dict[i] |= c << 16;
    }
  }

  // input range functions
  bool empty() { return index == dict.length; }
  T front() { return dict[index] & 0x0000_FFFF; }
  void popFront() { ++index; }

  // search elements
  auto nextIndexOf(wchar key)
  {
    scope(exit) index = 0;

    size_t i = 1;
    while(!empty)
    {
      if(front == key)
      {
        return i;
      } else i++;
      popFront();
    }
    return 0;
  }
}
//
alias ConvUpper = MixString!(wchar, dictU);
alias ConvLower = MixString!(wchar, dictL);

void main()
{
  auto test = ConvUpper(alphabets.l);/*
  foreach(wchar c; test)
  {
    c.writefln!"%4X: %s"(c);
  }//*/

  string text = "fıstıkçı şâhap bir insandır!";
  foreach(wchar c; text)
  {
    if(auto result = test.nextIndexOf(c))
    {
      wchar lookup = test.dict[result - 1] >> 16;
      lookup.write;
    } else
      c.write;
  }
  writeln;
}
/*

FISTIKÇI ŞÂHAP BİR İNSANDIR!

*/

SDB@79

On Saturday, 2 September 2023 at 14:20:58 UTC, Richard (Rikki) Andrew Cattermole wrote:

I don't think speed is a big issue because a thousand pages and possibly 47 letters old text (kutadgu-bilig-fergana-holograph.txt: ~ 2 MB.) is completed in under 1 second. The conversion done includes reading from the file, finding the counterparts, and writing to the file...

For-example:

enum abece
{
  b = "AEINRLİDKMUYTBSOÜŞZGÇHĞVCÖPFJXWÂÎÛĖĀĪŪĦŜŊĠŻṬẒḲĮ".to!(wchar[]),
  k = "aeınrlidkmuytbsoüşzgçhğvcöpfjxwâîûėāīūħŝŋġżṭẓḳį".to!(wchar[]),
  ele = "gusiocCOISUG".to!(wchar[])
}

void main()
{
  alias MSbyk = MixString!(wchar, abece.b);
  enum bütünSözlük = "aeınrlidkmuytbsoüşzgçhğvcöpfjxwâîûėāīūħŝŋġżṭẓḳį"; // abece.k.to!string;
  auto büyük = MSbyk(bütünSözlük);

  // Source: https://archive.org/download/kutadgu-bilig-fergana-nushasi/681053_djvu.txt
  auto dosya = File("KutadguBilig.txt", "r");
  while (!dosya.eof)
  {
    foreach(wchar c; dosya.readln)
    {
      if(auto result = büyük.nextIndexOf(c))
      {
        wchar lookup = büyük.dict[result - 1] >> 16;
        lookup.write;
      } else {
        c.write;
      }
    }
    writeln;
  }
} /*
pico@enpi:~/Projeler/NewLookup$ time ./newLookupTable > result.txt

real  0m0,875s
user  0m0,859s
sys   0m0,016s
*/

On Saturday, 2 September 2023 at 14:20:58 UTC, Richard (Rikki) Andrew Cattermole wrote:

Thank you, I will read the book you mentioned.

SDB@79

On Sunday, 3 September 2023 at 10:36:58 UTC, Salih Dincer wrote:

enum abece
{
  b = "AEINRLİDKMUYTBSOÜŞZGÇHĞVCÖPFJXWÂÎÛĖĀĪŪĦŜŊĠŻṬẒḲĮ".to!(wchar[]),
  k = "aeınrlidkmuytbsoüşzgçhğvcöpfjxwâîûėāīūħŝŋġżṭẓḳį".to!(wchar[]),
  ele = "gusiocCOISUG".to!(wchar[])
}

void main()
{
  alias MSbyk = MixString!(wchar, abece.b);
  enum bütünSözlük = "aeınrlidkmuytbsoüşzgçhğvcöpfjxwâîûėāīūħŝŋġżṭẓḳį"; // abece.k.to!string;

I wonder why I can't use abece.k directly. The error it gives is as follows:

> core.exception.ArrayIndexError@newLookupTable.d(39):
> index [1] is out of bounds for array of length 1

SDB@79