Nezih Aşula anezih

## unmunch.py
# This is "unmunching" script for Hunspell dictionaries, based on Spylls (full Python port of Hunspell):
# https://github.com/zverok/spylls
#
# "Unmunching" (Hunspell's term) is a process of turning affix-compressed dictionary into plain list
# of all language's words. E.g. for English, in the dictionary we have "spell/JSMDRZG" (stem + flags
# declaring what suffixes and prefixes it might have), and we can run this script:
#
#   python unmunch.py path/to/en_US spell
#
# Which will produce this list:

## TrCase.md

      
              2 files
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                anezih
                / TrCase.md
            
            
              Last active
              January 4, 2024 15:36
            
              
                Türkçe metinlerde büyük/küçük harf değiştiren Python sınıfı
              
          
    Türkçe metinleri doğru bir şekilde tamamı küçük harf (lowercase), tamamı büyük harf (uppercase) ve sözcüklerin ilk harflerinin büyük olduğu (title case) biçimlerine dönüştürmeye yarayan Python sınıfı. Bu sınıf Python'un büyük İ ve küçük ı konusunda yaşadığı beceriksizliği göz önüne alır. Ayrıca, metni başlık biçimine çevirirken "ve"nin küçük harfle başlamasına, tireden sonra gelen harfin de büyük harf olmasına özen gösterir (Kuruluş isimlerini dönüştürürken önemli).

  
## words.cs
using System.Collections.Generic;
using System.Linq;
using Hunspell;

namespace ConsoleApplication5
{
    class Program
    {
        static void Main(string[] args)
        {

## unxor.ps1
function unxor {
    param (
        [string]$text
    )
    $enc = [System.Text.Encoding]::BigEndianUnicode
    $key = $enc.GetBytes("ş")
    $bytes = $enc.GetBytes($text)

    $cycle = 0
    for ($i = 0; $i -lt $bytes.Length; $i++) {

## pocketbook2tsv.py
import os
import re
import sys
import zlib

from struct import unpack

OFFSET = 0x6B4

"""

## dictzip.py
# https://github.com/anezih/StarDictNet/blob/main/StarDictNet/DictZip.cs
# https://framagit.org/tuxor1337/dictzip.js/-/blob/main/dictzip_sync.js

import os
import zlib

from dataclasses import dataclass
from struct import unpack

class SUBFIELD:

## zemberek_python_word_gen.py
import pprint

from zemberek.morphology import TurkishMorphology
from zemberek.morphology.lexicon import RootLexicon
from zemberek.morphology.morphotactics.turkish_morphotactics import get_morpheme_map

MORPHOLOGY = TurkishMorphology.create_with_defaults()

def generate_noun(word, morphology):
    morpheme_map = get_morpheme_map()

## HunspellWordForms.csproj
<Project Sdk="Microsoft.NET.Sdk">

  <PropertyGroup>
    <TargetFramework>net7.0</TargetFramework>
    <Version>1.4.0</Version>
  </PropertyGroup>

  <ItemGroup Condition=" '$(TargetFramework)' == 'net7.0' ">
    <PackageReference Include="WeCantSpell.Hunspell" Version="4.0.0" />
  </ItemGroup>
	# This is "unmunching" script for Hunspell dictionaries, based on Spylls (full Python port of Hunspell):
	# https://github.com/zverok/spylls
	#
	# "Unmunching" (Hunspell's term) is a process of turning affix-compressed dictionary into plain list
	# of all language's words. E.g. for English, in the dictionary we have "spell/JSMDRZG" (stem + flags
	# declaring what suffixes and prefixes it might have), and we can run this script:
	#
	# python unmunch.py path/to/en_US spell
	#
	# Which will produce this list:
	using System.Collections.Generic;
	using System.Linq;
	using Hunspell;

	namespace ConsoleApplication5
	{
	class Program
	{
	static void Main(string[] args)
	{
	function unxor {
	param (
	[string]$text
	)
	$enc = [System.Text.Encoding]::BigEndianUnicode
	$key = $enc.GetBytes("ş")
	$bytes = $enc.GetBytes($text)

	$cycle = 0
	for ($i = 0; $i -lt $bytes.Length; $i++) {
	import os
	import re
	import sys
	import zlib

	from struct import unpack

	OFFSET = 0x6B4

	"""
	# https://github.com/anezih/StarDictNet/blob/main/StarDictNet/DictZip.cs
	# https://framagit.org/tuxor1337/dictzip.js/-/blob/main/dictzip_sync.js

	import os
	import zlib

	from dataclasses import dataclass
	from struct import unpack

	class SUBFIELD:
	import pprint

	from zemberek.morphology import TurkishMorphology
	from zemberek.morphology.lexicon import RootLexicon
	from zemberek.morphology.morphotactics.turkish_morphotactics import get_morpheme_map

	MORPHOLOGY = TurkishMorphology.create_with_defaults()

	def generate_noun(word, morphology):
	morpheme_map = get_morpheme_map()
	<Project Sdk="Microsoft.NET.Sdk">

	<PropertyGroup>
	<TargetFramework>net7.0</TargetFramework>
	<Version>1.4.0</Version>
	</PropertyGroup>

	<ItemGroup Condition=" '$(TargetFramework)' == 'net7.0' ">
	<PackageReference Include="WeCantSpell.Hunspell" Version="4.0.0" />
	</ItemGroup>