#445 FixTransilerations

This commit is contained in:
Hamid Reza Mohammadi 2024-07-21 15:15:22 +03:30
parent 6c96ac37d9
commit 13c77cd48f
4 changed files with 84 additions and 2 deletions

View File

@ -19320,6 +19320,11 @@
transilerate verse data from Persian to Tajiki
</summary>
</member>
<member name="M:RMuseum.Services.Implementation.GanjoorService.FixTransilerations">
<summary>
one time fix for transilerations
</summary>
</member>
<member name="M:RMuseum.Services.Implementation.GanjoorService.GetPoets(System.Boolean,System.Boolean)">
<summary>
Get List of poets

View File

@ -7,6 +7,7 @@ using System.Collections.Generic;
using RSecurityBackend.Services.Implementation;
using RMuseum.Utils;
using RMuseum.Models.Ganjoor;
using NAudio.Gui;
namespace RMuseum.Services.Implementation
{
@ -115,7 +116,67 @@ namespace RMuseum.Services.Implementation
});
}
/// <summary>
/// one time fix for transilerations
/// </summary>
public void FixTransilerations()
{
_backgroundTaskQueue.QueueBackgroundWorkItem
(
async token =>
{
using (RMuseumDbContext context = new RMuseumDbContext(new DbContextOptions<RMuseumDbContext>())) //this is long running job, so _context might be already been freed/collected by GC
{
LongRunningJobProgressServiceEF jobProgressServiceEF = new LongRunningJobProgressServiceEF(context);
var job = (await jobProgressServiceEF.NewJob($"FixTransilerations", "Query data")).Result;
try
{
var poets = await context.TajikPoets.ToListAsync();
foreach (var poet in poets)
{
poet.TajikNickname = LanguageUtils.CleanTextForTransileration(poet.TajikNickname);
poet.TajikDescription = LanguageUtils.CleanTextForTransileration(poet.TajikDescription);
context.Update(poet);
await context.SaveChangesAsync();
}
var cats = await context.TajikCats.ToListAsync();
foreach (var cat in cats)
{
cat.TajikTitle = LanguageUtils.CleanTextForTransileration(cat.TajikTitle);
cat.TajikDescription = LanguageUtils.CleanTextForTransileration(cat.TajikTitle);
context.Update(cat);
await context.SaveChangesAsync();
}
var poems = await context.TajikPoems.ToListAsync();
foreach(var poem in poems)
{
poem.TajikTitle = LanguageUtils.CleanTextForTransileration(poem.TajikTitle);
context.Update(poem);
await context.SaveChangesAsync();
}
var verses = await context.TajikVerses.ToListAsync();
foreach (var verse in verses)
{
verse.TajikText = LanguageUtils.CleanTextForTransileration(verse.TajikText);
context.Update(verse);
await context.SaveChangesAsync();
}
await jobProgressServiceEF.UpdateJob(job.Id, 100, "", true);
}
catch (Exception exp)
{
await jobProgressServiceEF.UpdateJob(job.Id, 100, "", false, exp.ToString());
}
}
});
}
}

View File

@ -76,6 +76,22 @@ namespace RMuseum.Services.Implementation
;
}
public static string CleanTextForTransileration(string text)
{
return text.Replace("‌", " ")//replace zwnj with space
.Replace("ّ", "")//tashdid
.Replace("َ", "")//a
.Replace("ِ", "")//e
.Replace("ُ", "")//o
.Replace("ً", "")//an
.Replace("ٍ", "")//en
.Replace("ٌ", "")//on
.Replace("ٔ", "")//ye
.Replace("ْ", "")//sokoon
;
}
public static string SameSoundLetters(string text)
{
return text.Replace("آ", "ا").Replace("ث", "س").Replace("ح", "ه").Replace("ذ", "ز").Replace("ص", "س").Replace("ض", "ز").Replace("ط", "ت").Replace("ظ", "ز").Replace("غ", "ق");

View File

@ -10,7 +10,7 @@ namespace RMuseum.Utils
{
public static string Transilerate(string input, string formDataForHassan)
{
input = LanguageUtils.MakeTextSearchable(input);
input = LanguageUtils.CleanTextForTransileration(input);
formDataForHassan = formDataForHassan.Replace("%D8%AD%D8%B3%D9%86", HttpUtility.UrlEncode(input));
HttpWebRequest request = HttpWebRequest.Create("http://persian-tajik.ir/farsitotajiki.aspx") as HttpWebRequest;