Merge pull request #8383 from OmrSi/include-composition-characters

Add an option to include composition characters in Line Length
2024-11-22 11:12:36 +01:00 · 2024-05-17 18:30:12 +02:00 · 2024-05-17 18:30:12 +02:00 · 712de43cec
commit 712de43cec
parent fc1e640409 c147f3929f
34 changed files with 71 additions and 75 deletions
--- a/LanguageBaseEnglish.xml
+++ b/LanguageBaseEnglish.xml
@ -2545,8 +2545,8 @@ can edit in same subtitle file (collaboration)</Information>
    <CpsLineLengthStyleCalcNoSpace>Count all except space</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, Latin 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, Latin 0.5, space 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignore Arabic diacritics</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignore Arabic diacritics/space</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
+    <CpsLineLengthStyleCalcIncludeCompositionCharacters>Include composition characters</CpsLineLengthStyleCalcIncludeCompositionCharacters>
+    <CpsLineLengthStyleCalcIncludeCompositionCharactersNotSpace>Include composition characters, not space</CpsLineLengthStyleCalcIncludeCompositionCharactersNotSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>No space or punctuation ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>No space or punctuation, cps only</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Music symbol</MusicSymbol>
--- a/src/libse/Common/Settings.cs
+++ b/src/libse/Common/Settings.cs
@ -1920,7 +1920,7 @@ $HorzAlign          =   Center
                SubtitleMaximumDisplayMilliseconds = 7007,
                SubtitleMinimumDisplayMilliseconds = 1000,
                SubtitleMaximumWordsPerMinute = 240,
-                CpsLineLengthStrategy = typeof(CalcIgnoreArabicDiacritics).Name,
+                CpsLineLengthStrategy = typeof(CalcAll).Name,
                MinimumMillisecondsBetweenLines = 83, // 2 frames for 23.976 fps videos
                DialogStyle = DialogType.DashBothLinesWithSpace,
                ContinuationStyle = ContinuationStyle.NoneLeadingTrailingEllipsis,
--- a/src/libse/Common/TextLengthCalculator/CalcAll.cs
+++ b/src/libse/Common/TextLengthCalculator/CalcAll.cs
@ -5,7 +5,7 @@ namespace Nikse.SubtitleEdit.Core.Common.TextLengthCalculator
    public class CalcAll : ICalcLength
    {
        /// <summary>
-        /// Calculate length of all text including space (tags are not counted).
+        /// Calculate length of all text including space but excluding composition characters (tags are not counted).
        /// </summary>
        public decimal CountCharacters(string text, bool forCps)
        {
--- a/src/libse/Common/TextLengthCalculator/CalcFactory.cs
+++ b/src/libse/Common/TextLengthCalculator/CalcFactory.cs
@ -12,8 +12,8 @@ namespace Nikse.SubtitleEdit.Core.Common.TextLengthCalculator
            new CalcNoSpace(),
            new CalcCjk(),
            new CalcCjkNoSpace(),
-            new CalcIgnoreArabicDiacritics(),
-            new CalcIgnoreArabicDiacriticsNoSpace(),
+            new CalcIncludeCompositionCharacters(),
+            new CalcIncludeCompositionCharactersNotSpace(),
            new CalcNoSpaceOrPunctuation(),
            new CalcNoSpaceOrPunctuationCpsOnly(),
        };
--- a/src/libse/Common/TextLengthCalculator/CalcIgnoreThaiCompositeCharacters.cs
+++ b/src/libse/Common/TextLengthCalculator/CalcIgnoreThaiCompositeCharacters.cs
@ -2,12 +2,10 @@

 namespace Nikse.SubtitleEdit.Core.Common.TextLengthCalculator
 {
-    public class CalcIgnoreThaiCompositeCharacters : ICalcLength
+    public class CalcIncludeCompositionCharacters : ICalcLength
    {
        /// <summary>
-        /// Calculate all text excluding Thai composite characters (tags are not counted).
-        /// Netflix rule: 35 characters per line (excluding all composite characters, i.e. tone marks, top and bottom vowels are not counted.
-        /// See https://partnerhelp.netflixstudios.com/hc/en-us/articles/220448308-Thai-Timed-Text-Style-Guide
+        /// Calculate all text including composition characters (tags are not counted).
        /// </summary>
        public decimal CountCharacters(string text, bool forCps)
        {
@ -31,14 +29,15 @@ namespace Nikse.SubtitleEdit.Core.Common.TextLengthCalculator
                        ch != '\u202B' &&
                        ch != '\u202C' &&
                        ch != '\u202D' &&
-                        ch != '\u202E')
+                        ch != '\u202E' &&
+                        !(ch >= '\u064B' && ch <= '\u0653'))
                    {
                        length++;
                    }
                }
                else
                {
-                    length++;
+                    length += element.Length;
                }
            }

--- a/src/libse/Common/TextLengthCalculator/CalcIncludeCompositionCharactersNotSpace.cs
+++ b/src/libse/Common/TextLengthCalculator/CalcIncludeCompositionCharactersNotSpace.cs
@ -0,0 +1,48 @@
+using System.Globalization;
+
+namespace Nikse.SubtitleEdit.Core.Common.TextLengthCalculator
+{
+    public class CalcIncludeCompositionCharactersNotSpace : ICalcLength
+    {
+        /// <summary>
+        /// Calculate all text including composition characters but not space (tags are not counted).
+        /// </summary>
+        public decimal CountCharacters(string text, bool forCps)
+        {
+            var s = HtmlUtil.RemoveHtmlTags(text, true);
+
+            const char zeroWidthSpace = '\u200B';
+            const char zeroWidthNoBreakSpace = '\uFEFF';
+            var length = 0;
+            for (var en = StringInfo.GetTextElementEnumerator(s); en.MoveNext();)
+            {
+                var element = en.GetTextElement();
+                if (element.Length == 1)
+                {
+                    var ch = element[0];
+                    if (!char.IsControl(ch) &&
+                        ch != ' ' &&
+                        ch != zeroWidthSpace &&
+                        ch != zeroWidthNoBreakSpace &&
+                        ch != '\u200E' &&
+                        ch != '\u200F' &&
+                        ch != '\u202A' &&
+                        ch != '\u202B' &&
+                        ch != '\u202C' &&
+                        ch != '\u202D' &&
+                        ch != '\u202E' &&
+                        !(ch >= '\u064B' && ch <= '\u0653'))
+                    {
+                        length++;
+                    }
+                }
+                else
+                {
+                    length += element.Length;
+                }
+            }
+
+            return length;
+        }
+    }
+}
--- a/src/libse/NetflixQualityCheck/NetflixCheckMaxCps.cs
+++ b/src/libse/NetflixQualityCheck/NetflixCheckMaxCps.cs
@ -29,11 +29,6 @@ namespace Nikse.SubtitleEdit.Core.NetflixQualityCheck
                    calc = CalcFactory.MakeCalculator(nameof(CalcCjk));
                }

-                if (controller.Language == "ar")
-                {
-                    calc = CalcFactory.MakeCalculator(nameof(CalcIgnoreArabicDiacritics));
-                }
-
                var charactersPerSeconds = Utilities.GetCharactersPerSecond(jp, calc);
                if (charactersPerSeconds > charactersPerSecond && !p.StartTime.IsMaxTime)
                {
--- a/src/ui/Languages/ar-EG.xml
+++ b/src/ui/Languages/ar-EG.xml
@ -2521,8 +2521,6 @@ ames.xml)</FixOnlyNamesCasing>
    <CpsLineLengthStyleCalcNoSpace>عد كل شيء باستثناء الفضاء</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1، اللاتينية 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1، اللاتينية 0.5، المسافة 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>تجاهل علامات التشكيل العربية</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>تجاهل علامات التشكيل/المسافة العربية</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>بدون مسافة أو علامات ترقيم ()[]-:;,.!؟</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>لا يوجد مسافة أو علامات الترقيم، CPS فقط</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>رمز الموسيقى</MusicSymbol>
--- a/src/ui/Languages/bg-BG.xml
+++ b/src/ui/Languages/bg-BG.xml
@ -2546,8 +2546,6 @@ https://github.com/SubtitleEdit/subtitleedit
    <CpsLineLengthStyleCalcNoSpace>Преброяване на всички, без интервалите</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, латински 0,5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, латински 0,5, интервал 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Игнорирай Арабските диакритични символи</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Игнорирай Арабските диакритични символи/интервал</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Без интервал или препинателни знаци ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Без интервал или препинателни знаци, само cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Замяна с музикален символ:</MusicSymbol>
--- a/src/ui/Languages/da-DK.xml
+++ b/src/ui/Languages/da-DK.xml
@ -2535,8 +2535,6 @@ kan redigere i samme undertekst fil (fælles online projekt)</Information>
    <CpsLineLengthStyleCalcNoSpace>Tæl alle undtagen mellemrum</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, latin 0,5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, latin 0,5, mellemrum 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignorer arabiske diakritiske tegn</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignorer arabiske diakritiske tegn/mellemrum</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Intet mellemrum eller tegnsætning ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Ingen mellemrum eller tegnsætning, kun cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Musik symbol</MusicSymbol>
--- a/src/ui/Languages/de-DE.xml
+++ b/src/ui/Languages/de-DE.xml
@ -2563,8 +2563,6 @@ Wir nutzen den dem Bild innewohnenden Rhythmus.</CreateSimpleChainingToolTip>
    <CpsLineLengthStyleCalcNoSpace>Zählen Sie alle außer Leerzeichen</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, Latein 0,5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, Latein 0,5, Leerzeichen 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignorieren Sie arabische diakritische Zeichen</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignorieren Sie arabische diakritische Zeichen/Leerzeichen</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Kein Leerzeichen oder Satzzeichen ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Kein Leerzeichen oder Satzzeichen, nur cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Musik Symbol</MusicSymbol>
--- a/src/ui/Languages/el-GR.xml
+++ b/src/ui/Languages/el-GR.xml
@ -2516,8 +2516,6 @@ Email: mailto:nikse.dk@gmail.com</AboutText1>
    <CpsLineLengthStyleCalcNoSpace>Υπολογισμός όλων πλην κενών</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, λατινικοί 0,5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, λατινικοί 0,5, κενό 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Αγνόηση αραβικών διακριτικών</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Αγνόηση αραβικών διακριτικών/κενών</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Χωρίς κενά και σημεία στίξης</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Χωρίς κενά και σημεία στίξης, χαρακτ./δευτ. μόνο</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Μουσικό σύμβολο</MusicSymbol>
--- a/src/ui/Languages/es-AR.xml
+++ b/src/ui/Languages/es-AR.xml
@ -2532,8 +2532,6 @@ puede editar el mismo archivo de subtítulo (colaboración)</Information>
    <CpsLineLengthStyleCalcNoSpace>Contar todo excepto los espacios</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, Latín 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, Latín 0.5, espacios 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignorar diacríticos árabes</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignorar diacríticos árabes/espacios</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Sin espacios ni signos de puntuación ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Sin espacios ni puntuación, solo cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Símbolos musicales</MusicSymbol>
--- a/src/ui/Languages/es-ES.xml
+++ b/src/ui/Languages/es-ES.xml
@ -2335,8 +2335,6 @@ puede editar el mismo archivo de subtítulo (colaboración)</Information>
    <CpsLineLengthStyleCalcNoSpace>Contar todo excepto los espacios</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, Latín 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, Latín 0.5, espacios 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignorar diacríticos árabes</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignorar diacríticos árabes/espacios</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Sin espacios ni signos de puntuación ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Sin espacios ni puntuación, solo cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Símbolos musicales</MusicSymbol>
--- a/src/ui/Languages/es-MX.xml
+++ b/src/ui/Languages/es-MX.xml
@ -2532,8 +2532,6 @@ puedan editar el mismo archivo de subtítulo (colaboración)</Information>
    <CpsLineLengthStyleCalcNoSpace>Contar todo excepto los espacios</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, Latín 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, Latín 0.5, espacios 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignorar diacríticos árabes</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignorar diacríticos árabes/espacios</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Sin espacios ni signos de puntuación ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Sin espacios ni puntuación, solo cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Símbolos musicales</MusicSymbol>
--- a/src/ui/Languages/fi-FI.xml
+++ b/src/ui/Languages/fi-FI.xml
@ -2527,8 +2527,6 @@ Mikäli tiedostoa on muokattu Subtitle Edit:llä, varmuuskopio voi olla käytett
    <CpsLineLengthStyleCalcNoSpace>Laske kaikki paitsi välilyönnit</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, latin 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, latin 0.5, välilyönti 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Jätä huomioimatta arabian diakriittiset merkinnnät</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Jätä huomioimatta arabian diakriittiset merkinnnät / välilyönnit</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Ei välilyöntiä tai välimerkkejä ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Ei välilyöntiä tai välimerkkejä, vain merkit</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Musiikkisymboli</MusicSymbol>
--- a/src/ui/Languages/fr-FR.xml
+++ b/src/ui/Languages/fr-FR.xml
@ -2515,8 +2515,6 @@ peuvent éditer le même fichier sous-titres (collaboration)</Information>
    <CpsLineLengthStyleCalcNoSpace>Compter tout sauf blancs</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, latin 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, latin 0.5, blanc 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignorer les diacritiques arabes</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignorer les diacritiques arabes/blanc</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Pas d'espace / ponctuation ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Pas d'espace / ponctuation, majusc.</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Symbole musical</MusicSymbol>
--- a/src/ui/Languages/he-IL.xml
+++ b/src/ui/Languages/he-IL.xml
@ -2348,8 +2348,6 @@ If you have edited this file with Subtitle Edit you might be able to find a back
    <CpsLineLengthStyleCalcNoSpace>ספור הכל מלבד החלל</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, לטינית 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, לטינית 0.5, רווח 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>התעלם מהדיאקריטיות בערבית</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>התעלם מהדיאקריטיות/רווח בערבית</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>אין רווח או סימני פיסוק ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>ללא רווח או סימני פיסוק, cps בלבד</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>סמל מוזיקה</MusicSymbol>
--- a/src/ui/Languages/hu-HU.xml
+++ b/src/ui/Languages/hu-HU.xml
@ -2342,8 +2342,6 @@ szerkesztheti ugyanazt a feliratfájlt (együttműködés)</Information>
    <CpsLineLengthStyleCalcNoSpace>Összes számolása a szóközt kivéve</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, Latin 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, Latin 0.5, szóköz 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Az arab diakritikus jelek figyelmen kívül hagyása</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Az arab diakritikus jelek/közök figyelmen kívül hagyása</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Nincs szóköz vagy írásjel ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Nincs szóköz vagy írásjel, csak cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Zene szimbólum</MusicSymbol>
--- a/src/ui/Languages/it-IT.xml
+++ b/src/ui/Languages/it-IT.xml
@ -2545,8 +2545,6 @@ stesso file di sottotitolo (collaborazione)</Information>
    <CpsLineLengthStyleCalcNoSpace>Conta tutto tranne gli spazi</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, latino 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, latino 0.5, spazio 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignora i segni diacritici arabi</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignora i segni diacritici arabi/spazi</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Nessuno spazio o punteggiatura ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Nessuno spazio o punteggiatura, solo cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Sostituisci con simbolo musicale:</MusicSymbol>
--- a/src/ui/Languages/ko-KR.xml
+++ b/src/ui/Languages/ko-KR.xml
@ -2542,8 +2542,6 @@ FFmpeg를 다운로드하고 사용하시겠습니까?</FfmpegNotFound>
    <CpsLineLengthStyleCalcNoSpace>모든 공백을 제외한 수</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>한중일 1, 라틴어 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>한중일 1, 라틴어 0.5, 공백 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>아랍어 분음부 무시</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>아랍어 분음부/공백 무시</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>공백 또는 구두점()[]-:;,.!? 없음</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>공백 또는 구두점 없음, cps 만</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>음표</MusicSymbol>
--- a/src/ui/Languages/nl-NL.xml
+++ b/src/ui/Languages/nl-NL.xml
@ -2527,8 +2527,6 @@ hetzelfde ondertitelbestand bewerken (samenwerken)</Information>
    <CpsLineLengthStyleCalcNoSpace>Alle tekens behalve spaties meetellen</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, Latin 0,5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, Latin 0,5, spatie 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Arabische diakritische tekens negeren</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Arabische diakritische tekens/spaties negeren</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Geen spaties of interpunctie ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Geen spaties of interpunctie, alleen voor CPS</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Vervangend muzieksymbool</MusicSymbol>
--- a/src/ui/Languages/pl-PL.xml
+++ b/src/ui/Languages/pl-PL.xml
@ -2531,8 +2531,6 @@ może edytować ten sam plik napisów (współpraca)</Information>
    <CpsLineLengthStyleCalcNoSpace>Policz wszystko oprócz spacji</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, Latin 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, Latin 0.5, spacja 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignoruj arabskie znaki diakrytyczne</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignoruj arabskie znaki diakrytyczne/spacje</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Brak spacji i znaków interpunkcji ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Bez spacji i znaków interpunkcyjnych, tylko ZNS</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Symbol muzyczny</MusicSymbol>
--- a/src/ui/Languages/pt-BR.xml
+++ b/src/ui/Languages/pt-BR.xml
@ -2535,8 +2535,6 @@ podem editar o mesmo arquivo de legenda (colaboração)</Information>
 		<CpsLineLengthStyleCalcNoSpace>Contar todos, menos espaços</CpsLineLengthStyleCalcNoSpace>
 		<CpsLineLengthStyleCalcCjk>CJK 1, latino 0.5</CpsLineLengthStyleCalcCjk>
 		<CpsLineLengthStyleCalcCjkNoSpace>CJK 1, latino 0.5, espaço 0</CpsLineLengthStyleCalcCjkNoSpace>
-		<CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignorar diacríticos em árabe</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-		<CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignorar diacríticos/espaço em árabe</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
 		<CpsLineLengthStyleCalcNoSpaceOrPunctuation>Sem espaço ou pontuação ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
 		<CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Sem espaço ou pontuação, somente cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
 		<MusicSymbol>Símbolo musical</MusicSymbol>
--- a/src/ui/Languages/pt-PT.xml
+++ b/src/ui/Languages/pt-PT.xml
@ -2546,8 +2546,6 @@ editar o mesmo ficheiro de legenda (colaboração)</Information>
    <CpsLineLengthStyleCalcNoSpace>Contar todos excepto o espaço</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, Latin 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, Latin 0.5, espaço 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignorar diacríticos em árabe</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignorar diacríticos/espaço em árabe</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Sem espaço ou pontuação ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Sem espaço ou pontuação, apenas cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Símbolo musical</MusicSymbol>
--- a/src/ui/Languages/ru-RU.xml
+++ b/src/ui/Languages/ru-RU.xml
@ -2553,8 +2553,6 @@ https://github.com/SubtitleEdit/subtitleedit
    <CpsLineLengthStyleCalcNoSpace>Исключить пробелы</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, латиница 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, латиница 0.5, пробел 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Игнор. арабскую диакритику</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Игнор. арабскую диакритику/пробел</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Без пробелов и знак. преп. ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Без пробелов и знак. преп., только CPS</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Музыкальный символ</MusicSymbol>
--- a/src/ui/Languages/sl-SI.xml
+++ b/src/ui/Languages/sl-SI.xml
@ -2360,8 +2360,6 @@ lahko ureja v isti datoteki s podnapisi (sodelovanje)</Information>
    <CpsLineLengthStyleCalcNoSpace>Preštej vse razen presledka</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, latinica 0,5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, latinica 0,5, presledek 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Prezri arabske diakritične znake</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Prezri arabske diakritične znake/presledek</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Brez presledkov ali ločil ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Brez presledkov ali ločil, samo cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Glasbeni simbol</MusicSymbol>
--- a/src/ui/Languages/sv-SE.xml
+++ b/src/ui/Languages/sv-SE.xml
@ -2544,8 +2544,6 @@ kan redigera i samma undertextfil (samarbete)</Information>
    <CpsLineLengthStyleCalcNoSpace>Räkna alla utom mellanslag</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, latin 0,5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, latin 0,5, mellanslag 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Ignorera arabiska diakritiska tecken</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Ignorera arabiska diakritiska tecken/mellanslag</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>Inget mellanslag eller skiljetecken ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>Inget mellanslag eller skiljetecken, endast cps</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>Musiksymbol</MusicSymbol>
--- a/src/ui/Languages/vi-VN.xml
+++ b/src/ui/Languages/vi-VN.xml
@ -2257,8 +2257,6 @@ có thể chỉnh sửa trong cùng một tập tin phụ đề (hợp tác vớ
    <CpsLineLengthStyleCalcNoSpace>Đếm tất cả ngoại trừ dấu cách</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1, latin 0,5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1, latin 0,5, dấu cách 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>Bỏ qua các dấu phụ tiếng Ả Rập</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>Bỏ qua dấu/dấu cách tiếng Ả Rập</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <MusicSymbol>Kí hiệu Âm nhạc</MusicSymbol>
    <MusicSymbolsReplace>Các ký hiệu âm nhạc cần thay thế (phân tách bằng dấu phẩy)</MusicSymbolsReplace>
    <FixCommonOcrErrorsUseHardcodedRules>Sửa lỗi OCR phổ biến - cũng sử dụng quy tắc hardcoded</FixCommonOcrErrorsUseHardcodedRules>
--- a/src/ui/Languages/zh-Hans.xml
+++ b/src/ui/Languages/zh-Hans.xml
@ -2531,8 +2531,6 @@ Command line: {1} {2}
    <CpsLineLengthStyleCalcNoSpace>统计除空格外的字符</CpsLineLengthStyleCalcNoSpace>
    <CpsLineLengthStyleCalcCjk>CJK 1，拉丁文 0.5</CpsLineLengthStyleCalcCjk>
    <CpsLineLengthStyleCalcCjkNoSpace>CJK 1，拉丁文 0.5，空格 0</CpsLineLengthStyleCalcCjkNoSpace>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacritics>忽略阿拉伯语变音符号</CpsLineLengthStyleCalcIgnoreArabicDiacritics>
-    <CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>忽略阿拉伯语变音符号/空格</CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuation>忽略空格或标点符号 ()[]-:;,.!?</CpsLineLengthStyleCalcNoSpaceOrPunctuation>
    <CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>忽略空格或标点符号，仅显示每秒字频</CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly>
    <MusicSymbol>音符</MusicSymbol>
--- a/src/ui/Logic/CpsLineLength.cs
+++ b/src/ui/Logic/CpsLineLength.cs
@ -19,10 +19,10 @@ namespace Nikse.SubtitleEdit.Logic
                    return LanguageSettings.Current.Settings.CpsLineLengthStyleCalcCjk;
                case nameof(CalcCjkNoSpace):
                    return LanguageSettings.Current.Settings.CpsLineLengthStyleCalcCjkNoSpace;
-                case nameof(CalcIgnoreArabicDiacritics):
-                    return LanguageSettings.Current.Settings.CpsLineLengthStyleCalcIgnoreArabicDiacritics;
-                case nameof(CalcIgnoreArabicDiacriticsNoSpace):
-                    return LanguageSettings.Current.Settings.CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace;
+                case nameof(CalcIncludeCompositionCharacters):
+                    return LanguageSettings.Current.Settings.CpsLineLengthStyleCalcIncludeCompositionCharacters;
+                case nameof(CalcIncludeCompositionCharactersNotSpace):
+                    return LanguageSettings.Current.Settings.CpsLineLengthStyleCalcIncludeCompositionCharactersNotSpace;
                case nameof(CalcNoSpaceOrPunctuation):
                    return LanguageSettings.Current.Settings.CpsLineLengthStyleCalcNoSpaceOrPunctuation;
                case nameof(CalcNoSpaceOrPunctuationCpsOnly):
--- a/src/ui/Logic/Language.cs
+++ b/src/ui/Logic/Language.cs
@ -2895,8 +2895,8 @@ can edit in same subtitle file (collaboration)",
                CpsLineLengthStyleCalcNoSpace = "Count all except space",
                CpsLineLengthStyleCalcCjk = "CJK 1, Latin 0.5",
                CpsLineLengthStyleCalcCjkNoSpace = "CJK 1, Latin 0.5, space 0",
-                CpsLineLengthStyleCalcIgnoreArabicDiacritics = "Ignore Arabic diacritics",
-                CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace = "Ignore Arabic diacritics/space",
+                CpsLineLengthStyleCalcIncludeCompositionCharacters = "Include composition characters",
+                CpsLineLengthStyleCalcIncludeCompositionCharactersNotSpace = "Include composition characters, not space",
                CpsLineLengthStyleCalcNoSpaceOrPunctuation = "No space or punctuation ()[]-:;,.!?",
                CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly = "No space or punctuation, cps only",
                ContinuationStyleNone = "None",
--- a/src/ui/Logic/LanguageDeserializer.cs
+++ b/src/ui/Logic/LanguageDeserializer.cs
@ -6922,11 +6922,11 @@ namespace Nikse.SubtitleEdit.Logic
                case "Settings/CpsLineLengthStyleCalcCjkNoSpace":
                    language.Settings.CpsLineLengthStyleCalcCjkNoSpace = reader.Value;
                    break;
-                case "Settings/CpsLineLengthStyleCalcIgnoreArabicDiacritics":
-                    language.Settings.CpsLineLengthStyleCalcIgnoreArabicDiacritics = reader.Value;
+                case "Settings/CpsLineLengthStyleCalcIncludeCompositionCharacters":
+                    language.Settings.CpsLineLengthStyleCalcIncludeCompositionCharacters = reader.Value;
                    break;
-                case "Settings/CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace":
-                    language.Settings.CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace = reader.Value;
+                case "Settings/CpsLineLengthStyleCalcIncludeCompositionCharactersNotSpace":
+                    language.Settings.CpsLineLengthStyleCalcIncludeCompositionCharactersNotSpace = reader.Value;
                    break;
                case "Settings/CpsLineLengthStyleCalcNoSpaceOrPunctuation":
                    language.Settings.CpsLineLengthStyleCalcNoSpaceOrPunctuation = reader.Value;
--- a/src/ui/Logic/LanguageStructure.cs
+++ b/src/ui/Logic/LanguageStructure.cs
@ -2718,8 +2718,8 @@
            public string CpsLineLengthStyleCalcNoSpace { get; set; }
            public string CpsLineLengthStyleCalcCjk { get; set; }
            public string CpsLineLengthStyleCalcCjkNoSpace { get; set; }
-            public string CpsLineLengthStyleCalcIgnoreArabicDiacritics { get; set; }
-            public string CpsLineLengthStyleCalcIgnoreArabicDiacriticsNoSpace { get; set; }
+            public string CpsLineLengthStyleCalcIncludeCompositionCharacters { get; set; }
+            public string CpsLineLengthStyleCalcIncludeCompositionCharactersNotSpace { get; set; }
            public string CpsLineLengthStyleCalcNoSpaceOrPunctuation { get; set; }
            public string CpsLineLengthStyleCalcNoSpaceOrPunctuationCpsOnly { get; set; }
            public string MusicSymbol { get; set; }