Merge branch 'master' into split-line

Dictionaries/eng_OCRFixReplaceList.xml

@@ -201,7 +201,7 @@
     <Word from="can*t" to="can't" />
     <Word from="can'i" to="can't" />
     <Word from="can'I" to="can't" />
-    <Word from="canlgetyou" to="canI get you" />
+    <Word from="canlgetyou" to="can I get you" />
     <Word from="cannotchange" to="cannot change" />
     <Word from="cannut" to="cannot" />
     <Word from="can'T" to="can't" />
@@ -404,7 +404,6 @@
     <Word from="forthe" to="for the" />
     <Word from="Foryears" to="For years" />
     <Word from="foryou" to="for you" />
-    <Word from="Foudeen" to="Fouteen" />
     <Word from="Foufleen" to="Fourteen" />
     <Word from="FourSeasons" to="Four Seasons" />
     <Word from="fr/ends" to="friends" />
@@ -1347,7 +1346,6 @@
     <Word from="vi/ay" to="way" />
     <Word from="visitjails" to="visit jails" />
     <Word from="Viva/di's" to="Vivaldi's" />
-    <Word from="vlll" to="vill" />
     <Word from="Voilá" to="Voilà" />
     <Word from="Voilé" to="Voilà" />
     <Word from="vvasjust" to="was just" />
@@ -2243,7 +2241,6 @@
     <Word from="Goodjob" to="Good job" />
     <Word from="google" to="Google" />
     <Word from="gothere" to="go there" />
-    <Word from="gotta" to="got to" />
     <Word from="grafier" to="grafter" />
     <Word from="granddad" to="grandad" />
     <Word from="Granddad" to="Grandad" />
@@ -2342,9 +2339,9 @@
     <Word from="lasagna" to="lasagne" />
     <Word from="leastpeople" to="least people" />
     <Word from="lfl" to="if I" />
-    <Word from="lfthafs" to="lf that's" />
+    <Word from="lfthafs" to="if that's" />
-    <Word from="lfthis" to="lf this" />
+    <Word from="lfthis" to="if this" />
-    <Word from="lfwe're" to="lf we're" />
+    <Word from="lfwe're" to="if we're" />
     <Word from="lifeform" to="life form" />
     <Word from="lightspeed" to="light speed" />
     <Word from="limón" to="lemon" />
@@ -2489,7 +2486,6 @@
     <Word from="shouldthinkthey're" to="should think they're" />
     <Word from="skeleton in the closet" to="skeleton in the cupboard" />
     <Word from="slipthrough" to="slip through" />
-    <Word from="smackeroonyos" to="smackeroonios" />
     <Word from="smanish" to="smartish" />
     <Word from="smith/es" to="smithies" />
     <Word from="someplace" to="some place" />
@@ -2508,7 +2504,6 @@
     <Word from="sufferthe" to="suffer the" />
     <Word from="swifier" to="swifter" />
     <Word from="t0" to="to" />
-    <Word from="tabnur" to="taboor" />
     <Word from="takeJuma" to="take Juma" />
     <Word from="takethe" to="take the" />
     <Word from="tatking" to="talking" />

installer/Subtitle_Edit_installer.iss

@@ -22,8 +22,8 @@
 
 
 ; preprocessor checks
-#if VER < EncodeVer(5,5,9)
+#if VER < EncodeVer(5,6,0)
-  #error Update your Inno Setup version (5.5.9 or newer)
+  #error Update your Inno Setup version (5.6.0 or newer)
 #endif
 
 #ifndef UNICODE
@@ -31,7 +31,7 @@
 #endif
 
 
-#define app_copyright "Copyright © 2001-2018, Nikse"
+#define app_copyright "Copyright © 2001-2019, Nikse"
 ; If you don't define "localize", i.e. comment out the following line then no translations
 ; for SubtitleEdit or the installer itself will be included in the installer
 #define localize
@@ -88,7 +88,7 @@ UninstallDisplayIcon={app}\SubtitleEdit.exe
 DefaultDirName={pf}\Subtitle Edit
 DefaultGroupName=Subtitle Edit
 VersionInfoVersion={#app_ver_full}
-MinVersion=5.1
+MinVersion=5.6
 LicenseFile=..\LICENSE.txt
 InfoAfterFile=..\Changelog.txt
 SetupIconFile=..\src\Icons\SE.ico

libse/Dictionaries/OcrFixReplaceList.cs

@@ -104,7 +104,7 @@ namespace Nikse.SubtitleEdit.Core.Dictionaries
             {
                 foreach (XmlNode item in node.ChildNodes)
                 {
-                    if (item.Attributes != null && HasValidAttributes(item, false))
+                    if (HasValidAttributes(item, false))
                     {
                         string to = item.Attributes["to"].Value;
                         string from = item.Attributes["from"].Value;
@@ -132,7 +132,7 @@ namespace Nikse.SubtitleEdit.Core.Dictionaries
             {
                 foreach (XmlNode item in node.ChildNodes)
                 {
-                    if (item.Attributes != null && HasValidAttributes(item, true))
+                    if (HasValidAttributes(item, true))
                     {
                         string to = item.Attributes["replaceWith"].Value;
                         string from = item.Attributes["find"].Value;

libse/Forms/SplitLongLinesHelper.cs

@@ -1,5 +1,4 @@
 using System;
-using System.Collections.Generic;
 
 namespace Nikse.SubtitleEdit.Core.Forms
 {
@@ -13,7 +12,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
                 return true;
             }
 
-            foreach (string noTagLine in noTagText.SplitToLines())
+            foreach (var line in s.SplitToLines())
             {
                 if (noTagLine.Length > singleLineMaxCharacters)
                 {
@@ -42,8 +41,6 @@ namespace Nikse.SubtitleEdit.Core.Forms
 
         public static Subtitle SplitLongLinesInSubtitle(Subtitle subtitle, int totalLineMaxCharacters, int singleLineMaxCharacters)
         {
-            var splittedIndexes = new List<int>();
-            var autoBreakedIndexes = new List<int>();
             var splittedSubtitle = new Subtitle(subtitle);
             splittedSubtitle.Paragraphs.Clear();
             string language = LanguageAutoDetect.AutoDetectGoogleLanguage(subtitle);
@@ -59,7 +56,6 @@ namespace Nikse.SubtitleEdit.Core.Forms
                         if (!QualifiesForSplit(text, singleLineMaxCharacters, totalLineMaxCharacters))
                         {
                             var newParagraph = new Paragraph(p) { Text = text };
-                            autoBreakedIndexes.Add(splittedSubtitle.Paragraphs.Count);
                             splittedSubtitle.Paragraphs.Add(newParagraph);
                             added = true;
                         }
@@ -86,9 +82,6 @@ namespace Nikse.SubtitleEdit.Core.Forms
                                     newParagraph2.Text = Utilities.AutoBreakLine(arr[1], language);
                                     newParagraph2.StartTime.TotalMilliseconds = newParagraph1.EndTime.TotalMilliseconds + spacing2;
 
-                                    splittedIndexes.Add(splittedSubtitle.Paragraphs.Count);
-                                    splittedIndexes.Add(splittedSubtitle.Paragraphs.Count + 1);
-
                                     string p1 = HtmlUtil.RemoveHtmlTags(newParagraph1.Text);
                                     var len = p1.Length - 1;
                                     if (p1.Length > 0 && (p1[len] == '.' || p1[len] == '!' || p1[len] == '?' || p1[len] == ':' || p1[len] == ')' || p1[len] == ']' || p1[len] == '♪'))

libse/Subtitle.cs

@@ -454,9 +454,12 @@ namespace Nikse.SubtitleEdit.Core
 
         public void Renumber(int startNumber = 1)
         {
-            foreach (Paragraph p in _paragraphs)
+            var index = startNumber;
+            int l = _paragraphs.Count;
+            while (index < l)
             {
-                p.Number = startNumber++;
+                var p = _paragraphs[index++];
+                p.Number = index;
             }
         }
 

libse/SubtitleFormats/VocapiaSplit.cs

@@ -38,6 +38,7 @@ namespace Nikse.SubtitleEdit.Core.SubtitleFormats
                 }
                 catch
                 {
+                    // ignored
                 }
             }
 
@@ -134,26 +135,6 @@ namespace Nikse.SubtitleEdit.Core.SubtitleFormats
             return Convert.ToDouble(s) * TimeCode.BaseUnit;
         }
 
-        public override bool HasStyleSupport
+        public override bool HasStyleSupport => true;
-        {
-            get { return true; }
-        }
-
-        public static List<string> GetStylesFromHeader(Subtitle subtitle)
-        {
-            var list = new List<string>();
-            foreach (Paragraph p in subtitle.Paragraphs)
-            {
-                if (!string.IsNullOrEmpty(p.Actor))
-                {
-                    if (list.IndexOf(p.Actor) < 0)
-                    {
-                        list.Add(p.Actor);
-                    }
-                }
-            }
-            return list;
-        }
-
     }
 }

libse/SubtitleFormats/WebVTT.cs

@@ -185,7 +185,7 @@ namespace Nikse.SubtitleEdit.Core.SubtitleFormats
                 {
                     subtitle.Header = "WEBVTT";
                 }
-                else if (p != null && hadEmptyLine && Utilities.IsInteger(line) &&
+                else if (p != null && hadEmptyLine && Utilities.IsInteger(line.RemoveChar('-')) &&
                          (RegexTimeCodesMiddle.IsMatch(next) ||
                           RegexTimeCodesShort.IsMatch(next) ||
                           RegexTimeCodes.IsMatch(next)))

libse/SubtitleFormats/WebVTTFileWithLineNumber.cs

@@ -60,7 +60,6 @@ namespace Nikse.SubtitleEdit.Core.SubtitleFormats
             Paragraph p = null;
             string positionInfo = string.Empty;
             bool hadEmptyLine = false;
-            int numbers = 0;
             for (var index = 0; index < lines.Count; index++)
             {
                 string line = lines[index];
@@ -112,12 +111,12 @@ namespace Nikse.SubtitleEdit.Core.SubtitleFormats
                 {
                     subtitle.Header = "WEBVTT FILE";
                 }
-                else if (p != null && hadEmptyLine && Utilities.IsInteger(line) &&
+                else if (p != null && hadEmptyLine && Utilities.IsInteger(line.RemoveChar('-')) &&
                          (RegexTimeCodesMiddle.IsMatch(next) ||
                           RegexTimeCodesShort.IsMatch(next) ||
                           RegexTimeCodes.IsMatch(next)))
                 {
-                    numbers++;
+                    // line number
                 }
                 else if (p != null)
                 {

src/Forms/AudioToText.cs

@@ -248,19 +248,24 @@ namespace Nikse.SubtitleEdit.Forms
         private static int GetLastTimeStampInSeconds(string text)
         {
             var lines = text.SplitToLines();
-            lines.Reverse();
+
-            foreach (var line in lines)
+            for (int i = lines.Count - 1; i >= 0; i--)
             {
-                if (!line.StartsWith('<') && !line.StartsWith('['))
+                string line = lines[i];
+                if (line.StartsWith('<') || line.StartsWith('['))
                 {
-                    var parts = line.Split();
+                    continue;
-                    if (parts.Length == 4)
+                }
-                    {
+
-                        if (double.TryParse(parts[1], out _) && double.TryParse(parts[2], out var end))
+                var words = line.Split();
-                        {
+                if (words.Length != 4)
-                            return (int)Math.Round(end);
+                {
-                        }
+                    continue;
-                    }
+                }
+
+                if (double.TryParse(words[1], out _) && double.TryParse(words[2], out var end))
+                {
+                    return (int)Math.Round(end);
                 }
             }
 

src/Logic/OCR/OcrFixEngine.cs

@@ -7,6 +7,7 @@ using System.Collections.Generic;
 using System.Drawing;
 using System.Globalization;
 using System.IO;
+using System.Linq;
 using System.Text;
 using System.Text.RegularExpressions;
 using System.Windows.Forms;
@@ -34,6 +35,7 @@ namespace Nikse.SubtitleEdit.Logic.Ocr
         private HashSet<string> _nameList = new HashSet<string>();
         private HashSet<string> _nameListUppercase = new HashSet<string>();
         private HashSet<string> _nameListWithApostrophe = new HashSet<string>();
+        private List<string> _nameListWithPeriods = new List<string>();
         private HashSet<string> _nameMultiWordList = new HashSet<string>(); // case sensitive phrases
         private HashSet<string> _abbreviationList;
         private HashSet<string> _userWordList = new HashSet<string>();
@@ -237,6 +239,7 @@ namespace Nikse.SubtitleEdit.Logic.Ocr
             _nameMultiWordList = _nameListObj.GetMultiNames();
             _nameListUppercase = new HashSet<string>();
             _nameListWithApostrophe = new HashSet<string>();
+            _nameListWithPeriods = new List<string>();
             _abbreviationList = new HashSet<string>();
 
             bool isEnglish = threeLetterIsoLanguageName.Equals("eng", StringComparison.OrdinalIgnoreCase);
@@ -254,11 +257,17 @@ namespace Nikse.SubtitleEdit.Logic.Ocr
                         _nameListWithApostrophe.Add(name + "'");
                     }
                 }
+
                 // Abbreviations.
                 if (name.EndsWith('.'))
                 {
                     _abbreviationList.Add(name);
                 }
+
+                if (name.Contains("."))
+                {
+                    _nameListWithPeriods.Add(name);
+                }
             }
             if (isEnglish)
             {
@@ -1244,7 +1253,7 @@ namespace Nikse.SubtitleEdit.Logic.Ocr
 
             string tempLine = line;
             const string p = " ¡¿,.!?:;()[]{}+-$£\"„”“#&%…—♪\r\n";
-            foreach (string name in _nameMultiWordList)
+            foreach (string name in _nameMultiWordList.Concat(_nameListWithPeriods))
             {
                 int start = tempLine.FastIndexOf(name);
                 if (start == 0 || (start > 0 && p.Contains(tempLine[start - 1])))