Minor update of libse

Author: niksedk

SubtitleEdit/Windows/Edit/SpellCheckController.cs

@@ -8,6 +8,7 @@
 using System.Text;
 using System.Threading.Tasks;
 using Nikse.SubtitleEdit.UILogic;
+using Nikse.SubtitleEdit.Core.Dictionaries;
 
 namespace Edit
 {
@@ -26,6 +27,7 @@ public partial class SpellCheckController : NSWindowController
         private List<SpellCheckWord> _words;
         private List<string> _skipAllList = new List<string>();
         private bool _abort = false;
+        private List<string> _namesEtcList = new List<string>();
 
         public SpellCheckController(IntPtr handle)
             : base(handle)
@@ -49,6 +51,12 @@ public override void AwakeFromNib()
             base.AwakeFromNib();
         }
 
+        void LoadNames()
+        {
+            var namesList = new NamesList(Configuration.DictionariesFolder, "en", Configuration.Settings.WordLists.UseOnlineNamesEtc, Configuration.Settings.WordLists.NamesEtcUrl);
+            _namesEtcList = namesList.GetAllNames();
+        }
+
         public void InitializeSpellCheck()
         {
             _spellChecker = new SpellChecker("en");
@@ -57,6 +65,7 @@ public void InitializeSpellCheck()
             _currentParagraphIndex = 0;
             _words = SpellChecker.Split(_subtitle.Paragraphs[0].Text);
             _wordsIndex = -1;
+            LoadNames();
             PrepareNextWord();
         }
 
@@ -67,13 +76,18 @@ public void InitializeSpellCheck()
 
         public void SkipAll()
         {
-            string word = _currentWord.ToLower().Trim();
+            string wordOriginalCasing = _currentWord.Trim();
+            string word = wordOriginalCasing.ToLower();
             _skipAllList.Add(word);
             _skipAllList.Add(word.ToUpper());
             if (word.Length > 0)
             {
                 _skipAllList.Add(word.Substring(0, 1).ToUpper() + word.Substring(1));
             }
+            if (!_skipAllList.Contains(wordOriginalCasing))
+            {
+                _skipAllList.Add(wordOriginalCasing);
+            }
             PrepareNextWord();
         }
 
@@ -138,6 +152,10 @@ private void PrepareNextWord()
                                     spelledOk = true;
                                 }
 
+                                if (!spelledOk && _namesEtcList.Contains(_currentWord))
+                                {
+                                    spelledOk = true;
+                                }
 
                                 if (!spelledOk)
                                 {

libse/Interfaces/IDoSpell.cs

@@ -0,0 +1,7 @@
+namespace Nikse.SubtitleEdit.Core.Interfaces
+{
+    public interface IDoSpell
+    {
+        bool DoSpell(string word);
+    }
+}

libse/Interfaces/IRtfTextConverter.cs

@@ -0,0 +1,8 @@
+namespace Nikse.SubtitleEdit.Core.Interfaces
+{
+    public interface IRtfTextConverter
+    {
+        string RtfToText(string rtf);
+        string TextToRtf(string text);
+    }
+}

libse/LibSE.csproj

@@ -408,6 +408,13 @@
     <Compile Include="VobSub\VobSubMergedPack.cs" />
     <Compile Include="VobSub\VobSubPack.cs" />
     <Compile Include="VobSub\VobSubParser.cs" />
+    <Compile Include="RichTextToPlainText.cs" />
+    <Compile Include="Interfaces\IDoSpell.cs" />
+    <Compile Include="Interfaces\IRtfTextConverter.cs" />
+    <Compile Include="SubtitleFormats\F4Rtf.cs" />
+    <Compile Include="SpellCheck\SpellCheckWord.cs" />
+    <Compile Include="SpellCheck\SpellCheckWordLists.cs" />
+    <Compile Include="SpellCheck\UndoObject.cs" />
   </ItemGroup>
   <Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" />
   <PropertyGroup>

libse/RichTextToPlainText.cs

@@ -0,0 +1,266 @@
+using Nikse.SubtitleEdit.Core.Interfaces;
+using System;
+using System.Collections.Generic;
+using System.Text;
+using System.Text.RegularExpressions;
+
+namespace Nikse.SubtitleEdit.Core
+{
+    /// <summary>
+    /// Rich Text to plain text
+    /// </summary>
+    /// <remarks>
+    /// Translated from Python located at:
+    /// http://stackoverflow.com/a/188877/448
+    /// to C# by Chris Benard - http://chrisbenard.net/2014/08/20/Extract-Text-from-RTF-in-.Net
+    /// </remarks>
+    public static class RichTextToPlainText
+    {
+
+        public static IRtfTextConverter NativeRtfTextConverter { get; set; }
+
+        private class StackEntry
+        {
+            public int NumberOfCharactersToSkip { get; private set; }
+            public bool Ignorable { get; private set; }
+
+            public StackEntry(int numberOfCharactersToSkip, bool ignorable)
+            {
+                NumberOfCharactersToSkip = numberOfCharactersToSkip;
+                Ignorable = ignorable;
+            }
+        }
+
+        private static readonly Regex RtfRegex = new Regex(@"\\([a-z]{1,32})(-?\d{1,10})?[ ]?|\\'([0-9a-f]{2})|\\([^a-z])|([{}])|[\r\n]+|(.)", RegexOptions.Singleline | RegexOptions.IgnoreCase);
+
+        private static readonly List<string> Destinations = new List<string>
+        {
+            "aftncn","aftnsep","aftnsepc","annotation","atnauthor","atndate","atnicn","atnid",
+            "atnparent","atnref","atntime","atrfend","atrfstart","author","background",
+            "bkmkend","bkmkstart","blipuid","buptim","category","colorschememapping",
+            "colortbl","comment","company","creatim","datafield","datastore","defchp","defpap",
+            "do","doccomm","docvar","dptxbxtext","ebcend","ebcstart","factoidname","falt",
+            "fchars","ffdeftext","ffentrymcr","ffexitmcr","ffformat","ffhelptext","ffl",
+            "ffname","ffstattext","field","file","filetbl","fldinst","fldrslt","fldtype",
+            "fname","fontemb","fontfile","fonttbl","footer","footerf","footerl","footerr",
+            "footnote","formfield","ftncn","ftnsep","ftnsepc","g","generator","gridtbl",
+            "header","headerf","headerl","headerr","hl","hlfr","hlinkbase","hlloc","hlsrc",
+            "hsv","htmltag","info","keycode","keywords","latentstyles","lchars","levelnumbers",
+            "leveltext","lfolevel","linkval","list","listlevel","listname","listoverride",
+            "listoverridetable","listpicture","liststylename","listtable","listtext",
+            "lsdlockedexcept","macc","maccPr","mailmerge","maln","malnScr","manager","margPr",
+            "mbar","mbarPr","mbaseJc","mbegChr","mborderBox","mborderBoxPr","mbox","mboxPr",
+            "mchr","mcount","mctrlPr","md","mdeg","mdegHide","mden","mdiff","mdPr","me",
+            "mendChr","meqArr","meqArrPr","mf","mfName","mfPr","mfunc","mfuncPr","mgroupChr",
+            "mgroupChrPr","mgrow","mhideBot","mhideLeft","mhideRight","mhideTop","mhtmltag",
+            "mlim","mlimloc","mlimlow","mlimlowPr","mlimupp","mlimuppPr","mm","mmaddfieldname",
+            "mmath","mmathPict","mmathPr","mmaxdist","mmc","mmcJc","mmconnectstr",
+            "mmconnectstrdata","mmcPr","mmcs","mmdatasource","mmheadersource","mmmailsubject",
+            "mmodso","mmodsofilter","mmodsofldmpdata","mmodsomappedname","mmodsoname",
+            "mmodsorecipdata","mmodsosort","mmodsosrc","mmodsotable","mmodsoudl",
+            "mmodsoudldata","mmodsouniquetag","mmPr","mmquery","mmr","mnary","mnaryPr",
+            "mnoBreak","mnum","mobjDist","moMath","moMathPara","moMathParaPr","mopEmu",
+            "mphant","mphantPr","mplcHide","mpos","mr","mrad","mradPr","mrPr","msepChr",
+            "mshow","mshp","msPre","msPrePr","msSub","msSubPr","msSubSup","msSubSupPr","msSup",
+            "msSupPr","mstrikeBLTR","mstrikeH","mstrikeTLBR","mstrikeV","msub","msubHide",
+            "msup","msupHide","mtransp","mtype","mvertJc","mvfmf","mvfml","mvtof","mvtol",
+            "mzeroAsc","mzeroDesc","mzeroWid","nesttableprops","nextfile","nonesttables",
+            "objalias","objclass","objdata","object","objname","objsect","objtime","oldcprops",
+            "oldpprops","oldsprops","oldtprops","oleclsid","operator","panose","password",
+            "passwordhash","pgp","pgptbl","picprop","pict","pn","pnseclvl","pntext","pntxta",
+            "pntxtb","printim","private","propname","protend","protstart","protusertbl","pxe",
+            "result","revtbl","revtim","rsidtbl","rxe","shp","shpgrp","shpinst",
+            "shppict","shprslt","shptxt","sn","sp","staticval","stylesheet","subject","sv",
+            "svb","tc","template","themedata","title","txe","ud","upr","userprops",
+            "wgrffmtfilter","windowcaption","writereservation","writereservhash","xe","xform",
+            "xmlattrname","xmlattrvalue","xmlclose","xmlname","xmlnstbl",
+            "xmlopen"
+        };
+
+        private static readonly Dictionary<string, string> SpecialCharacters = new Dictionary<string, string>
+        {
+            { "par", "\n" },
+            { "sect", "\n\n" },
+            { "page", "\n\n" },
+            { "line", "\n" },
+            { "tab", "\t" },
+            { "emdash", "\u2014" },
+            { "endash", "\u2013" },
+            { "emspace", "\u2003" },
+            { "enspace", "\u2002" },
+            { "qmspace", "\u2005" },
+            { "bullet", "\u2022" },
+            { "lquote", "\u2018" },
+            { "rquote", "\u2019" },
+            { "ldblquote", "\u201C" },
+            { "rdblquote", "\u201D" },
+        };
+
+        /// <summary>
+        /// Strip RTF Tags from RTF Text
+        /// </summary>
+        /// <param name="inputRtf">RTF formatted text</param>
+        /// <returns>Plain text from RTF</returns>
+        internal static string ConvertToText(string inputRtf)
+        {
+            if (inputRtf == null)
+            {
+                return null;
+            }
+
+            // use interface converter if available
+            if (NativeRtfTextConverter != null)
+            {
+                NativeRtfTextConverter.RtfToText(inputRtf);
+            }
+
+            var stack = new Stack<StackEntry>();
+            bool ignorable = false;              // Whether this group (and all inside it) are "ignorable".
+            int ucskip = 1;                      // Number of ASCII characters to skip after a unicode character.
+            int curskip = 0;                     // Number of ASCII characters left to skip
+            var outList = new List<string>();    // Output buffer.
+
+            MatchCollection matches = RtfRegex.Matches(inputRtf);
+
+            if (matches.Count > 0)
+            {
+                foreach (Match match in matches)
+                {
+                    string word = match.Groups[1].Value;
+                    string arg = match.Groups[2].Value;
+                    string hex = match.Groups[3].Value;
+                    string character = match.Groups[4].Value;
+                    string brace = match.Groups[5].Value;
+                    string tchar = match.Groups[6].Value;
+
+                    if (!String.IsNullOrEmpty(brace))
+                    {
+                        curskip = 0;
+                        if (brace == "{")
+                        {
+                            // Push state
+                            stack.Push(new StackEntry(ucskip, ignorable));
+                        }
+                        else if (brace == "}")
+                        {
+                            // Pop state
+                            StackEntry entry = stack.Pop();
+                            ucskip = entry.NumberOfCharactersToSkip;
+                            ignorable = entry.Ignorable;
+                        }
+                    }
+                    else if (!String.IsNullOrEmpty(character)) // \x (not a letter)
+                    {
+                        curskip = 0;
+                        if (character == "~")
+                        {
+                            if (!ignorable)
+                            {
+                                outList.Add("\xA0");
+                            }
+                        }
+                        else if ("{}\\".Contains(character))
+                        {
+                            if (!ignorable)
+                            {
+                                outList.Add(character);
+                            }
+                        }
+                        else if (character == "*")
+                        {
+                            ignorable = true;
+                        }
+                    }
+                    else if (!String.IsNullOrEmpty(word)) // \foo
+                    {
+                        curskip = 0;
+                        if (Destinations.Contains(word))
+                        {
+                            ignorable = true;
+                        }
+                        else if (ignorable)
+                        {
+                        }
+                        else if (SpecialCharacters.ContainsKey(word))
+                        {
+                            outList.Add(SpecialCharacters[word]);
+                        }
+                        else if (word == "uc")
+                        {
+                            ucskip = Int32.Parse(arg);
+                        }
+                        else if (word == "u")
+                        {
+                            int c = Int32.Parse(arg);
+                            if (c < 0)
+                            {
+                                c += 0x10000;
+                            }
+                            outList.Add(Char.ConvertFromUtf32(c));
+                            curskip = ucskip;
+                        }
+                    }
+                    else if (!String.IsNullOrEmpty(hex)) // \'xx
+                    {
+                        if (curskip > 0)
+                        {
+                            curskip -= 1;
+                        }
+                        else if (!ignorable)
+                        {
+                            int c = Int32.Parse(hex, System.Globalization.NumberStyles.HexNumber);
+                            outList.Add(Char.ConvertFromUtf32(c));
+                        }
+                    }
+                    else if (!String.IsNullOrEmpty(tchar))
+                    {
+                        if (curskip > 0)
+                        {
+                            curskip -= 1;
+                        }
+                        else if (!ignorable)
+                        {
+                            outList.Add(tchar);
+                        }
+                    }
+                }
+            }
+            return String.Join(String.Empty, outList.ToArray());
+        }
+
+        internal static string ConvertToRtf(string value)
+        {
+            if (string.IsNullOrWhiteSpace(value))
+            {
+                return string.Empty;
+            }
+
+            // use interface converter if available
+            if (NativeRtfTextConverter != null)
+            {
+                NativeRtfTextConverter.TextToRtf(value);
+            }
+
+            // special RTF chars
+            var backslashed = new StringBuilder(value);
+            backslashed.Replace(@"\", @"\\");
+            backslashed.Replace(@"{", @"\{");
+            backslashed.Replace(@"}", @"\}");
+            backslashed.Replace(Environment.NewLine, @"\par" + Environment.NewLine);
+
+            // convert string char by char
+            var sb = new StringBuilder();
+            foreach (char character in backslashed.ToString())
+            {
+                if (character <= 0x7f)
+                    sb.Append(character);
+                else
+                    sb.Append("\\u" + Convert.ToUInt32(character) + "?");
+            }
+
+            return @"{\rtf1\ansi\ansicpg1252\deff0{\fonttbl\f0\fswiss Helvetica;}\f0\pard " + sb + @"\par" + Environment.NewLine + "}";
+        }
+
+    }
+
+}

libse/SpellCheck/SpellCheckWord.cs

@@ -0,0 +1,8 @@
+namespace Nikse.SubtitleEdit.Core.SpellCheck
+{
+    public class SpellCheckWord
+    {
+        public int Index { get; set; }
+        public string Text { get; set; }
+    }
+}