private void ParseText(Row Row, Segment CurrentSegment, string Text)
{
int CurrentPosition = 0;
bool HasComplex = true;
while (true)
{
ScanResult_Word Word = GetNextWord(Text, CurrentSegment, CurrentPosition, ref HasComplex);
if (!Word.HasContent)
{
ParseTools.AddString(Text.Substring(CurrentPosition), Row, CurrentSegment.BlockType.Style, CurrentSegment);
break;
}
else
{
ParseTools.AddString(Text.Substring(CurrentPosition, Word.Position - CurrentPosition), Row, CurrentSegment.BlockType.Style, CurrentSegment);
ParseTools.AddPatternString(Word.Token, Row, Word.Pattern, Word.ParentList.Style, CurrentSegment, false);
CurrentPosition = Word.Position + Word.Token.Length;
}
}
}
private ScanResult_Word GetNextWord(string Text,Segment CurrentSegment,int StartPos,ref bool HasComplex)
{
BlockType block= CurrentSegment.BlockType;
#region ComplexFind
int BestComplexPos =-1;
Pattern BestComplexPattern =null;
string BestComplexToken ="";
ScanResult_Word complexword=new ScanResult_Word();
if (HasComplex)
{
foreach (Pattern pattern in block.ComplexPatterns)
{
PatternScanResult scanres= pattern.IndexIn (Text,StartPos,pattern.Parent.CaseSensitive,this.Separators);
if (scanres.Token != "")
{
if (scanres.Index < BestComplexPos || BestComplexPos ==-1)
{
BestComplexPos=scanres.Index;
BestComplexPattern = pattern;
BestComplexToken = scanres.Token;
}
}
}
if (BestComplexPattern != null)
{
complexword.HasContent =true;
complexword.ParentList = BestComplexPattern.Parent;
complexword.Pattern = BestComplexPattern;
complexword.Position = BestComplexPos;
complexword.Token = BestComplexToken;
HasComplex=true;
}
else
{
HasComplex=false;
}
}
#endregion
#region SimpleFind
ScanResult_Word simpleword=new ScanResult_Word();
for (int i= StartPos ;i<Text.Length;i++)
{
//bailout if we found a complex pattern before this char pos
if (i>complexword.Position && complexword.HasContent)
break;
#region 3+ char pattern
if (i<=Text.Length-3)
{
string key=Text.Substring (i,3).ToLower ();
PatternCollection patterns2 =(PatternCollection)block.LookupTable[key];
//ok , there are patterns that start with this char
if (patterns2 != null)
{
foreach (Pattern pattern in patterns2)
{
int len=pattern.StringPattern.Length;
if (i+len>Text.Length)
continue;
char lastpatternchar=char.ToLower(pattern.StringPattern[len-1]);
char lasttextchar=char.ToLower (Text[i+len-1]);
#region Case Insensitive
if (lastpatternchar==lasttextchar)
{
if (!pattern.IsKeyword || (pattern.IsKeyword && pattern.HasSeparators (Text,i)))
{
if (!pattern.Parent.CaseSensitive)
{
string s=Text.Substring (i,len).ToLower ();
if (s==pattern.StringPattern.ToLower())
{
simpleword.HasContent =true;
simpleword.ParentList = pattern.Parent;
simpleword.Pattern = pattern;
simpleword.Position = i;
if (pattern.Parent.NormalizeCase)
simpleword.Token = pattern.StringPattern;
else
simpleword.Token = Text.Substring (i,len);
break;
}
}
else
{
string s=Text.Substring (i,len);
if (s==pattern.StringPattern)
{
simpleword.HasContent =true;
simpleword.ParentList = pattern.Parent;
simpleword.Pattern = pattern;
simpleword.Position = i;
simpleword.Token = pattern.StringPattern;
break;
}
}
}
}
}
#endregion
}
}
#endregion
if (simpleword.HasContent)
break;
#region single char pattern
char c=Text[i];
PatternCollection patterns =(PatternCollection)block.LookupTable[c];
if (patterns != null)
{
//ok , there are patterns that start with this char
foreach (Pattern pattern in patterns)
{
int len=pattern.StringPattern.Length;
if (i+len>Text.Length)
continue;
char lastpatternchar=pattern.StringPattern[len-1];
char lasttextchar=Text[i+len-1];
if (!pattern.Parent.CaseSensitive)
{
#region Case Insensitive
if (char.ToLower(lastpatternchar)==char.ToLower(lasttextchar))
{
if (!pattern.IsKeyword || (pattern.IsKeyword && pattern.HasSeparators (Text,i)))
{
string s=Text.Substring (i,len).ToLower ();
if (s==pattern.StringPattern.ToLower())
{
simpleword.HasContent =true;
simpleword.ParentList = pattern.Parent;
simpleword.Pattern = pattern;
simpleword.Position = i;
simpleword.Token = Text.Substring (i,len);
break;
}
}
}
#endregion
}
else
{
#region Case Sensitive
if (lastpatternchar==lasttextchar)
{
if (!pattern.IsKeyword || (pattern.IsKeyword && pattern.HasSeparators (Text,i)))
{
string s=Text.Substring (i,len);
if (s==pattern.StringPattern)
{
simpleword.HasContent =true;
simpleword.ParentList = pattern.Parent;
simpleword.Pattern = pattern;
simpleword.Position = i;
simpleword.Token = pattern.StringPattern;
break;
}
}
}
#endregion
}
}
if (simpleword.HasContent)
break;
}
#endregion
}
#endregion
if (complexword.HasContent && simpleword.HasContent)
{
if (simpleword.Position == complexword.Position)
{
if (simpleword.Token.Length > complexword.Token.Length)
return simpleword;
else
return complexword;
}
if (simpleword.Position < complexword.Position)
return simpleword;
if (simpleword.Position > complexword.Position)
return complexword;
}
if (simpleword.HasContent)
return simpleword;
if (complexword.HasContent)
return complexword;
return new ScanResult_Word ();
}
private ScanResult_Word GetNextComplexWord(String Text,Segment CurrentSegment,int StartPositon)
{
if (StartPositon >= Text.Length)
return new ScanResult_Word ();
ScanResult_Word Result = new ScanResult_Word ();
int CurrentPosition = 0;
//look for keywords
foreach (PatternList List in CurrentSegment.BlockType.KeywordsList)
{
foreach (Pattern Word in List.ComplexPatterns)
{
PatternScanResult psr= Word.IndexIn (Text,StartPositon,false,Separators);
CurrentPosition = psr.Index;
if ((CurrentPosition < Result.Position || Result.HasContent == false) && psr.Token != "")
{
Result.HasContent =true;
Result.Position = CurrentPosition;
Result.Token =psr.Token;
Result.Pattern = Word;
Result.ParentList = List;
if (List.NormalizeCase)
if (!Word.IsComplex)
Result.Token =Word.StringPattern;
}
}
}
//look for operators
foreach (PatternList List in CurrentSegment.BlockType.OperatorsList)
{
foreach (Pattern Word in List.ComplexPatterns)
{
PatternScanResult psr= Word.IndexIn (Text,StartPositon,false,Separators);
CurrentPosition = psr.Index;
if ((CurrentPosition < Result.Position || Result.HasContent == false) && psr.Token != "")
{
Result.HasContent =true;
Result.Position = CurrentPosition;
Result.Token =psr.Token;
Result.Pattern = Word;
Result.ParentList = List;
if (List.NormalizeCase)
if (!Word.IsComplex)
Result.Token =Word.StringPattern;
}
}
}
if (Result.HasContent)
return Result;
else
return new ScanResult_Word ();
}
private ScanResult_Word GetNextComplexWord(String Text, Segment CurrentSegment, int StartPositon)
{
if (StartPositon >= Text.Length)
{
return(new ScanResult_Word());
}
ScanResult_Word Result = new ScanResult_Word();
int CurrentPosition = 0;
//look for keywords
foreach (PatternList List in CurrentSegment.BlockType.KeywordsList)
{
foreach (Pattern Word in List.ComplexPatterns)
{
PatternScanResult psr = Word.IndexIn(Text, StartPositon, false, Separators);
CurrentPosition = psr.Index;
if ((CurrentPosition < Result.Position || Result.HasContent == false) && psr.Token != "")
{
Result.HasContent = true;
Result.Position = CurrentPosition;
Result.Token = psr.Token;
Result.Pattern = Word;
Result.ParentList = List;
if (List.NormalizeCase)
{
if (!Word.IsComplex)
{
Result.Token = Word.StringPattern;
}
}
}
}
}
//look for operators
foreach (PatternList List in CurrentSegment.BlockType.OperatorsList)
{
foreach (Pattern Word in List.ComplexPatterns)
{
PatternScanResult psr = Word.IndexIn(Text, StartPositon, false, Separators);
CurrentPosition = psr.Index;
if ((CurrentPosition < Result.Position || Result.HasContent == false) && psr.Token != "")
{
Result.HasContent = true;
Result.Position = CurrentPosition;
Result.Token = psr.Token;
Result.Pattern = Word;
Result.ParentList = List;
if (List.NormalizeCase)
{
if (!Word.IsComplex)
{
Result.Token = Word.StringPattern;
}
}
}
}
}
if (Result.HasContent)
{
return(Result);
}
else
{
return(new ScanResult_Word());
}
}
private ScanResult_Word GetNextWord(string Text, Segment CurrentSegment, int StartPos, ref bool HasComplex)
{
BlockType block = CurrentSegment.BlockType;
#region ComplexFind
int BestComplexPos = -1;
Pattern BestComplexPattern = null;
string BestComplexToken = "";
ScanResult_Word complexword = new ScanResult_Word();
if (HasComplex)
{
foreach (Pattern pattern in block.ComplexPatterns)
{
PatternScanResult scanres = pattern.IndexIn(Text, StartPos, pattern.Parent.CaseSensitive, this.Separators);
if (scanres.Token != "")
{
if (scanres.Index < BestComplexPos || BestComplexPos == -1)
{
BestComplexPos = scanres.Index;
BestComplexPattern = pattern;
BestComplexToken = scanres.Token;
}
}
}
if (BestComplexPattern != null)
{
complexword.HasContent = true;
complexword.ParentList = BestComplexPattern.Parent;
complexword.Pattern = BestComplexPattern;
complexword.Position = BestComplexPos;
complexword.Token = BestComplexToken;
HasComplex = true;
}
else
{
HasComplex = false;
}
}
#endregion
#region SimpleFind
ScanResult_Word simpleword = new ScanResult_Word();
for (int i = StartPos; i < Text.Length; i++)
{
//bailout if we found a complex pattern before this char pos
if (i > complexword.Position && complexword.HasContent)
{
break;
}
#region 3+ char pattern
if (i <= Text.Length - 3)
{
string key = Text.Substring(i, 3).ToLower();
PatternCollection patterns2 = (PatternCollection)block.LookupTable[key];
//ok , there are patterns that start with this char
if (patterns2 != null)
{
foreach (Pattern pattern in patterns2)
{
int len = pattern.StringPattern.Length;
if (i + len > Text.Length)
{
continue;
}
char lastpatternchar = char.ToLower(pattern.StringPattern[len - 1]);
char lasttextchar = char.ToLower(Text[i + len - 1]);
#region Case Insensitive
if (lastpatternchar == lasttextchar)
{
if (!pattern.IsKeyword || (pattern.IsKeyword && pattern.HasSeparators(Text, i)))
{
if (!pattern.Parent.CaseSensitive)
{
string s = Text.Substring(i, len).ToLower();
if (s == pattern.StringPattern.ToLower())
{
simpleword.HasContent = true;
simpleword.ParentList = pattern.Parent;
simpleword.Pattern = pattern;
simpleword.Position = i;
if (pattern.Parent.NormalizeCase)
{
simpleword.Token = pattern.StringPattern;
}
else
{
simpleword.Token = Text.Substring(i, len);
}
break;
}
}
else
{
string s = Text.Substring(i, len);
if (s == pattern.StringPattern)
{
simpleword.HasContent = true;
simpleword.ParentList = pattern.Parent;
simpleword.Pattern = pattern;
simpleword.Position = i;
simpleword.Token = pattern.StringPattern;
break;
}
}
}
}
}
#endregion
}
}
#endregion
if (simpleword.HasContent)
{
break;
}
#region single char pattern
char c = Text[i];
PatternCollection patterns = (PatternCollection)block.LookupTable[c];
if (patterns != null)
{
//ok , there are patterns that start with this char
foreach (Pattern pattern in patterns)
{
int len = pattern.StringPattern.Length;
if (i + len > Text.Length)
{
continue;
}
char lastpatternchar = pattern.StringPattern[len - 1];
char lasttextchar = Text[i + len - 1];
if (!pattern.Parent.CaseSensitive)
{
#region Case Insensitive
if (char.ToLower(lastpatternchar) == char.ToLower(lasttextchar))
{
if (!pattern.IsKeyword || (pattern.IsKeyword && pattern.HasSeparators(Text, i)))
{
string s = Text.Substring(i, len).ToLower();
if (s == pattern.StringPattern.ToLower())
{
simpleword.HasContent = true;
simpleword.ParentList = pattern.Parent;
simpleword.Pattern = pattern;
simpleword.Position = i;
simpleword.Token = Text.Substring(i, len);
break;
}
}
}
#endregion
}
else
{
#region Case Sensitive
if (lastpatternchar == lasttextchar)
{
if (!pattern.IsKeyword || (pattern.IsKeyword && pattern.HasSeparators(Text, i)))
{
string s = Text.Substring(i, len);
if (s == pattern.StringPattern)
{
simpleword.HasContent = true;
simpleword.ParentList = pattern.Parent;
simpleword.Pattern = pattern;
simpleword.Position = i;
simpleword.Token = pattern.StringPattern;
break;
}
}
}
#endregion
}
}
if (simpleword.HasContent)
{
break;
}
}
#endregion
}
#endregion
if (complexword.HasContent && simpleword.HasContent)
{
if (simpleword.Position == complexword.Position)
{
if (simpleword.Token.Length > complexword.Token.Length)
{
return(simpleword);
}
else
{
return(complexword);
}
}
if (simpleword.Position < complexword.Position)
{
return(simpleword);
}
if (simpleword.Position > complexword.Position)
{
return(complexword);
}
}
if (simpleword.HasContent)
{
return(simpleword);
}
if (complexword.HasContent)
{
return(complexword);
}
return(new ScanResult_Word());
}