public USFMDocument ParseFromString(string input)
{
Regex splitRegex = new Regex("\\\\([a-z0-9*]+)([^\\\\]*)");
USFMDocument output = new USFMDocument();
foreach (Match match in splitRegex.Matches(input))
{
if (IgnoredTags.Contains(match.Groups[1].Value))
{
continue;
}
ConvertToMarkerResult result = ConvertToMarker(match.Groups[1].Value, match.Groups[2].Value);
if (result.marker is TRMarker && !output.GetTypesPathToLastMarker().Contains(typeof(TableBlock)))
{
output.Insert(new TableBlock());
}
output.Insert(result.marker);
if (!string.IsNullOrWhiteSpace(result.remainingText))
{
output.Insert(new TextBlock(result.remainingText));
}
}
return(output);
}
/// <summary>
/// Generate a list of Markers from a string
/// </summary>
/// <param name="input">USFM String to tokenize</param>
/// <returns>A List of Markers based upon the string</returns>
private List <Marker> TokenizeFromString(string input)
{
List <Marker> output = new List <Marker>();
bool isInVMarkerNow = false;
foreach (Match match in splitRegex.Matches(input))
{
if (IgnoredTags.Contains(match.Groups[1].Value))
{
continue;
}
ConvertToMarkerResult result = ConvertToMarker(match.Groups[1].Value, match.Groups[2].Value);
result.marker.Position = match.Index;
output.Add(result.marker);
//Conditions for the spaces between tags to be included as whitespace in a verse
var vMarker = new VMarker();
bool isAllowedByVMarker = vMarker.AllowedContents.Contains(result.marker.GetType());
bool doesNotAllowVMarker = !result.marker.AllowedContents.Contains(typeof(VMarker));
if (result.marker is VMarker)
{
isInVMarkerNow = true;
}
if (!isAllowedByVMarker && !(result.marker is VMarker))
{
isInVMarkerNow = false;
}
//deciding when to include textblocks
//whitespace textblocks is added to the list when the tag is a Allowed by VMarker, does not allow VMarker, and is current in a VMarker
//this solves the problem of \v 1 \tl hello \tl* \tl hello \tl* appearing as hellohello instead of hello hello
if (!string.IsNullOrWhiteSpace(result.remainingText) ||
(!string.IsNullOrEmpty(result.remainingText) && isAllowedByVMarker && doesNotAllowVMarker && isInVMarkerNow))
{
output.Add(new TextBlock(result.remainingText));
}
}
return(output);
}
/// <summary>
/// Generate a list of Markers from a string
/// </summary>
/// <param name="input">USFM String to tokenize</param>
/// <returns>A List of Markers based upon the string</returns>
private List <Marker> TokenizeFromString(string input)
{
List <Marker> output = new List <Marker>();
foreach (Match match in splitRegex.Matches(input))
{
if (IgnoredTags.Contains(match.Groups[1].Value))
{
continue;
}
ConvertToMarkerResult result = ConvertToMarker(match.Groups[1].Value, match.Groups[2].Value);
result.marker.Position = match.Index;
output.Add(result.marker);
if (!string.IsNullOrWhiteSpace(result.remainingText))
{
output.Add(new TextBlock(result.remainingText));
}
}
return(output);
}