/// <summary>
/// Loads the lexic resource.
/// </summary>
/// <param name="output">The output.</param>
/// <param name="resourceFilePath">The resource file path.</param>
public void LoadLexicResource(ILogBuilder output, String resourceFilePath)
{
List <String> lines = new List <String>();
// <---------------------------------------------- [
if (isLoaded)
{
return;
}
String pt = "";
if (!localCache.isNullOrEmpty())
{
pt = localCache;
lines.AddRange(File.ReadLines(localCache));
}
if (lines.Count < 100)
{
pt = resourceFilePath;
lines = new List <string>();
lines.AddRange(File.ReadAllLines(resourceFilePath));
}
Int32 i = 0;
Int32 iCycle = lines.Count() / 20;
Int32 l = lines.Count();
Int32 c = 0;
Double p = 0;
output.logStartPhase("Loading", "Loading the lexic resource - with mode: " + mode.ToString());
output.log("Start of loading lexic resource [" + pt + "]");
// Parallel.ForEach(lines, new ParallelOptions { MaxDegreeOfParallelism=1 }, (line) =>
Parallel.ForEach(lines, new ParallelOptions {
MaxDegreeOfParallelism = 1
}, (line) =>
// Parallel.ForEach(lines, (line) =>
{
string inflectForm = "";
string lemma = "";
string gramTag = "";
SelectFromLine(line, out inflectForm, out lemma, out gramTag);
lexicInflection inflect = null;
if (!inflectForm.isNullOrEmpty())
{
if (!ContainsKey(inflectForm))
{
inflect = new lexicInflection(line);
inflect.lemmaForm = lemma;
inflect.name = inflectForm;
inflect.inflectedForm = inflectForm;
inflect.lexicalDefinitionLine = line;
if (spellAlternator.IsInitiated)
{
String altInflectedForm = spellAlternator.ConvertFromAtoB(inflectForm);
spellAlternatives.GetOrAdd(altInflectedForm, inflectForm);
}
Add(inflectForm, inflect);
}
else
{
inflect = base[inflectForm];
}
lexicGrammarCase gramCase = null;
if (mode == textResourceIndexResolveMode.resolveOnLoad)
{
var gramTagColl = grammTagConverter.ConvertFromString(gramTag);
gramCase = inflect.AddGrammarCase(gramTagColl);
gramCase.lexicalDefinitionLine = gramTag;
}
else
{
gramCase = new lexicGrammarCase();
gramCase.lexicalDefinitionLine = gramTag;
gramCase.name = "gc" + i.ToString();
inflect.Add(gramCase);
}
// <----------------- construction of Lemma centered dictionary
lexicGraphSetWithLemma lxSet = null;
if (!registratedLemmaIndex.ContainsKey(lemma))
{
lock (LemmaIndexLock)
{
if (!registratedLemmaIndex.ContainsKey(lemma))
{
lxSet = new lexicGraphSetWithLemma();
lxSet.lemmaForm = lemma;
registratedLemmaIndex.TryAdd(lemma, lxSet);
}
}
}
lxSet = registratedLemmaIndex[lemma];
if (!lxSet.ContainsKey(inflectForm))
{
lock (SetLock)
{
if (!lxSet.ContainsKey(inflectForm))
{
lxSet.TryAdd(inflect.name, inflect);
}
}
}
Interlocked.Increment(ref c);
Interlocked.Increment(ref i);
if (c > iCycle)
{
lock (loadStatusLock)
{
if (c > iCycle)
{
c = 0;
p = i.GetRatio(l);
output.AppendLine("Done: _" + p.ToString("P2") + "_");
}
}
}
}
});
output.logEndPhase();
output.log("End of loading process");
isLoaded = true;
}
/// <summary>
/// Renders the token into string form
/// </summary>
/// <param name="token">The token.</param>
/// <param name="mode">The mode.</param>
/// <returns></returns>
private static String renderString(pipelineTaskSubjectContentToken token, contentTokenSubjectRenderMode mode)
{
StringBuilder sb = new StringBuilder();
if (token == null)
{
sb.Append(textMapBase.SEPARATOR);
return(sb.ToString());
}
switch (mode)
{
default:
case contentTokenSubjectRenderMode.currentForm:
sb.Append(token.currentForm);
break;
case contentTokenSubjectRenderMode.lemmaForm:
if (token.graph != null)
{
sb.Append(token.graph.lemmaForm);
}
else
{
sb.Append(token.currentForm);
}
break;
case contentTokenSubjectRenderMode.descriptive:
sb.Append(token.currentForm);
if (token.graph != null)
{
sb.Append(textMapBase.MAINLEVEL_COMMA);
sb.Append(token.graph.lemmaForm);
}
sb.Append(textMapBase.MAINLEVEL_COMMA);
renderGramCase(sb, token.flagBag, false);
break;
case contentTokenSubjectRenderMode.flagsForm:
renderGramCase(sb, token.flagBag, false);
break;
case contentTokenSubjectRenderMode.flagsFullForm:
renderGramCase(sb, token.flagBag, true);
break;
case contentTokenSubjectRenderMode.initialForm:
sb.Append(token.initialForm);
break;
case contentTokenSubjectRenderMode.none:
break;
case contentTokenSubjectRenderMode.posTypeAndGramTagForm:
//sb.Append("[");
sb.Append(renderString(token, contentTokenSubjectRenderMode.posTypeTagForm));
//sb.Backspace(textMapBase.SEPARATOR);
if (token.graph != null)
{
for (int i = 0; i < token.graph.Count(); i++)
{
lexicGrammarCase pt = token.graph[i] as lexicGrammarCase;
renderGramCase(sb, pt.tags.GetTags(), false);
if (i < token.graph.Count() - 1)
{
sb.Append(textMapBase.MAINLEVEL_COMMA);
}
}
}
//sb.Append("]");
break;
case contentTokenSubjectRenderMode.posTypeTagForm:
List <pos_type> posTypeTags = new List <pos_type>();
Boolean ok = false;
if (token.graph != null)
{
var pst = token.graph.GetTagFromGramTags <pos_type>();
foreach (var ps in pst)
{
posTypeTags.AddUnique(ps);
}
if (posTypeTags.Any())
{
ok = true;
}
}
if (ok == false)
{
var pst = token.flagBag.getAllOfType <pos_type>(false);
foreach (var ps in pst)
{
posTypeTags.AddUnique(ps);
}
}
if (!posTypeTags.Any())
{
posTypeTags.Add(pos_type.none);
}
foreach (pos_type pt in posTypeTags)
{
if (pt != pos_type.none)
{
sb.Append(pt.ToString());
if (pt != posTypeTags.Last())
{
sb.Append(textMapBase.SUBLEVEL_COMMA);
}
}
}
break;
}
sb.Append(" ");
return(sb.ToString());
}
