public IGAnlys_Word ForceWordANlys(string key, List <string> contentMorphemes)
{
var morphemes = analyzer.AnalyzeImmediate(key);
IGAnlys_Word wordBeingBuilt = null;
foreach (var morpheme in morphemes)
{
contentMorphemes.Add(morpheme.word);
if (wordBeingBuilt == null)
{
wordBeingBuilt = new IGAnlys_Word();
}
wordBeingBuilt.AddMorphemeText(morpheme.word);
}
return(wordBeingBuilt);
}
public IncrementalGAnalyzer PickBestElement(string key)
{
var morphemes = analyzer.AnalyzeImmediate(key);
bool doIgnoreNext = false;
bool isUnreadableNext = false;
List <IncrementalGAnalyzer> analyzers = new List <IncrementalGAnalyzer>();
IGAnlys_Word wordBeingBuilt = null;
foreach (var morpheme in morphemes)
{
if (morpheme.id == 0)
{
if (wordBeingBuilt == null)
{
wordBeingBuilt = new IGAnlys_Word();
}
wordBeingBuilt.AddMorphemeText(morpheme.word);
}
else if (wordBeingBuilt != null)
{
analyzers.Add(ModifyAnalyzer(wordBeingBuilt, ref doIgnoreNext, ref isUnreadableNext));
wordBeingBuilt = null;
}
if (morpheme.id == 1)
{
if (int.TryParse(morpheme.word, out int morphemeID))
{
analyzers.Add(ModifyAnalyzer(new IGAnlys_Quote {
morphemeID = morphemeID
}, ref doIgnoreNext, ref isUnreadableNext));
}
else
{
if (!doIgnoreNext)
{
analyzers.Add(dict.dict[morpheme.word]);
}
else
{
analyzers.Add(new IGAnlys_IgnoreBlock {
baseAnalyzer = dict.dict[morpheme.word]
});
}
doIgnoreNext = false;
}
}
else if (morpheme.id == 2)
{
doIgnoreNext = true;
}
else if (morpheme.id == 3)
{
isUnreadableNext = true;
}
}
if (wordBeingBuilt != null)
{
analyzers.Add(ModifyAnalyzer(wordBeingBuilt, ref doIgnoreNext, ref isUnreadableNext));
}
if (analyzers.Count == 1)
{
return(analyzers[0]);
}
else if (analyzers.Count > 1)
{
var sequence = new IGAnlys_Sequence();
foreach (var analyzer in analyzers)
{
sequence.analyzers.Add(analyzer);
}
return(new IGAnlys_ResultClusterizer {
baseAnalyzer = sequence
});
}
return(null);
}
public ExampleNLangProcessor(string dictionaryFilePath)
{
#region MAnlys
var mAnlys = new StdMAnalyzer {
};
{
var ignoreReader = new IgnoreBlockReader {
markers = new List <string> {
" ", "\r", "\n", "\t"
}
};
var markerReader = new MarkerBlockReader {
markers = new List <MarkerAndFormatID> {
new MarkerAndFormatID {
marker = ".", formatID = 2
},
new MarkerAndFormatID {
marker = ",", formatID = 3
},
new MarkerAndFormatID {
marker = "###", formatID = 4
},
new MarkerAndFormatID {
marker = ":", formatID = 5
},
}
};
var quoteBlockMarker = new QuoteBlockReader {
formatID = 1, leftMarker = "\"", rightMarker = "\""
};
mAnlys.blockReaderes.Add(ignoreReader);
mAnlys.blockReaderes.Add(markerReader);
mAnlys.blockReaderes.Add(quoteBlockMarker);
mAnlys.generalReaders.Add(new NumberReader {
});
mAnlys.generalReaders.Add(new WordReader {
});
}
#endregion
#region MAnlys for dictionary creation
var mAnlysForDict = new StdMAnalyzer {
};
{
var ignoreReader = new IgnoreBlockReader {
markers = new List <string> {
" "
}
};
var markerReader = new MarkerBlockReader {
markers = new List <MarkerAndFormatID> {
new MarkerAndFormatID {
marker = "(IGNORE)", formatID = 2
},
new MarkerAndFormatID {
marker = "(UNREADABLE)", formatID = 3
}
}
};
var quoteBlockMarker = new QuoteBlockReader {
formatID = 1, leftMarker = "#", rightMarker = "#"
};
mAnlysForDict.blockReaderes.Add(ignoreReader);
mAnlysForDict.blockReaderes.Add(markerReader);
mAnlysForDict.blockReaderes.Add(quoteBlockMarker);
mAnlysForDict.generalReaders.Add(new WordReader {
});
}
#endregion
#region dictionary creation
var gDict = new IncrGAnlysDictionary();
var formatReader = new FormatReader();
FormatReader.fReader = new FormToGAnlys {
analyzer = mAnlysForDict, dict = gDict
};
FormatReader.gAnlysDict = gDict;
FormatReader.metaInfos = new Dictionary <string, GrammarBlock>();
FormatReader.metaInfos[StdMetaInfos.sentenceCluster.word] = StdMetaInfos.sentenceCluster;
FormatReader.metaInfos[StdMetaInfos.nominalBlock.word] = StdMetaInfos.nominalBlock;
FormatReader.metaInfos[StdMetaInfos.verbalBlock.word] = StdMetaInfos.verbalBlock;
FormatReader.metaInfos[StdMetaInfos.quoteBlock.word] = StdMetaInfos.quoteBlock;
FormatReader.metaInfos[StdMetaInfos.sv.word] = StdMetaInfos.sv;
FormatReader.metaInfos[StdMetaInfos.conditionSV.word] = StdMetaInfos.conditionSV;
FormatReader.metaInfos[StdMetaInfos.negated.word] = StdMetaInfos.negated;
FormatReader.metaInfos[StdMetaInfos.title.word] = StdMetaInfos.title;
FormatReader.metaInfos[StdMetaInfos.clusterExtractable.word] = StdMetaInfos.clusterExtractable;
FormatReader.metaInfos[StdMetaInfos.metaCluster.word] = StdMetaInfos.metaCluster;
FormatReader.metaInfos[StdMetaInfos.anonymousCommand.word] = StdMetaInfos.anonymousCommand;
FormatReader.metaInfos[StdMetaInfos.modifierCluster.word] = StdMetaInfos.modifierCluster;
FormatReader.metaInfos[StdMetaInfos.quoteSV.word] = StdMetaInfos.quoteSV;
FormatReader.metaInfos[StdMetaInfos.pronoun.word] = StdMetaInfos.pronoun;
FormatReader.metaInfos[StdMetaInfos.plural.word] = StdMetaInfos.plural;
FormatReader.metaInfos[StdMetaInfos.unreadable.word] = StdMetaInfos.unreadable;
{
var conjCand = new IGAnlys_Candidates {
};
var and = new IGAnlys_Word {
};
and.AddMorphemeText("and");
var or = new IGAnlys_Word {
};
or.AddMorphemeText("or");
var quote = new IGAnlys_Quote {
morphemeID = 3
};
conjCand.candidates.Add(and);
conjCand.candidates.Add(or);
conjCand.candidates.Add(quote);
var conjGAnlys = new IGAnlys_RepeatableBlock {
baseAnalyzer = conjCand
};
FormatReader.cojunctionIGAnlys = conjGAnlys;
FormatReader.preparer = new AnalyzePreparer();
}
#endregion
var dictionaryJsonText = File.ReadAllText(dictionaryFilePath);
var reader = new RootReader {
};
reader.subReader.Push(new GrammarDictRoot {
gAnlysDict = gDict
});
reader.Read(dictionaryJsonText);
var rootGAnlys = gDict.dict["RootUnit"];
nlProcessor = new MGSyntacticProcessor {
gAnalyzer = new StdGrammarAnalyzer {
incrGAnalyzer = rootGAnlys, analyzePreparer = FormatReader.preparer
},
mAnalyzer = mAnlys
};
}
