NLP-2043 fixes to engine for foreign, fixes to livedata direct_ queries

Author: chatscriptnlp

BINARIES/chatscript.exe

@@ -15,6 +15,7 @@ couple 2 WORD_NUMBER
 deuce 2  WORD_NUMBER  
 pair 2  WORD_NUMBER  
 half 2 FRACTION_NUMBER  
+halves 2 FRACTION_NUMBER  
 three 3  REAL_NUMBER 
 third 3 WORD_NUMBER 
 triple 3  WORD_NUMBER 

LIVEDATA/ENGLISH/numbers.txt

@@ -155,7 +155,6 @@ QUERY: directflag_v		"1vq: queue v : f"						# (? love ?)
 # 2. walk thru q, looking at facts were q item is verb
 # 3. fact must have flag on it from match argument
 
-
 # find facts given an object
 QUERY: direct_o		"1oq: queue o"							# (? ? cat)
 # 1. tag object with 1 and queue it
@@ -169,35 +168,35 @@ QUERY: directflag_o		"1oq: queue o : f"							# (? ? cat)
 # 3. there are no constraints to match, so all facts are accepted that have factflag on
 
 # find facts given subject and verb
-QUERY: direct_sv	"1sq 2vt: queue s: match v2"			# (dog love ?)
+QUERY: direct_sv	"1sq 2vT: queue s: match v2"			# (dog love ?)
 # 1. tag subject with 1 and queue it
 # 2. mark verb with 2 (no queuing)
 # 3. walk thru q, looking at facts where q item is subject
 # 4. accept facts where verb is marked with 2
 
 # find facts given subject and verb
-QUERY: directflag_sv	"1sq 2vt: queue s: match v2 f"			# (dog love ?)
+QUERY: directflag_sv	"1sq 2vT: queue s: match v2 f"			# (dog love ?)
 # 1. tag subject with 1 and queue it
 # 2. mark verb with 2 (no queuing)
 # 3. walk thru q, looking at facts where q item is subject
 # 4. accept facts where verb is marked with 2 and fact flag  is on
 
 # find facts given fact subject and verb
-QUERY: direct_Sv	"1Sq 2vt: queue s: match v2"			# (dog love ?)
+QUERY: direct_Sv	"1Sq 2vT: queue s: match v2"			# (dog love ?)
 # 1. tag subject with 1 and queue it
 # 2. mark verb with 2 (no queuing)
 # 3. walk thru q, looking at facts where q item is subject
 # 4. accept facts where verb is marked with 2
 
 # find facts given verb and object
-QUERY: direct_vo	"1oq 2vt: queue o: match v2"			# (? love cat)
+QUERY: direct_vo	"1oq 2vT: queue o: match v2"			# (? love cat)
 # 1. tag object with 1 and queue it
 # 2. mark verb with 2 (no queuing)
 # 3. walk thru q, looking at facts where q item is object
 # 4. accept facts where verb is marked with 2
 
 # find facts given verb and object and flag
-QUERY: directflag_vo	"1oq 2vt: queue o: match v2 f"			# (? love cat)
+QUERY: directflag_vo	"1oq 2vT: queue o: match v2 f"			# (? love cat)
 # 1. tag object with 1 and queue it
 # 2. mark verb with 2 (no queuing)
 # 3. walk thru q, looking at facts where q item is object
@@ -211,22 +210,22 @@ QUERY: direct_vO	"1Oq 2vt: queue o: match v2"			# (? love cat)
 # 4. accept facts where verb is marked with 2
 
 # find facts given subject and object
-QUERY: direct_so	"1sq 2ot: queue s: match o2"			# (dog ? cat)
+QUERY: direct_so	"1sq 2oT: queue s: match o2"			# (dog ? cat)
 # 1. tag subject with 1 and queue it
 # 2. mark object with 2 (no queuing)
 # 3. walk thru q, looking at facts where q item is subject
 # 4. accept facts where object is marked with 2
 
 # find facts given subject verb and object
-QUERY: direct_svo	"1oq 2vt 3st: queue o: match v2 s3"	# (dog love cat)
+QUERY: direct_svo	"1oq 2vT 3sT: queue o: match v2 s3"	# (dog love cat)
 # 1. tag object with 1 and queue it
 # 2. mark verb with 2 (no queuing)
 # 3. mark subject with 3 (no queuing)
 # 4. walk thru q, looking at facts where q item is object
 # 5. accept facts where verb is marked with 2 and subject is marked with 3
 
 # find facts given subject verb and object and flag
-QUERY: directflag_svo	"1oq 2vt 3st: queue o: match v2 s3  f"	# (dog love cat)
+QUERY: directflag_svo	"1oq 2vT 3sT: queue o: match v2 s3  f"	# (dog love cat)
 # 1. tag object with 1 and queue it
 # 2. mark verb with 2 (no queuing)
 # 3. mark subject with 3 (no queuing)

LIVEDATA/SYSTEM/queries.txt

@@ -306,7 +306,8 @@ char* GetCanonical(WORDP D)
 {
 	std::map<WORDP,WORDP>::iterator it;
 	it = canonicalWords.find(D);
-	return (it != canonicalWords.end())	? it->second->word  : NULL;
+	if (it == canonicalWords.end()) return NULL;
+	return it->second->word;
 }
 
 WORDP GetTense(WORDP D)
@@ -1853,6 +1854,7 @@ void WriteDictionary(WORDP D,uint64 data)
 	WriteDictionaryReference((char*)"conjugate",GetTense(D),out);
 	WriteDictionaryReference((char*)"plural",GetPlural(D),out);
 	WriteDictionaryReference((char*)"comparative",GetComparison(D),out);
+	if (GetCanonical(D)) WriteDictionaryReference((char*)"lemma", FindWord(GetCanonical(D)), out);
 
 	//   show the meanings, with illustrative gloss
 

SRC/dictionarySystem.cpp

@@ -608,7 +608,9 @@ uint64 GetPosData( int at, char* original,WORDP& revise, WORDP &entry,WORDP &can
 
 	if (externalTagger || stricmp(language, "english"))
 	{
-		entry = canonical = StoreWord(original);
+		entry  = StoreWord(original);
+		canonical = FindWord(GetCanonical(entry));
+		if (!canonical) canonical = entry;
 		return 0; // remote pos tagging or none
 	}
 

SRC/english.cpp

@@ -9317,6 +9317,13 @@ static void BuildForeign(char* input)
 		printf("file not found");
 		return;
 	}
+
+	UseDictionaryFile(NULL);
+	InitFacts();
+	InitDictionary();
+	InitStackHeap();
+	InitCache();
+
 	sprintf(name,"DICT/%s",language);
 	MakeDirectory(name);
 	ClearDictionaryFiles();
@@ -9339,6 +9346,7 @@ static void BuildForeign(char* input)
 		*close = 0;
 		strcpy(lemma, ptr + 1);
 		*close = ')';
+		if (!strcmp(lemma, word)) *lemma = 0; // cancel same lemma
 
 		char pos[MAX_WORD_SIZE];
 		unsigned int flags = 0;
@@ -9351,10 +9359,12 @@ static void BuildForeign(char* input)
 			WORDP D = FindWord(pos);
 			if (D) flags |= D->properties;
 		}
-		StoreWord(word, flags);
+		WORDP D = StoreWord(word, flags);
+		if (*lemma) SetCanonical(D, MakeMeaning(StoreWord(lemma)));
 	}
 	fclose(in);
 	WalkDictionary(WriteDictionary);
+	myexit("end foreign build");
 }
 
 static void TrimIt(char* name,uint64 flag)