Merge pull request #106 from abruere/master

Improve Harry's Wikipedia example

Author: chatscriptnlp

RAWDATA/HARRY/keywordless.top

@@ -1,4 +1,4 @@
-# this is the topic for anything that has no obvious topic. 
+# this is the topic for anything that has no obvious topic.
 # it is called directly from the control script when everything else fails.
 
 topic: ~keywordless nostay()
@@ -12,30 +12,32 @@ u: (< say _*) keep() repeat() '_0
 #! yes, if user just says OK or yes or continue, then move along and give control to bot
 u: ( < [~yesanswer ~more]>) ^keep() gambit($$currenttopic) # current topic gets to continue
 
-?: (what is a _*1 >) keep() $$tmp = _0
-	 $$url = ^"\"https://en.wikipedia.org/w/api.php?action=query&prop=extracts&exsentences=2&exintro=&explaintext=&format=json&titles=$$tmp\""
-	 $$user_agent = ^"myemail@hotmail.com User-Agent: Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; WOW64; Trident/6.0)"
-	 $$tmp = ^jsonopen(GET $$url "" $$user_agent)
+#! What is democracy?
+#! What is climate change?
+?: (what be {a} _*~2 >) ^keep() $$tmp = '_0
+	$$url = ^"\"https://en.wikipedia.org/w/api.php?action=query&prop=extracts&exsentences=2&exintro=&explaintext=&format=json&utf8=&redirects=&titles=$$tmp\""
+	# Url escaping is done by ^jsonopen
+	$$user_agent = ^"myemail@hotmail.com User-Agent: Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; WOW64; Trident/6.0)"
+	$$tmp = ^jsonopen(GET $$url "" $$user_agent)
 		# ^jsontree($$tmp)
 		# ^jsonpath(  ".query .pages .56333 .extract" $$tmp)
-		@0 = query(direct_v ? extract ? 1)
+		@0 = ^query(direct_v ? extract ? 1)
 		@0object
-			
-?: (who be _*1  >) keep()  $$tmp = substitute(character '_0 _ %20 )
-	 $$url = ^"\"https://en.wikipedia.org/w/api.php?action=query&prop=extracts&exsentences=2&exintro=&explaintext=&format=json&titles=$$tmp\""
-	 $$user_agent = ^"myemail@hotmail.com User-Agent: Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; WOW64; Trident/6.0)"
-	 $$tmp = ^jsonopen(GET $$url "" $$user_agent)
-		# ^jsontree($$tmp)
-		# ^jsonpath(  ".query .pages .56333 .extract" $$tmp)
-		@0 = query(direct_v ? extract ? 1)
-		@0object
-	
-?: (who be _*1 _*1 >) keep()  $$tmp = join('_0  %20  '_1)
-	 $$url = ^"\"https://en.wikipedia.org/w/api.php?action=query&prop=extracts&exsentences=2&exintro=&explaintext=&format=json&titles=$$tmp\""
-	 $$user_agent = ^"myemail@hotmail.com User-Agent: Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; WOW64; Trident/6.0)"
-	 $$tmp = ^jsonopen(GET $$url "" $$user_agent)
+
+#! Who is Gandhi
+#! Who is Lyndon Johnson # merged to Lyndon_Jonhnson
+#! Who is Athenian democracy # testing two non merged words
+?: (who be _*~2 >) ^keep()
+	$$tmp = ^pos(capitalize ^original(_0))
+	##<<
+		Using original instead of '_0 to skip Wordnet dictionnary, since Wikipedia has more searchable content.
+		and correct spelling is left to the user.  In return this avoids excessive spellcheck on proper nouns.
+		Wikipedia does not systematically redirect mis-cased requests. Proper names should always be capitalized
+	##>>
+	$$url = ^"\"https://en.wikipedia.org/w/api.php?action=query&prop=extracts&exsentences=2&exintro=&explaintext=&format=json&utf8=&redirects=&titles=$$tmp\""
+	$$user_agent = ^"myemail@hotmail.com User-Agent: Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; WOW64; Trident/6.0)"
+	$$tmp = jsonopen(GET $$url "" $$user_agent)
 		# ^jsontree($$tmp)
 		# ^jsonpath(  ".query .pages .56333 .extract" $$tmp)
-		@0 = query(direct_v ? extract ? 1)
+		@0 = ^query(direct_v ? extract ? 1)
 		@0object
-