Project

General

Profile

« Previous | Next » 

Revision 29246

integrated branch providing more structured Document model. Added new Distance algos and conditions. Allow to specify strict conditions.

View differences:

result.pace.conf
3 3
		acronyms { fields = [title], params = { max = 1, minLen = 2, maxLen = 4} },
4 4
		ngrampairs { fields = [title], params = { max = 1, ngramLen = 3} },
5 5
		suffixprefix { fields = [title], params = { max = 1, len = 3 } } 
6
	},	
6
	},
7
	strictconditions {
8
		exactMatch { fields = [pid] }
9
	}, 
7 10
	conditions { 
8 11
		yearMatch { fields = [dateofacceptance] },
9
		titleVersionMatch { fields = [title] } 
12
		titleVersionMatch { fields = [title] },
13
		sizeMatch { fields = [authors] } 
10 14
	},
11 15
	model {
12 16
		pid { algo = ExactMatch, type = String, weight = 0.0, ignoreMissing = true, path = pid/value, overrideMatch = true }, 	
13 17
		title { algo = JaroWinkler, type = String, weight = 1.0, ignoreMissing = false, path = result/metadata/title/value },
14
		dateofacceptance { algo = Null, type = String, weight = 0.0, ignoreMissing = true, path = result/metadata/dateofacceptance/value } 	
18
		dateofacceptance { algo = Null, type = String, weight = 0.0, ignoreMissing = true, path = result/metadata/dateofacceptance/value } ,
19
		authors { algo = Null, type = List, weight = 0.0, ignoreMissing = true, path = result/author/metadata/fullname/value } 		
15 20
	},
16 21
	blacklists = {
17 22
		title = [

Also available in: Unified diff