Add LIX tests

summarize/readability_test.go

@@ -27,6 +27,7 @@ func TestReadability(t *testing.T) {
 		assert.True(t, check(test.StdDevGrade, a.StdDevGradeLevel))
 		assert.True(t, check(test.DaleChall, a.DaleChall))
 		assert.True(t, check(test.ReadingEase, a.ReadingEase))
+		assert.True(t, check(test.LIX, a.LIX))
 	}
 }
 

summarize/summarize.go

@@ -69,6 +69,7 @@ type Assessment struct {
 	FleschKincaid        float64
 	GunningFog           float64
 	SMOG                 float64
+	LIX                  float64
 
 	// mean & standard deviation of the above estimated grade levels
 	MeanGradeLevel   float64
@@ -143,7 +144,8 @@ func (d *Document) Assess() *Assessment {
 	a := Assessment{
 		FleschKincaid: d.FleschKincaid(), ReadingEase: d.FleschReadingEase(),
 		GunningFog: d.GunningFog(), SMOG: d.SMOG(), DaleChall: d.DaleChall(),
-		AutomatedReadability: d.AutomatedReadability(), ColemanLiau: d.ColemanLiau()}
+		AutomatedReadability: d.AutomatedReadability(), ColemanLiau: d.ColemanLiau(),
+		LIX: d.LIX()}
 
 	gradeScores := []float64{
 		a.FleschKincaid, a.AutomatedReadability, a.GunningFog, a.SMOG,

summarize/summarize_test.go

@@ -28,6 +28,7 @@ type testCase struct {
 	FleschKincaid        float64
 	GunningFog           float64
 	SMOG                 float64
+	LIX                  float64
 
 	MeanGrade   float64
 	StdDevGrade float64

testdata/summarize.json

@@ -12,7 +12,8 @@
         "MeanGrade": 13.21,
         "StdDevGrade": 0.72,
         "DaleChall": 9.51,
-        "ReadingEase": 47.29
+        "ReadingEase": 47.29,
+        "LIX": 54.06
     },
     {
         "text": "Existing computer programs that measure readability are based largely upon subroutines which estimate number of syllables, usually by counting vowels. The shortcoming in estimating syllables is that it necessitates keypunching the prose into the computer. There is no need to estimate syllables since word length in letters is a better predictor of readability than word length in syllables. Therefore, a new readability formula was computed that has for its predictors letters per 100 words and sentences per 100 words. Both predictors can be counted by an optical scanning device, and thus the formula makes it economically feasible for an organization such as the U.S. Office of Education to calibrate the readability of all textbooks for the public school system.",
@@ -27,7 +28,8 @@
         "MeanGrade": 16.34,
         "StdDevGrade": 1.29,
         "DaleChall": 12.19,
-        "ReadingEase": 24.14
+        "ReadingEase": 24.14,
+        "LIX": 59.09
     },
     {
         "text": "He teaches science (He previously worked for 5 years as an engineer.) at the local University.",
@@ -42,6 +44,7 @@
         "MeanGrade": 11.06,
         "StdDevGrade": 2.03,
         "DaleChall": 10.66,
-        "ReadingEase": 53.12
+        "ReadingEase": 53.12,
+        "LIX": 47.25
     }
 ]