Merge pull request #5 from Dynom/ImplementingAListEndpoint

Config and endpoints
Dynom · Jul 3, 2018 · 141c1ae · 141c1ae
2 parents ce050f5 + 44bbedc
commit 141c1ae
Show file tree

Hide file tree

Showing 20 changed files with 706 additions and 163 deletions.
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -18,6 +18,6 @@ jobs:
       - run: dep ensure -v -vendor-only
       - run: go get -v -t -d ./...
       - run: go get -u github.com/alecthomas/gometalinter && gometalinter -i
-      - run: gometalinter -t -D gotype -D errcheck --vendor --cyclo-over=10 --deadline=10m --enable=testify --enable=test --enable=gofmt --enable=unused -e "should have"  ./...
+      - run: gometalinter -t -D errcheck -D gotype -D ineffassig --vendor --cyclo-over=10 --deadline=5m --enable=testify --enable=test --enable=gofmt --enable=megacheck --enable=nakedret -e "Errors unhandled" ./...
       - run: go test -test.v -test.cover -test.race -test.coverprofile=coverage.txt -test.covermode=atomic ./... 
       - run: bash <(curl -s https://codecov.io/bash)
diff --git a/Gopkg.lock b/Gopkg.lock
diff --git a/README.md b/README.md
@@ -31,7 +31,18 @@ out-of-the-box as a library, a webservice or as a set of packages to build your
 By default it uses [Jaro-Winkler](https://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance) to calculate similarity.
 
 ## As a webservice
-@todo
+
+In a nutshell
+```bash
+curl 'http://localhost:1337/list/domains' -d '{"input": "foomail.com"}'
+{"result":"hotmail.com","score":0.9030303030303031}
+```
+
+### The path /list/< name >
+The name corresponds with a list definition in the config.yml. Using this approach the service can be used for various 
+types of data. This is both for efficiency (shorter lists to iterate over) and to be more opinionated. when no list by 
+that name is found, a 404 is returned.
+
 
 ## As a library
 You can use the various components that make up TySug individually or as a whole.
@@ -99,24 +110,23 @@ To help people avoid submitting an incorrect e-mail address, one could try the f
 
 ```go
 func SuggestAlternative(email string, domains []string) (string, float64) {
-
     i := strings.LastIndex(email, "@")
     if i <= 0 || i >= len(email) {
         return email, 0
     }
-    
+
     // Extracting the local and domain parts
     localPart := email[:i]
     hostname := email[i+1:]
-    
+
     sug, _ := finder.New(domains)
-    alternative, score := sug.Find(hostname)
-    
-    if score > 0.9 {
+    alternative, score, exact := sug.Find(hostname)
+
+    if exact || score > 0.9 {
         combined := localPart + "@" + alternative
         return combined, score
     }
-    
+
     return email, score
 }
 ```

diff --git a/algorithm_test.go b/algorithm_test.go
@@ -4,7 +4,6 @@ import (
 	"testing"
 
 	"fmt"
-	"math"
 	"strings"
 
 	"github.com/Dynom/TySug/finder"
@@ -14,15 +13,14 @@ import (
 
 const (
 	defaultTestAlgorithm = `JaroWinkler .7/4`
-	floatTolerance       = 0.000001
 )
 
 // Several algorithms to test with.
 var algorithms = map[string]finder.Algorithm{
 	"Ukkonen 1/1/1": func(a, b string) float64 {
 		return -1 * float64(smetrics.Ukkonen(a, b, 1, 1, 1))
 	},
-	"JaroWinkler .7/4": func(a, b string) float64 {
+	defaultTestAlgorithm: func(a, b string) float64 {
 		return smetrics.JaroWinkler(a, b, .7, 4)
 	},
 	"WagnerFischer 1/1/1": func(a, b string) float64 {
@@ -82,7 +80,7 @@ func TestAlgorithms(t *testing.T) {
 			for expectedDomain, emailsToTest := range testData {
 				for _, domain := range emailsToTest {
 
-					bestMatch, score := sug.Find(domain)
+					bestMatch, score, _ := sug.Find(domain)
 					if bestMatch != expectedDomain {
 						t.Logf("Related score: %f", score)
 						t.Logf("Expected '%s' to result in '%s'. Instead I got: '%s'.", domain, expectedDomain, bestMatch)
@@ -96,7 +94,7 @@ func TestAlgorithms(t *testing.T) {
 func TestNew(t *testing.T) {
 	expect := "example"
 	sug, _ := finder.New([]string{expect, "ample"}, finder.WithAlgorithm(algorithms[defaultTestAlgorithm]))
-	alt, _ := sug.Find("exampel")
+	alt, _, _ := sug.Find("exampel")
 
 	if alt != expect {
 		t.Errorf("Expected '%s' to be '%s'.", alt, expect)
@@ -114,14 +112,14 @@ func TestTestExactMatch(t *testing.T) {
 
 	for _, td := range cases {
 		sug, _ := finder.New([]string{"foo", "example", "CaseSensitive", "cASEsENSITIVE"}, finder.WithAlgorithm(algorithms[defaultTestAlgorithm]))
-		match, score := sug.Find(td.Input)
+		match, _, exact := sug.Find(td.Input)
 
 		if match != td.Expect {
 			t.Errorf("Expected the input '%s' to result in '%s', however the best match is '%s'", td.Input, td.Expect, match)
 		}
 
-		if math.Abs(1-score) > floatTolerance {
-			t.Errorf("Expected a score of ~1.0, instead it is: %f", score)
+		if !exact {
+			t.Errorf("Expected an exact match, instead I got %t", exact)
 		}
 	}
 }
@@ -137,7 +135,7 @@ func TestApproximateMatch(t *testing.T) {
 
 	for _, td := range cases {
 		sug, _ := finder.New([]string{td.Reference}, finder.WithAlgorithm(algorithms[defaultTestAlgorithm]))
-		match, _ := sug.Find(td.Input)
+		match, _, _ := sug.Find(td.Input)
 
 		if match != td.Reference {
 			t.Errorf("Expected the input '%s' to result in '%s', however the best match '%s'", td.Input, td.Reference, match)
@@ -150,19 +148,19 @@ func BenchmarkBasicUsage(b *testing.B) {
 
 	b.Run("Direct match", func(b *testing.B) {
 		for i := 0; i < b.N; i++ {
-			_, _ = sug.Find("foo")
+			_, _, _ = sug.Find("foo")
 		}
 	})
 
 	b.Run("Non direct match, low score", func(b *testing.B) {
 		for i := 0; i < b.N; i++ {
-			_, _ = sug.Find("juice")
+			_, _, _ = sug.Find("juice")
 		}
 	})
 
 	b.Run("Non direct match, high score", func(b *testing.B) {
 		for i := 0; i < b.N; i++ {
-			_, _ = sug.Find("butterfyl")
+			_, _, _ = sug.Find("butterfyl")
 		}
 	})
 }
@@ -190,9 +188,9 @@ func SuggestAlternative(email string, domains []string) (string, float64) {
 	hostname := email[i+1:]
 
 	sug, _ := finder.New(domains, finder.WithAlgorithm(algorithms[defaultTestAlgorithm]))
-	alternative, score := sug.Find(strings.ToLower(hostname))
+	alternative, score, exact := sug.Find(strings.ToLower(hostname))
 
-	if score > 0.9 {
+	if exact || score > 0.9 {
 		combined := localPart + "@" + alternative
 		return combined, score
 	}

diff --git a/config.yml b/config.yml
@@ -0,0 +1,118 @@
+client:
+  referencesMax: 100
+  inputLengthMax: 50
+
+CORS:
+  # Not defining allowedOrigins will use wildcard '*', meaning all clients are allowed.
+  #allowedOrigins:
+  #  - http://example.org
+  #  - https://api.example.com
+
+server:
+  listenOn: "0.0.0.0:1337"
+
+references:
+  domains:
+    - gmail.com
+    - yahoo.com
+    - hotmail.com
+    - aol.com
+    - hotmail.co.uk
+    - hotmail.fr
+    - msn.com
+    - yahoo.fr
+    - wanadoo.fr
+    - orange.fr
+    - comcast.net
+    - yahoo.co.uk
+    - yahoo.com.br
+    - yahoo.co.in
+    - live.com
+    - rediffmail.com
+    - free.fr
+    - gmx.de
+    - web.de
+    - yandex.ru
+    - ymail.com
+    - libero.it
+    - outlook.com
+    - uol.com.br
+    - bol.com.br
+    - mail.ru
+    - cox.net
+    - hotmail.it
+    - sbcglobal.net
+    - sfr.fr
+    - live.fr
+    - verizon.net
+    - live.co.uk
+    - googlemail.com
+    - yahoo.es
+    - ig.com.br
+    - live.nl
+    - bigpond.com
+    - terra.com.br
+    - yahoo.it
+    - neuf.fr
+    - yahoo.de
+    - alice.it
+    - rocketmail.com
+    - att.net
+    - laposte.net
+    - facebook.com
+    - bellsouth.net
+    - yahoo.in
+    - hotmail.es
+    - charter.net
+    - yahoo.ca
+    - yahoo.com.au
+    - rambler.ru
+    - hotmail.de
+    - tiscali.it
+    - shaw.ca
+    - yahoo.co.jp
+    - sky.com
+    - earthlink.net
+    - optonline.net
+    - freenet.de
+    - t-online.de
+    - aliceadsl.fr
+    - virgilio.it
+    - home.nl
+    - qq.com
+    - telenet.be
+    - me.com
+    - yahoo.com.ar
+    - tiscali.co.uk
+    - yahoo.com.mx
+    - voila.fr
+    - gmx.net
+    - mail.com
+    - planet.nl
+    - tin.it
+    - live.it
+    - ntlworld.com
+    - arcor.de
+    - yahoo.co.id
+    - frontiernet.net
+    - hetnet.nl
+    - live.com.au
+    - yahoo.com.sg
+    - zonnet.nl
+    - club-internet.fr
+    - juno.com
+    - optusnet.com.au
+    - blueyonder.co.uk
+    - bluewin.ch
+    - skynet.be
+    - sympatico.ca
+    - windstream.net
+    - mac.com
+    - centurytel.net
+    - chello.nl
+    - live.ca
+    - aim.com
+    - bigpond.net.au
+    - hotmail.nl
+    - ziggo.nl
+    - live.com