Set a custom user-agent header when fetching CTC Cambridge stops data

This is required because their hosting provider is returning a 503 "service unavailable" when the user agent is Go-http-client.
Fix default to match docs
2024-04-17 17:19:42 +01:00 · 2023-01-19 16:43:09 +00:00 · 2023-01-19 16:21:32 +00:00 · 2023-01-19 16:20:22 +00:00 · 2021-06-18 11:56:16 +01:00 · 2021-04-12 09:15:20 +01:00
10 changed files with 343 additions and 50 deletions
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@ -0,0 +1,25 @@
+stages:
+  - build
+  - deploy
+
+build-gpx-anomalies:
+  stage: build
+  image: golang:1.15-buster
+  before_script:
+    - apt-get -qq update && apt-get --yes install zip
+  script:
+    - env GOOS=windows go build -o gpx-anomalies.exe ./cmd/gpx-anomalies
+    - zip gpx-anomalies.zip gpx-anomalies.exe
+  artifacts:
+    paths:
+      - gpx-anomalies.zip
+
+publish-gpx-anomalies:
+  stage: deploy
+  image: curlimages/curl:latest
+  variables:
+    GIT_STRATEGY: none
+  script:
+    - 'curl --header "JOB-TOKEN: $CI_JOB_TOKEN" --upload-file gpx-anomalies.zip "${CI_API_V4_URL}/projects/${CI_PROJECT_ID}/packages/generic/gpx-anomalies/latest/gpx-anomalies.zip"'
+  rules:
+    - if: '$CI_COMMIT_BRANCH == "master"'
--- a/cmd/analyze-gpx/main.go
+++ b/cmd/analyze-gpx/main.go
@ -19,8 +19,11 @@ import (
 func main() {
 	log.SetFlags(0)
 	stopNames := flag.String("stops", "", "Source for refreshment stops")
-	minDist := flag.Float64("min-dist", 0.2, "Minimum distance (km) between points of interest")
-	minSettlement := flag.String("min-settlement", "Other Settlement", "Exclude populated places smaller than this (City, Town, Village, Hamlet, Other Settlement)")
+	stopRect := flag.Float64("sr", placenames.DefaultGPXSummarizerConfig.CoffeeStopSearchRectangleSize, "Size (m) of the rectangle we search for coffee stops near the route")
+	stopDupDist := flag.Float64("sdd", placenames.DefaultGPXSummarizerConfig.CoffeeStopDuplicateDistance, "Suppress recurrences of coffee stops within this distance (km)")
+	dupDist := flag.Float64("dd", placenames.DefaultGPXSummarizerConfig.PointOfInterestDuplicateDistance, "Suppress recurrences of points of interest within this distance (km)")
+	minDist := flag.Float64("md", placenames.DefaultGPXSummarizerConfig.PointOfInterestMinimumDistance, "Minimum distance (km) between points of interest")
+	minSettlement := flag.String("ms", "Other Settlement", "Exclude populated places smaller than this (City, Town, Village, Hamlet, Other Settlement)")
 	flag.Parse()
 	if flag.NArg() != 1 {
 		log.Fatal("Usage: %s [--stops=ctccambridge|cyclingmaps] [--min-dist X] [--min-settlement S] GPX_FILE_OR_DIRECTORY")
@ -38,12 +41,16 @@ func main() {
 			log.Fatal(err)
 		}
 	}
-	gs, err := placenames.NewGPXSummarizer()
+	gs, err := placenames.NewGPXSummarizer(
+		placenames.WithMinimumSettlement(*minSettlement),
+		placenames.WithPointOfInterestMinimumDistance(*minDist),
+		placenames.WithPointOfInterestDuplicateDistance(*dupDist),
+		placenames.WithCoffeeStopSearchRectangleSize(*stopRect),
+		placenames.WithCoffeeStopDuplicateDistance(*stopDupDist),
+	)
 	if err != nil {
 		log.Fatal(err)
 	}
-	gs.SetMinDistance(*minDist)
-	gs.SetMinSettlement(*minSettlement)
 	if info.IsDir() {
 		err = summarizeDirectory(gs, stops, inFile)
 	} else {
--- a/cmd/gpx-anomalies/main.go
+++ b/cmd/gpx-anomalies/main.go
@ -0,0 +1,135 @@
+package main
+
+import (
+	"fmt"
+	"log"
+	"math"
+	"os"
+
+	"github.com/fofanov/go-osgb"
+	"github.com/twpayne/go-gpx"
+	"github.com/urfave/cli/v2"
+)
+
+func main() {
+	log.SetFlags(0)
+	app := &cli.App{
+		Name:  "gpx-anomalies",
+		Usage: "Find repeated points in a GPX track",
+		Flags: []cli.Flag{
+			&cli.StringFlag{
+				Name:     "gpx-file",
+				Aliases:  []string{"g"},
+				Usage:    "Name of GPX file to process",
+				Required: true,
+			},
+			&cli.Float64Flag{
+				Name:    "fuzz",
+				Aliases: []string{"f"},
+				Usage:   "Consider two points coincident if they are within FUZZ kilometres of each other",
+				Value:   0.005,
+			},
+			&cli.Float64Flag{
+				Name:    "min-distance",
+				Aliases: []string{"min"},
+				Usage:   "Only show repeats that appear at least MIN kilometers apart",
+				Value:   0.1,
+			},
+			&cli.Float64Flag{
+				Name:    "max-distance",
+				Aliases: []string{"max"},
+				Usage:   "Do not show repeats that appear more than MAX kilometers apart",
+				Value:   5.0,
+			},
+		},
+		Action: func(c *cli.Context) error {
+			points, err := readGPXTrack(c.String("gpx-file"))
+			if err != nil {
+				log.Fatal(err)
+			}
+			findDuplicates(
+				points,
+				c.Float64("fuzz")*1000.0,
+				c.Float64("min-distance")*1000.0,
+				c.Float64("max-distance")*1000.0,
+			)
+			return nil
+		},
+	}
+	if err := app.Run(os.Args); err != nil {
+		log.Fatal(err)
+	}
+
+}
+
+func findDuplicates(points []RoutePoint, fuzz, minDist, maxDist float64) {
+	var lastError *RoutePoint
+	for i := range points {
+		p := points[i]
+		for j := i + 1; j < len(points); j++ {
+			q := points[j]
+			if p.Distance == q.Distance {
+				continue
+			}
+			d := euclideanDistance(p.Coordinate, q.Coordinate)
+			D := q.Distance - p.Distance
+			if d < fuzz && D > minDist && D < maxDist {
+				if lastError == nil || p.Distance-lastError.Distance > 500 {
+					fmt.Printf("Point (%0.f, %0.f) revisited at %0.2f km and %0.2f km\n",
+						p.Coordinate.Easting, p.Coordinate.Northing, p.Distance/1000.0, q.Distance/1000.0)
+				}
+				lastError = &p
+			}
+		}
+	}
+}
+
+func euclideanDistance(p, q *osgb.OSGB36Coordinate) float64 {
+	x := p.Easting - q.Easting
+	y := p.Northing - q.Northing
+	return math.Sqrt(x*x + y*y)
+}
+
+func readGPXTrack(filename string) ([]RoutePoint, error) {
+	r, err := os.Open(filename)
+	if err != nil {
+		return nil, fmt.Errorf("error opening %s for reading: %v", filename, err)
+	}
+	defer r.Close()
+	g, err := gpx.Read(r)
+	if err != nil {
+		return nil, fmt.Errorf("error reading GPS track %s: %v", filename, err)
+	}
+	trans, err := osgb.NewOSTN15Transformer()
+	if err != nil {
+		return nil, fmt.Errorf("error constructing coordinate transformer: %v", err)
+	}
+	distance := 0.0
+	var prevPoint *osgb.OSGB36Coordinate
+	var points []RoutePoint
+	for _, trk := range g.Trk {
+		for _, seg := range trk.TrkSeg {
+			for _, trkPt := range seg.TrkPt {
+				gpsCoord := osgb.NewETRS89Coord(trkPt.Lon, trkPt.Lat, trkPt.Ele)
+				p, err := trans.ToNationalGrid(gpsCoord)
+				if err != nil {
+					return nil, fmt.Errorf("error converting coordinates to National Grid: %v", err)
+				}
+				if prevPoint != nil {
+					distance += euclideanDistance(prevPoint, p)
+				}
+				points = append(points, RoutePoint{
+					Coordinate: p,
+					Distance:   distance,
+				})
+				prevPoint = p
+			}
+		}
+	}
+	return points, nil
+}
+
+type RoutePoint struct {
+	Coordinate *osgb.OSGB36Coordinate
+	Distance   float64
+}
--- a/go.mod
+++ b/go.mod
@ -3,12 +3,14 @@ module github.com/ray1729/gpx-utils
 go 1.13

 require (
-	github.com/d4l3k/messagediff v1.2.1 // indirect
+	github.com/cpuguy83/go-md2man/v2 v2.0.0 // indirect
 	github.com/dhconnelly/rtreego v1.0.0
 	github.com/fofanov/go-osgb v0.0.0-20170711141822-6893d1f95cd9
+	github.com/russross/blackfriday/v2 v2.1.0 // indirect
 	github.com/twpayne/go-geom v1.3.6 // indirect
 	github.com/twpayne/go-gpx v1.2.0
-	github.com/wlbr/mule v0.0.0-20200329114911-0724e1639b62 // indirect
-	golang.org/x/net v0.0.0-20201201195509-5d6afe98e0b7 // indirect
-	golang.org/x/text v0.3.4 // indirect
+	github.com/urfave/cli/v2 v2.3.0
+	github.com/wlbr/mule v0.0.0-20200517121540-6f9faa2e2d0b // indirect
+	golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9 // indirect
+	golang.org/x/net v0.0.0-20210410081132-afb366fc7cd1 // indirect
 )
--- a/go.sum
+++ b/go.sum
@ -1,4 +1,5 @@
 github.com/Azure/go-ansiterm v0.0.0-20170929234023-d6e3b3328b78/go.mod h1:LmzpDX56iTiv29bbRTIsUNlaFfuhWRQBWjQdVyAevI8=
+github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
 github.com/DATA-DOG/go-sqlmock v1.3.2/go.mod h1:f/Ixk793poVmq4qj/V1dPUg2JEAKC73Q5eFN3EC/SaM=
 github.com/Masterminds/goutils v1.1.0/go.mod h1:8cTjp+g8YejhMuvIA5y2vz3BpJxksy863GQaJW2MFNU=
 github.com/Masterminds/semver v1.5.0/go.mod h1:MB6lktGJrhw8PrUyiEoblNEGEQ+RzHPF078ddwwvV3Y=
@ -7,8 +8,12 @@ github.com/Microsoft/go-winio v0.4.14/go.mod h1:qXqCSQ3Xa7+6tgxaGTIe4Kpcdsi+P8jB
 github.com/Nvveen/Gotty v0.0.0-20120604004816-cd527374f1e5/go.mod h1:lmUJ/7eu/Q8D7ML55dXQrVaamCz2vxCfdQBasLZfHKk=
 github.com/cenkalti/backoff/v3 v3.0.0/go.mod h1:cIeZDE3IrqwwJl6VUwCN6trj1oXrTS4rc0ij+ULvLYs=
 github.com/containerd/continuity v0.0.0-20190827140505-75bee3e2ccb6/go.mod h1:GL3xCUCBDV3CZiTSEKksMWbLE66hEyuu9qyDOOqM47Y=
-github.com/d4l3k/messagediff v1.2.1/go.mod h1:Oozbb1TVXFac9FtSIxHBMnBCq2qeH/2KkEQxENCrlLo=
+github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d h1:U+s90UTSYgptZMwQh2aRr3LuazLJIa+Pg3Kc1ylSYVY=
+github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsrgA7czyZG/E6dU=
+github.com/cpuguy83/go-md2man/v2 v2.0.0 h1:EoUDS0afbrsXAZ9YQ9jdu/mZ2sXgT1/2yyNng4PGlyM=
+github.com/cpuguy83/go-md2man/v2 v2.0.0/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsrgA7czyZG/E6dU=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dhconnelly/rtreego v1.0.0 h1:1+V1STGw+zwx7jpvH/fwbeC5w5gZfn+XinARU45oRek=
 github.com/dhconnelly/rtreego v1.0.0/go.mod h1:SDozu0Fjy17XH1svEXJgdYq8Tah6Zjfa/4Q33Z80+KM=
@ -32,7 +37,14 @@ github.com/opencontainers/image-spec v1.0.1/go.mod h1:BtxoFyWECRxE4U/7sNtV5W15zM
 github.com/opencontainers/runc v1.0.0-rc9/go.mod h1:qT5XzbpPznkRYVz/mWwUaVBUv2rmF59PVA73FjuZG0U=
 github.com/ory/dockertest/v3 v3.6.0/go.mod h1:4ZOpj8qBUmh8fcBSVzkH2bws2s91JdGvHUqan4GHEuQ=
 github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/russross/blackfriday/v2 v2.0.1 h1:lPqVAte+HuHNfhJ/0LC98ESWRz8afy9tM/0RK8m9o+Q=
+github.com/russross/blackfriday/v2 v2.0.1/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
+github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
+github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
+github.com/shurcooL/sanitized_anchor_name v1.0.0 h1:PdmoCO6wvbs+7yrJyMORt4/BmY5IYyJwS/kOiWx8mHo=
+github.com/shurcooL/sanitized_anchor_name v1.0.0/go.mod h1:1NzhyTcUVG4SuEtjjoZeVRXNmyL/1OwPU0+IJeTBvfc=
 github.com/sirupsen/logrus v1.4.1/go.mod h1:ni0Sbl8bgC9z8RoU9G6nDWqqs/fq4eDPysMBDgk/93Q=
 github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE=
 github.com/spf13/pflag v1.0.3/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4=
@ -41,31 +53,32 @@ github.com/stretchr/objx v0.1.1/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+
 github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
+github.com/stretchr/testify v1.6.1 h1:hDPOHmpOpP40lSULcqw7IrRb/u7w6RpDC9399XyoNd0=
 github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
-github.com/twpayne/go-geom v1.0.0 h1:ARrRnN4+rBX3LZFZQy9NFeXXlgQqVL4OOvAcnLdgy2g=
 github.com/twpayne/go-geom v1.0.0/go.mod h1:RWsl+e3XSahOul/KH2BHCfF0QxSL4RMnMlFw/TNmET0=
 github.com/twpayne/go-geom v1.3.6 h1:O27mIXZnMYiZi0ZD8ewjs/IT/ZOFVbZHBzPjA9skdmg=
 github.com/twpayne/go-geom v1.3.6/go.mod h1:XTyWHR6+l9TUYONbbK4ImUTYbWDCu2ySSPrZmmiA0Pg=
-github.com/twpayne/go-gpx v1.1.1 h1:vbg0lRc/ZKSu8ev84/hJWZtplKJdBbucNmks4TNzSqQ=
-github.com/twpayne/go-gpx v1.1.1/go.mod h1:fQ+EsiFNgDuErUYyI0ZOgZPB+ACxW58L16oormty798=
 github.com/twpayne/go-gpx v1.2.0 h1:Jjq0NKXgHmEXXhmQue4KWtAVG5gxkAYY+FvsM1AliLQ=
 github.com/twpayne/go-gpx v1.2.0/go.mod h1:70xTQn0dGph3dgKIPxfl0K3XMVNpulC70/e383iHouA=
 github.com/twpayne/go-kml v1.0.0/go.mod h1:LlvLIQSfMqYk2O7Nx8vYAbSLv4K9rjMvLlEdUKWdjq0=
 github.com/twpayne/go-kml v1.5.1/go.mod h1:kz8jAiIz6FIdU2Zjce9qGlVtgFYES9vt7BTPBHf5jl4=
 github.com/twpayne/go-polyline v1.0.0/go.mod h1:ICh24bcLYBX8CknfvNPKqoTbe+eg+MX1NPyJmSBo7pU=
 github.com/twpayne/go-waypoint v0.0.0-20200706203930-b263a7f6e4e8/go.mod h1:qj5pHncxKhu9gxtZEYWypA/z097sxhFlbTyOyt9gcnU=
-github.com/wlbr/mule v0.0.0-20200329114911-0724e1639b62 h1:vHDdpwOGHzfFKbMLEnnM0s1jnGLjsQ9EPWtCFWMJs8o=
-github.com/wlbr/mule v0.0.0-20200329114911-0724e1639b62/go.mod h1:uDXgZTfL0uJWiY/MQKcqI5VPQV8PCooNsWXozHf7CJ8=
+github.com/urfave/cli/v2 v2.3.0 h1:qph92Y649prgesehzOrQjdWyxFOp/QVM+6imKHad91M=
+github.com/urfave/cli/v2 v2.3.0/go.mod h1:LJmUH05zAU44vOAcrfzZQKsZbVcdbOG8rtL3/XcUArI=
+github.com/wlbr/mule v0.0.0-20200517121540-6f9faa2e2d0b h1:wZDyxL+jeSaBLmUFM+k/P97BbS8z3QYKcfbvWPnKq9Q=
+github.com/wlbr/mule v0.0.0-20200517121540-6f9faa2e2d0b/go.mod h1:uDXgZTfL0uJWiY/MQKcqI5VPQV8PCooNsWXozHf7CJ8=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20200323165209-0ec3e9974c59/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
-golang.org/x/net v0.0.0-20180824152047-4bcd98cce591 h1:4S2XUgvg3hUNTvxI307qkFPb9zKHG3Nf9TXFzX/DZZI=
 golang.org/x/net v0.0.0-20180824152047-4bcd98cce591/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20191003171128-d98b1b443823/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20201201195509-5d6afe98e0b7 h1:3uJsdck53FDIpWwLeAXlia9p4C8j0BO2xZrqzKpL0D8=
 golang.org/x/net v0.0.0-20201201195509-5d6afe98e0b7/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
+golang.org/x/net v0.0.0-20210410081132-afb366fc7cd1 h1:4qWs8cYYH6PoEFy4dfhDFgoMGkwAcETd+MmPdCPMzUc=
+golang.org/x/net v0.0.0-20210410081132-afb366fc7cd1/go.mod h1:9tjilg8BloeKEkVJvy7fQ90B1CfIiPueXVOjqfkSzI8=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@ -74,16 +87,23 @@ golang.org/x/sys v0.0.0-20190422165155-953cdadca894/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20190507160741-ecd444e8653b/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200121082415-34d275377bf9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/text v0.3.0 h1:g61tztE5qeGQ89tm6NTjjM9VPIm088od1l6aSorWRWg=
+golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210330210617-4fbd30eecc44/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.4 h1:0YWbFKbhXG/wIiuHDSKpS0Iy7FSA+u45VtBMfQcFTTc=
 golang.org/x/text v0.3.4/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.6 h1:aRYxNxv6iGQlyVaZmk6ZgYEDa+Jg18DxebPSrd6bg1M=
+golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190624222133-a101b041ded4/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v2 v2.2.3/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.7/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c h1:dUUwHk2QECo/6vqA44rthZ8ie2QXMNeKRTHCNY2nXvo=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gotest.tools/v3 v3.0.2/go.mod h1:3SzNCllyD9/Y+b5r9JIKQ474KzkZyqLqEfYqMsX94Bk=
--- a/pkg/cafes/common.go
+++ b/pkg/cafes/common.go
@ -9,6 +9,9 @@ import (
 	"github.com/dhconnelly/rtreego"
 )

+// Size (in metres) of the bounding box around a stop
+const stopRectangleSize = 50
+
 type RefreshmentStop struct {
 	Name     string
 	Url      string
@ -18,7 +21,7 @@ type RefreshmentStop struct {

 func (s *RefreshmentStop) Bounds() *rtreego.Rect {
 	p := rtreego.Point{s.Easting, s.Northing}
-	return p.ToRect(100)
+	return p.ToRect(stopRectangleSize)
 }

 func (s *RefreshmentStop) Contains(p rtreego.Point) bool {
--- a/pkg/cafes/ctccam.go
+++ b/pkg/cafes/ctccam.go
@ -54,7 +54,12 @@ func BuildCtcCamIndex(r io.Reader) (*rtreego.Rtree, error) {

 func FetchCtcCamIndex() (*rtreego.Rtree, error) {
 	log.Printf("Fetching %s", ctcCamWaypointsUrl)
-	res, err := http.Get(ctcCamWaypointsUrl)
+	req, err := http.NewRequest(http.MethodGet, ctcCamWaypointsUrl, nil)
+	if err != nil {
+		return nil, fmt.Errorf("error constructing waypoints request: %v", err)
+	}
+	req.Header.Set("User-Agent", "gpx-utils")
+	res, err := http.DefaultClient.Do(req)
 	if err != nil {
 		return nil, fmt.Errorf("error getting %s: %v", ctcCamWaypointsUrl, err)
 	}
--- a/pkg/placenames/summarize.go
+++ b/pkg/placenames/summarize.go
@ -9,9 +9,8 @@ import (

 	"github.com/dhconnelly/rtreego"
 	"github.com/fofanov/go-osgb"
-	"github.com/twpayne/go-gpx"
-
 	"github.com/ray1729/gpx-utils/pkg/cafes"
+	"github.com/twpayne/go-gpx"
 )

 var populatedPlaceRank = map[string]int{
@ -22,14 +21,80 @@ var populatedPlaceRank = map[string]int{
 	"Other Settlement": 1,
 }

+// GPXSummarizerConfig allows override of defaults used by the search algorithm.
+type GPXSummarizerConfig struct {
+	CoffeeStopSearchRectangleSize    float64
+	CoffeeStopDuplicateDistance      float64
+	PointOfInterestDuplicateDistance float64
+	PointOfInterestMinimumDistance   float64
+	MinimumSettlementRank            int
+}
+
+var DefaultGPXSummarizerConfig = GPXSummarizerConfig{
+	CoffeeStopSearchRectangleSize:    500.0, // m
+	CoffeeStopDuplicateDistance:      2.0,   // km
+	PointOfInterestDuplicateDistance: 1.0,   // km
+	PointOfInterestMinimumDistance:   0.0,   // km
+	MinimumSettlementRank:            1,     // "Other Settlement"
+}
+
+type Option func(*GPXSummarizerConfig)
+
+// WithCoffeeStopSearchRectangleSize overrides the size (in metres) of the rectangle searched
+// for coffee stops near the route. Default 500m.
+func WithCoffeeStopSearchRectangleSize(d float64) Option {
+	return func(c *GPXSummarizerConfig) {
+		c.CoffeeStopSearchRectangleSize = d
+	}
+}
+
+// WithCoffeeStopDuplicateDistance overrides the distance (in kilometers) we look back along the
+// route when suppressing duplicate coffee stop entries. This should be at least twice the
+// CoffeeStopSearchRectangleSize. Default 2km.
+func WithCoffeeStopDuplicateDistance(d float64) Option {
+	return func(c *GPXSummarizerConfig) {
+		c.CoffeeStopDuplicateDistance = d
+	}
+}
+
+// WithPointOfInterestDuplicateDistance overrides the distance (in km) we look back along
+// the route when suppressing duplicate points of interest.
+func WithPointOfInterestDuplicateDistance(d float64) Option {
+	return func(c *GPXSummarizerConfig) {
+		c.PointOfInterestDuplicateDistance = d
+	}
+}
+
+// WithPointOfInterestMinimumDistance overrides the minimum distance (in km) between points
+// of interest (if two POI appear within this distance, the second one is suppressed). Default
+// 0km (no suppression).
+func WithPointOfInterestMinimumDistance(d float64) Option {
+	return func(c *GPXSummarizerConfig) {
+		c.PointOfInterestMinimumDistance = d
+	}
+}
+
+func WithMinimumSettlement(s string) Option {
+	rank, ok := populatedPlaceRank[s]
+	if !ok {
+		panic(fmt.Sprintf("invalid settlement type: %s", s))
+	}
+	return func(c *GPXSummarizerConfig) {
+		c.MinimumSettlementRank = rank
+	}
+}
+
 type GPXSummarizer struct {
 	poi   *rtreego.Rtree
 	trans osgb.CoordinateTransformer
-	minDist           float64
-	minSettlementRank int
+	conf  GPXSummarizerConfig
 }

-func NewGPXSummarizer() (*GPXSummarizer, error) {
+func NewGPXSummarizer(opts ...Option) (*GPXSummarizer, error) {
+	conf := DefaultGPXSummarizerConfig
+	for _, f := range opts {
+		f(&conf)
+	}
 	trans, err := osgb.NewOSTN15Transformer()
 	if err != nil {
 		return nil, err
@ -38,15 +103,7 @@ func NewGPXSummarizer() (*GPXSummarizer, error) {
 	if err != nil {
 		return nil, err
 	}
-	return &GPXSummarizer{poi: rt, trans: trans, minDist: 0.2, minSettlementRank: 1}, nil
-}
-
-func (gs *GPXSummarizer) SetMinSettlement(t string) {
-	gs.minSettlementRank = populatedPlaceRank[t]
-}
-
-func (gs *GPXSummarizer) SetMinDistance(d float64) {
-	gs.minDist = d
+	return &GPXSummarizer{poi: rt, trans: trans, conf: conf}, nil
 }

 func distance(p1, p2 rtreego.Point) float64 {
@ -108,7 +165,6 @@ func (gs *GPXSummarizer) SummarizeTrack(r io.Reader, stops *rtreego.Rtree) (*Tra
 	var prevPlace string
 	var prevPlacePoint rtreego.Point
 	var prevPoint rtreego.Point
-	var prevStop *cafes.RefreshmentStop
 	var start rtreego.Point
 	var dN, dE float64

@ -141,25 +197,44 @@ func (gs *GPXSummarizer) SummarizeTrack(r io.Reader, stops *rtreego.Rtree) (*Tra
 				s.Distance += distance(thisPoint, prevPoint)
 				dE += thisPoint[0] - start[0]
 				dN += thisPoint[1] - start[1]
-				if nn.Contains(thisPoint) {
+				if nn.Contains(thisPoint) && populatedPlaceRank[nn.Type] >= gs.conf.MinimumSettlementRank {
 					s.Counties[nn.County]++
-					if nn.Name != prevPlace &&
-						distance(thisPoint, prevPlacePoint) > gs.minDist &&
-						populatedPlaceRank[nn.Type] >= gs.minSettlementRank {
+					seenRecently := false
+					for i := len(s.PointsOfInterest) - 1; i >= 0; i-- {
+						if i < len(s.PointsOfInterest)-1 && s.Distance-s.PointsOfInterest[i].Distance > gs.conf.PointOfInterestDuplicateDistance {
+							break
+						}
+						if nn.Name == s.PointsOfInterest[i].Name {
+							seenRecently = true
+							break
+						}
+					}
+					if !seenRecently && distance(thisPoint, prevPlacePoint) > gs.conf.PointOfInterestMinimumDistance {
 						s.PointsOfInterest = append(s.PointsOfInterest, POI{Name: nn.Name, Type: nn.Type, Distance: s.Distance})
 						prevPlace = nn.Name
 						prevPlacePoint = thisPoint
 					}
 				}
 				if stops != nil {
-					stop, ok := stops.NearestNeighbor(thisPoint).(*cafes.RefreshmentStop)
-					if ok && stop.Contains(thisPoint) && (prevStop == nil || stop.Name != prevStop.Name) {
+					for _, nearbyStop := range stops.SearchIntersect(thisPoint.ToRect(gs.conf.CoffeeStopSearchRectangleSize)) {
+						stop := nearbyStop.(*cafes.RefreshmentStop)
+						seenRecently := false
+						for i := len(s.RefreshmentStops) - 1; i >= 0; i-- {
+							if i < len(s.RefreshmentStops)-1 && s.Distance-s.RefreshmentStops[i].Distance > gs.conf.CoffeeStopDuplicateDistance {
+								break
+							}
+							if s.RefreshmentStops[i].Name == stop.Name {
+								seenRecently = true
+								break
+							}
+						}
+						if !seenRecently {
 							s.RefreshmentStops = append(s.RefreshmentStops, RefreshmentStop{
 								Name:     stop.Name,
 								Url:      stop.Url,
 								Distance: s.Distance,
 							})
-						prevStop = stop
+						}
 					}
 				}
 				prevPoint = thisPoint
--- a/pkg/rwgps/handler.go
+++ b/pkg/rwgps/handler.go
@ -41,7 +41,7 @@ func (h *RWGPSHandler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 	}
 	routeId, err := strconv.Atoi(rawRouteId)
 	if err != nil {
-		log.Println("Error parsing route id '%s': %v", rawRouteId, err)
+		log.Printf("Error parsing route id '%s': %v", rawRouteId, err)
 		http.Error(w, fmt.Sprintf("Invalid routeId: %s", rawRouteId), http.StatusBadRequest)
 		return
 	}
--- a/scripts/summarizeRoutes.py
+++ b/scripts/summarizeRoutes.py
@ -0,0 +1,21 @@
+#!/usr/bin/python3
+
+import csv
+import sys
+
+path = sys.argv[1]
+
+with open(path) as f:
+    r = csv.reader(f)
+    skip = True
+    for x in r:
+        if skip:
+            skip = False
+            continue
+        coffee = x[7].strip()
+        lunch = x[8].strip()
+        tea = x[9].strip()
+        if coffee and tea:
+            print(coffee + ", " + lunch + ", " + tea)
+
+
Author	SHA1	Message	Date
Ray Miller	f09fd9a418	Set a custom user-agent header when fetching CTC Cambridge stops data This is required because their hosting provider is returning a 503 "service unavailable" when the user agent is Go-http-client.	2024-04-17 17:19:42 +01:00
Ray Miller	4ef3eca5a4	Fix default to match docs	2023-01-19 16:43:09 +00:00
Ray Miller	bd7eb246d5	Improvements to duplicate suppression, cafe stop search, and configurability. When suppressing duplicate cafes and place names, look back a certain distance along the route rather than just the previous point of interest. When searching for cafes, use SearchIntersect() to return all entries in the bounding rectangle, not just the nearest. Remove (most) hard-coded constants and allow these to be overriden by options to the NewGPXSummarizer() constructor.	2023-01-19 16:21:32 +00:00
Ray Miller	4de001c867	Fix bug in logging: need Printf as string contains format directives.	2023-01-19 16:20:22 +00:00
Ray Miller	9ec3b2e980	Increase the search radius for cafe stops	2021-06-18 11:56:16 +01:00
Ray Miller	f740686d2f	Improved duplicate suppression	2021-04-12 09:15:20 +01:00
Ray Miller	34bdaeab71	Suppress duplicates in the output	2021-04-11 18:39:17 +01:00
Ray Miller	bc6affbce1	Call the executable exe	2021-04-10 14:22:22 +01:00
Ray Miller	08f37e8592	Add CI/CD config	2021-04-10 14:15:03 +01:00
Ray Miller	a3e30a5a3c	Add gpx-anomalies command	2021-04-10 14:01:23 +01:00