tests: add tests and GHA workflow

.gitattributes

@@ -0,0 +1,2 @@
+.snapshots/ linguist-generated=true
+testdata/ linguist-generated=true

.github/workflows/go.yml

@@ -0,0 +1,38 @@
+on:
+  push:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: install go
+        uses: actions/setup-go@v4
+        with:
+          go-version: 'stable'
+      - name: install python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.x'
+      - name: install rust
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+      - name: install python dependencies
+        run: pip install twine build
+      - name: install go dependencies
+        run: go install gotest.tools/gotestsum@latest
+      - name: run golangci-lint
+        uses: reviewdog/action-golangci-lint@v2
+      - name: build
+        run: go build
+      - name: test
+        run: gotestsum --jsonfile unit-tests.json
+      - name: annotate tests
+        if: always()
+        uses: guyarb/[email protected]
+        with:
+          test-results: unit-tests.json

.gitignore

@@ -0,0 +1,4 @@
+testdata/packages/
+!testdata/packages/.gitkeep
+.idea
+*.iml

archiver/archive_reader_test.go

@@ -0,0 +1 @@
+package archiver_test

distributions/distribution_test.go

@@ -0,0 +1 @@
+package distributions_test

distributions/metadata_test.go

@@ -0,0 +1 @@
+package distributions_test

distributions/sdist_test.go

@@ -0,0 +1 @@
+package distributions_test

distributions/wheel_test.go

@@ -0,0 +1 @@
+package distributions_test

go.mod

@@ -7,4 +7,13 @@ require (
 	golang.org/x/text v0.13.0
 )
 
-require golang.org/x/sys v0.12.0 // indirect
+require (
+	github.com/bradleyjkemp/cupaloy v2.3.0+incompatible // indirect
+	github.com/davecgh/go-spew v1.1.1 // indirect
+	github.com/google/go-cmp v0.6.0 // indirect
+	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/stretchr/objx v0.5.0 // indirect
+	github.com/stretchr/testify v1.8.4 // indirect
+	golang.org/x/sys v0.12.0 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+)

go.sum

@@ -1,6 +1,27 @@
+github.com/bradleyjkemp/cupaloy v2.3.0+incompatible h1:UafIjBvWQmS9i/xRg+CamMrnLTKNzo+bdmT/oH34c2Y=
+github.com/bradleyjkemp/cupaloy v2.3.0+incompatible/go.mod h1:Au1Xw1sgaJ5iSFktEhYsS0dbQiS1B0/XMXl+42y9Ilk=
+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/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+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/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
+github.com/stretchr/objx v0.5.0 h1:1zr/of2m5FGMsad5YfcqgdqdWrIhu+EBEJRhR1U7z/c=
+github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
+github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
+github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
+github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 golang.org/x/crypto v0.13.0 h1:mvySKfSWJ+UKUii46M40LOvyWfN0s2U+46/jDd0e6Ck=
 golang.org/x/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc=
 golang.org/x/sys v0.12.0 h1:CM0HF96J0hcLAwsHPJZjfdNzs0gftsLfgKt57wWHJ0o=
 golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/text v0.13.0 h1:ablQoSUd0tRdKxZewP80B+BaqeKJuVhuRxj/dkrun3k=
 golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

packages/hash_manager_test.go

@@ -0,0 +1 @@
+package packages_test

packages/package_test.go

@@ -0,0 +1 @@
+package packages_test

packages/utils_test.go

@@ -0,0 +1 @@
+package packages_test

parse.go

@@ -48,7 +48,7 @@ func findDistributions(dists []string) ([]string, error) {
 		if err != nil {
 			return nil, err
 		}
-		if files == nil || len(files) == 0 {
+		if len(files) == 0 {
 			return nil, fmt.Errorf("cannot find file (or expand pattern): %s", filename)
 		}
 

parse_test.go

@@ -0,0 +1,177 @@
+package parse_test
+
+import (
+	"fmt"
+	"github.com/google/go-cmp/cmp"
+	"github.com/rstudio/python-distribution-parser"
+	"github.com/stretchr/testify/assert"
+	"log"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"path"
+
+	"os"
+	"os/exec"
+	"path/filepath"
+	"testing"
+)
+
+var twine = "twine"
+var testdata = "testdata/packages/"
+var repositoryUrls = []string{
+	"https://github.com/ActiveState/appdirs",
+	"https://github.com/pallets/click",
+	"https://github.com/python/importlib_metadata",
+	"https://github.com/matplotlib/matplotlib",
+	"https://github.com/sdispater/pendulum",
+	"https://github.com/pytest-dev/pytest",
+}
+
+// toRepositoryName converts a repository name to the name of the folder the repository will be cloned in
+// for example, https://github.com/ActiveState/appdirs => appdirs
+func toRepositoryName(repositoryUrl string) (string, error) {
+	result, err := url.Parse(repositoryUrl)
+	if err != nil {
+		return "", err
+	}
+	return path.Base(result.Path), nil
+}
+
+func getRepositoryPath(repository string) string {
+	return fmt.Sprintf("%s%s/", testdata, repository)
+}
+
+func getDistributionPath(repository string) string {
+	return fmt.Sprintf("%sdist/", getRepositoryPath(repository))
+}
+
+func getTarballPath(repository string) (string, error) {
+	distributionPath := getDistributionPath(repository)
+	files, err := os.ReadDir(distributionPath)
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	var tarballs []string
+
+	for _, file := range files {
+		if filepath.Ext(file.Name()) == ".gz" {
+			tarballs = append(tarballs, file.Name())
+		}
+	}
+
+	if len(tarballs) != 1 {
+		return "", fmt.Errorf("unexpected number of .gz files in %s: %d", distributionPath, len(tarballs))
+	}
+	return fmt.Sprintf("%s%s", distributionPath, tarballs[0]), nil
+}
+
+func clone(repositoryUrl string) error {
+	repositoryName, err := toRepositoryName(repositoryUrl)
+	if err != nil {
+		return err
+	}
+
+	_, err = os.Stat(getRepositoryPath(repositoryName))
+	if os.IsNotExist(err) {
+		cmd := exec.Command("git", "clone", repositoryUrl)
+		cmd.Dir = testdata
+		cmd.Stdout = os.Stdout
+		cmd.Stderr = os.Stderr
+		err := cmd.Run()
+		return err
+	} else {
+		log.Printf("%s is already cloned", repositoryName)
+		return nil
+	}
+}
+
+func buildDistribution(repository string) error {
+	_, err := os.Stat(getDistributionPath(repository))
+	if os.IsNotExist(err) {
+		cmd := exec.Command("python", "-m", "build")
+		cmd.Dir = getRepositoryPath(repository)
+		cmd.Stdout = os.Stdout
+		cmd.Stderr = os.Stderr
+		err := cmd.Run()
+		return err
+	} else {
+		log.Printf("%s is already built", repository)
+		return nil
+	}
+
+}
+
+func getTwineMetadata(repository string) (map[string][]string, error) {
+	var expectedMetadata map[string][]string
+
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		_ = r.ParseMultipartForm(100000)
+		expectedMetadata = r.MultipartForm.Value
+	}))
+	defer ts.Close()
+
+	tarball, err := getTarballPath(repository)
+	if err != nil {
+		return nil, err
+	}
+
+	cmd := exec.Command(twine, "upload", tarball)
+	cmd.Env = append(cmd.Env, fmt.Sprintf("TWINE_REPOSITORY_URL=%s", ts.URL))
+	cmd.Env = append(cmd.Env, "TWINE_USERNAME=user")
+	cmd.Env = append(cmd.Env, "TWINE_PASSWORD=password")
+
+	cmd.Stdout = os.Stdout
+	cmd.Stderr = os.Stderr
+	err = cmd.Run()
+	if err != nil {
+		return nil, err
+	}
+
+	return expectedMetadata, nil
+}
+
+func getParserMetadata(repository string) (map[string][]string, error) {
+	tarball, err := getTarballPath(repository)
+	if err != nil {
+		return nil, err
+	}
+
+	result, err := parse.Parse(tarball)
+	if err != nil {
+		return nil, err
+	}
+
+	if len(result) != 1 {
+		return nil, fmt.Errorf("unexpected length: %d", len(result))
+	}
+
+	distribution := result[0]
+	return distribution.MetadataMap(), nil
+}
+
+func TestParse(t *testing.T) {
+	for _, repositoryUrl := range repositoryUrls {
+		log.Printf("testing %s", repositoryUrl)
+
+		err := clone(repositoryUrl)
+		if err != nil {
+			log.Fatal(err)
+		}
+
+		repositoryName, err := toRepositoryName(repositoryUrl)
+		assert.Nil(t, err)
+
+		err = buildDistribution(repositoryName)
+		assert.Nil(t, err)
+
+		expectedMetadata, err := getTwineMetadata(repositoryName)
+		assert.Nil(t, err)
+
+		actualMetadata, err := getParserMetadata(repositoryName)
+		assert.Nil(t, err)
+
+		assert.Empty(t, cmp.Diff(expectedMetadata, actualMetadata))
+	}
+}