initial commit

.gitignore

@@ -0,0 +1,3 @@
+api-raml/
+article-json/
+validate-article-json

go.mod

@@ -0,0 +1,14 @@
+module validate-article-json
+
+go 1.20
+
+require github.com/santhosh-tekuri/jsonschema/v5 v5.3.1
+
+require (
+	github.com/kr/pretty v0.3.1 // indirect
+	github.com/kr/text v0.2.0 // indirect
+	github.com/rogpeppe/go-internal v1.9.0 // indirect
+	github.com/tidwall/gjson v1.15.0 // indirect
+	github.com/tidwall/match v1.1.1 // indirect
+	github.com/tidwall/pretty v1.2.1 // indirect
+)

go.sum

@@ -0,0 +1,17 @@
+github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
+github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
+github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
+github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
+github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
+github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
+github.com/rogpeppe/go-internal v1.9.0 h1:73kH8U+JUqXU8lRuOHeVHaa/SZPifC7BkcraZVejAe8=
+github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
+github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 h1:lZUw3E0/J3roVtGQ+SCrUrg3ON6NgVqpn3+iol9aGu4=
+github.com/santhosh-tekuri/jsonschema/v5 v5.3.1/go.mod h1:uToXkOrWAZ6/Oc07xWQrPOhJotwFIyu2bBVN41fcDUY=
+github.com/tidwall/gjson v1.15.0 h1:5n/pM+v3r5ujuNl4YLZLsQ+UE5jlkLVm7jMzT5Mpolw=
+github.com/tidwall/gjson v1.15.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
+github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
+github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=
+github.com/tidwall/pretty v1.2.0/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
+github.com/tidwall/pretty v1.2.1 h1:qjsOFOWWQl+N3RsoF5/ssm1pHmJJwhjlSbZ51I6wMl4=
+github.com/tidwall/pretty v1.2.1/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=

main.go

@@ -0,0 +1,125 @@
+package main
+
+// "If you want a fast and correct validator, pick santhosh-tekuri/jsonschema."
+// - https://dev.to/vearutop/benchmarking-correctness-and-performance-of-go-json-schema-validators-3247
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"strings"
+	"time"
+
+	"github.com/santhosh-tekuri/jsonschema/v5"
+	"github.com/tidwall/gjson"
+)
+
+// todo:
+// https://json-schema.org/understanding-json-schema/reference/regular_expressions.html
+// https://github.com/santhosh-tekuri/jsonschema/issues/113
+
+func panic_on_err(err error, action string) {
+	if err != nil {
+		panic(fmt.Sprintf("failed with '%s' while '%s'", err.Error(), action))
+	}
+}
+
+func slurp_bytes(path string) []byte {
+	body, err := os.ReadFile(path)
+	panic_on_err(err, "slurping bytes from path: "+path)
+	return body
+}
+
+func fail(msg string) int {
+	println(msg)
+	return 1
+}
+
+func success(msg string) int {
+	println(msg)
+	return 0
+}
+
+type Foo struct {
+	Label  string
+	Path   string
+	Schema *jsonschema.Schema
+}
+
+func main() {
+
+	// parse args
+
+	args := os.Args[1:]
+	article_json_path := args[0]
+
+	// configure validator
+
+	loader := jsonschema.Loaders["file"]
+	c := jsonschema.NewCompiler()
+	c.Draft = jsonschema.Draft4
+	schema_file_list := map[string]string{
+		"POA": "api-raml/dist/model/article-poa.v3.json",
+		"VOR": "api-raml/dist/model/article-vor.v7.json",
+	}
+	schema_map := map[string]Foo{}
+
+	for label, path := range schema_file_list {
+		rdr, err := loader(path)
+		panic_on_err(err, fmt.Sprintf("loading '%s' schema file: ", label, path))
+		err = c.AddResource(label, rdr)
+		panic_on_err(err, "adding schema to compiler: "+label)
+		schema, err := c.Compile(label)
+		panic_on_err(err, "compiling schema: "+label)
+		schema_map[label] = Foo{
+			Label:  label,
+			Path:   path,
+			Schema: schema,
+		}
+	}
+
+	// read article data and determine schema to use
+
+	article_json_bytes := slurp_bytes(article_json_path)
+	result := gjson.GetBytes(article_json_bytes, "article.status")
+	if !result.Exists() {
+		panic("'article.status' field in article data not found: " + article_json_path)
+	}
+	schema_key := strings.ToUpper(result.String()) // "poa" => "POA"
+	schema, present := schema_map[schema_key]
+	if !present {
+		panic("schema not found: " + schema_key)
+	}
+
+	// article-json contains 'journal', 'snippet' and 'article' sections.
+	// extract just the 'article' from the article data.
+
+	result = gjson.GetBytes(article_json_bytes, "article")
+	if !result.Exists() {
+		panic("'article' field in article data not found: " + article_json_path)
+	}
+	// what is happening here?? we're extracting a slice of the matching bytes
+	// from the article-json without converting it to a string then back to bytes.
+	var raw []byte
+	if result.Index > 0 {
+		raw = article_json_bytes[result.Index : result.Index+len(result.Raw)]
+	} else {
+		raw = []byte(result.Raw)
+	}
+
+	// convert the article-json data into a simple go datatype
+	var article interface{}
+	err := json.Unmarshal(raw, &article)
+	panic_on_err(err, "unmarshalling article section bytes")
+
+	// finally, validate!
+
+	start := time.Now()
+	err = schema.Schema.Validate(article)
+	if err != nil {
+		os.Exit(fail("input file is not valid: " + err.Error()))
+	}
+	t := time.Now()
+	elapsed := t.Sub(start)
+	os.Exit(success(fmt.Sprintf("%s article validated in %s", schema.Label, elapsed)))
+}