Merge pull request #104 from spdx/json

Merge JSON saving into main

docs/jsonloader.md

@@ -0,0 +1,24 @@
+SPDX-License-Identifier: CC-BY-4.0
+
+## Working
+
+A UnmarshallJSON function on the spdx.Document2_2 struct is defined so that when the JSON is unmarshalled in it the function is called and we can implement the process in a custom way . Then  a new map[string]interface{} is deifined which temporarily holds the unmarshalled json . The map is then parsed into the spdx.Document2_2 using functions defined for it’s different sections .
+
+JSON  →  map[string]interface{}  → spdx.Document2_2
+
+## Some Key Points 
+
+- The packages have a property "hasFiles" defined in the schema which is an array of the SPDX Identifiers of the files of that pacakge . The parses first parses all the files into the Unpackaged files map of the document and then when it parses the packages , it removes the respective files from the unpackaged files map and places it inside the files map of that package .
+
+- The snippets have a property "snippetFromFile" which has the SPDX identiifer of the file to which the snippet is related . Thus the snippets require the files to be parsed before them . Then the snippets are parsed one by one and inserted into the respective files using this property .
+
+
+The json file loader in `package jsonloader` makes the following assumptions:
+
+
+### Order of appearance of the properties 
+* The parser does not make any pre-assumptions based on the order in which the properties appear . 
+
+
+### Annotations
+* The json spdx schema does not define the SPDX Identifier property for the annotation object . The parser assumes the spdx Identifier of the parent property of the currently being parsed annotation array to be the SPDX Identifer for all the annotation objects of that array.

docs/jsonsaver.md

@@ -0,0 +1,28 @@
+SPDX-License-Identifier: CC-BY-4.0
+
+## Working
+
+The spdx document is converted to map[string]interface{} and then the entire map is converted to json using a single json Marshall function call . The saver uses a tempoarary storage to store all the files (Paackaged and Unpackaged) together in a single data structure in order to comply with the json schema defined by spdx .
+
+spdx.Document2_2  →  map[string]interface{}  → JSON
+
+## Some Key Points
+
+- The packages have a property "hasFiles" defined in the schema which is an array of the SPDX Identifiers of the files of that pacakge . The saver iterates through the files of a package and inserted all the SPDX Identifiers of the files in the "hasFiles" array . In addition it adds the file to a temporary storage map to store all the files of the entire document at a single place .
+
+- The files require the packages to be saved before them in order to ensure that the packaged files are added to the temporary storage before the files are saved .
+
+- The snippets are saved after the files and a property "snippetFromFile" identifies the file of the snippets.
+
+The json file loader in `package jsonsaver` makes the following assumptions:
+
+
+### Order of appearance of the properties
+* The saver does not make any pre-assumptions based on the order in which the properties are saved . 
+
+
+### Annotations
+* The json spdx schema does not define the SPDX Identifier property for the annotation object . The saver inserts the annotation inside the element who spdx identifier mathches the annotation SPDX identifier .
+
+### Indentation
+* The jsonsaver uses the marshall indent function with "" as he prefix and "\t" as the indent character  , passed as funtion parameters .

examples/10-jsonloader/example_json_loader.go

@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: Apache-2.0 OR GPL-2.0-or-later
+
+// Example for: *jsonparser2v2*
+
+// This example demonstrates loading an SPDX json from disk into memory,
+// and then logging out some attributes to the console .
+
+package main
+
+import (
+	"fmt"
+	"os"
+	"strings"
+
+	"github.com/spdx/tools-golang/jsonloader"
+)
+
+func main() {
+
+	// check that we've received the right number of arguments
+	args := os.Args
+	if len(args) != 3 {
+		fmt.Printf("Usage: %v <spdx-file-in> <spdx-file-out>\n", args[0])
+		fmt.Printf("  Load SPDX 2.2 tag-value file <spdx-file-in>, and\n")
+		fmt.Printf("  save it out to <spdx-file-out>.\n")
+		return
+	}
+
+	// open the SPDX file
+	fileIn := args[1]
+	r, err := os.Open(fileIn)
+	if err != nil {
+		fmt.Printf("Error while opening %v for reading: %v", fileIn, err)
+		return
+	}
+	defer r.Close()
+
+	// try to load the SPDX file's contents as a json file, version 2.2
+	doc, err := jsonloader.Load2_2(r)
+	if err != nil {
+		fmt.Printf("Error while parsing %v: %v", args[1], err)
+		return
+	}
+
+	// if we got here, the file is now loaded into memory.
+	fmt.Printf("Successfully loaded %s\n", args[1])
+
+	fmt.Println(strings.Repeat("=", 80))
+	fmt.Println("Some Attributes of the Document:")
+	fmt.Printf("Document Name:         %s\n", doc.CreationInfo.DocumentName)
+	fmt.Printf("DataLicense:           %s\n", doc.CreationInfo.DataLicense)
+	fmt.Printf("Document NameSpace:    %s\n", doc.CreationInfo.DocumentNamespace)
+	fmt.Printf("SPDX Document Version: %s\n", doc.CreationInfo.SPDXVersion)
+	fmt.Println(strings.Repeat("=", 80))
+}

examples/9-tvtojson/exampletvtojson.go

@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: Apache-2.0 OR GPL-2.0-or-later
+
+// Example for: *tvloader*, *jsonsaver*
+
+// This example demonstrates loading an SPDX tag-value file from disk into memory,
+// and re-saving it to a different json file on disk.
+
+package main
+
+import (
+	"fmt"
+	"os"
+
+	"github.com/spdx/tools-golang/jsonsaver"
+	"github.com/spdx/tools-golang/tvloader"
+)
+
+func main() {
+
+	// check that we've received the right number of arguments
+	args := os.Args
+	if len(args) != 3 {
+		fmt.Printf("Usage: %v <spdx-file-in> <spdx-file-out>\n", args[0])
+		fmt.Printf("  Load SPDX 2.2 tag-value file <spdx-file-in>, and\n")
+		fmt.Printf("  save it out to <spdx-file-out>.\n")
+		return
+	}
+
+	// open the SPDX file
+	fileIn := args[1]
+	r, err := os.Open(fileIn)
+	if err != nil {
+		fmt.Printf("Error while opening %v for reading: %v", fileIn, err)
+		return
+	}
+	defer r.Close()
+
+	// try to load the SPDX file's contents as a tag-value file, version 2.2
+	doc, err := tvloader.Load2_2(r)
+	if err != nil {
+		fmt.Printf("Error while parsing %v: %v", args[1], err)
+		return
+	}
+
+	// if we got here, the file is now loaded into memory.
+	fmt.Printf("Successfully loaded %s\n", args[1])
+
+	// we can now save it back to disk, using jsonsaver.
+
+	// create a new file for writing
+	fileOut := args[2]
+	w, err := os.Create(fileOut)
+	if err != nil {
+		fmt.Printf("Error while opening %v for writing: %v", fileOut, err)
+		return
+	}
+	defer w.Close()
+
+	// try to save the document to disk as an SPDX json file, version 2.2
+	err = jsonsaver.Save2_2(doc, w)
+	if err != nil {
+		fmt.Printf("Error while saving %v: %v", fileOut, err)
+		return
+	}
+
+	// it worked
+	fmt.Printf("Successfully saved %s\n", fileOut)
+}

examples/README.md

@@ -64,9 +64,23 @@ the same identifier in both documents.
 This example demonstrates loading an SPDX rdf file from disk into memory 
 and then printing the corresponding spdx struct for the document.
 
-## 8-jsonloader
+## 8-jsontotv
 
 *jsonloader*, *tvsaver*
 
 This example demonstrates loading an SPDX json from disk into memory
 and then re-saving it to a different file on disk in tag-value format.
+
+## 9-tvtojson
+
+*jsonsaver*, *tvloader*
+
+This example demonstrates loading an SPDX tag-value from disk into memory
+and then re-saving it to a different file on disk in json format.
+
+## 10-jsonloader
+
+*jsonloader*
+
+This example demonstrates loading an SPDX json from disk into memory
+and then logging some of the attributes to the console.

jsonloader/jsonloader_test.go

@@ -3,6 +3,7 @@
 package jsonloader
 
 import (
+	"bytes"
 	"fmt"
 	"io"
 	"os"
@@ -45,6 +46,14 @@ func TestLoad2_2(t *testing.T) {
 			},
 			wantErr: false,
 		},
+		{
+			name: "fail - invalidjson ",
+			args: args{
+				content: bytes.NewReader([]byte(`{"Hello":"HI",}`)),
+			},
+			want:    nil,
+			wantErr: true,
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
@@ -53,7 +62,7 @@ func TestLoad2_2(t *testing.T) {
 				t.Errorf("Load2_2() error = %v, wantErr %v", err, tt.wantErr)
 				return
 			}
-			if !reflect.DeepEqual(got.CreationInfo, tt.want.CreationInfo) {
+			if !tt.wantErr && !reflect.DeepEqual(got.CreationInfo, tt.want.CreationInfo) {
 				t.Errorf("Load2_2() = %v, want %v", got.CreationInfo, tt.want.CreationInfo)
 			}
 		})

jsonloader/parser2v2/parse_annotations_test.go

@@ -31,6 +31,26 @@ func TestJSONSpdxDocument_parseJsonAnnotations2_2(t *testing.T) {
 	  } ]
 	}
   `)
+	data2 := []byte(`{
+	"annotations" : [ {
+	"annotationDate" : "2010-02-10T00:00:00Z",
+	"annotationType" : "REVIEW",
+	"annotator" : "Person: Joe Reviewer",
+	"comment" : "This is just an example.  Some of the non-standard licenses look like they are actually BSD 3 clause licenses",
+	"Hello":"hellp"
+  }]
+}
+`)
+	data3 := []byte(`{
+	"annotations" : [ {
+	"annotationDate" : "2010-02-10T00:00:00Z",
+	"annotationType" : "REVIEW",
+	"annotator" : "Fasle: Joe Reviewer",
+	"comment" : "This is just an example.  Some of the non-standard licenses look like they are actually BSD 3 clause licenses",
+	"Hello":"hellp"
+  }]
+}
+`)
 
 	annotationstest1 := []*spdx.Annotation2_2{
 		{
@@ -60,7 +80,12 @@ func TestJSONSpdxDocument_parseJsonAnnotations2_2(t *testing.T) {
 	}
 
 	var specs JSONSpdxDocument
+	var specs2 JSONSpdxDocument
+	var specs3 JSONSpdxDocument
+
 	json.Unmarshal(data, &specs)
+	json.Unmarshal(data2, &specs2)
+	json.Unmarshal(data3, &specs3)
 
 	type args struct {
 		key           string
@@ -88,16 +113,41 @@ func TestJSONSpdxDocument_parseJsonAnnotations2_2(t *testing.T) {
 			want:    annotationstest1,
 			wantErr: false,
 		},
+		{
+			name: "failure test - invaid creator type",
+			spec: specs2,
+			args: args{
+				key:           "annotations",
+				value:         specs2["annotations"],
+				doc:           &spdxDocument2_2{},
+				SPDXElementID: spdx.DocElementID{DocumentRefID: "", ElementRefID: "DOCUMENT"},
+			},
+			want:    nil,
+			wantErr: true,
+		},
+		{
+			name: "failure test - invalid tag",
+			spec: specs3,
+			args: args{
+				key:           "annotations",
+				value:         specs3["annotations"],
+				doc:           &spdxDocument2_2{},
+				SPDXElementID: spdx.DocElementID{DocumentRefID: "", ElementRefID: "DOCUMENT"},
+			},
+			want:    nil,
+			wantErr: true,
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			if err := tt.spec.parseJsonAnnotations2_2(tt.args.key, tt.args.value, tt.args.doc, tt.args.SPDXElementID); (err != nil) != tt.wantErr {
 				t.Errorf("JSONSpdxDocument.parseJsonAnnotations2_2() error = %v, wantErr %v", err, tt.wantErr)
 			}
-
-			for i := 0; i < len(tt.want); i++ {
-				if !reflect.DeepEqual(tt.args.doc.Annotations[i], tt.want[i]) {
-					t.Errorf("Load2_2() = %v, want %v", tt.args.doc.Annotations[i], tt.want[i])
+			if !tt.wantErr {
+				for i := 0; i < len(tt.want); i++ {
+					if !reflect.DeepEqual(tt.args.doc.Annotations[i], tt.want[i]) {
+						t.Errorf("Load2_2() = %v, want %v", tt.args.doc.Annotations[i], tt.want[i])
+					}
 				}
 			}
 

jsonloader/parser2v2/parse_creation_info.go

@@ -79,9 +79,9 @@ func parseCreators(creators interface{}, ci *spdx.CreationInfo2_2) error {
 			}
 			switch subkey {
 			case "Person":
-				ci.CreatorPersons = append(ci.CreatorPersons, strings.TrimSuffix(subvalue, " ()"))
+				ci.CreatorPersons = append(ci.CreatorPersons, subvalue)
 			case "Organization":
-				ci.CreatorOrganizations = append(ci.CreatorOrganizations, strings.TrimSuffix(subvalue, " ()"))
+				ci.CreatorOrganizations = append(ci.CreatorOrganizations, subvalue)
 			case "Tool":
 				ci.CreatorTools = append(ci.CreatorTools, subvalue)
 			default: