Add Smile header decoding (#1)

Author: thomshutt

Makefile

@@ -0,0 +1,11 @@
+.PHONY: all
+all: fmt test
+
+.PHONY: fmt
+fmt:
+	go fmt ./...
+	go mod tidy
+
+.PHONY: test 
+test:
+	go test -race ./...

domain/header.go

@@ -0,0 +1,45 @@
+package domain
+
+import (
+	"errors"
+)
+
+type Header struct {
+	Version                           int
+	RawBinaryPresent                  bool
+	SharedStringValueEncodingEnabled  bool
+	SharedPropertyNameEncodingEnabled bool
+}
+
+/*
+Header consists of:
+
+    Constant byte #0: 0x3A (ASCII ':')
+    Constant byte #1: 0x29 (ASCII ')')
+    Constant byte #2: 0x0A (ASCII linefeed, '\n')
+    Variable byte #3, consisting of bits:
+        Bits 4-7 (4 MSB): 4-bit version number; 0x00 for current version (note: it is possible that some bits may be reused if necessary)
+        Bits 3: Reserved
+        Bit 2 (mask 0x04) Whether '''raw binary''' (unescaped 8-bit) values may be present in content
+        Bit 1 (mask 0x02): Whether '''shared String value''' checking was enabled during encoding -- if header missing, default value of "false" must be assumed for decoding (meaning parser need not store decoded String values for back referencing)
+        Bit 0 (mask 0x01): Whether '''shared property name''' checking was enabled during encoding -- if header missing, default value of "true" must be assumed for decoding (meaning parser MUST store seen property names for possible back references)
+
+And basically first 2 bytes form simple smiley and 3rd byte is a (Unix) linefeed: this to make command-line-tool based identification simple: choice of bytes is not significant beyond visual appearance. Fourth byte contains minimal versioning marker and additional configuration bits.
+*/
+func DecodeHeader(b []byte) (Header, error) {
+	if len(b) < 4 {
+		return Header{}, errors.New("smile format must begin with a 4-byte header")
+	}
+
+	if b[0] != ':' || b[1] != ')' || b[2] != '\n' {
+		return Header{}, errors.New("smile format must begin with the ':)' header followed by a newline")
+	}
+
+	var flags uint8 = b[3]
+	return Header{
+		Version:                           int(flags >> 4),
+		RawBinaryPresent:                  (0x04 & flags) != 0,
+		SharedStringValueEncodingEnabled:  (0x02 & flags) != 0,
+		SharedPropertyNameEncodingEnabled: (0x01 & flags) != 0,
+	}, nil
+}

domain/header_test.go

@@ -0,0 +1,35 @@
+package domain
+
+import (
+	"github.com/stretchr/testify/require"
+	"github.com/zencoder/go-smile/testdata"
+	"testing"
+)
+
+func TestDecodeHeader(t *testing.T) {
+	b := testdata.LoadJSONOrgSample1(t)
+
+	header, err := DecodeHeader(b)
+	require.NoError(t, err)
+
+	require.Equal(
+		t,
+		Header{
+			Version:                           0,
+			RawBinaryPresent:                  false,
+			SharedStringValueEncodingEnabled:  true,
+			SharedPropertyNameEncodingEnabled: true,
+		},
+		header,
+	)
+}
+
+func TestDecodeHeaderWithoutData(t *testing.T) {
+	_, err := DecodeHeader([]byte{})
+	require.EqualError(t, err, "smile format must begin with a 4-byte header")
+}
+
+func TestDecodeHeaderWithoutSmilieFails(t *testing.T) {
+	_, err := DecodeHeader([]byte{':', '(', '\n', '1'})
+	require.EqualError(t, err, "smile format must begin with the ':)' header followed by a newline")
+}

go.mod

@@ -1,3 +1,5 @@
 module github.com/zencoder/go-smile
 
 go 1.14
+
+require github.com/stretchr/testify v1.6.1

go.sum

@@ -0,0 +1,12 @@
+github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8=
+github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+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 h1:4G4v2dO3VZwixGIRoQ5Lfboy6nUhCyYzaqnIAPPhYs4=
+github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/testify v1.6.1 h1:hDPOHmpOpP40lSULcqw7IrRb/u7w6RpDC9399XyoNd0=
+github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+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.v3 v3.0.0-20200313102051-9f266ea9e77c h1:dUUwHk2QECo/6vqA44rthZ8ie2QXMNeKRTHCNY2nXvo=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

main.go

@@ -1,5 +1,7 @@
 package main
 
-func main() {
+import "fmt"
 
+func main() {
+	fmt.Println("Hello World!")
 }

testdata/json-org-sample1.smile

@@ -0,0 +1,2 @@
+:)
+��glossary��titleOexample glossary�GlossDiv�A@S�GlossList��GlossEntry��IDCSGML�SortAs�GlossTermcStandard Generalized Markup Language�Acronym�AbbrevLISO 8879:1986�GlossDef��para�A meta-markup language, used to create markup languages such as DocBook.��GlossSeeAlso�BGMLBXML���GlossSeeEmarkup�����

testdata/json-org-sample2.smile

@@ -0,0 +1,2 @@
+:)
+��menu��idCfile�valueCFile�popup��menuitem��BBNew�onclickMCreateNewDoc()��BCOpenEHOpenDoc()��BDCloseEICloseDoc()�����

testdata/json-org-sample3.smile

@@ -0,0 +1,2 @@
+:)
+��widget��debugAon�window��titleYSample Konfabulator Widget�nameJmain_window�width$��height$���image��srcMImages/Sun.pngDCsun1�hOffset$��vOffset$��alignmentEcenter��text��dataIClick Here�size$
��styleCboldDDtext1I$�J$�K�onMouseUphsun1.opacity = (sun1.opacity / 100) * 90;���

testdata/json-org-sample4.smile

@@ -0,0 +1,2 @@
+:)
+��web-app��servlet���servlet-nameGcofaxCDS�servlet-classWorg.cofax.cds.CDSServlet�init-param��configGlossary:installationAtOPhiladelphia, PA�configGlossary:[email protected]�configGlossary:poweredByDCofax�configGlossary:poweredByIconP/images/cofax.gif�configGlossary:staticPathN/content/static�templateProcessorClassXorg.cofax.WysiwygTemplate�templateLoaderClass\org.cofax.FilesTemplateLoader�templatePathHtemplates�templateOverridePath �defaultListTemplateOlistTemplate.htm�defaultFileTemplateRarticleTemplate.htm�useJSP"�jspListTemplateOlistTemplate.jsp�jspFileTemplateRarticleTemplate.jsp�cachePackageTagsTrack$��cachePackageTagsStore$��cachePackageTagsRefresh$
��cacheTemplatesTrack$��cacheTemplatesStore$
��cacheTemplatesRefreshގcachePagesTrack$��cachePagesStore$��cachePagesRefreshԒcachePagesDirtyReadԗsearchEngineListTemplateWforSearchEnginesList.htm�searchEngineFileTemplateSforSearchEngines.htm�searchEngineRobotsDbPWEB-INF/robots.db�useDataStore#�dataStoreClassUorg.cofax.SqlDataStore�redirectionClassWorg.cofax.SqlRedirection�dataStoreNameDcofax�dataStoreDriverkcom.microsoft.jdbc.sqlserver.SQLServerDriver�dataStoreUrlzjdbc:microsoft:sqlserver://LOCALHOST:1433;DatabaseName=goon�dataStoreUserAsa�dataStorePasswordQdataStoreTestQuery�dataStoreTestQueryaSET NOCOUNT ON;select test='test';�dataStoreLogFilec/usr/local/tomcat/logs/datastore.log�dataStoreInitConnsԐdataStoreMaxConns$��dataStoreConnUsageLimit$��dataStoreLogLevelDdebug�maxUrlLength$����BIcofaxEmailCYorg.cofax.cds.EmailServletD��mailHostDmail1�mailHostOverrideDmail2���BIcofaxAdminCYorg.cofax.cds.AdminServlet��BJfileServletCXorg.cofax.cds.FileServlet��BIcofaxToolsC^org.cofax.cms.CofaxToolsServletD�LNtoolstemplates/�logŠlogLocationd/usr/local/tomcat/logs/CofaxTools.log�logMaxSize �dataLogŽdataLogLocationa/usr/local/tomcat/logs/dataLog.log�dataLogMaxSize �removePageCached/content/admin/remove?cache=pages&id=�removeTemplateCacheh/content/admin/remove?cache=templates&id=�fileTransferFolders/usr/local/tomcat/webapps/content/fileTransferFolder�lookInContext‹adminGroupIDȉbetaServer#����servlet-mapping��cofaxCDS@/�cofaxEmailR/cofaxutil/aemail/*�cofaxAdminG/admin/*�fileServletH/static/*�cofaxToolsG/tools/*��taglib��taglib-uriHcofax.tld�taglib-locationV/WEB-INF/tlds/cofax.tld���

testdata/json-org-sample5.smile

@@ -0,0 +1,2 @@
+:)
+��menu��headerISVG Viewer�items���idCOpen��CFOpenNew�labelGOpen New�!�CEZoomInDFZoom In��CFZoomOutDGZoom Out��CKOriginalViewDLOriginal View�!�CFQuality��CDPause��CCMute�!�CCFindDFFind...��CHFindAgainDIFind Again��CCCopy��CHCopyAgainDICopy Again��CFCopySVGDGCopy SVG��CFViewSVGDGView SVG��CIViewSourceDJView Source��CESaveAsDFSave As�!�CCHelp��CDAboutDXAbout Adobe CVG Viewer...����

testdata/testdata.go

@@ -0,0 +1,40 @@
+package testdata
+
+import (
+	"github.com/stretchr/testify/require"
+	"io/ioutil"
+	"path/filepath"
+	"runtime"
+	"testing"
+)
+
+func LoadJSONOrgSample1(t *testing.T) []byte {
+	return LoadTestData(t, "json-org-sample1.smile")
+}
+
+func LoadJSONOrgSample2(t *testing.T) []byte {
+	return LoadTestData(t, "json-org-sample2.smile")
+}
+
+func LoadJSONOrgSample3(t *testing.T) []byte {
+	return LoadTestData(t, "json-org-sample3.smile")
+}
+
+func LoadJSONOrgSample4(t *testing.T) []byte {
+	return LoadTestData(t, "json-org-sample4.smile")
+}
+
+func LoadUnicodeSample(t *testing.T) []byte {
+	return LoadTestData(t, "unicode.smile")
+}
+
+func LoadTestData(t *testing.T, filename string) []byte {
+	_, testdataFile, _, _ := runtime.Caller(0)
+	testdataDir := filepath.Dir(testdataFile)
+	filename = filepath.Join(testdataDir, filename)
+
+	b, err := ioutil.ReadFile(filename)
+	require.NoError(t, err, "Error reading test file %q", filename)
+
+	return b
+}

testdata/unicode.smile

@@ -0,0 +1,3 @@
+:)
+
��chilllllllllllllllllllllllld�Niñññññññññññññññññññññññño�child-jp�子供�child�Niño�
+