added named struct extraction flag

.github/workflows/code_quality.yml

@@ -0,0 +1,22 @@
+name: Code quality
+
+on:
+  push:
+    branches:
+      - master
+
+jobs:
+  code-quality:
+    name: Code quality
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@master
+
+      - name: Set up Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: '1.17'
+
+      - name: Unit tests
+        run: go test -v ./...

Makefile

@@ -3,7 +3,7 @@ SHELL = /bin/bash
 TARGETS = zek
 PKGNAME = zek
 ARCH = amd64
-VERSION = 0.1.16
+VERSION = 0.1.21
 
 .PHONY: all
 all: $(TARGETS)
@@ -52,7 +52,7 @@ rpm: $(TARGETS) docs/$(PKGNAME).1
 
 .PHONY: release
 release:
-	@export GITHUB_TOKEN="..."
+	@echo export GITHUB_TOKEN="..."
 	@echo go tag $(VERSION)
 	@echo goreleaser release --rm-dist
 

README.md

@@ -78,7 +78,8 @@ type Rss struct {
 
 ## Online
 
-Try it online at [https://www.onlinetool.io/xmltogo/](https://www.onlinetool.io/xmltogo/) -- thanks, [kjk](https://github.com/kjk)!
+* try online via WASM: [https://xml-to-go.github.io/](https://xml-to-go.github.io/), thanks [YaroslavPodorvanov](https://github.com/YaroslavPodorvanov)!
+* try it online at [https://blog.kowalczyk.info/tools/xmltogo/](https://blog.kowalczyk.info/tools/xmltogo/) -- thanks, [kjk](https://github.com/kjk)!
 
 ## About
 
@@ -98,7 +99,7 @@ Downsides:
 
 * experimental, early, buggy, unstable prototype,
 * no support for recursive types (similar to *Russian Doll* strategy, [[1](https://medbiq.org/std_specs/techguidelines/xmldesignguidelines.pdf#page=7)])
-* no type inference, everything is accessible as string.
+* no type inference, everything is accessible as string (without a schema, type inference may fail if the type *guess* is wrong)
 
 Bugs:
 
@@ -113,6 +114,7 @@ Related projects:
 * https://github.com/bemasher/JSONGen
 * https://github.com/dutchcoders/XMLGen
 * https://github.com/gnewton/chidley
+* https://github.com/twpayne/go-xmlstruct
 
 And other [awesome XML utilities](https://github.com/avelino/awesome-go#xml).
 
@@ -144,6 +146,8 @@ Usage of zek:
   -F    skip formatting
   -P string
         if set, write out struct within a package with the given name
+  -S int
+        read at most this many tags, approximately (0=unlimited)
   -c    emit more compact struct (noop, as this is the default since 0.1.7)
   -d    debug output
   -e    add comments with example

cmd/zek/main.go

@@ -23,6 +23,7 @@ var (
 	debug                = flag.Bool("d", false, "debug output")
 	createExampleProgram = flag.Bool("p", false, "write out an example program")
 	tagName              = flag.String("t", "", "emit struct for tag matching this name")
+	notInlineStructs     = flag.Bool("I", false, "do not inline children tags as anonymous structs")
 	skipFormatting       = flag.Bool("F", false, "skip formatting")
 	strict               = flag.Bool("s", false, "strict parsing and writing")
 	exampleMaxChars      = flag.Int("x", 25, "max chars for example")
@@ -35,6 +36,7 @@ var (
 	outputFile           = flag.String("o", "", "if set, write to output file, not stdout")
 	packageName          = flag.String("P", "", "if set, write out struct within a package with the given name")
 	fixedBanner          = flag.Bool("B", false, "use a fixed banner string (e.g. for CI)")
+	readAtMost           = flag.Int64("S", 0, "read at most this many tags, approximately (0=unlimited)")
 )
 
 func main() {
@@ -73,7 +75,11 @@ func main() {
 		}
 		reader = io.MultiReader(rs...)
 	}
-	if _, err := root.ReadFrom(reader); err != nil {
+	opts := zek.ReadOpts{
+		MaxExamples: *maxExamples,
+		MaxTokens:   *readAtMost,
+	}
+	if _, err := root.ReadFrom(reader, &opts); err != nil {
 		log.Fatal(err)
 	}
 	// Move root, if we have a tagName. Ignore unknown names.
@@ -99,6 +105,7 @@ func main() {
 	sw.Strict = *strict
 	sw.ExampleMaxChars = *exampleMaxChars
 	sw.Compact = !*nonCompact
+	sw.InlineStructs = !*notInlineStructs
 	sw.UniqueExamples = *uniqueExamples
 	sw.OmitEmptyText = *omitEmptyText
 	if *fixedBanner {

docs/zek.md

@@ -75,6 +75,9 @@ at https://www.onlinetool.io/xmltogo/.
 -s
 :  Strict parsing.
 
+-S
+: raed at most this many tokens, approximately (0=unlimited)
+
 -t
 :  Emit struct for tag matching this name.
 

go.mod

@@ -1,10 +1,10 @@
 module github.com/miku/zek
 
-go 1.12
+go 1.17
 
 require (
-	github.com/sethgrid/pester v0.0.0-20190127155807-68a33a018ad0
-	golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2 // indirect
-	golang.org/x/net v0.0.0-20210917221730-978cfadd31cf
-	golang.org/x/text v0.3.7 // indirect
+	github.com/sethgrid/pester v1.2.0
+	golang.org/x/net v0.19.0
 )
+
+require golang.org/x/text v0.14.0 // indirect

go.sum

@@ -1,18 +1,43 @@
-github.com/sethgrid/pester v0.0.0-20190127155807-68a33a018ad0 h1:X9XMOYjxEfAYSy3xK1DzO5dMkkWhs9E9UCcS1IERx2k=
-github.com/sethgrid/pester v0.0.0-20190127155807-68a33a018ad0/go.mod h1:Ad7IjTpvzZO8Fl0vh9AzQ+j/jYZfyp2diGwI8m5q+ns=
+github.com/sethgrid/pester v1.2.0 h1:adC9RS29rRUef3rIKWPOuP1Jm3/MmB6ke+OhE5giENI=
+github.com/sethgrid/pester v1.2.0/go.mod h1:hEUINb4RqvDxtoCaU0BNT/HV4ig5kfgOasrf1xcvr0A=
+github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
-golang.org/x/net v0.0.0-20200301022130-244492dfa37a h1:GuSPYbZzB5/dcLNCwLQLsg3obCJtX9IJhpXkvY7kzk0=
-golang.org/x/net v0.0.0-20200301022130-244492dfa37a/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
-golang.org/x/net v0.0.0-20210917221730-978cfadd31cf h1:R150MpwJIv1MpS0N/pc+NhTM8ajzvlmxlY5OYsrevXQ=
-golang.org/x/net v0.0.0-20210917221730-978cfadd31cf/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
+golang.org/x/crypto v0.16.0/go.mod h1:gCAAfMLgwOJRpTjQ2zCCt2OcSfYMTeZVSRtQlPC7Nq4=
+golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
+golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
+golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
+golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
+golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
+golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
+golang.org/x/net v0.19.0 h1:zTwKpTd2XuCqf8huc7Fo2iSy+4RHPd10s4KzeTnVr1c=
+golang.org/x/net v0.19.0/go.mod h1:CfAk/cbD4CthTvqiEl8NpboMuiuOYsAr/7NOjZJtv1U=
+golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.15.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
+golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
+golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
+golang.org/x/term v0.15.0/go.mod h1:BDl952bC7+uMoWR75FIrCDx79TPU9oHkTZ9yRbYOrX0=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
-golang.org/x/text v0.3.2 h1:tW2bmiBqwgJj/UpqtC8EpXEZVYOwU0yG4iWbprSVAcs=
-golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
-golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.3.7 h1:olpwvP2KacW1ZWvsR7uQhoyTYvKAupfQrRGBFM352Gk=
+golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
+golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
+golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
+golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
+golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
+golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
+golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

node.go

@@ -45,10 +45,16 @@ type Node struct {
 	childFreqs  map[xml.Name]int // Count child tag occurrences, used temporarily.
 }
 
+// ReadOpts groups options for parsing.
+type ReadOpts struct {
+	MaxExamples int
+	MaxTokens   int64
+}
+
 // readNode reads XML from a reader and returns a parsed node. If node is
 // given, it is reused, allowing for multiple passes (e.g. from multiple
 // files). XXX: maxExamples should be factored out into options.
-func readNode(r io.Reader, root *Node, maxExamples int) (node *Node, n int64, err error) {
+func readNode(r io.Reader, root *Node, opts *ReadOpts) (node *Node, n int64, err error) {
 	var (
 		cw  = countwriter{}
 		dec = xml.NewDecoder(io.TeeReader(r, &cw))
@@ -60,6 +66,8 @@ func readNode(r io.Reader, root *Node, maxExamples int) (node *Node, n int64, er
 	}
 	stack := Stack{}
 	stack.Put(root)
+	var i int64
+OUTER:
 	for {
 		token, err := dec.Token()
 		if err == io.EOF {
@@ -68,6 +76,7 @@ func readNode(r io.Reader, root *Node, maxExamples int) (node *Node, n int64, er
 		if err != nil {
 			return root, cw.n, err
 		}
+		i++
 		switch t := token.(type) {
 		case xml.StartElement:
 			parent := stack.Peek().(*Node)
@@ -76,13 +85,16 @@ func readNode(r io.Reader, root *Node, maxExamples int) (node *Node, n int64, er
 		case xml.EndElement:
 			n := stack.Pop().(*Node)
 			n.End()
+			if opts.MaxTokens > 0 && i > opts.MaxTokens {
+				break OUTER
+			}
 		case xml.CharData:
 			v := strings.TrimSpace(string(t))
 			if v == "" {
 				break
 			}
 			n := stack.Peek().(*Node)
-			if len(n.Examples) < maxExamples {
+			if len(n.Examples) < opts.MaxExamples {
 				// XXX: sample better, e.g. reservoir dictionary.
 				n.Examples = append(n.Examples, v)
 			}
@@ -92,9 +104,9 @@ func readNode(r io.Reader, root *Node, maxExamples int) (node *Node, n int64, er
 	return root, cw.n, nil
 }
 
-// ReadFrom reads XML from a reader.
-func (node *Node) ReadFrom(r io.Reader) (int64, error) {
-	nn, n, err := readNode(r, nil, node.MaxExamples)
+// ReadFrom reads XML from a reader. TODO: pass read options.
+func (node *Node) ReadFrom(r io.Reader, opts *ReadOpts) (int64, error) {
+	nn, n, err := readNode(r, nil, opts)
 	if err != nil {
 		return n, err
 	}

node_test.go

@@ -419,7 +419,7 @@ func TestNodeReadFrom(t *testing.T) {
 	for _, c := range cases {
 		r := strings.NewReader(c.input)
 		node := new(Node)
-		_, err := node.ReadFrom(r)
+		_, err := node.ReadFrom(r, &ReadOpts{MaxExamples: 10})
 		if err != c.err {
 			t.Errorf("got %v, want %v", err, c.err)
 		}
@@ -462,7 +462,7 @@ func TestHeight(t *testing.T) {
 	for _, c := range cases {
 		r := strings.NewReader(c.input)
 		node := new(Node)
-		_, err := node.ReadFrom(r)
+		_, err := node.ReadFrom(r, &ReadOpts{MaxExamples: 10})
 		if err != nil {
 			t.Errorf("failed to parse tree: %s", err)
 		}
@@ -475,7 +475,7 @@ func TestHeight(t *testing.T) {
 func TestByName(t *testing.T) {
 	r := strings.NewReader(`<a><b><c></c></b></a>`)
 	root := new(Node)
-	if _, err := root.ReadFrom(r); err != nil {
+	if _, err := root.ReadFrom(r, &ReadOpts{MaxExamples: 10}); err != nil {
 		t.Errorf("got %v, want nil", err)
 	}
 
@@ -892,7 +892,7 @@ func TestNodeReadFromAll(t *testing.T) {
 		}
 
 		node := new(Node)
-		_, err := node.ReadFrom(io.MultiReader(readers...))
+		_, err := node.ReadFrom(io.MultiReader(readers...), &ReadOpts{MaxExamples: 10})
 		if err != c.err {
 			t.Errorf("got %v, want %v", err, c.err)
 		}

packaging/deb/control.amd64

@@ -1,5 +1,5 @@
 Package: zek
-Version: 0.1.16
+Version: 0.1.21
 Section: utils
 Priority: optional
 Architecture: amd64

packaging/deb/control.any

@@ -1,5 +1,5 @@
 Package: zek
-Version: 0.1.16
+Version: 0.1.21
 Section: utils
 Priority: optional
 Architecture: any

packaging/deb/zek/DEBIAN/control

@@ -1,5 +1,5 @@
 Package: zek
-Version: 0.1.16
+Version: 0.1.21
 Section: utils
 Priority: optional
 Architecture: amd64

packaging/rpm/zek.spec

@@ -1,6 +1,6 @@
 Summary:    Generate a Go struct from an XML document.
 Name:       zek
-Version: 0.1.16
+Version: 0.1.21
 Release:    0
 License:    GPL
 BuildArch:  x86_64