golang.org/x/net v0.0.0-20210525063256-abc453219eb5: html.NewTokenizer

Clean-room public code sample — generation instructions

Write a brand-new, minimal, self-contained code sample in this clean-room directory.
Do not copy, paraphrase, or reference any existing project source. Work only from this spec.

A csx.json manifest scaffold already exists. Do not recreate it from memory. Preserve its case.goal, packages and symbols; fill its empty case.contract with exact assertions and correct its environment, commands and verifierAdapter for the files you generate.

Goal: verify golang.org/x/net/html.NewTokenizer in pkg:golang/golang.org/x/net@v0.0.0-20210525063256-abc453219eb5
Kind: HOW

Use EXACTLY these public packages and versions:
  - pkg:golang/golang.org/x/net@v0.0.0-20210525063256-abc453219eb5
Demonstrate these symbols/APIs:
  - golang.org/x/net/html.NewTokenizer

Rules:
  - One focused purpose; the smallest project that proves the goal.
  - Include a contract test (test/contract.*) that runs OFFLINE and exits 0 exactly when the goal behavior works.
  - Pin every dependency with a lockfile so resolution is reproducible.
  - No secrets, credentials, or tokens. No real URLs (only example.com or localhost). No absolute paths.
  - No personal names, emails, company names, or project identifiers of any kind.
  - No binaries and no generated output (node_modules, dist, target, venv, .git, .env).
  - Keep it under 200 files and 256KB packed.

{"case":{"caseId":"case:sha256:e9aae093d0fe988a9e2c8020c0f0c2f4c9f9eda5a66b5a03f79bb8772cab212d","contract":["html.NewTokenizer creates a streaming HTML tokenizer over an io.Reader and sequentially yields StartTagToken, TextToken, EndTagToken, SelfClosingTagToken, CommentToken, and ErrorToken (io.EOF) via Next()","Tokenizer.Token(), TagName(), TagAttr(), and Text() extract element tag names, attributes, and text content from tokenized HTML nodes"],"goal":"verify golang.org/x/net/html.NewTokenizer in pkg:golang/golang.org/x/net@v0.0.0-20210525063256-abc453219eb5","kind":"HOW","packages":["pkg:golang/golang.org/x/net@v0.0.0-20210525063256-abc453219eb5"],"schemaVersion":1,"symbols":["golang.org/x/net/html.NewTokenizer"]},"contractCommand":["go","run","./test"],"environment":{"arch":"x64","distro":"ubuntu","ecosystem":"golang","libc":"glibc","libcVersion":"2.39","os":"linux","osVersionBucket":"24","packageManager":"go","schemaVersion":1},"license":"MIT-0","packages":["pkg:golang/golang.org/x/net@v0.0.0-20210525063256-abc453219eb5"],"schemaVersion":1,"subject":"pkg:golang/golang.org/x/net@v0.0.0-20210525063256-abc453219eb5","symbols":["golang.org/x/net/html.NewTokenizer"],"verifierAdapter":"golang@1"}

module example.com/sample

go 1.21

require golang.org/x/net v0.0.0-20210525063256-abc453219eb5

golang.org/x/net v0.0.0-20210525063256-abc453219eb5 h1:wjuX4b5yYQnEQHzd+CBcrcC6OVR2J1CN6mUy0oSxIPo=
golang.org/x/net v0.0.0-20210525063256-abc453219eb5/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=

package main

import (
	"fmt"
	"io"
	"strings"

	"golang.org/x/net/html"
)

func main() {
	markup := `<section id="main"><h1>Title</h1><br class="spacer"/><!--note--></section>`
	tz := html.NewTokenizer(strings.NewReader(markup))

	for {
		tt := tz.Next()
		if tt == html.ErrorToken {
			if tz.Err() == io.EOF {
				break
			}
			panic(tz.Err())
		}
		tok := tz.Token()
		fmt.Printf("%v: %s (attrs=%d)\n", tt, tok.Data, len(tok.Attr))
	}
}

{
  "schemaVersion": 1,
  "goal": "verify golang.org/x/net/html.NewTokenizer in pkg:golang/golang.org/x/net@v0.0.0-20210525063256-abc453219eb5",
  "kind": "HOW",
  "packages": [
    "pkg:golang/golang.org/x/net@v0.0.0-20210525063256-abc453219eb5"
  ],
  "symbols": [
    "golang.org/x/net/html.NewTokenizer"
  ]
}

package main

import (
	"fmt"
	"io"
	"os"
	"strings"

	"golang.org/x/net/html"
)

func fail(msg string, args ...any) {
	fmt.Fprintf(os.Stderr, "FAIL: "+msg+"\n", args...)
	os.Exit(1)
}

func main() {
	input := `<article data-kind="post"><h2>Heading</h2><hr class="rule"/><!--comment--></article>`
	tz := html.NewTokenizer(strings.NewReader(input))
	if tz == nil {
		fail("expected non-nil Tokenizer from html.NewTokenizer")
	}

	// 1. StartTagToken: <article data-kind="post">
	if tt := tz.Next(); tt != html.StartTagToken {
		fail("expected StartTagToken for <article>, got %v", tt)
	}
	tok := tz.Token()
	if tok.Data != "article" || len(tok.Attr) != 1 || tok.Attr[0].Key != "data-kind" || tok.Attr[0].Val != "post" {
		fail("unexpected start tag token: %+v", tok)
	}

	// 2. StartTagToken: <h2>
	if tt := tz.Next(); tt != html.StartTagToken {
		fail("expected StartTagToken for <h2>, got %v", tt)
	}
	if name, hasAttr := tz.TagName(); string(name) != "h2" || hasAttr {
		fail("unexpected TagName for <h2>: %q, hasAttr=%v", string(name), hasAttr)
	}

	// 3. TextToken: Heading
	if tt := tz.Next(); tt != html.TextToken {
		fail("expected TextToken, got %v", tt)
	}
	if text := string(tz.Text()); text != "Heading" {
		fail("expected text 'Heading', got %q", text)
	}

	// 4. EndTagToken: </h2>
	if tt := tz.Next(); tt != html.EndTagToken {
		fail("expected EndTagToken for </h2>, got %v", tt)
	}
	if tok := tz.Token(); tok.Data != "h2" {
		fail("expected end tag 'h2', got %q", tok.Data)
	}

	// 5. SelfClosingTagToken: <hr class="rule"/>
	if tt := tz.Next(); tt != html.SelfClosingTagToken {
		fail("expected SelfClosingTagToken for <hr/>, got %v", tt)
	}
	if k, v, more := tz.TagAttr(); string(k) != "class" || string(v) != "rule" || more {
		fail("unexpected TagAttr on <hr/>: %q=%q (more=%v)", string(k), string(v), more)
	}

	// 6. CommentToken: <!--comment-->
	if tt := tz.Next(); tt != html.CommentToken {
		fail("expected CommentToken, got %v", tt)
	}
	if tok := tz.Token(); tok.Data != "comment" {
		fail("expected comment data 'comment', got %q", tok.Data)
	}

	// 7. EndTagToken: </article>
	if tt := tz.Next(); tt != html.EndTagToken {
		fail("expected EndTagToken for </article>, got %v", tt)
	}
	if tok := tz.Token(); tok.Data != "article" {
		fail("expected end tag 'article', got %q", tok.Data)
	}

	// 8. ErrorToken with io.EOF at end of stream
	if tt := tz.Next(); tt != html.ErrorToken {
		fail("expected ErrorToken at EOF, got %v", tt)
	}
	if err := tz.Err(); err != io.EOF {
		fail("expected io.EOF from Err(), got %v", err)
	}
}