golang.org/x/net v0.0.0-20191119073136-fc4aabc6c914: html.Parse, html.Render, publicsuffix.PublicSuffix

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 pkg:golang/golang.org/x/net@v0.0.0-20191119073136-fc4aabc6c914
Kind: HOW

Use EXACTLY these public packages and versions:
  - pkg:golang/golang.org/x/net@v0.0.0-20191119073136-fc4aabc6c914

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:sha256:379bb6c4dd76586b4978003dfa1d3bcc4ca80c590f3fd7b98e756adf567f5018","contract":["html.Parse parses an HTML document into a node tree to extract the document title and anchor href attributes","html.Render serializes a parsed html.Node tree back into valid HTML while preserving escaped entities","publicsuffix.PublicSuffix and publicsuffix.EffectiveTLDPlusOne resolve the ICANN public suffix and registrable domain and reject bare suffixes"],"goal":"verify pkg:golang/golang.org/x/net@v0.0.0-20191119073136-fc4aabc6c914","kind":"HOW","packages":["pkg:golang/golang.org/x/net@v0.0.0-20191119073136-fc4aabc6c914"],"schemaVersion":1,"symbols":["html.Parse","html.Render","publicsuffix.PublicSuffix","publicsuffix.EffectiveTLDPlusOne"]},"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@v0.0.0-20191119073136-fc4aabc6c914"],"schemaVersion":1,"subject":"pkg:golang/golang.org/x/net@v0.0.0-20191119073136-fc4aabc6c914","symbols":["html.Parse","html.Render","publicsuffix.PublicSuffix","publicsuffix.EffectiveTLDPlusOne"],"verifierAdapter":"golang@1"}

module sample

go 1.21

require golang.org/x/net v0.0.0-20191119073136-fc4aabc6c914

golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/net v0.0.0-20191119073136-fc4aabc6c914 h1:MlY3mEfbnWGmUi4rtHOtNnnnN4UJRGSyLPx+DXA5Sq4=
golang.org/x/net v0.0.0-20191119073136-fc4aabc6c914/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=

package sample

import (
	"bytes"
	"strings"

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

// ParseTitleAndLinks parses an HTML document and returns the text of the first <title> element
// along with all href attribute values from <a> elements.
func ParseTitleAndLinks(docHTML string) (string, []string, error) {
	root, err := html.Parse(strings.NewReader(docHTML))
	if err != nil {
		return "", nil, err
	}
	var title string
	var links []string
	var visit func(*html.Node)
	visit = func(n *html.Node) {
		if n.Type == html.ElementNode {
			if n.Data == "title" && title == "" && n.FirstChild != nil && n.FirstChild.Type == html.TextNode {
				title = n.FirstChild.Data
			}
			if n.Data == "a" {
				for _, a := range n.Attr {
					if a.Key == "href" {
						links = append(links, a.Val)
					}
				}
			}
		}
		for c := n.FirstChild; c != nil; c = c.NextSibling {
			visit(c)
		}
	}
	visit(root)
	return title, links, nil
}

// RenderFragment parses and re-renders an HTML document string.
func RenderFragment(docHTML string) (string, error) {
	root, err := html.Parse(strings.NewReader(docHTML))
	if err != nil {
		return "", err
	}
	var out bytes.Buffer
	if err := html.Render(&out, root); err != nil {
		return "", err
	}
	return out.String(), nil
}

// DomainInfo returns the public suffix, whether it is ICANN-managed, and the eTLD+1 for a host.
func DomainInfo(host string) (suffix string, icann bool, etldPlusOne string, err error) {
	suffix, icann = publicsuffix.PublicSuffix(host)
	etldPlusOne, err = publicsuffix.EffectiveTLDPlusOne(host)
	return suffix, icann, etldPlusOne, err
}

{
  "schemaVersion": 1,
  "goal": "verify pkg:golang/golang.org/x/net@v0.0.0-20191119073136-fc4aabc6c914",
  "kind": "HOW",
  "packages": [
    "pkg:golang/golang.org/x/net@v0.0.0-20191119073136-fc4aabc6c914"
  ]
}

package main

import (
	"fmt"
	"os"
	"strings"

	"sample"
)

func must(cond bool, msg string) {
	if !cond {
		fmt.Fprintln(os.Stderr, "FAIL:", msg)
		os.Exit(1)
	}
}

func main() {
	rawHTML := `<!DOCTYPE html><html><head><title>Sample Page</title></head><body><a href="https://example.com/a">A</a><span><a href="https://example.com/b">B</a></span></body></html>`
	title, links, err := sample.ParseTitleAndLinks(rawHTML)
	must(err == nil, "ParseTitleAndLinks failed")
	must(title == "Sample Page", "unexpected title: "+title)
	must(len(links) == 2 && links[0] == "https://example.com/a" && links[1] == "https://example.com/b", fmt.Sprintf("unexpected links: %v", links))

	rendered, err := sample.RenderFragment("<p>1 &lt; 2 &amp; 3 &gt; 0</p>")
	must(err == nil, "RenderFragment failed")
	must(strings.Contains(rendered, "<p>1 &lt; 2 &amp; 3 &gt; 0</p>"), "unexpected rendered output: "+rendered)

	suffix, icann, etld1, err := sample.DomainInfo("shop.service.example.co.uk")
	must(err == nil, "DomainInfo failed")
	must(suffix == "co.uk", "unexpected suffix: "+suffix)
	must(icann, "expected co.uk to be ICANN-managed")
	must(etld1 == "example.co.uk", "unexpected etld+1: "+etld1)

	_, _, _, err = sample.DomainInfo("co.uk")
	must(err != nil, "expected error for bare public suffix")
}