golang.org/x/net v0.51.0: html.TextToken

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.TextToken in pkg:golang/golang.org/x/net@v0.51.0
Kind: HOW

Use EXACTLY these public packages and versions:
  - pkg:golang/golang.org/x/net@v0.51.0
Demonstrate these symbols/APIs:
  - golang.org/x/net/html.TextToken

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:d83f3ecd39a99f6b70c45777da5ca470138e16918440e17058a6e4da090160d9","contract":["html.TextToken is a TokenType constant representing text content in HTML tokenization","html.TextToken String method returns 'Text' and is distinct from other TokenType constants","Tokenizer emits html.TextToken when encountering text nodes within HTML markup","Token with Type html.TextToken stores unescaped text in Data and returns escaped HTML via String","CollectTextTokens gathers text from all html.TextToken instances across an HTML stream"],"goal":"verify golang.org/x/net/html.TextToken in pkg:golang/golang.org/x/net@v0.51.0","kind":"HOW","packages":["pkg:golang/golang.org/x/net@v0.51.0"],"schemaVersion":1,"symbols":["golang.org/x/net/html.TextToken"]},"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@v0.51.0"],"schemaVersion":1,"subject":"pkg:golang/golang.org/x/net@v0.51.0","symbols":["golang.org/x/net/html.TextToken"],"verifierAdapter":"golang@1"}

module sample

go 1.26.6

require golang.org/x/net v0.51.0

golang.org/x/net v0.51.0 h1:94R/GTO7mt3/4wIKpcR5gkGmRLOuE/2hNGeWq/GBIFo=
golang.org/x/net v0.51.0/go.mod h1:aamm+2QF5ogm02fjy5Bb7CQ0WMt1/WVM7FtyaTLlA9Y=

{
  "schemaVersion": 1,
  "goal": "verify golang.org/x/net/html.TextToken in pkg:golang/golang.org/x/net@v0.51.0",
  "kind": "HOW",
  "packages": [
    "pkg:golang/golang.org/x/net@v0.51.0"
  ],
  "symbols": [
    "golang.org/x/net/html.TextToken"
  ]
}

package main

import (
	"fmt"
	"os"
	"strings"

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

func main() {
	// Assertion 1: html.TextToken is a TokenType constant representing text content in HTML tokenization
	var tt html.TokenType = html.TextToken
	if !sample.IsTextToken(tt) {
		fmt.Fprintf(os.Stderr, "expected IsTextToken to return true for html.TextToken\n")
		os.Exit(1)
	}

	// Assertion 2: html.TextToken String method returns 'Text' and is distinct from other TokenType constants
	if tt.String() != "Text" {
		fmt.Fprintf(os.Stderr, "expected tt.String() to be %q, got %q\n", "Text", tt.String())
		os.Exit(1)
	}
	if html.TextToken == html.ErrorToken ||
		html.TextToken == html.StartTagToken ||
		html.TextToken == html.EndTagToken ||
		html.TextToken == html.SelfClosingTagToken ||
		html.TextToken == html.CommentToken ||
		html.TextToken == html.DoctypeToken {
		fmt.Fprintf(os.Stderr, "html.TextToken must be distinct from other TokenType constants\n")
		os.Exit(1)
	}

	// Assertion 3: Tokenizer emits html.TextToken when encountering text nodes within HTML markup
	inputHTML := "<div>Hello <span>World</span>!</div>"
	z := html.NewTokenizer(strings.NewReader(inputHTML))
	var textTokens []string
	for {
		tokenType := z.Next()
		if tokenType == html.ErrorToken {
			break
		}
		if tokenType == html.TextToken {
			tok := z.Token()
			if tok.Type != html.TextToken {
				fmt.Fprintf(os.Stderr, "token Type mismatch: expected html.TextToken, got %v\n", tok.Type)
				os.Exit(1)
			}
			textTokens = append(textTokens, tok.Data)
		}
	}
	if len(textTokens) != 3 || textTokens[0] != "Hello " || textTokens[1] != "World" || textTokens[2] != "!" {
		fmt.Fprintf(os.Stderr, "unexpected text tokens: %v\n", textTokens)
		os.Exit(1)
	}

	// Assertion 4: Token with Type html.TextToken stores unescaped text in Data and returns escaped HTML via String
	rawContent := "1 < 2 & 'quotes' \"double\""
	createdToken := sample.NewTextToken(rawContent)
	if createdToken.Type != html.TextToken {
		fmt.Fprintf(os.Stderr, "expected createdToken.Type to be html.TextToken, got %v\n", createdToken.Type)
		os.Exit(1)
	}
	if createdToken.Data != rawContent {
		fmt.Fprintf(os.Stderr, "expected createdToken.Data to be %q, got %q\n", rawContent, createdToken.Data)
		os.Exit(1)
	}
	rendered := createdToken.String()
	expectedEscaped := "1 &lt; 2 &amp; &#39;quotes&#39; &#34;double&#34;"
	if rendered != expectedEscaped {
		fmt.Fprintf(os.Stderr, "expected rendered string %q, got %q\n", expectedEscaped, rendered)
		os.Exit(1)
	}

	// Assertion 5: CollectTextTokens gathers text from all html.TextToken instances across an HTML stream
	fragment := "<p>Alpha &amp; Beta</p> <!-- comment --> <span>Gamma</span>"
	collected, err := sample.CollectTextTokens(strings.NewReader(fragment))
	if err != nil {
		fmt.Fprintf(os.Stderr, "CollectTextTokens failed: %v\n", err)
		os.Exit(1)
	}
	if len(collected) != 4 || collected[0] != "Alpha & Beta" || collected[1] != " " || collected[2] != " " || collected[3] != "Gamma" {
		fmt.Fprintf(os.Stderr, "unexpected collected tokens: %q\n", collected)
		os.Exit(1)
	}

	fullText, err := sample.ExtractText(strings.NewReader(fragment))
	if err != nil {
		fmt.Fprintf(os.Stderr, "ExtractText failed: %v\n", err)
		os.Exit(1)
	}
	if fullText != "Alpha & Beta  Gamma" {
		fmt.Fprintf(os.Stderr, "expected fullText %q, got %q\n", "Alpha & Beta  Gamma", fullText)
		os.Exit(1)
	}

	fmt.Println("All html.TextToken contract assertions passed.")
}

package sample

import (
	"io"
	"strings"

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

// IsTextToken returns true if the given TokenType is html.TextToken.
func IsTextToken(tt html.TokenType) bool {
	return tt == html.TextToken
}

// NewTextToken creates an html.Token of type html.TextToken with the specified text.
func NewTextToken(text string) html.Token {
	return html.Token{
		Type: html.TextToken,
		Data: text,
	}
}

// CollectTextTokens tokenizes the HTML input from r and returns all text strings
// extracted from html.TextToken occurrences.
func CollectTextTokens(r io.Reader) ([]string, error) {
	z := html.NewTokenizer(r)
	var texts []string
	for {
		tt := z.Next()
		if tt == html.ErrorToken {
			err := z.Err()
			if err == io.EOF {
				break
			}
			return nil, err
		}
		if tt == html.TextToken {
			tok := z.Token()
			texts = append(texts, tok.Data)
		}
	}
	return texts, nil
}

// ExtractText joins all html.TextToken data from the HTML stream into a single string.
func ExtractText(r io.Reader) (string, error) {
	texts, err := CollectTextTokens(r)
	if err != nil {
		return "", err
	}
	return strings.Join(texts, ""), nil
}