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

Use EXACTLY these public packages and versions:
  - pkg:golang/golang.org/x/net@v0.0.0-20191119073136-fc4aabc6c914
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:sha256:9bb31747816e61db9baace8a687a2a8503d4d0aaf2f2b5c7ad0f70876ef650e0","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 unescaped 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@v0.0.0-20191119073136-fc4aabc6c914","kind":"HOW","packages":["pkg:golang/golang.org/x/net@v0.0.0-20191119073136-fc4aabc6c914"],"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@v0.0.0-20191119073136-fc4aabc6c914"],"schemaVersion":1,"subject":"pkg:golang/golang.org/x/net@v0.0.0-20191119073136-fc4aabc6c914","symbols":["golang.org/x/net/html.TextToken"],"verifierAdapter":"golang@1"}

module sample

go 1.26.6

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=

{
  "schemaVersion": 1,
  "goal": "verify golang.org/x/net/html.TextToken in 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"
  ],
  "symbols": [
    "golang.org/x/net/html.TextToken"
  ]
}

package main

import (
	"fmt"
	"os"
	"strings"

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

func main() {
	// 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(html.TextToken) to be true\n")
		os.Exit(1)
	}

	// 2. html.TextToken String method returns 'Text' and is distinct from other TokenType constants
	if tt.String() != "Text" {
		fmt.Fprintf(os.Stderr, "expected html.TextToken.String() to return 'Text', got %q\n", 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, "expected html.TextToken to be distinct from other TokenType constants\n")
		os.Exit(1)
	}

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

	// 4. Token with Type html.TextToken stores unescaped text in Data and returns escaped HTML via String
	raw := "a < b & 'c' \"d\""
	tok := sample.NewTextToken(raw)
	if tok.Type != html.TextToken || tok.Data != raw {
		fmt.Fprintf(os.Stderr, "unexpected token fields: %+v\n", tok)
		os.Exit(1)
	}
	wantEscaped := "a &lt; b &amp; &#39;c&#39; &#34;d&#34;"
	if tok.String() != wantEscaped {
		fmt.Fprintf(os.Stderr, "expected %q, got %q\n", wantEscaped, tok.String())
		os.Exit(1)
	}

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

	joined, err := sample.JoinTextTokens(strings.NewReader(stream))
	if err != nil {
		fmt.Fprintf(os.Stderr, "JoinTextTokens failed: %v\n", err)
		os.Exit(1)
	}
	if joined != "One & TwoThree" {
		fmt.Fprintf(os.Stderr, "expected joined text %q, got %q\n", "One & TwoThree", joined)
		os.Exit(1)
	}
}

package sample

import (
	"io"
	"strings"

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

// IsTextToken reports whether tt is html.TextToken.
func IsTextToken(tt html.TokenType) bool {
	return tt == html.TextToken
}

// NewTextToken constructs an html.Token with Type set to html.TextToken.
func NewTextToken(data string) html.Token {
	return html.Token{
		Type: html.TextToken,
		Data: data,
	}
}

// CollectTextTokens reads HTML from r and returns the unescaped text data of each html.TextToken.
func CollectTextTokens(r io.Reader) ([]string, error) {
	z := html.NewTokenizer(r)
	var out []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()
			out = append(out, tok.Data)
		}
	}
	return out, nil
}

// JoinTextTokens concatenates all html.TextToken values from r into a single string.
func JoinTextTokens(r io.Reader) (string, error) {
	parts, err := CollectTextTokens(r)
	if err != nil {
		return "", err
	}
	return strings.Join(parts, ""), nil
}