Make HTML behave exactly like other content formats (note)

Fixes #11999
author: Bjørn Erik Pedersen <bjorn.erik.pedersen@gmail.com> 2024-02-07 10:30:32 +0100
committer: Bjørn Erik Pedersen <bjorn.erik.pedersen@gmail.com> 2024-02-07 21:37:04 +0100
commit: 676e6875dac391f1ec1f7369ed2d59439f434806 (patch)
tree: af689eec1f48d511169f8b07f4c65420c7479413
parent: 068ccde4c75d018b977f4169308b3c994c6f3031 (diff)
9 files changed, 107 insertions, 175 deletions
diff --git a/helpers/general.go b/helpers/general.go
index 35e35a7e0..859d1ead7 100644
--- a/helpers/general.go
+++ b/helpers/general.go
@@ -328,7 +328,7 @@ func PrintFs(fs afero.Fs, path string, w io.Writer) {
 	}
 
 	afero.Walk(fs, path, func(path string, info os.FileInfo, err error) error {
-		fmt.Println(path)
+		fmt.Fprintln(w, filepath.ToSlash(path))
 		return nil
 	})
 }
diff --git a/hugolib/integrationtest_builder.go b/hugolib/integrationtest_builder.go
index 222c8ec2d..194b79c68 100644
--- a/hugolib/integrationtest_builder.go
+++ b/hugolib/integrationtest_builder.go
@@ -10,6 +10,7 @@ import (
 	"os"
 	"path/filepath"
 	"regexp"
+	"sort"
 	"strings"
 	"sync"
 	"testing"
@@ -273,6 +274,32 @@ func (s *IntegrationTestBuilder) AssertFileContentExact(filename string, matches
 	}
 }
 
+func (s *IntegrationTestBuilder) AssertPublishDir(matches ...string) {
+	s.Helper()
+	var buff bytes.Buffer
+	helpers.PrintFs(s.H.Fs.PublishDir, "", &buff)
+	printFsLines := strings.Split(buff.String(), "\n")
+	sort.Strings(printFsLines)
+	content := strings.TrimSpace((strings.Join(printFsLines, "\n")))
+	for _, m := range matches {
+		cm := qt.Commentf("Match: %q\nIn:\n%s", m, content)
+		lines := strings.Split(m, "\n")
+		for _, match := range lines {
+			match = strings.TrimSpace(match)
+			var negate bool
+			if strings.HasPrefix(match, "! ") {
+				negate = true
+				match = strings.TrimPrefix(match, "! ")
+			}
+			if negate {
+				s.Assert(content, qt.Not(qt.Contains), match, cm)
+				continue
+			}
+			s.Assert(content, qt.Contains, match, cm)
+		}
+	}
+}
+
 func (s *IntegrationTestBuilder) AssertFileExists(filename string, b bool) {
 	checker := qt.IsNil
 	if !b {
diff --git a/hugolib/page_test.go b/hugolib/page_test.go
index d17f3fbce..9a904ee46 100644
--- a/hugolib/page_test.go
+++ b/hugolib/page_test.go
@@ -1540,32 +1540,6 @@ CONTENT:{{ .Content }}
 	)
 }
 
-// https://github.com/gohugoio/hugo/issues/5478
-func TestPageWithCommentedOutFrontMatter(t *testing.T) {
-	b := newTestSitesBuilder(t)
-	b.WithSimpleConfigFile()
-
-	b.WithContent("page.md", `<!--
-+++
-title = "hello"
-+++
--->
-This is the content.
-`)
-
-	b.WithTemplatesAdded("layouts/_default/single.html", `
-Title: {{ .Title }}
-Content:{{ .Content }}
-`)
-
-	b.CreateSites().Build(BuildCfg{})
-
-	b.AssertFileContent("public/page/index.html",
-		"Title: hello",
-		"Content:<p>This is the content.</p>",
-	)
-}
-
 func TestHomePageWithNoTitle(t *testing.T) {
 	b := newTestSitesBuilder(t).WithConfigFile("toml", `
 title = "Site Title"
diff --git a/hugolib/pagebundler_test.go b/hugolib/pagebundler_test.go
index c6f9155ea..35778a9b6 100644
--- a/hugolib/pagebundler_test.go
+++ b/hugolib/pagebundler_test.go
@@ -757,3 +757,81 @@ func TestPageBundlerHome(t *testing.T) {
 Title: Home|First Resource: data.json|Content: <p>Hook Len Page Resources 1</p>
 `)
 }
+
+func TestHTMLFilesIsue11999(t *testing.T) {
+	t.Parallel()
+
+	files := `
+-- hugo.toml --
+disableKinds = ["taxonomy", "term", "rss", "sitemap", "robotsTXT", "404"]
+[permalinks]
+posts = "/myposts/:slugorfilename"
+-- content/posts/markdown-without-frontmatter.md --
+-- content/posts/html-without-frontmatter.html --
+<html>hello</html>
+-- content/posts/html-with-frontmatter.html --
+---
+title: "HTML with frontmatter"
+---
+<html>hello</html>
+-- content/posts/html-with-commented-out-frontmatter.html --
+<!--
+---
+title: "HTML with commented out frontmatter"
+---
+-->
+<html>hello</html>
+-- content/posts/markdown-with-frontmatter.md --
+---
+title: "Markdown"
+---
+-- content/posts/mybundle/index.md --
+---
+title: My Bundle
+---
+-- content/posts/mybundle/data.txt --
+Data.txt
+-- content/posts/mybundle/html-in-bundle-without-frontmatter.html --
+<html>hell</html>
+-- content/posts/mybundle/html-in-bundle-with-frontmatter.html --
+---
+title: Hello
+---
+<html>hello</html>
+-- content/posts/mybundle/html-in-bundle-with-commented-out-frontmatter.html --
+<!--
+---
+title: "HTML with commented out frontmatter"
+---
+-->
+<html>hello</html>
+-- layouts/index.html --
+{{ range site.RegularPages }}{{ .RelPermalink }}|{{ end }}$
+-- layouts/_default/single.html --
+{{ .Title }}|{{ .RelPermalink }}Resources: {{ range .Resources }}{{ .Name }}|{{ end }}$
+
+`
+	b := Test(t, files)
+
+	b.AssertFileContent("public/index.html", "/myposts/html-with-commented-out-frontmatter/|/myposts/html-without-frontmatter/|/myposts/markdown-without-frontmatter/|/myposts/html-with-frontmatter/|/myposts/markdown-with-frontmatter/|/myposts/mybundle/|$")
+
+	b.AssertFileContent("public/myposts/mybundle/index.html",
+		"My Bundle|/myposts/mybundle/Resources: html-in-bundle-with-commented-out-frontmatter.html|html-in-bundle-without-frontmatter.html|html-in-bundle-with-frontmatter.html|data.txt|$")
+
+	b.AssertPublishDir(`
+index.html
+myposts/html-with-commented-out-frontmatter
+myposts/html-with-commented-out-frontmatter/index.html
+myposts/html-with-frontmatter
+myposts/html-with-frontmatter/index.html
+myposts/html-without-frontmatter
+myposts/html-without-frontmatter/index.html
+myposts/markdown-with-frontmatter
+myposts/markdown-with-frontmatter/index.html
+myposts/markdown-without-frontmatter
+myposts/markdown-without-frontmatter/index.html
+myposts/mybundle/data.txt
+myposts/mybundle/index.html
+! myposts/mybundle/html-in-bundle-with-frontmatter.html
+`)
+}
diff --git a/hugolib/pages_capture.go b/hugolib/pages_capture.go
index a7f8faaf0..9bf88c240 100644
--- a/hugolib/pages_capture.go
+++ b/hugolib/pages_capture.go
@@ -15,7 +15,6 @@ package hugolib
 
 import (
 	"context"
-	"errors"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -27,8 +26,6 @@ import (
 	"github.com/bep/logg"
 	"github.com/gohugoio/hugo/common/paths"
 	"github.com/gohugoio/hugo/common/rungroup"
-	"github.com/gohugoio/hugo/helpers"
-	"github.com/gohugoio/hugo/parser/pageparser"
 	"github.com/spf13/afero"
 
 	"github.com/gohugoio/hugo/source"
@@ -77,26 +74,6 @@ type pagesCollector struct {
 	g rungroup.Group[hugofs.FileMetaInfo]
 }
 
-func (c *pagesCollector) copyFile(fim hugofs.FileMetaInfo) error {
-	meta := fim.Meta()
-	f, err := meta.Open()
-	if err != nil {
-		return fmt.Errorf("copyFile: failed to open: %w", err)
-	}
-
-	s := c.m.s
-
-	target := filepath.Join(s.PathSpec.GetTargetLanguageBasePath(), meta.PathInfo.Path())
-
-	defer f.Close()
-
-	fs := s.PublishFsStatic
-
-	s.PathSpec.ProcessingStats.Incr(&s.PathSpec.ProcessingStats.Files)
-
-	return helpers.WriteToDisk(filepath.Clean(target), f, fs)
-}
-
 // Collect collects content by walking the file system and storing
 // it in the content tree.
 // It may be restricted by filenames set on the collector (partial build).
@@ -136,14 +113,7 @@ func (c *pagesCollector) Collect() (collectErr error) {
 		NumWorkers: numWorkers,
 		Handle: func(ctx context.Context, fi hugofs.FileMetaInfo) error {
 			if err := c.m.AddFi(fi); err != nil {
-				if errors.Is(err, pageparser.ErrPlainHTMLDocumentsNotSupported) {
-					// Reclassify this as a static file.
-					if err := c.copyFile(fi); err != nil {
-						return err
-					}
-				} else {
-					return hugofs.AddFileInfoToError(err, fi, c.fs)
-				}
+				return hugofs.AddFileInfoToError(err, fi, c.fs)
 			}
 			numFilesProcessedTotal.Add(1)
 			if numFilesProcessedTotal.Load()%1000 == 0 {
diff --git a/hugolib/site_test.go b/hugolib/site_test.go
index 967fb827d..63088ee88 100644
--- a/hugolib/site_test.go
+++ b/hugolib/site_test.go
@@ -32,11 +32,6 @@ import (
 	"github.com/gohugoio/hugo/resources/page"
 )
 
-const (
-	templateMissingFunc = "{{ .Title | funcdoesnotexists }}"
-	templateWithURLAbs  = "<a href=\"/foobar.jpg\">Going</a>"
-)
-
 func TestDraftAndFutureRender(t *testing.T) {
 	t.Parallel()
 	c := qt.New(t)
@@ -577,60 +572,6 @@ func doTestSectionNaming(t *testing.T, canonify, uglify, pluralize bool) {
 	}
 }
 
-func TestAbsURLify(t *testing.T) {
-	t.Parallel()
-	c := qt.New(t)
-	sources := [][2]string{
-		{filepath.FromSlash("sect/doc1.html"), "<!doctype html><html><head></head><body><a href=\"#frag1\">link</a></body></html>"},
-		{filepath.FromSlash("blue/doc2.html"), "---\nf: t\n---\n<!doctype html><html><body>more content</body></html>"},
-	}
-	for _, baseURL := range []string{"http://auth/bub", "http://base", "//base"} {
-		for _, canonify := range []bool{true, false} {
-
-			cfg, fs := newTestCfg()
-
-			cfg.Set("uglyURLs", true)
-			cfg.Set("canonifyURLs", canonify)
-			cfg.Set("baseURL", baseURL)
-
-			configs, err := loadTestConfigFromProvider(cfg)
-			c.Assert(err, qt.IsNil)
-
-			for _, src := range sources {
-				writeSource(t, fs, filepath.Join("content", src[0]), src[1])
-			}
-
-			writeSource(t, fs, filepath.Join("layouts", "blue/single.html"), templateWithURLAbs)
-
-			s := buildSingleSite(t, deps.DepsCfg{Fs: fs, Configs: configs}, BuildCfg{})
-			th := newTestHelper(s.conf, s.Fs, t)
-
-			tests := []struct {
-				file, expected string
-			}{
-				{"public/blue/doc2.html", "<a href=\"%s/foobar.jpg\">Going</a>"},
-				{"public/sect/doc1.html", "<!doctype html><html><head></head><body><a href=\"#frag1\">link</a></body></html>"},
-			}
-
-			for _, test := range tests {
-
-				expected := test.expected
-
-				if strings.Contains(expected, "%s") {
-					expected = fmt.Sprintf(expected, baseURL)
-				}
-
-				if !canonify {
-					expected = strings.Replace(expected, baseURL, "", -1)
-				}
-
-				th.assertFileContent(test.file, expected)
-
-			}
-		}
-	}
-}
-
 var weightedPage1 = `+++
 weight = "2"
 title = "One"
diff --git a/parser/pageparser/pagelexer.go b/parser/pageparser/pagelexer.go
index bd903b771..5f90e3687 100644
--- a/parser/pageparser/pagelexer.go
+++ b/parser/pageparser/pagelexer.go
@@ -43,8 +43,6 @@ type pageLexer struct {
 	summaryDivider []byte
 	// Set when we have parsed any summary divider
 	summaryDividerChecked bool
-	// Whether we're in a HTML comment.
-	isInHTMLComment bool
 
 	lexerShortcodeState
 
@@ -102,8 +100,6 @@ var (
 	delimTOML         = []byte("+++")
 	delimYAML         = []byte("---")
 	delimOrg          = []byte("#+")
-	htmlCommentStart  = []byte("<!--")
-	htmlCommentEnd    = []byte("-->")
 )
 
 func (l *pageLexer) next() rune {
@@ -232,13 +228,6 @@ func (l *pageLexer) errorf(format string, args ...any) stateFunc {
 	return nil
 }
 
-// documentError can be used to signal a fatal error in the lexing process.
-// nil terminates the parser
-func (l *pageLexer) documentError(err error) stateFunc {
-	l.err = err
-	return nil
-}
-
 func (l *pageLexer) consumeCRLF() bool {
 	var consumed bool
 	for _, r := range crLf {
@@ -251,15 +240,6 @@ func (l *pageLexer) consumeCRLF() bool {
 	return consumed
 }
 
-func (l *pageLexer) consumeToNextLine() {
-	for {
-		r := l.next()
-		if r == eof || isEndOfLine(r) {
-			return
-		}
-	}
-}
-
 func (l *pageLexer) consumeToSpace() {
 	for {
 		r := l.next()
@@ -441,10 +421,6 @@ func lexMainSection(l *pageLexer) stateFunc {
 		return lexDone
 	}
 
-	if l.isInHTMLComment {
-		return lexEndFrontMatterHTMLComment
-	}
-
 	// Fast forward as far as possible.
 	skip := l.sectionHandlers.skip()
 
diff --git a/parser/pageparser/pagelexer_intro.go b/parser/pageparser/pagelexer_intro.go
index 25af4170b..0ff0958fe 100644
--- a/parser/pageparser/pagelexer_intro.go
+++ b/parser/pageparser/pagelexer_intro.go
@@ -13,10 +13,6 @@
 
 package pageparser
 
-import "errors"
-
-var ErrPlainHTMLDocumentsNotSupported = errors.New("plain HTML documents not supported")
-
 func lexIntroSection(l *pageLexer) stateFunc {
 	l.summaryDivider = summaryDivider
 
@@ -39,19 +35,6 @@ LOOP:
 		case r == byteOrderMark:
 			l.emit(TypeIgnore)
 		case !isSpace(r) && !isEndOfLine(r):
-			if r == '<' {
-				l.backup()
-				if l.hasPrefix(htmlCommentStart) {
-					// This may be commented out front matter, which should
-					// still be read.
-					l.consumeToNextLine()
-					l.isInHTMLComment = true
-					l.emit(TypeIgnore)
-					continue LOOP
-				} else {
-					return l.documentError(ErrPlainHTMLDocumentsNotSupported)
-				}
-			}
 			break LOOP
 		}
 	}
@@ -60,19 +43,6 @@ LOOP:
 	return lexMainSection
 }
 
-func lexEndFrontMatterHTMLComment(l *pageLexer) stateFunc {
-	l.isInHTMLComment = false
-	right := l.index(htmlCommentEnd)
-	if right == -1 {
-		return l.errorf("starting HTML comment with no end")
-	}
-	l.pos += right + len(htmlCommentEnd)
-	l.emit(TypeIgnore)
-
-	// Now move on to the shortcodes.
-	return lexMainSection
-}
-
 func lexFrontMatterJSON(l *pageLexer) stateFunc {
 	// Include the left delimiter
 	l.backup()
diff --git a/parser/pageparser/pageparser_intro_test.go b/parser/pageparser/pageparser_intro_test.go
index df2f2579b..12f4fc61c 100644
--- a/parser/pageparser/pageparser_intro_test.go
+++ b/parser/pageparser/pageparser_intro_test.go
@@ -61,13 +61,9 @@ var crLfReplacer = strings.NewReplacer("\r", "#", "\n", "$")
 var frontMatterTests = []lexerTest{
 	{"empty", "", []typeText{tstEOF}, nil},
 	{"Byte order mark", "\ufeff\nSome text.\n", []typeText{nti(TypeIgnore, "\ufeff"), tstSomeText, tstEOF}, nil},
-	{"HTML Document", `  <html>  `, nil, ErrPlainHTMLDocumentsNotSupported},
-	{"HTML Document with shortcode", `<html>{{< sc1 >}}</html>`, nil, ErrPlainHTMLDocumentsNotSupported},
 	{"No front matter", "\nSome text.\n", []typeText{tstSomeText, tstEOF}, nil},
 	{"YAML front matter", "---\nfoo: \"bar\"\n---\n\nSome text.\n", []typeText{tstFrontMatterYAML, tstSomeText, tstEOF}, nil},
 	{"YAML empty front matter", "---\n---\n\nSome text.\n", []typeText{nti(TypeFrontMatterYAML, ""), tstSomeText, tstEOF}, nil},
-	{"YAML commented out front matter", "<!--\n---\nfoo: \"bar\"\n---\n-->\nSome text.\n", []typeText{nti(TypeIgnore, "<!--\n"), tstFrontMatterYAML, nti(TypeIgnore, "-->"), tstSomeText, tstEOF}, nil},
-	{"YAML commented out front matter, no end", "<!--\n---\nfoo: \"bar\"\n---\nSome text.\n", []typeText{nti(TypeIgnore, "<!--\n"), tstFrontMatterYAML, nti(tError, "starting HTML comment with no end")}, nil},
 	// Note that we keep all bytes as they are, but we need to handle CRLF
 	{"YAML front matter CRLF", "---\r\nfoo: \"bar\"\r\n---\n\nSome text.\n", []typeText{tstFrontMatterYAMLCRLF, tstSomeText, tstEOF}, nil},
 	{"TOML front matter", "+++\nfoo = \"bar\"\n+++\n\nSome text.\n", []typeText{tstFrontMatterTOML, tstSomeText, tstEOF}, nil},
author	Bjørn Erik Pedersen <bjorn.erik.pedersen@gmail.com>	2024-02-07 10:30:32 +0100
committer	Bjørn Erik Pedersen <bjorn.erik.pedersen@gmail.com>	2024-02-07 21:37:04 +0100
commit	676e6875dac391f1ec1f7369ed2d59439f434806 (patch)
tree	af689eec1f48d511169f8b07f4c65420c7479413
parent	068ccde4c75d018b977f4169308b3c994c6f3031 (diff)