diff options
| 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 /parser | |
| parent | 068ccde4c75d018b977f4169308b3c994c6f3031 (diff) | |
Make HTML behave exactly like other content formats (note)
Fixes #11999
Diffstat (limited to 'parser')
| -rw-r--r-- | parser/pageparser/pagelexer.go | 24 | ||||
| -rw-r--r-- | parser/pageparser/pagelexer_intro.go | 30 | ||||
| -rw-r--r-- | parser/pageparser/pageparser_intro_test.go | 4 |
3 files changed, 0 insertions, 58 deletions
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}, |