diff options
| author | Bjørn Erik Pedersen <bjorn.erik.pedersen@gmail.com> | 2020-03-09 12:04:33 +0100 |
|---|---|---|
| committer | Bjørn Erik Pedersen <bjorn.erik.pedersen@gmail.com> | 2020-03-09 15:01:55 +0100 |
| commit | ffcb4aeb8e392a80da7cad0f1e03a4102efb24ec (patch) | |
| tree | 945afe631ef8451f8a401b0a159a78b64e905713 /parser | |
| parent | 8279d2e2271ee64725133d36a12d1d7e2158bffd (diff) | |
Fix handling of HTML files without front matter
This means that any HTML file inside /content will be treated as a regular file.
If you want it processes with shortcodes and a layout, add front matter.
The defintion of an HTML file here is:
* File with extension .htm or .html
* With first non-whitespace character "<" that isn't a HTML comment.
This is in line with the documentation.
Fixes #7030
Fixes #7028
See #6789
Diffstat (limited to 'parser')
| -rw-r--r-- | parser/pageparser/item.go | 1 | ||||
| -rw-r--r-- | parser/pageparser/pagelexer_intro.go | 11 | ||||
| -rw-r--r-- | parser/pageparser/pageparser_intro_test.go | 5 |
3 files changed, 4 insertions, 13 deletions
diff --git a/parser/pageparser/item.go b/parser/pageparser/item.go index 48003ee86..9224fba94 100644 --- a/parser/pageparser/item.go +++ b/parser/pageparser/item.go @@ -140,7 +140,6 @@ const ( tEOF // page items - TypeHTMLStart // document starting with < as first non-whitespace TypeLeadSummaryDivider // <!--more-->, # more TypeFrontMatterYAML TypeFrontMatterTOML diff --git a/parser/pageparser/pagelexer_intro.go b/parser/pageparser/pagelexer_intro.go index 56dd4224d..539e6cfaa 100644 --- a/parser/pageparser/pagelexer_intro.go +++ b/parser/pageparser/pagelexer_intro.go @@ -42,21 +42,14 @@ LOOP: if r == '<' { l.backup() if l.hasPrefix(htmlCommentStart) { - // This may be commented out front mattter, which should + // This may be commented out front matter, which should // still be read. l.consumeToNextLine() l.isInHTMLComment = true l.emit(TypeIgnore) continue LOOP } else { - if l.pos > l.start { - l.emit(tText) - } - l.next() - // This is the start of a plain HTML document with no - // front matter. I still can contain shortcodes, so we - // have to keep looking. - l.emit(TypeHTMLStart) + return l.errorf("plain HTML documents not supported") } } break LOOP diff --git a/parser/pageparser/pageparser_intro_test.go b/parser/pageparser/pageparser_intro_test.go index 0f20ae5a1..e776cb3ee 100644 --- a/parser/pageparser/pageparser_intro_test.go +++ b/parser/pageparser/pageparser_intro_test.go @@ -38,7 +38,6 @@ var ( tstFrontMatterJSON = nti(TypeFrontMatterJSON, tstJSON+"\r\n") tstSomeText = nti(tText, "\nSome text.\n") tstSummaryDivider = nti(TypeLeadSummaryDivider, "<!--more-->\n") - tstHtmlStart = nti(TypeHTMLStart, "<") tstNewline = nti(tText, "\n") tstORG = ` @@ -55,8 +54,8 @@ var crLfReplacer = strings.NewReplacer("\r", "#", "\n", "$") var frontMatterTests = []lexerTest{ {"empty", "", []Item{tstEOF}}, {"Byte order mark", "\ufeff\nSome text.\n", []Item{nti(TypeIgnore, "\ufeff"), tstSomeText, tstEOF}}, - {"HTML Document", ` <html> `, []Item{nti(tText, " "), tstHtmlStart, nti(tText, "html> "), tstEOF}}, - {"HTML Document with shortcode", `<html>{{< sc1 >}}</html>`, []Item{tstHtmlStart, nti(tText, "html>"), tstLeftNoMD, tstSC1, tstRightNoMD, nti(tText, "</html>"), tstEOF}}, + {"HTML Document", ` <html> `, []Item{nti(tError, "plain HTML documents not supported")}}, + {"HTML Document with shortcode", `<html>{{< sc1 >}}</html>`, []Item{nti(tError, "plain HTML documents not supported")}}, {"No front matter", "\nSome text.\n", []Item{tstSomeText, tstEOF}}, {"YAML front matter", "---\nfoo: \"bar\"\n---\n\nSome text.\n", []Item{tstFrontMatterYAML, tstSomeText, tstEOF}}, {"YAML empty front matter", "---\n---\n\nSome text.\n", []Item{nti(TypeFrontMatterYAML, ""), tstSomeText, tstEOF}}, |