Add an HTML mode to posts, page intros and announcements

Markdown is the default and unchanged; the editor's new Format switch
stores the text as raw HTML instead, put on the blog exactly as written.
Like the custom HTML module it is unsanitised on purpose: the escape
hatch for embeds, scripts and inline styles that Markdown cannot express.

The source column keeps holding the text in both modes and a `format`
column says how to read it, so the public templates and the feed still
print the stored `*_html`. The dashboard preview of HTML goes into a
sandboxed iframe rather than the page, because a superadmin edits other
people's blogs and their markup must never run on the dashboard origin.
Search snippets of HTML posts are cut from a tag-stripped copy.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Sd8UPWrvyYCLj97JexNw3A

1 files changed, 19 insertions, 2 deletions

diff --git a/internal/web/search.go b/internal/web/search.go
index ef554ae..9af980d 100644
--- a/internal/web/search.go
+++ b/internal/web/search.go
@@ -1,11 +1,14 @@
 package web
 
 import (
+	"html"
 	"html/template"
 	"regexp"
 	"strings"
 	"unicode/utf8"
 
+	"github.com/microcosm-cc/bluemonday"
+
 	"github.com/gramanas/blogspace/internal/store"
 )
 
@@ -32,8 +35,22 @@ type searchHit struct {
 	Snippet template.HTML
 }
 
-// searchSnippet is a short piece of the Markdown body around the first match,
-// with the match marked; when only the title matched it is the body's start.
+var stripTags = bluemonday.StrictPolicy()
+
+// snippetSource is the text a post's snippet is cut from: the Markdown as
+// written, or an HTML post with its tags stripped so the excerpt reads as
+// prose. (Postgres still matches against the source, so a query can hit a
+// tag or attribute name in an HTML post; the snippet then shows the text
+// nearest to it.)
+func snippetSource(p *store.Post) string {
+	if p.Format == store.FormatHTML {
+		return html.UnescapeString(stripTags.Sanitize(p.BodyMD))
+	}
+	return p.BodyMD
+}
+
+// searchSnippet is a short piece of the body around the first match, with the
+// match marked; when only the title matched it is the body's start.
 func searchSnippet(body string, re *regexp.Regexp) template.HTML {
 	text := strings.Join(strings.Fields(body), " ")
 	loc := re.FindStringIndex(text)