From 984004115864610ac52bda6726e53be209b9831c Mon Sep 17 00:00:00 2001
From: Jan-Erik Rediger <janerik@fnordig.de>
Date: Fri, 22 Apr 2022 23:41:41 +0200
Subject: [PATCH] Strip markdown tags before indexing

---
 index.sh | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/index.sh b/index.sh
index f45d165..8f5b570 100755
--- a/index.sh
+++ b/index.sh
@@ -21,5 +21,37 @@ PRAGMA foreign_keys = ON;
 " >/dev/null
 
 markdown-to-sqlite "$DATABASE_PATH" posts _posts/*
+
+sqlite-utils convert "$DATABASE_PATH" posts text '
+from markdown import Markdown
+import io
+
+__md = None
+
+def define():
+    global __md
+    def unmark_element(element, stream=None):
+        global io
+        if stream is None:
+            stream = io.StringIO()
+        if element.text:
+            stream.write(element.text)
+        for sub in element:
+            unmark_element(sub, stream)
+        if element.tail:
+            stream.write(element.tail)
+        return stream.getvalue()
+
+    Markdown.output_formats["plain"] = unmark_element
+    __md = Markdown(output_format="plain")
+    __md.stripTopLevelTags = False
+
+define()
+
+def convert(text):
+    global __md
+    return __md.convert(text)
+'
+
 sqlite-utils enable-fts --fts5 "$DATABASE_PATH" posts title text 2>/dev/null || true
 sqlite-utils rebuild-fts "$DATABASE_PATH" posts