added RaG

web/backend/app/services/espd/html_util.py

@@ -0,0 +1,32 @@
+"""HTML helpers for ESPD rich-text content."""
+
+from __future__ import annotations
+
+import re
+from html import unescape
+
+
+def html_to_plain(html: str) -> str:
+    if not html:
+        return ""
+    text = html
+    text = re.sub(r"(?i)<br\s*/?>", "\n", text)
+    text = re.sub(r"(?i)</p\s*>", "\n\n", text)
+    text = re.sub(r"(?i)</h[1-6]\s*>", "\n\n", text)
+    text = re.sub(r"(?i)</li\s*>", "\n", text)
+    text = re.sub(r"(?i)<li[^>]*>", "• ", text)
+    text = re.sub(r"(?i)</tr\s*>", "\n", text)
+    text = re.sub(r"(?i)</td\s*>", "\t", text)
+    text = re.sub(r"<[^>]+>", "", text)
+    text = unescape(text)
+    text = re.sub(r"\n{3,}", "\n\n", text)
+    return text.strip()
+
+
+def plain_to_html(text: str) -> str:
+    if not text:
+        return ""
+    parts = [p.strip() for p in text.replace("\r\n", "\n").split("\n\n") if p.strip()]
+    if not parts:
+        parts = [text.strip()] if text.strip() else []
+    return "".join(f"<p>{p.replace(chr(10), '<br/>')}</p>" for p in parts)