edits

app.py

@@ -144,9 +144,21 @@ def scisearch(query, language, num_results=10):
 
     return results, highlight_terms
 
+PII_TAGS = {"KEY", "EMAIL", "USER", "IP_ADDRESS", "ID", "IPv4", "IPv6"}
+PII_PREFIX = "PI:"
+
+def process_pii(text):
+    for tag in PII_TAGS:
+        text = text.replace(
+            PII_PREFIX + tag,
+            """<b><mark style="background: Fuchsia; color: Lime;">REDACTED {}</mark></b>""".format(tag),
+            )
+    return text
+
 def highlight_string(paragraph: str, highlight_terms: list) -> str:
     for term in highlight_terms:
-        paragraph = re.sub(f"\\b{term}\\b", f"<mark>{term}</mark>", paragraph, flags=re.I)
+        paragraph = re.sub(f"\\b{term}\\b", f"<b>{term}</b>", paragraph, flags=re.I)
+    paragraph = process_pii(paragraph)
     return paragraph
 
 def process_results(hits: list, highlight_terms: list) -> str:
@@ -154,7 +166,7 @@ def process_results(hits: list, highlight_terms: list) -> str:
     for i, hit in enumerate(hits):
         res_head = f"""
                     <div class="searchresult">
-                        <h2>{i}. Document ID: {hit['docid']}</h2>
+                        <h2>{i+1}. Document ID: {hit['docid']}</h2>
                         <p>Language: <string>{hit['lang']}</string>, Score: {round(hit['score'], 2)}</p>              
                     """
         for subhit in hit['meta']['docs']:
@@ -221,8 +233,8 @@ if st.sidebar.button("Search"):
         }
         
         .searchresult h2 {
-            font-size: 15px;
-            line-height: 14px;
+            font-size: 19px;
+            line-height: 18px;
             font-weight: normal;
             color: rgb(7, 111, 222);
             margin-bottom: 0px;