code style

app.py

@@ -1,81 +1,92 @@
-import http.client as http_client
 import json
-import logging
 import os
 import pprint
 import re
-import string
 
+import requests
 import streamlit as st
 import streamlit.components.v1 as components
-import requests
-
 
 pp = pprint.PrettyPrinter(indent=2)
 st.set_page_config(page_title="Gaia Search", layout="wide")
 
-os.makedirs(os.path.join(os.getcwd(),".streamlit"), exist_ok = True)
-with open(os.path.join(os.getcwd(),".streamlit/config.toml"), "w") as file:
-    file.write(
-        '[theme]\nbase="light"'
-    )
-
-LANG_MAPPING = {'Arabic':'ar',
-                'Catalan':'ca',
-                'Code':'code',
-                'English':'en',
-                'Spanish':'es',
-                'French':'fr',
-                'Indonesian':'id',
-                'Indic':'indic',
-                'Niger-Congo':'nigercongo',
-                'Portuguese': 'pt',
-                'Vietnamese': 'vi',
-                'Chinese': 'zh',
-                'Detect Language':'detect_language',
-                'All':'all'}
+os.makedirs(os.path.join(os.getcwd(), ".streamlit"), exist_ok=True)
+with open(os.path.join(os.getcwd(), ".streamlit/config.toml"), "w") as file:
+    file.write('[theme]\nbase="light"')
 
+LANG_MAPPING = {
+    "Arabic": "ar",
+    "Catalan": "ca",
+    "Code": "code",
+    "English": "en",
+    "Spanish": "es",
+    "French": "fr",
+    "Indonesian": "id",
+    "Indic": "indic",
+    "Niger-Congo": "nigercongo",
+    "Portuguese": "pt",
+    "Vietnamese": "vi",
+    "Chinese": "zh",
+    "Detect Language": "detect_language",
+    "All": "all",
+}
 
 
 st.sidebar.markdown(
-"""
-<style>
-.aligncenter {
-    text-align: center;
-    font-weight: bold;
-    font-size: 50px;
-}
-</style>
-<p class="aligncenter">Gaia Search 🌖🌏</p>
-<p style="text-align: center;"> A search engine for the LAION large scale image caption corpora</p>
-""",
-unsafe_allow_html=True,
+    """
+    <style>
+        .aligncenter {
+            text-align: center;
+            font-weight: bold;
+            font-size: 50px;
+        }
+    </style>
+    <p class="aligncenter">Gaia Search 🌖🌏</p>
+    <p style="text-align: center;"> A search engine for the LAION large scale image caption corpora</p>
+    """,
+    unsafe_allow_html=True,
 )
 
 st.sidebar.markdown(
-"""
-<style>
-.aligncenter {
-    text-align: center;
-}
-</style>
-<p style='text-align: center'>
-<a href="" >GitHub</a> | <a href="" >Project Report</a>
-</p>
-<p class="aligncenter">
-  <a href="" target="_blank"> 
-        <img src="https://colab.research.google.com/assets/colab-badge.svg"/>
-    </a>
-</p>
-""",
-unsafe_allow_html=True,
+    """
+    <style>
+        .aligncenter {
+            text-align: center;
+        }
+    </style>
+    <p style='text-align: center'>
+    <a href="" >GitHub</a> | <a href="" >Project Report</a>
+    </p>
+    <p class="aligncenter">
+    <a href="" target="_blank"> 
+            <img src="https://colab.research.google.com/assets/colab-badge.svg"/>
+        </a>
+    </p>
+    """,
+    unsafe_allow_html=True,
 )
 
-query = st.sidebar.text_input(label='Search query', value='')
+query = st.sidebar.text_input(label="Search query", value="")
 language = st.sidebar.selectbox(
-    'Language',
-    ('Arabic', 'Catalan', 'Code', 'English', 'Spanish', 'French', 'Indonesian', 'Indic', 'Niger-Congo', 'Portuguese', 'Vietnamese', 'Chinese', 'Detect Language', 'All'),
-    index=3)
+    "Language",
+    (
+        "Arabic",
+        "Catalan",
+        "Code",
+        "English",
+        "Spanish",
+        "French",
+        "Indonesian",
+        "Indic",
+        "Niger-Congo",
+        "Portuguese",
+        "Vietnamese",
+        "Chinese",
+        "Detect Language",
+        "All",
+    ),
+    index=3,
+)
 max_results = st.sidebar.slider(
     "Maximum Number of Results",
     min_value=1,
@@ -84,22 +95,25 @@ max_results = st.sidebar.slider(
     value=10,
     help="Maximum Number of Documents to return",
 )
-footer="""<style>
-.footer {
-position: fixed;
-left: 0;
-bottom: 0;
-width: 100%;
-background-color: white;
-color: black;
-text-align: center;
-}
-</style>
-<div class="footer">
-<p>Powered by <a href="https://huggingface.co/" >HuggingFace 🤗</a> and <a href="https://github.com/castorini/pyserini" >Pyserini 🦆</a></p>
-</div>
+footer = """
+    <style>
+        .footer {
+            position: fixed;
+            left: 0;
+            bottom: 0;
+            width: 100%;
+            background-color: white;
+            color: black;
+            text-align: center;
+        }
+    </style>
+    <div class="footer">
+        <p>
+            Powered by <a href="https://huggingface.co/" >HuggingFace 🤗</a> and <a href="https://github.com/castorini/pyserini" >Pyserini 🦆</a>
+        </p>
+    </div>
 """
-st.sidebar.markdown(footer,unsafe_allow_html=True)
+st.sidebar.markdown(footer, unsafe_allow_html=True)
 
 
 def scisearch(query, language, num_results=10):
@@ -144,23 +158,29 @@ 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),
-            )
+            """<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"<b>{term}</b>", paragraph, flags=re.I)
     paragraph = process_pii(paragraph)
     return paragraph
 
+
 def process_results(hits: list, highlight_terms: list) -> str:
     hit_list = []
     for i, hit in enumerate(hits):
@@ -169,7 +189,7 @@ def process_results(hits: list, highlight_terms: list) -> str:
                         <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']:
+        for subhit in hit["meta"]["docs"]:
             res_head += f"""
                         <button onclick="load_image({subhit['_id']})">Load Image</button><br>
                         <p><img id='{subhit['_id']}' src='{subhit['URL']}'  style="width:400px;height:auto;display:none;"></p>
@@ -189,22 +209,25 @@ if st.sidebar.button("Search"):
     hits, highlight_terms = scisearch(query, LANG_MAPPING[language], max_results)
     html_results = process_results(hits, highlight_terms)
     rendered_results = f"""
-            <div id="searchresultsarea">
-                <br>
-                <p id="searchresultsnumber">About {max_results} results</p>
-                {html_results}
-            </div>
-                        """
-    st.markdown("""
-                <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.0.2/dist/css/bootstrap.min.css" rel="stylesheet" 
-                    integrity="sha384-EVSTQN3/azprG1Anm3QDgpJLIm9Nao0Yz1ztcQTwFspd3yD65VohhpuuCOmLASjC" crossorigin="anonymous">
-                """,
-                unsafe_allow_html=True)
+        <div id="searchresultsarea">
+            <br>
+            <p id="searchresultsnumber">About {max_results} results</p>
+            {html_results}
+        </div>
+    """
+    st.markdown(
+        """
+        <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.0.2/dist/css/bootstrap.min.css" rel="stylesheet" 
+            integrity="sha384-EVSTQN3/azprG1Anm3QDgpJLIm9Nao0Yz1ztcQTwFspd3yD65VohhpuuCOmLASjC" crossorigin="anonymous">
+        """,
+        unsafe_allow_html=True,
+    )
     st.markdown(
         """
-        <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css">                                  
+        <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css">
         """,
-        unsafe_allow_html=True)
+        unsafe_allow_html=True,
+    )
     st.markdown(
         f"""
         <div class="row no-gutters mt-3 align-items-center">
@@ -219,38 +242,35 @@ if st.sidebar.button("Search"):
             </div>
         </div> 
         """,
-        unsafe_allow_html=True)
+        unsafe_allow_html=True,
+    )
     components.html(
         """
         <style>
-        #searchresultsarea {
-            font-family: 'Arial';
-        }
-        
-        #searchresultsnumber {
-            font-size: 0.8rem;
-            color: gray;
-        }
-        
-        .searchresult h2 {
-            font-size: 19px;
-            line-height: 18px;
-            font-weight: normal;
-            color: rgb(7, 111, 222);
-            margin-bottom: 0px;
-            margin-top: 25px;
-        }
-        
-        .searchresult a {
-            font-size: 12px;
-            line-height: 12px;
-            color: green;
-            margin-bottom: 0px;
-        }
-    
-        .dark-mode {
-          color: white;
-        }
+            #searchresultsarea {
+                font-family: 'Arial';
+            }
+            #searchresultsnumber {
+                font-size: 0.8rem;
+                color: gray;
+            }
+            .searchresult h2 {
+                font-size: 19px;
+                line-height: 18px;
+                font-weight: normal;
+                color: rgb(7, 111, 222);
+                margin-bottom: 0px;
+                margin-top: 25px;
+            }
+            .searchresult a {
+                font-size: 12px;
+                line-height: 12px;
+                color: green;
+                margin-bottom: 0px;
+            }
+            .dark-mode {
+                color: white;
+            }
         </style>
         <script>
         function load_image(id){
@@ -269,5 +289,8 @@ if st.sidebar.button("Search"):
         }
         </script>
         <button onclick="myFunction()">Toggle dark mode</button>
-        """ + rendered_results, height=800, scrolling=True
-        )
+        """
+        + rendered_results,
+        height=800,
+        scrolling=True,
+    )