Update app.py

app.py

@@ -79,27 +79,77 @@ def create_search_url_wikipedia(search_query):
     base_url = "https://www.wikipedia.org/search-redirect.php?family=wikipedia&language=en&search="
     return base_url + search_query.replace(' ', '+').replace('–', '%E2%80%93').replace('&', 'and')
 
-def scan_for_xml_files_and_generate_links():
-    xml_files = [f for f in os.listdir('.') if f.endswith('.xml')]
+def process_foia_xml_file(filename: str):
+    """Process FOIA XML file and display results with emojis"""
+    try:
+        tree = ET.parse(filename)
+        root = tree.getroot()
+        
+        # Namespace dictionary
+        ns = {
+            'iepd': 'http://leisp.usdoj.gov/niem/FoiaAnnualReport/exchange/1.03',
+            'foia': 'http://leisp.usdoj.gov/niem/FoiaAnnualReport/extension/1.03',
+            'nc': 'http://niem.gov/niem/niem-core/2.0',
+            'j': 'http://niem.gov/niem/domains/jxdm/4.1'
+        }
+
+        # Extract basic info
+        org = root.find(".//nc:Organization", ns)
+        org_name = org.find("nc:OrganizationName", ns).text if org is not None else "Unknown"
+        org_abbr = org.find("nc:OrganizationAbbreviationText", ns).text if org is not None else "N/A"
+        fiscal_year = root.find(".//foia:DocumentFiscalYearDate", ns).text if root.find(".//foia:DocumentFiscalYearDate", ns) is not None else "N/A"
+        
+        st.subheader(f"📋 {org_name} ({org_abbr}) FOIA Report {fiscal_year}")
+        st.write(f"[Wikipedia - {org_name}]({create_search_url_wikipedia(org_name)})")
+
+        # Processing Statistics
+        proc_stats = root.find(".//foia:ProcessedRequestSection/foia:ProcessingStatistics", ns)
+        if proc_stats is not None:
+            st.write("📊 **Request Processing Statistics**")
+            st.write(f"- Pending at Start: {proc_stats.find('foia:ProcessingStatisticsPendingAtStartQuantity', ns).text} ⏳")
+            st.write(f"- Received: {proc_stats.find('foia:ProcessingStatisticsReceivedQuantity', ns).text} 📥")
+            st.write(f"- Processed: {proc_stats.find('foia:ProcessingStatisticsProcessedQuantity', ns).text} ✅")
+            st.write(f"- Pending at End: {proc_stats.find('foia:ProcessingStatisticsPendingAtEndQuantity', ns).text} ⏳")
+
+        # Request Dispositions
+        disp = root.find(".//foia:RequestDispositionSection/foia:RequestDisposition", ns)
+        if disp is not None:
+            st.write("📑 **Request Dispositions**")
+            st.write(f"- Full Grants: {disp.find('foia:RequestDispositionFullGrantQuantity', ns).text} ✅")
+            st.write(f"- Partial Grants: {disp.find('foia:RequestDispositionPartialGrantQuantity', ns).text} ➕")
+            st.write(f"- Full Denials: {disp.find('foia:RequestDispositionFullExemptionDenialQuantity', ns).text} ❌")
+            denial = disp.find('foia:NonExemptionDenial', ns)
+            if denial is not None:
+                st.write(f"- Non-Exemption Denial ({denial.find('foia:NonExemptionDenialReasonCode', ns).text}): {denial.find('foia:NonExemptionDenialQuantity', ns).text} 📭")
+
+        # Applied Exemptions
+        exemptions = root.findall(".//foia:RequestDispositionAppliedExemptionsSection/foia:ComponentAppliedExemptions/foia:AppliedExemption", ns)
+        if exemptions:
+            st.write("🚫 **Applied Exemptions**")
+            for ex in exemptions:
+                code = ex.find('foia:AppliedExemptionCode', ns).text
+                qty = ex.find('foia:AppliedExemptionQuantity', ns).text
+                st.write(f"- {code}: {qty} times")
+
+        # Response Times
+        resp_time = root.find(".//foia:ProcessedResponseTimeSection/foia:ProcessedResponseTime", ns)
+        if resp_time is not None:
+            st.write("⏰ **Response Times**")
+            simple = resp_time.find('foia:SimpleResponseTime', ns)
+            if simple is not None:
+                st.write(f"- Simple Requests:")
+                st.write(f"  - Median: {simple.find('foia:ResponseTimeMedianDaysValue', ns).text} days ⏱️")
+                st.write(f"  - Average: {simple.find('foia:ResponseTimeAverageDaysValue', ns).text} days 📈")
+
+    except ET.ParseError:
+        st.error(f"❌ Error parsing XML file: {filename}")
+
+def list_xml_files():
+    xml_files = [f[:-4] for f in os.listdir('.') if f.endswith('.xml')]
     if not xml_files:
-        st.markdown("No XML files found in the directory.")
-        return
-
-    markdown_table = "Filename | Abbreviation | Full Name | Links\n--- | --- | --- | ---\n"
-    for xml_file in xml_files:
-        try:
-            tree = ET.parse(xml_file)
-            root = tree.getroot()
-            for org in root.findall(".//nc:Organization", namespaces={'nc': 'http://niem.gov/niem/niem-core/2.0'}):
-                short_name = org.find("nc:OrganizationAbbreviationText", namespaces={'nc': 'http://niem.gov/niem/niem-core/2.0'})
-                long_name = org.find("nc:OrganizationName", namespaces={'nc': 'http://niem.gov/niem/niem-core/2.0'})
-                if short_name is not None and long_name is not None:
-                    links = f"[Abbreviation Wikipedia]({create_search_url_wikipedia(short_name.text)}) | [Full Name Wikipedia]({create_search_url_wikipedia(long_name.text)})"
-                    markdown_table += f"{xml_file} | {short_name.text} | {long_name.text} | {links}\n"
-        except ET.ParseError:
-            st.warning(f"Could not parse XML file: {xml_file}")
-    
-    st.markdown(markdown_table)
+        st.markdown("No XML files found in the directory. 📂❓")
+        return []
+    return xml_files
 
 def search_foia_content(query: str, agency: str = None) -> Dict:
     results = {
@@ -115,7 +165,6 @@ def search_foia_content(query: str, agency: str = None) -> Dict:
 def main():
     st.title("Freedom of Information Act (FOIA) Explorer 🌍📊")
     
-    # Tabs for different views
     tab1, tab2 = st.tabs(["Agency Browser", "FOIA Datasets & XML Scanner"])
 
     with tab1:
@@ -170,6 +219,7 @@ def main():
         st.header("FOIA Datasets & XML Scanner")
         st.write("""
         The Freedom of Information Act (FOIA) empowers individuals by granting access to previously unreleased information and documents controlled by the United States government. Championing transparency and accountability, FOIA serves as a foundation for democratic engagement and open government initiatives. 🎉✨
+        Below is a list of datasets available under FOIA, alongside guessed Wikipedia URLs for more information. 📚🔍
         """)
         
         st.markdown("""
@@ -192,8 +242,15 @@ def main():
         for dataset in datasets:
             st.markdown(f"- **{dataset}**: [Wikipedia]({create_search_url_wikipedia(dataset)})")
 
-        st.markdown("### Organizations in Found XML Files")
-        scan_for_xml_files_and_generate_links()
+        st.markdown("### Available FOIA XML Reports")
+        xml_files = list_xml_files()
+        for xml_file in xml_files:
+            col1, col2 = st.columns([3, 1])
+            with col1:
+                st.markdown(f"- [{xml_file}]({xml_file}.xml)")
+            with col2:
+                if st.button(f"📊 Process {xml_file}", key=f"process_{xml_file}"):
+                    process_foia_xml_file(f"{xml_file}.xml")
 
 if __name__ == "__main__":
     main()