First version - Single search only -- Proto

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.9
+
+RUN apt-get update && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --trusted-host pypi.org --trusted-host pypi.python.org --trusted-host files.pythonhosted.org --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,436 @@
+from io import StringIO
+import numpy as np
+import pandas as pd
+import requests
+from bs4 import BeautifulSoup
+import json
+import os
+import traceback
+import uuid
+import zipfile
+import io
+import subprocess
+import os
+import re
+import time
+from datetime import datetime
+import warnings
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import FileResponse
+from fastapi.staticfiles import StaticFiles
+from pydantic import BaseModel
+from typing import Any, Dict, List, Literal, Optional
+
+warnings.filterwarnings("ignore")
+
+app = FastAPI(title="3GPP Document Finder API", 
+              description="API to find 3GPP documents based on TSG document IDs")
+
+app.mount("/static", StaticFiles(directory="static"), name="static")
+
+origins = [
+    "*",
+]
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# def get_text(specification: str, version: str):
+#     """Récupère les bytes du PDF à partir d'une spécification et d'une version."""
+#     doc_id = specification
+#     series = doc_id.split(".")[0]
+    
+#     response = requests.get(
+#         f"https://www.3gpp.org/ftp/Specs/archive/{series}_series/{doc_id}/{doc_id.replace('.', '')}-{version}.zip", 
+#         verify=False,
+#         headers={"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'}
+#     )
+    
+#     if response.status_code != 200:
+#         raise Exception(f"Téléchargement du ZIP échoué pour {specification}-{version}")
+    
+#     zip_bytes = io.BytesIO(response.content)
+    
+#     with zipfile.ZipFile(zip_bytes) as zf:
+#         for file_name in zf.namelist():
+#             if file_name.endswith("zip"):
+#                 print("Another ZIP !")
+#                 zip_bytes = io.BytesIO(zf.read(file_name))
+#                 zf = zipfile.ZipFile(zip_bytes)
+#                 for file_name2 in zf.namelist():
+#                     if file_name2.endswith("doc") or file_name2.endswith("docx"):
+#                         if "cover" in file_name2.lower():
+#                             print("COVER !")
+#                             continue
+#                         ext = file_name2.split(".")[-1]
+#                         doc_bytes = zf.read(file_name2)
+#                         temp_id = str(uuid.uuid4())
+#                         input_path = f"/tmp/{temp_id}.{ext}"
+#                         output_path = f"/tmp/{temp_id}.txt"
+                        
+#                         with open(input_path, "wb") as f:
+#                             f.write(doc_bytes)
+                        
+#                         subprocess.run([
+#                             "libreoffice",
+#                             "--headless",
+#                             "--convert-to", "txt",
+#                             "--outdir", "/tmp",
+#                             input_path
+#                         ], check=True)
+                        
+#                         with open(output_path, "r") as f:
+#                             txt_data = [line.strip() for line in f if line.strip()]
+                        
+#                         os.remove(input_path)
+#                         os.remove(output_path)
+#                         return txt_data
+#             elif file_name.endswith("doc") or file_name.endswith("docx"):
+#                 if "cover" in file_name.lower():
+#                     print("COVER !")
+#                     continue
+#                 ext = file_name.split(".")[-1]
+#                 doc_bytes = zf.read(file_name)
+#                 temp_id = str(uuid.uuid4())
+#                 input_path = f"/tmp/{temp_id}.{ext}"
+#                 output_path = f"/tmp/{temp_id}.txt"
+                
+#                 print("Ecriture")
+#                 with open(input_path, "wb") as f:
+#                     f.write(doc_bytes)
+
+#                 print("Convertissement")                
+#                 subprocess.run([
+#                     "libreoffice",
+#                     "--headless",
+#                     "--convert-to", "txt",
+#                     "--outdir", "/tmp",
+#                     input_path
+#                 ], check=True)
+                
+#                 print("Ecriture TXT")
+#                 with open(output_path, "r", encoding="utf-8") as f:
+#                     txt_data = [line.strip() for line in f if line.strip()]
+                
+#                 os.remove(input_path)
+#                 os.remove(output_path)
+#                 return txt_data
+    
+#     raise Exception(f"Aucun fichier .doc/.docx trouvé dans le ZIP pour {specification}-{version}")
+
+# def get_scope(specification: str, version: str):
+#     try:
+#         spec_text = get_text(specification, version)
+#         scp_i = 0
+#         nxt_i = 0
+#         for x in range(len(spec_text)):
+#             text = spec_text[x]
+#             if re.search(r"scope$", text, flags=re.IGNORECASE):
+#                 scp_i = x
+#                 nxt_i = scp_i + 10
+#             if re.search(r"references$", text, flags=re.IGNORECASE):
+#                 nxt_i = x
+
+#         return re.sub(r"\s+", " ", " ".join(spec_text[scp_i+1:nxt_i])) if len(spec_text[scp_i+1:nxt_i]) < 2 else "Not found"
+#     except Exception as e:
+#         traceback.print_exception(e)
+#         return "Not found (error)"
+
+class DocRequest(BaseModel):
+    doc_id: str
+
+class DocResponse(BaseModel):
+    doc_id: str
+    url: str
+    scope: Optional[str] = None
+    search_time: float
+
+# class BatchDocRequest(BaseModel):
+#     doc_ids: List[str]
+#     release: Optional[int] = None
+
+# class BatchDocResponse(BaseModel):
+#     results: Dict[str, str]
+#     missing: List[str]
+#     search_time: float
+
+# class KeywordRequest(BaseModel):
+#     keywords: str
+#     release: Optional[str] = None
+#     wg: Optional[str] = None
+#     spec_type: Optional[Literal["TS", "TR"]] = None
+#     mode: Optional[Literal["and", "or"]] = "and"
+
+# class KeywordResponse(BaseModel):
+#     results: List[Dict[str, str]]
+#     search_time: float
+
+class DocFinder:
+    def __init__(self):
+        self.main_ftp_url = "https://docbox.etsi.org/SET"
+        self.session = requests.Session()
+        self.indexer_file = "indexed_docs.json"
+        self.indexer, self.last_indexer_date = self.load_indexer()
+        self.session.post("https://portal.etsi.org/ETSIPages/LoginEOL.ashx", verify=False, headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36"}, data=json.dumps({"username": os.environ.get("EOL_USER"), "password": os.environ.get("EOL_PASSWORD")}))
+    
+    def load_indexer(self):
+        if os.path.exists(self.indexer_file):
+            with open(self.indexer_file, "r", encoding="utf-8") as f:
+                x = json.load(f)
+                return x["docs"], x["last_indexed_date"]
+        return {}, None
+
+    def save_indexer(self):
+        today = datetime.today()
+        self.last_indexer_date = today.strftime("%d/%m/%Y-%H:%M:%S")
+        with open(self.indexer_file, "w", encoding="utf-8") as f:
+            output = {"docs": self.indexer, "last_indexed_date": self.last_indexer_date}
+            json.dump(output, f, indent=4, ensure_ascii=False)
+    
+    def get_workgroup(self, doc: str):
+        main_tsg = "SET-WG-R" if any(doc.startswith(kw) for kw in ["SETREQ", "SCPREQ"]) else "SET-WG-T" if any(doc.startswith(kw) for kw in ["SETTEC", "SCPTEC"]) else "SET" if any(doc.startswith(kw) for kw in ["SET", "SCP"]) else None
+        if main_tsg is None:
+            return None, None, None
+        regex = re.search(r'\(([^)]+)\)', doc)
+        workgroup = "20" + regex.group(1)
+        return main_tsg, workgroup, doc
+
+    def find_workgroup_url(self, main_tsg, workgroup):
+        response = self.session.get(f"{self.main_ftp_url}/{main_tsg}/05-CONTRIBUTIONS", verify=False)
+        soup = BeautifulSoup(response.text, 'html.parser')
+        for item in soup.find_all("tr"):
+            link = item.find("a")
+            if link and workgroup in link.get_text():
+                return f"{self.main_ftp_url}/{main_tsg}/05-CONTRIBUTIONS/{link.get_text()}"
+
+        return f"{self.main_ftp_url}/{main_tsg}/05-CONTRIBUTIONS/{workgroup}"
+    
+    def get_docs_from_url(self, url):
+        try:
+            response = self.session.get(url, verify=False, timeout=15)
+            soup = BeautifulSoup(response.text, "html.parser")
+            return [item.get_text() for item in soup.select("tr td a")]
+        except Exception as e:
+            print(f"Error accessing {url}: {e}")
+            return []
+    
+    def search_document(self, doc_id: str):
+        original = doc_id
+
+        if original in self.indexer:
+            return self.indexer[original]
+        for doc in self.indexer:
+            if doc.startswith(original):
+                return self.indexer[doc]
+        
+        main_tsg, workgroup, doc = self.get_workgroup(doc_id)
+        if main_tsg:
+            wg_url = self.find_workgroup_url(main_tsg, workgroup)
+            if wg_url:
+                files = self.get_docs_from_url(wg_url)
+                for f in files:
+                    if doc in f.lower() or original in f:
+                        doc_url = f"{wg_url}/{f}"
+                        self.indexer[original] = doc_url
+                        self.save_indexer()
+                        return doc_url
+        return f"Document {doc_id} not found"
+
+# class DocFinder:
+#     def __init__(self):
+#         self.main_ftp_url = "https://www.3gpp.org/ftp"
+#         self.indexer_file = "indexed_docs.json"
+#         self.indexer, self.last_indexer_date = self.load_indexer()
+
+#     def load_indexer(self):
+#         """Load existing index if available"""
+#         if os.path.exists(self.indexer_file):
+#             with open(self.indexer_file, "r", encoding="utf-8") as f:
+#                 x = json.load(f)
+#                 return x["docs"], x["last_indexed_date"]
+#         return {}, None
+    
+#     def save_indexer(self):
+#         """Save the updated index"""
+#         self.last_indexer_date = today.strftime("%d/%m/%Y-%H:%M:%S")
+#         with open(self.indexer_file, "w", encoding="utf-8") as f:
+#             today = datetime.today()
+#             output = {"docs": self.indexer, "last_indexed_date": self.last_indexer_date}
+#             json.dump(output, f, indent=4, ensure_ascii=False)
+    
+#     def get_workgroup(self, doc):
+#         main_tsg = "tsg_ct" if doc[0] == "C" else "tsg_sa" if doc[0] == "S" else None
+#         if main_tsg is None:
+#             return None, None, None
+#         workgroup = f"WG{int(doc[1])}" if doc[1].isnumeric() else main_tsg.upper()
+#         return main_tsg, workgroup, doc
+    
+#     def find_workgroup_url(self, main_tsg, workgroup):
+#         """Find the URL for the specific workgroup"""
+#         response = requests.get(f"{self.main_ftp_url}/{main_tsg}", verify=False)
+#         soup = BeautifulSoup(response.text, 'html.parser')
+        
+#         for item in soup.find_all("tr"):
+#             link = item.find("a")
+#             if link and workgroup in link.get_text():
+#                 return f"{self.main_ftp_url}/{main_tsg}/{link.get_text()}"
+                
+#         return f"{self.main_ftp_url}/{main_tsg}/{workgroup}"
+
+#     def get_docs_from_url(self, url):
+#         """Get list of documents/directories from a URL"""
+#         try:
+#             response = requests.get(url, verify=False, timeout=10)
+#             soup = BeautifulSoup(response.text, "html.parser")
+#             return [item.get_text() for item in soup.select("tr td a")]
+#         except Exception as e:
+#             print(f"Error accessing {url}: {e}")
+#             return []
+    
+#     def search_document(self, doc_id: str, release=None):
+#         original_id = doc_id
+
+#         if original_id in self.indexer:
+#             return self.indexer[original_id]
+#         for doc in self.indexer:
+#             if doc.startswith(original_id):
+#                 return self.indexer[doc]
+
+#         # 2. Recherche live "classique" (TSG/CT)
+#         main_tsg, workgroup, doc = self.get_workgroup(doc_id)
+#         if main_tsg:
+#             wg_url = self.find_workgroup_url(main_tsg, workgroup)
+#             if wg_url:
+#                 meeting_folders = self.get_docs_from_url(wg_url)
+#                 for folder in meeting_folders:
+#                     meeting_url = f"{wg_url}/{folder}"
+#                     meeting_contents = self.get_docs_from_url(meeting_url)
+#                     key = "docs" if "docs" in [x.lower() for x in meeting_contents] else "tdocs" if "tdocs" in [x.lower() for x in meeting_contents] else None
+#                     if key is not None:
+#                         docs_url = f"{meeting_url}/{key}"
+#                         files = self.get_docs_from_url(docs_url)
+#                         for file in files:
+#                             if doc in file.lower() or original_id in file:
+#                                 doc_url = f"{docs_url}/{file}"
+#                                 self.indexer[original_id] = doc_url
+#                                 return doc_url
+#                         # ZIP subfolder
+#                         if "zip" in [x for x in files]:
+#                             zip_url = f"{docs_url}/zip"
+#                             zip_files = self.get_docs_from_url(zip_url)
+#                             for file in zip_files:
+#                                 if doc in file.lower() or original_id in file:
+#                                     doc_url = f"{zip_url}/{file}"
+#                                     self.indexer[original_id] = doc_url
+#                                     self.save_indexer()
+#                                     return doc_url
+
+#         # 3. Dernier recours : tenter dans /ftp/workshop (recherche live)
+#         workshop_url = f"{self.main_ftp_url}/workshop"
+#         meetings = self.get_docs_from_url(workshop_url)
+#         for meeting in meetings:
+#             if meeting in ['./', '../']:
+#                 continue
+#             meeting_url = f"{workshop_url}/{meeting}"
+#             contents = self.get_docs_from_url(meeting_url)
+#             for sub in contents:
+#                 if sub.lower() in ['docs', 'tdocs']:
+#                     docs_url = f"{meeting_url}/{sub}"
+#                     files = self.get_docs_from_url(docs_url)
+#                     for file in files:
+#                         if doc_id.lower() in file.lower() or original_id in file:
+#                             doc_url = f"{docs_url}/{file}"
+#                             self.indexer[original_id] = doc_url
+#                             self.save_indexer()
+#                             return doc_url
+#                     if "zip" in [x.lower() for x in files]:
+#                         zip_url = f"{docs_url}/zip"
+#                         zip_files = self.get_docs_from_url(zip_url)
+#                         for file in zip_files:
+#                             if doc_id.lower() in file.lower() or original_id in file:
+#                                 doc_url = f"{zip_url}/{file}"
+#                                 self.indexer[original_id] = doc_url
+#                                 self.save_indexer()
+#                                 return doc_url
+
+#         return f"Document {doc_id} not found"
+
+@app.get("/")
+async def main_menu():
+    return FileResponse(os.path.join("templates", "index.html"))
+
+# @app.post("/search-spec", response_model=KeywordResponse)
+# def search_spec(request: KeywordRequest):
+#     start_time = time.time()
+#     kws = [_.lower() for _ in request.keywords.split(" ")]
+#     results = []
+
+#     for string, spec in finder_spec.indexer_specs.items():
+#         if request.mode == "and":
+#             if not all(kw in string.lower() for kw in kws):
+#                 continue
+#         elif request.mode == "or":
+#             if not any(kw in string.lower() for kw in kws):
+#                 continue
+#         release = request.release
+#         working_group = request.wg
+#         spec_type = request.spec_type
+
+#         if spec.get('version', None) is None or (release is not None and spec["version"].split(".")[0] != str(release)):
+#             continue
+#         if spec.get('working_group', None) is None or (working_group is not None and spec["working_group"] != working_group):
+#             continue
+#         if spec_type is not None and spec["type"] != spec_type:
+#             continue
+
+#         results.append(spec)
+#     if len(results) > 0:
+#         return KeywordResponse(
+#             results=results,
+#             search_time=time.time() - start_time
+#         )
+#     else:
+#         raise HTTPException(status_code=404, detail="Specifications not found")
+
+finder = DocFinder()
+
+@app.post("/find", response_model=DocResponse)
+def find_document(request: DocRequest):
+    start_time = time.time()
+    result = finder.search_document(request.doc_id)
+
+    if "not found" not in result and "Could not" not in result and "Unable" not in result:
+        return DocResponse(
+            doc_id=request.doc_id,
+            url=result,
+            search_time=time.time() - start_time
+        )
+    else:
+        raise HTTPException(status_code=404, detail=result)
+
+# @app.post("/batch", response_model=BatchDocResponse)
+# def find_documents_batch(request: BatchDocRequest):
+#     start_time = time.time()
+    
+#     results = {}
+#     missing = []
+    
+#     for doc_id in request.doc_ids:
+#         finder = finder_tsg if doc_id[0].isalpha() else finder_spec
+#         result = finder.search_document(doc_id)
+#         if "not found" not in result and "Could not" not in result and "Unable" not in result:
+#             results[doc_id] = result
+#         else:
+#             missing.append(doc_id)
+    
+#     return BatchDocResponse(
+#         results=results,
+#         missing=missing,
+#         search_time=time.time() - start_time
+#     )

requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+uvicorn[standard]
+requests
+beautifulsoup4
+pydantic
+numpy
+pandas
+lxml

static/script.js

@@ -0,0 +1,321 @@
+// DOM elements
+const dynamicDesc = document.getElementById("dynamicDesc");
+const dynamicTitle = document.getElementById("dynamicTitle");
+
+// const singleModeBtn = document.getElementById('single-mode-btn');
+// const batchModeBtn = document.getElementById('batch-mode-btn');
+// const keywordModeBtn = document.getElementById("keyword-mode-btn");
+
+const singleInput = document.querySelector('.single-input');
+// const batchInput = document.querySelector('.batch-input');
+// const keywordSearchInput = document.querySelector(".keyword-input");
+
+const docIdInput = document.getElementById('doc-id');
+// const batchIdsInput = document.getElementById('batch-ids');
+// const keywordInput = document.getElementById("keywords");
+
+const searchBtn = document.getElementById('search-btn');
+const batchSearchBtn = document.getElementById('batch-search-btn');
+const keywordSearchBtn = document.getElementById("keyword-search-btn");
+
+const loader = document.getElementById('loader');
+const resultsContainer = document.getElementById('results-container');
+const resultsList = document.getElementById('results-list');
+const resultsStats = document.getElementById('results-stats');
+const errorMessage = document.getElementById('error-message');
+
+// Search mode toggle
+// singleModeBtn.addEventListener('click', () => {
+//     dynamicTitle.textContent = "Find 3GPP Documents";
+//     dynamicDesc.textContent = "Enter a TSG document ID / specification ID (e.g., S1-123456, C2-987654 or 31.102) to locate the document in the 3GPP FTP server.";
+
+//     singleModeBtn.classList.add('active');
+//     keywordModeBtn.classList.remove("active");
+//     batchModeBtn.classList.remove('active');
+
+//     singleInput.style.display = 'block';
+//     batchInput.style.display = 'none';
+//     keywordSearchInput.style.display = "none";
+// });
+
+// batchModeBtn.addEventListener('click', () => {
+//     dynamicTitle.textContent = "Find multiple 3GPP Documents";
+//     dynamicDesc.textContent = "Enter a list of TSG document ID / specification ID (e.g., S1-123456, C2-987654 or 31.102) to locate all of the specified documents in the 3GPP FTP server.";
+
+//     batchModeBtn.classList.add('active');
+//     keywordModeBtn.classList.remove("active");
+//     singleModeBtn.classList.remove('active');
+
+//     batchInput.style.display = 'block';
+//     keywordSearchInput.style.display = "none";
+//     singleInput.style.display = 'none';
+// });
+
+// keywordModeBtn.addEventListener('click', () => {
+//     dynamicTitle.textContent = "Search 3GPP specifications";
+//     dynamicDesc.textContent = "With keywords and filters, find all of 3GPP's specifications that matches your needs (with keywords, specification number, release or even working group (C1, S5, SP, CP: always the first letter of the group followed by the workgroup number)";
+
+//     keywordModeBtn.classList.add("active");
+//     singleModeBtn.classList.remove('active');
+//     batchModeBtn.classList.remove("active");
+
+//     singleInput.style.display = "none";
+//     batchInput.style.display = "none";
+//     keywordSearchInput.style.display = "block";
+// })
+
+// keywordSearchBtn.addEventListener("click", async ()=>{
+//     const keywords = keywordInput.value.trim();
+//     if (!keywords) {
+//         showError("Please enter at least one keyword");
+//         return;
+//     }
+
+//     showLoader();
+//     hideError();
+
+//     try{
+//         const response = await fetch("/search-spec", {
+//             method: "POST",
+//             headers: {
+//                 "Content-Type": "application/json"
+//             },
+//             body: JSON.stringify({ keywords })
+//         });
+
+//         const data = await response.json();
+//         if (response.ok){
+//             displayKeywordResults(data);
+//         } else {
+//             showError('Error processing batch request');
+//         }
+//     } catch (error) {
+//         showError('Error connecting to the server. Please check if the API is running.');
+//         console.error('Error:', error);
+//     } finally {
+//         hideLoader();
+//     }
+// })
+
+
+// Single document search
+searchBtn.addEventListener('click', async () => {
+    const docId = docIdInput.value.trim();
+    if (!docId) {
+        showError('Please enter a document ID');
+        return;
+    }
+
+    showLoader();
+    hideError();
+    
+    try {
+        const response = await fetch(`/find`, {
+            method: 'POST',
+            headers: {
+                'Content-Type': 'application/json'
+            },
+            body: JSON.stringify({ doc_id: docId })
+        });
+
+        const data = await response.json();
+        
+        if (response.ok) {
+            displaySingleResult(data);
+        } else {
+            displaySingleNotFound(docId, data.detail);
+        }
+    } catch (error) {
+        showError('Error connecting to the server. Please check if the API is running.');
+        console.error('Error:', error);
+    } finally {
+        hideLoader();
+    }
+});
+
+// Batch document search
+// batchSearchBtn.addEventListener('click', async () => {
+//     const batchText = batchIdsInput.value.trim();
+//     if (!batchText) {
+//         showError('Please enter at least one document ID');
+//         return;
+//     }
+
+//     const docIds = batchText.split('\n')
+//         .map(id => id.trim())
+//         .filter(id => id !== '');
+
+//     if (docIds.length === 0) {
+//         showError('Please enter at least one valid document ID');
+//         return;
+//     }
+
+//     showLoader();
+//     hideError();
+    
+//     try {
+//         const response = await fetch(`/batch`, {
+//             method: 'POST',
+//             headers: {
+//                 'Content-Type': 'application/json'
+//             },
+//             body: JSON.stringify({ doc_ids: docIds })
+//         });
+
+//         const data = await response.json();
+        
+//         if (response.ok) {
+//             displayBatchResults(data);
+//         } else {
+//             showError('Error processing batch request');
+//         }
+//     } catch (error) {
+//         showError('Error connecting to the server. Please check if the API is running.');
+//         console.error('Error:', error);
+//     } finally {
+//         hideLoader();
+//     }
+// });
+
+// Display single result
+function displaySingleResult(data) {
+    resultsList.innerHTML = '';
+    
+    const resultItem = document.createElement('div');
+    resultItem.className = 'result-item';
+    let scopeItem = data.scope ? `<p>Scope : ${data.scope}</p>` : ""
+    resultItem.innerHTML = `
+        <div class="result-header">
+            <div class="result-id">${data.doc_id}</div>
+            <div class="result-status status-found">Found</div>
+        </div>
+        <div class="result-url">
+            <a href="${data.url}" target="_blank">${data.url}</a>
+            ${scopeItem}
+        </div>
+    `;
+    
+    resultsList.appendChild(resultItem);
+    resultsStats.textContent = `Found in ${data.search_time.toFixed(2)} seconds`;
+    resultsContainer.style.display = 'block';
+}
+
+// Display single not found result
+function displaySingleNotFound(docId, message) {
+    resultsList.innerHTML = '';
+    
+    const resultItem = document.createElement('div');
+    resultItem.className = 'result-item';
+    resultItem.innerHTML = `
+        <div class="result-header">
+            <div class="result-id">${docId}</div>
+            <div class="result-status status-not-found">Not Found</div>
+        </div>
+        <div>${message}</div>
+    `;
+    
+    resultsList.appendChild(resultItem);
+    resultsStats.textContent = 'Document not found';
+    resultsContainer.style.display = 'block';
+}
+
+// function displayKeywordResults(data) {
+//     resultsList.innerHTML = '';
+    
+//     data.results.forEach(spec => {
+//         const resultItem = document.createElement("div");
+//         resultItem.className = "result-item"
+//         resultItem.innerHTML = `
+//             <div class="result-header">
+//                 <div class="result-id">${spec.id}</div>
+//                 <div class="result-status status-found">Found</div>
+//             </div>
+//             <div class="result-url">
+//                 <p>Title: ${spec.title}</p>
+//                 <p>Type: ${spec.type}</p>
+//                 <p>Release: ${spec.release}</p>
+//                 <p>Version: ${spec.version}</p>
+//                 <p>WG: ${spec.working_group}</p>
+//                 <p>URL: <a target="_blank" href="${spec.url}">${spec.url}</a></p>
+//                 <p>Scope: ${spec.scope}</p>
+//             </div>
+//         `;
+//         resultsList.appendChild(resultItem);
+//     });
+//     resultsStats.textContent = `Found in ${data.search_time.toFixed(2)} seconds`
+//     resultsContainer.style.display = 'block';
+// }
+
+// // Display batch results
+// function displayBatchResults(data) {
+//     resultsList.innerHTML = '';
+    
+//     // Found documents
+//     Object.entries(data.results).forEach(([docId, url]) => {
+//         const resultItem = document.createElement('div');
+//         resultItem.className = 'result-item';
+//         resultItem.innerHTML = `
+//             <div class="result-header">
+//                 <div class="result-id">${docId}</div>
+//                 <div class="result-status status-found">Found</div>
+//             </div>
+//             <div class="result-url">
+//                 <a href="${url}" target="_blank">${url}</a>
+//             </div>
+//         `;
+//         resultsList.appendChild(resultItem);
+//     });
+    
+//     // Not found documents
+//     data.missing.forEach(docId => {
+//         const resultItem = document.createElement('div');
+//         resultItem.className = 'result-item';
+//         resultItem.innerHTML = `
+//             <div class="result-header">
+//                 <div class="result-id">${docId}</div>
+//                 <div class="result-status status-not-found">Not Found</div>
+//             </div>
+//         `;
+//         resultsList.appendChild(resultItem);
+//     });
+    
+//     const foundCount = Object.keys(data.results).length;
+//     const totalCount = foundCount + data.missing.length;
+    
+//     resultsStats.textContent = `Found ${foundCount} of ${totalCount} documents in ${data.search_time.toFixed(2)} seconds`;
+//     resultsContainer.style.display = 'block';
+// }
+
+// Show loader
+function showLoader() {
+    loader.style.display = 'block';
+}
+
+// Hide loader
+function hideLoader() {
+    loader.style.display = 'none';
+}
+
+// Show error message
+function showError(message) {
+    errorMessage.textContent = message;
+    errorMessage.style.display = 'block';
+}
+
+// Hide error message
+function hideError() {
+    errorMessage.style.display = 'none';
+}
+
+// Enter key event for single search
+docIdInput.addEventListener('keypress', (e) => {
+    if (e.key === 'Enter') {
+        searchBtn.click();
+    }
+});
+
+// keywordInput.addEventListener('keypress', (event)=>{
+//     if (event.key === "Enter"){
+//         keywordSearchBtn.click();
+//     }
+// })

static/style.css

@@ -0,0 +1,344 @@
+:root {
+    --primary-color: #8ab4f8;
+    --secondary-color: #181a20;
+    --accent-color: #4285f4;
+    --text-color: #e8eaed;
+    --light-text: #b0b5bd;
+    --error-color: #ff6d6d;
+    --success-color: #34e89e;
+    --border-color: #282b33;
+    --shadow-color: rgba(0, 0, 0, 0.7);
+}
+
+* {
+    margin: 0;
+    padding: 0;
+    box-sizing: border-box;
+}
+
+body {
+    font-family: 'Roboto', sans-serif;
+    background-color: var(--secondary-color);
+    color: var(--text-color);
+    line-height: 1.6;
+    padding: 0;
+    margin: 0;
+}
+
+.container {
+    max-width: 1200px;
+    margin: 0 auto;
+    padding: 20px;
+}
+
+header {
+    background-color: #23262f;
+    box-shadow: 0 2px 10px var(--shadow-color);
+    padding: 20px 0;
+    position: sticky;
+    top: 0;
+    z-index: 100;
+}
+
+.header-content {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+}
+
+.logo {
+    display: flex;
+    align-items: center;
+}
+
+.logo img {
+    height: 40px;
+    margin-right: 10px;
+}
+
+.logo h1 {
+    font-size: 24px;
+    font-weight: 500;
+    color: var(--primary-color);
+}
+
+.search-container {
+    background-color: #23262f;
+    border-radius: 8px;
+    box-shadow: 0 4px 15px var(--shadow-color);
+    padding: 30px;
+    margin-top: 30px;
+}
+
+.search-header {
+    margin-bottom: 20px;
+}
+
+.search-header h2 {
+    font-size: 22px;
+    font-weight: 500;
+    color: var(--text-color);
+    margin-bottom: 10px;
+}
+
+.search-header p {
+    color: var(--light-text);
+    font-size: 16px;
+}
+
+.search-form {
+    display: flex;
+    flex-direction: column;
+    gap: 20px;
+}
+
+.input-group {
+    display: flex;
+    flex-direction: column;
+    gap: 8px;
+}
+
+.input-group label {
+    font-size: 14px;
+    font-weight: 500;
+    color: var(--light-text);
+}
+
+.input-field {
+    display: flex;
+    gap: 10px;
+}
+
+.input-field input {
+    flex: 1;
+    padding: 12px 16px;
+    border: 1px solid var(--border-color);
+    border-radius: 4px;
+    font-size: 16px;
+    background: #181a20;
+    color: var(--text-color);
+    outline: none;
+    transition: border-color 0.3s;
+}
+
+.input-field input:focus {
+    border-color: var(--primary-color);
+    box-shadow: 0 0 0 2px rgba(138, 180, 248, 0.15);
+}
+
+.btn {
+    background-color: var(--primary-color);
+    color: #181a20;
+    border: none;
+    border-radius: 4px;
+    padding: 12px 24px;
+    font-size: 16px;
+    font-weight: 500;
+    cursor: pointer;
+    transition: background-color 0.3s;
+}
+
+.btn:hover {
+    background-color: var(--accent-color);
+    color: #fff;
+}
+
+.search-mode {
+    display: flex;
+    gap: 20px;
+    margin-bottom: 20px;
+}
+
+.search-mode button {
+    background: none;
+    border: none;
+    font-size: 16px;
+    font-weight: 500;
+    color: var(--light-text);
+    padding: 8px 16px;
+    cursor: pointer;
+    border-bottom: 2px solid transparent;
+    transition: all 0.3s;
+}
+
+.search-mode button.active {
+    color: var(--primary-color);
+    border-bottom: 2px solid var(--primary-color);
+}
+
+.batch-input {
+    display: none;
+}
+
+.keyword-input {
+    display: none;
+}
+
+.batch-input textarea {
+    width: 100%;
+    height: 120px;
+    padding: 12px 16px;
+    border: 1px solid var(--border-color);
+    border-radius: 4px;
+    font-size: 16px;
+    font-family: 'Roboto', sans-serif;
+    resize: vertical;
+    outline: none;
+    background: #181a20;
+    color: var(--text-color);
+}
+
+.batch-input textarea:focus {
+    border-color: var(--primary-color);
+    box-shadow: 0 0 0 2px rgba(138, 180, 248, 0.15);
+}
+
+.batch-input .hint {
+    font-size: 14px;
+    color: var(--light-text);
+    margin-top: 8px;
+}
+
+.results-container {
+    margin-top: 30px;
+    background-color: #23262f;
+    border-radius: 8px;
+    box-shadow: 0 4px 15px var(--shadow-color);
+    padding: 30px;
+    display: none;
+}
+
+.results-header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-bottom: 20px;
+    padding-bottom: 15px;
+    border-bottom: 1px solid var(--border-color);
+}
+
+.results-header h2 {
+    font-size: 22px;
+    font-weight: 500;
+}
+
+.results-stats {
+    color: var(--light-text);
+    font-size: 14px;
+}
+
+.results-list {
+    display: flex;
+    flex-direction: column;
+    gap: 15px;
+}
+
+.result-item {
+    padding: 15px;
+    border: 1px solid var(--border-color);
+    border-radius: 8px;
+    background: #181a20;
+    transition: box-shadow 0.3s;
+}
+
+.result-item:hover {
+    box-shadow: 0 4px 8px var(--shadow-color);
+}
+
+.result-header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-bottom: 10px;
+}
+
+.result-id {
+    font-weight: 500;
+    font-size: 18px;
+    color: var(--primary-color);
+}
+
+.result-status {
+    font-size: 14px;
+    padding: 4px 12px;
+    border-radius: 12px;
+}
+
+.status-found {
+    background-color: rgba(52, 232, 158, 0.1);
+    color: var(--success-color);
+}
+
+.status-not-found {
+    background-color: rgba(255, 109, 109, 0.1);
+    color: var(--error-color);
+}
+
+.result-url {
+    word-break: break-all;
+    margin-top: 10px;
+}
+
+.result-url a {
+    color: var(--primary-color);
+    text-decoration: none;
+    transition: color 0.3s;
+}
+
+.result-url a:hover {
+    text-decoration: underline;
+}
+
+.loader {
+    display: none;
+    text-align: center;
+    padding: 20px;
+}
+
+.spinner {
+    border: 4px solid rgba(255, 255, 255, 0.1);
+    border-radius: 50%;
+    border-top: 4px solid var(--primary-color);
+    width: 40px;
+    height: 40px;
+    animation: spin 1s linear infinite;
+    margin: 0 auto;
+}
+
+@keyframes spin {
+    0% { transform: rotate(0deg); }
+    100% { transform: rotate(360deg); }
+}
+
+.error-message {
+    background-color: rgba(255, 109, 109, 0.1);
+    color: var(--error-color);
+    padding: 15px;
+    border-radius: 4px;
+    margin-top: 20px;
+    display: none;
+}
+
+footer {
+    text-align: center;
+    padding: 30px 0;
+    margin-top: 50px;
+    color: var(--light-text);
+    font-size: 14px;
+}
+
+@media (max-width: 768px) {
+    .header-content {
+        flex-direction: column;
+        gap: 15px;
+    }
+
+    .input-field {
+        flex-direction: column;
+    }
+
+    .search-mode {
+        overflow-x: auto;
+        padding-bottom: 5px;
+    }
+}

templates/index.html

@@ -0,0 +1,80 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>ETSI Document Finder</title>
+    <link rel="stylesheet" href="/static/style.css">
+    <link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Roboto:wght@300;400;500;700&display=swap">
+</head>
+<body>
+    <header>
+        <div class="container header-content">
+            <div class="logo">
+                <h1>ETSI Document Finder</h1>
+            </div>
+        </div>
+    </header>
+
+    <div class="container">
+        <div class="search-container">
+            <div class="search-header">
+                <h2 id="dynamicTitle">Find ETSI Documents</h2>
+                <p id="dynamicDesc">Enter a SET/SCP document IDto locate the document in the ETSI DocBox server.</p>
+            </div>
+
+            <div class="search-mode">
+                <button id="single-mode-btn" class="active">Single Document</button>
+                <!-- <button id="batch-mode-btn">Batch Search</button>
+                <button id="keyword-mode-btn">Keyword Search</button> -->
+            </div>
+
+            <div class="search-form">
+                <div class="input-group single-input">
+                    <label for="doc-id">Document ID</label>
+                    <div class="input-field">
+                        <input type="text" id="doc-id" placeholder="Enter SET/SCP document ID (e.g. SETREQ(15)0015451r1, SCP(12)15151, SCPTEC(11)44754r3)">
+                        <button id="search-btn" class="btn">Search</button>
+                    </div>
+                </div>
+
+                <!-- <div class="input-group batch-input">
+                    <label for="batch-ids">Document IDs or Specification IDs (one per line)</label>
+                    <textarea id="batch-ids" placeholder="Enter document IDs or specification IDs, one per line (e.g., S1-123456, C2-987654, 31.102)"></textarea>
+                    <div class="hint">Enter one document ID per line</div>
+                    <button id="batch-search-btn" class="btn" style="margin-top: 10px;">Search All</button>
+                </div>
+
+                <div class="input-group keyword-input">
+                    <label for="keywords">Keywords</label>
+                    <div class="input-field">
+                        <input type="text" id="keywords" placeholder="Enter your keywords separated by space">
+                        <button id="keyword-search-btn" class="btn">Search</button>
+                    </div>
+                </div> -->
+            </div>
+
+            <div class="error-message" id="error-message"></div>
+
+            <div class="loader" id="loader">
+                <div class="spinner"></div>
+                <p>Searching for documents...</p>
+            </div>
+        </div>
+
+        <div class="results-container" id="results-container">
+            <div class="results-header">
+                <h2>Search Results</h2>
+                <div class="results-stats" id="results-stats"></div>
+            </div>
+            <div class="results-list" id="results-list"></div>
+        </div>
+    </div>
+
+    <footer>
+        <p>© 2025 ETSI Document Finder | Powered by FastAPI</p>
+    </footer>
+
+    <script src="/static/script.js"></script>
+</body>
+</html>