import os
from dotenv import load_dotenv
from utils.document_management import load_document, generate_filename_from_details
from utils.vector_db import VectorDB
from langchain.schema import Document
from uuid import uuid4
import re


# Load environment variables
load_dotenv()

# Initialize services
# Load all the transcriptions from the "transcription_data" directory
working_dir = os.path.join(os.getcwd(), "_backend" ,"data", "meeting_minutes_data")
if os.getenv("ENVIRONMENT") == "production":
    working_dir = os.path.join(os.getcwd(), "data","meeting_minutes_data")
vector_db_name = "meeting_minutes"
vector_db_embedding_length = 1536

# First, collect all documents
all_documents = []
all_files = []

# Walk through the directory to find all *_transcribed.srt files
for root, dirs, files in os.walk(working_dir):
    for file in files:
        if file.endswith(".md"):
            file_path = os.path.join(root, file)
            # clipping everything before honduras_data 
            relative_path = os.path.relpath(file_path, working_dir)
            all_files.append(relative_path)

minute_start_pattern = re.compile(
    r"^\|\s*---\s*\|\s*---\s*\|\s*$"  # Matches | --- | --- |
    r"\n"
    r"^\|[^\|\n]*\w[^\|\n]*?\|\s*\|\s*$"  # Matches a generic content line (e.g., date/name)
    r"\n"
    r"^\|\s*\*\*Interviewee Name:\*\*",  # Matches the line with | **Interviewee Name:**
    re.MULTILINE
)

for file_path in all_files:
    path = os.path.join(working_dir, file_path)
    
    content = load_document(path, raw_text=True)

    if content is None:
        print(f"Skipping file {file_path} as it could not be loaded.")
        continue
    
    # Matching the content with the regex pattern
    matches = list(minute_start_pattern.finditer(content))
    header_block = ""
    start_index = matches[0].start() if matches else 0
    end_index = matches[-1].end() if matches else len(content)

    header_block = content[start_index:end_index].strip()
    body = content[end_index:].strip()
    body = body.rstrip("|  |  |")

    filename, info = generate_filename_from_details(header_block)

    docuemnt = Document(
        page_content=body,
        metadata={
            "file_name": filename,
            "interview_date": info[0],
            "interviewee_name_role": info[1],
            "id": str(uuid4()),
            "url": f"https://ifad.sharepoint.com/:t:/r/sites/IFAD-CLEIFAD11andIFAD12/Shared%20Documents/General/07.%20HQ%20Interviews/Minutes/{filename}?csf=1&web=1",
            "content": body,
        }
    )

    all_documents.append(docuemnt)
            
# Now create the vector database with all documents at once (this will delete and recreate)
if all_documents:
    if os.path.exists(os.path.join(working_dir, "chroma_db")):
        import shutil
        # Remove the existing vector database directory
        shutil.rmtree(os.path.join(working_dir, "chroma_db"))
        print("Removed existing vector database directory.")

    vector_db = VectorDB(
        collection_name=vector_db_name,
        embedding_length=vector_db_embedding_length,
        open_ai_api_key=os.getenv("OPENAI_API_KEY"),
        working_dir=working_dir,
        documents=all_documents
    )
    print(f"Created new vector database with {len(all_documents)} documents")
else:
    print("No documents found to process")

print("Vector database reset and data upload complete with ChromaDB.")