ia.py

import os
import yaml
import csv  # ✅ Import CSV module to properly parse quoted values

from src.config import ensure_config, PROJECT_ROOT
from src.upload import upload_files
from src.update import modify_item_metadata
from src.log import log_action

def ia():
    # Ensure the Internet Archive configuration exists
    ensure_config()

    # Load settings
    with open("settings.yml", "r") as file:
        settings = yaml.safe_load(file)

    prefix = settings["ia"]["item_prefix"]
    suffix = settings["ia"]["item_suffix"]
    separator = settings["ia"]["item_separator"]
    untitled = settings["ia"]["item_untitled"]
    source = settings["source"]["dir"]

    # Define directory for files_to_upload
    assets_dir = os.path.join(PROJECT_ROOT, source, "assets")

    # Ensure the directory exists
    if not os.path.exists(assets_dir):
        print(f"❌ Error: Directory '{assets_dir}' not found!")
        exit(1)

    # Load coodebook.csv
    codebook = []
    codebook_path = os.path.join(PROJECT_ROOT, source, "codebook.csv")
    with open(codebook_path, newline="", encoding="utf-8") as f:
        reader = csv.reader(f)
        codebook = list(reader)    

    # ✅ Load items.csv properly
    items = []
    items_path = os.path.join(PROJECT_ROOT, source, "items.csv")
    with open(items_path, newline="", encoding="utf-8") as f:
        reader = csv.reader(f)  # ✅ Properly parses quoted CSV fields
        items = list(reader)

    # ✅ Load files.csv properly
    files = []
    files_path = os.path.join(PROJECT_ROOT, source, "files.csv")
    with open(files_path, newline="", encoding="utf-8") as f:
        reader = csv.reader(f)
        files = list(reader)

    # ✅ Load metadata.csv properly
    metadata = []
    metadata_path = os.path.join(PROJECT_ROOT, source, "metadata.csv")
    with open(metadata_path, newline="", encoding="utf-8") as f:
        reader = csv.reader(f)
        metadata = list(reader)

    # ✅ Iterate through each item
    for item in items:
        if not item:  # Ensure the row isn't empty
            continue

        # Get the identifier and prepend abolition_now_ to it   
        id = item[0]

        # If the id is empty, make identifier separator.join([prefix, str(id)]) else make it empty
        identifier = separator.join([prefix, str(id)]) if id else ""
        log_action(f"Processing: {id}", "info")

        # ✅ Get the files to upload
        files_to_upload = [file[1] for file in files if file and file[0] == id]

        # ✅ Get the metadata row for the item
        core_metadata = {
            "title": item[1] if item[1] else f"{untitled}",
            "creator": item[2],
        }

        codes = []

        for entry in metadata:
            if entry and entry[0] == id:
                # Get the codes for the item and make this string a list
            
                codes = entry[1]
                break  # Stop after finding the first match

        # ✅ Upload files
        upload_files(identifier, files_to_upload)

        # ✅ Update Metadata
        modify_item_metadata(identifier, core_metadata, codes, codebook)

if __name__ == "__main__":
    ia()