import csv
import os
import re

def remove_links(definitions: str) -> str:
    definitions = re.sub(r"\[\[([^\|\]\]]*)\]\]", r"\1", definitions)
    definitions = re.sub(r"\[\[[^\[\[]*\|([^\|\]\]]*)\]\]", r"\1", definitions)
    return definitions


def read_markdown_file(file_path: str, filename: str) -> tuple[str, str] | None:
    try:
        with open(file_path, "r", encoding="utf-8") as f:
            content = f.read()

        word = os.path.splitext(filename)[0]

        content_parts = content.split("??")
        if len(content_parts) > 1:
            definitions = content_parts[1]
        else:
            raise Exception("No delimiter found")

        filtered_lines = []
        for line in definitions.split("\n"):
            line = line.strip()
            if line.startswith(("n.", "adj.", "adv.", "v.")):
                filtered_lines.append(line)

        definitions = "\n".join(filtered_lines)
        definitions = remove_links(definitions)
        return word, definitions
    except Exception as e:
        print(f"Error reading {file_path}: {e}")
        return None


def walk_directory(directory=".") -> list[tuple[str, str]]:
    """
    Recursively reads all .md files in the given directory and its subdirectories.
    Prints the filename and contents of each file.

    Args:
        directory (str): The directory to start searching from. Defaults to current directory.
    """
    word_definitions = []
    for root, dirs, files in os.walk(directory):
        for file in files:
            if not file.endswith(".md"):
                continue

            file_path = os.path.join(root, file)
            result = read_markdown_file(file_path, file)
            if not result:
                continue

            word, definitions = result
            word_definitions.append((word, definitions))

    return word_definitions


if __name__ == "__main__":
    word_definitions = walk_directory("words/PartB")
    # Sort word_definitions alphabetically by word (first element of each tuple)
    word_definitions.sort(key=lambda x: x[0])

    # Write to text file
    with open("word_definitions.txt", "w", encoding="utf-8") as textfile:
        # Write each word and its definitions to the text file
        for word, definitions in word_definitions:
            textfile.write(f"{word},{definitions}\n\n")

    print(len(word_definitions))