soulxpodcast/utils/text.py

import re
from typing import List

def remove_space_between_chinese(text):

    text = re.sub(r'([\u4e00-\u9fff])\s+([\u4e00-\u9fff])', r'\1\2', text)


    text = re.sub(r'([a-zA-Z])\s+([\u4e00-\u9fff])', r'\1\2', text)


    text = re.sub(r'([\u4e00-\u9fff])\s+([a-zA-Z])', r'\1\2', text)

    return text


def normalize_text(current_text):





    current_text = re.sub(r'([\u4e00-\u9fff])\s+([\u4e00-\u9fff])', r'\1\2', current_text)


    current_text = re.sub(r'([a-zA-Z])\s+([\u4e00-\u9fff])', r'\1\2', current_text)


    current_text = re.sub(r'([\u4e00-\u9fff])\s+([a-zA-Z])', r'\1\2', current_text)


    if re.search(r'[\u4e00-\u9fff]$', current_text):

        if current_text[-1] not in ",.?!。，？！":
            current_text += "。"


    elif re.search(r'[a-zA-Z]$', current_text):

        if current_text[-1] not in ".!?":
            current_text += "."

    return current_text


def check_monologue_text(text: str, prefix: str = None) -> bool:
    text = text.strip()

    if prefix is not None and (not text.startswith(prefix)):
        return False

    if prefix is not None:
        text = text.removeprefix(prefix)
    text = text.strip()

    if len(text) == 0:
        return False
    return True

def check_dialect_prompt_text(text: str, prefix: str = None) -> bool:
    text = text.strip()

    if prefix is not None and (not text.startswith(prefix)):
        return False
    text = text.strip()

    if len(text) == 0:
        return False
    return True

def check_dialogue_text(text_list: List[str]) -> bool:
    if len(text_list) == 0:
        return False
    for text in text_list:
        if not (
            check_monologue_text(text, "[S1]")
            or check_monologue_text(text, "[S2]")
            or check_monologue_text(text, "[S3]")
            or check_monologue_text(text, "[S4]")
        ):
            return False
    return True