初始化提交

app/utils/file_security.py

@@ -0,0 +1,39 @@
+import os
+from asyncio import log
+
+
+def resolve_path_within_directory(
+    base_dir: str,
+    unsafe_path: str,
+    *,
+    require_file: bool = True,
+) -> str:
+    # 用户传入的路径可能是文件名、相对路径、绝对路径，也可能夹带 `../`。
+    # 这里统一解析成真实路径，并用 commonpath 判断它是否仍在允许目录内。
+    # 这样比简单判断字符串前缀可靠，可以覆盖符号链接、重复分隔符、相对路径
+    # 等场景，适用于上传目录、素材目录、任务产物目录这类白名单目录。
+    if not unsafe_path:
+        raise ValueError("empty path is not allowed")
+
+    base_dir_real = os.path.realpath(base_dir)
+    candidate_path = unsafe_path
+
+    if not os.path.isabs(candidate_path):
+        candidate_path = os.path.join(base_dir_real, candidate_path)
+
+
+    resolved_path = os.path.realpath(candidate_path)
+
+    try:
+        common_path = os.path.commonpath([base_dir_real, resolved_path])
+    except ValueError as exc:
+        # Windows 下不同盘符会触发 ValueError，这类路径一定不属于允许目录。
+        raise ValueError("path is outside the allowed directory") from exc
+
+    if common_path != base_dir_real:
+        raise ValueError("path is outside the allowed directory")
+
+    if require_file and not os.path.isfile(resolved_path):
+        raise ValueError("file does not exist")
+
+    return resolved_path

app/utils/utils.py

@@ -0,0 +1,236 @@
+import json
+import locale
+import os
+from pathlib import Path
+import threading
+from typing import Any
+from uuid import uuid4
+
+from loguru import logger
+
+from app.models import const
+
+
+def get_response(status: int, data: Any = None, message: str = ""):
+    obj = {
+        "status": status,
+    }
+    if data:
+        obj["data"] = data
+    if message:
+        obj["message"] = message
+    return obj
+
+
+def to_json(obj):
+    try:
+        # Define a helper function to handle different types of objects
+        def serialize(o):
+            # If the object is a serializable type, return it directly
+            if isinstance(o, (int, float, bool, str)) or o is None:
+                return o
+            # If the object is binary data, convert it to a base64-encoded string
+            elif isinstance(o, bytes):
+                return "*** binary data ***"
+            # If the object is a dictionary, recursively process each key-value pair
+            elif isinstance(o, dict):
+                return {k: serialize(v) for k, v in o.items()}
+            # If the object is a list or tuple, recursively process each element
+            elif isinstance(o, (list, tuple)):
+                return [serialize(item) for item in o]
+            # If the object is a custom type, attempt to return its __dict__ attribute
+            elif hasattr(o, "__dict__"):
+                return serialize(o.__dict__)
+            # Return None for other cases (or choose to raise an exception)
+            else:
+                return None
+
+        # Use the serialize function to process the input object
+        serialized_obj = serialize(obj)
+
+        # Serialize the processed object into a JSON string
+        return json.dumps(serialized_obj, ensure_ascii=False, indent=4)
+    except Exception as e:
+        logger.error(f"failed to serialize object to json: {str(e)}")
+        return None
+
+
+def get_uuid(remove_hyphen: bool = False):
+    u = str(uuid4())
+    if remove_hyphen:
+        u = u.replace("-", "")
+    return u
+
+
+def root_dir():
+    return os.path.dirname(os.path.dirname(os.path.dirname(os.path.realpath(__file__))))
+
+
+def storage_dir(sub_dir: str = "", create: bool = False):
+    d = os.path.join(root_dir(), "storage")
+    if sub_dir:
+        d = os.path.join(d, sub_dir)
+    if create and not os.path.exists(d):
+        os.makedirs(d)
+
+    return d
+
+
+def resource_dir(sub_dir: str = ""):
+    d = os.path.join(root_dir(), "resource")
+    if sub_dir:
+        d = os.path.join(d, sub_dir)
+    return d
+
+
+def task_dir(sub_dir: str = ""):
+    d = os.path.join(storage_dir(), "tasks")
+    if sub_dir:
+        d = os.path.join(d, sub_dir)
+    if not os.path.exists(d):
+        os.makedirs(d)
+    return d
+
+
+def font_dir(sub_dir: str = ""):
+    d = resource_dir("fonts")
+    if sub_dir:
+        d = os.path.join(d, sub_dir)
+    if not os.path.exists(d):
+        os.makedirs(d)
+    return d
+
+
+def song_dir(sub_dir: str = ""):
+    d = resource_dir("songs")
+    if sub_dir:
+        d = os.path.join(d, sub_dir)
+    if not os.path.exists(d):
+        os.makedirs(d)
+    return d
+
+
+def public_dir(sub_dir: str = ""):
+    d = resource_dir("public")
+    if sub_dir:
+        d = os.path.join(d, sub_dir)
+    if not os.path.exists(d):
+        os.makedirs(d)
+    return d
+
+
+def run_in_background(func, *args, **kwargs):
+    def run():
+        try:
+            func(*args, **kwargs)
+        except Exception as e:
+            logger.error(f"run_in_background error: {e}", exc_info=True)
+
+    thread = threading.Thread(target=run, daemon=False)
+    thread.start()
+    return thread
+
+
+def time_convert_seconds_to_hmsm(seconds) -> str:
+    hours = int(seconds // 3600)
+    seconds = seconds % 3600
+    minutes = int(seconds // 60)
+    milliseconds = int(seconds * 1000) % 1000
+    seconds = int(seconds % 60)
+    return "{:02d}:{:02d}:{:02d},{:03d}".format(hours, minutes, seconds, milliseconds)
+
+
+def text_to_srt(idx: int, msg: str, start_time: float, end_time: float) -> str:
+    start_time = time_convert_seconds_to_hmsm(start_time)
+    end_time = time_convert_seconds_to_hmsm(end_time)
+    srt = """%d
+%s --> %s
+%s
+        """ % (
+        idx,
+        start_time,
+        end_time,
+        msg,
+    )
+    return srt
+
+
+def str_contains_punctuation(word):
+    for p in const.PUNCTUATIONS:
+        if p in word:
+            return True
+    return False
+
+
+def split_string_by_punctuations(s):
+    result = []
+    txt = ""
+
+    previous_char = ""
+    next_char = ""
+    for i in range(len(s)):
+        char = s[i]
+        if char == "\n":
+            result.append(txt.strip())
+            txt = ""
+            continue
+
+        if i > 0:
+            previous_char = s[i - 1]
+        if i < len(s) - 1:
+            next_char = s[i + 1]
+
+        if char == "." and previous_char.isdigit() and next_char.isdigit():
+            # # In the case of "withdraw 10,000, charged at 2.5% fee", the dot in "2.5" should not be treated as a line break marker
+            txt += char
+            continue
+
+        if char == "," and previous_char.isdigit() and next_char.isdigit():
+            # 英文数字里的千分位逗号不是断句符，例如 "1,000 years"。
+            # Edge TTS 的 word boundary 通常会把这种数字整体作为连续内容返回；
+            # 如果这里拆成 "1" 和 "000 years"，后续字幕聚合会无法匹配脚本原文，
+            # 进而错误回退到 Whisper。
+            txt += char
+            continue
+
+        if char not in const.PUNCTUATIONS:
+            txt += char
+        else:
+            result.append(txt.strip())
+            txt = ""
+    result.append(txt.strip())
+    # filter empty string
+    result = list(filter(None, result))
+    return result
+
+
+def md5(text):
+    import hashlib
+
+    return hashlib.md5(text.encode("utf-8")).hexdigest()
+
+
+def get_system_locale():
+    try:
+        loc = locale.getdefaultlocale()
+        # zh_CN, zh_TW return zh
+        # en_US, en_GB return en
+        language_code = loc[0].split("_")[0]
+        return language_code
+    except Exception:
+        return "en"
+
+
+def load_locales(i18n_dir):
+    _locales = {}
+    for root, dirs, files in os.walk(i18n_dir):
+        for file in files:
+            if file.endswith(".json"):
+                lang = file.split(".")[0]
+                with open(os.path.join(root, file), "r", encoding="utf-8") as f:
+                    _locales[lang] = json.loads(f.read())
+    return _locales
+
+
+def parse_extension(filename):
+    return Path(filename).suffix.lower().lstrip('.')