mirror of
https://github.com/zhayujie/chatgpt-on-wechat.git
synced 2026-02-08 01:02:22 +08:00
118 lines
3.3 KiB
Python
118 lines
3.3 KiB
Python
import io
|
||
import os
|
||
import re
|
||
from urllib.parse import urlparse
|
||
from PIL import Image
|
||
from common.log import logger
|
||
|
||
def fsize(file):
|
||
if isinstance(file, io.BytesIO):
|
||
return file.getbuffer().nbytes
|
||
elif isinstance(file, str):
|
||
return os.path.getsize(file)
|
||
elif hasattr(file, "seek") and hasattr(file, "tell"):
|
||
pos = file.tell()
|
||
file.seek(0, os.SEEK_END)
|
||
size = file.tell()
|
||
file.seek(pos)
|
||
return size
|
||
else:
|
||
raise TypeError("Unsupported type")
|
||
|
||
|
||
def compress_imgfile(file, max_size):
|
||
if fsize(file) <= max_size:
|
||
return file
|
||
file.seek(0)
|
||
img = Image.open(file)
|
||
rgb_image = img.convert("RGB")
|
||
quality = 95
|
||
while True:
|
||
out_buf = io.BytesIO()
|
||
rgb_image.save(out_buf, "JPEG", quality=quality)
|
||
if fsize(out_buf) <= max_size:
|
||
return out_buf
|
||
quality -= 5
|
||
|
||
|
||
def split_string_by_utf8_length(string, max_length, max_split=0):
|
||
encoded = string.encode("utf-8")
|
||
start, end = 0, 0
|
||
result = []
|
||
while end < len(encoded):
|
||
if max_split > 0 and len(result) >= max_split:
|
||
result.append(encoded[start:].decode("utf-8"))
|
||
break
|
||
end = min(start + max_length, len(encoded))
|
||
# 如果当前字节不是 UTF-8 编码的开始字节，则向前查找直到找到开始字节为止
|
||
while end < len(encoded) and (encoded[end] & 0b11000000) == 0b10000000:
|
||
end -= 1
|
||
result.append(encoded[start:end].decode("utf-8"))
|
||
start = end
|
||
return result
|
||
|
||
|
||
def get_path_suffix(path):
|
||
path = urlparse(path).path
|
||
return os.path.splitext(path)[-1].lstrip('.')
|
||
|
||
|
||
def convert_webp_to_png(webp_image):
|
||
from PIL import Image
|
||
try:
|
||
webp_image.seek(0)
|
||
img = Image.open(webp_image).convert("RGBA")
|
||
png_image = io.BytesIO()
|
||
img.save(png_image, format="PNG")
|
||
png_image.seek(0)
|
||
return png_image
|
||
except Exception as e:
|
||
logger.error(f"Failed to convert WEBP to PNG: {e}")
|
||
raise
|
||
|
||
|
||
def remove_markdown_symbol(text: str):
|
||
# 移除markdown格式，目前先移除**
|
||
if not text:
|
||
return text
|
||
return re.sub(r'\*\*(.*?)\*\*', r'\1', text)
|
||
|
||
|
||
def expand_path(path: str) -> str:
|
||
"""
|
||
Expand user path with proper Windows support.
|
||
|
||
On Windows, os.path.expanduser('~') may not work properly in some shells (like PowerShell).
|
||
This function provides a more robust path expansion.
|
||
|
||
Args:
|
||
path: Path string that may contain ~
|
||
|
||
Returns:
|
||
Expanded absolute path
|
||
"""
|
||
if not path:
|
||
return path
|
||
|
||
# Try standard expansion first
|
||
expanded = os.path.expanduser(path)
|
||
|
||
# If expansion didn't work (path still starts with ~), use HOME or USERPROFILE
|
||
if expanded.startswith('~'):
|
||
import platform
|
||
if platform.system() == 'Windows':
|
||
# On Windows, try USERPROFILE first, then HOME
|
||
home = os.environ.get('USERPROFILE') or os.environ.get('HOME')
|
||
else:
|
||
# On Unix-like systems, use HOME
|
||
home = os.environ.get('HOME')
|
||
|
||
if home:
|
||
# Replace ~ with home directory
|
||
if path == '~':
|
||
expanded = home
|
||
elif path.startswith('~/') or path.startswith('~\\'):
|
||
expanded = os.path.join(home, path[2:])
|
||
|
||
return expanded
|