def count_lines(filename):
    """快速统计文件行数（兼容大文件）"""
    with open(filename, 'rb') as f:
        line_count = 0
        last_char = b''
        file_size = 0
        buf_size = 1024 * 1024  # 1MB缓冲区
        
        while True:
            buf = f.read(buf_size)
            if not buf:
                break
            file_size += len(buf)
            line_count += buf.count(b'\n')
            last_char = buf[-1:] if buf else last_char
        
        # 处理特殊情况
        if file_size == 0:  # 空文件
            return 0
        if last_char != b'\n':  # 最后一行无换行符
            line_count += 1
        
        return line_count

def simple_count(filename):
    """简单行数统计（适用于小文件）"""
    with open(filename, 'r') as f:
        return sum(1 for _ in f)

import subprocess

def wc_count(filename):
    """使用系统命令统计（仅限Unix系统）"""
    result = subprocess.run(['wc', '-l', filename], stdout=subprocess.PIPE)
    return int(result.stdout.split()[0])

import gzip
import os

def count_lines(filename):
    """
    统计文件行数（支持普通文件和gz压缩文件）
    
    参数：
        filename (str): 文件路径，支持.gz扩展名的压缩文件
        
    返回：
        int: 文件行数，出错返回-1
    """
    try:
        # 自动检测文件类型
        is_gzip = filename.lower().endswith('.gz')
        
        # 选择打开方式
        opener = gzip.open if is_gzip else open
        
        with opener(filename, 'rb') as f:
            line_count = 0
            file_size = 0
            last_char = b''
            buf_size = 1024 * 1024  # 1MB缓冲区
            
            while True:
                buf = f.read(buf_size)
                if not buf:
                    break
                file_size += len(buf)
                line_count += buf.count(b'\n')
                last_char = buf[-1:] if buf else last_char
            
            # 处理特殊情况
            if file_size == 0:
                return 0
            if last_char != b'\n':
                line_count += 1
                
            return line_count
    
    except (gzip.BadGzipFile, IOError) as e:
        print(f"读取文件错误：{str(e)}")
        return -1
    except Exception as e:
        print(f"未知错误：{str(e)}")
        return -1

# 使用示例
if __name__ == "__main__":
    files = [
        'normal.txt',       # 普通文本文件
        'compressed.gz',    # gzip压缩文件
        'empty_file.txt',   # 空文件
        'no_newline.txt'    # 最后一行无换行符的文件
    ]
    
    for f in files:
        lines = count_lines(f)
        if lines >= 0:
            print(f"文件 {f} 的行数：{lines}")

from collections import Counter

def kmer_count_basic(sequence, k):
    return Counter(sequence[i:i+k] for i in range(len(sequence)-k+1))

from collections import defaultdict

def kmer_count_fast(sequence, k):
    mapping = {'A': 0, 'T': 1, 'C': 2, 'G': 3}
    base = 4  # 4种碱基
    factor = base ** (k-1)
    
    # 初始化第一个k-mer的哈希值
    current_hash = 0
    for i in range(k):
        current_hash = current_hash * base + mapping[sequence[i]]
    
    counts = defaultdict(int)
    counts[current_hash] = 1
    
    # 滑动窗口计算后续k-mer哈希
    for i in range(1, len(sequence) - k + 1):
        # 移除左侧字符贡献，添加右侧新字符
        left_char = mapping[sequence[i-1]]
        right_char = mapping[sequence[i + k -1]]
        current_hash = (current_hash - left_char * factor) * base + right_char
        counts[current_hash] += 1
    
    return counts

import numpy as np
from collections import defaultdict

def kmer_count_numpy(sequence, k):
    mapping = {'A':0, 'T':1, 'C':2, 'G':3}
    int_seq = np.array([mapping[c] for c in sequence], dtype=np.uint8)
    
    # 生成滑动窗口视图（无内存复制）
    shape = (len(int_seq) - k + 1, k)
    strides = (int_seq.strides[0], int_seq.strides[0])
    windows = np.lib.stride_tricks.as_strided(int_seq, shape=shape, strides=strides)
    
    # 计算k-mer的整数编码（基数4）
    powers = 4 ** np.arange(k-1, -1, -1)
    kmer_ints = np.dot(windows, powers)
    
    # 统计频率
    unique, counts = np.unique(kmer_ints, return_counts=True)
    return dict(zip(unique, counts))

import subprocess

def run_jellyfish(sequence_file, k, output_file):
    # 生成Jellyfish命令
    cmd = f"jellyfish count -m {k} -s 100M -t 8 -C {sequence_file} -o {output_file}"
    subprocess.run(cmd, shell=True, check=True)
    # 读取结果
    cmd = f"jellyfish dump {output_file}"
    result = subprocess.check_output(cmd, shell=True).decode()
    return result

import gzip

# 以二进制模式('rb')打开文件
with gzip.open('example.txt.gz', 'rb') as f:
    compressed_data = f.read()  # 读取压缩数据（字节流）
    text_content = compressed_data.decode('utf-8')  # 解码为字符串

# 写入txt文件
with open('output.txt', 'w', encoding='utf-8') as txt_file:
    txt_file.write(text_content)