Python实现固定列宽文本格式化终极指南

import textwrap

text = "python is an interpreted, high-level, general-purpose programming language."

# 基础换行
wrapped = textwrap.fill(text, width=30)
print(wrapped)
"""
python is an interpreted,
high-level, general-purpose
programming language.
"""

# 保留段落结构
paragraphs = text.split('. ')
wrapped_paragraphs = [textwrap.fill(p, width=30) for p in paragraphs]
print("\n\n".join(wrapped_paragraphs))

# 自定义首行缩进
formatted = textwrap.fill(
    text,
    width=40,
    initial_indent='> ',    # 首行缩进
    subsequent_indent='| '   # 后续行缩进
)
print(formatted)
"""
> python is an interpreted, high-
| level, general-purpose
| programming language.
"""

# 处理长单词
long_word_text = "this sentence contains a verylongwordthatneedstobebroken."
wrapped = textwrap.fill(
    long_word_text,
    width=20,
    break_long_words=true,
    break_on_hyphens=false
)
print(wrapped)
"""
this sentence
contains a
verylongwordthatnee
dstobebroken.
"""

class columnformatter:
    """高级列宽格式化器"""
    def __init__(self, width=80, indent=0, hanging_indent=0):
        self.width = width
        self.indent = indent
        self.hanging_indent = hanging_indent
    
    def format(self, text):
        """格式化文本"""
        # 移除多余空白
        text = ' '.join(text.split())
        
        # 初始化结果列表
        lines = []
        current_line = []
        current_length = self.indent
        
        # 处理每个单词
        for word in text.split():
            word_length = len(word)
            
            # 检查是否超出宽度
            if current_length + word_length + len(current_line) > self.width:
                # 添加当前行
                lines.append(" " * self.indent + " ".join(current_line))
                
                # 重置行
                current_line = [word]
                current_length = self.hanging_indent + word_length
            else:
                current_line.append(word)
                current_length += word_length
        
        # 添加最后一行
        if current_line:
            lines.append(" " * self.indent + " ".join(current_line))
        
        return "\n".join(lines)

# 使用示例
formatter = columnformatter(width=30, indent=4, hanging_indent=2)
formatted_text = formatter.format(text)
print(formatted_text)

def justify_text(text, width):
    """两端对齐文本"""
    words = text.split()
    lines = []
    current_line = []
    current_length = 0
    
    for word in words:
        # 计算添加单词后的长度
        if current_line:
            new_length = current_length + len(word) + 1
        else:
            new_length = len(word)
        
        if new_length <= width:
            current_line.append(word)
            current_length = new_length
        else:
            # 对当前行进行两端对齐
            lines.append(justify_line(current_line, width))
            current_line = [word]
            current_length = len(word)
    
    # 处理最后一行（左对齐）
    if current_line:
        lines.append(" ".join(current_line))
    
    return "\n".join(lines)

def justify_line(words, width):
    """单行两端对齐"""
    if len(words) == 1:
        return words[0].ljust(width)
    
    # 计算总空格数
    total_chars = sum(len(word) for word in words)
    total_spaces = width - total_chars
    gaps = len(words) - 1
    
    # 计算基本空格和额外空格
    base_spaces = total_spaces // gaps
    extra_spaces = total_spaces % gaps
    
    # 构建行
    line = words[0]
    for i in range(1, len(words)):
        # 分配空格
        spaces = base_spaces + (1 if i <= extra_spaces else 0)
        line += ' ' * spaces + words[i]
    
    return line

# 测试
text = "python is an interpreted high-level general-purpose programming language."
print(justify_text(text, 40))
"""
python   is  an  interpreted  high-level
general-purpose programming language.
"""

def generate_table(data, headers, col_width=15):
    """生成固定列宽表格"""
    # 表头分隔线
    separator = '+' + '+'.join(['-' * col_width] * len(headers)) + '+'
    
    # 构建表头
    header_line = '|' + '|'.join(
        f"{h:^{col_width}}" for h in headers
    ) + '|'
    
    # 构建数据行
    rows = []
    for row in data:
        row_line = '|' + '|'.join(
            f"{str(cell):^{col_width}}" for cell in row
        ) + '|'
        rows.append(row_line)
    
    # 组合表格
    return '\n'.join([separator, header_line, separator] + rows + [separator])

# 使用示例
headers = ["product", "price", "stock"]
data = [
    ["laptop", 999.99, 15],
    ["phone", 699.99, 30],
    ["tablet", 399.99, 25]
]

print(generate_table(data, headers))

class smarttableformatter:
    """智能表格格式化器"""
    def __init__(self, headers, alignments=none):
        self.headers = headers
        self.alignments = alignments or ['^'] * len(headers)
        self.col_widths = [len(h) for h in headers]
    
    def update_widths(self, row):
        for i, cell in enumerate(row):
            cell_str = str(cell)
            self.col_widths[i] = max(self.col_widths[i], len(cell_str))
    
    def format_row(self, row):
        formatted = []
        for i, cell in enumerate(row):
            width = self.col_widths[i]
            align = self.alignments[i]
            formatted.append(f"{str(cell):{align}{width}}")
        return '| ' + ' | '.join(formatted) + ' |'
    
    def format_table(self, data):
        # 计算列宽
        for row in data:
            self.update_widths(row)
        
        # 生成分隔线
        separator = '+-' + '-+-'.join(
            '-' * (w + 2) for w in self.col_widths
        ) + '-+'
        
        # 生成表头
        header_row = self.format_row(self.headers)
        
        # 生成数据行
        data_rows = [self.format_row(row) for row in data]
        
        return '\n'.join([separator, header_row, separator] + data_rows + [separator])

# 使用示例
headers = ["product", "price", "stock", "rating"]
data = [
    ["laptop", 999.99, 15, 4.5],
    ["smartphone", 699.99, 30, 4.7],
    ["tablet", 399.99, 25, 4.3]
]

formatter = smarttableformatter(headers, alignments=['<', '>', '>', '^'])
print(formatter.format_table(data))

import os
import shutil

def adaptive_wrap(text, indent=0):
    """根据终端宽度自适应换行"""
    # 获取终端宽度
    terminal_width = shutil.get_terminal_size().columns
    
    # 计算可用宽度
    available_width = terminal_width - indent
    
    # 格式化文本
    return textwrap.fill(
        text,
        width=available_width,
        initial_indent=' ' * indent,
        subsequent_indent=' ' * indent
    )

# 使用示例
long_text = "python is an interpreted, high-level, general-purpose programming language."
print(adaptive_wrap(long_text, indent=4))

def colorize_table(data, headers, col_widths):
    """带颜色的表格输出"""
    # ansi颜色代码
    colors = {
        'header': '\033[1;34m',  # 加粗蓝色
        'row': '\033[0m',        # 默认
        'alt_row': '\033[38;5;245m', # 灰色
        'reset': '\033[0m'
    }
    
    # 表头分隔线
    separator = '+' + '+'.join(['-' * w for w in col_widths]) + '+'
    
    # 构建表头
    header_line = '|' + '|'.join(
        f"{colors['header']}{h:^{w}}{colors['reset']}" 
        for h, w in zip(headers, col_widths)
    ) + '|'
    
    # 构建数据行
    rows = []
    for i, row in enumerate(data):
        color = colors['alt_row'] if i % 2 == 1 else colors['row']
        row_line = '|' + '|'.join(
            f"{color}{str(cell):^{w}}{colors['reset']}" 
            for cell, w in zip(row, col_widths)
        ) + '|'
        rows.append(row_line)
    
    # 组合表格
    return '\n'.join([separator, header_line, separator] + rows + [separator])

# 使用示例
headers = ["id", "name", "score"]
data = [
    [1, "alice", 95.5],
    [2, "bob", 88.2],
    [3, "charlie", 91.8]
]
col_widths = [5, 10, 8]

print(colorize_table(data, headers, col_widths))

class fixedwidthlogformatter(logging.formatter):
    """固定宽度日志格式化器"""
    def __init__(self, widths, fmt=none, datefmt=none):
        """
        widths: 各字段宽度字典
        """
        self.widths = widths
        super().__init__(fmt, datefmt)
    
    def format(self, record):
        # 格式化时间
        record.asctime = self.formattime(record, self.datefmt)
        
        # 对齐各字段
        for field, width in self.widths.items():
            if hasattr(record, field):
                value = getattr(record, field)
                setattr(record, field, f"{value:<{width}}")
        
        return super().format(record)

# 配置日志
logger = logging.getlogger("app")
handler = logging.streamhandler()

formatter = fixedwidthlogformatter(
    widths={
        'levelname': 8,
        'name': 15,
        'funcname': 15
    },
    fmt='%(asctime)s | %(levelname)s | %(name)s | %(funcname)s | %(message)s',
    datefmt='%y-%m-%d %h:%m:%s'
)

handler.setformatter(formatter)
logger.addhandler(handler)
logger.setlevel(logging.debug)

# 测试日志
logger.debug("starting application")
logger.info("configuration loaded")

def align_log_file(input_path, output_path, column_widths):
    """对齐日志文件列"""
    with open(input_path, 'r') as fin:
        with open(output_path, 'w') as fout:
            for line in fin:
                # 分割列
                columns = line.strip().split('|')
                
                # 对齐每列
                aligned = []
                for i, col in enumerate(columns):
                    width = column_widths[i] if i < len(column_widths) else 20
                    aligned.append(f"{col.strip():<{width}}")
                
                # 写入对齐后的行
                fout.write(" | ".join(aligned) + "\n")

# 使用示例
align_log_file(
    "raw.log", 
    "aligned.log",
    column_widths=[25, 10, 15, 40]
)

def stream_text_format(input_file, output_file, width=80):
    """大文件流式格式化"""
    with open(input_file, 'r') as fin:
        with open(output_file, 'w') as fout:
            buffer = ""
            while true:
                chunk = fin.read(4096)
                if not chunk and not buffer:
                    break
                
                buffer += chunk
                while '\n' in buffer:
                    line, buffer = buffer.split('\n', 1)
                    wrapped = textwrap.fill(line, width=width)
                    fout.write(wrapped + '\n')
            
            # 处理剩余内容
            if buffer:
                wrapped = textwrap.fill(buffer, width=width)
                fout.write(wrapped)

def large_table_generator(data_source, headers, col_widths):
    """生成大型表格的生成器"""
    # 计算分隔线
    separator = '+' + '+'.join(['-' * w for w in col_widths]) + '+'
    
    # 生成表头
    header_line = '|' + '|'.join(
        f"{h:^{w}}" for h, w in zip(headers, col_widths)
    ) + '|'
    
    # 返回生成器
    yield separator
    yield header_line
    yield separator
    
    # 生成数据行
    for row in data_source:
        row_line = '|' + '|'.join(
            f"{str(cell):^{w}}" for cell, w in zip(row, col_widths)
        ) + '|'
        yield row_line
    
    yield separator

# 使用示例
def mock_data_generator(count):
    """模拟大数据生成器"""
    for i in range(count):
        yield [f"product{i}", i * 10, i % 5 + 1]

# 处理100万行数据
with open("big_table.txt", "w") as f:
    for line in large_table_generator(
        mock_data_generator(1000000),
        headers=["name", "price", "stock"],
        col_widths=[20, 10, 10]
    ):
        f.write(line + "\n")

def generate_log_report(log_file, output_file, width=80):
    """生成固定列宽的日志分析报告"""
    # 分析日志数据
    error_count = 0
    warning_count = 0
    log_entries = []
    
    with open(log_file, 'r') as f:
        for line in f:
            if "error" in line:
                error_count += 1
                log_entries.append(("error", line.strip()))
            elif "warning" in line:
                warning_count += 1
                log_entries.append(("warning", line.strip()))
    
    # 生成报告
    report = [
        "=" * width,
        f"log analysis report".center(width),
        "=" * width,
        "",
        f"total errors: {error_count}".ljust(width),
        f"total warnings: {warning_count}".ljust(width),
        "",
        "detailed log entries:",
        "-" * width
    ]
    
    # 添加日志条目
    for level, entry in log_entries:
        wrapped_entry = textwrap.fill(
            f"[{level}] {entry}",
            width=width,
            initial_indent='  ',
            subsequent_indent='    '
        )
        report.append(wrapped_entry)
    
    # 写入文件
    with open(output_file, 'w') as f:
        f.write("\n".join(report))

# 使用示例
generate_log_report("app.log", "log_report.txt", width=100)

def format_query_results(connection, query, output_width=80):
    """格式化数据库查询结果"""
    cursor = connection.cursor()
    cursor.execute(query)
    
    # 获取列名
    columns = [desc[0] for desc in cursor.description]
    col_width = output_width // len(columns)
    
    # 生成表头
    header = "|".join(f"{col:^{col_width}}" for col in columns)
    separator = "-" * output_width
    
    # 构建报告
    report = [separator, header, separator]
    
    # 添加数据行
    for row in cursor.fetchall():
        row_str = "|".join(
            f"{str(value)[:col_width-3]:^{col_width}}" 
            for value in row
        )
        report.append(row_str)
    
    report.append(separator)
    return "\n".join(report)

# 使用示例
import sqlite3
conn = sqlite3.connect("example.db")
query = "select id, name, price from products"
print(format_query_results(conn, query, output_width=100))

import timeit

# 测试数据
text = "python is an interpreted, high-level, general-purpose programming language." * 100

# 测试函数
def test_textwrap():
    return textwrap.fill(text, width=80)

def test_custom_formatter():
    formatter = columnformatter(width=80)
    return formatter.format(text)

def test_justify():
    return justify_text(text, width=80)

# 性能测试
methods = {
    "textwrap": test_textwrap,
    "custom_formatter": test_custom_formatter,
    "justify": test_justify
}

results = {}
for name, func in methods.items():
    time = timeit.timeit(func, number=100)
    results[name] = time

print("100次操作耗时:")
for name, time in sorted(results.items(), key=lambda x: x[1]):
    print(f"{name}: {time:.4f}秒")

# 大文件使用流式处理
with open("large.txt") as fin, open("formatted.txt", "w") as fout:
    for line in fin:
        fout.write(textwrap.fill(line, width=80) + "\n")

# 添加颜色增强可读性
print(f"\033[1;32m{header.center(width)}\033[0m")

# 处理全角字符
from wcwidth import wcswidth
def real_width(text):
    return wcswidth(text)

try:
    formatted = justify_text(text, width)
except valueerror as e:
    # 回退到简单格式化
    formatted = textwrap.fill(text, width)

class testtextformatting(unittest.testcase):
    def test_textwrap_formatting(self):
        text = "this is a test."
        result = textwrap.fill(text, width=10)
        self.assertequal(result, "this is a\ntest.")
    
    def test_table_formatting(self):
        headers = ["name", "age"]
        data = [["alice", 30]]
        table = generate_table(data, headers)
        self.assertin("alice", table)
        self.assertin("30", table)