bitool 0.1.2__py3-none-any.whl

bitool/cmd/io.py

@@ -0,0 +1,248 @@
+"""文件IO命令模块.
+
+提供文件读写相关的命令实现.
+"""
+
+from __future__ import annotations
+
+import shutil
+from dataclasses import dataclass
+from pathlib import Path
+
+from bitool.cmd._base import BaseCommand
+from bitool.core import logger
+
+
+def _backup_file(filepath: Path, backup_path: Path | None = None) -> Path | None:
+    """备份文件辅助函数.
+
+    参数:
+        filepath: 源文件路径
+        backup_path: 备份文件路径, 如果为 None 则自动生成
+
+    返回:
+        备份文件路径, 如果备份失败则返回 None
+    """
+    # 如果未指定备份路径, 自动生成带 .bak 后缀的路径
+    if backup_path is None or str(backup_path) == ".":
+        backup_path = filepath.with_suffix(filepath.suffix + ".bak")
+
+    try:
+        # 确保备份文件父目录存在
+        if not backup_path.parent.exists():
+            backup_path.parent.mkdir(parents=True, exist_ok=True)
+
+        shutil.copy2(filepath, backup_path)
+        logger.info(msg=f"已备份文件: `{filepath}` -> `{backup_path}`")
+    except OSError as e:
+        logger.error(msg=f"备份文件时出错: `{e}`", exc_info=True)
+        return None
+    else:
+        return backup_path
+
+
+@dataclass
+class WriteFileCommand(BaseCommand):
+    """写入文件命令."""
+
+    name = "write_file"
+    description = "写入文件命令"
+
+    filepath: Path = Path()
+    content: str = ""
+    overwrite: bool = True
+    backup: bool = True
+
+    def run(self) -> bool:
+        """写入文件."""
+        # 确保父目录存在
+        if not self.filepath.parent.exists():
+            self.filepath.parent.mkdir(parents=True, exist_ok=True)
+
+        # 处理文件已存在的情况
+        if self.filepath.exists():
+            if not self.overwrite:
+                logger.warning(msg=f"文件已存在且不允许覆盖: `{self.filepath}`")
+                return False
+
+            # 如果需要备份, 使用辅助函数创建备份文件
+            if self.backup and _backup_file(self.filepath) is None:
+                return False
+
+        # 写入文件内容
+        try:
+            self.filepath.write_text(data=self.content, encoding="utf-8")
+        except OSError as e:
+            logger.error(msg=f"写入文件时出错: `{e}`", exc_info=True)
+            return False
+        else:
+            logger.info(msg=f"写入`{self.filepath}` 成功")
+            return True
+
+
+@dataclass
+class ReadFileCommand(BaseCommand):
+    """读取文件命令."""
+
+    name = "read_file"
+    description = "读取文件命令"
+
+    filepath: Path = Path()
+    content: str = ""
+
+    def run(self) -> bool:
+        """读取文件内容."""
+        if not self.filepath.exists():
+            logger.warning(msg=f"文件不存在: `{self.filepath}`")
+            return False
+
+        if not self.filepath.is_file():
+            logger.warning(msg=f"路径不是文件: `{self.filepath}`")
+            return False
+
+        try:
+            self.content: str = self.filepath.read_text(encoding="utf-8")
+            logger.info(msg=f"读取`{self.filepath}` 成功")
+        except OSError as e:
+            logger.error(msg=f"读取文件时出错: `{e}`", exc_info=True)
+            return False
+        else:
+            return True
+
+
+@dataclass
+class BackupFileCommand(BaseCommand):
+    """备份文件命令."""
+
+    name = "backup_file"
+    description = "备份文件命令"
+
+    filepath: Path = Path()
+    backup_path: Path = Path()
+
+    def run(self) -> bool:
+        """备份文件."""
+        if not self.filepath.exists():
+            logger.warning(msg=f"文件不存在: `{self.filepath}`")
+            return False
+
+        if not self.filepath.is_file():
+            logger.warning(msg=f"路径不是文件: `{self.filepath}`")
+            return False
+
+        # 使用辅助函数进行备份
+        return _backup_file(self.filepath, self.backup_path) is not None
+
+
+@dataclass
+class CopyFileCommand(BaseCommand):
+    """复制文件命令."""
+
+    name = "copy_file"
+    description = "复制文件命令"
+
+    source: Path = Path()
+    destination: Path = Path()
+    overwrite: bool = True
+
+    def run(self) -> bool:
+        """复制文件."""
+        if not self.source.exists():
+            logger.warning(msg=f"源文件不存在: `{self.source}`")
+            return False
+
+        if not self.source.is_file():
+            logger.warning(msg=f"源路径不是文件: `{self.source}`")
+            return False
+
+        # 检查目标文件是否已存在
+        if self.destination.exists() and not self.overwrite:
+            logger.warning(msg=f"目标文件已存在且不允许覆盖: `{self.destination}`")
+            return False
+
+        try:
+            # 确保目标文件父目录存在
+            if not self.destination.parent.exists():
+                self.destination.parent.mkdir(parents=True, exist_ok=True)
+
+            shutil.copy2(self.source, self.destination)
+            logger.info(msg=f"已复制文件: `{self.source}` -> `{self.destination}`")
+        except OSError as e:
+            logger.error(msg=f"复制文件时出错: `{e}`", exc_info=True)
+            return False
+        else:
+            return True
+
+
+@dataclass
+class MoveFileCommand(BaseCommand):
+    """移动文件命令."""
+
+    name = "move_file"
+    description = "移动文件命令"
+
+    source: Path = Path()
+    destination: Path = Path()
+    overwrite: bool = True
+
+    def run(self) -> bool:
+        """移动文件."""
+        if not self.source.exists():
+            logger.warning(msg=f"源文件不存在: `{self.source}`")
+            return False
+
+        if not self.source.is_file():
+            logger.warning(msg=f"源路径不是文件: `{self.source}`")
+            return False
+
+        # 检查目标文件是否已存在
+        if self.destination.exists() and not self.overwrite:
+            logger.warning(msg=f"目标文件已存在且不允许覆盖: `{self.destination}`")
+            return False
+
+        try:
+            # 确保目标文件父目录存在
+            if not self.destination.parent.exists():
+                self.destination.parent.mkdir(parents=True, exist_ok=True)
+
+            shutil.move(str(self.source), str(self.destination))
+            logger.info(msg=f"已移动文件: `{self.source}` -> `{self.destination}`")
+        except OSError as e:
+            logger.error(msg=f"移动文件时出错: `{e}`", exc_info=True)
+            return False
+        else:
+            return True
+
+
+@dataclass
+class DeleteFileCommand(BaseCommand):
+    """删除文件命令."""
+
+    name = "delete_file"
+    description = "删除文件命令"
+
+    filepath: Path = Path()
+    force: bool = False
+
+    def run(self) -> bool:
+        """删除文件."""
+        if not self.filepath.exists():
+            if self.force:
+                logger.info(msg=f"文件不存在, 跳过删除: `{self.filepath}`")
+                return True
+            else:
+                logger.warning(msg=f"文件不存在: `{self.filepath}`")
+                return False
+
+        if not self.filepath.is_file():
+            logger.warning(msg=f"路径不是文件: `{self.filepath}`")
+            return False
+
+        try:
+            self.filepath.unlink()
+            logger.info(msg=f"已删除文件: `{self.filepath}`")
+        except OSError as e:
+            logger.error(msg=f"删除文件时出错: `{e}`", exc_info=True)
+            return False
+        else:
+            return True

bitool/cmd/pdf.py

@@ -0,0 +1,385 @@
+"""PDF操作模块, 提供用户友好的PDF操作接口."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from pathlib import Path
+
+try:
+    import fitz  # PyMuPDF
+
+    HAS_PYMUPDF = True
+except ImportError:
+    HAS_PYMUPDF = False
+
+from bitool.cmd import BaseCommand
+from bitool.core import logger
+
+__all__ = [
+    "CompressPdfCommand",
+    "ImagesToPdfCommand",
+    "MergePdfsCommand",
+    "PdfToImagesCommand",
+    "SplitPdfCommand",
+]
+
+
+@dataclass
+class SplitPdfCommand(BaseCommand):
+    """按页数拆分PDF命令
+
+    将PDF文件按照指定的页数拆分成多个小文件
+    """
+
+    name = "split_pdf"
+    description = "按页数拆分PDF"
+
+    input_path: Path = field(default_factory=Path.cwd)
+    output_dir: Path = field(default_factory=Path.cwd)
+    pages_per_file: int = 1
+    output_files: list[str] = field(default_factory=list)
+
+    def run(self) -> bool:
+        """执行PDF拆分操作
+
+        Returns:
+            操作是否成功
+        """
+        if not HAS_PYMUPDF:
+            logger.error("未安装PyMuPDF库, 请安装: pip install PyMuPDF")
+            return False
+
+        if self.pages_per_file <= 0:
+            logger.error("每文件页数必须大于0")
+            return False
+
+        if not self.input_path.exists():
+            logger.error(f"输入文件不存在: {self.input_path}")
+            return False
+
+        try:
+            # 确保输出目录存在
+            self.output_dir.mkdir(parents=True, exist_ok=True)
+
+            logger.info(
+                f"开始拆分PDF: {self.input_path}, 每文件 {self.pages_per_file} 页"
+            )
+
+            # 打开PDF文档
+            doc = fitz.open(self.input_path)
+            total_pages = len(doc)
+            self.output_files = []
+
+            try:
+                # 计算需要拆分成多少个文件
+                num_files = (
+                    total_pages + self.pages_per_file - 1
+                ) // self.pages_per_file
+
+                for i in range(num_files):
+                    # 创建新文档
+                    new_doc = fitz.open()
+                    start_page = i * self.pages_per_file
+                    end_page = min(start_page + self.pages_per_file, total_pages)
+
+                    # 添加页面到新文档
+                    for page_num in range(start_page, end_page):
+                        new_doc.insert_pdf(doc, from_page=page_num, to_page=page_num)
+
+                    # 保存新文档
+                    output_path = self.output_dir / f"part_{i + 1}.pdf"
+                    new_doc.save(str(output_path))
+                    new_doc.close()
+                    self.output_files.append(str(output_path))
+
+                logger.info(f"PDF拆分完成, 生成 {len(self.output_files)} 个文件")
+            finally:
+                doc.close()
+        except FileNotFoundError as e:
+            logger.error(f"输入文件不存在: {e}")
+            return False
+        except ValueError as e:
+            logger.error(f"参数错误: {e}")
+            return False
+        except Exception as e:  # noqa: BLE001
+            logger.error(f"PDF拆分失败: {e}")
+            return False
+        else:
+            return len(self.output_files) > 0
+
+
+@dataclass
+class MergePdfsCommand(BaseCommand):
+    """合并多个PDF文件命令
+
+    将多个PDF文件合并成一个完整的PDF文件
+    """
+
+    name = "merge_pdfs"
+    description = "合并多个PDF文件"
+
+    input_paths: list[Path] = field(default_factory=list)
+    output_path: Path = field(default_factory=lambda: Path.cwd())
+
+    def run(self) -> bool:
+        """执行PDF合并操作
+
+        Returns:
+            操作是否成功
+        """
+        if not HAS_PYMUPDF:
+            logger.error("未安装PyMuPDF库, 请安装: pip install PyMuPDF")
+            return False
+
+        if not self.input_paths:
+            logger.error("输入文件列表为空")
+            return False
+
+        try:
+            logger.info(
+                f"开始合并 {len(self.input_paths)} 个PDF文件 -> {self.output_path}"
+            )
+
+            # 创建新文档
+            merged_doc = fitz.open()
+
+            try:
+                # 遍历所有输入文件
+                for input_path in self.input_paths:
+                    if not input_path.exists():
+                        logger.error(f"输入文件不存在: {input_path}")
+                        return False
+                    doc = fitz.open(str(input_path))
+                    merged_doc.insert_pdf(doc)
+                    doc.close()
+
+                # 确保输出目录存在
+                self.output_path.parent.mkdir(parents=True, exist_ok=True)
+
+                # 保存合并后的文档
+                merged_doc.save(str(self.output_path))
+                logger.info(f"PDF合并完成: {self.output_path}")
+            finally:
+                merged_doc.close()
+        except FileNotFoundError as e:
+            logger.error(f"输入文件不存在: {e}")
+            return False
+        except Exception as e:  # noqa: BLE001
+            logger.error(f"PDF合并失败: {e}")
+            return False
+        else:
+            return True
+
+
+@dataclass
+class CompressPdfCommand(BaseCommand):
+    """压缩PDF文件命令
+
+    对PDF文件进行压缩以减小文件大小
+    """
+
+    name = "compress_pdf"
+    description = "压缩PDF文件"
+
+    input_path: Path = field(default_factory=Path.cwd)
+    output_path: Path = field(default_factory=Path.cwd)
+    quality: int = 75
+
+    def run(self) -> bool:
+        """执行PDF压缩操作
+
+        Returns:
+            操作是否成功
+        """
+        if not HAS_PYMUPDF:
+            logger.error("未安装PyMuPDF库, 请安装: pip install PyMuPDF")
+            return False
+
+        if not (1 <= self.quality <= 100):
+            logger.error("压缩质量必须在1-100之间")
+            return False
+
+        if not self.input_path.exists():
+            logger.error(f"输入文件不存在: {self.input_path}")
+            return False
+
+        try:
+            logger.info(f"开始压缩PDF: {self.input_path} -> {self.output_path}")
+
+            # 打开PDF文档
+            doc = fitz.open(self.input_path)
+
+            try:
+                # 确保输出目录存在
+                self.output_path.parent.mkdir(parents=True, exist_ok=True)
+
+                # 使用PyMuPDF的压缩功能
+                doc.save(
+                    str(self.output_path),
+                    garbage=4,  # 删除未使用的对象
+                    deflate=True,  # 压缩流
+                    clean=True,  # 清理内容
+                )
+                logger.info(f"PDF压缩完成: {self.output_path}")
+            finally:
+                doc.close()
+        except FileNotFoundError as e:
+            logger.error(f"输入文件不存在: {e}")
+            return False
+        except ValueError as e:
+            logger.error(f"参数错误: {e}")
+            return False
+        except Exception as e:  # noqa: BLE001
+            logger.error(f"PDF压缩失败: {e}")
+            return False
+        else:
+            return True
+
+
+@dataclass
+class PdfToImagesCommand(BaseCommand):
+    """将PDF转换为图片命令
+
+    将PDF文件的每一页转换为图片格式
+    """
+
+    name = "pdf_to_images"
+    description = "将PDF转换为图片"
+
+    input_path: Path = field(default_factory=lambda: Path.cwd())
+    output_dir: Path = field(default_factory=lambda: Path.cwd())
+    fmt: str = "png"
+    dpi: int = 150
+    output_files: list[str] = field(default_factory=list)
+
+    def run(self) -> bool:
+        """执行PDF转图片操作
+
+        Returns:
+            操作是否成功
+        """
+        if not HAS_PYMUPDF:
+            logger.error("未安装PyMuPDF库, 请安装: pip install PyMuPDF")
+            return False
+
+        if not self.input_path.exists():
+            logger.error(f"输入文件不存在: {self.input_path}")
+            return False
+
+        try:
+            logger.info(f"开始转换PDF为图片: {self.input_path} -> {self.output_dir}")
+
+            # 确保输出目录存在
+            self.output_dir.mkdir(parents=True, exist_ok=True)
+
+            # 打开PDF文档
+            doc = fitz.open(str(self.input_path))
+            self.output_files = []
+
+            try:
+                # 计算缩放比例 (DPI / 72是PDF的默认分辨率)
+                zoom = self.dpi / 72.0
+                mat = fitz.Matrix(zoom, zoom)
+
+                # 遍历每一页
+                for page_num in range(len(doc)):
+                    page = doc[page_num]
+
+                    # 渲染页面为图片
+                    pix = page.get_pixmap(matrix=mat)
+
+                    # 保存图片
+                    output_path = self.output_dir / f"page_{page_num + 1}.{self.fmt}"
+                    pix.save(str(output_path))
+                    self.output_files.append(str(output_path))
+
+                logger.info(f"PDF转图片完成, 生成 {len(self.output_files)} 个文件")
+            finally:
+                doc.close()
+        except FileNotFoundError as e:
+            logger.error(f"输入文件不存在: {e}")
+            return False
+        except ValueError as e:
+            logger.error(f"参数错误: {e}")
+            return False
+        except Exception as e:  # noqa: BLE001
+            logger.error(f"PDF转图片失败: {e}")
+            return False
+        else:
+            return len(self.output_files) > 0
+
+
+@dataclass
+class ImagesToPdfCommand(BaseCommand):
+    """将图片列表转换为PDF命令
+
+    将多张图片合并成一个PDF文件
+    """
+
+    name = "images_to_pdf"
+    description = "将图片列表转换为PDF"
+
+    image_paths: list[Path] = field(default_factory=list)
+    output_path: Path = field(default_factory=lambda: Path.cwd())
+    page_size: str = "auto"
+
+    def run(self) -> bool:
+        """执行图片转PDF操作
+
+        Returns:
+            操作是否成功
+        """
+        if not HAS_PYMUPDF:
+            logger.error("未安装PyMuPDF库, 请安装: pip install PyMuPDF")
+            return False
+
+        if not self.image_paths:
+            logger.error("图片列表为空")
+            return False
+
+        try:
+            logger.info(
+                f"开始将 {len(self.image_paths)} 张图片转换为PDF: {self.output_path}"
+            )
+
+            # 创建新PDF文档
+            pdf_doc = fitz.open()
+
+            try:
+                # 遍历所有图片
+                for image_path in self.image_paths:
+                    if not image_path.exists():
+                        logger.error(f"图片文件不存在: {image_path}")
+                        return False
+                    # 打开图片
+                    img_doc = fitz.open(str(image_path))
+
+                    # 将图片转换为PDF页面
+                    pdf_bytes = img_doc.convert_to_pdf()
+                    img_pdf = fitz.open("pdf", pdf_bytes)
+
+                    # 插入到主文档
+                    pdf_doc.insert_pdf(img_pdf)
+
+                    img_doc.close()
+                    img_pdf.close()
+
+                # 确保输出目录存在
+                self.output_path.parent.mkdir(parents=True, exist_ok=True)
+
+                # 保存PDF
+                pdf_doc.save(str(self.output_path))
+                logger.info(f"图片转PDF完成: {self.output_path}")
+            finally:
+                pdf_doc.close()
+        except FileNotFoundError as e:
+            logger.error(f"输入文件不存在: {e}")
+            return False
+        except ValueError as e:
+            logger.error(f"参数错误: {e}")
+            return False
+        except Exception as e:  # noqa: BLE001
+            logger.error(f"图片转PDF失败: {e}")
+            return False
+        else:
+            return True