Skip to content

armgit / camel

Public Imported from GitHub
0

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

18.8 KB
Raw Blame
<a id="camel.toolkits.file_toolkit"></a>

<a id="camel.toolkits.file_toolkit.FileToolkit"></a>

## FileToolkit

```python
class FileToolkit(BaseToolkit):
```

A comprehensive toolkit for file operations including reading,
writing, and editing files.

This class provides cross-platform (macOS, Linux, Windows) support for:
- Reading various file formats (text, JSON, YAML, PDF, DOCX)
- Writing to multiple formats (Markdown, DOCX, PDF, plaintext, JSON,
YAML, CSV, HTML)
- Editing and modifying existing files with content replacement
- Automatic backup creation before modifications
- Custom encoding and enhanced formatting options

<a id="camel.toolkits.file_toolkit.FileToolkit.__init__"></a>

### __init__

```python
def __init__(
    self,
    working_directory: Optional[str] = None,
    timeout: Optional[float] = None,
    default_encoding: str = 'utf-8',
    backup_enabled: bool = True
):
```

Initialize the FileToolkit.

**Parameters:**

- **working_directory** (str, optional): The default directory for output files. If not provided, it will be determined by the `CAMEL_WORKDIR` environment variable (if set). If the environment variable is not set, it defaults to `camel_working_dir`.
- **timeout** (Optional[float]): The timeout for the toolkit. (default: :obj:`None`)
- **default_encoding** (str): Default character encoding for text operations. (default: :obj:`utf-8`)
- **backup_enabled** (bool): Whether to create backups of existing files before overwriting. (default: :obj:`True`)

<a id="camel.toolkits.file_toolkit.FileToolkit._resolve_filepath"></a>

### _resolve_filepath

```python
def _resolve_filepath(self, file_path: str):
```

Convert the given string path to a Path object.

If the provided path is not absolute, it is made relative to the
default output directory. The filename part is sanitized to replace
spaces and special characters with underscores, ensuring safe usage
in downstream processing.

**Parameters:**

- **file_path** (str): The file path to resolve.

**Returns:**

  Path: A fully resolved (absolute) and sanitized Path object.

<a id="camel.toolkits.file_toolkit.FileToolkit._resolve_search_path"></a>

### _resolve_search_path

```python
def _resolve_search_path(self, path: Optional[str] = None):
```

Resolve a search directory without sanitizing it.

<a id="camel.toolkits.file_toolkit.FileToolkit._resolve_existing_filepath"></a>

### _resolve_existing_filepath

```python
def _resolve_existing_filepath(self, file_path: str):
```

Resolve a file path without sanitizing the filename.

<a id="camel.toolkits.file_toolkit.FileToolkit._tool_error"></a>

### _tool_error

```python
def _tool_error(self, message: str):
```

<a id="camel.toolkits.file_toolkit.FileToolkit._sanitize_filename"></a>

### _sanitize_filename

```python
def _sanitize_filename(self, filename: str):
```

Sanitize a filename by replacing any character that is not
alphanumeric, a dot (.), hyphen (-), or underscore (_) with an
underscore (_).

**Parameters:**

- **filename** (str): The original filename which may contain spaces or special characters.

**Returns:**

  str: The sanitized filename with disallowed characters replaced by
underscores.

<a id="camel.toolkits.file_toolkit.FileToolkit._iter_grep_candidate_files"></a>

### _iter_grep_candidate_files

```python
def _iter_grep_candidate_files(
    self,
    root: Path,
    glob_pattern: str,
    file_type: Optional[str]
):
```

<a id="camel.toolkits.file_toolkit.FileToolkit._render_grep_context_block"></a>

### _render_grep_context_block

```python
def _render_grep_context_block(
    self,
    file_path: Path,
    lines: List[str],
    match_index: int,
    context_lines: int
):
```

<a id="camel.toolkits.file_toolkit.FileToolkit._render_grep_multiline_block"></a>

### _render_grep_multiline_block

```python
def _render_grep_multiline_block(
    self,
    file_path: Path,
    lines: List[str],
    start_line: int,
    end_line: int,
    context_lines: int
):
```

<a id="camel.toolkits.file_toolkit.FileToolkit._normalize_notebook_source"></a>

### _normalize_notebook_source

```python
def _normalize_notebook_source(self, new_source: str):
```

<a id="camel.toolkits.file_toolkit.FileToolkit._build_notebook_cell"></a>

### _build_notebook_cell

```python
def _build_notebook_cell(self, new_source: str, cell_type: str):
```

<a id="camel.toolkits.file_toolkit.FileToolkit._write_text_file"></a>

### _write_text_file

```python
def _write_text_file(
    self,
    file_path: Path,
    content: str,
    encoding: str = 'utf-8'
):
```

Write text content to a plaintext file.

**Parameters:**

- **file_path** (Path): The target file path.
- **content** (str): The text content to write.
- **encoding** (str): Character encoding to use. (default: :obj:`utf-8`) (default: utf-8)

<a id="camel.toolkits.file_toolkit.FileToolkit._create_backup"></a>

### _create_backup

```python
def _create_backup(self, file_path: Path):
```

Create a backup of the file if it exists and backup is enabled.

**Parameters:**

- **file_path** (Path): The file path to backup.

**Returns:**

  Optional[Path]: Path to the backup file if created, None otherwise.

<a id="camel.toolkits.file_toolkit.FileToolkit._write_docx_file"></a>

### _write_docx_file

```python
def _write_docx_file(self, file_path: Path, content: str):
```

Write text content to a DOCX file with default formatting.

**Parameters:**

- **file_path** (Path): The target file path.
- **content** (str): The text content to write.

<a id="camel.toolkits.file_toolkit.FileToolkit._write_pdf_file"></a>

### _write_pdf_file

```python
def _write_pdf_file(
    self,
    file_path: Path,
    title: str,
    content: Union[str, List[List[str]]],
    use_latex: bool = False
):
```

Write text content to a PDF file with LaTeX and table support.

**Parameters:**

- **file_path** (Path): The target file path.
- **title** (str): The document title.
- **content** (Union[str, List[List[str]]]): The content to write. Can
- **be**: - String: Supports Markdown-style tables and LaTeX math expressions - List[List[str]]: Table data as list of rows for direct table rendering
- **use_latex** (bool): Whether to use LaTeX for math rendering. (default: :obj:`False`)

<a id="camel.toolkits.file_toolkit.FileToolkit._process_text_content"></a>

### _process_text_content

```python
def _process_text_content(
    self,
    story,
    content: str,
    heading_style,
    body_style
):
```

Process text content and add to story.

**Parameters:**

- **story**: The reportlab story list to append to
- **content** (str): The text content to process
- **heading_style**: Style for headings
- **body_style**: Style for body text

<a id="camel.toolkits.file_toolkit.FileToolkit._find_table_line_ranges"></a>

### _find_table_line_ranges

```python
def _find_table_line_ranges(self, lines: List[str]):
```

Find line ranges that contain markdown tables.

**Parameters:**

- **lines** (List[str]): List of lines to analyze.

**Returns:**

  List[Tuple[int, int]]: List of (start_line, end_line) tuples
for table ranges.

<a id="camel.toolkits.file_toolkit.FileToolkit._register_chinese_font"></a>

### _register_chinese_font

```python
def _register_chinese_font(self):
```

**Returns:**

  str: The font name to use for Chinese text.

<a id="camel.toolkits.file_toolkit.FileToolkit._parse_markdown_table"></a>

### _parse_markdown_table

```python
def _parse_markdown_table(self, lines: List[str]):
```

Parse markdown-style tables from a list of lines.

**Parameters:**

- **lines** (List[str]): List of text lines that may contain tables.

**Returns:**

  List[List[List[str]]]: List of tables, where each table is a list
of rows, and each row is a list of cells.

<a id="camel.toolkits.file_toolkit.FileToolkit._is_table_row"></a>

### _is_table_row

```python
def _is_table_row(self, line: str):
```

Check if a line appears to be a table row.

**Parameters:**

- **line** (str): The line to check.

**Returns:**

  bool: True if the line looks like a table row.

<a id="camel.toolkits.file_toolkit.FileToolkit._is_table_separator"></a>

### _is_table_separator

```python
def _is_table_separator(self, line: str):
```

Check if a line is a table separator (e.g., |---|---|).

**Parameters:**

- **line** (str): The line to check.

**Returns:**

  bool: True if the line is a table separator.

<a id="camel.toolkits.file_toolkit.FileToolkit._parse_table_row"></a>

### _parse_table_row

```python
def _parse_table_row(self, line: str):
```

Parse a single table row into cells.

**Parameters:**

- **line** (str): The table row line.

**Returns:**

  List[str]: List of cell contents.

<a id="camel.toolkits.file_toolkit.FileToolkit._create_pdf_table"></a>

### _create_pdf_table

```python
def _create_pdf_table(self, table_data: List[List[str]]):
```

Create a formatted table for PDF.

**Parameters:**

- **table_data** (List[List[str]]): Table data as list of rows.

**Returns:**

  Table: A formatted reportlab Table object.

<a id="camel.toolkits.file_toolkit.FileToolkit._convert_markdown_to_html"></a>

### _convert_markdown_to_html

```python
def _convert_markdown_to_html(self, text: str):
```

Convert basic markdown formatting to HTML for PDF rendering.

**Parameters:**

- **text** (str): Text with markdown formatting.

**Returns:**

  str: Text with HTML formatting.

<a id="camel.toolkits.file_toolkit.FileToolkit._ensure_html_utf8_meta"></a>

### _ensure_html_utf8_meta

```python
def _ensure_html_utf8_meta(self, content: str):
```

Ensure HTML content has UTF-8 meta tag.

**Parameters:**

- **content** (str): The HTML content.

**Returns:**

  str: HTML content with UTF-8 meta tag.

<a id="camel.toolkits.file_toolkit.FileToolkit._write_csv_file"></a>

### _write_csv_file

```python
def _write_csv_file(
    self,
    file_path: Path,
    content: Union[str, List[List]],
    encoding: str = 'utf-8-sig'
):
```

Write CSV content to a file.

**Parameters:**

- **file_path** (Path): The target file path.
- **content** (Union[str, List[List]]): The CSV content as a string or list of lists.
- **encoding** (str): Character encoding to use. (default: :obj:`utf-8-sig`)

<a id="camel.toolkits.file_toolkit.FileToolkit._write_json_file"></a>

### _write_json_file

```python
def _write_json_file(
    self,
    file_path: Path,
    content: str,
    encoding: str = 'utf-8'
):
```

Write JSON content to a file.

**Parameters:**

- **file_path** (Path): The target file path.
- **content** (str): The JSON content as a string.
- **encoding** (str): Character encoding to use. (default: :obj:`utf-8`) (default: utf-8)

<a id="camel.toolkits.file_toolkit.FileToolkit._write_simple_text_file"></a>

### _write_simple_text_file

```python
def _write_simple_text_file(
    self,
    file_path: Path,
    content: str,
    encoding: str = 'utf-8'
):
```

Write text content to a file (used for HTML, Markdown, YAML, etc.).

**Parameters:**

- **file_path** (Path): The target file path.
- **content** (str): The content to write.
- **encoding** (str): Character encoding to use. (default: :obj:`utf-8`) (default: utf-8)

<a id="camel.toolkits.file_toolkit.FileToolkit.write_to_file"></a>

### write_to_file

```python
def write_to_file(
    self,
    title: str,
    content: Union[str, List[List[str]]],
    filename: str,
    encoding: Optional[str] = None,
    use_latex: bool = False
):
```

Write the given content to a file.

If the file exists, it will be overwritten. Supports multiple formats:
Markdown (.md, .markdown, default), Plaintext (.txt), CSV (.csv),
DOC/DOCX (.doc, .docx), PDF (.pdf), JSON (.json), YAML (.yml, .yaml),
and HTML (.html, .htm).

**Parameters:**

- **title** (str): The title of the document.
- **content** (Union[str, List[List[str]]]): The content to write to the file. Content format varies by file type: - Text formats (txt, md, html, yaml): string - CSV: string or list of lists - JSON: string or serializable object
- **filename** (str): The name or path of the file. If a relative path is supplied, it is resolved to self.working_directory.
- **encoding** (Optional[str]): The character encoding to use. (default: :obj: `None`)
- **use_latex** (bool): Whether to use LaTeX for math rendering. (default: :obj:`False`)

**Returns:**

  str: A message indicating success or error details.

<a id="camel.toolkits.file_toolkit.FileToolkit.read_file"></a>

### read_file

```python
def read_file(self, file_paths: Union[str, List[str]]):
```

Read and return content of one or more files using MarkItDown
for better format support.

This method uses MarkItDownLoader to convert various file formats
to Markdown. It supports a wide range of formats including:
- PDF (.pdf)
- Microsoft Office: Word (.doc, .docx), Excel (.xls, .xlsx),
PowerPoint (.ppt, .pptx)
- EPUB (.epub)
- HTML (.html, .htm)
- Images (.jpg, .jpeg, .png) for OCR
- Audio (.mp3, .wav) for transcription
- Text-based formats (.csv, .json, .xml, .txt, .md)
- ZIP archives (.zip)

**Parameters:**

- **file_paths** (Union[str, List[str]]): A single file path or a list of file paths to read. Paths can be relative or absolute. If relative, they will be resolved relative to the working directory.

**Returns:**

  Union[str, Dict[str, str]]:
- If a single file path is provided: Returns the content as
a string.
- If multiple file paths are provided: Returns a dictionary
where keys are file paths and values are the corresponding
content in Markdown format.
If conversion fails, returns an error message.

<a id="camel.toolkits.file_toolkit.FileToolkit.edit_file"></a>

### edit_file

```python
def edit_file(
    self,
    file_path: str,
    old_content: str,
    new_content: str
):
```

Edit a file by replacing specified content.

This method performs simple text replacement in files. It reads
the file, replaces all occurrences of old_content with new_content,
and writes the result back.

**Parameters:**

- **file_path** (str): The path to the file to edit. Can be relative or absolute. If relative, it will be resolved relative to the working directory.
- **old_content** (str): The exact text to find and replace.
- **new_content** (str): The text to replace old_content with.

**Returns:**

  str: A success message if the edit was successful, or an
error message if the content wasn't found or an error occurred.

<a id="camel.toolkits.file_toolkit.FileToolkit.glob_files"></a>

### glob_files

```python
def glob_files(self, pattern: str, path: Optional[str] = None):
```

Find files by glob pattern and sort by modification time.

**Parameters:**

- **pattern** (str): Glob pattern to match, for example :obj:`**/*.js`.
- **path** (Optional[str]): Optional directory to search from. If not provided, the toolkit working directory is used.

**Returns:**

  Union[List[str], str]: Matching absolute file paths sorted by most
recent modification time first, or an error message.

<a id="camel.toolkits.file_toolkit.FileToolkit.grep_files"></a>

### grep_files

```python
def grep_files(
    self,
    pattern: str,
    path: str,
    glob_pattern: str = '*',
    file_type: Optional[str] = None,
    output_mode: str = 'content',
    ignore_case: bool = False,
    context_lines: int = 0,
    head_limit: int = 20,
    multiline: bool = False
):
```

Search file content with a regular expression.

**Parameters:**

- **pattern** (str): Regular expression to search for.
- **path** (str): Directory to search recursively.
- **glob_pattern** (str): Glob filter for candidate files before searching content. (default: :obj:`"*"`)
- **file_type** (Optional[str]): Optional file extension filter without requiring the leading dot. (default: :obj:`None`)
- **output_mode** (str): One of :obj:`content`, :obj:`files_with_matches`, or :obj:`count`. (default: :obj:`"content"`)
- **ignore_case** (bool): Whether to search case-insensitively. (default: :obj:`False`)
- **context_lines** (int): Number of surrounding lines to include when :obj:`output_mode` is :obj:`content`. (default: :obj:`0`)
- **head_limit** (int): Maximum number of blocks or file paths to return. (default: :obj:`20`)
- **multiline** (bool): Whether the regex may span multiple lines. (default: :obj:`False`)

**Returns:**

  Any: Matching content blocks, matching file paths, aggregate
counts, or an error string depending on :obj:`output_mode`.

<a id="camel.toolkits.file_toolkit.FileToolkit.notebook_edit_cell"></a>

### notebook_edit_cell

```python
def notebook_edit_cell(
    self,
    notebook_path: str,
    new_source: str = '',
    cell_id: Optional[str] = None,
    cell_type: Optional[str] = None,
    edit_mode: str = 'replace'
):
```

Edit, insert, or delete a cell in a Jupyter notebook.

**Parameters:**

- **notebook_path** (str): Absolute or working-directory-relative path to the notebook file.
- **new_source** (str): New source for the cell when inserting or replacing.
- **cell_id** (Optional[str]): Target cell ID. Required for replace and delete, and used as the insertion anchor when inserting.
- **cell_type** (Optional[str]): Cell type for inserted cells, or optional replacement cell type. Supported values are :obj:`code` and :obj:`markdown`.
- **edit_mode** (str): One of :obj:`replace`, :obj:`insert`, or :obj:`delete`.

**Returns:**

  str: Confirmation describing the notebook update, or an error
message.

<a id="camel.toolkits.file_toolkit.FileToolkit.search_files"></a>

### search_files

```python
def search_files(
    self,
    pattern: str,
    file_types: Optional[List[str]] = None,
    file_pattern: Optional[str] = None,
    path: Optional[str] = None
):
```

Search for a text pattern in files with specified extensions or
file patterns.

This method searches for a text pattern (case-insensitive substring
match) in files matching either the specified file types or a file
pattern. It returns structured results showing which files contain
the pattern, along with line numbers and matching content.

**Parameters:**

- **pattern** (str): The text pattern to search for (case-insensitive string match).
- **file_types** (Optional[List[str]]): List of file extensions to search (e.g., ["md", "txt", "py"]). Do not include the dot. If not provided and file_pattern is also not provided, defaults to ["md"] (markdown files). Ignored if file_pattern is provided. (default: :obj:`None`)
- **file_pattern** (Optional[str]): Glob pattern for matching files (e.g., "*_workflow.md", "test_*.py"). If provided, this overrides file_types. (default: :obj:`None`)
- **path** (Optional[str]): Directory to search in. If not provided, uses the working_directory. Can be relative or absolute. (default: :obj:`None`)

**Returns:**

  str: JSON-formatted string containing search results with the
structure:
`\{
"pattern": "search_pattern",
"searched_path": "/absolute/path",
"file_types": ["md", "txt"],
"file_pattern": "*_workflow.md",
"matches": [
\{
"file": "relative/path/to/file.md",
"line": 42,
"content": "matching line content"
\},
...
],
"total_matches": 10,
"files_searched": 5
\}`
If an error occurs, returns a JSON string with an "error" key.

<a id="camel.toolkits.file_toolkit.FileToolkit.get_tools"></a>

### get_tools

```python
def get_tools(self):
```

**Returns:**

  List[FunctionTool]: A list of FunctionTool objects representing
the available functions in this toolkit.