Ryan Malloy
31948d6ffc
Some checks are pending
Test Dashboard / test-and-dashboard (push) Waiting to run
Named for Milton Waddams, who was relocated to the basement with boxes of legacy documents. He handles the .doc and .xls files from 1997 that nobody else wants to touch. - Rename package from mcp-office-tools to mcwaddams - Update author to Ryan Malloy - Update all imports and references - Add Office Space themed README narrative - All 53 tests passing
95 lines
1.9 KiB
Python
95 lines
1.9 KiB
Python
"""Utility modules for MCP Office Tools."""
|
|
|
|
from .validation import (
|
|
OfficeFileError,
|
|
validate_office_file,
|
|
validate_office_path,
|
|
get_supported_extensions,
|
|
get_format_info,
|
|
detect_file_format,
|
|
is_url,
|
|
download_office_file
|
|
)
|
|
|
|
from .file_detection import (
|
|
detect_format,
|
|
classify_document_type
|
|
)
|
|
|
|
from .caching import (
|
|
OfficeFileCache,
|
|
get_cache,
|
|
resolve_office_file_path
|
|
)
|
|
|
|
from .decorators import (
|
|
resolve_field_defaults,
|
|
handle_office_errors
|
|
)
|
|
|
|
from .processing import (
|
|
TEMP_DIR,
|
|
DEBUG,
|
|
_extract_basic_metadata,
|
|
_calculate_health_score,
|
|
_get_health_recommendations,
|
|
_smart_truncate_content,
|
|
_parse_page_range,
|
|
_get_processing_recommendation,
|
|
)
|
|
|
|
from .word_processing import (
|
|
_extract_word_text,
|
|
_extract_word_images,
|
|
_extract_word_metadata,
|
|
_convert_docx_to_markdown,
|
|
_convert_docx_with_python_docx,
|
|
_convert_doc_to_markdown,
|
|
_get_ultra_fast_summary,
|
|
_find_bookmark_content_range,
|
|
_find_chapter_content_range,
|
|
_get_available_headings,
|
|
_has_page_break,
|
|
_analyze_document_size,
|
|
_paragraph_to_markdown,
|
|
_table_to_markdown,
|
|
_html_to_markdown,
|
|
_extract_markdown_structure,
|
|
)
|
|
|
|
from .excel_processing import (
|
|
_extract_excel_text,
|
|
_extract_excel_images,
|
|
_extract_excel_metadata,
|
|
)
|
|
|
|
from .powerpoint_processing import (
|
|
_extract_powerpoint_text,
|
|
_extract_powerpoint_images,
|
|
_extract_powerpoint_metadata,
|
|
)
|
|
|
|
__all__ = [
|
|
# Validation
|
|
"OfficeFileError",
|
|
"validate_office_file",
|
|
"validate_office_path",
|
|
"get_supported_extensions",
|
|
"get_format_info",
|
|
"detect_file_format",
|
|
"is_url",
|
|
"download_office_file",
|
|
|
|
# File detection
|
|
"detect_format",
|
|
"classify_document_type",
|
|
|
|
# Caching
|
|
"OfficeFileCache",
|
|
"get_cache",
|
|
"resolve_office_file_path",
|
|
|
|
# Decorators
|
|
"resolve_field_defaults",
|
|
"handle_office_errors"
|
|
] |