Abimael MartellandClaude Opus 4.6
506b2a0c70
Both bindings now expose the same 6 function families: process, detect, classify, extractText, extractTextWithPositions, and extractTextInRegions. Bumps PyO3 from 0.22 to 0.25 for Python 3.14 support. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
118 lines
3.2 KiB
Python
118 lines
3.2 KiB
Python
"""Type stubs for pdf_inspector."""
|
|
|
|
from typing import Optional
|
|
|
|
class PdfResult:
|
|
"""Result of processing a PDF file."""
|
|
pdf_type: str
|
|
"""'text_based', 'scanned', 'image_based', or 'mixed'."""
|
|
markdown: Optional[str]
|
|
page_count: int
|
|
processing_time_ms: int
|
|
pages_needing_ocr: list[int]
|
|
title: Optional[str]
|
|
confidence: float
|
|
is_complex_layout: bool
|
|
pages_with_tables: list[int]
|
|
pages_with_columns: list[int]
|
|
has_encoding_issues: bool
|
|
|
|
class PdfClassification:
|
|
"""Lightweight PDF classification result."""
|
|
pdf_type: str
|
|
"""'text_based', 'scanned', 'image_based', or 'mixed'."""
|
|
page_count: int
|
|
pages_needing_ocr: list[int]
|
|
"""0-indexed page numbers that need OCR."""
|
|
confidence: float
|
|
|
|
class TextItem:
|
|
"""A positioned text item extracted from a PDF."""
|
|
text: str
|
|
x: float
|
|
y: float
|
|
width: float
|
|
height: float
|
|
font: str
|
|
font_size: float
|
|
page: int
|
|
is_bold: bool
|
|
is_italic: bool
|
|
item_type: str
|
|
|
|
class RegionText:
|
|
"""Extracted text for a single region."""
|
|
text: str
|
|
needs_ocr: bool
|
|
"""True when the text should not be trusted."""
|
|
|
|
class PageRegionTexts:
|
|
"""Extracted text for one page's regions."""
|
|
page: int
|
|
"""0-indexed page number."""
|
|
regions: list[RegionText]
|
|
|
|
def process_pdf(path: str, pages: Optional[list[int]] = None) -> PdfResult:
|
|
"""Process a PDF: detect type, extract text, convert to Markdown."""
|
|
...
|
|
|
|
def process_pdf_bytes(data: bytes, pages: Optional[list[int]] = None) -> PdfResult:
|
|
"""Process a PDF from bytes in memory."""
|
|
...
|
|
|
|
def detect_pdf(path: str) -> PdfResult:
|
|
"""Fast detection only — no text extraction."""
|
|
...
|
|
|
|
def detect_pdf_bytes(data: bytes) -> PdfResult:
|
|
"""Fast detection from bytes."""
|
|
...
|
|
|
|
def classify_pdf(path: str) -> PdfClassification:
|
|
"""Lightweight classification — type, page count, and OCR pages (0-indexed)."""
|
|
...
|
|
|
|
def classify_pdf_bytes(data: bytes) -> PdfClassification:
|
|
"""Lightweight classification from bytes."""
|
|
...
|
|
|
|
def extract_text(path: str) -> str:
|
|
"""Extract plain text from a PDF."""
|
|
...
|
|
|
|
def extract_text_bytes(data: bytes) -> str:
|
|
"""Extract plain text from PDF bytes."""
|
|
...
|
|
|
|
def extract_text_with_positions(path: str, pages: Optional[list[int]] = None) -> list[TextItem]:
|
|
"""Extract text with position information."""
|
|
...
|
|
|
|
def extract_text_with_positions_bytes(data: bytes, pages: Optional[list[int]] = None) -> list[TextItem]:
|
|
"""Extract text with position information from bytes."""
|
|
...
|
|
|
|
def extract_text_in_regions(
|
|
path: str,
|
|
page_regions: list[tuple[int, list[list[float]]]],
|
|
) -> list[PageRegionTexts]:
|
|
"""Extract text within bounding-box regions from a PDF file.
|
|
|
|
Args:
|
|
path: Path to the PDF file.
|
|
page_regions: List of (page_0indexed, [[x1, y1, x2, y2], ...]) tuples.
|
|
"""
|
|
...
|
|
|
|
def extract_text_in_regions_bytes(
|
|
data: bytes,
|
|
page_regions: list[tuple[int, list[list[float]]]],
|
|
) -> list[PageRegionTexts]:
|
|
"""Extract text within bounding-box regions from PDF bytes.
|
|
|
|
Args:
|
|
data: PDF file contents as bytes.
|
|
page_regions: List of (page_0indexed, [[x1, y1, x2, y2], ...]) tuples.
|
|
"""
|
|
...
|