Metadata-Version: 2.5
Name: titanocr
Version: 0.0.1
Summary: TitanOCR — deterministic, CPU-first OCR + document-structure engine. Name reservation; the engine release is in progress.
Project-URL: Homepage, https://github.com/Phantom-IN/titanocr
Project-URL: Repository, https://github.com/Phantom-IN/titanocr
Author: TitanOCR
License-Expression: Apache-2.0
Keywords: document-ai,layout-analysis,ocr,pdf,table-extraction
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Classifier: Topic :: Text Processing
Requires-Python: >=3.9
Description-Content-Type: text/markdown

# TitanOCR

**This release is a name reservation. It contains no OCR code yet.**

TitanOCR is a standalone, general-purpose OCR and document-structure engine: give it any PDF or
image — born-digital, scanned, or phone-photographed; printed, hybrid, or handwritten — and it
returns faithful text and structure with pixel-level provenance. Every value carries its page,
bounding box, origin and confidence. Deterministic, auditable, and **CPU-only** on the primary
path; a vision model is a budgeted escalation for what CPU OCR cannot yet read confidently, never
the default.

The engine is being finished at **https://github.com/Phantom-IN/titanocr**, and will be published
here as version 0.1.0 or later. Until then:

```python
import titanocr

titanocr.IS_PLACEHOLDER  # True — this is the reservation, not the engine
```

When the real release lands, `pip install --upgrade titanocr` replaces this placeholder.

Licensed under Apache-2.0.
