WFGY/ProblemMap/GlobalFixMap/OCR_Parsing/multi_language_and_fonts.md

Multi-language and Fonts: OCR Parsing Guardrails

Stabilize OCR when documents mix scripts, uncommon fonts, or character sets. Prevent silent corruption when engines guess wrong language or merge glyphs across font families.

Open these first

• OCR parsing checklist: ocr-parsing-checklist.md
• Data contracts: data-contracts.md
• Tokenization and casing: tokenization_and_casing.md
• Unicode normalization: normalization_and_scaling.md

Acceptance targets

• Language detection accuracy ≥ 0.95 per block
• Font mis-read rate < 1% per 1,000 chars
• No cross-script merges (CJK vs Latin, RTL vs LTR)
• ΔS(question, retrieved) ≤ 0.45 after language split

---

Typical failure signatures → fix

• CJK vs Latin collisions
  OCR merges Latin letters inside Chinese/Japanese text. Split into script-specific blocks, then re-OCR with correct language model.

• Right-to-left scripts (Arabic, Hebrew) misaligned
  Store direction=rtl metadata. Reverse tokens if engine defaults to LTR.

• Uncommon fonts or stylized typefaces
  Preprocess with font normalization (convert to system fonts). Use OCR engine with adaptive recognition.

• Mixed languages in same paragraph
  Detect language per line or span. Store lang_code for each.

• Math vs text confusion
  Superscripts, subscripts, and symbols misinterpreted as language characters. Route math zones separately. Tag as math_block.

---

Fix in 60 seconds

1. Detect language per block
   Run script detection. Assign lang_code and direction. Reject ambiguous blocks.

2. Normalize Unicode
   Apply NFKC, collapse ligatures, unify spacing.

3. Re-OCR with correct model
   For each block, call OCR with explicit lang_code. Prefer specialized models (e.g., PaddleOCR multilingual, ABBYY).

4. Attach metadata
   Store lang_code, direction, font_name if available.

5. Audit with ΔS
   Probe retrieval stability with three paraphrases. If ΔS ≥ 0.60, recheck font normalization.

---

Data contract extension

{
"block\_id": "scan12\_line4",
"lang\_code": "zh",
"direction": "ltr",
"font\_name": "SimSun",
"text\_clean": "...",
"confidence": 0.93,
"source\_url": "..."
}

---

Minimal recipes by engine

• Google Document AI
  Use detectedLanguages.languageCode per block. Reject if confidence < 0.8.

• AWS Textract
  No native multi-lang. Wrap with external script detection. Add lang_code manually.

• Azure OCR
  language field auto-detected. Cross-check with Unicode ranges.

• ABBYY
  Supports per-block language tags. Ensure config has all needed languages.

• PaddleOCR
  Use multilingual model. Explicitly set --lang flag to avoid mis-guess.

---

Verification

• Script coverage: verify all scripts recognized.
• Direction check: RTL blocks labeled correctly.
• Font audit: ensure no decorative font corruption.
• Retrieval stability: ΔS stable across paraphrases.

---

Copy-paste LLM prompt

You have TXTOS and WFGY Problem Map loaded.

My OCR block:

* text\_clean: "..."
* lang\_code: "ar"
* direction: "rtl"
* font\_name: "Courier"

Check:

1. If characters look corrupted, fail fast and cite fix page.
2. Enforce schema with lang\_code and direction.
3. Return JSON: { "answer":"...", "citations":\[...], "ΔS":0.xx, "λ\_state":"..." }

---

🔗 Quick-Start Downloads (60 sec)

Tool	Link	3-Step Setup
WFGY 1.0 PDF	Engine Paper	1️⃣ Download · 2️⃣ Upload to your LLM · 3️⃣ Ask “Answer using WFGY + <your question>”
TXT OS (plain-text OS)	TXTOS.txt	1️⃣ Download · 2️⃣ Paste into any LLM chat · 3️⃣ Type “hello world” — OS boots instantly

---

🧭 Explore More

Module	Description	Link
WFGY Core	WFGY 2.0 engine is live: full symbolic reasoning architecture and math stack	View →
Problem Map 1.0	Initial 16-mode diagnostic and symbolic fix framework	View →
Problem Map 2.0	RAG-focused failure tree, modular fixes, and pipelines	View →
Semantic Clinic Index	Expanded failure catalog: prompt injection, memory bugs, logic drift	View →
Semantic Blueprint	Layer-based symbolic reasoning & semantic modulations	View →
Benchmark vs GPT-5	Stress test GPT-5 with full WFGY reasoning suite	View →
🧙‍♂️ Starter Village 🏡	New here? Lost in symbols? Click here and let the wizard guide you through	Start →

---

👑 Early Stargazers: See the Hall of Fame —
⭐ WFGY Engine 2.0 is already unlocked. ⭐ Star the repo to help others discover it and unlock more on the Unlock Board.