Api Endpoint

Arabic Text Repair for PDF and OCR Extraction

Repair Arabic text extracted from PDFs and OCR. Many PDFs encode Arabic as Unicode Presentation Forms: it renders identically but is a different byte sequence, so search and retrieval fail silently and invisibly. Also fixes visual-order reversal, invisible bidi controls, and Arabic-Indic digits that NFKC does not convert. Deterministic and lossless — encoding only, never wording. Essential for RAG pipelines ingesting Arabic documents.

Open interactive test console

Offering

Provider
bazaar-catalog.vercel.app
Method
GET
Offering type
Api Endpoint
Transport type
http
Category
General Utilities
Delivery
Not provided
Pricing model
Not provided
x402 version
2

Endpoint context

URL
https://bazaar-catalog.vercel.app/api/arabic/repair
MIME type
application/json
First seen
2026-10-16T02:59:31.787Z
Last seen
Tags
arabic, rtl, pdf, ocr, RAG, text-processing, unicode, normalization

Payment pricing

x402 payment terms are the authoritative price for calling this endpoint.

Payment option 1
0.02 USDC
Atomic price: 20000 · Network: eip155:8453 · Asset: USDC · Scheme: exact
Raw x402 terms
[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "20000",
    "payTo": "0x21353452E547B306a6007d834C433a118638D3b3"
  }
]

Observed health

Status
Healthy
Latest latency
55 ms
Average latency
62 ms
HTTP status
402
Last checked
Reachability
100% over 15 checks

Latency is measured to the first response headers. A reachable result does not verify response accuracy or merchant identity.

Input schema

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "const": "http"
    },
    "method": {
      "type": "string",
      "enum": [
        "GET"
      ]
    },
    "queryParams": {
      "type": "object",
      "properties": {
        "text": {
          "type": "string",
          "description": "Arabic text extracted from a PDF, OCR engine, or document parser (max 100,000 chars)"
        },
        "reverse": {
          "type": "string",
          "description": "Override visual-order detection: 'true' forces line reversal, 'false' prevents it. Omit for auto-detection."
        },
        "normalizeDigits": {
          "type": "string",
          "description": "Set 'false' to keep Arabic-Indic digits (٠-٩) instead of converting to ASCII. Default converts."
        }
      },
      "required": [
        "text"
      ]
    }
  },
  "required": [
    "type",
    "method"
  ],
  "additionalProperties": false
}

Output schema

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string"
    },
    "example": {
      "type": "object"
    }
  },
  "required": [
    "type"
  ]
}