{"uid":"cap_8Hsh5k7x0688cowLglXpz","slug":"duo-data-utilities-unicode-analysis-3a39265b","name":"Duo Data Utilities – Unicode Analysis","description":"Analyse a string at the Unicode level: apply NFC, NFD, NFKC or NFKD, report which forms it is already in, list the scripts present (all Unicode scripts), and flag confusable and homoglyph characters — Cyrillic а in a Latin word, fullwidth or mathematical look-alikes, all-look-alike words — plus zero-width joiners, bidirectional overrides, invisible and blank characters. Returns per-character detail with code points, names and the ASCII character each imitates.","url":"https://api.duoleads.com/v1/text/unicode?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["text"],"properties":{"form":{"enum":["nfc","nfd","nfkc","nfkd"],"type":"string","default":"nfc","maxLength":64,"description":"Normalisation form to apply, default nfc."},"text":{"type":"string","maxLength":1024,"description":"Text to analyse, at most 1024 characters."},"detail":{"enum":["summary","full"],"type":"string","default":"summary","maxLength":64,"description":"summary (default) or full per-code-point detail (capped at 256 entries)."}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["ok","route","version","data","meta"],"properties":{"ok":{"const":true},"data":{"type":"object","required":["normalised","form","already_normalised","lengths","scripts","mixed_script","suspicious","ascii_safe"],"properties":{"form":{"type":"string"},"lengths":{"type":"object","required":["code_points","graphemes","utf8_bytes","utf16_units"],"properties":{"graphemes":{"type":"integer"},"utf8_bytes":{"type":"integer"},"code_points":{"type":"integer"},"utf16_units":{"type":"integer"}}},"scripts":{"type":"array","items":{"type":"string"}},"ascii_safe":{"type":"boolean"},"characters":{"type":"array","items":{"type":"object","required":["index","char","code_point","name","category","script"],"properties":{"char":{"type":"string"},"name":{"type":["string","null"]},"index":{"type":"integer"},"script":{"type":["string","null"]},"category":{"type":"string"},"code_point":{"type":"string"}}}},"normalised":{"type":"string"},"suspicious":{"type":"array","items":{"type":"object","required":["index","char","code_point","name","category","kind","looks_like"],"properties":{"char":{"type":"string"},"kind":{"type":"string"},"name":{"type":["string","null"]},"index":{"type":"integer"},"category":{"type":"string"},"code_point":{"type":"string"},"looks_like":{"type":["string","null"]}}}},"mixed_script":{"type":"boolean"},"already_normalised":{"type":"object","required":["nfc","nfd","nfkc","nfkd"],"properties":{"nfc":{"type":"boolean"},"nfd":{"type":"boolean"},"nfkc":{"type":"boolean"},"nfkd":{"type":"boolean"}}},"characters_truncated":{"type":"boolean"}}},"meta":{"type":"object","required":["request_id","computed_at","price_usd","deterministic","disclaimer"],"properties":{"sources":{"type":"array","items":{"type":"object","required":["id","version","published"]}},"price_usd":{"type":"string"},"disclaimer":{"type":"string"},"request_id":{"type":"string"},"computed_at":{"type":"string","description":"RFC 3339 UTC with milliseconds"},"deterministic":{"type":"boolean"}}},"route":{"const":"/v1/text/unicode"},"version":{"type":"string"}}}}}}},"responseSchema":{"type":"json","example":{"ok":true,"data":{"form":"nfd","lengths":{"graphemes":4,"utf8_bytes":6,"code_points":5,"utf16_units":5},"scripts":["Latin"],"ascii_safe":false,"normalised":"café","suspicious":[],"mixed_script":false,"already_normalised":{"nfc":true,"nfd":false,"nfkc":true,"nfkd":false}},"meta":{"sources":[{"id":"unicode-confusables","licence":"Unicode License v3","version":"18.0.0","published":"2026-08-06","attribution":"Unicode confusables.txt (UTS #39), (c) Unicode, Inc."}],"price_usd":"0.05","disclaimer":"Factual output of a deterministic computation over public data. Provided as is, with no warranty of accuracy, completeness or availability. Not investment, financial, legal, tax, medical or any other professional advice, and not a recommendation. Verify before relying on it. Terms: https://api.duoleads.com/terms","request_id":"01K6B7Q4ZC8H3F2M9WXR5TYN0D","computed_at":"2026-09-28T12:00:00.000Z","deterministic":true},"route":"/v1/text/unicode","version":"1.0.0"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.05","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.05/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_3XSEkJ20D4zfpyzKvgnn_","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.05","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Analyses a string at the Unicode level: applies NFC/NFD/NFKC/NFKD normalisation, reports which forms the string is already in, lists scripts present, and flags confusable, homoglyph, invisible, and bidirectional-override characters with per-character detail.","exampleAgentPrompt":"Can you analyse the string 'pаypal.com' for hidden confusable or homoglyph characters — I want to know if any Cyrillic or other non-Latin characters are sneaking in — and give me the full per-character detail including code points?","exampleUseCases":[{"title":"Detect spoofed username at registration","prompt":"A new user just signed up with the display name 'Аdmin' — can you check it for confusable or homoglyph characters and tell me whether any characters are Cyrillic or otherwise impersonating ASCII letters?"},{"title":"Normalise user input before database storage","prompt":"Before I store this user-submitted text in the database, normalise it to NFC form and tell me whether it was already NFC-normalised, and how many graphemes and UTF-8 bytes it contains."},{"title":"Audit a suspicious URL for Unicode trickery","prompt":"This URL looks weird to me: 'https://microsоft.com' — can you run it through full Unicode analysis to find any bidirectional overrides, invisible characters, or zero-width joiners hiding in it?"}],"resultDescription":"Returns a JSON object with the normalised string, grapheme/code-point/UTF-8 byte/UTF-16 unit counts, a list of scripts present, boolean flags for ASCII-safety and mixed-script, which normalisation forms the input already satisfies, and an array of suspicious characters each containing its code point, Unicode name, and the ASCII character it imitates.","failureModes":["Missing required 'text' query parameter returns a 400 error","Text exceeding 1024 characters is rejected","Invalid 'form' enum value (not nfc/nfd/nfkc/nfkd) returns a 400 error","Invalid 'detail' enum value returns a 400 error","Payment not provided or insufficient for the $0.05 USDC x402 charge returns a 402 response","Network timeout or 5xx on provider side"],"whenToPreferThis":"Choose this endpoint when you need to detect Unicode-based spoofing, homoglyph attacks, or invisible/control characters in user-supplied strings — especially usernames, domain names, URLs, or any text where look-alike characters could be exploited. Prefer it over generic string-processing tools when you need simultaneous normalisation, script enumeration, and confusable-character flagging in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-02T00:46:19.052Z","isFirstParty":false,"canonicalSlug":"duo-data-utilities-unicode-analysis-3a39265b"}