{"id":147635,"date":"2025-11-07T17:12:02","date_gmt":"2025-11-07T15:12:02","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/google-opublikoval-magika-1-0-instrumentarij-dlya-opredeleniya-tipa-soderzhimogo-fajlov"},"modified":"2026-02-26T20:20:26","modified_gmt":"2026-02-26T18:20:26","slug":"google-opublikoval-magika-1-0-instrumentarij-dlya-opredeleniya-tipa-soderzhimogo-fajlov","status":"publish","type":"post","link":"https:\/\/prohoster.info\/pt\/blog\/news\/google-opublikoval-magika-1-0-instrumentarij-dlya-opredeleniya-tipa-soderzhimogo-fajlov","title":{"rendered":"O Google publicou o Magika 1.0, uma ferramenta para determinar o tipo de conte\u00fado de arquivos","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p>A Google apresentou o lan\u00e7amento da ferramenta Magika 1.0, destinada a determinar o tipo de conte\u00fado com base na an\u00e1lise dos dados dispon\u00edveis no arquivo. O Magika pode identificar com precis\u00e3o as linguagens de programa\u00e7\u00e3o, m\u00e9todos de compress\u00e3o, pacotes de instala\u00e7\u00e3o, c\u00f3digo execut\u00e1vel, tipos de marca\u00e7\u00e3o, formatos de \u00e1udio, v\u00eddeo, documentos e imagens utilizados no conte\u00fado. A ferramenta relacionada ao projeto e o modelo de aprendizado de m\u00e1quina est\u00e3o dispon\u00edveis sob a licen\u00e7a Apache 2.0. As liga\u00e7\u00f5es foram preparadas para as linguagens Rust, Python, JavaScript\/TypeScript e Go.       <\/p>\n<p>Diferente de projetos semelhantes que determinam o tipo MIME com base no conte\u00fado, o Magika se destaca ao aplicar m\u00e9todos de aprendizado de m\u00e1quina, <a href=\"https:\/\/prohoster.info\/pt\/server\/\"  data-wpil-monitor-id=\"4017\">mais alto<\/a> e precis\u00e3o na identifica\u00e7\u00e3o. O modelo foi treinado usando o framework Keras com 100 milh\u00f5es de exemplos de arquivos (o tamanho do conjunto de dados \u00e9 superior a 3 TB) e suporta o reconhecimento de 200 tipos de dados com precis\u00e3o de pelo menos 99%. O modelo est\u00e1 empacotado no formato ONNX e tem apenas alguns megabytes. A utiliza\u00e7\u00e3o de m\u00e9todos de aprendizado de m\u00e1quina profundo permitiu aumentar em 50% a precis\u00e3o da determina\u00e7\u00e3o em compara\u00e7\u00e3o com o sistema anteriormente utilizado pelo Google, que era baseado em regras definidas manualmente.      <\/p>\n<p>No Google, o sistema \u00e9 utilizado para classificar arquivos nos servi\u00e7os Gmail, Drive, Code Insight e Safe Browsing durante a execu\u00e7\u00e3o de verifica\u00e7\u00f5es de seguran\u00e7a e conformidade com as regras dos servi\u00e7os. A integra\u00e7\u00e3o do Magika \u00e9 garantida nas plataformas VirusTotal e abuse.ch como um elo para a filtragem prim\u00e1ria de arquivos antes da execu\u00e7\u00e3o de analisadores espec\u00edficos. A configura\u00e7\u00e3o do Magika implantada na infraestrutura do Google permite a varredura de v\u00e1rios milh\u00f5es de arquivos por segundo e centenas de bilh\u00f5es de arquivos por semana. Ap\u00f3s o carregamento do modelo, o tempo de gera\u00e7\u00e3o de sa\u00edda \u00e9 de 5 ms ao ser testado em um \u00fanico n\u00facleo de CPU. O tempo de determina\u00e7\u00e3o quase n\u00e3o depende do tamanho do arquivo.    <\/p>\n<p>Para integrar o Magika em seus projetos, foram preparadas uma ferramenta de linha de comando, pacotes para Python, Rust e Go, al\u00e9m de uma biblioteca JavaScript que pode funcionar no navegador ou em projetos baseados em Node.js. A interface de linha de comando e a API suportam a execu\u00e7\u00e3o de opera\u00e7\u00f5es em modo batch, ou seja, permitem verificar v\u00e1rios arquivos em uma \u00fanica solicita\u00e7\u00e3o. H\u00e1 um modo de varredura recursiva em todo o conte\u00fado do diret\u00f3rio e tr\u00eas modos de previs\u00e3o para ajustar a resist\u00eancia a erros (alta confian\u00e7a, m\u00e9dia confian\u00e7a e melhor palpite).       <\/p>\n<p>Inicialmente, o projeto foi desenvolvido em Python, mas ao preparar o lan\u00e7amento da vers\u00e3o 1.0, o motor de identifica\u00e7\u00e3o de tipos de conte\u00fado foi reescrito em Rust, permitindo alcan\u00e7ar um desempenho mais alto, mantendo um n\u00edvel adequado de seguran\u00e7a no c\u00f3digo. Para a execu\u00e7\u00e3o do modelo de aprendizado de m\u00e1quina, foi utilizado o framework ONNX Runtime, e para o processamento ass\u00edncrono paralelo de solicita\u00e7\u00f5es \u2014 a biblioteca Tokio. No MacBook Pro (M4), o desempenho do motor permite processar cerca de 1000 arquivos por segundo.      <\/p>\n<p>Al\u00e9m do novo mecanismo, as mudan\u00e7as no lan\u00e7amento 1.0 incluem a amplia\u00e7\u00e3o do n\u00famero de tipos suportados de aproximadamente 100 para 200; a adi\u00e7\u00e3o de um novo cliente de linha de comando, escrito em Rust; aumento da precis\u00e3o na determina\u00e7\u00e3o de formatos de texto, como arquivos de configura\u00e7\u00e3o e c\u00f3digo; e a reestrutura\u00e7\u00e3o dos m\u00f3dulos para Python e TypeScript para facilitar sua integra\u00e7\u00e3o com outros projetos. Entre os novos tipos de conte\u00fado suportados est\u00e3o: formatos utilizados em aprendizado de m\u00e1quina e IA; linguagens de programa\u00e7\u00e3o Swift, Kotlin, TypeScript, Dart, Solidity (solidity), Web Assembly e Zig; componentes de DevOps (Dockerfiles, TOML, HashiCorp, arquivos de build Bazel e regras YARA); banco de dados SQLite; arquivos AutoCAD (dwg, dxf), Adobe Photoshop (psd) e fontes (woff, woff2). A separa\u00e7\u00e3o de c\u00f3digo em C++ e C, JavaScript e TypeScript foi aprimorada.<br \/>\n<br \/>Fonte: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/www.opennet.ru\/opennews\/art.shtml?num=64201\">opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Google \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u0440\u0435\u043b\u0438\u0437 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u044f Magika 1.0, \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d\u043d\u043e\u0433\u043e \u0434\u043b\u044f \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u0442\u0438\u043f\u0430 \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u043c\u043e\u0433\u043e \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u0430\u043d\u0430\u043b\u0438\u0437\u0430 \u0438\u043c\u0435\u044e\u0449\u0438\u0445\u0441\u044f \u0432 \u0444\u0430\u0439\u043b\u0435 \u0434\u0430\u043d\u043d\u044b\u0445. Magika \u043c\u043e\u0436\u0435\u0442 \u0442\u043e\u0447\u043d\u043e \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u044f\u0442\u044c \u0432 \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u043c\u043e\u043c \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u043c\u044b\u0435 \u044f\u0437\u044b\u043a\u0438 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f, \u043c\u0435\u0442\u043e\u0434\u044b \u0441\u0436\u0430\u0442\u0438\u044f, \u0443\u0441\u0442\u0430\u043d\u043e\u0432\u043e\u0447\u043d\u044b\u0435 \u043f\u0430\u043a\u0435\u0442\u044b, \u0438\u0441\u043f\u043e\u043b\u043d\u044f\u0435\u043c\u044b\u0439 \u043a\u043e\u0434, \u0432\u0438\u0434\u044b \u0440\u0430\u0437\u043c\u0435\u0442\u043a\u0438, \u0444\u043e\u0440\u043c\u0430\u0442\u044b \u0437\u0432\u0443\u043a\u0430, \u0432\u0438\u0434\u0435\u043e, \u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u043e\u0432 \u0438 \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0439. \u0421\u0432\u044f\u0437\u0430\u043d\u043d\u044b\u0439 \u0441 \u043f\u0440\u043e\u0435\u043a\u0442\u043e\u043c \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0439 \u0438 \u0433\u043e\u0442\u043e\u0432\u0430\u044f \u043c\u043e\u0434\u0435\u043b\u044c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0440\u0430\u0441\u043f\u0440\u043e\u0441\u0442\u0440\u0430\u043d\u044f\u044e\u0442\u0441\u044f \u043f\u043e\u0434 \u043b\u0438\u0446\u0435\u043d\u0437\u0438\u0435\u0439 Apache [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-147635","post","type-post","status-publish","format-standard","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.3 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Google \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u0440\u0435\u043b\u0438\u0437 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u044f Magika 1.0, \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d\u043d\u043e\u0433\u043e \u0434\u043b\u044f \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u0442\u0438\u043f\u0430 \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u043c\u043e\u0433\u043e \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u0430\u043d\u0430\u043b\u0438\u0437\u0430 \u0438\u043c\u0435\u044e\u0449\u0438\u0445\u0441\u044f \u0432 \u0444\u0430\u0439\u043b\u0435 \u0434\u0430\u043d\u043d\u044b\u0445.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/pt\/blog\/news\/google-opublikoval-magika-1-0-instrumentarij-dlya-opredeleniya-tipa-soderzhimogo-fajlov\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.3\" \/>\n\t\t<meta property=\"og:locale\" content=\"pt_PT\" \/>\n\t\t<meta property=\"og:site_name\" content=\"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47Google \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b Magika 1.0, \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0439 \u0434\u043b\u044f \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u0442\u0438\u043f\u0430 \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u043c\u043e\u0433\u043e \u0444\u0430\u0439\u043b\u043e\u0432 | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Google \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u0440\u0435\u043b\u0438\u0437 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u044f Magika 1.0, \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d\u043d\u043e\u0433\u043e \u0434\u043b\u044f \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u0442\u0438\u043f\u0430 \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u043c\u043e\u0433\u043e \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u0430\u043d\u0430\u043b\u0438\u0437\u0430 \u0438\u043c\u0435\u044e\u0449\u0438\u0445\u0441\u044f \u0432 \u0444\u0430\u0439\u043b\u0435 \u0434\u0430\u043d\u043d\u044b\u0445.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/pt\/blog\/news\/google-opublikoval-magika-1-0-instrumentarij-dlya-opredeleniya-tipa-soderzhimogo-fajlov\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2025-11-07T15:12:02+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2026-02-26T18:20:26+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47Google lan\u00e7ou Magika 1.0, uma ferramenta para determinar o tipo de conte\u00fado de arquivos | ProHoster","description":"A Google lan\u00e7ou a vers\u00e3o 1.0 da ferramenta Magika, projetada para determinar o tipo de conte\u00fado com base na an\u00e1lise dos dados contidos em um arquivo.","canonical_url":"https:\/\/prohoster.info\/pt\/blog\/news\/google-opublikoval-magika-1-0-instrumentarij-dlya-opredeleniya-tipa-soderzhimogo-fajlov","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"pt_PT","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47Google \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b Magika 1.0, \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0439 \u0434\u043b\u044f \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u0442\u0438\u043f\u0430 \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u043c\u043e\u0433\u043e \u0444\u0430\u0439\u043b\u043e\u0432 | ProHoster","og:description":"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Google \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u0440\u0435\u043b\u0438\u0437 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u044f Magika 1.0, \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d\u043d\u043e\u0433\u043e \u0434\u043b\u044f \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u0442\u0438\u043f\u0430 \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u043c\u043e\u0433\u043e \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u0430\u043d\u0430\u043b\u0438\u0437\u0430 \u0438\u043c\u0435\u044e\u0449\u0438\u0445\u0441\u044f \u0432 \u0444\u0430\u0439\u043b\u0435 \u0434\u0430\u043d\u043d\u044b\u0445.","og:url":"https:\/\/prohoster.info\/pt\/blog\/news\/google-opublikoval-magika-1-0-instrumentarij-dlya-opredeleniya-tipa-soderzhimogo-fajlov","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2025-11-07T15:12:02+00:00","article:modified_time":"2026-02-26T18:20:26+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"147635","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-02-26 18:21:29","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2026-01-23 15:49:19","updated":"2026-02-26 18:21:29","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts\/147635","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/comments?post=147635"}],"version-history":[{"count":1,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts\/147635\/revisions"}],"predecessor-version":[{"id":162834,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts\/147635\/revisions\/162834"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/media?parent=147635"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/categories?post=147635"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/tags?post=147635"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}