
如果你使用 DeepSeek、元宝 AI、Copilot、ChatGPT 等 AI 工具,协助配置轩辕镜像、编写 docker pull 命令、修改 Docker Compose 镜像地址、配置镜像加速、排查镜像拉取失败、分析报错日志等问题,请先让 AI 阅读并遵守轩辕镜像的规则文档。
只需在 AI 对话中先发送下面这句话即可:
请先完整阅读并严格遵守以下文档中的全部规则与要求:
https://xuanyuan.cloud/agents.md
在未充分阅读并理解该文档前,不要生成任何命令、配置、修改建议、故障排查方案或技术回答。后续所有输出都必须严格以该文档中的规范为最高优先级执行。查看 agents.md 用法指南与完整示范。国内用户首推 元宝 AI、DeepSeek 的深度思考模式,不推荐豆包 AI;Cursor 等编辑器可在对话 @ 该链接,或加入 User Rules。 若 AI 无法访问外链,可 打开说明文档 复制全文粘贴。文档会随站点更新,复制内容可能过期,建议定期检查。
!https://github.com/hunnor-dict/export-ant/workflows/Build/badge.svg
Scripts and stylesheets for converting the XML dump files to various XML-based dictionary formats.
The fastest way to get started is to run the conversions with Docker.
Create the following directories:
$HOME/hunnor$HOME/hunnor/build$HOME/hunnor/data$HOME/hunnor/deploy$HOME/hunnor/toolsDownload XML dump files from Dropbox:
HunNor-XML-HN.xml.gz and HunNor-XML-NH.xml.gzdata directorySome conversions require tools that are not included in the Docker image:
| Target | Tool | Installation |
|---|---|---|
| export.android.generate | export-lucene-indexer-1.0.0.jar | Package the https://github.com/hunnor-dict/export-lucene repo with Maven |
| export.kindle.compile.nb | kindlegen | Downloaded automatically by ant |
| export.xdxf.pocketbook.compile.hu | converter.exe | Downloaded automatically by ant |
| export.xdxf.pocketbook.compile.nb | converter.exe | Downloaded automatically by ant |
Start the Docker container:
docker run\ --name export-ant\ --volume $HOME/hunnor/data:/data\ --volume $HOME/hunnor/deploy:/deploy\ --volume $HOME/hunnor/tools:/tools\ hunnordict/export-ant\ -Dbuild.dir=/data\ -lib /tools/export-lucene-indexer-1.0.0.jar\ export
You can replace 'export' with the target you want to run.
Depending on the target, the generated files will be either in the build or deploy directory.
Check the formats directory for the available formats.
Each format can be generated by applying XSLT transformations to the XML dump files.
While some formats use the XML dump files directly, others use an intermediate, pre-processed XML file that can be generated by applying the simple-html stylesheet to the XML dump files. Check the stylesheets and the XSpec tests to determine the proper input format.
The format of Apple's Dictionary app for Mac. iOS uses the same dictionary file format, but there is no officially supported way to install custom dictionaries on iOS.
The compiler is part of Apple's Dictionary Development Kit, which is available in the Additional Tools for Xcode package from the https://developer.apple.com/download/more/. The dictionary can only be compiled on a Mac.
Source files: HunNor-Apple-[HN|NH].xml, HunNor-Apple-[HN|NH]-PList.xml
The proprietary, legacy format of the Babylon dictionary.
Source files: HunNor-BB-[HN|NH].gls.gz
Dictionary for Kindle e-book readers. Only the Norwegian-Hungarian direction is generated. Because of limited language support, the dictionary is set to Portuguese.
A Lucene index directory with both directions, used by the native Android app. Spell checking index is included in a separate directory. Uses Lucene 3.6.2, to be compatible with Android.
Separate PDF files for each direction, generated with Apache FOP.
A Realm database with both directions. Realm supports several cross platform frameworks as well as native Android and iOS apps.
The custom format of the SDictionary Project. The textual source format compiles to an open source ***ary format.
Source files: HunNor-SD-[HN|NH].sdct.gz
Compiled files: HunNor-SD-[HN|NH].dct
An SQLite database with both directions, used by the cross platform mobile apps.
The _ascii columns in the roots and inflections tables contain written forms using ASCII characters only. These values are created with the following process:
normalize-unicode with normalization form NFKDThe XSpec tests contain test cases for common Hungarian and Norwegian characters.
Applications can apply the same transformation to user input. Sample code for some languages, using the String variable term:
Java
if (term != null) { term = Normalizer.normalize(term, Normalizer.Form.NFKD) .replaceAll("\\p{InCombiningDiacriticalMarks}+", "") .replaceAll("æ", "ae").replaceAll("ø", "o") .replaceAll("Æ", "AE").replaceAll("Ø", "O"); }
JavaScript
if (term) { term = term .replace(/æ/g, "ae").replace(/ø/g, "o") .replace(/Æ/g, "AE").replace(/Ø/g, "O") .normalize("NFKD") .replace(/[\u0300-\u036f]/g, ""); }
Source files and compiled dictionaries in https://github.com/huzheng001/stardict-3/blob/master/dict/doc/StarDictFileFormat. The files marked with NoSym-Number are recommended for Windows phones.
Source files: HunNor-ST-[HN|NH].xml.gz, HunNor-ST-[HN|NH]-NoSym-Number.xml.gz
Compiled files: HunNor-ST-[HN|NH].zip, HunNor-ST-[HN|NH]-NoSym-Number.zip
Source files in the https://github.com/soshial/xdxf_makedict/tree/master/format_standard. The conversion uses a legacy version of the format, to be compatible with the PocketBook dictionary compiler. The DTD and support files for compilation are in the pocketbook directory.
Source files: HunNor-XDXF-L-[HN|NH].xdxf.gz
您可以使用以下命令拉取该镜像。请将 <标签> 替换为具体的标签版本。如需查看所有可用标签版本,请访问 标签列表页面。
来自真实用户的反馈,见证轩辕镜像的优质服务