mirror of
https://git.openapi.site/https://github.com/desirecore/market.git
synced 2026-06-06 06:50:42 +08:00
feat: skills i18n 改造（schemaVersion 1.1，零向后兼容） (#1)
* feat: skills i18n 改造 — schemaVersion 1.1，零向后兼容
把 21 个 skills + 1 个 agent + manifest/categories 全量迁移到 schemaVersion 1.1
的 i18n 结构，配套 CI AI 翻译流水线（GitHub Models）与本地工具链。
## 关键变更
### 数据结构（破坏性，schemaVersion 1.0 → 1.1）
- SKILL.md: 顶层 name 改为 ASCII slug（== 目录名，符合 agentskills.io 规范）；
中文显示名/short_desc/description 全部迁入 metadata.i18n.<locale>
- agents/<id>/agent.json: shortDesc/fullDesc/tags/persona.{role,traits} 迁入
i18n.<locale>；changelog[].changes 改为 { <locale>: string[] } 对象
- categories.json: 每个分类的 label/description 迁入 i18n.<locale>，顶层只剩
color/icon
- manifest.json: 加 supportedLocales / defaultLocale；顶层 description 迁入
i18n.<locale>
### Body 文件结构
- 根 SKILL.md = frontmatter + default_locale (en-US) body
- SKILL.<locale>.md = 各 locale 的 markdown body（首行 <!-- locale: xx --> 自校验）
### 工具链（scripts/i18n/）
- glossary.json: zh→en 术语表 + do_not_translate 白名单
- schema/skill-frontmatter.schema.json: i18n frontmatter JSON Schema
- validate-i18n.py: 8 条校验规则（name 合规 / locale 完整性 / hash 一致性等）
- translate.py: GitHub Models / Anthropic 双 backend，sha256 增量翻译
- migrate.py: 一次性迁移脚本（旧格式 → i18n 结构）
### CI（.github/workflows/）
- i18n-validate.yml: PR 触发跑 validate + translate --check
- i18n-translate.yml: PR 触发用 GitHub Models（默认 openai/gpt-5-mini）翻译缺失
locale，自动追加 commit；可切到 ANTHROPIC_API_KEY 走 Claude
### 文档
- docs/I18N.md: 作者贡献指南（schema 说明 / 提交流程 / 常见问题）
- README.md: 加多语言段落
## 验证
- uv run scripts/i18n/validate-i18n.py: OK，49 文件 0 错误
- uv run scripts/i18n/translate.py --check: 0 stale locale
- 21 skills 标题数 zh-CN == en-US 严格对齐（最大 66=66）
- skills-ref 规范校验：全部通过（顶层 name ASCII slug + description 单字段）
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(i18n): 修复 PR #1 review 反馈的 6 项问题
- schema: translated_by 正则放宽为 ^(human|ai:[A-Za-z0-9._:/-]+)$，接受
'ai:github:openai/gpt-5-mini' 这类 backend:model 形式（CI 翻译输出格式）
- README + docs/I18N.md: 修正"CI 用 Claude API"误导描述，正确说明默认是
GitHub Models（openai/gpt-5-mini）+ GITHUB_TOKEN，可选切到 Anthropic
- skills/minimax-tts/SKILL.md & SKILL.zh-CN.md: 删除多余的 ``` 闭合，避免
Markdown 后续渲染错乱
- skills/docx/SKILL.md: 翻译时丢失的 • Unicode escape 示例已恢复，
与 zh-CN 版本对齐
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
GitHub
227
scripts/i18n/glossary.json
Normal file
227
scripts/i18n/glossary.json
Normal file
@@ -0,0 +1,227 @@
|
||||
{
|
||||
"$schema": "./schema/glossary.schema.json",
|
||||
"_comment": "DesireCore Market i18n glossary. Used by translate.py to keep terminology consistent across skills. Add domain-specific entries as new skills are added.",
|
||||
"version": "1.0.0",
|
||||
"default_source_locale": "zh-CN",
|
||||
"default_target_locale": "en-US",
|
||||
"terms": {
|
||||
"zh-CN_to_en-US": {
|
||||
"智能体": "Agent",
|
||||
"技能": "Skill",
|
||||
"工具": "Tool",
|
||||
"市场": "Market",
|
||||
"工作流": "workflow",
|
||||
"黄金样本": "gold sample",
|
||||
"触发词": "trigger keyword",
|
||||
"落地页": "landing page",
|
||||
"仪表盘": "Dashboard",
|
||||
"海报": "poster",
|
||||
"登录态": "logged-in session",
|
||||
"联网访问": "Web Access",
|
||||
"网页抓取": "page fetching",
|
||||
"网络搜索": "web search",
|
||||
"联网搜索": "web search",
|
||||
"调研": "research",
|
||||
"公文": "official document",
|
||||
"备忘录": "memo",
|
||||
"合同": "contract",
|
||||
"信函": "letter",
|
||||
"信函模板": "letter template",
|
||||
"报告": "report",
|
||||
"发票": "invoice",
|
||||
"目录": "table of contents",
|
||||
"页眉页脚": "header and footer",
|
||||
"页码": "page number",
|
||||
"脚注": "footnote",
|
||||
"尾注": "endnote",
|
||||
"修订": "tracked changes",
|
||||
"批注": "comment",
|
||||
"签名": "signature",
|
||||
"表单": "form",
|
||||
"字段": "field",
|
||||
"电子表格": "spreadsheet",
|
||||
"工作表": "worksheet",
|
||||
"数据透视表": "pivot table",
|
||||
"图表": "chart",
|
||||
"幻灯片": "slide",
|
||||
"演示文稿": "presentation",
|
||||
"幻灯片母版": "slide master",
|
||||
"环境配置": "environment setup",
|
||||
"运行环境": "runtime",
|
||||
"容器": "container",
|
||||
"沙箱": "sandbox",
|
||||
"镜像": "image",
|
||||
"权限": "permission",
|
||||
"白名单": "allowlist",
|
||||
"黑名单": "blocklist",
|
||||
"凭据": "credential",
|
||||
"密钥": "secret",
|
||||
"存储桶": "bucket",
|
||||
"对象存储": "object storage",
|
||||
"上传": "upload",
|
||||
"下载": "download",
|
||||
"拷贝": "copy",
|
||||
"迁移": "migration",
|
||||
"校验": "validation",
|
||||
"回退": "fallback",
|
||||
"回滚": "rollback",
|
||||
"审批": "approval",
|
||||
"审计": "audit",
|
||||
"灰度": "canary release",
|
||||
"发布": "release",
|
||||
"通道": "channel",
|
||||
"稳定通道": "stable channel",
|
||||
"金丝雀通道": "canary channel",
|
||||
"维护者": "maintainer",
|
||||
"贡献者": "contributor",
|
||||
"作者": "author",
|
||||
"风险等级": "risk level",
|
||||
"图片生成": "image generation",
|
||||
"语音合成": "text-to-speech",
|
||||
"视频生成": "video generation",
|
||||
"邮箱操作": "Email Operations",
|
||||
"邮件": "email",
|
||||
"收件箱": "inbox",
|
||||
"草稿": "draft",
|
||||
"标签": "label",
|
||||
"分类": "category",
|
||||
"附件": "attachment",
|
||||
"自动回复": "auto-reply",
|
||||
"群发": "bulk send",
|
||||
"智能回复": "smart reply",
|
||||
"团队管理": "team management",
|
||||
"技能管理": "skills management",
|
||||
"调度": "orchestration",
|
||||
"中枢": "central",
|
||||
"中枢调度器": "central orchestrator",
|
||||
"数字员工": "digital worker",
|
||||
"人格": "persona",
|
||||
"原则": "principle",
|
||||
"持久化": "persistence",
|
||||
"系统中枢": "system core",
|
||||
"节流": "throttling",
|
||||
"限流": "rate limiting",
|
||||
"重试": "retry",
|
||||
"幂等": "idempotency",
|
||||
"命令行": "CLI",
|
||||
"脚本": "script",
|
||||
"二进制": "binary",
|
||||
"依赖": "dependency",
|
||||
"包管理器": "package manager",
|
||||
"镜像源": "registry mirror",
|
||||
"节省 Token": "save tokens",
|
||||
"节省成本": "save cost",
|
||||
"安装": "install",
|
||||
"卸载": "uninstall",
|
||||
"升级": "upgrade",
|
||||
"降级": "downgrade",
|
||||
"热更新": "hot-reload",
|
||||
"冷启动": "cold start",
|
||||
"调试": "debug",
|
||||
"远程调试": "remote debugging",
|
||||
"断点": "breakpoint",
|
||||
"排查": "troubleshoot",
|
||||
"技能创建器": "skill creator",
|
||||
"技能创作": "skill authoring",
|
||||
"技能模板": "skill template",
|
||||
"前端设计": "Frontend Design",
|
||||
"网页设计": "web design",
|
||||
"UI 设计": "UI design",
|
||||
"界面设计": "interface design",
|
||||
"组件": "component",
|
||||
"美化": "polish",
|
||||
"样式": "style",
|
||||
"主题": "theme",
|
||||
"配色": "color scheme",
|
||||
"字体": "font",
|
||||
"字号": "font size",
|
||||
"栅格": "grid",
|
||||
"暗色模式": "dark mode",
|
||||
"亮色模式": "light mode",
|
||||
"无障碍": "accessibility",
|
||||
"响应式": "responsive",
|
||||
"动效": "motion / animation",
|
||||
"交互": "interaction",
|
||||
"用户体验": "UX",
|
||||
"用户界面": "UI",
|
||||
"渲染": "render",
|
||||
"构建": "build",
|
||||
"打包": "bundle",
|
||||
"热重载": "hot reload"
|
||||
}
|
||||
},
|
||||
"do_not_translate": [
|
||||
"anthropic",
|
||||
"claude",
|
||||
"DesireCore",
|
||||
"AgentFS",
|
||||
"MCP",
|
||||
"Claude Code",
|
||||
"Anthropic",
|
||||
"Markdown",
|
||||
"YAML",
|
||||
"JSON",
|
||||
"SVG",
|
||||
"PDF",
|
||||
"DOCX",
|
||||
"PPTX",
|
||||
"XLSX",
|
||||
"S3",
|
||||
"MinIO",
|
||||
"MiniMax",
|
||||
"OpenAI",
|
||||
"Kling",
|
||||
"Jina",
|
||||
"Reader",
|
||||
"Playwright",
|
||||
"CDP",
|
||||
"Chrome",
|
||||
"GitHub",
|
||||
"Gmail",
|
||||
"Outlook",
|
||||
"IMAP",
|
||||
"SMTP",
|
||||
"WSL",
|
||||
"WSL2",
|
||||
"Docker",
|
||||
"Podman",
|
||||
"Kubernetes",
|
||||
"Node.js",
|
||||
"Python",
|
||||
"TypeScript",
|
||||
"JavaScript",
|
||||
"Bash",
|
||||
"BeautifulSoup",
|
||||
"LibreOffice",
|
||||
"Poppler",
|
||||
"Pandoc",
|
||||
"Tesseract",
|
||||
"Unicode",
|
||||
"UTF-8",
|
||||
"REST",
|
||||
"API",
|
||||
"URL",
|
||||
"HTTP",
|
||||
"HTTPS",
|
||||
"OAuth",
|
||||
"JWT",
|
||||
"Lucide",
|
||||
"React",
|
||||
"Vue",
|
||||
"Next.js",
|
||||
"Tailwind",
|
||||
"CSS",
|
||||
"HTML",
|
||||
"SKILL.md",
|
||||
"frontmatter",
|
||||
"metadata"
|
||||
],
|
||||
"preserve_patterns": [
|
||||
"^```[\\s\\S]*?```$",
|
||||
"`[^`\\n]+`",
|
||||
"https?://[^\\s)]+",
|
||||
"<[a-zA-Z][\\s\\S]*?>",
|
||||
"\\$[A-Z_][A-Z0-9_]*",
|
||||
"\\b[a-z][a-zA-Z0-9_]*\\.[a-z][a-zA-Z0-9_]*\\b"
|
||||
]
|
||||
}
|
||||
235
scripts/i18n/migrate.py
Executable file
235
scripts/i18n/migrate.py
Executable file
@@ -0,0 +1,235 @@
|
||||
#!/usr/bin/env -S uv run --script
|
||||
# /// script
|
||||
# requires-python = ">=3.10"
|
||||
# dependencies = ["ruamel.yaml>=0.18"]
|
||||
# ///
|
||||
"""One-shot migration: convert legacy SKILL.md frontmatter to i18n format.
|
||||
|
||||
For each skill directory:
|
||||
1. Read SKILL.md frontmatter (legacy format with Chinese top-level name).
|
||||
2. Move legacy `name` -> metadata.i18n.<source>.name (default source: zh-CN).
|
||||
3. Move legacy `market.short_desc` -> metadata.i18n.<source>.short_desc.
|
||||
4. Set top-level `name` to the directory name (ASCII slug).
|
||||
5. Add metadata.i18n.{default_locale=en-US, source_locale=<src>, locales=[src]}.
|
||||
6. Move existing body to SKILL.<source>.md (with `<!-- locale: <src> -->` header).
|
||||
7. Replace root SKILL.md body with a translation-pending placeholder.
|
||||
8. Compute source_hash for the source locale.
|
||||
|
||||
DOES NOT TRANSLATE — translate.py (the CI script) fills in the en-US body & i18n block
|
||||
afterwards. After migration, the skill is structurally valid but only has source_locale
|
||||
content; en-US locale is added by translate.py on the next CI run.
|
||||
|
||||
Usage:
|
||||
scripts/i18n/migrate.py --dry-run # preview, default
|
||||
scripts/i18n/migrate.py --apply # write changes
|
||||
scripts/i18n/migrate.py --apply skills/web-access # one skill
|
||||
scripts/i18n/migrate.py --apply --source zh-CN # set source locale (default zh-CN)
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
from datetime import date
|
||||
from io import StringIO
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from ruamel.yaml import YAML
|
||||
from ruamel.yaml.scalarstring import LiteralScalarString, FoldedScalarString
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
DEFAULT_LOCALE = "en-US"
|
||||
PLACEHOLDER_BODY = (
|
||||
"<!-- TRANSLATION PENDING: this body will be auto-translated from "
|
||||
"metadata.i18n.<source_locale>.body by scripts/i18n/translate.py on the next CI run. -->\n"
|
||||
"\n"
|
||||
"# {dir_name}\n"
|
||||
"\n"
|
||||
"_Translation pending. See `{source_body}` for the source-language version._\n"
|
||||
)
|
||||
|
||||
FRONTMATTER_RE = re.compile(r"^---\s*\n(.*?)\n---\s*\n(.*)$", re.DOTALL)
|
||||
|
||||
|
||||
def make_yaml() -> YAML:
|
||||
y = YAML()
|
||||
y.indent(mapping=2, sequence=4, offset=2)
|
||||
y.width = 4096
|
||||
y.preserve_quotes = True
|
||||
return y
|
||||
|
||||
|
||||
def load_frontmatter(text: str) -> tuple[Any, str]:
|
||||
m = FRONTMATTER_RE.match(text)
|
||||
if not m:
|
||||
raise ValueError("File is missing YAML frontmatter")
|
||||
yaml_text, body = m.group(1), m.group(2)
|
||||
yaml = make_yaml()
|
||||
fm = yaml.load(yaml_text)
|
||||
return fm, body
|
||||
|
||||
|
||||
def dump_frontmatter(fm: Any, body: str) -> str:
|
||||
yaml = make_yaml()
|
||||
buf = StringIO()
|
||||
yaml.dump(fm, buf)
|
||||
return f"---\n{buf.getvalue()}---\n\n{body.lstrip()}"
|
||||
|
||||
|
||||
def source_hash(body: str, i18n_strings: dict[str, str]) -> str:
|
||||
h = hashlib.sha256()
|
||||
h.update(body.encode("utf-8"))
|
||||
h.update(b"\x00")
|
||||
h.update(json.dumps(i18n_strings, sort_keys=True, ensure_ascii=False).encode("utf-8"))
|
||||
return f"sha256:{h.hexdigest()[:16]}"
|
||||
|
||||
|
||||
def migrate_skill(skill_dir: Path, source_locale: str, default_locale: str, apply: bool) -> dict[str, Any]:
|
||||
"""Return a dict describing the planned changes for this skill."""
|
||||
rel = skill_dir.relative_to(REPO_ROOT).as_posix()
|
||||
skill_md = skill_dir / "SKILL.md"
|
||||
plan: dict[str, Any] = {"skill": rel, "actions": [], "errors": []}
|
||||
|
||||
if not skill_md.is_file():
|
||||
plan["errors"].append("SKILL.md not found")
|
||||
return plan
|
||||
|
||||
text = skill_md.read_text(encoding="utf-8")
|
||||
try:
|
||||
fm, body = load_frontmatter(text)
|
||||
except ValueError as e:
|
||||
plan["errors"].append(str(e))
|
||||
return plan
|
||||
|
||||
# Already migrated?
|
||||
metadata = fm.get("metadata") or {}
|
||||
if isinstance(metadata, dict) and "i18n" in metadata and isinstance(metadata.get("i18n"), dict):
|
||||
plan["actions"].append("already migrated, skipping")
|
||||
return plan
|
||||
|
||||
legacy_name = fm.get("name", "").strip()
|
||||
legacy_short_desc = ""
|
||||
market = fm.get("market")
|
||||
if isinstance(market, dict):
|
||||
legacy_short_desc = (market.get("short_desc") or "").strip()
|
||||
# Remove short_desc from market — it has migrated.
|
||||
if "short_desc" in market:
|
||||
market.pop("short_desc", None)
|
||||
|
||||
legacy_description = fm.get("description", "")
|
||||
|
||||
# New top-level name = directory name
|
||||
new_name = skill_dir.name
|
||||
fm["name"] = new_name
|
||||
|
||||
# Build metadata.i18n
|
||||
if not isinstance(metadata, dict):
|
||||
metadata = {}
|
||||
fm["metadata"] = metadata
|
||||
|
||||
i18n_block: dict[str, Any] = {
|
||||
"default_locale": default_locale,
|
||||
"source_locale": source_locale,
|
||||
"locales": [source_locale],
|
||||
}
|
||||
|
||||
# Source body file
|
||||
source_body_filename = f"SKILL.{source_locale}.md"
|
||||
source_body_path = skill_dir / source_body_filename
|
||||
source_body_text = f"<!-- locale: {source_locale} -->\n\n{body.lstrip()}"
|
||||
|
||||
# Source locale strings
|
||||
src_strings = {
|
||||
"name": legacy_name or new_name,
|
||||
"short_desc": legacy_short_desc or legacy_name or new_name,
|
||||
}
|
||||
if legacy_description:
|
||||
src_strings["description"] = (
|
||||
legacy_description if isinstance(legacy_description, str) else str(legacy_description)
|
||||
)
|
||||
|
||||
src_hash = source_hash(body, src_strings)
|
||||
|
||||
src_block: dict[str, Any] = {
|
||||
"name": src_strings["name"],
|
||||
"short_desc": src_strings["short_desc"],
|
||||
}
|
||||
if "description" in src_strings:
|
||||
# Use folded style for long descriptions to keep frontmatter readable
|
||||
desc = src_strings["description"]
|
||||
src_block["description"] = FoldedScalarString(desc) if "\n" in desc or len(desc) > 80 else desc
|
||||
src_block["body"] = f"./{source_body_filename}"
|
||||
src_block["source_hash"] = src_hash
|
||||
src_block["translated_by"] = "human"
|
||||
|
||||
i18n_block[source_locale] = src_block
|
||||
metadata["i18n"] = i18n_block
|
||||
|
||||
# Plan actions
|
||||
plan["actions"].append(f"rename top-level name '{legacy_name}' -> '{new_name}'")
|
||||
plan["actions"].append(f"add metadata.i18n.{source_locale} (name, short_desc, description, body, source_hash)")
|
||||
plan["actions"].append(f"create {source_body_filename} ({len(body)} chars)")
|
||||
placeholder = PLACEHOLDER_BODY.format(dir_name=new_name, source_body=source_body_filename)
|
||||
plan["actions"].append(f"replace root SKILL.md body with translation-pending placeholder ({len(placeholder)} chars)")
|
||||
if legacy_short_desc:
|
||||
plan["actions"].append("remove market.short_desc (migrated to i18n)")
|
||||
|
||||
if apply:
|
||||
# Write source body file
|
||||
source_body_path.write_text(source_body_text, encoding="utf-8")
|
||||
# Write new root SKILL.md (frontmatter + placeholder body)
|
||||
new_root = dump_frontmatter(fm, placeholder)
|
||||
skill_md.write_text(new_root, encoding="utf-8")
|
||||
plan["written"] = [
|
||||
source_body_path.relative_to(REPO_ROOT).as_posix(),
|
||||
skill_md.relative_to(REPO_ROOT).as_posix(),
|
||||
]
|
||||
|
||||
return plan
|
||||
|
||||
|
||||
def main(argv: list[str]) -> int:
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument("paths", nargs="*", help="Skill directories to migrate (default: all under skills/)")
|
||||
parser.add_argument("--apply", action="store_true", help="Write changes (default: dry-run)")
|
||||
parser.add_argument("--dry-run", action="store_true", help="Preview only (default)")
|
||||
parser.add_argument("--source", default="zh-CN", help="Source locale (default: zh-CN)")
|
||||
parser.add_argument("--default", dest="default_locale", default=DEFAULT_LOCALE,
|
||||
help=f"Default locale (default: {DEFAULT_LOCALE})")
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
apply = args.apply and not args.dry_run
|
||||
|
||||
if args.paths:
|
||||
targets = [Path(p).resolve() for p in args.paths]
|
||||
else:
|
||||
targets = sorted((REPO_ROOT / "skills").iterdir())
|
||||
targets = [t for t in targets if t.is_dir() and (t / "SKILL.md").is_file()]
|
||||
|
||||
plans: list[dict[str, Any]] = []
|
||||
for skill_dir in targets:
|
||||
if not skill_dir.is_dir() or not (skill_dir / "SKILL.md").is_file():
|
||||
continue
|
||||
plans.append(migrate_skill(skill_dir, args.source, args.default_locale, apply))
|
||||
|
||||
print(f"\n{'APPLIED' if apply else 'DRY-RUN'} migration plan ({len(plans)} skills):\n")
|
||||
for p in plans:
|
||||
if p.get("errors"):
|
||||
print(f" ✗ {p['skill']}: ERRORS: {p['errors']}")
|
||||
else:
|
||||
print(f" • {p['skill']}: {len(p['actions'])} action(s)")
|
||||
for a in p["actions"]:
|
||||
print(f" - {a}")
|
||||
print()
|
||||
if not apply:
|
||||
print("Re-run with --apply to write changes.")
|
||||
else:
|
||||
print("Migration complete. Run scripts/i18n/validate-i18n.py to verify.")
|
||||
return 1 if any(p.get("errors") for p in plans) else 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main(sys.argv[1:]))
|
||||
156
scripts/i18n/schema/skill-frontmatter.schema.json
Normal file
156
scripts/i18n/schema/skill-frontmatter.schema.json
Normal file
@@ -0,0 +1,156 @@
|
||||
{
|
||||
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||
"$id": "https://desirecore.net/market/schema/skill-frontmatter.schema.json",
|
||||
"title": "DesireCore Market Skill Frontmatter (i18n)",
|
||||
"description": "JSON Schema for the YAML frontmatter of a SKILL.md in the DesireCore market. Compatible with the agentskills.io specification: https://agentskills.io/specification",
|
||||
"type": "object",
|
||||
"required": ["name", "description", "version", "metadata"],
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"name": {
|
||||
"description": "Spec-required. Must equal the parent directory name. Lowercase ASCII letters, digits, hyphens. 1-64 chars. Must not start/end with hyphen, must not contain consecutive hyphens, must not be 'anthropic' or 'claude'.",
|
||||
"type": "string",
|
||||
"minLength": 1,
|
||||
"maxLength": 64,
|
||||
"pattern": "^(?!-)(?!.*--)(?!anthropic$)(?!claude$)[a-z0-9](?:[a-z0-9-]*[a-z0-9])?$"
|
||||
},
|
||||
"description": {
|
||||
"description": "Spec-required. 1-1024 chars. Single field used by Claude for skill discovery. Multilingual trigger keywords are accepted (Anthropic-recommended pattern for multilingual users).",
|
||||
"type": "string",
|
||||
"minLength": 1,
|
||||
"maxLength": 1024
|
||||
},
|
||||
"license": {
|
||||
"type": "string"
|
||||
},
|
||||
"compatibility": {
|
||||
"type": "string",
|
||||
"maxLength": 500
|
||||
},
|
||||
"version": {
|
||||
"description": "SemVer string. Required by DesireCore market.",
|
||||
"type": "string",
|
||||
"pattern": "^\\d+\\.\\d+\\.\\d+(?:-[0-9A-Za-z.-]+)?(?:\\+[0-9A-Za-z.-]+)?$"
|
||||
},
|
||||
"type": {
|
||||
"description": "DesireCore extension. Skill behavior class.",
|
||||
"type": "string",
|
||||
"enum": ["procedural", "meta", "knowledge", "tool"]
|
||||
},
|
||||
"risk_level": {
|
||||
"description": "DesireCore extension.",
|
||||
"type": "string",
|
||||
"enum": ["low", "medium", "high", "critical"]
|
||||
},
|
||||
"status": {
|
||||
"description": "DesireCore extension. Whether the skill is enabled by default.",
|
||||
"type": "string",
|
||||
"enum": ["enabled", "disabled", "deprecated", "experimental"]
|
||||
},
|
||||
"disable-model-invocation": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"tags": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string",
|
||||
"pattern": "^[a-z0-9][a-z0-9-]*$"
|
||||
},
|
||||
"uniqueItems": true
|
||||
},
|
||||
"allowed-tools": {
|
||||
"type": "string"
|
||||
},
|
||||
"metadata": {
|
||||
"type": "object",
|
||||
"required": ["author", "i18n"],
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"author": { "type": "string" },
|
||||
"updated_at": {
|
||||
"type": "string",
|
||||
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
|
||||
},
|
||||
"i18n": { "$ref": "#/$defs/i18nBlock" }
|
||||
}
|
||||
},
|
||||
"market": {
|
||||
"type": "object",
|
||||
"additionalProperties": true,
|
||||
"properties": {
|
||||
"icon": { "type": "string" },
|
||||
"category": { "type": "string" },
|
||||
"channel": {
|
||||
"type": "string",
|
||||
"enum": ["latest", "stable", "canary", "beta"]
|
||||
},
|
||||
"maintainer": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"name": { "type": "string" },
|
||||
"verified": { "type": "boolean" }
|
||||
},
|
||||
"required": ["name"]
|
||||
},
|
||||
"compatible_agents": {
|
||||
"type": "array",
|
||||
"items": { "type": "string" }
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"$defs": {
|
||||
"bcp47Locale": {
|
||||
"description": "BCP-47 locale tag: ll-RR (lowercase language, uppercase region).",
|
||||
"type": "string",
|
||||
"pattern": "^[a-z]{2,3}(?:-[A-Z]{2})?$"
|
||||
},
|
||||
"i18nBlock": {
|
||||
"type": "object",
|
||||
"required": ["default_locale", "source_locale", "locales"],
|
||||
"properties": {
|
||||
"default_locale": { "$ref": "#/$defs/bcp47Locale" },
|
||||
"source_locale": { "$ref": "#/$defs/bcp47Locale" },
|
||||
"locales": {
|
||||
"type": "array",
|
||||
"minItems": 1,
|
||||
"uniqueItems": true,
|
||||
"items": { "$ref": "#/$defs/bcp47Locale" }
|
||||
}
|
||||
},
|
||||
"additionalProperties": {
|
||||
"$ref": "#/$defs/localePayload"
|
||||
}
|
||||
},
|
||||
"localePayload": {
|
||||
"description": "Per-locale display strings and body pointer. Keyed by BCP-47 locale tag.",
|
||||
"type": "object",
|
||||
"required": ["name", "short_desc"],
|
||||
"properties": {
|
||||
"name": { "type": "string", "minLength": 1, "maxLength": 200 },
|
||||
"short_desc": { "type": "string", "minLength": 1, "maxLength": 300 },
|
||||
"description": { "type": "string", "minLength": 1, "maxLength": 2000 },
|
||||
"body": {
|
||||
"description": "Relative path to the body Markdown for this locale, e.g. ./SKILL.zh-CN.md or ./SKILL.md.",
|
||||
"type": "string",
|
||||
"pattern": "^\\./[A-Za-z0-9._/-]+\\.md$"
|
||||
},
|
||||
"source_hash": {
|
||||
"description": "sha256:<8-hex> of source body+i18n strings at translation time. Written by translate.py.",
|
||||
"type": "string",
|
||||
"pattern": "^sha256:[0-9a-f]{8,64}$"
|
||||
},
|
||||
"translated_by": {
|
||||
"description": "'human' for human-authored content; 'ai:<backend>:<model-id>' or 'ai:<model-id>' for machine-translated content. Examples: 'ai:github:openai/gpt-5-mini', 'ai:anthropic:claude-sonnet-4-6', 'ai:claude-opus-4-7'.",
|
||||
"type": "string",
|
||||
"pattern": "^(human|ai:[A-Za-z0-9._:/-]+)$"
|
||||
},
|
||||
"translated_at": {
|
||||
"type": "string",
|
||||
"pattern": "^\\d{4}-\\d{2}-\\d{2}(?:T\\d{2}:\\d{2}:\\d{2}Z?)?$"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false
|
||||
}
|
||||
}
|
||||
}
|
||||
530
scripts/i18n/translate.py
Executable file
530
scripts/i18n/translate.py
Executable file
@@ -0,0 +1,530 @@
|
||||
#!/usr/bin/env -S uv run --script
|
||||
# /// script
|
||||
# requires-python = ">=3.10"
|
||||
# dependencies = ["ruamel.yaml>=0.18", "httpx>=0.27"]
|
||||
# ///
|
||||
"""AI translation pipeline for DesireCore market skills.
|
||||
|
||||
For each skill directory, ensure metadata.i18n contains every locale declared in
|
||||
manifest.json/supportedLocales. When a target locale is missing or stale (its
|
||||
source_hash differs from the current source body+strings hash), translate from
|
||||
metadata.i18n.<source_locale>.body using an LLM.
|
||||
|
||||
Backends (auto-selected, in this priority):
|
||||
1. GitHub Models (default) — uses GITHUB_TOKEN with `models: read` permission,
|
||||
OpenAI-compatible chat-completions API at https://models.github.ai/inference.
|
||||
Model defaults to `openai/gpt-5-mini` (configure with TRANSLATE_MODEL).
|
||||
2. Anthropic API direct — used when ANTHROPIC_API_KEY is set AND
|
||||
TRANSLATE_BACKEND=anthropic. Endpoint https://api.anthropic.com/v1/messages.
|
||||
Model should be a Claude model id (e.g. claude-sonnet-4-6).
|
||||
|
||||
Translations preserve:
|
||||
- Markdown structure (heading hierarchy, list ordering, tables, fences)
|
||||
- Inline code, fenced code blocks, URLs, file paths
|
||||
- SVG, HTML tags, YAML keys
|
||||
- Glossary terms from scripts/i18n/glossary.json
|
||||
- Reserved words from glossary.do_not_translate
|
||||
|
||||
Output:
|
||||
- Updates metadata.i18n.<target_locale>.{name,short_desc,description,source_hash,
|
||||
translated_by,translated_at}
|
||||
- For target_locale == default_locale: writes the translated body to root SKILL.md
|
||||
- Otherwise: writes SKILL.<target_locale>.md
|
||||
|
||||
Usage:
|
||||
GITHUB_TOKEN=... scripts/i18n/translate.py # all stale locales
|
||||
scripts/i18n/translate.py skills/web-access # one skill
|
||||
scripts/i18n/translate.py --target en-US skills/web-access # one locale
|
||||
scripts/i18n/translate.py --check # dry-run, exit 1 if stale
|
||||
scripts/i18n/translate.py --human # mark new translations as human (lock)
|
||||
|
||||
Env:
|
||||
GITHUB_TOKEN required when backend=github (CI: provided automatically)
|
||||
ANTHROPIC_API_KEY required when TRANSLATE_BACKEND=anthropic
|
||||
TRANSLATE_BACKEND 'github' (default) | 'anthropic'
|
||||
TRANSLATE_MODEL backend-specific model id; default depends on backend
|
||||
TRANSLATE_ENDPOINT override endpoint URL
|
||||
TRANSLATE_MAX_RETRIES default 3
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
import time
|
||||
from datetime import datetime, timezone
|
||||
from io import StringIO
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import httpx
|
||||
from ruamel.yaml import YAML
|
||||
from ruamel.yaml.scalarstring import FoldedScalarString
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
GLOSSARY_PATH = REPO_ROOT / "scripts" / "i18n" / "glossary.json"
|
||||
|
||||
DEFAULT_BACKEND = os.environ.get("TRANSLATE_BACKEND", "github").lower()
|
||||
DEFAULT_MODEL_BY_BACKEND = {
|
||||
"github": os.environ.get("TRANSLATE_MODEL", "openai/gpt-5-mini"),
|
||||
"anthropic": os.environ.get("TRANSLATE_MODEL", "claude-sonnet-4-6"),
|
||||
}
|
||||
DEFAULT_ENDPOINT_BY_BACKEND = {
|
||||
"github": "https://models.github.ai/inference",
|
||||
"anthropic": "https://api.anthropic.com",
|
||||
}
|
||||
MAX_RETRIES = int(os.environ.get("TRANSLATE_MAX_RETRIES", "3"))
|
||||
HTTP_TIMEOUT = httpx.Timeout(connect=10, read=180, write=30, pool=10)
|
||||
|
||||
FRONTMATTER_RE = re.compile(r"^---\s*\n(.*?)\n---\s*\n(.*)$", re.DOTALL)
|
||||
HEADING_RE = re.compile(r"^(#{1,6})\s+\S", re.MULTILINE)
|
||||
LOCALE_HEADER_RE = re.compile(r"^<!--\s*locale:\s*[a-zA-Z-]+\s*-->\s*\n+", re.MULTILINE)
|
||||
|
||||
|
||||
def make_yaml() -> YAML:
|
||||
y = YAML()
|
||||
y.indent(mapping=2, sequence=4, offset=2)
|
||||
y.width = 4096
|
||||
y.preserve_quotes = True
|
||||
return y
|
||||
|
||||
|
||||
def load_skill(skill_md: Path) -> tuple[Any, str]:
|
||||
text = skill_md.read_text(encoding="utf-8")
|
||||
m = FRONTMATTER_RE.match(text)
|
||||
if not m:
|
||||
raise ValueError(f"{skill_md}: no frontmatter")
|
||||
fm = make_yaml().load(m.group(1))
|
||||
return fm, m.group(2)
|
||||
|
||||
|
||||
def dump_skill(fm: Any, body: str) -> str:
|
||||
yaml = make_yaml()
|
||||
buf = StringIO()
|
||||
yaml.dump(fm, buf)
|
||||
return f"---\n{buf.getvalue()}---\n\n{body.lstrip()}"
|
||||
|
||||
|
||||
def strip_locale_header(text: str) -> str:
|
||||
return LOCALE_HEADER_RE.sub("", text, count=1)
|
||||
|
||||
|
||||
def compute_source_hash(body: str, strings: dict[str, str]) -> str:
|
||||
h = hashlib.sha256()
|
||||
h.update(body.encode("utf-8"))
|
||||
h.update(b"\x00")
|
||||
h.update(json.dumps(strings, sort_keys=True, ensure_ascii=False).encode("utf-8"))
|
||||
return f"sha256:{h.hexdigest()[:16]}"
|
||||
|
||||
|
||||
def heading_count(text: str) -> int:
|
||||
return len(HEADING_RE.findall(text))
|
||||
|
||||
|
||||
def load_glossary() -> dict[str, Any]:
|
||||
if not GLOSSARY_PATH.is_file():
|
||||
return {"terms": {}, "do_not_translate": []}
|
||||
return json.loads(GLOSSARY_PATH.read_text(encoding="utf-8"))
|
||||
|
||||
|
||||
# ----------------------------- prompt construction -----------------------------
|
||||
|
||||
def build_system_prompt(source_locale: str, target_locale: str, glossary: dict[str, Any]) -> str:
|
||||
terms_key = f"{source_locale}_to_{target_locale}"
|
||||
terms = glossary.get("terms", {}).get(terms_key, {})
|
||||
do_not_translate = glossary.get("do_not_translate", [])
|
||||
|
||||
rules = (
|
||||
f"You are a precise technical translator for DesireCore market skill documentation.\n"
|
||||
f"Translate from {source_locale} to {target_locale}.\n\n"
|
||||
"STRICT RULES:\n"
|
||||
"1. Preserve Markdown structure exactly: heading levels, list nesting, tables, blockquotes, "
|
||||
"fenced code blocks (```...```), inline code (`...`), HTML tags, SVG, YAML keys.\n"
|
||||
"2. NEVER translate: code inside fences, inline `code`, URLs, file paths, command-line args, "
|
||||
"env vars (e.g., $FOO, ${BAR}), Python/JS identifiers, YAML/JSON keys, version numbers.\n"
|
||||
"3. Preserve exact heading text styling: '# H1', '## H2', etc.\n"
|
||||
"4. Preserve list markers: '- ', '* ', '1. '. Preserve checkbox '[ ]' and '[x]'.\n"
|
||||
"5. Preserve emoji, ASCII art (e.g. boxed diagrams), tree-view characters (├ └ │ ─).\n"
|
||||
"6. Translate body prose, table cells (text only, not code), and short heading words.\n"
|
||||
"7. Keep the output length within ~110% of the input length when possible.\n"
|
||||
"8. Do NOT add explanatory comments, translator notes, or 'Translated from...' headers.\n"
|
||||
"9. The first line may be an HTML comment '<!-- locale: ... -->'. Update its locale code "
|
||||
"to the target locale; otherwise leave the comment unchanged.\n"
|
||||
)
|
||||
glossary_lines = ["GLOSSARY (use these mappings exactly):"]
|
||||
for src, tgt in terms.items():
|
||||
glossary_lines.append(f" {src} → {tgt}")
|
||||
if do_not_translate:
|
||||
glossary_lines.append("\nDO NOT TRANSLATE these brand/technical terms (keep verbatim):")
|
||||
glossary_lines.append(" " + ", ".join(do_not_translate))
|
||||
|
||||
output_format = (
|
||||
"\n\nRESPONSE FORMAT:\n"
|
||||
"Return ONLY a single JSON object with these keys (no preamble, no code fence around the JSON):\n"
|
||||
" - body: translated Markdown body (string, may contain backticks/fences)\n"
|
||||
" - name: translated short name (string, ≤100 chars)\n"
|
||||
" - short_desc: translated short description (string, ≤200 chars)\n"
|
||||
" - description: translated long description (string, ≤2000 chars)\n"
|
||||
)
|
||||
|
||||
return rules + "\n" + "\n".join(glossary_lines) + output_format
|
||||
|
||||
|
||||
# ----------------------------- backends -----------------------------
|
||||
|
||||
def call_github_models(system_prompt: str, user_payload: str, model: str, endpoint: str) -> str:
|
||||
"""Call GitHub Models inference API (OpenAI-compatible chat completions).
|
||||
|
||||
Endpoint base: https://models.github.ai/inference
|
||||
Auth: Authorization: Bearer <GITHUB_TOKEN> (token must have `models: read` scope).
|
||||
"""
|
||||
token = os.environ.get("GITHUB_TOKEN") or os.environ.get("GH_TOKEN")
|
||||
if not token:
|
||||
raise RuntimeError(
|
||||
"GITHUB_TOKEN (or GH_TOKEN) not set. In CI, ensure your job has `permissions: models: read`. "
|
||||
"Locally, create a fine-grained PAT with 'Models: Read' permission."
|
||||
)
|
||||
url = f"{endpoint.rstrip('/')}/chat/completions"
|
||||
payload = {
|
||||
"model": model,
|
||||
"messages": [
|
||||
{"role": "system", "content": system_prompt},
|
||||
{"role": "user", "content": user_payload},
|
||||
],
|
||||
"temperature": 0.1,
|
||||
"max_tokens": 8192,
|
||||
}
|
||||
headers = {
|
||||
"Authorization": f"Bearer {token}",
|
||||
"Content-Type": "application/json",
|
||||
"Accept": "application/vnd.github+json",
|
||||
"X-GitHub-Api-Version": "2022-11-28",
|
||||
}
|
||||
return _post_with_retries(url, headers, payload, extract=_extract_openai_text)
|
||||
|
||||
|
||||
def call_anthropic(system_prompt: str, user_payload: str, model: str, endpoint: str) -> str:
|
||||
"""Call Anthropic Messages API directly."""
|
||||
api_key = os.environ.get("ANTHROPIC_API_KEY")
|
||||
if not api_key:
|
||||
raise RuntimeError("ANTHROPIC_API_KEY not set")
|
||||
url = f"{endpoint.rstrip('/')}/v1/messages"
|
||||
payload = {
|
||||
"model": model,
|
||||
"max_tokens": 8192,
|
||||
"system": [{"type": "text", "text": system_prompt, "cache_control": {"type": "ephemeral"}}],
|
||||
"messages": [{"role": "user", "content": user_payload}],
|
||||
"temperature": 0.1,
|
||||
}
|
||||
headers = {
|
||||
"x-api-key": api_key,
|
||||
"anthropic-version": "2023-06-01",
|
||||
"content-type": "application/json",
|
||||
}
|
||||
return _post_with_retries(url, headers, payload, extract=_extract_anthropic_text)
|
||||
|
||||
|
||||
def _extract_openai_text(resp_json: dict) -> str:
|
||||
try:
|
||||
return resp_json["choices"][0]["message"]["content"]
|
||||
except (KeyError, IndexError, TypeError) as e:
|
||||
raise RuntimeError(f"Unexpected OpenAI-compatible response shape: {resp_json}") from e
|
||||
|
||||
|
||||
def _extract_anthropic_text(resp_json: dict) -> str:
|
||||
try:
|
||||
parts = resp_json["content"]
|
||||
return "".join(p.get("text", "") for p in parts if p.get("type") == "text")
|
||||
except (KeyError, TypeError) as e:
|
||||
raise RuntimeError(f"Unexpected Anthropic response shape: {resp_json}") from e
|
||||
|
||||
|
||||
def _post_with_retries(url: str, headers: dict, payload: dict, *, extract) -> str:
|
||||
last_err: Exception | None = None
|
||||
for attempt in range(1, MAX_RETRIES + 1):
|
||||
try:
|
||||
with httpx.Client(timeout=HTTP_TIMEOUT) as client:
|
||||
resp = client.post(url, headers=headers, json=payload)
|
||||
if resp.status_code == 429 or resp.status_code >= 500:
|
||||
raise httpx.HTTPStatusError(f"{resp.status_code}", request=resp.request, response=resp)
|
||||
resp.raise_for_status()
|
||||
return extract(resp.json())
|
||||
except (httpx.HTTPStatusError, httpx.RequestError, json.JSONDecodeError) as e:
|
||||
last_err = e
|
||||
if attempt < MAX_RETRIES:
|
||||
wait = 2 ** attempt
|
||||
sys.stderr.write(f"[translate] retry {attempt}/{MAX_RETRIES} after {wait}s ({e})\n")
|
||||
time.sleep(wait)
|
||||
raise RuntimeError(f"Translation failed after {MAX_RETRIES} attempts: {last_err}")
|
||||
|
||||
|
||||
def call_llm(system_prompt: str, user_payload: str, *, backend: str, model: str, endpoint: str) -> dict[str, str]:
|
||||
if backend == "github":
|
||||
text = call_github_models(system_prompt, user_payload, model, endpoint)
|
||||
elif backend == "anthropic":
|
||||
text = call_anthropic(system_prompt, user_payload, model, endpoint)
|
||||
else:
|
||||
raise RuntimeError(f"Unknown backend: {backend}")
|
||||
return parse_json_response(text)
|
||||
|
||||
|
||||
def parse_json_response(text: str) -> dict[str, str]:
|
||||
text = text.strip()
|
||||
if text.startswith("```"):
|
||||
text = re.sub(r"^```(?:json)?\s*\n", "", text)
|
||||
text = re.sub(r"\n```\s*$", "", text)
|
||||
try:
|
||||
obj = json.loads(text)
|
||||
except json.JSONDecodeError as e:
|
||||
m = re.search(r"\{.*\}", text, re.DOTALL)
|
||||
if m:
|
||||
obj = json.loads(m.group(0))
|
||||
else:
|
||||
raise RuntimeError(f"Failed to parse model response as JSON: {e}\n--- Raw response ---\n{text[:500]}")
|
||||
for k in ("body", "name", "short_desc"):
|
||||
if k not in obj or not isinstance(obj[k], str):
|
||||
raise RuntimeError(f"Translation response missing required key '{k}'")
|
||||
obj.setdefault("description", "")
|
||||
return obj
|
||||
|
||||
|
||||
# ----------------------------- per-skill translation -----------------------------
|
||||
|
||||
def translate_skill(
|
||||
skill_dir: Path,
|
||||
target_locale: str,
|
||||
*,
|
||||
check_only: bool,
|
||||
mark_human: bool,
|
||||
backend: str,
|
||||
model: str,
|
||||
endpoint: str,
|
||||
) -> dict[str, Any]:
|
||||
rel = skill_dir.relative_to(REPO_ROOT).as_posix()
|
||||
skill_md = skill_dir / "SKILL.md"
|
||||
plan: dict[str, Any] = {"skill": rel, "target": target_locale, "actions": [], "errors": []}
|
||||
|
||||
fm, root_body = load_skill(skill_md)
|
||||
metadata = fm.get("metadata") or {}
|
||||
i18n = metadata.get("i18n") if isinstance(metadata, dict) else None
|
||||
if not isinstance(i18n, dict):
|
||||
plan["errors"].append("metadata.i18n missing — run migrate.py first")
|
||||
return plan
|
||||
|
||||
source_locale = i18n.get("source_locale")
|
||||
default_locale = i18n.get("default_locale")
|
||||
if not source_locale or not default_locale:
|
||||
plan["errors"].append("i18n missing source_locale or default_locale")
|
||||
return plan
|
||||
if target_locale == source_locale:
|
||||
plan["actions"].append("target == source, skipping")
|
||||
return plan
|
||||
|
||||
src_block = i18n.get(source_locale) or {}
|
||||
src_body_path_str = src_block.get("body")
|
||||
if not src_body_path_str:
|
||||
plan["errors"].append(f"i18n.{source_locale}.body not set")
|
||||
return plan
|
||||
src_body_file = (skill_dir / src_body_path_str.removeprefix("./")).resolve()
|
||||
if not src_body_file.is_file():
|
||||
plan["errors"].append(f"source body file not found: {src_body_path_str}")
|
||||
return plan
|
||||
|
||||
src_body_text = strip_locale_header(src_body_file.read_text(encoding="utf-8"))
|
||||
src_strings = {
|
||||
"name": str(src_block.get("name", "")),
|
||||
"short_desc": str(src_block.get("short_desc", "")),
|
||||
}
|
||||
if src_block.get("description"):
|
||||
src_strings["description"] = str(src_block["description"])
|
||||
current_hash = compute_source_hash(src_body_text, src_strings)
|
||||
|
||||
target_block = i18n.get(target_locale) or {}
|
||||
if target_block.get("translated_by") == "human":
|
||||
if target_block.get("source_hash") != current_hash:
|
||||
plan["actions"].append(
|
||||
f"WARN: human-translated locale {target_locale} is stale "
|
||||
f"(source_hash drift). Skipping; please update manually."
|
||||
)
|
||||
else:
|
||||
plan["actions"].append(f"locale {target_locale} is human-locked, skipping")
|
||||
return plan
|
||||
|
||||
needs = (not target_block) or (target_block.get("source_hash") != current_hash)
|
||||
if not needs:
|
||||
plan["actions"].append(f"locale {target_locale} is up-to-date (hash match), skipping")
|
||||
return plan
|
||||
|
||||
if check_only:
|
||||
plan["actions"].append(f"locale {target_locale} needs translation (hash mismatch or missing)")
|
||||
plan["needs_translation"] = True
|
||||
return plan
|
||||
|
||||
payload = {
|
||||
"source_locale": source_locale,
|
||||
"target_locale": target_locale,
|
||||
"skill_id": skill_dir.name,
|
||||
"source": {
|
||||
"name": src_strings["name"],
|
||||
"short_desc": src_strings["short_desc"],
|
||||
"description": src_strings.get("description", ""),
|
||||
"body": src_body_text,
|
||||
},
|
||||
}
|
||||
user_payload = (
|
||||
"Translate the following skill content. Return ONLY the JSON object as specified.\n\n"
|
||||
f"```json\n{json.dumps(payload, ensure_ascii=False)}\n```"
|
||||
)
|
||||
glossary = load_glossary()
|
||||
system_prompt = build_system_prompt(source_locale, target_locale, glossary)
|
||||
|
||||
plan["actions"].append(f"calling {backend}/{model} for {target_locale} translation ...")
|
||||
translated = call_llm(system_prompt, user_payload, backend=backend, model=model, endpoint=endpoint)
|
||||
|
||||
src_h = heading_count(src_body_text)
|
||||
tgt_h = heading_count(translated["body"])
|
||||
if abs(tgt_h - src_h) > 0:
|
||||
plan["errors"].append(f"heading count mismatch (source={src_h}, target={tgt_h}); rejecting")
|
||||
return plan
|
||||
|
||||
if target_locale not in i18n.get("locales", []):
|
||||
i18n["locales"].append(target_locale)
|
||||
new_block: dict[str, Any] = {
|
||||
"name": translated["name"],
|
||||
"short_desc": translated["short_desc"],
|
||||
}
|
||||
if translated.get("description"):
|
||||
desc = translated["description"]
|
||||
new_block["description"] = FoldedScalarString(desc) if "\n" in desc or len(desc) > 80 else desc
|
||||
if target_locale == default_locale:
|
||||
new_block["body"] = "./SKILL.md"
|
||||
else:
|
||||
new_block["body"] = f"./SKILL.{target_locale}.md"
|
||||
new_block["source_hash"] = current_hash
|
||||
translator_tag = "human" if mark_human else f"ai:{backend}:{model}"
|
||||
new_block["translated_by"] = translator_tag
|
||||
new_block["translated_at"] = datetime.now(tz=timezone.utc).strftime("%Y-%m-%d")
|
||||
i18n[target_locale] = new_block
|
||||
|
||||
body_to_write = translated["body"]
|
||||
if target_locale == default_locale:
|
||||
body_to_write = LOCALE_HEADER_RE.sub("", body_to_write, count=1)
|
||||
skill_md.write_text(dump_skill(fm, body_to_write), encoding="utf-8")
|
||||
plan["actions"].append(f"wrote root SKILL.md with translated body ({len(body_to_write)} chars)")
|
||||
else:
|
||||
target_body_file = skill_dir / f"SKILL.{target_locale}.md"
|
||||
if not body_to_write.startswith("<!-- locale:"):
|
||||
body_to_write = f"<!-- locale: {target_locale} -->\n\n{body_to_write.lstrip()}"
|
||||
target_body_file.write_text(body_to_write, encoding="utf-8")
|
||||
skill_md.write_text(dump_skill(fm, root_body), encoding="utf-8")
|
||||
plan["actions"].append(f"wrote {target_body_file.name} ({len(body_to_write)} chars) and updated root frontmatter")
|
||||
|
||||
return plan
|
||||
|
||||
|
||||
def get_target_locales(args: argparse.Namespace) -> list[str]:
|
||||
if args.target:
|
||||
return [args.target]
|
||||
manifest_path = REPO_ROOT / "manifest.json"
|
||||
if not manifest_path.is_file():
|
||||
return ["en-US"]
|
||||
try:
|
||||
manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
|
||||
except json.JSONDecodeError:
|
||||
return ["en-US"]
|
||||
return list(manifest.get("supportedLocales") or ["en-US"])
|
||||
|
||||
|
||||
def resolve_backend(args: argparse.Namespace) -> tuple[str, str, str]:
|
||||
backend = (args.backend or DEFAULT_BACKEND).lower()
|
||||
if backend not in ("github", "anthropic"):
|
||||
raise SystemExit(f"Unknown backend '{backend}'; choose 'github' or 'anthropic'")
|
||||
model = args.model or DEFAULT_MODEL_BY_BACKEND[backend]
|
||||
endpoint = args.endpoint or os.environ.get("TRANSLATE_ENDPOINT") or DEFAULT_ENDPOINT_BY_BACKEND[backend]
|
||||
return backend, model, endpoint
|
||||
|
||||
|
||||
def list_github_models() -> int:
|
||||
token = os.environ.get("GITHUB_TOKEN") or os.environ.get("GH_TOKEN")
|
||||
if not token:
|
||||
sys.stderr.write("ERROR: GITHUB_TOKEN/GH_TOKEN not set\n")
|
||||
return 2
|
||||
url = "https://models.github.ai/catalog/models"
|
||||
with httpx.Client(timeout=HTTP_TIMEOUT) as c:
|
||||
resp = c.get(url, headers={"Authorization": f"Bearer {token}"})
|
||||
resp.raise_for_status()
|
||||
for m in resp.json():
|
||||
print(f" {m.get('id',''):50s} {m.get('publisher','')}")
|
||||
return 0
|
||||
|
||||
|
||||
def main(argv: list[str]) -> int:
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument("paths", nargs="*", help="Skill directories (default: all under skills/)")
|
||||
parser.add_argument("--target", help="Single target locale (default: all manifest.supportedLocales)")
|
||||
parser.add_argument("--check", action="store_true", help="Report stale translations; exit 1 if any")
|
||||
parser.add_argument("--human", action="store_true", help="Mark new translations as 'human' (locks against re-translation)")
|
||||
parser.add_argument("--backend", choices=("github", "anthropic"), help="Override backend (default: env TRANSLATE_BACKEND or 'github')")
|
||||
parser.add_argument("--model", help="Override model id")
|
||||
parser.add_argument("--endpoint", help="Override API endpoint")
|
||||
parser.add_argument("--list-models", action="store_true", help="List models in GitHub Models catalog and exit")
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
if args.list_models:
|
||||
return list_github_models()
|
||||
|
||||
backend, model, endpoint = resolve_backend(args)
|
||||
|
||||
if not args.check:
|
||||
if backend == "github" and not (os.environ.get("GITHUB_TOKEN") or os.environ.get("GH_TOKEN")):
|
||||
sys.stderr.write("ERROR: GITHUB_TOKEN (or GH_TOKEN) not set for backend='github'\n")
|
||||
return 2
|
||||
if backend == "anthropic" and not os.environ.get("ANTHROPIC_API_KEY"):
|
||||
sys.stderr.write("ERROR: ANTHROPIC_API_KEY not set for backend='anthropic'\n")
|
||||
return 2
|
||||
|
||||
if args.paths:
|
||||
targets = [Path(p).resolve() for p in args.paths]
|
||||
else:
|
||||
targets = sorted((REPO_ROOT / "skills").iterdir())
|
||||
targets = [t for t in targets if t.is_dir() and (t / "SKILL.md").is_file()]
|
||||
|
||||
target_locales = get_target_locales(args)
|
||||
|
||||
plans: list[dict[str, Any]] = []
|
||||
for skill_dir in targets:
|
||||
if not (skill_dir.is_dir() and (skill_dir / "SKILL.md").is_file()):
|
||||
continue
|
||||
for tl in target_locales:
|
||||
plans.append(translate_skill(
|
||||
skill_dir, tl,
|
||||
check_only=args.check, mark_human=args.human,
|
||||
backend=backend, model=model, endpoint=endpoint,
|
||||
))
|
||||
|
||||
needs = [p for p in plans if p.get("needs_translation")]
|
||||
errs = [p for p in plans if p.get("errors")]
|
||||
if args.check:
|
||||
for p in plans:
|
||||
for a in p["actions"]:
|
||||
print(f" [{p['skill']}/{p['target']}] {a}")
|
||||
for p in errs:
|
||||
for e in p["errors"]:
|
||||
print(f" ERROR [{p['skill']}/{p['target']}]: {e}")
|
||||
return 1 if needs else 0
|
||||
|
||||
print(f"Backend: {backend} Model: {model} Endpoint: {endpoint}\n")
|
||||
for p in plans:
|
||||
print(f"{p['skill']} → {p['target']}:")
|
||||
for a in p["actions"]:
|
||||
print(f" - {a}")
|
||||
for e in p.get("errors", []):
|
||||
print(f" ✗ ERROR: {e}")
|
||||
return 1 if errs else 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main(sys.argv[1:]))
|
||||
340
scripts/i18n/validate-i18n.py
Executable file
340
scripts/i18n/validate-i18n.py
Executable file
@@ -0,0 +1,340 @@
|
||||
#!/usr/bin/env -S uv run --script
|
||||
# /// script
|
||||
# requires-python = ">=3.10"
|
||||
# dependencies = ["pyyaml>=6.0"]
|
||||
# ///
|
||||
"""Validate DesireCore market i18n state.
|
||||
|
||||
Checks:
|
||||
1. SKILL.md frontmatter top-level `name` matches parent dir name and is spec-compliant.
|
||||
2. metadata.i18n.default_locale and source_locale are listed in metadata.i18n.locales.
|
||||
3. Each declared locale has metadata.i18n.<locale>.{name,short_desc}.
|
||||
4. metadata.i18n.<locale>.body, if present, points to an existing file; otherwise the
|
||||
fallback chain must terminate at a readable root SKILL.md.
|
||||
5. SKILL.<locale>.md, if it declares <!-- locale: ... -->, must match the filename locale.
|
||||
6. Frontmatter parses cleanly; heading count of locale body matches source body (+/- 0).
|
||||
7. categories.json's per-category i18n covers all locales declared in manifest.json.
|
||||
8. Top-level description is 1-1024 chars (spec); top-level name is 1-64 chars (spec).
|
||||
|
||||
Exit codes:
|
||||
0 = pass
|
||||
1 = validation errors found
|
||||
2 = unexpected runtime error / missing dependencies
|
||||
|
||||
Usage:
|
||||
python3 scripts/i18n/validate-i18n.py # validate everything under repo root
|
||||
python3 scripts/i18n/validate-i18n.py skills/web-access # validate single skill
|
||||
python3 scripts/i18n/validate-i18n.py --json # machine-readable output
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Any, Iterable
|
||||
|
||||
try:
|
||||
import yaml
|
||||
except ImportError:
|
||||
sys.stderr.write("ERROR: PyYAML is required. Install with: pip install pyyaml\n")
|
||||
sys.exit(2)
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
|
||||
NAME_PATTERN = re.compile(r"^(?!-)(?!.*--)[a-z0-9](?:[a-z0-9-]*[a-z0-9])?$")
|
||||
RESERVED_NAMES = {"anthropic", "claude"}
|
||||
LOCALE_PATTERN = re.compile(r"^[a-z]{2,3}(?:-[A-Z]{2})?$")
|
||||
LOCALE_HEADER_PATTERN = re.compile(r"^<!--\s*locale:\s*([a-zA-Z-]+)\s*-->")
|
||||
HEADING_PATTERN = re.compile(r"^(#{1,6})\s+\S", re.MULTILINE)
|
||||
FRONTMATTER_RE = re.compile(r"^---\s*\n(.*?)\n---\s*\n(.*)$", re.DOTALL)
|
||||
|
||||
|
||||
@dataclass
|
||||
class Issue:
|
||||
path: str
|
||||
rule: str
|
||||
message: str
|
||||
severity: str = "error"
|
||||
|
||||
def to_dict(self) -> dict[str, str]:
|
||||
return {
|
||||
"path": self.path,
|
||||
"rule": self.rule,
|
||||
"message": self.message,
|
||||
"severity": self.severity,
|
||||
}
|
||||
|
||||
|
||||
@dataclass
|
||||
class Report:
|
||||
issues: list[Issue] = field(default_factory=list)
|
||||
|
||||
def add(self, issue: Issue) -> None:
|
||||
self.issues.append(issue)
|
||||
|
||||
@property
|
||||
def has_errors(self) -> bool:
|
||||
return any(i.severity == "error" for i in self.issues)
|
||||
|
||||
|
||||
def parse_frontmatter(text: str) -> tuple[dict[str, Any] | None, str | None, str | None]:
|
||||
"""Return (frontmatter_dict, body, error). All three Nones means file is empty."""
|
||||
if not text.strip():
|
||||
return None, None, "empty file"
|
||||
m = FRONTMATTER_RE.match(text)
|
||||
if not m:
|
||||
return None, None, "no YAML frontmatter (file must start with '---')"
|
||||
try:
|
||||
fm = yaml.safe_load(m.group(1)) or {}
|
||||
except yaml.YAMLError as e:
|
||||
return None, None, f"YAML parse error: {e}"
|
||||
if not isinstance(fm, dict):
|
||||
return None, None, "frontmatter must be a YAML mapping"
|
||||
return fm, m.group(2), None
|
||||
|
||||
|
||||
def heading_count(text: str) -> int:
|
||||
return len(HEADING_PATTERN.findall(text or ""))
|
||||
|
||||
|
||||
def validate_skill(skill_dir: Path, report: Report, declared_locales: set[str] | None = None) -> None:
|
||||
"""Validate one skill directory (must contain SKILL.md)."""
|
||||
rel_dir = skill_dir.relative_to(REPO_ROOT).as_posix()
|
||||
skill_md = skill_dir / "SKILL.md"
|
||||
if not skill_md.is_file():
|
||||
report.add(Issue(rel_dir, "structure", "SKILL.md not found"))
|
||||
return
|
||||
|
||||
text = skill_md.read_text(encoding="utf-8")
|
||||
fm, body, err = parse_frontmatter(text)
|
||||
if err:
|
||||
report.add(Issue(f"{rel_dir}/SKILL.md", "rule-6", err))
|
||||
return
|
||||
assert fm is not None and body is not None
|
||||
|
||||
name = fm.get("name", "")
|
||||
description = fm.get("description", "")
|
||||
|
||||
# Rule 1: name spec-compliance + matches dir
|
||||
if not isinstance(name, str) or not NAME_PATTERN.match(name) or len(name) > 64 or name in RESERVED_NAMES:
|
||||
report.add(Issue(
|
||||
f"{rel_dir}/SKILL.md", "rule-1",
|
||||
f"name {name!r} is not spec-compliant (must be lowercase ASCII + hyphens, 1-64 chars, not 'anthropic'/'claude')"
|
||||
))
|
||||
if name != skill_dir.name:
|
||||
report.add(Issue(
|
||||
f"{rel_dir}/SKILL.md", "rule-1",
|
||||
f"name '{name}' must equal parent dir name '{skill_dir.name}' (spec)"
|
||||
))
|
||||
|
||||
# Rule 8: description length
|
||||
if not isinstance(description, str) or not (1 <= len(description) <= 1024):
|
||||
report.add(Issue(
|
||||
f"{rel_dir}/SKILL.md", "rule-8",
|
||||
f"description must be 1-1024 chars (got {len(description) if isinstance(description, str) else 'non-string'})"
|
||||
))
|
||||
|
||||
# Rule 2/3/4: i18n block
|
||||
metadata = fm.get("metadata") or {}
|
||||
i18n = metadata.get("i18n") if isinstance(metadata, dict) else None
|
||||
if not isinstance(i18n, dict):
|
||||
report.add(Issue(f"{rel_dir}/SKILL.md", "rule-2", "metadata.i18n block missing"))
|
||||
return
|
||||
|
||||
default_locale = i18n.get("default_locale")
|
||||
source_locale = i18n.get("source_locale")
|
||||
locales = i18n.get("locales") or []
|
||||
if not isinstance(locales, list) or not all(isinstance(x, str) for x in locales):
|
||||
report.add(Issue(f"{rel_dir}/SKILL.md", "rule-2", "metadata.i18n.locales must be a list of strings"))
|
||||
return
|
||||
locale_set = set(locales)
|
||||
|
||||
for tag in ("default_locale", "source_locale"):
|
||||
val = i18n.get(tag)
|
||||
if not isinstance(val, str) or not LOCALE_PATTERN.match(val):
|
||||
report.add(Issue(f"{rel_dir}/SKILL.md", "rule-2", f"metadata.i18n.{tag} '{val!r}' is not a valid BCP-47 locale"))
|
||||
elif val not in locale_set:
|
||||
report.add(Issue(f"{rel_dir}/SKILL.md", "rule-2", f"metadata.i18n.{tag} '{val}' not present in metadata.i18n.locales"))
|
||||
|
||||
if declared_locales is not None:
|
||||
missing = declared_locales - locale_set
|
||||
if missing:
|
||||
report.add(Issue(
|
||||
f"{rel_dir}/SKILL.md", "rule-7",
|
||||
f"manifest declares locales {sorted(declared_locales)} but skill is missing {sorted(missing)}",
|
||||
severity="error"
|
||||
))
|
||||
|
||||
# Rule 3: per-locale name/short_desc presence
|
||||
source_body_text: str | None = None
|
||||
for locale in locales:
|
||||
if not LOCALE_PATTERN.match(locale):
|
||||
report.add(Issue(f"{rel_dir}/SKILL.md", "rule-3", f"locale '{locale}' is not a valid BCP-47 tag"))
|
||||
continue
|
||||
payload = i18n.get(locale)
|
||||
if not isinstance(payload, dict):
|
||||
report.add(Issue(f"{rel_dir}/SKILL.md", "rule-3", f"metadata.i18n.{locale} block missing or not a mapping"))
|
||||
continue
|
||||
for required in ("name", "short_desc"):
|
||||
v = payload.get(required)
|
||||
if not isinstance(v, str) or not v.strip():
|
||||
report.add(Issue(
|
||||
f"{rel_dir}/SKILL.md", "rule-3",
|
||||
f"metadata.i18n.{locale}.{required} is missing or empty"
|
||||
))
|
||||
|
||||
# Rule 4: body file presence
|
||||
body_path_str = payload.get("body")
|
||||
body_text: str | None = None
|
||||
if body_path_str:
|
||||
if not isinstance(body_path_str, str) or not body_path_str.startswith("./"):
|
||||
report.add(Issue(
|
||||
f"{rel_dir}/SKILL.md", "rule-4",
|
||||
f"metadata.i18n.{locale}.body must be a relative path starting with './' (got {body_path_str!r})"
|
||||
))
|
||||
else:
|
||||
body_file = (skill_dir / body_path_str.removeprefix("./")).resolve()
|
||||
if not body_file.is_file():
|
||||
report.add(Issue(
|
||||
f"{rel_dir}/SKILL.md", "rule-4",
|
||||
f"metadata.i18n.{locale}.body points to missing file '{body_path_str}'"
|
||||
))
|
||||
else:
|
||||
body_text = body_file.read_text(encoding="utf-8")
|
||||
# Rule 5: locale header self-check (only when not the root SKILL.md)
|
||||
if body_file.name != "SKILL.md":
|
||||
first_line = body_text.splitlines()[0] if body_text else ""
|
||||
m = LOCALE_HEADER_PATTERN.match(first_line)
|
||||
if m and m.group(1) != locale:
|
||||
report.add(Issue(
|
||||
f"{rel_dir}/{body_file.name}", "rule-5",
|
||||
f"file declares locale '{m.group(1)}' but is referenced as '{locale}'"
|
||||
))
|
||||
else:
|
||||
# Fallback to root SKILL.md body (default_locale must have a usable body)
|
||||
if locale == default_locale:
|
||||
body_text = body
|
||||
else:
|
||||
# OK to omit body for non-default locales (will fall back at runtime)
|
||||
pass
|
||||
|
||||
if locale == source_locale:
|
||||
source_body_text = body_text or body # source defaults to root if not specified
|
||||
|
||||
# Rule 6: heading count consistency between source and other locales' bodies
|
||||
if source_body_text is not None:
|
||||
source_count = heading_count(source_body_text)
|
||||
for locale in locales:
|
||||
if locale == source_locale:
|
||||
continue
|
||||
payload = i18n.get(locale) or {}
|
||||
body_path_str = payload.get("body")
|
||||
if body_path_str:
|
||||
body_file = (skill_dir / body_path_str.removeprefix("./")).resolve()
|
||||
if body_file.is_file():
|
||||
other_text = body_file.read_text(encoding="utf-8")
|
||||
other_count = heading_count(other_text)
|
||||
if other_count != source_count:
|
||||
report.add(Issue(
|
||||
f"{rel_dir}/{body_file.name}", "rule-6",
|
||||
f"heading count {other_count} differs from source ({source_count})",
|
||||
severity="warning",
|
||||
))
|
||||
|
||||
|
||||
def validate_market_root(report: Report) -> set[str]:
|
||||
"""Validate manifest.json + categories.json. Returns the declared locale set or empty."""
|
||||
manifest_path = REPO_ROOT / "manifest.json"
|
||||
categories_path = REPO_ROOT / "categories.json"
|
||||
|
||||
declared: set[str] = set()
|
||||
if manifest_path.is_file():
|
||||
try:
|
||||
manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
|
||||
except json.JSONDecodeError as e:
|
||||
report.add(Issue("manifest.json", "rule-7", f"JSON parse error: {e}"))
|
||||
manifest = {}
|
||||
supported = manifest.get("supportedLocales") or []
|
||||
if not isinstance(supported, list) or not all(isinstance(x, str) and LOCALE_PATTERN.match(x) for x in supported):
|
||||
report.add(Issue("manifest.json", "rule-7", "supportedLocales must be a list of BCP-47 tags"))
|
||||
else:
|
||||
declared = set(supported)
|
||||
default = manifest.get("defaultLocale")
|
||||
if declared and default not in declared:
|
||||
report.add(Issue("manifest.json", "rule-7", f"defaultLocale '{default}' not in supportedLocales"))
|
||||
|
||||
if categories_path.is_file() and declared:
|
||||
try:
|
||||
categories = json.loads(categories_path.read_text(encoding="utf-8"))
|
||||
except json.JSONDecodeError as e:
|
||||
report.add(Issue("categories.json", "rule-7", f"JSON parse error: {e}"))
|
||||
return declared
|
||||
for cat_id, cat in categories.items():
|
||||
i18n = cat.get("i18n") if isinstance(cat, dict) else None
|
||||
if not isinstance(i18n, dict):
|
||||
report.add(Issue("categories.json", "rule-7", f"category '{cat_id}' missing i18n block"))
|
||||
continue
|
||||
for locale in declared:
|
||||
payload = i18n.get(locale)
|
||||
if not isinstance(payload, dict) or not payload.get("label"):
|
||||
report.add(Issue(
|
||||
"categories.json", "rule-7",
|
||||
f"category '{cat_id}' missing i18n.{locale}.label"
|
||||
))
|
||||
return declared
|
||||
|
||||
|
||||
def iter_skill_dirs(targets: Iterable[Path]) -> Iterable[Path]:
|
||||
for t in targets:
|
||||
if t.is_file() and t.name == "SKILL.md":
|
||||
yield t.parent
|
||||
elif t.is_dir() and (t / "SKILL.md").is_file():
|
||||
yield t
|
||||
elif t.is_dir():
|
||||
for child in sorted(t.iterdir()):
|
||||
if child.is_dir() and (child / "SKILL.md").is_file():
|
||||
yield child
|
||||
|
||||
|
||||
def main(argv: list[str]) -> int:
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument("paths", nargs="*", help="Skills or directories to validate (default: repo root)")
|
||||
parser.add_argument("--json", action="store_true", help="Emit machine-readable JSON")
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
report = Report()
|
||||
declared_locales = validate_market_root(report)
|
||||
|
||||
if args.paths:
|
||||
targets = [Path(p).resolve() for p in args.paths]
|
||||
else:
|
||||
targets = [REPO_ROOT / "skills"]
|
||||
|
||||
for skill_dir in iter_skill_dirs(targets):
|
||||
validate_skill(skill_dir, report, declared_locales=declared_locales or None)
|
||||
|
||||
if args.json:
|
||||
json.dump([i.to_dict() for i in report.issues], sys.stdout, indent=2, ensure_ascii=False)
|
||||
sys.stdout.write("\n")
|
||||
else:
|
||||
if not report.issues:
|
||||
print("OK: no i18n issues found.")
|
||||
else:
|
||||
for issue in report.issues:
|
||||
marker = "ERROR" if issue.severity == "error" else "WARN "
|
||||
print(f"[{marker}] {issue.path} :: {issue.rule} :: {issue.message}")
|
||||
errors = sum(1 for i in report.issues if i.severity == "error")
|
||||
warns = sum(1 for i in report.issues if i.severity == "warning")
|
||||
print(f"\n{errors} error(s), {warns} warning(s).")
|
||||
|
||||
return 1 if report.has_errors else 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
sys.exit(main(sys.argv[1:]))
|
||||
except KeyboardInterrupt:
|
||||
sys.exit(130)
|
||||
Reference in New Issue
Block a user