Gemini API でアプリのローカリゼーションを自動QAする: 翻訳ドリフトを早期検出する構造化出力パイプライン

# localization_qa.py
import os
import google.generativeai as genai
 
genai.configure(api_key=os.environ["GEMINI_API_KEY"])
 
EVAL_SCHEMA = {
    "type": "object",
    "properties": {
        "accuracy":     {"type": "integer", "minimum": 1, "maximum": 5},
        "fluency":      {"type": "integer", "minimum": 1, "maximum": 5},
        "consistency":  {"type": "integer", "minimum": 1, "maximum": 5},
        "context_fit":  {"type": "integer", "minimum": 1, "maximum": 5},
        "issues":       {"type": "array", "items": {"type": "string"}},
        "suggested_translation": {"type": "string"},
    },
    "required": ["accuracy", "fluency", "consistency", "context_fit", "issues"],
}
 
EVAL_INSTRUCTIONS = """\
あなたはアプリのローカリゼーション QA エンジニアです。
以下の翻訳を 4 軸で 1〜5 のスケールで評価してください。
- accuracy: ソース文字列の意味を保っているか
- fluency: 対象言語のネイティブから見て自然か
- consistency: 提示した過去の翻訳例と用語・語調が揃っているか
- context_fit: 提示した UI コンテキストに合致しているか
issues には具体的な問題点を箇条書きで挙げ、提案訳を suggested_translation に入れてください。
"""
 
def evaluate_translation(
    source_text: str,
    translated_text: str,
    target_lang: str,
    glossary: dict[str, str],
    prior_examples: list[dict],
    ui_context: dict,
) -> dict:
    model = genai.GenerativeModel(
        "gemini-2.5-pro",
        generation_config={
            "response_mime_type": "application/json",
            "response_schema": EVAL_SCHEMA,
            "temperature": 0.1,
        },
        system_instruction=EVAL_INSTRUCTIONS,
    )
 
    prompt = f"""\
[Target Language] {target_lang}
[UI Context] screen_id={ui_context['screen_id']}, control={ui_context['control_kind']}
[Glossary] {glossary}
[Prior Examples in this language]
{prior_examples}
 
[Source (en)] {source_text}
[Translation ({target_lang})] {translated_text}
"""
    response = model.generate_content(prompt)
    return response.parsed if hasattr(response, "parsed") else \
           __import__("json").loads(response.text)

# diff_extractor.py
import re
import subprocess
from pathlib import Path
 
STRING_RE = re.compile(r'^"([^"]+)"\s*=\s*"((?:[^"\\]|\\.)*)";\s*$')
 
def parse_strings(path: Path) -> dict[str, str]:
    out = {}
    for line in path.read_text(encoding="utf-8").splitlines():
        m = STRING_RE.match(line.strip())
        if m:
            out[m.group(1)] = m.group(2)
    return out
 
def extract_changed_keys(repo: Path, file_rel: str, base_ref: str = "HEAD~1"):
    new = parse_strings(repo / file_rel)
    try:
        old_raw = subprocess.check_output(
            ["git", "show", f"{base_ref}:{file_rel}"],
            cwd=repo, text=True
        )
        old = {}
        for line in old_raw.splitlines():
            m = STRING_RE.match(line.strip())
            if m:
                old[m.group(1)] = m.group(2)
    except subprocess.CalledProcessError:
        old = {}
    changed = {k: v for k, v in new.items() if old.get(k) != v}
    return changed

# consistency.py
import google.generativeai as genai
import numpy as np
 
def embed(texts: list[str]) -> np.ndarray:
    res = genai.embed_content(
        model="models/text-embedding-004",
        content=texts,
        task_type="SEMANTIC_SIMILARITY",
    )
    return np.array(res["embedding"])
 
def top_k_similar(query: str, corpus: list[tuple[str, str]], k: int = 5):
    """corpus: [(key, translation), ...] 同じ target_lang のもの"""
    if not corpus:
        return []
    q = embed([query])[0]
    matrix = embed([t for _, t in corpus])
    sims = matrix @ q / (np.linalg.norm(matrix, axis=1) * np.linalg.norm(q) + 1e-9)
    idx = np.argsort(-sims)[:k]
    return [corpus[i] for i in idx]

# .github/workflows/localization-qa.yml
name: Localization QA
on:
  pull_request:
    paths:
      - "Localizable/**/*.strings"
      - "app/src/main/res/values-*/strings.xml"
 
jobs:
  qa:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
      - uses: actions/setup-python@v5
        with: { python-version: "3.12" }
      - run: pip install google-generativeai numpy
      - name: Run QA
        env:
          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
        run: python scripts/localization_qa.py --base-ref ${{ github.event.pull_request.base.sha }}
      - name: Comment on PR
        if: always()
        uses: actions/github-script@v7
        with:
          script: |
            const fs = require("fs");
            const body = fs.readFileSync("qa-report.md", "utf-8");
            github.rest.issues.createComment({
              owner: context.repo.owner,
              repo: context.repo.repo,
              issue_number: context.issue.number,
              body
            });