I compared Gemma 4 31B and Claude Sonnet 4.6 for OCR and structured extraction of business documents, and evaluated their costs and accuracy

"""Performs OCR and structured extraction of documents using Gemma 4 31B (Bedrock Mantle), measuring speed/tokens/cost.

Tries both PNG and PDF for the same document to compare differences by input format.

Connection method:
- Endpoint: https://bedrock-mantle.{REGION}.api.aws/openai/v1 (OpenAI-compatible Chat Completions)
- Authentication: Generate IAM token using provide_token(region) from aws-bedrock-token-generator
- Gemma 4 31B available regions: us-east-1, us-east-2, us-west-2, eu-central-1

Usage:
    export AWS_PROFILE="<your-profile>"   # Specify the profile to use
    export AWS_REGION="us-east-1"
    python3 scripts/gemma4_ocr.py
"""

from __future__ import annotations

import base64
import json
import os
import time
from dataclasses import dataclass, asdict
from pathlib import Path

from openai import OpenAI
from aws_bedrock_token_generator import provide_token

# --- Configuration ---
MODEL_ID = "google.gemma-4-31b"
REGION = os.environ.get("AWS_REGION", "us-east-1")
BASE_URL = f"https://bedrock-mantle.{REGION}.api.aws/openai/v1"

# Pricing (USD per 1M tokens, Bedrock official on-demand)
PRICE_INPUT_PER_1M = 0.14
PRICE_OUTPUT_PER_1M = 0.40
USD_JPY = 150.0  # Exchange rate is approximate and subject to change

ROOT = Path(__file__).resolve().parent.parent
PNG_DIR = ROOT / "png"
PDF_DIR = ROOT / "pdf"
RESULT_DIR = ROOT / "results" / "gemma"

# Verification targets (3 types that are complex and commonly used in practice)
SELECTED = ["invoice", "payslip", "travel_expense"]

PROMPT = (
    "This document is a Japanese business document. Please read all the information "
    "described and output it in structured JSON format. Also determine the document type (doc_type). "
    "No extra explanations or markdown decorations are needed; please return JSON only."
)

@dataclass
class OcrResult:
    file: str
    fmt: str  # "png" or "pdf"
    elapsed_sec: float
    input_tokens: int
    output_tokens: int
    total_tokens: int
    finish_reason: str
    cost_usd: float
    cost_jpy: float
    output_text: str

def build_content(path: Path) -> list[dict]:
    """Assembles content for Chat Completions based on file format.

    PNG is passed as image_url, PDF is passed in file format (OpenAI-compatible).
    """
    b64 = base64.b64encode(path.read_bytes()).decode()
    if path.suffix.lower() == ".pdf":
        media = {
            "type": "file",
            "file": {
                "filename": path.name,
                "file_data": f"data:application/pdf;base64,{b64}",
            },
        }
    else:
        media = {
            "type": "image_url",
            "image_url": {"url": f"data:image/png;base64,{b64}"},
        }
    return [media, {"type": "text", "text": PROMPT}]

def build_client() -> OpenAI:
    """Creates an OpenAI-compatible client for Bedrock Mantle.

    Authentication uses provide_token(region) to generate an IAM token passed to api_key.
    Uses the standard credentials chain (AWS_PROFILE, etc.).
    """
    if not os.environ.get("AWS_PROFILE") and not os.environ.get("AWS_ACCESS_KEY_ID"):
        raise SystemExit("AWS credentials not found. Please specify the profile to use.")
    return OpenAI(base_url=BASE_URL, api_key=provide_token(region=REGION))

def ocr_one(client: OpenAI, path: Path, fmt: str) -> OcrResult:
    """Performs OCR and structured extraction of a single file and returns measurements."""
    start = time.perf_counter()
    resp = client.chat.completions.create(
        model=MODEL_ID,
        messages=[{"role": "user", "content": build_content(path)}],
    )
    elapsed = time.perf_counter() - start

    usage = resp.usage
    choice = resp.choices[0]
    in_tok = usage.prompt_tokens
    out_tok = usage.completion_tokens
    cost_usd = (
        in_tok / 1_000_000 * PRICE_INPUT_PER_1M
        + out_tok / 1_000_000 * PRICE_OUTPUT_PER_1M
    )
    return OcrResult(
        file=path.stem,
        fmt=fmt,
        elapsed_sec=round(elapsed, 2),
        input_tokens=in_tok,
        output_tokens=out_tok,
        total_tokens=in_tok + out_tok,
        finish_reason=choice.finish_reason,
        cost_usd=round(cost_usd, 6),
        cost_jpy=round(cost_usd * USD_JPY, 4),
        output_text=choice.message.content or "",
    )

def run_format(client: OpenAI, fmt: str, results: list[OcrResult]) -> None:
    """Processes targets in the specified format (png/pdf) and appends results to the list."""
    base_dir = PNG_DIR if fmt == "png" else PDF_DIR
    ext = ".png" if fmt == "png" else ".pdf"
    print(f"\n=== Format: {fmt.upper()} ===")
    print(f"{'File':<24}{'Sec':>7}{'InputTok':>9}{'OutputTok':>9}{'Finish':>9}{'JPY':>9}")
    print("-" * 67)
    for stem in SELECTED:
        path = base_dir / f"{stem}{ext}"
        if not path.exists():
            print(f"{stem:<24} Not found: {path}")
            continue
        try:
            r = ocr_one(client, path, fmt)
        except Exception as e:  # noqa: BLE001  Catch-all for verification script
            print(f"{stem:<24} Error: {str(e)[:120]}")
            continue
        results.append(r)
        print(
            f"{r.file:<24}{r.elapsed_sec:>7}{r.input_tokens:>9}"
            f"{r.output_tokens:>9}{r.finish_reason:>9}{r.cost_jpy:>9}"
        )
        (RESULT_DIR / f"{r.file}__{fmt}.json").write_text(
            r.output_text, encoding="utf-8"
        )

def summarize(fmt: str, results: list[OcrResult]) -> dict | None:
    """Displays summary by format and returns a summary dict."""
    rs = [r for r in results if r.fmt == fmt]
    if not rs:
        return None
    n = len(rs)
    tin = sum(r.input_tokens for r in rs)
    tout = sum(r.output_tokens for r in rs)
    tjpy = sum(r.cost_jpy for r in rs)
    tusd = sum(r.cost_usd for r in rs)
    tsec = sum(r.elapsed_sec for r in rs)
    print(
        f"[{fmt.upper()}] {n} items | Avg {tsec/n:.2f}sec/item | "
        f"Input {tin//n}tok/item Output {tout//n}tok/item | "
        f"{tjpy/n:.3f}JPY/item → 1000 items approx {tjpy/n*1000:.0f}JPY"
    )
    return {
        "format": fmt,
        "count": n,
        "avg_sec": round(tsec / n, 2),
        "avg_input_tokens": tin // n,
        "avg_output_tokens": tout // n,
        "total_cost_jpy": round(tjpy, 4),
        "total_cost_usd": round(tusd, 6),
        "per_1000_jpy": round(tjpy / n * 1000, 1),
    }

def main() -> None:
    client = build_client()
    print(f"Endpoint: {BASE_URL}")
    print(f"Model: {MODEL_ID} / Targets: {len(SELECTED)} types x PNG/PDF")

    results: list[OcrResult] = []
    run_format(client, "png", results)
    run_format(client, "pdf", results)

    if not results:
        raise SystemExit("No successful results.")

    print("\n=== Summary (by format) ===")
    png_sum = summarize("png", results)
    pdf_sum = summarize("pdf", results)

    summary = {
        "model": MODEL_ID,
        "region": REGION,
        "usd_jpy": USD_JPY,
        "by_format": [s for s in (png_sum, pdf_sum) if s],
        "results": [asdict(r) for r in results],
    }
    (RESULT_DIR / "summary.json").write_text(
        json.dumps(summary, ensure_ascii=False, indent=2), encoding="utf-8"
    )
    print(f"\nDetails: {RESULT_DIR}/summary.json")

if __name__ == "__main__":
    main()

"""Performs OCR and structured extraction of documents using Claude Sonnet 4.6 (Bedrock Runtime), measuring speed/tokens/cost.

A script for comparison under the same conditions as Gemma 4. Since Sonnet 4.6 does not support bedrock-mantle,
the conventional bedrock-runtime Converse API (with image/PDF input support) is used.

Connection method:
- API: bedrock-runtime Converse (boto3)
- Model: us.anthropic.claude-sonnet-4-6 (inference profile)
- Input: PNG=image block, PDF=document block

Usage:
    export AWS_PROFILE="<your-profile>"   # Specify the profile to use
    export AWS_REGION="us-east-1"
    python3 scripts/sonnet46_ocr.py
"""

from __future__ import annotations

import json
import os
import time
from dataclasses import dataclass, asdict
from pathlib import Path

import boto3

# --- Configuration ---
MODEL_ID = "us.anthropic.claude-sonnet-4-6"
REGION = os.environ.get("AWS_REGION", "us-east-1")

# Pricing (USD per 1M tokens, Bedrock official on-demand)
PRICE_INPUT_PER_1M = 3.00
PRICE_OUTPUT_PER_1M = 15.00
USD_JPY = 150.0  # Exchange rate is approximate and subject to change

ROOT = Path(__file__).resolve().parent.parent
PNG_DIR = ROOT / "png"
PDF_DIR = ROOT / "pdf"
RESULT_DIR = ROOT / "results" / "sonnet"

# Verification targets (same 3 types as Gemma 4)
SELECTED = ["invoice", "payslip", "travel_expense"]

PROMPT = (
    "This document is a Japanese business document. Please read all the information "
    "described and output it in structured JSON format. Also determine the document type (doc_type). "
    "No extra explanations or markdown decorations are needed; please return JSON only."
)

@dataclass
class OcrResult:
    file: str
    fmt: str
    elapsed_sec: float
    input_tokens: int
    output_tokens: int
    total_tokens: int
    stop_reason: str
    cost_usd: float
    cost_jpy: float
    output_text: str

def build_content(path: Path) -> list[dict]:
    """Assembles content blocks for the Converse API.

    PNG is passed as an image block, PDF as a document block.
    A fixed name is used for document name since only alphanumeric characters are allowed.
    """
    raw = path.read_bytes()
    if path.suffix.lower() == ".pdf":
        media = {
            "document": {
                "format": "pdf",
                "name": "document",
                "source": {"bytes": raw},
            }
        }
    else:
        media = {
            "image": {
                "format": "png",
                "source": {"bytes": raw},
            }
        }
    return [media, {"text": PROMPT}]

def ocr_one(client, path: Path, fmt: str) -> OcrResult:
    """Performs OCR and structured extraction of a single file and returns measurements."""
    start = time.perf_counter()
    resp = client.converse(
        modelId=MODEL_ID,
        messages=[{"role": "user", "content": build_content(path)}],
    )
    elapsed = time.perf_counter() - start

    usage = resp["usage"]
    in_tok = usage["inputTokens"]
    out_tok = usage["outputTokens"]
    text = resp["output"]["message"]["content"][0]["text"]
    cost_usd = (
        in_tok / 1_000_000 * PRICE_INPUT_PER_1M
        + out_tok / 1_000_000 * PRICE_OUTPUT_PER_1M
    )
    return OcrResult(
        file=path.stem,
        fmt=fmt,
        elapsed_sec=round(elapsed, 2),
        input_tokens=in_tok,
        output_tokens=out_tok,
        total_tokens=in_tok + out_tok,
        stop_reason=resp.get("stopReason", ""),
        cost_usd=round(cost_usd, 6),
        cost_jpy=round(cost_usd * USD_JPY, 4),
        output_text=text,
    )

def run_format(client, fmt: str, results: list[OcrResult]) -> None:
    """Processes targets in the specified format (png/pdf) and appends results to the list."""
    base_dir = PNG_DIR if fmt == "png" else PDF_DIR
    ext = ".png" if fmt == "png" else ".pdf"
    print(f"\n=== Format: {fmt.upper()} ===")
    print(f"{'File':<24}{'Sec':>7}{'InputTok':>9}{'OutputTok':>9}{'Stop':>10}{'JPY':>9}")
    print("-" * 68)
    for stem in SELECTED:
        path = base_dir / f"{stem}{ext}"
        if not path.exists():
            print(f"{stem:<24} Not found: {path}")
            continue
        try:
            r = ocr_one(client, path, fmt)
        except Exception as e:  # noqa: BLE001  Catch-all for verification script
            print(f"{stem:<24} Error: {str(e)[:120]}")
            continue
        results.append(r)
        print(
            f"{r.file:<24}{r.elapsed_sec:>7}{r.input_tokens:>9}"
            f"{r.output_tokens:>9}{r.stop_reason:>10}{r.cost_jpy:>9}"
        )
        (RESULT_DIR / f"{r.file}__{fmt}.json").write_text(
            r.output_text, encoding="utf-8"
        )

def summarize(fmt: str, results: list[OcrResult]) -> dict | None:
    """Displays summary by format and returns a summary dict."""
    rs = [r for r in results if r.fmt == fmt]
    if not rs:
        return None
    n = len(rs)
    tin = sum(r.input_tokens for r in rs)
    tout = sum(r.output_tokens for r in rs)
    tjpy = sum(r.cost_jpy for r in rs)
    tusd = sum(r.cost_usd for r in rs)
    tsec = sum(r.elapsed_sec for r in rs)
    print(
        f"[{fmt.upper()}] {n} items | Avg {tsec/n:.2f}sec/item | "
        f"Input {tin//n}tok/item Output {tout//n}tok/item | "
        f"{tjpy/n:.3f}JPY/item → 1000 items approx {tjpy/n*1000:.0f}JPY"
    )
    return {
        "format": fmt,
        "count": n,
        "avg_sec": round(tsec / n, 2),
        "avg_input_tokens": tin // n,
        "avg_output_tokens": tout // n,
        "total_cost_jpy": round(tjpy, 4),
        "total_cost_usd": round(tusd, 6),
        "per_1000_jpy": round(tjpy / n * 1000, 1),
    }

def main() -> None:
    if not os.environ.get("AWS_PROFILE") and not os.environ.get("AWS_ACCESS_KEY_ID"):
        raise SystemExit("AWS credentials not found. Please specify the profile to use.")
    client = boto3.client("bedrock-runtime", region_name=REGION)
    print(f"Model: {MODEL_ID} / Targets: {len(SELECTED)} types x PNG/PDF")

    results: list[OcrResult] = []
    run_format(client, "png", results)
    run_format(client, "pdf", results)

    if not results:
        raise SystemExit("No successful results.")

    print("\n=== Summary (by format) ===")
    png_sum = summarize("png", results)
    pdf_sum = summarize("pdf", results)

    summary = {
        "model": MODEL_ID,
        "region": REGION,
        "usd_jpy": USD_JPY,
        "by_format": [s for s in (png_sum, pdf_sum) if s],
        "results": [asdict(r) for r in results],
    }
    (RESULT_DIR / "summary.json").write_text(
        json.dumps(summary, ensure_ascii=False, indent=2), encoding="utf-8"
    )
    print(f"\nDetails: {RESULT_DIR}/summary.json")

if __name__ == "__main__":
    main()

{
  "doc_type": "請求書",
  "issuer": {
    "name": "合同会社テストワークス",
    "address": "〒150-0001 東京都渋谷区架空1-1-1 架空ビル5F",
    "tel": "03-1234-5678",
    "registration_number": "T1234567890123",
    "contact_person": "鈴木太郎"
  },
  "recipient": {
    "name": "架空システム開発株式会社 御中"
  },
  "invoice_details": {
    "invoice_number": "INV-2026-0612",
    "issue_date": "2026年6月12日",
    "payment_deadline": "2026年7月31日",
    "total_amount": 495000,
    "currency": "JPY"
  },
  "items": [
    { "description": "Webアプリ設計・開発（6月分）", "quantity": 1, "unit_price": 350000, "amount": 350000 },
    { "description": "保守運用サポート", "quantity": 1, "unit_price": 80000, "amount": 80000 },
    { "description": "サーバー利用料", "quantity": 2, "unit_price": 10000, "amount": 20000 }
  ],
  "summary": {
    "subtotal": 450000,
    "consumption_tax_rate": "10%",
    "consumption_tax_amount": 45000,
    "total_amount": 495000
  },
  "payment_info": {
    "bank_name": "架空銀行",
    "branch_name": "渋谷支店",
    "account_type": "普通",
    "account_number": "1234567",
    "account_holder": "ゴウドウガイシャテストワークス"
  }
}

{
  "doc_type": "請求書",
  "bill_to": "架空システム開発 株式会社 御中",
  "issuer": {
    "company_name": "合同会社テストワークス",
    "address": "〒150-0001 東京都渋谷区架空1-1-1 架空ビル5F",
    "tel": "03-1234-5678",
    "registration_number": "T1234567890123",
    "contact_person": "鈴木 太郎"
  },
  "invoice_details": {
    "invoice_number": "INV-2026-0612",
    "issue_date": "2026年6月12日",
    "payment_deadline": "2026年7月31日",
    "total_amount": 495000,
    "currency": "JPY"
  },
  "line_items": [
    { "description": "Webアプリ設計・開発 (6月分)", "quantity": 1, "unit_price": 350000, "amount": 350000 },
    { "description": "保守運用サポート", "quantity": 1, "unit_price": 80000, "amount": 80000 },
    { "description": "サーバー利用料", "quantity": 2, "unit_price": 10000, "amount": 20000 }
  ],
  "summary": {
    "subtotal": 450000,
    "tax_rate": "10%",
    "tax_amount": 45000,
    "total": 495000
  },
  "payment_info": {
    "bank_name": "架空銀行",
    "branch_name": "渋谷支店",
    "account_type": "普通",
    "account_number": "1234567",
    "account_holder": "ゴウドウガイシャテストワークス"
  }
}

{
  "doc_type": "請求書",
  "invoice_number": "INV-2026-0612",
  "issue_date": "2026-06-12",
  "payment_due_date": "2026-07-31",
  "bill_to": { "company_name": "架空システム開発 株式会社" },
  "bill_from": {
    "company_name": "合同会社テストワークス",
    "postal_code": "150-0001",
    "address": "東京都渋谷区架空1-1-1 架空ビル5F",
    "tel": "03-1234-5678",
    "registration_number": "T1234567890123",
    "contact_person": "鈴木 太郎"
  },
  "total_amount_with_tax": 495000,
  "items": [
    { "description": "Webアプリ設計・開発（6月分）", "quantity": 1, "unit_price": 350000, "amount": 350000 },
    { "description": "保守運用サポート", "quantity": 1, "unit_price": 80000, "amount": 80000 },
    { "description": "サーバー利用料", "quantity": 2, "unit_price": 10000, "amount": 20000 }
  ],
  "subtotal": 450000,
  "tax_rate": 0.10,
  "tax_amount": 45000,
  "total": 495000,
  "bank_transfer": {
    "bank_name": "架空銀行",
    "branch_name": "渋谷支店",
    "account_type": "普通",
    "account_number": "1234567",
    "account_holder": "ゴウドウガイシャテストワークス"
  }
}

{
  "doc_type": "請求書",
  "invoice_number": "INV-2026-0612",
  "issue_date": "2026-06-12",
  "bill_to": { "company_name": "架空システム開発 株式会社" },
  "bill_from": {
    "company_name": "合同会社テストワークス",
    "postal_code": "150-0001",
    "address": "東京都渋谷区架空1-1-1 架空ビル5F",
    "tel": "03-1234-5678",
    "registration_number": "T1234567890123",
    "contact_person": "鈴木 太郎"
  },
  "items": [
    { "description": "Webアプリ設計・開発（6月分）", "quantity": 1, "unit_price": 350000, "amount": 350000 },
    { "description": "保守運用サポート", "quantity": 1, "unit_price": 80000, "amount": 80000 },
    { "description": "サーバー利用料", "quantity": 2, "unit_price": 10000, "amount": 20000 }
  ],
  "subtotal": 450000,
  "tax_rate": 0.10,
  "tax_amount": 45000,
  "total_amount": 495000,
  "payment_due_date": "2026-07-31",
  "bank_transfer_info": {
    "bank_name": "架空銀行",
    "branch_name": "渋谷支店",
    "account_type": "普通",
    "account_number": "1234567",
    "account_holder": "ゴウドウガイシャテストワークス"
  }
}

{
  "doc_type": "給与明細書",
  "employee_info": {
    "employee_number": "E-10293",
    "name": "佐藤 健太",
    "department": "開発部",
    "company": "架空テクノロジー株式会社"
  },
  "pay_period": {
    "target_month": "2026年5月分",
    "payment_date": "2026年6月15日"
  },
  "earnings": {
    "basic_salary": 320000,
    "executive_allowance": 40000,
    "overtime_allowance": 52300,
    "commuting_allowance": 14800,
    "total_earnings": 427100
  },
  "deductions": {
    "health_insurance": 21300,
    "employees_pension": 39000,
    "employment_insurance": 2562,
    "income_tax": 11200,
    "residence_tax": 23500,
    "total_deductions": 97562
  },
  "attendance": {
    "working_days": 20,
    "absent_days": 0,
    "overtime_hours": 22.5,
    "paid_leave_days": 12
  },
  "net_pay": 329538
}

{
  "doc_type": "給与明細書",
  "employee_info": {
    "employee_number": "E-10293",
    "name": "佐藤 健太",
    "department": "開発部",
    "company": "架空テクノロジー株式会社"
  },
  "pay_period": {
    "target_month": "2026年5月分",
    "payment_date": "2026年6月15日"
  },
  "earnings": {
    "breakdown": [
      { "item": "基本給", "amount": 320000 },
      { "item": "役職手当", "amount": 40000 },
      { "item": "残業手当", "amount": 52300 },
      { "item": "通勤手当", "amount": 14800 }
    ],
    "total_earnings": 427100
  },
  "deductions": {
    "breakdown": [
      { "item": "健康保険", "amount": 21300 },
      { "item": "厚生年金", "amount": 39000 },
      { "item": "雇用保険", "amount": 2562 },
      { "item": "所得税", "amount": 11200 },
      { "item": "住民税", "amount": 23500 }
    ],
    "total_deductions": 97562
  },
  "attendance": {
    "working_days": 20,
    "absent_days": 0,
    "overtime_hours": 22.5,
    "paid_leave_remaining": 12
  },
  "net_payment": 329538
}

{
  "doc_type": "給与明細書",
  "period": { "year": 2026, "month": 5, "label": "2026年5月分" },
  "payment_date": "2026年6月15日",
  "employee": {
    "employee_id": "E-10293",
    "name": "佐藤 健太",
    "department": "開発部",
    "company": "架空テクノロジー株式会社"
  },
  "earnings": {
    "base_salary": 320000,
    "position_allowance": 40000,
    "overtime_allowance": 52300,
    "commuting_allowance": 14800,
    "total_earnings": 427100
  },
  "deductions": {
    "health_insurance": 21300,
    "welfare_pension": 39000,
    "employment_insurance": 2562,
    "income_tax": 11200,
    "resident_tax": 23500,
    "total_deductions": 97562
  },
  "attendance": {
    "working_days": 20,
    "absent_days": 0,
    "overtime_hours": 22.5,
    "paid_leave_remaining": 12
  },
  "net_payment": 329538
}

{
  "doc_type": "給与明細書",
  "period": { "year": 2026, "month": 5, "label": "2026年5月分" },
  "payment_date": "2026年6月15日",
  "employee": {
    "employee_number": "E-10293",
    "name": "佐藤 健太",
    "department": "開発部"
  },
  "company": { "name": "架空テクノロジー株式会社" },
  "earnings": {
    "base_salary": 320000,
    "position_allowance": 40000,
    "overtime_allowance": 52300,
    "commuting_allowance": 14800,
    "total_earnings": 427100
  },
  "deductions": {
    "health_insurance": 21300,
    "welfare_pension": 39000,
    "employment_insurance": 2562,
    "income_tax": 11200,
    "resident_tax": 23500,
    "total_deductions": 97562
  },
  "attendance": {
    "working_days": 20,
    "absent_days": 0,
    "overtime_hours": 22.5,
    "remaining_paid_leave_days": 12
  },
  "net_payment": 329538
}

{
  "doc_type": "出張旅費精算書",
  "application_date": "2026年6月12日",
  "department": "営業部",
  "name": "渡辺 三郎",
  "business_trip_period": {
    "start_date": "2026年6月3日",
    "end_date": "2026年6月5日"
  },
  "destination": "名古屋（空架商談）",
  "expenses": [
    { "date": "6/3", "description": "東京→名古屋", "transportation": "新幹線", "amount": 11300 },
    { "date": "6/3", "description": "宿泊費（1泊）", "transportation": "ホテル", "amount": 9800 },
    { "date": "6/4", "description": "市内移動", "transportation": "地下鉄・タクシー", "amount": 2400 },
    { "date": "6/4", "description": "宿泊費（1泊）", "transportation": "ホテル", "amount": 9800 },
    { "date": "6/5", "description": "名古屋→東京", "transportation": "新幹線", "amount": 11300 },
    { "date": "6/3-5", "description": "日当（3日分）", "transportation": null, "amount": 9000 }
  ],
  "total_amount": 53600,
  "advance_payment": 50000,
  "settlement_amount": 3600
}

{
  "doc_type": "出張旅費精算書",
  "application_date": "2026年6月12日",
  "department": "営業部",
  "name": "渡辺 三郎",
  "trip_period": {
    "start_date": "2026年6月3日",
    "end_date": "2026年6月5日"
  },
  "destination": "名古屋（架空商談）",
  "expenses": [
    { "date": "6/3", "description": "東京→名古屋", "transportation": "新幹線", "amount": 11300 },
    { "date": "6/3", "description": "宿泊費（1泊）", "transportation": "ホテル", "amount": 9800 },
    { "date": "6/4", "description": "市内移動", "transportation": "地下鉄・タクシー", "amount": 2400 },
    { "date": "6/4", "description": "宿泊費（1泊）", "transportation": "ホテル", "amount": 9800 },
    { "date": "6/5", "description": "名古屋→東京", "transportation": "新幹線", "amount": 11300 },
    { "date": "6/3-5", "description": "日当（3日分）", "transportation": "―", "amount": 9000 }
  ],
  "total_amount": 53600,
  "advance_payment": 50000,
  "settlement_amount": 3600
}

{
  "doc_type": "出張旅費精算書",
  "申請日": "2026年6月12日",
  "所属": "営業部",
  "氏名": "渡辺 三郎",
  "出張期間": { "開始": "2026年6月3日", "終了": "2026年6月5日" },
  "出張先": "名古屋",
  "出張目的": "架空商談",
  "明細": [
    { "日付": "6/3", "区間・内容": "東京→名古屋", "交通手段": "新幹線", "金額": 11300 },
    { "日付": "6/3", "区間・内容": "宿泊費（1泊）", "交通手段": "ホテル", "金額": 9800 },
    { "日付": "6/4", "区間・内容": "市内移動", "交通手段": "地下鉄・タクシー", "金額": 2400 },
    { "日付": "6/4", "区間・内容": "宿泊費（1泊）", "交通手段": "ホテル", "金額": 9800 },
    { "日付": "6/5", "区間・内容": "名古屋→東京", "交通手段": "新幹線", "金額": 11300 },
    { "日付": "6/3-5", "区間・内容": "日当（3日分）", "交通手段": null, "金額": 9000 }
  ],
  "合計金額": 53600,
  "仮払金": 50000,
  "精算額": { "種別": "追加支給", "金額": 3600 },
  "承認欄": { "申請": null, "上長": null, "経理": null }
}

{
  "doc_type": "出張旅費精算書",
  "申請日": "2026年6月12日",
  "所属": "営業部",
  "氏名": "渡辺 三郎",
  "出張期間": { "開始": "2026年6月3日", "終了": "2026年6月5日" },
  "出張先": "名古屋（架空商談）",
  "明細": [
    { "日付": "6/3", "区間・内容": "東京→名古屋", "交通手段": "新幹線", "金額": 11300 },
    { "日付": "6/3", "区間・内容": "宿泊費（1泊）", "交通手段": "ホテル", "金額": 9800 },
    { "日付": "6/4", "区間・内容": "市内移動", "交通手段": "地下鉄・タクシー", "金額": 2400 },
    { "日付": "6/4", "区間・内容": "宿泊費（1泊）", "交通手段": "ホテル", "金額": 9800 },
    { "日付": "6/5", "区間・内容": "名古屋→東京", "交通手段": "新幹線", "金額": 11300 },
    { "日付": "6/3-5", "区間・内容": "日当（3日分）", "交通手段": null, "金額": 9000 }
  ],
  "合計金額": 53600,
  "仮払金": 50000,
  "精算額": { "種別": "追加支給", "金額": 3600 },
  "承認欄": { "申請": null, "上長": null, "経理": null }
}