構造化処理開発ガイド

*RAS_DATA_START
*FILE_DATETIME 2023-01-15 10:30:00
*SAMPLE_NAME Al2O3_sample
*TARGET_NAME Cu
*TUBE_VOLTAGE 40.0
*TUBE_CURRENT 30.0
*SCAN_MODE continuous
*SCAN_SPEED 2.0
*SCAN_STEP 0.02
*START_ANGLE 10.0
*STOP_ANGLE 90.0
*RAS_HEADER_START
... (詳細なメタデータ)
*RAS_HEADER_END
*RAS_INT_START
10.0000 1200.0000 1.0000
10.0200 1205.0000 1.0000
10.0400 1198.0000 1.0000
... (測定データ)
*RAS_INT_END
*RAS_DATA_END

*MEAS_COND_XG_VOLTAGE "40"           # 管電圧（kV）
*MEAS_COND_XG_CURRENT "30"           # 管電流（mA）
*HW_XG_TARGET_NAME "Cu"              # X線源（Cu）
*HW_XG_WAVE_LENGTH_ALPHA1 "1.540593" # 波長α1（Å）
*HW_XG_WAVE_LENGTH_ALPHA2 "1.544414" # 波長α2（Å）
*MEAS_SCAN_START "25.0000"           # 測定開始角度
*MEAS_SCAN_STOP "60.0000"            # 測定終了角度
*MEAS_SCAN_STEP "0.0100"             # 測定ステップ
*MEAS_SCAN_SPEED "8.0000"            # 測定速度（deg/min）
*MEAS_SCAN_MODE "CONTINUOUS"         # 測定モード

*FILE_SAMPLE "Test Sample"           # 試料名
*FILE_COMMENT "XRD example"          # コメント
*FILE_MEMO "Rigaku XRD memo"         # メモ
*FILE_OPERATOR "English"             # 操作者
*FILE_USERGROUP "Academic"           # ユーザーグループ

*MEAS_SCAN_START_TIME "11/21/2017 08:32:31" # 測定開始時刻
*MEAS_SCAN_END_TIME "11/21/2017 08:37:42"   # 測定終了時刻
*MEAS_DATA_COUNT "3501"                     # データ点数
*FILE_VERSION "1"                           # ファイルバージョン

{
    "file_sample": {
        "name": {
            "ja": "試料名",
            "en": "Sample Name"
        },
        "schema": {
            "type": "string"
        }
    },
    "file_comment": {
        "name": {
            "ja": "ファイルコメント",
            "en": "File Comment"
        },
        "schema": {
            "type": "string"
        }
    },
    ...
}

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "myproject/XRD/project",
  "description": "固有情報と試料情報のスキーマ",
  "type": "object",
  "required": [
      "custom",
      "sample"
  ],
  "properties": {
      "custom": {
        "type": "object",
        "label": {
          "ja": "固有情報",
          "en": "Specific Information"
        },
        "required": [],
        "properties": {
          "measurement_temperature": {
              "type": "number",
              "label": {
                "ja": "測定温度",
                "en": "Measurement Temperature"
              },
              "options": {
                "unit": "C"
              }
          }
        }
      },
      "sample": {
        "type": "object",
        "label": {
          "ja": "試料情報",
          "en": "Sample Information"
        },
        "required": [
          "names"
        ],
        "properties": {
          "generalAttributes": {
              "type": "array",
              "items": [
                {
                  "type": "object",
                  "required": [
                      "termId"
                  ],
                  "properties": {
                      "termId": {
                        "const": "3adf9874-7bcb-e5f8-99cb-3d6fd9d7b55e"
                      }
                  }
                },
                {
                  "type": "object",
                  "required": [
                      "termId"
                  ],
                  "properties": {
                      "termId": {
                        "const": "e2d20d02-2e38-2cd3-b1b3-66fdb8a11057"
                      }
                  }
                },
                {
                  "type": "object",
                  "required": [
                      "termId"
                  ],
                  "properties": {
                      "termId": {
                        "const": "efcf34e7-4308-c195-6691-6f4d28ffc9bb"
                      }
                  }
                },
                {
                  "type": "object",
                  "required": [
                      "termId"
                  ],
                  "properties": {
                      "termId": {
                        "const": "7cc57dfb-8b70-4b3a-5315-fbce4cbf73d0"
                      }
                  }
                },
                {
                  "type": "object",
                  "required": [
                      "termId"
                  ],
                  "properties": {
                      "termId": {
                        "const": "1e70d11d-cbdd-bfd1-9301-9612c29b4060"
                      }
                  }
                },
                {
                  "type": "object",
                  "required": [
                      "termId"
                  ],
                  "properties": {
                      "termId": {
                        "const": "5e166ac4-bfcd-457a-84bc-8626abe9188f"
                      }
                  }
                },
                {
                  "type": "object",
                  "required": [
                      "termId"
                  ],
                  "properties": {
                      "termId": {
                        "const": "0d0417a3-3c3b-496a-b0fb-5a26f8a74166"
                      }
                  }
                }
              ]
          }
        }
      }
  }
}

# 新しいプロジェクトを作成する場合
uv init rde-struct-project
cd rde-struct-project

mkdir rde-struct-project
cd rde-struct-project
pyhton3 -m venv .venv
source .venv/bin/activate

pip install rdetoolkit

uv add rdetoolkit
uv sync

# pip
python3 -m rdetoolkit init
# uv
uv run python -m rdetoolkit init

rde-struct-project/
├── container
│   ├── data
│   │   ├── inputdata
│   │   ├── invoice
│   │   │   └── invoice.json
│   │   └── tasksupport
│   │       ├── invoice.schema.json
│   │       └── metadata-def.json
│   ├── modules/ # カスタムモジュール群を配置するディレクトリ
│   ├── Dockerfile
│   ├── main.py # 構造化処理エントリーポイント
│   └── requirements.txt
├── input
│   ├── inputdata
│   └── invoice
│       └── invoice.json
└── templates
    └── tasksupport
        ├── invoice.schema.json
        └── metadata-def.json

cp metadata-def.json container/data/tasksupport/
cp invoice.schema.json container/data/tasksupport/
cp invoice.json container/data/invoice/
cp metadata-def.json templates/tasksupport
cp invoice.schema.json templates/tasksupport
cp metadata-def.json templates/tasksupport/tasksupport/
cp invoice.schema.json templates/tasksupport/tasksupport/

cp XRD_RIGAKU.ras container/data/inputdata/

system:
    save_raw: true
    save_nonshared_raw: false
    magic_variable: false
    save_thumbnail_image: true

container
├── data
│   ├── inputdata
│   │   └── XRD_RIGAKU.ras
│   ├── invoice
│   │   └── invoice.json
│   └── tasksupport
│       ├── invoice.schema.json
│       └── metadata-def.json
├── Dockerfile
├── main.py
├── modules
│   ├── __init__.py
│   └── mymodule.py
└── requirements.txt

import rdetoolkit

from modules.mymodule import my_xrd_func

rdetoolkit.workflows.run(custom_dataset_function=my_xrd_func)

from rdetoolkit.models.rde2types import RdeInputDirPaths, RdeOutputResourcePath

def my_xrd_func(srcpaths: RdeInputDirPaths, resource_paths: RdeOutputResourcePath):
    pass

from pathlib import Path
import re
import pandas as pd

from rdetoolkit.models.rde2types import RdeInputDirPaths, RdeOutputResourcePath


def parse_ras_file(filepath: str | Path) -> tuple[dict[str, str], pd.DataFrame]:
    """RASファイル解析: メタデータと測定データを抽出"""
    metadata, data_lines = {}, []

    with open(filepath, 'r', encoding='utf-8') as f:
        lines = f.readlines()

    in_data = False
    for line in lines:
        line = line.strip()
        if not line:
            continue

        if line.startswith('*'):
            if line == '*RAS_INT_START':
                in_data = True
            elif line == '*RAS_INT_END':
                break
            elif not in_data:
                parts = line[1:].split(' ', 1)
                if len(parts) == 2 and parts[1].strip():
                    key = re.sub(r'[^a-zA-Z0-9]+', '_', parts[0].lower()).strip('_')
                    metadata[key] = parts[1].strip().strip('"')
        elif in_data:
            parts = line.split()
            if len(parts) == 3:
                try:
                    x, i, a = float(parts[0]), float(parts[1]), float(parts[2])
                    data_lines.append([x, i * a])
                except ValueError:
                    continue

    return metadata, pd.DataFrame(data_lines, columns=['two_theta', 'intensity'])


def my_xrd_func(srcpaths: RdeInputDirPaths, resource_paths: RdeOutputResourcePath):
    # 入力ファイルの読み込み
    # rasファイルが一つしかないため、最初のファイルを対象とする
    metadata, dataframe = parse_ras_file(resource_paths.rawfiles[0])

from pathlib import Path
import re
import pandas as pd

from rdetoolkit.models.rde2types import RdeInputDirPaths, RdeOutputResourcePath
from rdetoolkit.rde2util import Meta


def parse_ras_file(filepath: str | Path) -> tuple[dict[str, str], pd.DataFrame]:
    """
    RASファイルを解析し、メタデータと測定データを抽出する
    """
    # ... 省略: 上記のparse_ras_file関数の内容をここに含める ...
    return metadata, df

# **追加**
def save_metadata(metadata: dict[str, str], metadata_def_json_path: str | Path, save_path: str | Path):
    """メタデータをmetadata-def.jsonに基づいて保存"""
    meta = Meta(metadata_def_json_path)
    meta.assign_vals(metadata)
    meta.writefile(str(save_path))


def my_xrd_func(srcpaths: RdeInputDirPaths, resource_paths: RdeOutputResourcePath):
    # 入力ファイルの読み込み
    metadata, dataframe = parse_ras_file(resource_paths.rawfiles[0])

    # **追加**: メタデータ保存処理
    metadata_def_json_path = srcpaths.tasksupport.joinpath("metadata-def.json")
    save_path = resource_paths.meta.joinpath("metadata.json")
    save_metadata(metadata, metadata_def_json_path, save_path)

def parse_ras_file(filepath: str | Path) -> tuple[dict[str, str], pd.DataFrame]:
    # ... 省略: 上記のparse_ras_file関数の内容をここに含める ...
    return metadata, df


def save_metadata(metadata: dict[str, str], metadata_def_json_path: str | Path, save_path: str | Path):
    # ... 省略: 上記のsave_metadata関数の内容をここに含める ...

def my_xrd_func(srcpaths: RdeInputDirPaths, resource_paths: RdeOutputResourcePath):
    metadata, dataframe = parse_ras_file(resource_paths.rawfiles[0])

    metadata_def_json_path = srcpaths.tasksupport.joinpath("metadata-def.json")
    save_path = resource_paths.meta.joinpath("metadata.json")
    save_metadata(metadata, metadata_def_json_path, save_path)

    # **追加**: 計測データの保存
    dataframe.to_csv(resource_paths.struct.joinpath("mesurement.csv"), index=False)

```python
def parse_ras_file(filepath: str | Path) -> tuple[dict[str, str], pd.DataFrame]:
    # ... 省略: 上記のparse_ras_file関数の内容をここに含める ...
    return metadata, df


def save_metadata(metadata: dict[str, str], metadata_def_json_path: str | Path, save_path: str | Path):
    # ... 省略: 上記のsave_metadata関数の内容をここに含める ...

def xrd_plot(data: pd.DataFrame, output_path: str | Path):
    """XRDプロット画像作成"""
    plt.figure(figsize=(10, 6))
    plt.plot(data['two_theta'], data['intensity'], label='Intensity')
    plt.xlabel('2Theta (degrees)')
    plt.ylabel('Intensity')
    plt.title('XRD Pattern')
    plt.legend()
    plt.grid()
    plt.savefig(output_path)
    plt.close()

def my_xrd_func(srcpaths: RdeInputDirPaths, resource_paths: RdeOutputResourcePath):
    metadata, dataframe = parse_ras_file(resource_paths.rawfiles[0])

    metadata_def_json_path = srcpaths.tasksupport.joinpath("metadata-def.json")
    save_path = resource_paths.meta.joinpath("metadata.json")
    save_metadata(metadata, metadata_def_json_path, save_path)

    # 計測データの保存
    dataframe.to_csv(resource_paths.struct.joinpath("mesurement.csv"), index=False)

    # **追加**: プロット画像作成
    xrd_plot(dataframe, resource_paths.main_image.joinpath("xrd_graph.png"))

from pathlib import Path
import re
import pandas as pd
import matplotlib.pyplot as plt

from rdetoolkit.models.rde2types import RdeInputDirPaths, RdeOutputResourcePath
from rdetoolkit.rde2util import Meta
from rdetoolkit.exceptions import StructuredError # **追加**

# ... 省略: 上記の関数群を内容をここに含める ...

def my_xrd_func(srcpaths: RdeInputDirPaths, resource_paths: RdeOutputResourcePath):
    """XRDデータ処理メイン関数"""
    try:
        # RASファイル解析
        metadata, dataframe = parse_ras_file(resource_paths.rawfiles[0])

        # メタデータ保存
        try:
            save_metadata(metadata,
                        srcpaths.tasksupport.joinpath("metadata-def.json"),
                        resource_paths.meta.joinpath("metadata.json"))
        except StructuredError as e:
            print(f"Error saving metadata: {e}")
            return None

        # 測定データ保存
        dataframe.to_csv(resource_paths.struct.joinpath("mesurement.csv"), index=False)

        # プロット画像作成
        xrd_plot(dataframe, resource_paths.main_image.joinpath("xrd_graph.png"))
    except Exception as e:
        raise StructuredError(f"An error occurred during XRD processing: {e}") from e

cd container
python3 main.py

container/data
├── inputdata
│   └── XRD_RIGAKU.ras
├── invoice
│   └── invoice.json
├── job.failed
├── main_image
│   └── xrd_graph.png
├── meta
│   └── metadata.json
├── nonshared_raw
│   └── XRD_RIGAKU.ras
├── raw
│   └── XRD_RIGAKU.ras
├── structured
│   └── mesurement.csv
├── tasksupport
│   ├── invoice.schema.json
│   ├── metadata-def.json
│   └── rdeconfig.yml
└── thumbnail
    └── xrd_graph.png

uv run python -m rdetoolkit artifact -s . -o rde_submit_files.zip

# 出力
📦 Archiving project files...
📌 - Source Directory: .
📌 - Output Archive: rde_submit_files.zip
✅ 🐳 Dockerfile found!: container/Dockerfile
✅ 🐍 requirements.txt found!: container/requirements.txt
🔍 Scanning for external connections...OK
🔍 Scanning for code security vulnerabilities...OK
✅ Archive created successfully: rde_submit_files.zip
✅ Archive and report generation completed successfully.: rde_submit_files.md