Byted Data Search

                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.

      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the
      direction or management of such entity, whether by contract or
      otherwise, or (ii) ownership of fifty percent (50%) or more of the
      outstanding shares, or (iii) beneficial ownership of such entity.

      "You" (or "Your") shall mean an individual or Legal Entity
      exercising permissions granted by this License.

      "Source" form shall mean the preferred form for making modifications,
      including but not limited to software source code, documentation
      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions
      to that Work or Derivative Works thereof, that is intentionally
      submitted to Licensor for inclusion in the Work by the copyright owner
      or by an individual or Legal Entity authorized to submit on behalf of
      the copyright owner. For the purposes of this definition, "submitted"
      means any form of electronic, verbal, or written communication sent
      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise
      designated in writing by the copyright owner as "Not a Contribution."

      "Contributor" shall mean Licensor and any individual or Legal Entity
      on behalf of whom a Contribution has been received by Licensor and
      subsequently incorporated within the Work.

   2. Grant of Copyright License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      copyright license to reproduce, prepare Derivative Works of,
      publicly display, publicly perform, sublicense, and distribute the
      Work and such Derivative Works in Source or Object form.

   3. Grant of Patent License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      (except as stated in this section) patent license to make, have made,
      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a
      cross-claim or counterclaim in a lawsuit) alleging that the Work
      or a Contribution incorporated within the Work constitutes direct
      or contributory patent infringement, then any patent licenses
      granted to You under this License for that Work shall terminate
      as of the date such litigation is filed.

   4. Redistribution. You may reproduce and distribute copies of the
      Work or Derivative Works thereof in any medium, with or without
      modifications, and in Source or Object form, provided that You
      meet the following conditions:

      (a) You must give any other recipients of the Work or
          Derivative Works a copy of this License; and

      (b) You must cause any modified files to carry prominent notices
          stating that You changed the files; and

      (c) You must retain, in the Source form of any Derivative Works
          that You distribute, all copyright, patent, trademark, and
          attribution notices from the Source form of the Work,
          excluding those notices that do not pertain to any part of
          the Derivative Works; and

      (d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,
          within a display generated by the Derivative Works, if and
          wherever such third-party notices normally appear. The contents
          of the NOTICE file are for informational purposes only and
          do not modify the License. You may add Your own attribution
          notices within Derivative Works that You distribute, alongside
          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.

      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or
      for any such Derivative Works as a whole, provided Your use,
      reproduction, and distribution of the Work otherwise complies with
      the conditions stated in this License.

   5. Submission of Contributions. Unless You explicitly state otherwise,
      any Contribution intentionally submitted for inclusion in the Work
      by You to the Licensor shall be under the terms and conditions of
      this License, without any additional terms or conditions.
      Notwithstanding the above, nothing herein shall supersede or modify
      the terms of any separate license agreement you may have executed
      with Licensor regarding such Contributions.

   6. Trademarks. This License does not grant permission to use the trade
      names, trademarks, service marks, or product names of the Licensor,
      except as required for reasonable and customary use in describing the
      origin of the Work and reproducing the content of the NOTICE file.

   7. Disclaimer of Warranty. Unless required by applicable law or
      agreed to in writing, Licensor provides the Work (and each
      Contributor provides its Contributions) on an "AS IS" BASIS,
      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
      implied, including, without limitation, any warranties or conditions
      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,
      whether in tort (including negligence), contract, or otherwise,
      unless required by applicable law (such as deliberate and grossly
      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all
      other commercial damages or losses), even if such Contributor
      has been advised of the possibility of such damages.

   9. Accepting Warranty or Additional Liability. While redistributing
      the Work or Derivative Works thereof, You may choose to offer,
      and charge a fee for, acceptance of support, warranty, indemnity,
      or other liability obligations and/or rights consistent with this
      License. However, in accepting such obligations, You may act only
      on Your own behalf and on Your sole responsibility, not on behalf
      of any other Contributor, and only if You agree to indemnify,
      defend, and hold each Contributor harmless for any liability
      incurred by, or claims asserted against, such Contributor by reason
      of your accepting any such warranty or additional liability.

   END OF TERMS AND CONDITIONS

   APPENDIX: How to apply the Apache License to your work.

      To apply the Apache License to your work, attach the following
      boilerplate notice, with the fields enclosed by brackets "[]"
      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright [yyyy] [name of copyright owner]

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.
   You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License.

#!/usr/bin/env python3
"""Describe datasource tool — retrieves metadata for available data sources.

Usage:
  python3 scripts/describe_datasource.py --datasource-id all
  python3 scripts/describe_datasource.py --datasource-id enterprise_basic_wide
"""

import argparse
import json
import sys

from mcp_gateway_client import (
    DEFAULT_MCP_GATEWAY_URL,
    call_mcp_tool,
    load_credentials,
    pretty_print_mcp_result,
)


def main() -> None:
    parser = argparse.ArgumentParser(
        description="查询数据源元数据（维度、字段类型、可用过滤操作符）",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
示例:
  # 列出所有数据源摘要
  python3 scripts/describe_datasource.py --datasource-id all

  # 查看企业基本信息宽表的完整字段定义
  python3 scripts/describe_datasource.py --datasource-id enterprise_basic_wide

  # 查看产业链企业信息字段
  python3 scripts/describe_datasource.py --datasource-id industry_chain_company_info
""",
    )

    parser.add_argument(
        "--datasource-id",
        default="all",
        help="数据源 ID，或 'all' 列出全部（默认: all）",
    )
    parser.add_argument(
        "--locale",
        default="zh-CN",
        help="字段描述语言（默认: zh-CN）",
    )
    parser.add_argument(
        "--url",
        default=DEFAULT_MCP_GATEWAY_URL,
        help="MCP Gateway URL",
    )
    parser.add_argument(
        "--access-key",
        default=None,
        help="VOLCENGINE_ACCESS_KEY（可选，覆盖环境变量）",
    )
    parser.add_argument(
        "--secret-key",
        default=None,
        help="VOLCENGINE_SECRET_KEY（可选，覆盖环境变量）",
    )
    parser.add_argument(
        "--raw-response",
        action="store_true",
        help="输出完整 MCP JSON-RPC 响应",
    )

    args = parser.parse_args()

    try:
        ak, sk = load_credentials(args.access_key, args.secret_key)
        resp = call_mcp_tool(
            url=args.url,
            access_key=ak,
            secret_key=sk,
            tool_name="describe_datasource",
            arguments={"datasource_id": args.datasource_id, "locale": args.locale},
        )

        if args.raw_response:
            print(json.dumps(resp, ensure_ascii=False, indent=2))
        else:
            pretty_print_mcp_result(resp)

    except Exception as exc:
        print(f"Error: {exc}", file=sys.stderr)
        sys.exit(1)


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
"""Get field enum values — quickly discover the distinct values a field can take.

Returns up to 200 distinct values for a given field in a datasource,
sorted by frequency (most common first). This is essential when you need
to construct exact-match filters (eq/in) but aren't sure what values
the field actually contains.

Usage:
  python3 scripts/get_field_enums.py --datasource-id enterprise_basic_wide --field reg_status
  python3 scripts/get_field_enums.py --datasource-id industry_chain_company_info --field base_name --filters 'chain_name:like:新能源汽车'
"""

import argparse
import json
import sys

from mcp_gateway_client import (
    DEFAULT_MCP_GATEWAY_URL,
    call_mcp_tool,
    extract_tool_text,
    load_credentials,
)


def main() -> None:
    parser = argparse.ArgumentParser(
        description="查询某个数据源中指定字段的枚举值（最多返回 200 个不同取值，按出现频次降序排列）",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
示例:
  # 查看企业状态有哪些取值
  python3 scripts/get_field_enums.py \\
    --datasource-id enterprise_basic_wide --field reg_status

  # 查看某产业链下企业的省份分布
  python3 scripts/get_field_enums.py \\
    --datasource-id industry_chain_company_info --field base_name \\
    --filters 'chain_name:like:新能源汽车'

  # 查看产业链区域指标中 region_level 有哪些取值
  python3 scripts/get_field_enums.py \\
    --datasource-id industry_chain_node_region_metric --field region_level
""",
    )

    parser.add_argument(
        "--datasource-id",
        required=True,
        help="数据源 ID（必填）",
    )
    parser.add_argument(
        "--field",
        required=True,
        help="要查询枚举值的字段名（必填）",
    )
    parser.add_argument(
        "--filters",
        default=None,
        help="可选的前置过滤条件，格式同 query_datasource（如 'chain_name:like:新能源汽车'）",
    )
    parser.add_argument(
        "--limit",
        type=int,
        default=200,
        help="最多返回的枚举值数量（默认: 200，上限: 300）",
    )
    parser.add_argument(
        "--url",
        default=DEFAULT_MCP_GATEWAY_URL,
        help="MCP Gateway URL",
    )
    parser.add_argument(
        "--access-key",
        default=None,
        help="VOLCENGINE_ACCESS_KEY（可选，覆盖环境变量）",
    )
    parser.add_argument(
        "--secret-key",
        default=None,
        help="VOLCENGINE_SECRET_KEY（可选，覆盖环境变量）",
    )

    args = parser.parse_args()

    # Cap limit at 50 (server max page_size)
    limit = min(args.limit, 300)

    try:
        ak, sk = load_credentials(args.access_key, args.secret_key)

        # Use group_by + aggregation to get distinct values via terms aggregation.
        # The server translates group_by into an ES terms aggregation whose
        # bucket size equals page_size, so we set page_size = limit.
        arguments = {
            "datasource_id": args.datasource_id,
            "group_by": args.field,
            "aggregation": f"{args.field}:count",
            "page_size": limit,
        }
        if args.filters:
            arguments["filters"] = args.filters

        resp = call_mcp_tool(
            url=args.url,
            access_key=ak,
            secret_key=sk,
            tool_name="query_datasource",
            arguments=arguments,
        )

        # --- Parse response ---
        tool_text = extract_tool_text(resp)
        if tool_text is None:
            # MCP-level error
            print(json.dumps(resp, ensure_ascii=False, indent=2), file=sys.stderr)
            sys.exit(1)

        parsed = json.loads(tool_text)

        # Check for server-side error
        if "error" in parsed:
            err = parsed["error"]
            print(f"Error [{err.get('code', 'UNKNOWN')}]: {err.get('message', '')}", file=sys.stderr)
            if "suggestion" in err:
                print(f"Suggestion: {err['suggestion']}", file=sys.stderr)
            sys.exit(1)

        # Extract enum values from aggregation_result
        agg_result = parsed.get("aggregation_result", [])
        if not agg_result:
            print(f"字段 '{args.field}' 在数据源 '{args.datasource_id}' 中未找到任何取值。", file=sys.stderr)
            print(f"请确认字段名是否正确（可运行: python3 scripts/describe_datasource.py --datasource-id {args.datasource_id}）", file=sys.stderr)
            sys.exit(0)

        # Each bucket in agg_result is a dict like:
        #   { "<field>": "<value>", "doc_count": 123, "<field>_count": 123 }
        values = []
        for bucket in agg_result:
            val = bucket.get(args.field)
            count = bucket.get("doc_count", 0)
            if val is not None:
                values.append({"value": val, "count": count})

        # Output
        print(f"数据源: {args.datasource_id}")
        print(f"字段:   {args.field}")
        if args.filters:
            print(f"过滤:   {args.filters}")
        print(f"共找到 {len(values)} 个不同取值（最多显示 {limit} 个）:\n")

        for i, item in enumerate(values, 1):
            print(f"  {i:>2}. {item['value']}  ({item['count']} 条)")

        # Also output a machine-readable JSON line for programmatic consumption
        print(f"\n[JSON] {json.dumps([v['value'] for v in values], ensure_ascii=False)}")

    except Exception as exc:
        print(f"Error: {exc}", file=sys.stderr)
        sys.exit(1)


if __name__ == "__main__":
    main()

import json
import os
from typing import Any, Dict, Optional, Tuple

import requests

DEFAULT_MCP_GATEWAY_URL = (
    "https://sd6k08f59gqcea6qe13vg.apigateway-cn-beijing.volceapi.com/mcp"
)


def _has_ark_skill_env() -> bool:
    """Check if ARK_SKILL_API_BASE and ARK_SKILL_API_KEY are both set.

    This is an internal authentication shortcut — when the runtime environment
    provides these variables the script can authenticate without requiring the
    user to configure Volcengine AK/SK.  The variables are never surfaced to
    end-users.
    """
    return bool(os.getenv("ARK_SKILL_API_BASE")) and bool(
        os.getenv("ARK_SKILL_API_KEY")
    )


def _get_skill_account_token() -> str:
    """Obtain a SKILL_ACCOUNT_TOKEN via the ARK GetSkillAuth API.

    Calls:
        GET {ARK_SKILL_API_BASE}?Version=2026-01-01&Action=GetSkillAuth
        Headers:
            Authorization: Bearer {ARK_SKILL_API_KEY}
            ServiceName: hqd

    Returns:
        The token string from response ``data`` field.

    Raises:
        RuntimeError: If the request fails or the response indicates an error.
    """
    ark_api_base = os.getenv("ARK_SKILL_API_BASE", "")
    ark_api_key = os.getenv("ARK_SKILL_API_KEY", "")

    auth_url = f"{ark_api_base}?Version=2026-01-01&Action=GetSkillAuth"
    headers = {
        "Authorization": f"Bearer {ark_api_key}",
        "ServiceName": "hqd",
    }

    resp = requests.get(auth_url, headers=headers, timeout=15, allow_redirects=True)
    resp.raise_for_status()

    body = resp.json()
    if body.get("code") != 0:
        raise RuntimeError(
            f"GetSkillAuth failed: code={body.get('code')}, msg={body.get('msg')}"
        )

    token = body.get("data")
    if not token:
        raise RuntimeError("GetSkillAuth returned empty token")

    return token


def load_credentials(
    access_key: Optional[str] = None, secret_key: Optional[str] = None
) -> Tuple[str, str]:
    """Load credentials from parameters or environment variables.

    Authentication is resolved in the following order:

    1. **Internal ARK Skill mode** — if both ``ARK_SKILL_API_BASE`` and
       ``ARK_SKILL_API_KEY`` are present in the environment, a
       ``SKILL_ACCOUNT_TOKEN`` is obtained from the ARK GetSkillAuth API.
       AK/SK is **not** required in this case, so this function returns
       ``("", "")``.

    2. **Volcengine AK/SK mode** — falls back to ``VOLCENGINE_ACCESS_KEY`` /
       ``VOLCENGINE_SECRET_KEY`` (or the shorter ``VOLC_ACCESS_KEY`` /
       ``VOLC_SECRET_KEY`` aliases).

    Returns:
        A ``(access_key, secret_key)`` tuple.  Both values are empty strings
        when internal ARK Skill mode is active.

    Raises:
        ValueError: If no valid credentials are found through either mode.
    """
    # --- Internal: ARK Skill env (transparent, user does not need to know) ---
    if _has_ark_skill_env():
        return "", ""

    # --- User-facing: Volcengine AK/SK ---
    ak = (
        access_key
        or os.getenv("VOLCENGINE_ACCESS_KEY")
        or os.getenv("VOLC_ACCESS_KEY")
        or ""
    )
    sk = (
        secret_key
        or os.getenv("VOLCENGINE_SECRET_KEY")
        or os.getenv("VOLC_SECRET_KEY")
        or ""
    )

    if not ak or not sk:
        raise ValueError(
            "Missing credentials. Please set environment variables:\n"
            "  export VOLCENGINE_ACCESS_KEY='your-access-key'\n"
            "  export VOLCENGINE_SECRET_KEY='your-secret-key'\n"
            "Get your AK/SK from: https://www.volcengine.com/docs/6291/65568"
        )

    return ak, sk


def call_mcp_tool(
    *,
    url: str,
    access_key: str,
    secret_key: str,
    tool_name: str,
    arguments: Dict[str, Any],
    request_id: int = 1,
    timeout_seconds: int = 30,
) -> Dict[str, Any]:
    """Call an MCP tool via the MCP Gateway.

    All requests are sent to ``DEFAULT_MCP_GATEWAY_URL`` regardless of
    authentication mode.

    Authentication modes
    --------------------
    * **ARK Skill mode** (``ARK_SKILL_API_BASE`` + ``ARK_SKILL_API_KEY`` set):
      1. Calls ``GetSkillAuth`` to obtain a ``SKILL_ACCOUNT_TOKEN``.
      2. Sends the MCP request to ``url`` (= ``DEFAULT_MCP_GATEWAY_URL``)
         with header ``Skill-Account-Token: <token>``.

    * **Volcengine AK/SK mode** (fallback):
      Sends the MCP request to ``url`` with ``Volc-Access-Key`` /
      ``Volc-Secret-Key`` headers.

    Args:
        url: MCP Gateway endpoint URL (used as the target in all modes)
        access_key: Volcengine Access Key (used only in AK/SK mode)
        secret_key: Volcengine Secret Key (used only in AK/SK mode)
        tool_name: Name of the MCP tool to invoke
        arguments: Tool arguments dict
        request_id: JSON-RPC request ID
        timeout_seconds: Request timeout in seconds

    Returns:
        JSON-RPC response dict

    Raises:
        requests.HTTPError: If the HTTP request fails
        requests.Timeout: If the request times out
        RuntimeError: If GetSkillAuth fails in ARK Skill mode
    """
    payload = {
        "jsonrpc": "2.0",
        "id": request_id,
        "method": "tools/call",
        "params": {"name": tool_name, "arguments": arguments},
    }

    # Always use the passed url (which defaults to DEFAULT_MCP_GATEWAY_URL in
    # all callers) — both auth modes hit the same gateway.
    target_url = url

    if _has_ark_skill_env():
        # --- ARK Skill mode ---
        # Step 1: Obtain SKILL_ACCOUNT_TOKEN via GetSkillAuth
        token = _get_skill_account_token()

        # Step 2: Call MCP Gateway with the token
        headers = {
            "Content-Type": "application/json",
            "Accept": "application/json",
            "Skill-Account-Token": token,
        }
    else:
        # --- Volcengine AK/SK mode ---
        headers = {
            "Content-Type": "application/json",
            "Accept": "application/json",
            "Volc-Access-Key": access_key,
            "Volc-Secret-Key": secret_key,
        }

    response = requests.post(
        target_url,
        headers=headers,
        data=json.dumps(payload, ensure_ascii=False).encode("utf-8"),
        timeout=timeout_seconds,
    )
    response.raise_for_status()
    return response.json()


def extract_tool_text(mcp_response: Dict[str, Any]) -> Optional[str]:
    """Extract text content from MCP tool response.

    Args:
        mcp_response: Raw JSON-RPC response from MCP Gateway

    Returns:
        Concatenated text content, or None if error or no text found
    """
    if "error" in mcp_response and mcp_response["error"]:
        return None

    result = mcp_response.get("result")
    if isinstance(result, dict):
        content = result.get("content")
        if isinstance(content, list):
            texts = []
            for item in content:
                if (
                    isinstance(item, dict)
                    and item.get("type") == "text"
                    and isinstance(item.get("text"), str)
                ):
                    texts.append(item["text"])
            if texts:
                return "\n".join(texts)

    if isinstance(result, str):
        return result

    return None


def pretty_print_mcp_result(mcp_response: Dict[str, Any]) -> None:
    """Pretty-print an MCP tool response.

    For text results, attempts JSON parsing for formatted output.
    Falls back to raw JSON-RPC dump on error or non-text responses.
    """
    if "error" in mcp_response and mcp_response["error"]:
        print(json.dumps(mcp_response, ensure_ascii=False, indent=2))
        return

    tool_text = extract_tool_text(mcp_response)
    if tool_text is None:
        print(json.dumps(mcp_response, ensure_ascii=False, indent=2))
        return

    try:
        parsed = json.loads(tool_text)
        print(json.dumps(parsed, ensure_ascii=False, indent=2))
    except Exception:
        print(tool_text)

#!/usr/bin/env python3
"""Query datasource tool — retrieves actual data from a data source.

Usage:
  python3 scripts/query_datasource.py --datasource-id enterprise_basic_wide --filters 'company_name:like:字节跳动'
  python3 scripts/query_datasource.py --datasource-id industry_chain_company_info --filters 'chain_name:like:新能源' --aggregation 'count'
"""

import argparse
import json
import sys

from mcp_gateway_client import (
    DEFAULT_MCP_GATEWAY_URL,
    call_mcp_tool,
    load_credentials,
    pretty_print_mcp_result,
)


def main() -> None:
    parser = argparse.ArgumentParser(
        description="查询数据源数据（支持过滤、聚合、分组、排序、分页）",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
示例:
  # 模糊搜索企业
  python3 scripts/query_datasource.py \\
    --datasource-id enterprise_basic_wide \\
    --filters 'company_name:like:字节跳动'

  # 聚合统计
  python3 scripts/query_datasource.py \\
    --datasource-id industry_chain_company_info \\
    --filters 'chain_name:like:新能源汽车' \\
    --aggregation 'count'

  # 分组统计
  python3 scripts/query_datasource.py \\
    --datasource-id industry_chain_company_info \\
    --filters 'chain_name:like:新能源汽车' \\
    --group-by 'base_name' \\
    --aggregation 'company_id:count'

  # 按证券编码查上市公司
  python3 scripts/query_datasource.py \\
    --datasource-id stock_company_brief \\
    --filters 'code:eq:000001'
""",
    )

    parser.add_argument("--datasource-id", required=True, help="数据源 ID（必填）")
    parser.add_argument(
        "--select-fields",
        default=None,
        help="逗号分隔的返回字段（可选，服务端默认返回所有非屏蔽维度字段）",
    )
    parser.add_argument(
        "--filters",
        default=None,
        help="过滤条件，格式: 'field:op:value'，多个用 ';' 分隔",
    )
    parser.add_argument(
        "--aggregation",
        default=None,
        help="聚合操作: 'count' | 'field:count' | 'field:distinct' | 'field:sum/avg/max/min'",
    )
    parser.add_argument(
        "--group-by",
        default=None,
        help="分组字段，逗号分隔（需配合 --aggregation 使用）",
    )
    parser.add_argument("--sort-field", default=None, help="排序字段名")
    parser.add_argument(
        "--sort-order",
        default="desc",
        choices=["asc", "desc"],
        help="排序方向（默认: desc）",
    )
    parser.add_argument("--page", type=int, default=1, help="页码，从 1 开始（默认: 1）")

    parser.add_argument(
        "--url",
        default=DEFAULT_MCP_GATEWAY_URL,
        help="MCP Gateway URL",
    )
    parser.add_argument(
        "--access-key",
        default=None,
        help="VOLCENGINE_ACCESS_KEY（可选，覆盖环境变量）",
    )
    parser.add_argument(
        "--secret-key",
        default=None,
        help="VOLCENGINE_SECRET_KEY（可选，覆盖环境变量）",
    )
    parser.add_argument(
        "--raw-response",
        action="store_true",
        help="输出完整 MCP JSON-RPC 响应",
    )

    args = parser.parse_args()

    if args.page < 1:
        raise SystemExit("--page must be >= 1")

    try:
        ak, sk = load_credentials(args.access_key, args.secret_key)
        arguments = {
            "datasource_id": args.datasource_id,
            "select_fields": args.select_fields,
            "filters": args.filters,
            "aggregation": args.aggregation,
            "group_by": args.group_by,
            "sort_field": args.sort_field,
            "sort_order": args.sort_order,
            "page": args.page,
        }
        # Remove None values to avoid sending unnecessary parameters
        arguments = {k: v for k, v in arguments.items() if v is not None}

        resp = call_mcp_tool(
            url=args.url,
            access_key=ak,
            secret_key=sk,
            tool_name="query_datasource",
            arguments=arguments,
        )

        if args.raw_response:
            print(json.dumps(resp, ensure_ascii=False, indent=2))
        else:
            pretty_print_mcp_result(resp)

    except Exception as exc:
        print(f"Error: {exc}", file=sys.stderr)
        sys.exit(1)


if __name__ == "__main__":
    main()