{"id":15139,"date":"2025-06-01T16:00:33","date_gmt":"2025-06-01T07:00:33","guid":{"rendered":"https:\/\/www.sambuichi.jp\/?p=15139"},"modified":"2025-06-02T08:14:21","modified_gmt":"2025-06-01T23:14:21","slug":"python%e3%81%a7%e6%a7%8b%e9%80%a0%e5%8c%96%e3%82%a4%e3%83%b3%e3%83%9c%e3%82%a4%e3%82%b9csv%e3%82%92%e8%87%aa%e5%8b%95%e7%94%9f%e6%88%90%e3%81%99%e3%82%8b%e3%82%b9%e3%82%af%e3%83%aa%e3%83%97%e3%83%88","status":"publish","type":"post","link":"https:\/\/www.sambuichi.jp\/?p=15139","title":{"rendered":"Python\u3067\u69cb\u9020\u5316CSV\u3092\u81ea\u52d5\u751f\u6210\u3059\u308b\u30b9\u30af\u30ea\u30d7\u30c8\u306e\u89e3\u8aac"},"content":{"rendered":"

Views: 35<\/p>

\n

Python\u3067\u69cb\u9020\u5316CSV\u3092\u81ea\u52d5\u751f\u6210\u3059\u308b\u30b9\u30af\u30ea\u30d7\u30c8\u306e\u89e3\u8aac<\/h1>\n
\nChatGPT (\u7de8\u96c6 \u4e09\u5206\u4e00\u4fe1\u4e4b\uff09<\/span>
\n2025-06-02<\/span>\n<\/div>\n<\/div>\n
\n
\n
\n
\n

\n\u672c\u8a18\u4e8b\u3067\u306f\u3001\u8907\u6570\u306eCSV\u30d5\u30a1\u30a4\u30eb\uff08\u8acb\u6c42\u66f8\u30fb\u8cb7\u624b\u30fb\u58f2\u624b\u30fb\u660e\u7d30\u30fb\u7a0e\u60c5\u5831\u306a\u3069\uff09\u3092\u3082\u3068\u306b\u3001\u69cb\u9020\u5316\u3055\u308c\u305f1\u679a\u307e\u305f\u306f\u8907\u6570\u306e\u8acb\u6c42\u66f8\u60c5\u5831\u3092\u51fa\u529b\u3059\u308bPython\u30b9\u30af\u30ea\u30d7\u30c8\u306b\u3064\u3044\u3066\u89e3\u8aac\u3057\u307e\u3059\u3002
\n\u4e2d\u5c0f\u4f01\u696d\u5171\u901aEDI\u3084XBRL-GL\u306a\u3069\u306e\u4ed5\u8a33\u5e33\u30fb\u30a4\u30f3\u30dc\u30a4\u30b9\u51e6\u7406\u306b\u5fdc\u7528\u53ef\u80fd\u3067\u3059\u3002\n<\/p><\/blockquote>\n<\/div>\n<\/div>\n<\/div>\n

\n

1. \u80cc\u666f<\/h2>\n
\n
\n

\u96fb\u5b50\u30a4\u30f3\u30dc\u30a4\u30b9\u3084\u69cb\u9020\u5316\u4f1a\u8a08\u30c7\u30fc\u30bf\u306e\u666e\u53ca\u306b\u3088\u308a\u3001\u8acb\u6c42\u30c7\u30fc\u30bf\u3092CSV\u5f62\u5f0f\u3067\u6a19\u6e96\u5316\u3057\u3001\u7a0e\u52d9\u30fb\u4f1a\u8a08\u30bd\u30d5\u30c8\u9593\u3067\u9023\u643a\u53ef\u80fd\u306b\u3059\u308b\u3053\u3068\u304c\u6c42\u3081\u3089\u308c\u3066\u3044\u307e\u3059\u3002\u672c\u30b9\u30af\u30ea\u30d7\u30c8\u306f\u3001\u305d\u306e\u305f\u3081\u306e\u30c6\u30f3\u30d7\u30ec\u30fc\u30c8\u3068\u306a\u308a\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n

\n

2. \u30b9\u30af\u30ea\u30d7\u30c8\u306e\u76ee\u7684<\/h2>\n
\n
\n
    \n
  • \n

    \u8acb\u6c42\u66f8\u3054\u3068\u306b\u69cb\u9020\u5316\u3055\u308c\u305f\u884c\u5f62\u5f0f\uff08\u30d8\u30c3\u30c0\u884c\u3001\u7a0e\u60c5\u5831\u884c\u3001\u660e\u7d30\u884c\uff09\u3092\u51fa\u529b<\/p>\n<\/li>\n

  • \n

    \u5358\u4e00\u307e\u305f\u306f\u8907\u6570\u306e\u8acb\u6c42\u66f8\u3092\u5bfe\u8c61\u306b\u3001\u67d4\u8edf\u306a\u51fa\u529b<\/p>\n<\/li>\n

  • \n

    Python\uff0bPandas\u306b\u3088\u308b\u30b7\u30f3\u30d7\u30eb\u306a\u5b9f\u88c5<\/p>\n<\/li>\n<\/ul>\n<\/div>\n<\/div>\n<\/div>\n

    \n

    3. \u30d5\u30a1\u30a4\u30eb\u69cb\u6210<\/h2>\n
    \n\n\n\n\n<\/colgroup>\n\n\n\n\n\n\n\n\n
    \n

    \u30d5\u30a1\u30a4\u30eb\u540d<\/p>\n<\/td>\n

    		\n

    \u5185\u5bb9<\/p>\n<\/td>\n<\/tr>\n

    \n

    Invoice.csv<\/p>\n<\/td>\n

    		\n

    \u8acb\u6c42\u66f8\u30d8\u30c3\u30c0\u60c5\u5831<\/p>\n<\/td>\n<\/tr>\n

    \n

    Buyer.csv<\/p>\n<\/td>\n

    		\n

    \u8cb7\u624b\uff08\u8acb\u6c42\u5148\uff09\u30de\u30b9\u30bf<\/p>\n<\/td>\n<\/tr>\n

    \n

    Seller.csv<\/p>\n<\/td>\n

    		\n

    \u58f2\u624b\uff08\u4f9b\u7d66\u8005\uff09\u30de\u30b9\u30bf<\/p>\n<\/td>\n<\/tr>\n

    \n

    InvoiceLine.csv<\/p>\n<\/td>\n

    		\n

    \u660e\u7d30\u884c\u60c5\u5831<\/p>\n<\/td>\n<\/tr>\n

    \n

    Item.csv<\/p>\n<\/td>\n

    		\n

    \u5546\u54c1\u30de\u30b9\u30bf\uff08\u54c1\u76ee\u540d\u3001\u7a0e\u7387\u306a\u3069\uff09<\/p>\n<\/td>\n<\/tr>\n

    \n

    TaxBreakdown.csv<\/p>\n<\/td>\n

    		\n

    \u7a0e\u533a\u5206\u3054\u3068\u306e\u7a0e\u60c5\u5831<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n

    \n

    4. \u51fa\u529b\u3055\u308c\u308bCSV\u69cb\u9020<\/h2>\n
    \n
    \n

    \u51fa\u529bCSV\u306f\u4ee5\u4e0b\u306e3\u968e\u5c64\u306e\u60c5\u5831\u3092\u542b\u307f\u307e\u3059\uff1a<\/p>\n<\/div>\n

    \n
      \n
    1. \n

      \u8acb\u6c42\u66f8\u30d8\u30c3\u30c0\uff08dInvoice\uff09<\/p>\n<\/li>\n

    2. \n

      \u7a0e\u660e\u7d30\uff08dTaxBreakdown\uff09<\/p>\n<\/li>\n

    3. \n

      \u660e\u7d30\u884c\uff08dInvoiceLine\uff09<\/p>\n<\/li>\n<\/ol>\n<\/div>\n

      \n

      \u3053\u308c\u306b\u3088\u308a\u3001\u30bf\u30d6\u5f62\u5f0f\u306e\u69cb\u9020\u5316CSV\uff08tidy data\uff09\u304c\u5b9f\u73fe\u3055\u308c\u307e\u3059\u3002<\/p>\n<\/div>\n<\/div>\n<\/div>\n

      \n

      5. \u5b9f\u884c\u30b3\u30de\u30f3\u30c9\u4f8b<\/h2>\n
      \n
      \n

      \u5358\u4e00\u8acb\u6c42\u66f8\uff08\u4f8b\uff1aINV002<\/code>\uff09\u3092\u51fa\u529b\uff1a<\/p>\n<\/div>\n

      \n
      \n
      python structured_invoice_csv.py --base_dir 2025\/202506\/20250601\/ \\\r\n       --invoice_id INV002 \\\r\n       --single_csv_path 2025\/202506\/20250601\/invoice_INV002.csv<\/code><\/pre>\n<\/div>\n<\/div>\n
      \n
      \u5168\u8acb\u6c42\u66f8\u3092\u51fa\u529b\uff1a<\/p>\n<\/div>\n
      \n
      \n
      python structured_invoice_csv.py --base_dir 2025\/202506\/20250601\/ \\\r\n       --all_csv_path 2025\/202506\/20250601\/invoice_all.csv<\/code><\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
      \n
      6. \u4e3b\u306a\u51e6\u7406\u306e\u6d41\u308c<\/h2>\n
      \n
      \n
      6.1. 1. \u5404CSV\u30d5\u30a1\u30a4\u30eb\u306e\u8aad\u307f\u8fbc\u307f<\/h3>\n
      \n
      \n
      invoice_df = pd.read_csv(...Invoice.csv)\r\nbuyer_df = pd.read_csv(...Buyer.csv)\r\n...<\/code><\/pre>\n<\/div>\n<\/div>\n<\/div>\n
      \n
      6.2. 2. \u30ab\u30e9\u30e0\u69cb\u9020\u5b9a\u7fa9<\/h3>\n
      \n
      \u51fa\u529bCSV\u306e\u5217\u69cb\u9020\u3092\u56fa\u5b9a\u3057\u3001\u8907\u6570\u30a4\u30f3\u30dc\u30a4\u30b9\u306b\u3082\u5bfe\u5fdc\u3002<\/p>\n<\/div>\n
      \n
      \n
      columns = [\r\n    \"dInvoice\", \"dTaxBreakdown\", \"dInvoiceLine\", ...\r\n]<\/code><\/pre>\n<\/div>\n<\/div>\n<\/div>\n
      \n
      6.3. 3. \u5358\u4e00\u30a4\u30f3\u30dc\u30a4\u30b9\u51fa\u529b\uff08export_single_invoice<\/code>\uff09<\/h3>\n
      \n
        \n
      1. \n
        \u30d8\u30c3\u30c0\u60c5\u5831\u306e\u62bd\u51fa\u3068\u51fa\u529b<\/p>\n<\/li>\n
      2. \n
        \u7a0e\u533a\u5206\u3054\u3068\u306b\u30e6\u30cb\u30fc\u30af\u30ad\u30fc\u3067\u4e26\u3079\u66ff\u3048\u3001dTaxBreakdown<\/code> \u756a\u53f7\u3092\u4ed8\u4e0e<\/p>\n<\/li>\n
      3. \n
        \u660e\u7d30\u884c\u3092 ID.factorize()<\/code> \u3067\u9806\u756a\u306b\u756a\u53f7\u4ed8\u3051\u3057\u51fa\u529b<\/p>\n<\/li>\n<\/ol>\n<\/div>\n<\/div>\n
        \n
        6.4. 4. \u5168\u30a4\u30f3\u30dc\u30a4\u30b9\u51fa\u529b\uff08export_all_invoices<\/code>\uff09<\/h3>\n
        \n
          \n
        1. \n
          \u8acb\u6c42\u66f8\u3092ID\u9806\u306b\u30bd\u30fc\u30c8\u3057 dInvoice<\/code> \u3092\u9023\u756a\u4ed8\u4e0e<\/p>\n<\/li>\n
        2. \n
          \u7a0e\u3068\u660e\u7d30\u306f\u5404\u30a4\u30f3\u30dc\u30a4\u30b9\u3054\u3068\u306b\u7e70\u308a\u8fd4\u3057\u51fa\u529b<\/p>\n<\/li>\n<\/ol>\n<\/div>\n<\/div>\n
          \n
          6.5. 5. \u66f8\u304d\u51fa\u3057\u51e6\u7406<\/h3>\n
          \n
          NA\/\u7a7a\u767d\u3092\u9069\u5207\u306b\u51e6\u7406\u3057\u3001utf-8-sig<\/code> \u3067CSV\u4fdd\u5b58\u3002<\/p>\n<\/div>\n
          \n
          \n
          df.to_csv(path, index=False, encoding=\"utf-8-sig\")<\/code><\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
          \n
          7. launch.json\u4f8b\uff08VS Code\uff09<\/h2>\n
          \n
          \n
          \n
          {\r\n  \"name\": \"\u69cb\u9020\u5316\u30a4\u30f3\u30dc\u30a4\u30b9CSV\u51fa\u529b\",\r\n  \"type\": \"python\",\r\n  \"request\": \"launch\",\r\n  \"program\": \"${workspaceFolder}\/structured_invoice_csv.py\",\r\n  \"args\": [\r\n    \"--base_dir\", \"2025\/202506\/20250601\/\",\r\n    \"--invoice_id\", \"INV002\",\r\n    \"--single_csv_path\", \"2025\/202506\/20250601\/invoice_INV002.csv\",\r\n    \"--all_csv_path\", \"2025\/202506\/20250601\/invoice_all.csv\"\r\n  ]\r\n}<\/code><\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
          \n
          8. \u304a\u308f\u308a\u306b<\/h2>\n
          \n
          \n
          \u3053\u306e\u30b9\u30af\u30ea\u30d7\u30c8\u306f\u3001\u5b9f\u52d9\u3067\u306e\u8acb\u6c42\u66f8\u3084\u30a4\u30f3\u30dc\u30a4\u30b9\u306e\u69cb\u9020\u5316\u51e6\u7406\u306b\u305d\u306e\u307e\u307e\u6d3b\u7528\u3067\u304d\u307e\u3059\u3002<\/p>\n<\/div>\n
          \n
          \n
          #!\/usr\/bin\/env python3\r\n# coding: utf-8\r\n\"\"\"\r\nUniversal Audit Data Adaptor: structured_csv.py\r\n\r\nThis script processes CSV files dumped from the RDB and converts them into a hierarchically organized structured CSV format.\r\n\r\ndesigned by SAMBUICHI, Nobuyuki (Sambuichi Professional Engineers Office)\r\nwritten by SAMBUICHI, Nobuyuki (Sambuichi Professional Engineers Office)\r\n\r\nCreation Date: 2025-05-30\r\nLast Modified: 2025-06-02\r\n\r\nMIT License\r\n\r\n(c) 2024 SAMBUICHI Nobuyuki (Sambuichi Professional Engineers Office)\r\n\r\nPermission is hereby granted, free of charge, to any person obtaining a copy\r\nof this software and associated documentation files (the \"Software\"), to deal\r\nin the Software without restriction, including without limitation the rights\r\nto use, copy, modify, merge, publish, distribute, sublicense, and\/or sell\r\ncopies of the Software, and to permit persons to whom the Software is\r\nfurnished to do so, subject to the following conditions:\r\n\r\nThe above copyright notice and this permission notice shall be included in all\r\ncopies or substantial portions of the Software.\r\n\r\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\r\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\r\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\r\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\r\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\r\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\r\nSOFTWARE.\r\n\"\"\"\r\nimport pandas as pd\r\nimport os\r\nimport argparse\r\n\r\ndef main(base_dir, invoice_id=None, single_csv_path=None, all_csv_path=None):\r\n    # \u51fa\u529b\u30d5\u30a1\u30a4\u30eb\u540d\u306e\u30c7\u30d5\u30a9\u30eb\u30c8\u8a2d\u5b9a\uff08\u6307\u5b9a\u304c\u306a\u3051\u308c\u3070\u6a19\u6e96\u306e\u30d5\u30a1\u30a4\u30eb\u540d\u3092\u4f7f\u7528\uff09\r\n    if single_csv_path is None:\r\n        single_csv_path = os.path.join(base_dir, \"structured_invoice_export0.csv\")\r\n    if all_csv_path is None:\r\n        all_csv_path = os.path.join(base_dir, \"structured_invoice_export1.csv\")\r\n\r\n    # --- CSV \u8aad\u307f\u8fbc\u307f ---\r\n    # \u5404\u7a2e\u30de\u30b9\u30bf\u30d5\u30a1\u30a4\u30eb\u3068\u53d6\u5f15\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u8fbc\u3080\r\n    invoice_df = pd.read_csv(os.path.join(base_dir, \"Invoice.csv\"), dtype=str)\r\n    buyer_df = pd.read_csv(os.path.join(base_dir, \"Buyer.csv\"), dtype=str)\r\n    seller_df = pd.read_csv(os.path.join(base_dir, \"Seller.csv\"), dtype=str)\r\n    tax_df = pd.read_csv(os.path.join(base_dir, \"TaxBreakdown.csv\"), dtype=str)\r\n    line_df = pd.read_csv(os.path.join(base_dir, \"InvoiceLine.csv\"), dtype=str)\r\n    item_df = pd.read_csv(os.path.join(base_dir, \"Item.csv\"), dtype=str)\r\n\r\n    # --- \u30ab\u30e9\u30e0\u5b9a\u7fa9 ---\r\n    # \u51fa\u529bCSV\u306e\u5217\u9806\u3068\u69cb\u9020\u3092\u5b9a\u7fa9\u3059\u308b\r\n    columns = [\r\n        \"dInvoice\", \"dTaxBreakdown\", \"dInvoiceLine\",\r\n        \"Invoice.ID\", \"issueDate\", \"typeCode\", \"dueDate\",\r\n        \"Buyer.name\", \"Seller.name\", \"Seller.taxID\",\r\n        \"sumOfLineNetAmount\", \"totalAmountWithoutTax\", \"totalTaxAmount\", \"totalAmountWithTax\",\r\n        \"TaxBreakdown.taxCategoryCode\", \"TaxBreakdown.taxCategoryRate\", \"TaxBreakdown.taxCategoryTaxAmount\",\r\n        \"InvoiceLine.ID\", \"InvoiceLine.netAmount\", \"InvoiceLine.quantity\", \"InvoiceLine.uom\",\r\n        \"Item.ID\", \"Item.name\", \"Item.price\", \"Item.baseQuantity\", \"Item.uom\",\r\n        \"Item.taxCategoryCode\", \"Item.taxCategoryRate\"\r\n    ]\r\n\r\n    # --- \u5358\u4e00\u8acb\u6c42\u66f8\u306e\u51fa\u529b\u51e6\u7406 ---\r\n    def export_single_invoice(inv_id):\r\n        rows = []\r\n        # \u5bfe\u8c61\u306e\u8acb\u6c42\u66f8\u30ec\u30b3\u30fc\u30c9\u3092\u62bd\u51fa\r\n        i = invoice_df[invoice_df[\"ID\"] == inv_id]\r\n        if i.empty:\r\n            raise ValueError(f\"Invoice {inv_id} not found.\")\r\n        i = i.iloc[0]\r\n        # Buyer\u304a\u3088\u3073Seller\u60c5\u5831\u3092\u53d6\u5f97\r\n        b = buyer_df[buyer_df[\"ID\"] == i[\"buyerID\"]].iloc[0]\r\n        s = seller_df[seller_df[\"ID\"] == i[\"sellerID\"]].iloc[0]\r\n\r\n        # \u8acb\u6c42\u66f8\u30d8\u30c3\u30c0\u884c\u3092\u8ffd\u52a0\r\n        rows.append({\r\n            \"dInvoice\": 1, \"dTaxBreakdown\": pd.NA, \"dInvoiceLine\": pd.NA,\r\n            \"Invoice.ID\": i[\"ID\"], \"issueDate\": i.get(\"issueDate\", \"\"), \"typeCode\": i.get(\"typeCode\", \"\"),\r\n            \"dueDate\": i.get(\"dueDate\", \"\"), \"Buyer.name\": b.get(\"name\", \"\"), \"Seller.name\": s.get(\"name\", \"\"),\r\n            \"Seller.taxID\": s.get(\"taxID\", \"\"), \"sumOfLineNetAmount\": i.get(\"sumOfLineNetAmount\", \"\"),\r\n            \"totalAmountWithoutTax\": i.get(\"totalAmountWithoutTax\", \"\"), \"totalTaxAmount\": i.get(\"totalTaxAmount\", \"\"),\r\n            \"totalAmountWithTax\": i.get(\"totalAmountWithTax\", \"\"),\r\n            **{k: \"\" for k in columns[14:]}\r\n        })\r\n\r\n        # \u7a0e\u60c5\u5831\u306e\u51fa\u529b\uff08\u30e6\u30cb\u30fc\u30af\u306a\u30ab\u30c6\u30b4\u30ea\u3054\u3068\u306b\u4e26\u3079\u66ff\u3048\u3066\u9806\u756a\u3092\u632f\u308b\uff09\r\n        tb = tax_df[tax_df[\"invoiceID\"] == inv_id].copy()\r\n        tb[\"key\"] = tb[\"taxCategoryCode\"].fillna('') + \"|\" + tb[\"taxCategoryRate\"].fillna('')\r\n        tb[\"dTaxBreakdown\"] = tb[\"key\"].factorize()[0] + 1\r\n\r\n        for _, t in tb.iterrows():\r\n            row = {k: \"\" for k in columns}\r\n            row.update({\r\n                \"dInvoice\": 1,\r\n                \"dTaxBreakdown\": t[\"dTaxBreakdown\"],\r\n                \"TaxBreakdown.taxCategoryCode\": t.get(\"taxCategoryCode\", \"\"),\r\n                \"TaxBreakdown.taxCategoryRate\": t.get(\"taxCategoryRate\", \"\"),\r\n                \"TaxBreakdown.taxCategoryTaxAmount\": t.get(\"taxCategoryTaxAmount\", \"\")\r\n            })\r\n            rows.append(row)\r\n\r\n        # \u660e\u7d30\u884c\u60c5\u5831\u306e\u51fa\u529b\r\n        il = line_df[line_df[\"invoiceID\"] == inv_id].copy()\r\n        il[\"dInvoiceLine\"] = il[\"ID\"].factorize()[0] + 1\r\n\r\n        for _, l in il.iterrows():\r\n            item = item_df[item_df[\"ID\"] == l[\"itemID\"]].iloc[0]\r\n            row = {k: \"\" for k in columns}\r\n            row.update({\r\n                \"dInvoice\": 1,\r\n                \"dInvoiceLine\": l[\"dInvoiceLine\"],\r\n                \"InvoiceLine.ID\": l.get(\"ID\", \"\"),\r\n                \"InvoiceLine.netAmount\": l.get(\"netAmount\", \"\"),\r\n                \"InvoiceLine.quantity\": l.get(\"quantity\", \"\"),\r\n                \"InvoiceLine.uom\": l.get(\"uom\", \"\"),\r\n                \"Item.ID\": item.get(\"ID\", \"\"), \"Item.name\": item.get(\"name\", \"\"),\r\n                \"Item.price\": item.get(\"price\", \"\"), \"Item.baseQuantity\": item.get(\"baseQuantity\", \"\"),\r\n                \"Item.uom\": item.get(\"uom\", \"\"), \"Item.taxCategoryCode\": item.get(\"taxCategoryCode\", \"\"),\r\n                \"Item.taxCategoryRate\": item.get(\"taxCategoryRate\", \"\")\r\n            })\r\n            rows.append(row)\r\n\r\n        return pd.DataFrame(rows, columns=columns)\r\n\r\n    # --- \u5168\u8acb\u6c42\u66f8\u306e\u51fa\u529b\u51e6\u7406 ---\r\n    def export_all_invoices():\r\n        rows = []\r\n        invoice_df_sorted = invoice_df.sort_values(\"ID\").copy()\r\n        invoice_df_sorted[\"dInvoice\"] = range(1, len(invoice_df_sorted) + 1)\r\n\r\n        for _, i in invoice_df_sorted.iterrows():\r\n            d_inv = i[\"dInvoice\"]\r\n            b = buyer_df[buyer_df[\"ID\"] == i[\"buyerID\"]].iloc[0]\r\n            s = seller_df[seller_df[\"ID\"] == i[\"sellerID\"]].iloc[0]\r\n\r\n            # \u8acb\u6c42\u66f8\u30d8\u30c3\u30c0\u884c\r\n            rows.append({\r\n                \"dInvoice\": d_inv, \"dTaxBreakdown\": pd.NA, \"dInvoiceLine\": pd.NA,\r\n                \"Invoice.ID\": i[\"ID\"], \"issueDate\": i.get(\"issueDate\", \"\"), \"typeCode\": i.get(\"typeCode\", \"\"),\r\n                \"dueDate\": i.get(\"dueDate\", \"\"), \"Buyer.name\": b.get(\"name\", \"\"), \"Seller.name\": s.get(\"name\", \"\"),\r\n                \"Seller.taxID\": s.get(\"taxID\", \"\"), \"sumOfLineNetAmount\": i.get(\"sumOfLineNetAmount\", \"\"),\r\n                \"totalAmountWithoutTax\": i.get(\"totalAmountWithoutTax\", \"\"), \"totalTaxAmount\": i.get(\"totalTaxAmount\", \"\"),\r\n                \"totalAmountWithTax\": i.get(\"totalAmountWithTax\", \"\"),\r\n                **{k: \"\" for k in columns[14:]}\r\n            })\r\n\r\n            # \u7a0e\u30d6\u30ec\u30fc\u30af\u30c0\u30a6\u30f3\u884c\r\n            tb = tax_df[tax_df[\"invoiceID\"] == i[\"ID\"]].copy()\r\n            tb[\"key\"] = tb[\"taxCategoryCode\"].fillna('') + \"|\" + tb[\"taxCategoryRate\"].fillna('')\r\n            tb[\"dTaxBreakdown\"] = tb[\"key\"].factorize()[0] + 1\r\n\r\n            for _, t in tb.iterrows():\r\n                row = {k: \"\" for k in columns}\r\n                row.update({\r\n                    \"dInvoice\": d_inv,\r\n                    \"dTaxBreakdown\": t[\"dTaxBreakdown\"],\r\n                    \"TaxBreakdown.taxCategoryCode\": t.get(\"taxCategoryCode\", \"\"),\r\n                    \"TaxBreakdown.taxCategoryRate\": t.get(\"taxCategoryRate\", \"\"),\r\n                    \"TaxBreakdown.taxCategoryTaxAmount\": t.get(\"taxCategoryTaxAmount\", \"\")\r\n                })\r\n                rows.append(row)\r\n\r\n            # \u660e\u7d30\u884c\r\n            il = line_df[line_df[\"invoiceID\"] == i[\"ID\"]].copy()\r\n            il[\"dInvoiceLine\"] = il[\"ID\"].factorize()[0] + 1\r\n\r\n            for _, l in il.iterrows():\r\n                item = item_df[item_df[\"ID\"] == l[\"itemID\"]].iloc[0]\r\n                row = {k: \"\" for k in columns}\r\n                row.update({\r\n                    \"dInvoice\": d_inv,\r\n                    \"dInvoiceLine\": l[\"dInvoiceLine\"],\r\n                    \"InvoiceLine.ID\": l.get(\"ID\", \"\"),\r\n                    \"InvoiceLine.netAmount\": l.get(\"netAmount\", \"\"),\r\n                    \"InvoiceLine.quantity\": l.get(\"quantity\", \"\"),\r\n                    \"InvoiceLine.uom\": l.get(\"uom\", \"\"),\r\n                    \"Item.ID\": item.get(\"ID\", \"\"), \"Item.name\": item.get(\"name\", \"\"),\r\n                    \"Item.price\": item.get(\"price\", \"\"), \"Item.baseQuantity\": item.get(\"baseQuantity\", \"\"),\r\n                    \"Item.uom\": item.get(\"uom\", \"\"), \"Item.taxCategoryCode\": item.get(\"taxCategoryCode\", \"\"),\r\n                    \"Item.taxCategoryRate\": item.get(\"taxCategoryRate\", \"\")\r\n                })\r\n                rows.append(row)\r\n\r\n        return pd.DataFrame(rows, columns=columns)\r\n\r\n    # --- \u51e6\u7406\u5206\u5c90 ---\r\n    if invoice_id:\r\n        # \u5358\u4e00\u8acb\u6c42\u66f8\u51fa\u529b\r\n        if single_csv_path:\r\n            df0 = export_single_invoice(invoice_id)\r\n            for col in [\"dInvoice\", \"dTaxBreakdown\", \"dInvoiceLine\"]:\r\n                df0[col] = df0[col].apply(lambda x: pd.NA if not str(x).strip().isdigit() else int(x)).astype(\"Int64\")\r\n            df0.to_csv(single_csv_path, index=False, encoding=\"utf-8-sig\")\r\n            print(f\"\u2705 Exported: {single_csv_path}\")\r\n        # \u5168\u8acb\u6c42\u66f8\u3082\u51fa\u529b\r\n        if all_csv_path:\r\n            df1 = export_all_invoices()\r\n            for col in [\"dInvoice\", \"dTaxBreakdown\", \"dInvoiceLine\"]:\r\n                df1[col] = df1[col].apply(lambda x: pd.NA if not str(x).strip().isdigit() else int(x)).astype(\"Int64\")\r\n            df1.to_csv(all_csv_path, index=False, encoding=\"utf-8-sig\")\r\n            print(f\"\u2705 Exported: {all_csv_path}\")\r\n    else:\r\n        # \u5168\u8acb\u6c42\u66f8\u51fa\u529b\uff08\u5358\u4f53\u8acb\u6c42\u66f8ID\u672a\u6307\u5b9a\u6642\uff09\r\n        df1 = export_all_invoices()\r\n        for col in [\"dInvoice\", \"dTaxBreakdown\", \"dInvoiceLine\"]:\r\n            df1[col] = df1[col].apply(lambda x: pd.NA if not str(x).strip().isdigit() else int(x)).astype(\"Int64\")\r\n        df1.to_csv(all_csv_path, index=False, encoding=\"utf-8-sig\")\r\n        print(f\"\u2705 Exported: {all_csv_path}\")\r\n\r\nif __name__ == \"__main__\":\r\n    parser = argparse.ArgumentParser(description=\"\u69cb\u9020\u5316\u30a4\u30f3\u30dc\u30a4\u30b9CSV\u30a8\u30af\u30b9\u30dd\u30fc\u30c8\")\r\n    parser.add_argument(\"--base_dir\", required=True, help=\"CSV\u30d5\u30a1\u30a4\u30eb\u683c\u7d0d\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\")\r\n    parser.add_argument(\"--invoice_id\", help=\"\u5358\u4e00\u8acb\u6c42\u66f8ID\uff08\u6307\u5b9a\u6642\u306f\u305d\u306e\u8acb\u6c42\u66f8\u3092\u51fa\u529b\uff09\")\r\n    parser.add_argument(\"--single_csv_path\", help=\"\u5358\u4e00\u8acb\u6c42\u66f8\u306e\u51fa\u529b\u5148\u30d5\u30a1\u30a4\u30eb\u30d1\u30b9\")\r\n    parser.add_argument(\"--all_csv_path\", help=\"\u5168\u8acb\u6c42\u66f8\u306e\u51fa\u529b\u5148\u30d5\u30a1\u30a4\u30eb\u30d1\u30b9\")\r\n    args = parser.parse_args()\r\n    main(\r\n        args.base_dir,\r\n        invoice_id=args.invoice_id,\r\n        single_csv_path=args.single_csv_path,\r\n        all_csv_path=args.all_csv_path\r\n    )<\/code><\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
          \n
          \nLast updated 2025-06-02 07:51:01 +0900\n<\/div>\n<\/div>\n
          \n
          \u76ee\u6b21<\/div>\n