Feature/create faculty parser

.gitignore

@@ -158,3 +158,5 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+~*.xlsx

src/models/base_info.py

@@ -4,9 +4,9 @@ def __init__(self, school_code="", president="") -> None:
         self.__president: str = president
 
     @property
-    def school_code(self):
+    def school_code(self) -> str:
         return self.__school_code
 
     @property
-    def president(self):
+    def president(self) -> str:
         return self.__president

src/models/faculty.py

@@ -0,0 +1,22 @@
+class Department:
+    def __init__(self, name: str) -> None:
+        self.__name: str = name
+        pass
+
+    @property
+    def name(self) -> str:
+        return self.__name
+
+
+class Faculty:
+    def __init__(self, name: str, departments: list[Department]) -> None:
+        self.__name: str = name
+        self.__departments: list[Department] = departments
+
+    @property
+    def name(self) -> str:
+        return self.__name
+
+    @property
+    def departments(self) -> list[Department]:
+        return self.__departments

src/parser/base_info_parser.py

@@ -2,57 +2,25 @@
 from openpyxl.worksheet.worksheet import Worksheet
 from openpyxl.cell.cell import Cell
 from src.models.base_info import BaseInfo
+from src.parser.parser import Parser
 
 
-class BaseInfoParser:
-    def __init__(self, sheet: Worksheet) -> None:
-        self.__sheet = sheet
-
+class BaseInfoParser(Parser):
     def parse(self) -> BaseInfo:
         """
         学校コードのセルを基準にデータを検索しパースする。
         """
         base_cell: Optional[Cell] = self._search_cell(
             "学校コード",
-            self.__sheet,
+            self._sheet,
         )
         if not base_cell:
             raise ValueError("学校コードが見つかりませんでした。")
         return BaseInfo(
-            school_code=self.__sheet.cell(
+            school_code=self._sheet.cell(
                 row=base_cell.row + 1, column=base_cell.column
             ).value,
-            president=self.__sheet.cell(
+            president=self._sheet.cell(
                 row=base_cell.row + 1, column=base_cell.column + 1
             ).value,
         )
-
-    def _search_cell(self, keyword: str, sheet: Worksheet) -> Optional[Cell]:
-        """
-        keywordをシートから検索し、最初に見つけたセルを返す。
-        検索はA1→A2→B2→B1→A3→B3→C3→C2→C1
-        のようにA1から(max_row, max_column)に直線を引くような方向で検索をする。
-
-        Args:
-            keyword (str): 検索するキーワード
-            sheet (Worksheet): 検索対象のシート
-        """
-
-        for i in range(sheet.max_column):
-            column = i + 1
-            # columnを縦に検索
-            for j in range(column - 1):
-                row = i + 1
-                column = j + 1
-                if sheet.cell(row=row, column=column).value == keyword:
-                    return sheet.cell(row=row, column=column)
-
-            # rowとcolumnが同じセルを検索
-            if sheet.cell(row=column, column=column).value == keyword:
-                return sheet.cell(row=column, column=column)
-
-            # rowを右から左に検索
-            for j in reversed(range(column - 1)):
-                row = j + 1
-                if sheet.cell(row=row, column=column).value == keyword:
-                    return sheet.cell(row=row, column=column)

src/parser/faculty_parser.py

@@ -0,0 +1,49 @@
+from typing import Optional
+from openpyxl.worksheet.worksheet import Worksheet
+from openpyxl.cell.cell import Cell
+from src.models.faculty import Department, Faculty
+from src.parser.parser import Parser
+
+
+class FacultyParser(Parser):
+    def parse(self) -> list[Faculty]:
+        """
+        学部のセルを基準にデータを検索しパースする。
+        """
+        base_cell: Optional[Cell] = self._search_cell(
+            "学部",
+            self._sheet,
+        )
+        if not base_cell:
+            raise ValueError('"学部"の文字が見つかりませんでした。')
+
+        row = base_cell.row + 3  # 学部の3行下から開始
+        column = base_cell.column
+        faculties: list[Faculty] = []
+        # 空白のセルが見つかるまで、下を検索
+        while self._sheet.cell(row=row, column=column).value not in [None, ""]:
+            faculty_name = self._sheet.cell(row=row, column=column).value
+
+            # 初めて見つけた学科の場合は新規追加
+            if faculty_name not in [f.name for f in faculties]:
+                faculties.append(
+                    Faculty(
+                        self._sheet.cell(row=row, column=column).value,
+                        [
+                            Department(
+                                self._sheet.cell(row=row, column=column + 2).value,
+                            )
+                        ],
+                    )
+                )
+            else:
+                for faculty in faculties:
+                    if faculty.name == faculty_name:
+                        faculty.departments.append(
+                            Department(
+                                self._sheet.cell(row=row, column=column + 2).value
+                            ),
+                        ),
+            row += 1
+
+        return faculties

src/parser/parser.py

@@ -0,0 +1,43 @@
+from abc import ABC, abstractmethod
+from openpyxl.worksheet.worksheet import Worksheet
+from openpyxl.cell.cell import Cell
+from typing import Optional
+
+
+class Parser(ABC):
+    def __init__(self, sheet: Worksheet) -> None:
+        self._sheet = sheet
+
+    @abstractmethod
+    def parse():
+        pass
+
+    def _search_cell(self, keyword: str, sheet: Worksheet) -> Optional[Cell]:
+        """
+        keywordをシートから検索し、最初に見つけたセルを返す。
+        検索はA1→A2→B2→B1→A3→B3→C3→C2→C1
+        のようにA1から(max_row, max_column)に直線を引くような方向で検索をする。
+
+        Args:
+            keyword (str): 検索するキーワード
+            sheet (Worksheet): 検索対象のシート
+        """
+        # 行か列の大きい方でループ
+        for i in range(max([sheet.max_column, sheet.max_row])):
+            column = i + 1
+            # columnを縦に検索
+            for j in range(column - 1):
+                row = i + 1
+                column = j + 1
+                if sheet.cell(row=row, column=column).value == keyword:
+                    return sheet.cell(row=row, column=column)
+
+            # rowとcolumnが同じセルを検索
+            if sheet.cell(row=column, column=column).value == keyword:
+                return sheet.cell(row=column, column=column)
+
+            # rowを右から左に検索
+            for j in reversed(range(column - 1)):
+                row = j + 1
+                if sheet.cell(row=row, column=column).value == keyword:
+                    return sheet.cell(row=row, column=column)

tests/parser/single_sheet_test_base.py

@@ -0,0 +1,36 @@
+from abc import ABC, abstractmethod
+import openpyxl
+from openpyxl.worksheet.worksheet import Worksheet
+import os
+import pytest
+from typing import Generic, TypeVar
+
+from src.parser.parser import Parser
+
+T = TypeVar("T")
+
+
+class SingleSheetTestBase(ABC, Generic[T]):
+    EXCEL_FILE_PATH_1 = f"{os.path.dirname(__file__)}/files/single_sheet_file1.xlsx"
+    EXCEL_FILE_PATH_2 = f"{os.path.dirname(__file__)}/files/single_sheet_file2.xlsx"
+    __book: openpyxl.Workbook
+
+    def setup_method(self, method):
+        pass
+
+    def teardown_method(self, method):
+        if self.__book:
+            self.__book.close()
+
+    def get_sheet(self, path) -> Worksheet:
+        self.__book = openpyxl.load_workbook(path)
+        return self.__book[self.__book.sheetnames[0]]
+
+    def parse(self, path: str) -> T:
+        sheet = self.get_sheet(path)
+        parser = self.get_parser(sheet)
+        return parser.parse()
+
+    @abstractmethod
+    def get_parser(self, sheet: Worksheet) -> Parser:
+        pass

tests/parser/test_base_info_parser.py

@@ -1,56 +1,33 @@
-import openpyxl
 from openpyxl.worksheet.worksheet import Worksheet
-import os
 import pytest
 from src.models.base_info import BaseInfo
 from src.parser.base_info_parser import BaseInfoParser
+from src.parser.parser import Parser
+from tests.parser.single_sheet_test_base import SingleSheetTestBase
 
 
-class TestBaseInfoParser:
-    EXCEL_FILE_PATH_1 = f"{os.path.dirname(__file__)}/files/single_sheet_file1.xlsx"
-    EXCEL_FILE_PATH_2 = f"{os.path.dirname(__file__)}/files/single_sheet_file2.xlsx"
-    __book: openpyxl.Workbook
-
-    @pytest.fixture
-    def wrap(self):
-        self.set_up()
-        yield
-        self.tear_down()
-
-    def set_up(self):
-        pass
-
-    def tear_down(self):
-        if self.__book:
-            self.__book.close()
-
-    def get_sheet(self, path) -> Worksheet:
-        self.__book = openpyxl.load_workbook(path)
-        return self.__book[self.__book.sheetnames[0]]
-
-    def parse(self, path: str) -> BaseInfo:
-        sheet = self.get_sheet(path)
-        parser = BaseInfoParser(sheet)
-        return parser.parse()
+class TestBaseInfoParser(SingleSheetTestBase[BaseInfo]):
+    def get_parser(self, sheet: Worksheet) -> Parser:
+        return BaseInfoParser(sheet)
 
     @pytest.mark.parametrize(
-        "path, expect",
+        "path, exp",
         [
-            (EXCEL_FILE_PATH_1, "F101110100010"),
-            (EXCEL_FILE_PATH_2, "F123310106522"),
+            (SingleSheetTestBase.EXCEL_FILE_PATH_1, "F101110100010"),
+            (SingleSheetTestBase.EXCEL_FILE_PATH_2, "F123310106522"),
         ],
     )
-    def test_should_parse_school_code(self, path: str, expect: str):
+    def test_should_parse_school_code(self, path: str, exp: str):
         base_info = self.parse(path)
-        assert base_info.school_code == expect
+        assert base_info.school_code == exp
 
     @pytest.mark.parametrize(
-        "path, expect",
+        "path, exp",
         [
-            (EXCEL_FILE_PATH_1, "寳金 清博"),
-            (EXCEL_FILE_PATH_2, "景山　節"),
+            (SingleSheetTestBase.EXCEL_FILE_PATH_1, "寳金 清博"),
+            (SingleSheetTestBase.EXCEL_FILE_PATH_2, "景山　節"),
         ],
     )
-    def test_should_parse_president(self, path: str, expect: str):
+    def test_should_parse_president(self, path: str, exp: str):
         base_info = self.parse(path)
-        assert base_info.president == expect
+        assert base_info.president == exp