Merge pull request #13 from gist-helper/develop

Develop

.gitignore

@@ -3,3 +3,6 @@
 *.pyc
 .venv
 .DS_Store
+.idea
+
+!config.json

README.md

@@ -1,6 +1,11 @@
-1. To test the parsing code 
+0. git checkout release
+
+1. To test the parsing code
+
 python parsing.py
 
 2. To apply the parsing result to server
-You need to specify the ip and port of backend server. 
-python parsing.py http://ip:port/meals/create
+
+(You need to specify the ip and port of backend server)
+
+python parsing.py http://ip:port/meals/create

config.json

@@ -0,0 +1,7 @@
+{
+  "filepath_bldg1_1_kor" : "./1_1_kor.xlsx",
+  "filepath_bldg1_1_eng" : "./1_1_eng.xlsx",
+  "filepath_bldg1_2_kor" : "./1_2_kor.xlsx",
+  "filepath_bldg1_2_eng" : "./1_2_eng.xlsx",
+  "filepath_bldg2" : "./2.xlsx"
+}

meal.py

@@ -8,8 +8,8 @@ class Meal:
     kind: str
     menu: str
     special: str
-    
-    def __init__(self, bldgType, langType, dateType, kindType, 
+
+    def __init__(self, bldgType, langType, dateType, kindType,
                  bldg, date, kind, menu, special) -> None:
         self.bldgType = bldgType
         self.langType = langType
@@ -21,12 +21,14 @@ def __init__(self, bldgType, langType, dateType, kindType,
         self.menu = menu
         self.special = special
 
+
 class MealWrapper:
     meal: Meal
 
     def __init__(self) -> None:
         self.meal = Meal()
 
+
 # constant
 KOR = 0
 ENG = 1
@@ -36,62 +38,79 @@ def __init__(self) -> None:
 BLDG2_1ST = 2
 
 BREAKFAST = 0
-LUNCH     = 1
-DINNER    = 2
-SPECIAL   = 3
+LUNCH = 1
+DINNER = 2
+SPECIAL = 3
 
 DATE_LEN = 10
-DATE = ["Mon", "Tue", "Wed", "Thr", "Fri", "Sat", "Sun"]
+DATE_1st = ["Mon", "Tue", "Wed", "Thr", "Fri"]  # 1학 요일
+DATE_2nd = ["Mon", "Tue", "Wed", "Thr", "Fri", "Sat", "Sun"]  # 2학 요일
 
 # kind of meal
-MEAL_KIND_KOR = [ "조식",  #0
-                  "중식",  #1
-                  "석식" ] #2
-MEAL_KIND_ENG = [ "Breakfast",   #0
-                  "Lunch",       #1
-                  "Dinner"     ] #2
+MEAL_KIND_KOR = ["조식",  # 0
+                 "중식",  # 1
+                 "석식"]  # 2
+MEAL_KIND_ENG = ["Breakfast",  # 0
+                 "Lunch",  # 1
+                 "Dinner"]  # 2
 
 # kind of building according to building type
-BLDG_KIND_KOR = [ "1학생회관 1층",  #0
-                  "1학생회관 2층",  #1
-                  "2학생회관 1층" ] #2
-BLDG_KIND_ENG = [ "Student Union Bldg.1 1st floor",  #0
-                  "Student Union Bldg.1 2nd floor",  #1
-                  "Student Union Bldg.2 1st floor" ] #2
-                  
+BLDG_KIND_KOR = ["1학생회관 1층",  # 0
+                 "1학생회관 2층",  # 1
+                 "2학생회관 1층"]  # 2
+BLDG_KIND_ENG = ["Student Union Bldg.1 1st floor",  # 0
+                 "Student Union Bldg.1 2nd floor",  # 1
+                 "Student Union Bldg.2 1st floor"]  # 2
+
 # excel column according to building type
-EXCEL_COL_BLDG0 = []                                                               #Bldg.1 1st
-EXCEL_COL_BLDG1 = []                                                               #Bldg.2 2nd
-EXCEL_COL_BLDG2 = ["A", "B", "C", "Mon", "Tue", "Wed", "Thr", "Fri", "Sat", "Sun"] #Bldg.2 1st
+# EXCEL_COL_BLDG0 = ["A", "B", "Mon", "Mon", "Tue", "Tue", "Wed", "Wed", "Thr", "Thr", "Fri", "Fri"]  # Bldg.1 1st
+# EXCEL_COL_BLDG1 = ["A", "Mon", "Tue", "Wed", "Thr", "Fri"]  # Bldg.1 2nd
+# EXCEL_COL_BLDG2 = ["A", "B", "C", "Mon", "Tue", "Wed", "Thr", "Fri", "Sat", "Sun"]  # Bldg.2 1st
+'''
+column 예외 존재 (2023.2.6의 1학1층한글 엑셀보면 쓸모없는 col이 있을 수 있음)
+이를 위해 요일 있는 행의 index로 접근
+'''
+EXCEL_COL_BLDG0 = [2, 11]
+EXCEL_COL_BLDG0_EXCEPT = []
+EXCEL_COL_BLDG1 = [1, 6]
+EXCEL_COL_BLDG2 = [3, 10]
 
-DATE_INDEX_BLDG0 = 0 #Bldg.1 1st
-DATE_INDEX_BLDG1 = 0 #Bldg.2 2nd
-DATE_INDEX_BLDG2 = 1 #Bldg.2 1st
+DATE_INDEX_BLDG0 = 4  # Bldg.1 1st
+DATE_INDEX_BLDG1 = 1  # Bldg.1 2nd
+DATE_INDEX_BLDG2 = 1  # Bldg.2 1st
 
-INDEX_ENDPOINTS_BLDG0 = []                                      #Bldg.1 1st
-INDEX_ENDPOINTS_BLDG1 = []                                      #Bldg.2 2nd
-INDEX_ENDPOINTS_BLDG2 = [[2, 12], [12, 20], [22, 29], [20, 22]] #Bldg.2 1st
+INDEX_ENDPOINTS_BLDG0 = [[5, 15], [15, 22], [23, 30], [22, 23]]  # Bldg.1 1st
+INDEX_ENDPOINTS_BLDG1 = [[0, 0], [2, 12], [0, 0], [0, 0]]        # Bldg.1 2nd
+INDEX_ENDPOINTS_BLDG1_EXCEPT = [4, 6] # 1학2층 엑셀은 숨겨진 행(5,7번) 존재하고 dummy 들어가있어 제외해야함.
+INDEX_ENDPOINTS_BLDG2 = [[2, 12], [12, 20], [22, 29], [20, 22]]  # Bldg.2 1st
 
 # allergy type according to allergy code
-ALGY_ING_KOR = [ "계란류", "우유", "메밀", "땅콩", "대두", 
-                 "밀", "고등어", "게", "새우", "돼지고기", 
-                 "복숭아", "토마토", "아황산류", "호두", "닭고기",
-                 "쇠고기", "오징어", "조개류", "잣" ]
-ALGY_ING_ENG = [ "egg", "milk", "buckwheat", "peanut", "soybean", 
-                 "wheat", "mackerel", "crab", "shrimp", "pork", 
-                 "peach", "tomato", "sulgite", "walnut", "chicken", 
-                 "beef", "squid", "shellfish", "pine nut" ]
+ALGY_1_ING_KOR = ["난류", "우유", "메밀", "대두", "땅콩", "밀",
+                  "새우", "돼지고기", "닭고기", "쇠고기", "오징어",
+                  "고등어", "조개류", "토마토", "아황산염"]
+ALGY_1_ING_ENG = ["egg", ",milk", "buckwheat", "soybean", "peanut", "wheat",
+                  "shrimp", "pork", "chicken", "beef", "squid",
+                  "mackerel", "shellfish", "tomato", "sulgite"]
+ALGY_2_ING_KOR = ["계란류", "우유", "메밀", "땅콩", "대두",
+                  "밀", "고등어", "게", "새우", "돼지고기",
+                  "복숭아", "토마토", "아황산류", "호두", "닭고기",
+                  "쇠고기", "오징어", "조개류", "잣"]
+ALGY_2_ING_ENG = ["egg", "milk", "buckwheat", "peanut", "soybean",
+                  "wheat", "mackerel", "crab", "shrimp", "pork",
+                  "peach", "tomato", "sulgite", "walnut", "chicken",
+                  "beef", "squid", "shellfish", "pine nut"]
 
 # [langType]
-ALGY_ING       = [ALGY_ING_KOR, ALGY_ING_ENG]
+ALGY_ING_1 = [ALGY_1_ING_KOR, ALGY_1_ING_ENG]
+ALGY_ING_2 = [ALGY_2_ING_KOR, ALGY_2_ING_ENG]
 
 # [langType][kindType]
-MEAL_KIND      = [MEAL_KIND_KOR, MEAL_KIND_ENG]
+MEAL_KIND = [MEAL_KIND_KOR, MEAL_KIND_ENG]
 
 # [langType][bldgType]
-BLDG_KIND      = [BLDG_KIND_KOR, BLDG_KIND_ENG]
+BLDG_KIND = [BLDG_KIND_KOR, BLDG_KIND_ENG]
 
 # [bldgType]
-EXCEL_COL_BLDG  = [EXCEL_COL_BLDG0, EXCEL_COL_BLDG1, EXCEL_COL_BLDG2]
-DATE_INDEX      = [DATE_INDEX_BLDG0, DATE_INDEX_BLDG1, DATE_INDEX_BLDG2]
-INDEX_ENDPOINTS  = [INDEX_ENDPOINTS_BLDG0, INDEX_ENDPOINTS_BLDG1, INDEX_ENDPOINTS_BLDG2]
+EXCEL_COL_BLDG = [EXCEL_COL_BLDG0, EXCEL_COL_BLDG1, EXCEL_COL_BLDG2]
+DATE_INDEX = [DATE_INDEX_BLDG0, DATE_INDEX_BLDG1, DATE_INDEX_BLDG2]
+INDEX_ENDPOINTS = [INDEX_ENDPOINTS_BLDG0, INDEX_ENDPOINTS_BLDG1, INDEX_ENDPOINTS_BLDG2]

parsing.py

@@ -1,40 +1,119 @@
 import sys
 import os
+from os.path import exists
 import requests
 import json
 import pandas as pd
-from meal import Meal
+from meal import Meal, INDEX_ENDPOINTS_BLDG1_EXCEPT
 from meal import KOR, ENG
 from meal import BREAKFAST, LUNCH, DINNER
-from meal import BLDG1_1ST, BLDG1_2ND, BLDG2_1ST 
-from meal import DATE_LEN, DATE
+from meal import BLDG1_1ST, BLDG1_2ND, BLDG2_1ST
+from meal import DATE_LEN, DATE_2nd,DATE_1st
 from meal import MEAL_KIND
 from meal import BLDG_KIND
 from meal import EXCEL_COL_BLDG, INDEX_ENDPOINTS, DATE_INDEX
 from util import ComplexEncoder, sanitize_menu
-from util import parsing_date, parsing_meal 
+from util import parsing_date, parsing_meal
+
 
 def parsing(excel_path: str, bldgType: int, langType: int) -> list:
-    col        = EXCEL_COL_BLDG [bldgType]
-    endpoint   = INDEX_ENDPOINTS[bldgType]
-    bldg       = BLDG_KIND      [langType][bldgType]
-    time_index = DATE_INDEX     [bldgType]
-
-    sheet = pd.read_excel(excel_path, sheet_name=langType, 
-                          index_col=None, header=None, names=col, engine='openpyxl')
-
+    col           = EXCEL_COL_BLDG [bldgType]
+    endpoint      = INDEX_ENDPOINTS[bldgType]
+    bldg          = BLDG_KIND      [langType][bldgType]
+    time_index    = DATE_INDEX     [bldgType]
+    start_col_idx = col[0]
+    end_col_idx   = col[1]
+
     parsing_result = []
-    for (dateType, date_str) in enumerate(DATE):
-        date_sheet = sheet[date_str]
-        date = parsing_date(time_index, date_sheet)
-        for kindType in [BREAKFAST, LUNCH, DINNER]:
-            kind = MEAL_KIND[langType][kindType]
-            menu, speical = parsing_meal[kindType](endpoint, date_sheet, langType, dateType)
-            meal = Meal(bldgType, langType, dateType, kindType, 
-                    bldg, date, kind, menu, speical)
-            parsing_result.append(meal.__dict__)        
+
+    # 1학 1층 한글
+    if bldgType == BLDG1_1ST and langType == 0:
+        xl = pd.read_excel(excel_path, sheet_name=None,
+                           index_col=None, header=None, names=None, engine='openpyxl')
+
+        # 맨 뒤에서 2번째 sheet가 이번주 sheet
+        last_sheet = list(xl.keys())[-2]
+        sheet = xl[last_sheet]
+
+        # 짝수 column만 사용
+        sheet_keys = sheet.keys()[start_col_idx : end_col_idx]
+        sheet_keys = sheet_keys[0::2]
+
+        for (dateType, date_str) in enumerate(sheet_keys):
+            date_sheet = sheet[date_str]
+            date = parsing_date(time_index, date_sheet)
+            for kindType in [BREAKFAST, LUNCH, DINNER]:
+                kind = MEAL_KIND[langType][kindType]
+                menu, special = parsing_meal[kindType](endpoint, date_sheet, langType, dateType, bldgType)
+                meal = Meal(bldgType, langType, dateType, kindType,
+                            bldg, date, kind, menu, special)
+                parsing_result.append(meal.__dict__)
+        return parsing_result
+
+    # 1학 1층 영어
+    elif bldgType == BLDG1_1ST and langType == 1:
+        sheet = pd.read_excel(excel_path, sheet_name=0,
+                              index_col=None, header=None, names=None, engine='openpyxl')
+
+        # 짝수 column만 사용
+        sheet_keys = sheet.keys()[start_col_idx: end_col_idx]
+        sheet_keys = sheet_keys[0::2]
+
+        for (dateType, date_str) in enumerate(sheet_keys):
+            date_sheet = sheet[date_str]
+            date = parsing_date(time_index, date_sheet)
+            for kindType in [BREAKFAST, LUNCH, DINNER]:
+                kind = MEAL_KIND[langType][kindType]
+                menu, special = parsing_meal[kindType](endpoint, date_sheet, langType, dateType, bldgType)
+                meal = Meal(bldgType, langType, dateType, kindType,
+                            bldg, date, kind, menu, special)
+                parsing_result.append(meal.__dict__)
+        return parsing_result
+
+    # 1학 2층
+    elif bldgType == BLDG1_2ND:
+        sheet = pd.read_excel(excel_path, sheet_name=0,
+                              index_col=None, header=None, names=None, engine='openpyxl')
+
+        for (dateType, date_str) in enumerate(sheet.keys()[start_col_idx : end_col_idx]):
+            date_sheet = sheet[date_str]
+            date = parsing_date(time_index, date_sheet)
+            for kindType in [LUNCH]:
+                kind = MEAL_KIND[langType][kindType]
+                menu, special = parsing_meal[kindType](endpoint, date_sheet, langType, dateType, bldgType, INDEX_ENDPOINTS_BLDG1_EXCEPT)
+                meal = Meal(bldgType, langType, dateType, kindType,
+                            bldg, date, kind, menu, special)
+                parsing_result.append(meal.__dict__)
+        return parsing_result
 
-    return parsing_result
+
+    if bldgType == 0 & langType == 1: #1학 영어 엑셀
+        for (dateType, date_str) in enumerate(DATE_1st):
+            date_sheet = sheet[date_str]
+            date = parsing_date(time_index, date_sheet)
+            for kindType in [BREAKFAST, LUNCH, DINNER]:
+                kind = MEAL_KIND[langType][kindType]
+                menu, special = parsing_meal[kindType](endpoint, date_sheet, langType, dateType, bldgType)
+                meal = Meal(bldgType, langType, dateType, kindType, 
+                        bldg, date, kind, menu, special)
+                parsing_result.append(meal.__dict__) 
+
+    # 2학
+    elif bldgType == BLDG2_1ST:
+        sheet = pd.read_excel(excel_path, sheet_name=langType,
+                              index_col=None, header=None, names=None, engine='openpyxl')
+
+        for (dateType, date_str) in enumerate(sheet.keys()[start_col_idx : end_col_idx]):
+            date_sheet = sheet[date_str]
+            date = parsing_date(time_index, date_sheet)
+            for kindType in [BREAKFAST, LUNCH, DINNER]:
+                kind = MEAL_KIND[langType][kindType]
+                menu, special = parsing_meal[kindType](endpoint, date_sheet, langType, dateType, bldgType)
+                meal = Meal(bldgType, langType, dateType, kindType,
+                            bldg, date, kind, menu, special)
+                parsing_result.append(meal.__dict__)
+        return parsing_result
+
 
 def parsingTest():
     excel_dir_path = "./excel"
@@ -50,26 +129,49 @@ def parsingTest():
     jsonFile = open("./2nd1floor_meal.json", "w", encoding="utf-8")
     json.dump(parsing_result, jsonFile, indent=4,
         ensure_ascii=False, cls=ComplexEncoder)
-    print("-------------------------------------------------")    
-
+    print("-------------------------------------------------")
+
+
 if __name__ == "__main__":
     Mode = 0
+    with open('config.json') as f:
+        config = json.load(f)
     if Mode == 0:
-        excel_path = "./2학생회관.xlsx"
+        filepath_bldg1_1_kor = config['filepath_bldg1_1_kor']
+        filepath_bldg1_1_eng = config['filepath_bldg1_1_eng']
+        filepath_bldg1_2_kor = config['filepath_bldg1_2_kor']
+        filepath_bldg1_2_eng = config['filepath_bldg1_2_eng']
+        filepath_bldg2       = config['filepath_bldg2']
+
         parsing_result = []
         print("-------------------------------------------------")
         print("parsing xlsx to json...")
-        parsing_result.extend(parsing(excel_path, BLDG2_1ST, KOR)) #2학 1층, 한글
-        parsing_result.extend(parsing(excel_path, BLDG2_1ST, ENG)) #2학 1층, 영어
+
+        if exists(filepath_bldg1_1_kor) and exists(filepath_bldg1_1_eng):
+            parsing_result.extend(parsing(filepath_bldg1_1_kor, BLDG1_1ST, KOR)) #1학 1층, 한글
+            parsing_result.extend(parsing(filepath_bldg1_1_eng, BLDG1_1ST, ENG)) #1학 1층, 영어
+            None
+        if exists(filepath_bldg1_2_kor) and exists(filepath_bldg1_2_eng):
+            parsing_result.extend(parsing(filepath_bldg1_2_kor, BLDG1_2ND, KOR)) #1학 2층, 한글
+            parsing_result.extend(parsing(filepath_bldg1_2_eng, BLDG1_2ND, ENG)) #1학 2층, 영어
+            None
+        if exists(filepath_bldg2):
+            parsing_result.extend(parsing(filepath_bldg2, BLDG2_1ST, KOR)) #2학 1층, 한글
+            parsing_result.extend(parsing(filepath_bldg2, BLDG2_1ST, ENG)) #2학 1층, 영어
+            None
+
         print("-------------------------------------------------")
+
         if len(sys.argv) == 1:
             # no url, save to local as json
             print("-------------------------------------------------")
             print("saving json...")
-            jsonFile = open("./2nd1floor_meal.json", "w", encoding="utf-8")
+
+            jsonFile = open("./meal.json", "w", encoding="utf-8")
             json.dump(parsing_result, jsonFile, indent=4,
-                ensure_ascii=False, cls=ComplexEncoder)
+                      ensure_ascii=False, cls=ComplexEncoder)
             print("-------------------------------------------------")
+
         elif len(sys.argv) == 2:
             # post to server
             url = sys.argv[1]
@@ -85,5 +187,6 @@ def parsingTest():
                     print(response)
                     print()
             print("-------------------------------------------------")
+
     elif Mode == 1:
         parsingTest()