更新至1.3.4版本

DC_OCEAN/Duplicate_Checker.py

@@ -80,7 +80,7 @@ def InitEnvironment(self, InputDir, OutputDir):
             raise Exception("Invalid Profile_Summary_Score_list!")
 
     '''
-        This program is used to determine whether the potential duplicate pairs quickly identified in the N02 step are actually duplicated, and if so, output
+        This program is used to determine whether the possible duplicates quickly identified in the N01 step are actually duplicated, and if so, output
         input data: the txt file output from the ./support/N01_Possible_Duplicate_Check.py
         output: two txt files: the duplicated list and the non-duplicated list. These two files can be opened by using Excel etc.
     '''
@@ -129,17 +129,16 @@ def duplicate_checke_manual(self, netCDF_filepath):
                 print('Duplicate result is: Not Duplicate')
 
     """
-        This program is used to determine whether the potential duplicate pairs quickly identified in the N01 step are actually duplicated, and if so, output
+        This program is used to determine whether the possible duplicates quickly identified in the N01 step are actually duplicated, and if so, output
         input data: the txt file output from the ./support/N01_Possible_Duplicate_Check.py
         output: two txt files: the duplicated list and the non-duplicated list. These two files can be opened by using Excel etc.
     """
     # mode = 0:  DuplicateCheckeList
     def duplicate_checke_multiple(self,netCDF_filepath,potential_txt_path):
 
-        ### Read potential_files_txt
+        ### Read possible_files_txt
         potential_files_list=self.read_potential_txt(potential_txt_path)
 
-
         # script_directory = os.path.dirname(potential_txt_path)
         script_directory, _filename = os.path.split(potential_txt_path)
 
@@ -191,7 +190,12 @@ def duplicate_checke_multiple(self,netCDF_filepath,potential_txt_path):
                     continue
 
                 ### Compare the data
-                isDuplicated,duplicate_multimodels=compair_main.compair(content1,content2)
+                isDuplicated, duplicate_multimodels = compair_main.compair(content1, content2)
+                # try:
+                #     isDuplicated,duplicate_multimodels=compair_main.compair(content1,content2)
+                # except:
+                #     print(filepath1)
+                #     print(filepath2)
 
                 ### Output nonduplicated profile pair information
                 if (isDuplicated == False):

DC_OCEAN/M00_Duplicate_Check_MAIN.py

@@ -8,8 +8,8 @@
 ###		Date	|	Author			|	Version		|	Description
 ### ------------|-------------------|---------------|---------------
 ### 2024-03-26	|                   |	1.1			|	Create
-### 2024-06-01	|                   |	1.2			|	Modify
-### 2024-07-04	|                   |	1.3			|	Modify
+### 2024-06-01	|                   |	1.2			|	Modified
+### 2024-07-04	|                   |	1.3			|	Modified
 ######################################################################
 
 """
@@ -44,13 +44,17 @@
 
 # Manually check whether the potential duplicates are exact duplicates based on some criterias one by one pair.
 def DuplicateCheckeManual(checker, InputDir, OutputDir):
+    if not os.path.isdir(OutputDir):
+        os.mkdir(OutputDir)
     if checker.validate_file(InputDir):
         checker.duplicate_checke_manual(InputDir)
     else:
         print("The entered path of netCDF files is not valid. Please ensure the path is correct and try again.")
 
 # Automatically check whether the potential duplicates list are exact duplicates based on some criterias.
 def DuplicateCheckeList(checker, InputDir, OutputDir):
+    if not os.path.isdir(OutputDir):
+        os.mkdir(OutputDir)
     # input the path with filename (*.txt) of the potential duplicated list output from N01_possible_duplicates.py
     potential_txt_path = OutputDir + "/sorted_unique_pairs_generic.txt"
     if checker.validate_file(potential_txt_path):
@@ -83,6 +87,8 @@ def DuplicateCheckeList(checker, InputDir, OutputDir):
     #initialization the code environment (class)
     oChecker = Duplicate_Checker.DuplicateChecker()  
     oChecker.InitEnvironment(InputDir, OutputDir)  
+
+
 
     if(iMode == 0):
         #mode = 0:  DuplicateCheckeList