Merge branch 'Kamlesh_EnhanceSummaryReport' into 'master'

Changes to allow varying number of collections during creating the summary report.

See merge request !158

Summarize_Newman_Html_Reports.py

@@ -14,9 +14,16 @@ import datetime
 # OSDU Platform Validation CI_CD_Notes.md of "Platform Validation project"
 # At present it is assuming 11 collections being run each of the four platforms
 # AWS, AZURE, GCP, IBM
-# In future work will be done where it should be able handle n number of collections instead of fix 11
-# At present this restriction is because of the way the writing of the excel file is implemented,
-# specially the writing of the last summary part, after all the collections are processed.
+# AT present
+# Number of collection can vary, but number of platforms is fixed.
+# Also it expects to have the collection report for each platform.
+# The Collection run date is extracted from the first collection report processed.
+# Also environment file is extracted from the first collection processed for each platform
+#
+# In future work can be done to make the number of platforms also variable
+# At present this restriction is there because 
+#   of the way the writing of the excel file is implemented.
+#   Also the Columns for each platform are fixed
 #=======================================================================================================
 # Method to process html report file and summarize the results in Excel file
 def processFile(fnm, platform, rowNo, colOffset, envFileNamesPopulated):
@@ -25,11 +32,11 @@ def processFile(fnm, platform, rowNo, colOffset, envFileNamesPopulated):
     # print("Row: ", rowNo)
     # print("Total Rows: ", totRows)
     # print("Column offset", colOffset)
-    # return()
     #
+    # Open the html file for reading
     html = open(fnm, 'r').read()   # local html
-    bs = BeautifulSoup(html, features="html.parser")
-    #
+    bs = BeautifulSoup(html, features="html.parser")    # parse the file
+    # Find the desired section of the file, extract the text and split to extract required information
     mydivs = bs.findAll("div", {"class": "col-sm-12 mb-3"})
     txt = mydivs[0].get_text()
     fileInfo = txt.split("\n")
@@ -52,7 +59,7 @@ def processFile(fnm, platform, rowNo, colOffset, envFileNamesPopulated):
     #           
     print(collectionName)
     print(enviornmentName)
-    # Save/Collect environment file name
+    # Save/Collect environment file names (only once, not for each collection)
     if (envFileNamesPopulated == False):
         if (colOffset == 0):
             env_file_names.append(enviornmentName)
@@ -89,7 +96,7 @@ def processFile(fnm, platform, rowNo, colOffset, envFileNamesPopulated):
         elif (count == 20):
             skippedTests = info       
         count += 1
-    #
+    # Compute the pass rate (percentage of test that passed for the collection)
     passRate = (100 * float(totalAssertionPassed ) / (float(totalAssertionPassed) + float(totalAssertionFailed)) )
 
     # print("totalRequestsPassed: " + totalRequestsPassed)
@@ -98,12 +105,13 @@ def processFile(fnm, platform, rowNo, colOffset, envFileNamesPopulated):
     # print("totalAssertionFailed: " + totalAssertionFailed)
     # print("skippedTests: " + skippedTests)
     # print(passRate)
-
+    #
+    # save the information
     records.append((collectionName, totalRequestsPassed, totalAssertionPassed, totalAssertionFailed, passRate ))
 
     curRow = len(records) - 1
     # print(records[curRow])
-    
+    # write the data to Excel file
     for col_num, data in enumerate(records[curRow]):
 
         l_colNum = col_num
@@ -113,7 +121,7 @@ def processFile(fnm, platform, rowNo, colOffset, envFileNamesPopulated):
             worksheet.write(rowNo, l_colNum, data, collection_cell_format)
         elif (l_colNum == 1):
             worksheet.write(rowNo, l_colNum, int(data), request_cell_format)
-        elif ( (l_colNum == 4) or (l_colNum == 8) or (l_colNum == 12) or (l_colNum == 16 ) ):
+        elif (l_colNum in pctColList):
             if (passRate >= 100.0):
                 worksheet.write(rowNo, l_colNum, data, greenPct_cell_format)
             elif (passRate < 60.0):
@@ -122,7 +130,8 @@ def processFile(fnm, platform, rowNo, colOffset, envFileNamesPopulated):
                 worksheet.write(rowNo, l_colNum, data, pct_cell_format)
         else:
             worksheet.write(rowNo, l_colNum, int(data), cell_format)
-    #Extract run Date Info
+    #
+    #Extract run Date Info only once from the first collection
     if (len(collection_run_date) == 0): 
         mydivs3 = bs.findAll("div", {"class": "col-md-9 col-lg-12 main"})
         txt3 = mydivs3[0].get_text()
@@ -145,19 +154,28 @@ records.append(("Collection Name", "#of Requests", "Pass", "Fail", "PassRate",""
 #Create and initialize the excel file
 workbook = xlsxwriter.Workbook('NewmanHtmlReportsSummary.xlsx')
 worksheet = workbook.add_worksheet()
-worksheet.set_column(0, 0, 40)
-worksheet.set_column(1, 1, 12)
+# set the column width
+worksheet.set_column(0, 0, 40)      # Column for Collection Name
+worksheet.set_column(1, 1, 12)      # Column for number of request
+# set variaous formats that will be used to wirte the data to the Excel file
 cell_format = workbook.add_format({'align': 'center', 'bold': True})
+#
 summ_cell_format = workbook.add_format({'align': 'left', 'bold': True})
 summ_right_cell_format = workbook.add_format({'align': 'right', 'bold': True})
-
+#
 request_cell_format = workbook.add_format({'align': 'center', 'bg_color': '#D8E4BC'})
-
+#
 collection_cell_format = workbook.add_format({'align': 'center', 'bold': True})
 collection_cell_format.set_font_color('blue')
 #
 total_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': 'orange', 'font_color': 'blue'})
 #
+total_num_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': 'orange', 'font_color': 'blue'})
+total_num_cell_format.set_num_format('0')
+#
+total_pct_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': 'orange', 'font_color': 'blue'})
+total_pct_cell_format.set_num_format('0.00')
+#
 pct_cell_format = workbook.add_format({'align': 'center', 'bold': True})
 pct_cell_format.set_num_format('0.00')
 #
@@ -171,15 +189,20 @@ redPct_cell_format.set_num_format('0.00')
 #
 head_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': '#78B0DE'})
 head_cell_format.set_font_size(14)
-
+#
 head2_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': '#BBD7EF', 'font_color': 'black'})
 head2_cell_format.set_font_size(12)
-
+#
 head2_green_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': '#BBD7EF', 'font_color': 'green'})
 head2_green_cell_format.set_font_size(12)
 head2_red_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': '#BBD7EF', 'font_color': 'red'})
 head2_red_cell_format.set_font_size(12)
-
+#
+fillColList = [5,9,13]          # column list that are acting as separator between platforms
+pctColList = [4,8,12,16]        # column list that hold passRate (percent) values
+passColList = [2,6,10,14]       # column list that hold number of request pass values
+failColList = [3,7,11,15]       # column list that hold number of request fail values
+#
 #Write the header records to excel file
 rowNum = 0
 col_offset = 0
@@ -190,9 +213,9 @@ for row_num in records:
         else:
             # print("rowNum: ", rowNum, "  col_num: ", col_num)
             if (rowNum == 1):
-                if ( (col_num == 2) or (col_num == 6) or (col_num == 10) or (col_num == 14) ):
+                if (col_num in passColList):
                     worksheet.write(rowNum, col_num, data, head2_green_cell_format)
-                elif ((col_num == 3) or (col_num == 7) or (col_num == 11) or (col_num == 15)):
+                elif (col_num in failColList):
                     worksheet.write(rowNum, col_num, data, head2_red_cell_format)
                 else:
                     worksheet.write(rowNum, col_num, data, head2_cell_format)
@@ -210,6 +233,8 @@ for file in os.listdir("."):
             continue
         else:
             # print(file)
+            # Extract platform from the filename and set the start column offset value for the platform
+            # First platform (AWS) start column offset also accomodates number of request column
             if (fileParts[0] != curPlatform):
                 #
                 localRowNo = rowNum
@@ -226,79 +251,83 @@ for file in os.listdir("."):
                 else:
                     print("Invalid platform: " + fileParts[0])
                     continue
-                env_file_names_populated = False
+                env_file_names_populated = False    # platform changed, save environment file
             else:
-                env_file_names_populated = True
+                env_file_names_populated = True     # want to save environment file only once for each platform
 
             if (fileParts[0] == "aws"):
                 collName.append(fileParts[1])
-
+            # Process, extract and write the information to the Excel file
             processFile(file, fileParts[0], localRowNo, col_offset, env_file_names_populated)     # process html report file
             localRowNo += 1
             print("")
-#
+# Summarize the results
 print("Total number of collections: ", len(collName) )
 print("Total number of reports summarized: ", (len(records)-2) )
 print("Total number of platforms", ((len(records) - 2)/len(collName)) )
+# Populate the Separator columns
 fill_cell_format = workbook.add_format({'bg_color': '#FFE1E5'})
 total_row_num = len(collName) + 2
 colList = [5,9,13]
 for i in range(2, total_row_num):
     for j in  range(len(colList)):
         worksheet.write(i, colList[j], "", fill_cell_format)
-#
+# Write the summary data to the Excel file, Values for the Total row, Collection run and summary report date and list of environment files
 total_cols = 17
+rowIndx = total_row_num 
+rowIndxStr = str(rowIndx+1)
+sumStartIdx =3
+sumEndIdx = rowIndx
+sumStartIdxStr = str(sumStartIdx)
+sumEndIdxStr = str(sumEndIdx)
+# popluate the arrays to sum the pass, fail and passRate values for each platform as well as total number of requests
+# e.g. [ ['B14', '{=SUM(B3:B13)}'],...,[...]]
+col_lables = [["B"+rowIndxStr, "{=SUM(B"+sumStartIdxStr+":B"+sumEndIdxStr+")}"], ["C"+rowIndxStr, "{=SUM(C"+sumStartIdxStr+":C"+sumEndIdxStr+")}"],
+              ["D"+rowIndxStr, "{=SUM(D"+sumStartIdxStr+":D"+sumEndIdxStr+")}"], ["E"+rowIndxStr, "{=SUM(E"+sumStartIdxStr+":E"+sumEndIdxStr+")}"],
+              ["G"+rowIndxStr, "{=SUM(G"+sumStartIdxStr+":G"+sumEndIdxStr+")}"], ["H"+rowIndxStr, "{=SUM(H"+sumStartIdxStr+":H"+sumEndIdxStr+")}"], ["I"+rowIndxStr, "{=SUM(I"+sumStartIdxStr+":I"+sumEndIdxStr+")}"],
+              ["K"+rowIndxStr, "{=SUM(K"+sumStartIdxStr+":K"+sumEndIdxStr+")}"], ["L"+rowIndxStr, "{=SUM(L"+sumStartIdxStr+":L"+sumEndIdxStr+")}"], ["M"+rowIndxStr, "{=SUM(M"+sumStartIdxStr+":M"+sumEndIdxStr+")}"],
+              ["O"+rowIndxStr, "{=SUM(O"+sumStartIdxStr+":O"+sumEndIdxStr+")}"], ["P"+rowIndxStr, "{=SUM(P"+sumStartIdxStr+":P"+sumEndIdxStr+")}"], ["Q"+rowIndxStr, "{=SUM(Q"+sumStartIdxStr+":Q"+sumEndIdxStr+")}"]]
+col_label_indx = 0
+# Populate/write the Total Row
 for j in range(total_cols):
     if (j == 0):
-        worksheet.write(13, j, "Total", total_cell_format)
-    elif ( (j == 5) or (j == 9) or (j == 13) ):
+        worksheet.write(rowIndx, j, "Total", total_cell_format)
+    elif (j in fillColList):
         worksheet.write(total_row_num, j, "", total_cell_format)
         # continue
-    elif (j == 1):
-        worksheet.write_formula('B14', '{=SUM(B3:B13)}', total_cell_format)
-    elif (j == 2):
-        worksheet.write_formula('C14', '{=SUM(C3:C13)}', total_cell_format)
-    elif (j == 3):
-        worksheet.write_formula('D14', '{=SUM(D3:D13)}', total_cell_format)
-    elif (j == 4):
-        worksheet.write_formula('E14', '{=SUM(E3:E13)}', total_cell_format)
-    elif (j == 6):
-        worksheet.write_formula('G14', '{=SUM(G3:G13)}', total_cell_format)
-    elif (j == 7):
-        worksheet.write_formula('H14', '{=SUM(H3:H13)}', total_cell_format)
-    elif (j == 8):
-        worksheet.write_formula('I14', '{=SUM(I3:I13)}', total_cell_format)
-    elif (j == 10):
-        worksheet.write_formula('K14', '{=SUM(K3:K13)}', total_cell_format)
-    elif (j == 11):
-        worksheet.write_formula('L14', '{=SUM(L3:L13)}', total_cell_format)
-    elif (j == 12):
-        worksheet.write_formula('M14', '{=SUM(M3:M13)}', total_cell_format)
-    elif (j == 14):
-        worksheet.write_formula('O14', '{=SUM(O3:O13)}', total_cell_format)
-    elif (j == 15):
-        worksheet.write_formula('P14', '{=SUM(P3:P13)}', total_cell_format)
-    elif (j == 16):
-        worksheet.write_formula('Q14', '{=SUM(Q3:Q13)}', total_cell_format)
-#
+    else:
+        colIndx = col_lables[col_label_indx]
+        if (j in pctColList):
+            worksheet.write_formula(colIndx[0], colIndx[1], total_pct_cell_format)
+        else:
+            worksheet.write_formula(colIndx[0], colIndx[1], total_num_cell_format)
+        col_label_indx += 1
+# Write the collection run date
 date_time_obj = datetime.datetime.strptime(collection_run_date[0], '%A, %d %B %Y %H:%M:%S')
 str1 = "Collection run date:  " + date_time_obj.strftime('%m/%d/%Y, %H:%M:%S')
-worksheet.write(15, 0, str1, summ_cell_format)
+rowIndx += 2
+worksheet.write(rowIndx, 0, str1, summ_cell_format)
+# Write the summary report date
 # str1 = "Summary report run date:\t " + (datetime.datetime.now().strftime('%A, %d %B %Y %H:%M:%S'))
 str1 = "Summary report date:  " + (datetime.datetime.now().strftime('%m/%d/%Y, %H:%M:%S'))
-worksheet.write(16, 0, str1, summ_cell_format)
-#
-worksheet.write(18, 0, "Environment Files:", summ_cell_format)
+rowIndx += 1
+worksheet.write(rowIndx, 0, str1, summ_cell_format)
+# Wrtie the list of environment files
+rowIndx += 1
+worksheet.write(rowIndx, 0, "Environment Files:", summ_cell_format)
 numOfEnvs = len(env_file_names)
+rowIndx += 1
 for i in range(numOfEnvs):
-    worksheet.write((19+i), 0, env_file_names[i], cell_format)
-#
+    worksheet.write(rowIndx, 0, env_file_names[i], cell_format)
+    rowIndx += 1
+# Close the Excel file
 workbook.close()
+# Log some summary data
 print(env_file_names)
 print(collection_run_date)
 print("Summary Report Date: ", datetime.datetime.now())
 print("Done")
 exit()
-#
+# End