Insert table to ppt

Script/PRONTO.py

@@ -28,6 +28,8 @@
 from decimal import Decimal
 from copy import deepcopy
 import pronto.pronto as pronto
+import pandas
+import math
 from pdf2image import convert_from_path
 
 runID = ""
@@ -731,45 +733,34 @@ def insert_image_to_ppt(DNA_sampleID,DNA_normal_sampleID,RNA_sampleID,DNA_image_
 	ppt.save(output_ppt_file)
 
 
-def insert_table_to_ppt(table_data_file,slide_n,table_name,left_h,top_h,width_h,left_t,top_t,width_t,height_t,font_size,table_header,output_ppt_file,if_print_rowNo,table_column_width,table_max_rows_per_slide):
-	table_file = open(table_data_file)
-	lines = table_file.readlines()
-	if not lines:
+def insert_table_to_ppt(table_file,slide_n,table_name,left_h,top_h,width_h,left_t,top_t,width_t,height_t,font_size,table_header,output_ppt_file,if_print_rowNo,table_column_width,table_max_rows_per_slide):
+
+	# load table data
+	try:
+		table_data = pandas.read_csv(table_file, sep='\t')
+	except pandas.errors.EmptyDataError:
+		logging.warning("{} is empty".format(table_file))
 		return
-	first_line = lines[0]
-	first_line_cells = first_line.split('\t')
+
+	# add empty columns for missing header columns and move additional columns to the right
+	table_data = pronto.normalize_column_index(table_data, table_header)
+
+	# determine column and row number
 	cols = len(table_header)
-	header_not_exist_in_table = []
-	for n in range(len(table_header)):
-		if_exist = False
-		if(table_header[n] in first_line_cells):
-			if_exist = True
-		if not if_exist:
-			header_not_exist_in_table.append(n)
-	data_rows = []
-	for line in lines[1:]:
-		line_cells =  line.split('\t')
-		if header_not_exist_in_table:
-			for num in header_not_exist_in_table:
-				line_cells.insert(num," ")
-		row_data = [cell.strip() for cell in line.split('\t')]
-		data_rows.append(row_data)
-	total_rows = len(data_rows)
+	rows = len(table_data)
 
-	ppt = Presentation(output_ppt_file)
-	if(table_max_rows_per_slide is None or total_rows <= table_max_rows_per_slide):
-		total_slides_needed = 1
-		rows_per_page = total_rows
-		start_slide_index = slide_n
-	else:
-		total_slides_needed = (total_rows + table_max_rows_per_slide -1) // table_max_rows_per_slide
-		rows_per_page = table_max_rows_per_slide
-		start_slide_index = None
+	# how many slides, and start slide index
+	if not table_max_rows_per_slide:
+		table_max_rows_per_slide = rows
+	total_slides_needed = math.ceil(rows / table_max_rows_per_slide)
+	start_slide_index = None if total_slides_needed > 1 else slide_n
 
+	ppt = Presentation(output_ppt_file)
 	for page_num in range(total_slides_needed):
-		start_idx = page_num * rows_per_page
-		end_idx = min(start_idx + rows_per_page, total_rows)
-		current_page_data = data_rows[start_idx:end_idx]
+		start_idx = page_num * table_max_rows_per_slide
+		end_idx = min(start_idx + table_max_rows_per_slide, rows)
+		data_rows = table_data.values.tolist()
+		current_page_data = data_rows[start_idx:end_idx] # use df
 		current_page_rows = len(current_page_data)
 		if(start_slide_index is not None and page_num == 0):
 			slide = ppt.slides[slide_n - 1]
@@ -796,18 +787,18 @@ def insert_table_to_ppt(table_data_file,slide_n,table_name,left_h,top_h,width_h,
 		textbox = slide.shapes.add_textbox(Inches(left_h),Inches(top_h),Inches(width_h),Inches(0.25))
 		tf = textbox.text_frame
 		if(if_print_rowNo == True):
-			if(table_max_rows_per_slide is not None):
-				tf.paragraphs[0].text = table_name +" (N=" + str(total_rows) + ", Page " + str(page_num+1) + "/" + str(total_slides_needed) + ")"
+			if(total_slides_needed > 1):
+				tf.paragraphs[0].text = table_name +" (N=" + str(rows) + ", Page " + str(page_num+1) + "/" + str(total_slides_needed) + ")"
 			else:
-				tf.paragraphs[0].text = table_name +" (N=" + str(total_rows) + ")"
+				tf.paragraphs[0].text = table_name +" (N=" + str(rows) + ")"
 		else:
 			tf.paragraphs[0].text = table_name
 		tf.paragraphs[0].font.size = Pt(8)
 		tf.paragraphs[0].font.bold = True
 		tf.paragraphs[0].alignment = PP_ALIGN.CENTER
 
 	ppt.save(output_ppt_file)
-	return total_rows
+	return rows
 
 
 def update_ppt_variant_summary_table(data_nrows,DNA_sampleID,RNA_sampleID,TMB_DRUP_nr,TMB_DRUP_str,DNA_variant_summary_file,RNA_variant_summary_file,output_file_preMTB_AppendixTable,output_table_file_filterResults_AllReporVariants_CodingRegion,output_ppt_file):

pronto/pronto.py

@@ -1,6 +1,7 @@
 import glob
 import logging
 import os
+import pandas
 
 # get tumor mutational burden label
 def get_tmb_string(val):
@@ -27,3 +28,15 @@ def glob_tsoppi_file(is_error, root, run_id, *path_units):
 	else:
 		logging.error("unsuccessful glob strings for {}:\n{}\n{}".format(run_id, glob_string_ous, glob_string_hus))
 		raise ValueError
+
+def normalize_column_index(df: pandas.DataFrame, exp_col_idx: list):
+	# determine current, missing and additional column indices
+	curr_col_idx = df.columns.tolist()
+	miss_col_idx = list(set(exp_col_idx) - set(curr_col_idx))
+	add_col_idx = list(set(curr_col_idx) - set(exp_col_idx))
+	# add missing column indices
+	for i in miss_col_idx:
+		df[i] = ' '
+	# combine expected with additional to get all present column indices and rearrange columns accordingly, additional columns are moved to the right
+	all_col_idx = exp_col_idx + add_col_idx
+	return df[all_col_idx]

pronto/tests/pronto_test.py

@@ -1,3 +1,4 @@
+import pandas
 import pytest
 import pronto.pronto
 
@@ -99,3 +100,85 @@ def test_get_tmb_string(input, exception, want):
 def test_glob_tsoppi_file(inputs, exception, want):
     with exception:
         assert pronto.pronto.glob_tsoppi_file(*inputs) == want
+
+@pytest.mark.parametrize(
+    "inputs, exception, want",
+    [
+        (
+            (
+                pandas.DataFrame({
+                    "one": [1, 2],
+                    "two": [3, 4],
+                    "three": [5, 6],
+                    "four": [7, 8],
+                }),
+                ["one", "two", "three", "four"],
+            ),
+            does_not_raise(),
+            pandas.DataFrame({
+                "one": [1, 2],
+                "two": [3, 4],
+                "three": [5, 6],
+                "four": [7, 8],
+            }),
+        ),
+        (
+            (
+                pandas.DataFrame({
+                    "one": [1, 2],
+                    "two": [3, 4],
+                    "four": [7, 8],
+                }),
+                ["one", "two", "three", "four"],
+            ),
+            does_not_raise(),
+            pandas.DataFrame({
+                "one": [1, 2],
+                "two": [3, 4],
+                "three": [' ', ' '],
+                "four": [7, 8],
+            }),
+        ),
+        (
+            (
+                pandas.DataFrame({
+                    "one": [1, 2],
+                    "two": [3, 4],
+                    "three": [5, 6],
+                    "four": [7, 8],
+                }),
+                ["two", "three", "four"],
+            ),
+            does_not_raise(),
+            pandas.DataFrame({
+                "two": [3, 4],
+                "three": [5, 6],
+                "four": [7, 8],
+                "one": [1, 2],
+            }),
+        ),
+        (
+            (
+                pandas.DataFrame({
+                    "one": [1, 2],
+                    "two": [3, 4],
+                    "four": [7, 8],
+                    "five": [9, 10],
+                }),
+                ["one", "two", "three", "four"],
+            ),
+            does_not_raise(),
+            pandas.DataFrame({
+                "one": [1, 2],
+                "two": [3, 4],
+                "three": [' ', ' '],
+                "four": [7, 8],
+                "five": [9, 10],
+            }),
+        ),
+    ]
+)
+def test_normalize_column_index(inputs, exception, want):
+    with exception:
+        get = pronto.pronto.normalize_column_index(*inputs)
+        assert want.equals(get)

requirements-test.txt

@@ -1,3 +1,3 @@
-pytest==7.4.3
+pytest-emoji==0.2.0
 pytest-md==0.2.0
-pytest-emoji==0.2.0
+pytest==7.4.3

requirements.txt

@@ -1,6 +1,7 @@
 click==8.1.7
+pandas==2.2.3
+pdf2image==1.17.0
 python-docx==1.1.0
 python-pptx==0.6.23
 xlrd==2.0.1
 xlutils==2.0.0
-pdf2image==1.17.0