Add new function to split the table generated in the end of the report when it is long.

Author: xiaoliz0

Config/configure_PRONTO.ini

@@ -9,6 +9,8 @@ data_path = /data/sample_data/analysis_results/
 encoding_sys = utf-8
 ;Specify the number of columns you want to do the filtering (NB: this will also make the script to generate the number of output tables):
 filter_col_nu = 5
+;Specify the number of max rows of the table per slide starting from the 8th slide in report. This is used to split long tables.
+table_max_rows_per_slide = 15
 ;Please modify this for local env if you use MTF files to import the clinical data into meta file. Specify the version of year of the MTF files.
 material_file_version = 2025
 

Script/PRONTO.py

@@ -784,6 +784,78 @@ def insert_table_to_ppt(table_data_file,slide_n,table_name,left_h,top_h,width_h,
 	return data_nrows
 
 
+def insert_table_to_ppt_end(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:
+		return
+	first_line = lines[0]
+	rows = len(lines)
+	first_line_cells = first_line.split('\t')
+	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:
+		if(line != first_line):
+			line_cells =  line.strip('\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)
+
+	ppt = Presentation(output_ppt_file)
+	if(rows <= table_max_rows_per_slide):
+		total_slides_needed = 1
+	else:
+		total_slides_needed = rows // table_max_rows_per_slide + 1
+
+	total_rows = len (data_rows)
+	start_idx = 0
+	while start_idx < total_rows:
+		end_idx  = min(start_idx + table_max_rows_per_slide, total_rows)
+		slide_data = data_rows[start_idx:end_idx]
+		slide = ppt.slides.add_slide(ppt.slide_layouts[6])
+		shapes = slide.shapes
+		left = Inches(left_t)
+		top = Inches(top_t)
+		width = Inches(width_t)
+		height = Inches(height_t)
+		table_rows = len(slide_data) + 1
+		table = shapes.add_table(table_rows,cols,left,top,width,height).table
+		for c in range(cols):
+			if table_column_width:
+				table.columns[c].width = Inches(table_column_width[c])
+			table.cell(0,c).text = table_header[c]
+			table.cell(0,c).text_frame.paragraphs[0].font.size = Pt(font_size)
+
+		for row_idx, row_data in enumerate(slide_data, start=1):
+			for col_idx in range(cols):
+				table.cell(row_idx,col_idx).text = str(row_data[col_idx])
+				table.cell(row_idx,col_idx).text_frame.paragraphs[0].font.size = Pt(font_size)
+
+		start_idx = end_idx
+
+		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):
+			tf.paragraphs[0].text = table_name +" (N=" + str(table_rows - 1) + ")"
+		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_slides_needed
+
+
 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):
 	DNA_summary_file = open(DNA_variant_summary_file)
 	global str_TMB_DRUP
@@ -1534,7 +1606,8 @@ def main(argv):
 				slide8_table_font_size = 7
 				if_print_rowNo = True
 				table8_column_width = [0.54, 0.96, 0.96, 0.51, 0.73, 1.12, 2.26, 0.79, 0.81, 0.53]
-				slide8_table_nrows = insert_table_to_ppt(slide8_table_data_file,slide8_table_ppSlide,slide8_table_name,slide8_header_left,slide8_header_top,slide8_header_width,slide8_table_left,slide8_table_top,slide8_table_width,slide8_table_height,slide8_table_font_size,slide8_table_header,output_ppt_file,if_print_rowNo,table8_column_width)
+				table_max_rows_per_slide = int(cfg.get("INPUT", "table_max_rows_per_slide")) - 1
+				slide8_table_slides = insert_table_to_ppt_end(slide8_table_data_file,slide8_table_ppSlide,slide8_table_name,slide8_header_left,slide8_header_top,slide8_header_width,slide8_table_left,slide8_table_top,slide8_table_width,slide8_table_height,slide8_table_font_size,slide8_table_header,output_ppt_file,if_print_rowNo,table8_column_width,table_max_rows_per_slide)
 
 				# Insert the CNV_overveiw_plots pictures A2, B3 and C1 into report.
 				A2_to_extract=[2]
@@ -1545,12 +1618,13 @@ def main(argv):
 					B3_C1_to_extract = [4, 5]
 				pdf_page_image_to_ppt(CNV_overview_plots_pdf,output_ppt_file,B3_C1_to_extract,width_scale=1,height_scale=0.5)
 
-        		# Change slides order.
+        			# Change slides order.
 				ppt = Presentation(output_ppt_file)
+				slide_count = len(ppt.slides)
 				slides = ppt.slides._sldIdLst
 				slides_list = list(slides)
 				slides.remove(slides_list[7])
-				slides.insert(12,slides_list[7])
+				slides.insert(slide_count + 1,slides_list[7])
 				ppt.save(output_ppt_file)
 				print("Generate report for " + DNA_sampleID)
 				ppt_nr += 1