#!/usr/bin/python
# -*- coding: utf-8 -*-

def fsize(filepath):
	import os
	finfo = os.stat(filepath)
	fsize = finfo.st_size
	KB = "%.2f" % (fsize/1024)
	return([fsize,KB])
	
#@profile
def createpdf_from_sourcepdf_pages_pdfrw(sourcepdf=None, pageslist=None, destpdf=None, debug=False):
	""" <https://github.com/pmaupin/pdfrw/blob/master/examples/subset.py>
		"""
	from pdfrw import PdfWriter,PdfReader
	#import pdfrw_bookmarks # code from https://github.com/pmaupin/pdfrw/issues/52#issuecomment-271190546
	pages = PdfReader(sourcepdf).pages
	totalpages = len(pages)
	outdata = PdfWriter(destpdf)
	for p in pageslist:
		if p<totalpages:
			if debug: print("pdfrw ",p)
			#pdfrw_pageannots(pages[p-1])
			outdata.addpage(pages[p-1])
	outdata.write()

#@profile
def createpdf_from_sourcepdf_pages_pypdf(sourcepdf=None, pageslist=None, destpdf=None, debug=False, compress=False):
	""" Generate destpdf with list of certain pages taken from sourcepdf. 
		- <https://pypdf2.readthedocs.io/en/stable/user/merging-pdfs.html>
		- SO [Extract specific pages of PDF and save it with Python](https://stackoverflow.com/a/51885963/710788)
		"""
	from pypdf import PdfWriter,PdfReader
	fsource = open(sourcepdf, "rb")
	merger = PdfWriter()
	totalpages = len(PdfReader(fsource).pages)
	for p in pageslist:
		if p<totalpages:
			if debug: print("pypdf ",p)
			# add page p (0-based index):
			merger.append(fileobj=fsource, pages=(p-1,p))
	if compress: # Compress the data
		for page in merger.pages:
			page.compress_content_streams()  # This is CPU intensive!
	# Write to an output PDF document
	output = open(destpdf, "wb")
	merger.write(output)
	# Close File Descriptors
	merger.close()
	output.close()

#from memory_profiler import profile
#@profile
def pypdf_vs_pdfrw():
	""" [performance comparative](https://github.com/pmaupin/pdfrw/issues/232#issuecomment-1436153435) between two packages:
		- pdfrw
		- pypdf
		"""
	print(datetime.now() - startTime, " before comparing")
	pdfurls = [
		"https://arxiv.org/pdf/2201.00151.pdf",
		"https://arxiv.org/pdf/1707.09725.pdf",
		"https://arxiv.org/pdf/2201.00021.pdf",
		"https://arxiv.org/pdf/2201.00037.pdf",
		"https://arxiv.org/pdf/2201.00069.pdf",
		"https://arxiv.org/pdf/2201.00178.pdf",
		"https://arxiv.org/pdf/2201.00201.pdf",
		"https://arxiv.org/pdf/1602.06541.pdf",
		"https://arxiv.org/pdf/2201.00200.pdf",
		"https://arxiv.org/pdf/2201.00022.pdf",
		"https://arxiv.org/pdf/2201.00029.pdf",
		"https://arxiv.org/pdf/1601.03642.pdf",
		]
	import requests,os
	pdfrw_Tsize = 0
	pdfrw_Ttime = 0
	pypdf_Tsize = 0
	pypdf_Ttime = 0
	for pdfurl in pdfurls:
		sourcepdf = pdfurl.split("/")[-1]
		if not os.path.exists(sourcepdf):
			response = requests.get(pdfurl, headers=None, params=None)
			if response.status_code == 200:
				with open(sourcepdf, 'wb') as f:
					f.write(response.content)
			else:
				print(response.status_code)
				print("COULDN'T DOWNLOAD  '{}' FILE:\n".format(pdfurl))
		if not os.path.exists(sourcepdf):
			print("\n","-_"*40,"\n\nSKIPPING '{}' FILE:\n".format(sourcepdf))
		else:
			print("\n","-_"*40,"\n\nTESTING WITH '{}' FILE:\n".format(sourcepdf))
			for i in range(1,6):
				pageslist=[4,6,8,9]*i #*5 eats all my memory when using pypdf with large pdf files
				print("-"*50,"\npageslist:",pageslist)
				start=datetime.now()
				destpdf=sourcepdf+"_pdfrw-test_{}.pdf".format(".".join([str(p) for p in pageslist]))
				createpdf_from_sourcepdf_pages_pdfrw(sourcepdf=sourcepdf, pageslist=pageslist, destpdf=destpdf); 
				pdfrw_t = round((datetime.now() - start).total_seconds(),3)
				pdfrw_s = fsize(destpdf)
				pdfrw_Ttime += pdfrw_t
				pdfrw_Tsize += pdfrw_s[0]
				print("pdfrw: {} KB output size, took {} seconds".format(pdfrw_s[1],pdfrw_t))
				start=datetime.now()
				destpdf=sourcepdf+"_pypdf-test_{}.pdf".format(".".join([str(p) for p in pageslist]))
				createpdf_from_sourcepdf_pages_pypdf(sourcepdf=sourcepdf, pageslist=pageslist, destpdf=destpdf);
				pypdf_t = round((datetime.now() - start).total_seconds(),3)
				pypdf_s = fsize(destpdf)
				pypdf_Ttime += pypdf_t
				pypdf_Tsize += pypdf_s[0]
				print("pypdf: {} KB output size, took {} seconds".format(pypdf_s[1],pypdf_t))
				print("pypdf_time / pdfrw_time = {} ratio".format(round(pypdf_t/pdfrw_t, 2)))
				print("pypdf_size / pdfrw_size = {} ratio".format(round(pypdf_s[0]/pdfrw_s[0], 2)))
			
	import pdfrw,pypdf
	print("-_"*40)
	print("\n pdfrw.__version__ {}\nAccumulated output file size: {:.2f} MB\nTotal time: {:.2f} seconds".format(
		pdfrw.__version__, pdfrw_Tsize/1024/1024, pdfrw_Ttime))
	print("\n pypdf.__version__ {}\nAccumulated output file size: {:.2f} MB\nTotal time: {:.2f} seconds".format(
		pypdf.__version__, pypdf_Tsize/1024/1024, pypdf_Ttime))

if __name__ == "__main__":
	import sys
	from datetime import datetime
	startTime = datetime.now()
	print("START: ",startTime)
	pypdf_vs_pdfrw()
	endTime = datetime.now()
	print("\nEND: ",endTime)
	print("\nTOTAL TIME: ",endTime-startTime)