From 82ee233ea82a40c626e95a191fe2d52c745db870 Mon Sep 17 00:00:00 2001 From: dsk7 Date: Sat, 23 Apr 2022 19:12:13 +0200 Subject: MAINT: Quadratic runtime while parsing reduced to linear (#808) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the PdfFileReader tries to find the xref marker, the readNextEndLine methods builds a so called line by reading byte-for-byte. Every time a new byte is read, it is concatenated with the currently read line. This leads to quadratic runtime O(n²) behavior as Python strings (also byte-strings) are immutable and have to be copied where n is the size of the file. For files where the xref marker can not be found at the end this takes a enormous amount of time: * 1mb of zeros at the end: 45.54 seconds * 2mb of zeros at the end: 357.04 seconds (measured on a laptop made in 2015) This pull request changes the relevant section of the code to become linear runtime O(n), leading to a run time of less then a second for both cases mentioned above. Furthermore this PR adds a regression test. --- PyPDF2/pdf.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/PyPDF2/pdf.py b/PyPDF2/pdf.py index 9979414..8b355e0 100644 --- a/PyPDF2/pdf.py +++ b/PyPDF2/pdf.py @@ -1930,7 +1930,7 @@ class PdfFileReader(object): def readNextEndLine(self, stream): debug = False if debug: print(">>readNextEndLine") - line = b_("") + line_parts = [] while True: # Prevent infinite loops in malformed PDFs if stream.tell() == 0: @@ -1957,10 +1957,10 @@ class PdfFileReader(object): break else: if debug: print(" x is neither") - line = x + line - if debug: print((" RNEL line:", line)) + line_parts.append(x) if debug: print("leaving RNEL") - return line + line_parts.reverse() + return b"".join(line_parts) def decrypt(self, password): """ -- 2.30.2