diff --git a/pdfmajor/document/PDFDocument.py b/pdfmajor/document/PDFDocument.py index 7ffc6ec..af85e87 100644 --- a/pdfmajor/document/PDFDocument.py +++ b/pdfmajor/document/PDFDocument.py @@ -1,3 +1,4 @@ +import warnings from pathlib import Path from typing import BinaryIO, Iterator, List, Optional @@ -60,8 +61,8 @@ class PDFDocument: yield page self.__processed_pages_done = True if len(self.__processed_pages) != self.num_pages: - print( - "WARN! number of pages proceseed with iter_pages did not match number of pages specified by the document's metadata!" + warnings.warn( + "Number of pages proceseed with iter_pages did not match number of pages specified by the document's metadata!" f"\n --> expected pages = {self.num_pages}" f"\n --> found pages = {len(self.__processed_pages)}" ) diff --git a/tests/samples/corrupt-pdfs/bad-page-count.pdf b/tests/samples/corrupt-pdfs/bad-page-count.pdf new file mode 100644 index 0000000..b1469ea Binary files /dev/null and b/tests/samples/corrupt-pdfs/bad-page-count.pdf differ diff --git a/tests/test_document.py b/tests/test_document.py index 3e076e4..8f8ed64 100644 --- a/tests/test_document.py +++ b/tests/test_document.py @@ -1,3 +1,4 @@ +import warnings from decimal import Decimal from typing import List from unittest import TestCase @@ -20,7 +21,7 @@ from pdfmajor.parser.objects.primitives import ( PDFReal, PDFString, ) -from tests.util import all_pdf_files +from tests.util import all_corrupt_pdf_files, all_pdf_files class ParsingState(TestCase): @@ -138,11 +139,19 @@ class ParsingState(TestCase): actual_pages = len(list(parser.iter_pages())) self.assertEqual(actual_pages, parser.num_pages) - def test_doc(self): - with all_pdf_files["bad-unicode.pdf"].get_window() as buffer: + # def test_doc(self): + # with all_pdf_files["bad-unicode.pdf"].get_window() as buffer: + # parser = PDFDocument(buffer) + # actual_pages = len(list(parser.iter_pages())) + # self.assertEqual(actual_pages, parser.num_pages) + + def test_warning_pagecount(self): + with all_corrupt_pdf_files["bad-page-count.pdf"].get_window() as buffer: parser = PDFDocument(buffer) - actual_pages = len(list(parser.iter_pages())) - self.assertEqual(actual_pages, parser.num_pages) + with warnings.catch_warnings(record=True) as w: + actual_pages = len(list(parser.iter_pages())) + self.assertEqual(len(w), 1) + self.assertNotEqual(actual_pages, parser.num_pages) class Structures(TestCase): diff --git a/tests/util.py b/tests/util.py index 2a2ef62..b3047fa 100644 --- a/tests/util.py +++ b/tests/util.py @@ -8,3 +8,8 @@ all_pdf_files = { file_path.name: BufferStream(file_path.open("rb")) for file_path in (CURRENT_FOLDER / "samples" / "pdf").iterdir() } + +all_corrupt_pdf_files = { + file_path.name: BufferStream(file_path.open("rb")) + for file_path in (CURRENT_FOLDER / "samples" / "corrupt-pdfs").iterdir() +}