Commit dbeab9e3 authored by Chris Lamb's avatar Chris Lamb 👀
Browse files

Don't crash if we can open a PDF file with PyPDF, but cannot parse the... 

Don't crash if we can open a PDF file with PyPDF, but cannot parse the annotations within. (Closes: #311)
parent 4dc5b2ff

diffoscope/comparators/pdf.py

+35 −27
Original line number Diff line number Diff line
@@ -17,6 +17,8 @@ 
# You should have received a copy of the GNU General Public License

# along with diffoscope.  If not, see <https://www.gnu.org/licenses/>.



import logging

import os

import re



from diffoscope.tools import python_module_missing, tool_required
@@ -25,6 +27,8 @@ from diffoscope.difference import Difference 
from .utils.file import File

from .utils.command import Command



logger = logging.getLogger(__name__)



try:

    import PyPDF2
@@ -95,13 +99,10 @@ class PdfFile(File): 


        return xs



    @staticmethod

    def dump_pypdf2_metadata(file):

    def dump_pypdf2_metadata(self, file):

        try:

            pdf = PyPDF2.PdfFileReader(file.path)

            document_info = pdf.getDocumentInfo()

        except PdfReadError as e:

            return f"(Could not extract metadata: {e})"



            if document_info is None:

                return ""
@@ -111,13 +112,15 @@ class PdfFile(File): 
                xs.append("{}: {!r}".format(k.lstrip("/"), v))



            return "\n".join(xs)

        except PdfReadError as e:

            msg = f"Could not extract PyPDF2 metadata from {os.path.basename(file.name)}: {e}"

            self.add_comment(msg)

            logger.error(msg)

            return ""



    @staticmethod

    def dump_pypdf2_annotations(file):

    def dump_pypdf2_annotations(self, file):

        try:

            pdf = PyPDF2.PdfFileReader(file.path)

        except PdfReadError as e:

            return f"(Could not open file: {e})"



            xs = []

            for x in range(pdf.getNumPages()):
@@ -132,3 +135,8 @@ class PdfFile(File): 
                    pass



            return "\n".join(xs)

        except PdfReadError as e:

            msg = f"Could not extract PyPDF2 annotations from {os.path.basename(file.name)}: {e}"

            file.add_comment(msg)

            logger.error(msg)

            return ""