Use python-xmp-toolkit for xmp check

Eliminates PyPDF2 and defusedxml as dependencies.

.travis.yml

@@ -17,6 +17,7 @@ addons:
     - libavcodec56
     - libavformat56
     - libavutil54
+    - libexempi3
     - libffi-dev
     - pngquant
     - poppler-utils

.travis/Brewfile

@@ -4,6 +4,7 @@ brew 'ghostscript'
 brew 'jbig2dec'
 brew 'jbig2enc'
 brew 'leptonica'
+brew 'exempi'
 brew 'libffi'
 brew 'libtiff'
 brew 'libxml2'

docs/release_notes.rst

@@ -15,7 +15,7 @@ v7
 
 -   The core algorithm for combining OCR layers with existing PDF pages has been rewritten and improved considerably.  The new algorithm uses less temporary disk space and eliminates object duplication and deduplication that was required when processing certain PDFs.
 
--   New dependency: `pikepdf <https://github.com/pikepdf>`_. pikepdf is a  powerful new Python PDF library driving the latest OCRmyPDF features, built on the proven and mature libqpdf C++ library.
+-   New dependency: `pikepdf <https://github.com/pikepdf>`_. pikepdf is a  powerful new Python PDF library driving the latest OCRmyPDF features, built on QPDF's proven and mature libqpdf C++ library.
 
 -   New feature: PDF optimization with ``-O`` or ``--optimize``.  After OCR, OCRmyPDF will perform image optimizations relevant to OCR PDFs.
 
@@ -37,6 +37,12 @@ v7
 
     +   ``-g``, the option to generate debug text pages, was removed because it was a maintenance burden and only worked in isolated cases. HOCR pages can still be previewed by running the hocrtransform.py with appropriate settings.
 
+-   Removed dependencies
+
+    +   ``PyPDF2`` is no longer used except in the test suite.
+
+    +   ``defusedxml`` is no longer used anywhere.
+
 -   The ``sandwich`` PDF renderer can be used with all supported versions of Tesseract, including that those priority to v3.05 which don't support ``-c textonly``
 
 -   ``--pdf-renderer auto`` option and the diagnostics used to select a PDF renderer now work better with old versions, but may make different decisions than past versions.

setup.py

@@ -247,13 +247,12 @@ setup(
     ],
     install_requires=[
         'cffi >= 1.9.1',          # must be a setup and install requirement
-        'defusedxml >= 0.5.0',    # pure Python, so track HEAD closely
         'img2pdf >= 0.2.4',       # pure Python, so track HEAD closely
         'pikepdf',
         'Pillow >= 4.0.0, != 5.1.0 ; sys_platform == "darwin"',
                                   # Pillow < 4 has BytesIO/TIFF bug w/img2pdf 0.2.3
                                   # block 5.1.0, broken wheels
-        'PyPDF2 >= 1.26',         # pure Python, so track HEAD closely
+        'python-xmp-toolkit >= 2, < 3',
         'reportlab >= 3.3.0',     # oldest released version with sane image handling
         'ruffus == 2.6.3',        # pinned - ocrmypdf implements a 2.6.3 workaround
     ],

src/ocrmypdf/pdfa.py

@@ -20,12 +20,9 @@
 from string import Template
 from binascii import hexlify
 from datetime import datetime
-from xml.parsers.expat import ExpatError
 import pkg_resources
-import PyPDF2 as pypdf
-import warnings
-from defusedxml.minidom import parseString as defused_parseString
-from unittest.mock import patch
+from libxmp.utils import file_to_dict
+from libxmp import consts
 
 ICC_PROFILE_RELPATH = 'data/sRGB.icc'
 
@@ -230,35 +227,32 @@ def file_claims_pdfa(filename):
 
     This checks if the XMP metadata contains a PDF/A marker.
     """
-    warnings.simplefilter('ignore', pypdf.utils.PdfReadWarning)
-    pdf = pypdf.PdfFileReader(filename)
-    try:
-        # Monkeypatch PyPDF2 to use defusedxml as its XML parser, for safety
-        with patch('xml.dom.minidom.parseString', new=defused_parseString):
-            xmp = pdf.getXmpMetadata()
-    except ExpatError:
-        return {'pass': False, 'output': 'pdf',
-                'conformance': 'Invalid XML metadata'}
 
-    try:
-        pdfa_nodes = xmp.getNodesInNamespace(
-            aboutUri='',
-            namespace='http://www.aiim.org/pdfa/ns/id/')
-    except AttributeError:
+    xmp = file_to_dict(filename)
+    if not xmp:
         return {'pass': False, 'output': 'pdf',
                 'conformance': 'No XMP metadata'}
 
-    pdfa_dict = {attr.localName: attr.value for attr in pdfa_nodes}
-    if not pdfa_dict:
+    if not consts.XMP_NS_PDFA_ID in xmp:
         return {'pass': False, 'output': 'pdf',
-                'conformance': 'No XMP metadata'}
+                'conformance': 'No PDF/A metadata in XMP'}
 
-    part_conformance = pdfa_dict['part'] + pdfa_dict['conformance']
+    pdfa_node = xmp[consts.XMP_NS_PDFA_ID]
+    def read_node(node, key):
+        return next(
+            (v for k, v, meta in pdfa_node if k == key), ''
+        )
+
+    part = read_node(pdfa_node, 'pdfaid:part')
+    conformance = read_node(pdfa_node, 'pdfaid:conformance')
+
+    part_conformance = part + conformance
     valid_part_conforms = {'1A', '1B', '2A', '2B', '2U', '3A', '3B', '3U'}
 
     conformance = 'PDF/A-{}'.format(
         part_conformance)
 
+    pdfa_dict = {}
     if part_conformance in valid_part_conforms:
         pdfa_dict['pass'] = True
         pdfa_dict['output'] = 'pdfa'

test_requirements.txt

@@ -4,4 +4,5 @@ pytest-xdist
 pytest-cov
 pytest-timeout
 python-xmp-toolkit   # requires apt-get install libexempi3
-                     # or brew install exempi
+                     # or brew install exempi
+PyPDF2 >= 1.26.0