Drop libxml2 dependency

It seems that Python's internal XML parser is good enough to do the job.

README.rst

@@ -96,7 +96,6 @@ Install dependencies::
    sudo apt-get install \
       zlib1g-dev \
       libjpeg-dev \
-      libxml2 \
       tesseract-ocr \
       qpdf \
       unpaper \

RELEASE_NOTES.rst

@@ -47,6 +47,7 @@ Changes
    - MuPDF_ tools
    - shell scripts
    - Java and JHOVE_
+   - libxml2
 
 -  Some new external dependencies are required or optional, compared to v2.x:
 
@@ -66,6 +67,10 @@ Changes
 Release candidates
 ------------------
 
+-  rc6:
+
+   - dropped libxml2 (Python lxml) since Python 3's internal XML parser is sufficient
+
 -  rc5:
 
    - dropped Java and JHOVE in favour of qpdf

ocrmypdf/hocrtransform.py

@@ -9,7 +9,7 @@
 ##############################################################################
 from reportlab.pdfgen.canvas import Canvas
 from reportlab.lib.units import inch
-from lxml import etree as ElementTree
+from xml.etree import ElementTree
 from PIL import Image
 from collections import namedtuple
 import re
@@ -35,8 +35,7 @@ class HocrTransform():
         self.dpi = dpi
         self.boxPattern = re.compile(r'bbox((\s+\d+){4})')
 
-        self.hocr = ElementTree.ElementTree()
+        self.hocr = ElementTree.parse(hocrFileName)
-        self.hocr.parse(hocrFileName)
 
         # if the hOCR file has a namespace, ElementTree requires its use to
         # find elements

setup.py

@@ -203,7 +203,6 @@ setup(
     install_requires=[
         'ruffus>=2.6.3',
         'Pillow>=2.4.0',
-        'lxml>=3.3.3',
         'reportlab>=3.1.44',
         'PyPDF2>=1.25.1'
     ],