diff --git a/README.md b/README.md
index 3a4d871..e468d54 100644
--- a/README.md
+++ b/README.md
@@ -1,23 +1,30 @@
-docx2html
-=========
+# docx2html
-Convert a docx (OOXML) file to html
+Convert a docx (OOXML) file to semantic HTML.
+All of Word formatting nonsense is stripped away and
+you're left with a cleanly-formatted version of the content.
-Usage
-=====
+
+## Usage
>>> from docx2html import convert
>>> html = convert('path/to/docx/file')
-Running Tests
-=============
+## Running Tests for Development
+
+ $ virtualenv path/to/new/virtualenv
+ $ source path/to/new/virtualenv/bin/activate
+ $ cd path/to/workspace
+ $ git clone git://github.com/PolicyStat/docx2html.git
+ $ cd docx2html
+ $ pip install .
+ $ pip install -r test_requirements.txt
$ ./run_tests.sh
-Description
-===========
+## Description
docx2html is designed to take a docx file and extract the content out and
convert that content to html. It does not care about styles or fonts or
@@ -46,3 +53,26 @@ is a list of what currently works:
* Simple headings
* Root level lists that are upper case roman numerals get converted to h2
tags
+
+### Handling embedded images
+
+docx2html allows you to specify how you would like to handle image uploading.
+For example, you might be uploading your images to Amazon S3 eg:
+Note: This documentation sucks, so you might need to read the source.
+
+ import os.path
+ from shutil import copyfile
+
+ from docx2html import convert
+
+ def handle_image(image_id, relationship_dict):
+ image_path = relationship_dict[image_id]
+ # Now do something to the image. Let's move it somewhere.
+ _, filename = os.path.split(image_path)
+ destination_path = os.path.join('/tmp', filename)
+ copyfile(image_path, destination_path)
+
+ # Return the `src` attribute to be used in the img tag
+ return 'file://%s' % destination
+
+ html = convert('path/to/docx/file', image_handler=handle_image)
diff --git a/docx2html/core.py b/docx2html/core.py
index a09803a..29774bd 100644
--- a/docx2html/core.py
+++ b/docx2html/core.py
@@ -1144,6 +1144,9 @@ def get_p_data(p, meta_data, is_td=False):
p_text += '
'
else: # We have an image
image_id = get_image_id(child)
+ if image_id not in meta_data.relationship_dict:
+ # This image does not have an image_id
+ continue
src = meta_data.image_handler(
image_id,
meta_data.relationship_dict,
diff --git a/docx2html/tests/__init__.py b/docx2html/tests/__init__.py
index a164a51..6d75948 100644
--- a/docx2html/tests/__init__.py
+++ b/docx2html/tests/__init__.py
@@ -187,6 +187,27 @@
""".strip()
+DOCUMENT_PICT_NO_IMAGEID_TEMPLATE = """
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+""".strip()
+
+
def assert_html_equal(actual_html, expected_html):
assert collapse_html(
actual_html,
diff --git a/docx2html/tests/test_xml.py b/docx2html/tests/test_xml.py
index b6143bf..a535aea 100644
--- a/docx2html/tests/test_xml.py
+++ b/docx2html/tests/test_xml.py
@@ -16,6 +16,7 @@
DOCUMENT_DRAWING_TEMPLATE,
DOCUMENT_LI_TEMPLATE,
DOCUMENT_PICT_TEMPLATE,
+ DOCUMENT_PICT_NO_IMAGEID_TEMPLATE,
DOCUMENT_P_TEMPLATE,
DOCUMENT_TBL_TEMPLATE,
DOCUMENT_TC_TEMPLATE,
@@ -402,3 +403,23 @@ def test_image_id_for_pict(self):
pict_tag = pict_tags[0]
image_id = get_image_id(pict_tag)
self.assertEqual(image_id, 'rId0')
+
+
+class PictImageTestCase(_TranslationTestCase):
+ expected_output = '''
+
+ '''
+
+ def get_xml(self):
+ pict = DOCUMENT_PICT_NO_IMAGEID_TEMPLATE
+ tags = [
+ pict,
+ ]
+ body = ''
+ for el in tags:
+ body += el
+
+ xml = DOCUMENT_XML_TEMPLATE % {
+ 'body': body,
+ }
+ return etree.fromstring(xml)
diff --git a/setup.py b/setup.py
index 135d7c1..c340146 100644
--- a/setup.py
+++ b/setup.py
@@ -30,7 +30,6 @@ def get_readme():
scripts=[],
zip_safe=False,
install_requires=['lxml==2.2.4', 'pillow==1.7.7'],
- tests_require=['nose'],
cmdclass={},
classifiers=[
"Development Status :: 3 - Alpha",
diff --git a/test_requirements.txt b/test_requirements.txt
new file mode 100644
index 0000000..a678696
--- /dev/null
+++ b/test_requirements.txt
@@ -0,0 +1,2 @@
+nose
+mock