forked from github/pelican
Extra functionality for pelican-import for wordpress imports
This commit is contained in:
Alistair Magee
parent
d91750090b
commit
ea3e160db1
3 changed files with 640 additions and 55 deletions
|
|
@ -4,10 +4,12 @@ from __future__ import unicode_literals, print_function
|
|||
import os
|
||||
import re
|
||||
|
||||
from pelican.tools.pelican_import import wp2fields, fields2pelican, decode_wp_content, build_header
|
||||
from pelican.tools.pelican_import import wp2fields, fields2pelican, decode_wp_content, build_header, build_markdown_header, get_attachments, download_attachments
|
||||
from pelican.tests.support import (unittest, temporary_folder, mute,
|
||||
skipIfNoExecutable)
|
||||
|
||||
from pelican.utils import slugify
|
||||
|
||||
CUR_DIR = os.path.dirname(__file__)
|
||||
WORDPRESS_XML_SAMPLE = os.path.join(CUR_DIR, 'content', 'wordpressexport.xml')
|
||||
WORDPRESS_ENCODED_CONTENT_SAMPLE = os.path.join(CUR_DIR,
|
||||
|
|
@ -29,6 +31,7 @@ class TestWordpressXmlImporter(unittest.TestCase):
|
|||
|
||||
def setUp(self):
|
||||
self.posts = list(wp2fields(WORDPRESS_XML_SAMPLE))
|
||||
self.custposts = list(wp2fields(WORDPRESS_XML_SAMPLE, True))
|
||||
|
||||
def test_ignore_empty_posts(self):
|
||||
self.assertTrue(self.posts)
|
||||
|
|
@ -54,6 +57,112 @@ class TestWordpressXmlImporter(unittest.TestCase):
|
|||
fname = list(silent_f2p(test_post, 'markdown', temp, dirpage=True))[0]
|
||||
self.assertTrue(fname.endswith('pages%sempty.md' % os.path.sep))
|
||||
|
||||
def test_dircat(self):
|
||||
silent_f2p = mute(True)(fields2pelican)
|
||||
test_posts = []
|
||||
for post in self.posts:
|
||||
# check post kind
|
||||
if len(post[5]) > 0: # Has a category
|
||||
test_posts.append(post)
|
||||
with temporary_folder() as temp:
|
||||
fnames = list(silent_f2p(test_posts, 'markdown', temp, dircat=True))
|
||||
index = 0
|
||||
for post in test_posts:
|
||||
name = post[2]
|
||||
category = slugify(post[5][0])
|
||||
name += '.md'
|
||||
filename = os.path.join(category, name)
|
||||
out_name = fnames[index]
|
||||
self.assertTrue(out_name.endswith(filename))
|
||||
index += 1
|
||||
|
||||
def test_unless_custom_post_all_items_should_be_pages_or_posts(self):
|
||||
self.assertTrue(self.posts)
|
||||
pages_data = []
|
||||
for title, content, fname, date, author, categ, tags, kind, format in self.posts:
|
||||
if kind == 'page' or kind == 'article':
|
||||
pass
|
||||
else:
|
||||
pages_data.append((title, fname))
|
||||
self.assertEqual(0, len(pages_data))
|
||||
|
||||
def test_recognise_custom_post_type(self):
|
||||
self.assertTrue(self.custposts)
|
||||
cust_data = []
|
||||
for title, content, fname, date, author, categ, tags, kind, format in self.custposts:
|
||||
if kind == 'article' or kind == 'page':
|
||||
pass
|
||||
else:
|
||||
cust_data.append((title, kind))
|
||||
self.assertEqual(3, len(cust_data))
|
||||
self.assertEqual(('A custom post in category 4', 'custom1'), cust_data[0])
|
||||
self.assertEqual(('A custom post in category 5', 'custom1'), cust_data[1])
|
||||
self.assertEqual(('A 2nd custom post type also in category 5', 'custom2'), cust_data[2])
|
||||
|
||||
def test_custom_posts_put_in_own_dir(self):
|
||||
silent_f2p = mute(True)(fields2pelican)
|
||||
test_posts = []
|
||||
for post in self.custposts:
|
||||
# check post kind
|
||||
if post[7] == 'article' or post[7] == 'page':
|
||||
pass
|
||||
else:
|
||||
test_posts.append(post)
|
||||
with temporary_folder() as temp:
|
||||
fnames = list(silent_f2p(test_posts, 'markdown', temp, wp_custpost = True))
|
||||
index = 0
|
||||
for post in test_posts:
|
||||
name = post[2]
|
||||
kind = post[7]
|
||||
name += '.md'
|
||||
filename = os.path.join(kind, name)
|
||||
out_name = fnames[index]
|
||||
self.assertTrue(out_name.endswith(filename))
|
||||
index += 1
|
||||
|
||||
def test_custom_posts_put_in_own_dir_and_catagory_sub_dir(self):
|
||||
silent_f2p = mute(True)(fields2pelican)
|
||||
test_posts = []
|
||||
for post in self.custposts:
|
||||
# check post kind
|
||||
if post[7] == 'article' or post[7] == 'page':
|
||||
pass
|
||||
else:
|
||||
test_posts.append(post)
|
||||
with temporary_folder() as temp:
|
||||
fnames = list(silent_f2p(test_posts, 'markdown', temp,
|
||||
wp_custpost=True, dircat=True))
|
||||
index = 0
|
||||
for post in test_posts:
|
||||
name = post[2]
|
||||
kind = post[7]
|
||||
category = slugify(post[5][0])
|
||||
name += '.md'
|
||||
filename = os.path.join(kind, category, name)
|
||||
out_name = fnames[index]
|
||||
self.assertTrue(out_name.endswith(filename))
|
||||
index += 1
|
||||
|
||||
def test_wp_custpost_true_dirpage_false(self):
|
||||
#pages should only be put in their own directory when dirpage = True
|
||||
silent_f2p = mute(True)(fields2pelican)
|
||||
test_posts = []
|
||||
for post in self.custposts:
|
||||
# check post kind
|
||||
if post[7] == 'page':
|
||||
test_posts.append(post)
|
||||
with temporary_folder() as temp:
|
||||
fnames = list(silent_f2p(test_posts, 'markdown', temp,
|
||||
wp_custpost=True, dirpage=False))
|
||||
index = 0
|
||||
for post in test_posts:
|
||||
name = post[2]
|
||||
name += '.md'
|
||||
filename = os.path.join('pages', name)
|
||||
out_name = fnames[index]
|
||||
self.assertFalse(out_name.endswith(filename))
|
||||
|
||||
|
||||
def test_can_toggle_raw_html_code_parsing(self):
|
||||
def r(f):
|
||||
with open(f) as infile:
|
||||
|
|
@ -137,3 +246,48 @@ class TestBuildHeader(unittest.TestCase):
|
|||
'これは広い幅の文字だけで構成されたタイトルです\n' +
|
||||
'##############################################\n\n')
|
||||
|
||||
def test_galleries_added_to_header(self):
|
||||
header = build_header('test', None, None, None, None,
|
||||
None, ['output/test1', 'output/test2'])
|
||||
self.assertEqual(header, 'test\n####\n' + ':attachments: output/test1, '
|
||||
+ 'output/test2\n\n')
|
||||
|
||||
def test_galleries_added_to_markdown_header(self):
|
||||
header = build_markdown_header('test', None, None, None, None, None,
|
||||
['output/test1', 'output/test2'])
|
||||
self.assertEqual(header, 'Title: test\n' + 'Attachments: output/test1, '
|
||||
+ 'output/test2\n\n')
|
||||
|
||||
@unittest.skipUnless(BeautifulSoup, 'Needs BeautifulSoup module')
|
||||
class TestWordpressXMLAttachements(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.attachments = get_attachments(WORDPRESS_XML_SAMPLE)
|
||||
|
||||
def test_recognise_attachments(self):
|
||||
self.assertTrue(self.attachments)
|
||||
self.assertTrue(len(self.attachments.keys()) == 3)
|
||||
|
||||
def test_attachments_associated_with_correct_post(self):
|
||||
self.assertTrue(self.attachments)
|
||||
for post in self.attachments.keys():
|
||||
if post is None:
|
||||
self.assertTrue(self.attachments[post][0] == 'https://upload.wikimedia.org/wikipedia/commons/thumb/2/2c/Pelican_lakes_entrance02.jpg/240px-Pelican_lakes_entrance02.jpg')
|
||||
elif post == 'with-excerpt':
|
||||
self.assertTrue(self.attachments[post][0] == 'http://thisurlisinvalid.notarealdomain/not_an_image.jpg')
|
||||
self.assertTrue(self.attachments[post][1] == 'http://en.wikipedia.org/wiki/File:Pelikan_Walvis_Bay.jpg')
|
||||
elif post == 'with-tags':
|
||||
self.assertTrue(self.attachments[post][0] == 'http://thisurlisinvalid.notarealdomain')
|
||||
else:
|
||||
self.fail('all attachments should match to a filename or None, {}'.format(post))
|
||||
|
||||
def test_download_attachments(self):
|
||||
real_file = os.path.join(CUR_DIR, 'content/article.rst')
|
||||
good_url = 'file://' + real_file
|
||||
bad_url = 'http://www.notarealsite.notarealdomain/not_a_file.txt'
|
||||
silent_da = mute()(download_attachments)
|
||||
with temporary_folder() as temp:
|
||||
#locations = download_attachments(temp, [good_url, bad_url])
|
||||
locations = list(silent_da(temp, [good_url, bad_url]))
|
||||
self.assertTrue(len(locations) == 1)
|
||||
directory = locations[0]
|
||||
self.assertTrue(directory.endswith('content/article.rst'))
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue