def test_path03(self):
"""<input dir>/index.html should be indexed as single html page
"""
index_file = os.path.join(self.test_input, 'index.html')
with open(index_file, 'w', encoding='UTF-8') as fh:
fh.write("""\
<!DOCTYPE html>
<html
data-scrapbook-create="20200101000000000"
data-scrapbook-modify="20200101000000000"
data-scrapbook-source="http://example.com">
<head>
<meta charset="UTF-8">
<title>MyTitle 中文</title>
</head>
<body>
page content
</body>
</html>
""")
for info in file2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_meta_files()
book.load_toc_files()
ids = list(book.meta.keys())
id_item = ids[0]
self.assertDictEqual(
book.meta, {
id_item: {
'title': 'MyTitle 中文',
'type': '',
'index': f'{id_item}.html',
'create': '20200101000000000',
'modify': '20200101000000000',
'source': 'http://example.com',
'icon': '',
'comment': '',
},
})
self.assertDictEqual(book.toc, {
'root': [
id_item,
],
})
self.assertEqual(
set(
glob.iglob(os.path.join(self.test_output, '**'),
recursive=True)),
{
os.path.join(self.test_output, ''),
os.path.join(self.test_output, f'{id_item}.html'),
})
def test_toc(self):
with open(self.test_input_rdf, 'w', encoding='UTF-8') as fh:
fh.write("""\
<?xml version="1.0"?>
<RDF:RDF xmlns:NS1="http://amb.vis.ne.jp/mozilla/scrapbook-rdf#"
xmlns:NC="http://home.netscape.com/NC-rdf#"
xmlns:RDF="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
<RDF:Seq RDF:about="urn:scrapbook:root">
<RDF:li RDF:resource="urn:scrapbook:item20200101000000"/>
<RDF:li RDF:resource="urn:scrapbook:item20200101000001"/>
<RDF:li RDF:resource="urn:scrapbook:item20200101000002"/>
<RDF:li RDF:resource="urn:scrapbook:item20200101000003"/>
<RDF:li RDF:resource="urn:scrapbook:item20200101000004"/>
</RDF:Seq>
<RDF:Seq RDF:about="urn:scrapbook:item20200101000001">
<RDF:li RDF:resource="urn:scrapbook:item20200101000005"/>
<RDF:li RDF:resource="urn:scrapbook:item20200101000006"/>
</RDF:Seq>
<RDF:Seq RDF:about="urn:scrapbook:item20200101000002">
<RDF:li RDF:resource="urn:scrapbook:item20200101000007"/>
<RDF:li RDF:resource="urn:scrapbook:item20200101000008"/>
</RDF:Seq>
<RDF:Seq RDF:about="urn:scrapbook:item20200101000003">
<RDF:li RDF:resource="urn:scrapbook:item20200101000009"/>
</RDF:Seq>
</RDF:RDF>
""")
for info in sb2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_toc_files()
self.assertEqual(
book.toc, {
'root': [
'20200101000000',
'20200101000001',
'20200101000002',
'20200101000003',
'20200101000004',
],
'20200101000001': [
'20200101000005',
'20200101000006',
],
'20200101000002': [
'20200101000007',
'20200101000008',
],
'20200101000003': [
'20200101000009',
],
})
def test_path01(self):
"""Test hierarchical folders for */index.html
"""
index_file = os.path.join(self.test_input, 'folder1#中文', 'folder2',
'folder_data', 'index.html')
os.makedirs(os.path.dirname(index_file), exist_ok=True)
with open(index_file, 'w', encoding='UTF-8') as fh:
fh.write("""\
<!DOCTYPE html>
<html
data-scrapbook-create="20200101000000000"
data-scrapbook-modify="20200101000000000"
data-scrapbook-source="http://example.com">
<head>
<meta charset="UTF-8">
<title>MyTitle 中文</title>
</head>
<body>
page content
</body>
</html>
""")
for info in file2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_meta_files()
book.load_toc_files()
ids = list(book.meta.keys())
id_folder1 = ids[0]
id_folder2 = ids[1]
id_item = ids[2]
self.assertDictEqual(
book.meta, {
id_folder1: {
'title': 'folder1#中文',
'type': 'folder',
'create': id_folder1,
'modify': id_folder1,
},
id_folder2: {
'title': 'folder2',
'type': 'folder',
'create': id_folder2,
'modify': id_folder2,
},
id_item: {
'title': 'MyTitle 中文',
'type': '',
'index': f'{id_item}/index.html',
'create': '20200101000000000',
'modify': '20200101000000000',
'source': 'http://example.com',
'icon': '',
'comment': '',
},
})
self.assertDictEqual(
book.toc, {
'root': [
id_folder1,
],
id_folder1: [
id_folder2,
],
id_folder2: [
id_item,
],
})
self.assertEqual(
set(
glob.iglob(os.path.join(self.test_output, '**'),
recursive=True)),
{
os.path.join(self.test_output, ''),
os.path.join(self.test_output, id_item),
os.path.join(self.test_output, id_item, 'index.html'),
})
def test_supporting_folder02(self):
"""Test for supporting folder *_files
"""
index_file = os.path.join(self.test_input, 'mypage.html')
with open(index_file, 'w', encoding='UTF-8') as fh:
fh.write("""\
<!DOCTYPE html>
<html
data-scrapbook-create="20200101000000000"
data-scrapbook-modify="20200101000000000"
data-scrapbook-source="http://example.com">
<head>
<meta charset="UTF-8">
<title>MyTitle 中文</title>
</head>
<body>
page content
<img src="mypage_files/picture.bmp">
</body>
</html>
""")
img_file = os.path.join(self.test_input, 'mypage_files', 'picture.bmp')
os.makedirs(os.path.dirname(img_file), exist_ok=True)
with open(img_file, 'wb') as fh:
fh.write(b'dummy')
for info in file2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_meta_files()
book.load_toc_files()
ids = list(book.meta.keys())
id_item = ids[0]
self.assertDictEqual(
book.meta, {
id_item: {
'title': 'MyTitle 中文',
'type': '',
'index': f'{id_item}/index.html',
'create': '20200101000000000',
'modify': '20200101000000000',
'source': 'http://example.com',
'icon': '',
'comment': '',
},
})
self.assertDictEqual(book.toc, {
'root': [
id_item,
],
})
self.assertEqual(
set(
glob.iglob(os.path.join(self.test_output, '**'),
recursive=True)),
{
os.path.join(self.test_output, ''),
os.path.join(self.test_output, id_item),
os.path.join(self.test_output, id_item, 'index.html'),
os.path.join(self.test_output, id_item, 'mypage.html'),
os.path.join(self.test_output, id_item, 'mypage_files'),
os.path.join(self.test_output, id_item, 'mypage_files',
'picture.bmp'),
})