def test_meta_type02(self):
"""Use "site" if it's "marked" and has sitemap.xml"""
index_file = os.path.join(self.test_input, 'data', '20200101010101',
'index.html')
sitemap_file = os.path.join(self.test_input, 'data', '20200101010101',
'sitemap.xml')
os.makedirs(os.path.dirname(sitemap_file))
with open(index_file, 'w', encoding='UTF-8') as fh:
pass
with open(sitemap_file, 'w', encoding='UTF-8') as fh:
pass
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:Description RDF:about="urn:scrapbook:item20200101010101"
NS1:type="marked" />
</RDF:RDF>
""")
for info in sb2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_meta_files()
self.assertEqual(book.meta['20200101010101']['type'], 'site')
self.assertTrue(book.meta['20200101010101']['marked'])
def test_meta_modify02(self):
"""Don't take mtime of index.html if not newer."""
index_file = os.path.join(self.test_input, 'data', '20200102030405',
'index.html')
os.makedirs(os.path.dirname(index_file))
with open(index_file, 'w', encoding='UTF-8') as fh:
pass
t = time.mktime((2020, 1, 1, 0, 0, 0, 0, 0, -1))
os.utime(index_file, (t, t))
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:Description RDF:about="urn:scrapbook:item20200102030405"
NS1:id="20200102030405"
NS1:type=""
NS1:create="20200102030406"
NS1:modify="20200102030407" />
</RDF:RDF>
""")
for info in sb2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_meta_files()
self.assertEqual(
book.meta['20200102030405']['modify'],
util.datetime_to_id(util.id_to_datetime_legacy('20200102030407')))
def test_meta_basic03(self):
"""Default value for missing keys.
- type: ""
- create: infer from id
- modify: infer from create (and then id)
"""
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:Description RDF:about="urn:scrapbook:item20200102030405" />
</RDF:RDF>
""")
for info in sb2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_meta_files()
self.assertDictEqual(book.meta['20200102030405'], {
'index': '20200102030405/index.html',
'type': '',
'create': util.datetime_to_id(util.id_to_datetime_legacy('20200102030405')),
'modify': util.datetime_to_id(util.id_to_datetime_legacy('20200102030405')),
})
def test_meta_basic02(self):
"""A typical item sample of legacy ScrapBook."""
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:Description RDF:about="urn:scrapbook:item20200102030405"
NS1:id="20200102030405"
NS1:type=""
NS1:title="dummy title"
NS1:chars=""
NS1:comment="dummy comment __BR__ 2nd line"
NS1:icon="favicon.ico"
NS1:source="http://example.com/foo" />
</RDF:RDF>
""")
for info in sb2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_meta_files()
self.assertDictEqual(book.meta['20200102030405'], {
'index': '20200102030405/index.html',
'title': 'dummy title',
'type': '',
'create': util.datetime_to_id(util.id_to_datetime_legacy('20200102030405')),
'modify': util.datetime_to_id(util.id_to_datetime_legacy('20200102030405')),
'source': 'http://example.com/foo',
'icon': 'favicon.ico',
'comment': 'dummy comment\n2nd line',
})
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_meta_basic04(self):
"""Should work correctly for another NS name
(seen in some scrapbook.rdf files)
"""
with open(self.test_input_rdf, 'w', encoding='UTF-8') as fh:
fh.write("""\
<?xml version="1.0"?>
<RDF:RDF xmlns:NS2="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:Description RDF:about="urn:scrapbook:item20200102030405"
NS2:id="20200102030405"
NS2:type=""
NS2:title="title"
NS2:comment="comment"
NS2:icon="favicon.ico"
NS2:source="http://example.com" />
</RDF:RDF>
""")
for info in sb2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_meta_files()
self.assertDictEqual(
book.meta['20200102030405'], {
'index':
'20200102030405/index.html',
'type':
'',
'create':
util.datetime_to_id(
util.id_to_datetime_legacy('20200102030405')),
'modify':
util.datetime_to_id(
util.id_to_datetime_legacy('20200102030405')),
'title':
'title',
'comment':
'comment',
'icon':
'favicon.ico',
'source':
'http://example.com',
})
def test_meta_icon01(self):
"""Resolve resource://scrapbook/data/<self-id>/..."""
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:Description RDF:about="urn:scrapbook:item20200102030405"
NS1:icon="resource://scrapbook/data/20200102030405/favicon.ico" />
</RDF:RDF>
""")
for info in sb2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_meta_files()
self.assertEqual(book.meta['20200102030405']['icon'], 'favicon.ico')
def test_meta_icon05(self):
"""Handle special chars."""
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:Description RDF:about="urn:scrapbook:item20200102030405"
NS1:icon="resource://scrapbook/%E4%B8%AD%E6%96%87%25%23abc.png" />
</RDF:RDF>
""")
for info in sb2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_meta_files()
self.assertEqual(book.meta['20200102030405']['icon'], '../../%E4%B8%AD%E6%96%87%25%23abc.png')
def test_meta_type01(self):
"""Translate types."""
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:Description RDF:about="urn:scrapbook:item20200101010101"
NS1:type="" />
<RDF:Description RDF:about="urn:scrapbook:item20200101010102"
NS1:type="combine" />
<RDF:Description RDF:about="urn:scrapbook:item20200101010103"
NS1:type="marked" />
<RDF:Description RDF:about="urn:scrapbook:item20200101010104"
NS1:type="note" />
<RDF:Description RDF:about="urn:scrapbook:item20200101010105"
NS1:type="notex" />
</RDF:RDF>
""")
for info in sb2wsb.run(self.test_input, self.test_output):
pass
book = Host(self.test_output).books['']
book.load_meta_files()
self.assertEqual(book.meta['20200101010101']['type'], '')
self.assertIsNone(book.meta['20200101010101'].get('marked'))
self.assertEqual(book.meta['20200101010102']['type'], 'combine')
self.assertIsNone(book.meta['20200101010102'].get('marked'))
self.assertEqual(book.meta['20200101010103']['type'], '')
self.assertTrue(book.meta['20200101010103']['marked'])
self.assertEqual(book.meta['20200101010104']['type'], 'postit')
self.assertIsNone(book.meta['20200101010104'].get('marked'))
self.assertEqual(book.meta['20200101010105']['type'], 'note')
self.assertIsNone(book.meta['20200101010105'].get('marked'))
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'),
})
