def test_h2_parsing(self):
data = process_file(os.path.join(
base_dir,
'files/api.fjson',
))
self.assertEqual(data['sections'][1]['id'],
'a-basic-api-client-using-slumber')
# Only capture h2's after the first section
for obj in data['sections'][1:]:
self.assertEqual(obj['content'][:5], '\n<h2>')
def test_h2_parsing(self):
data = process_file(
os.path.join(
base_dir,
'files/api.fjson',
)
)
self.assertEqual(data['sections'][1]['id'], 'a-basic-api-client-using-slumber')
# Only capture h2's after the first section
for obj in data['sections'][1:]:
self.assertEqual(obj['content'][:5], '\n<h2>')
def get_processed_json(self):
file_path = self.json_file_path
try:
return process_file(file_path)
except Exception:
log.warning(
'Unhandled exception during search processing file: %s' % file_path
)
return {
'headers': [], 'content': '', 'path': file_path, 'title': '',
'sections': []
}
def get_processed_json(self):
"""
Get the parsed JSON for search indexing.
Check for two paths for each index file
This is because HTMLDir can generate a file from two different places:
* foo.rst
* foo/index.rst
Both lead to `foo/index.html`
https://github.com/rtfd/readthedocs.org/issues/5368
"""
file_path = None
if settings.RTD_BUILD_MEDIA_STORAGE:
storage = get_storage_class(settings.RTD_BUILD_MEDIA_STORAGE)()
fjson_paths = []
basename = os.path.splitext(self.path)[0]
fjson_paths.append(basename + '.fjson')
if basename.endswith('/index'):
new_basename = re.sub(r'\/index$', '', basename)
fjson_paths.append(new_basename + '.fjson')
storage_path = self.project.get_storage_path(
type_='json',
version_slug=self.version.slug,
include_file=False)
try:
for fjson_path in fjson_paths:
file_path = storage.join(storage_path, fjson_path)
if storage.exists(file_path):
return process_file(file_path)
except Exception:
log.warning(
'Unhandled exception during search processing file: %s',
file_path,
)
else:
log.warning(
'Skipping HTMLFile processing because of no storage backend')
return {
'path': file_path,
'title': '',
'sections': [],
'domain_data': {},
}
def test_h2_parsing(self):
data = process_file(os.path.join(
base_dir,
'files/api.fjson',
), )
self.assertEqual(data['path'], 'api')
self.assertEqual(data['sections'][1]['id'],
'a-basic-api-client-using-slumber')
self.assertTrue(
data['sections'][1]['content'].startswith('You can use Slumber'))
self.assertEqual(data['title'], 'Read the Docs Public API')
self.assertTrue(
len(data['sections']) > 0,
'There are many sections for the processed file')
# There should be no new line character present
for section in data['sections']:
self.assertFalse('\n' in section['content'])
def get_processed_json(self):
"""
Get the parsed JSON for search indexing.
Check for two paths for each index file
This is because HTMLDir can generate a file from two different places:
* foo.rst
* foo/index.rst
Both lead to `foo/index.html`
https://github.com/rtfd/readthedocs.org/issues/5368
"""
paths = []
basename = os.path.splitext(self.path)[0]
paths.append(basename + '.fjson')
if basename.endswith('/index'):
new_basename = re.sub(r'\/index$', '', basename)
paths.append(new_basename + '.fjson')
full_json_path = self.project.get_production_media_path(
type_='json', version_slug=self.version.slug, include_file=False
)
try:
for path in paths:
file_path = os.path.join(full_json_path, path)
if os.path.exists(file_path):
return process_file(file_path)
except Exception:
log.warning(
'Unhandled exception during search processing file: %s',
file_path,
)
return {
'headers': [],
'content': '',
'path': file_path,
'title': '',
'sections': [],
}
