@@ -68,48 +68,49 @@ SCHEMA = Schema(
extension=TEXT(stored=True)
)
IDX_NAME = 'HG_INDEX'
FORMATTER = HtmlFormatter('span', between='\n<span class="break">...</span>\n')
FRAGMENTER = ContextFragmenter(200)
CHGSETS_SCHEMA = Schema(
raw_id=ID(unique=True, stored=True),
date=NUMERIC(stored=True),
last=BOOLEAN(),
owner=TEXT(),
repository=ID(unique=True, stored=True),
author=TEXT(stored=True),
message=FieldType(format=Characters(), analyzer=ANALYZER,
scorable=True, stored=True),
parents=TEXT(),
added=TEXT(),
removed=TEXT(),
changed=TEXT(),
CHGSET_IDX_NAME = 'CHGSET_INDEX'
class MakeIndex(BasePasterCommand):
max_args = 1
min_args = 1
usage = "CONFIG_FILE"
summary = "Creates index for full text search given configuration file"
group_name = "RhodeCode"
takes_config_file = -1
parser = Command.standard_parser(verbose=True)
def command(self):
logging.config.fileConfig(self.path_to_ini_file)
from pylons import config
add_cache(config)
engine = engine_from_config(config, 'sqlalchemy.db1.')
init_model(engine)
index_location = config['index_dir']
repo_location = self.options.repo_location \
if self.options.repo_location else RepoModel().repos_path
repo_list = map(strip, self.options.repo_list.split(',')) \
if self.options.repo_list else None
repo_update_list = map(strip, self.options.repo_update_list.split(',')) \
if self.options.repo_update_list else None
@@ -197,48 +198,53 @@ class WhooshResultWrapper(object):
def __getitem__(self, key):
"""
Slicing of resultWrapper
i, j = key.start, key.stop
slices = []
for docid in self.doc_ids[i:j]:
slices.append(self.get_full_content(docid))
return slices
def get_full_content(self, docid):
res = self.searcher.stored_fields(docid[0])
log.debug('result: %s' % res)
if self.search_type == 'content':
full_repo_path = jn(self.repo_location, res['repository'])
f_path = res['path'].split(full_repo_path)[-1]
f_path = f_path.lstrip(os.sep)
content_short = self.get_short_content(res, docid[1])
res.update({'content_short': content_short,
'content_short_hl': self.highlight(content_short),
'f_path': f_path
})
elif self.search_type == 'path':
res.update({'f_path': f_path})
elif self.search_type == 'message':
res.update({'message_hl': self.highlight(res['message'])})
return res
def get_short_content(self, res, chunks):
return ''.join([res['content'][chunk[0]:chunk[1]] for chunk in chunks])
def get_chunks(self):
Smart function that implements chunking the content
but not overlap chunks so it doesn't highlight the same
close occurrences twice.
:param matcher:
:param size:
memory = [(0, 0)]
if self.matcher.supports('positions'):
for span in self.matcher.spans():
start = span.startchar or 0
@@ -69,24 +69,31 @@ class TestSearchController(TestControlle
{'q': 'changed:tests/utils.py',
'type': 'commit'})
response.mustcontain('a00c1b6f5d7a6ae678fd553a8b81d92367f7ecf1')
def test_search_commit_added_file(self):
self.log_user()
response = self.app.get(url(controller='search', action='index'),
{'q': 'added:README.rst',
response.mustcontain('2 results')
#HG
response.mustcontain('3803844fdbd3b711175fc3da9bdacfcd6d29a6fb')
#GIT
response.mustcontain('ff7ca51e58c505fec0dd2491de52c622bb7a806b')
def test_search_author(self):
{'q': 'author:marcin@python-blog.com raw_id:b986218ba1c9b0d6a259fac9b050b1724ed8e545',
response.mustcontain('1 results')
def test_search_file_name(self):
{'q': 'README.rst', 'type': 'path'})
\ No newline at end of file
Status change: