kallithea Changeset - 73e3599971da

Changeset - 73e3599971da

Parent rev.

Child rev.

[Not reviewed]

default

0 2 0

FUJIWARA Katsunori - 9 years ago 2017-01-22 18:17:38
foozy@lares.dti.ne.jp

journal: make "repository:" filtering condition work as expected (Issue #261)

Before this revision, journal filtering conditions like as below never
match against any entry, even if there are corresponded repositories.

- repository:foo/bar
- repository:foo-bar

Whoosh library, which is used to parse filtering condition, does:

- treat almost all non-alphanumeric characters as delimiter at
parsing condition
- join each conditions at filtering by "AND", by default

For example, filtering condition "repository:foo/bar" is translated as
"repository:foo AND repository:bar". This combined condition never
matches against any entry, because it is impossible that "repository"
field in DBMS table "user_logs" has both "foo" and "bar" values at
same time.

Using TEXT for "repository" of JOURNAL_SCHEMA causes this issue,
because TEXT assumes tokenization at parsing.

In addition to it, using TEXT also causes unintentional ignorance of
"stop words" in filtering conditions. For example, "this", "a", "you",
and so on are ignored at parsing, because these are too generic words
(from point of view of generic "text search").

To make "repository:" filtering condition work as expected, this
revision uses ID instead of TEST for "repository" of
JOURNAL_COLUMN. ID avoids both tokenization and removing "stop words".

This replacement should be safe with already existing DBMS instance,
because:

- JOURNAL_SCHEMA is used only to parse filtering condition
- DBMS table "user_logs" itself is defined by UserLog class
(in kallithea/model/db.py)

BTW, using ID also avoids normalization by lowercase-ing. But this
doesn't violate current case-insensitive search policy, because
LOWER-ing in actual SQL query is achieved by get_filterion() or so in
kallithea/controllers/admin/admin.py.

2 files changed with 5 insertions and 5 deletions:

kallithea/lib/indexers/__init__.py

kallithea/tests/functional/test_admin.py

0 comments (0 inline, 0 general)

kallithea/lib/indexers/__init__.py

➞

Show inline comments

@@ @@ -37,97 +37,97 @@ from whoosh.analysis import RegexTokeniz @@
 from whoosh.fields import TEXT, ID, STORED, NUMERIC, BOOLEAN, Schema, FieldType, DATETIME
 from whoosh.formats import Characters
 from whoosh.highlight import highlight as whoosh_highlight, HtmlFormatter, ContextFragmenter
 from kallithea.lib.utils2 import LazyProperty
 log = logging.getLogger(__name__)
 # CUSTOM ANALYZER wordsplit + lowercase filter
 ANALYZER = RegexTokenizer(expression=r"\w+") | LowercaseFilter()
 #INDEX SCHEMA DEFINITION
 SCHEMA = Schema(
     fileid=ID(unique=True),
     owner=TEXT(),
     repository=TEXT(stored=True),
     path=TEXT(stored=True),
     content=FieldType(format=Characters(), analyzer=ANALYZER,
                       scorable=True, stored=True),
     modtime=STORED(),
     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'
 # used only to generate queries in journal
 JOURNAL_SCHEMA = Schema(
     username=TEXT(),
     date=DATETIME(),
     action=TEXT(),
-    repository=TEXT(),
+    repository=ID(),
     ip=TEXT(),
+)
 class WhooshResultWrapper(object):
     def __init__(self, search_type, searcher, matcher, highlight_items,
                  repo_location):
         self.search_type = search_type
         self.searcher = searcher
         self.matcher = matcher
         self.highlight_items = highlight_items
         self.fragment_size = 200
         self.repo_location = repo_location
     @LazyProperty
     def doc_ids(self):
         docs_id = []
         while self.matcher.is_active():
             docnum = self.matcher.id()
             chunks = [offsets for offsets in self.get_chunks()]
             docs_id.append([docnum, chunks])
             self.matcher.next()
         return docs_id
     def __str__(self):
         return '<%s at %s>' % (self.__class__.__name__, len(self.doc_ids))
     def __repr__(self):
         return self.__str__()
     def __len__(self):
         return len(self.doc_ids)
     def __iter__(self):
         """
         Allows Iteration over results,and lazy generate content
         *Requires* implementation of ``__getitem__`` method.
         """
         for docid in self.doc_ids:
             yield self.get_full_content(docid)
     def __getitem__(self, key):
         """
         Slicing of resultWrapper
         """
         i, j = key.start, key.stop

kallithea/tests/functional/test_admin.py

➞

Show inline comments

@@ @@ -106,90 +106,90 @@ class TestAdminController(TestController @@
                                     filter='username:demo'))
         response.mustcontain(' 1087 Entries')
     def test_filter_journal_filter_exact_match_on_username_camelCase(self):
         self.log_user()
         response = self.app.get(url(controller='admin/admin', action='index',
                                     filter='username:DemO'))
         response.mustcontain(' 1087 Entries')
     def test_filter_journal_filter_wildcard_on_username(self):
         self.log_user()
         response = self.app.get(url(controller='admin/admin', action='index',
                                     filter='username:*test*'))
         response.mustcontain(' 100 Entries')
     def test_filter_journal_filter_prefix_on_username(self):
         self.log_user()
         response = self.app.get(url(controller='admin/admin', action='index',
                                     filter='username:demo*'))
         response.mustcontain(' 1101 Entries')
     def test_filter_journal_filter_prefix_on_user_or_other_user(self):
         self.log_user()
         response = self.app.get(url(controller='admin/admin', action='index',
                                     filter='username:demo OR username:volcan'))
         response.mustcontain(' 1095 Entries')  # 1087 + 8
     def test_filter_journal_filter_wildcard_on_action(self):
         self.log_user()
         response = self.app.get(url(controller='admin/admin', action='index',
                                     filter='action:*pull_request*'))
         response.mustcontain(' 187 Entries')
     def test_filter_journal_filter_on_date(self):
         self.log_user()
         response = self.app.get(url(controller='admin/admin', action='index',
                                     filter='date:20121010'))
         response.mustcontain(' 47 Entries')
     def test_filter_journal_filter_on_date_2(self):
         self.log_user()
         response = self.app.get(url(controller='admin/admin', action='index',
                                     filter='date:20121020'))
         response.mustcontain(' 17 Entries')
     @parametrize('filter,hit', [
         #### "repository:" filtering
         # "/" is used for grouping
-        ('repository:group/test', 0),
+        ('repository:group/test', 4),
         # "-" is often used for "-fork"
-        ('repository:fork-test1', 0),
+        ('repository:fork-test1', 5),
         # using "stop words"
         ('repository:this', 2036),
         ('repository:this/is-it', 2036),
         ('repository:this', 1),
         ('repository:this/is-it', 1),
         ## additional tests to quickly find out regression in the future
         ## (and check case-insensitive search, too)
         # non-ascii character "." and "-"
         ('repository:TESTIES1.2.3', 4),
         ('repository:test_git_repo', 2),
         # combination with wildcard "*"
         ('repository:GROUP/*', 182),
         ('repository:*/test', 7),
         ('repository:fork-*', 273),
         ('repository:*-Test1', 5),
         #### "username:" filtering
         # "-" is valid character
         ('username:peso-xxx', 0),
         # using "stop words"
         ('username:this-is-it', 2036),
         ## additional tests to quickly find out regression in the future
         ## (and check case-insensitive search, too)
         # non-ascii character "." and "-"
         ('username:ADMIN_xanroot', 6),
         ('username:robert.Zaremba', 3),
         # combination with wildcard "*"
         ('username:THIS-*', 2),
         ('username:*-IT', 2),
     ])
     def test_filter_journal_filter_tokenization(self, filter, hit):
         self.log_user()
         response = self.app.get(url(controller='admin/admin', action='index',
                                     filter=filter))
         if hit != 1:
             response.mustcontain(' %s Entries' % hit)
         else:
             response.mustcontain(' 1 Entry')

0 comments (0 inline, 0 general)