# HG changeset patch
# User FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
# Date 1485105458 -32400
# Node ID caef0be399489fd71c9e2d744fe928a352f6b9ab
# Parent  2ff913970025ef152b436cd791290eb078de5681
search: make "repository:" condition work as expected

Before this revision, "repository:foo" condition at searching for
"File contents" or "File names" shows files in repositories below.

  - foo
  - foo/bar
  - foo-bar
  - and so on ...

Whoosh library, which is used to parse text for indexing and seaching,
does:

  - treat almost all non-alphanumeric characters as delimiter both at
    indexing search items and at parsing search condition
  - make each fields for a search item be indexed by multiple values

For example, files in "foo/bar" repository are indexed by "foo" and
"bar" in "repository" field. This tokenization make "repository:foo"
search condition match against files in "foo/bar" repository, too.

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

This issue can't be resolved by using ID instead of TEXT for
"repository" of SCHEMA, like as previous revisions for JOURNAL_SCHEMA,
because:

  - highlight-ing file content requires SCHEMA to support "positions"
    feature, but using ID instead of TEXT disables it
  - using ID violates current case-insensitive search policy, because
    it preserves case of text

To make "repository:" condition work as expected, this revision
explicitly specifies "analyzer", which does:

  - avoid tokenization
  - match case-insensitively
  - avoid removing "stop words" from text

This revision requires full re-building index tables, because indexing
schema is changed.

BTW, "repository:" condition at searching for "Commit messages" uses
CHGSETS_SCHEMA instead of SCHEMA. The former uses ID for "repository",
and it does:

  - avoid issues by tokenization and removing "stop words"

  - disable "positions" feature of CHGSETS_SCHEMA

    But highlight-ing file content isn't needed at searching for
    "Commit messages". Therefore, this can be ignored.

  - preserve case of text

    This violates current case-insensitive search policy, This issue
    will be fixed by subsequent revision, because fixing it isn't so
    simple.

diff -r 2ff913970025 -r caef0be39948 kallithea/lib/indexers/__init__.py
--- a/kallithea/lib/indexers/__init__.py	Mon Jan 23 02:17:38 2017 +0900
+++ b/kallithea/lib/indexers/__init__.py	Mon Jan 23 02:17:38 2017 +0900
@@ -33,7 +33,7 @@
 # Add location of top level folder to sys.path
 sys.path.append(dirname(dirname(dirname(os.path.realpath(__file__)))))
 
-from whoosh.analysis import RegexTokenizer, LowercaseFilter
+from whoosh.analysis import RegexTokenizer, LowercaseFilter, IDTokenizer
 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
@@ -44,11 +44,20 @@
 # CUSTOM ANALYZER wordsplit + lowercase filter
 ANALYZER = RegexTokenizer(expression=r"\w+") | LowercaseFilter()
 
+# CUSTOM ANALYZER raw-string + lowercase filter
+#
+# This is useful to:
+# - avoid tokenization
+# - avoid removing "stop words" from text
+# - search case-insensitively
+#
+ICASEIDANALYZER = IDTokenizer() | LowercaseFilter()
+
 #INDEX SCHEMA DEFINITION
 SCHEMA = Schema(
     fileid=ID(unique=True),
     owner=TEXT(),
-    repository=TEXT(stored=True),
+    repository=TEXT(stored=True, analyzer=ICASEIDANALYZER),
     path=TEXT(stored=True),
     content=FieldType(format=Characters(), analyzer=ANALYZER,
                       scorable=True, stored=True),
diff -r 2ff913970025 -r caef0be39948 kallithea/tests/functional/test_search_indexing.py
--- a/kallithea/tests/functional/test_search_indexing.py	Mon Jan 23 02:17:38 2017 +0900
+++ b/kallithea/tests/functional/test_search_indexing.py	Mon Jan 23 02:17:38 2017 +0900
@@ -113,9 +113,9 @@
         (u'group/*'),
     ])
     @parametrize('searchtype,query,hit', [
-        #('content', 'this_should_be_unique_content', 1),
+        ('content', 'this_should_be_unique_content', 1),
         ('commit', 'this_should_be_unique_commit_log', 1),
-        #('path', 'this_should_be_unique_filename.txt', 1),
+        ('path', 'this_should_be_unique_filename.txt', 1),
     ])
     def test_repository_tokenization(self, reponame, searchtype, query, hit):
         self.log_user()