kallithea Changeset - a0ef98f2520b

Changeset - a0ef98f2520b

Parent rev.

Child rev.

[Not reviewed]

beta

0 2 0

Marcin Kuzminski - 13 years ago 2012-06-05 00:27:59
marcin@python-works.com

#453 added ID field in whoosh SCHEMA that solves the issue of reindexing modified files

2 files changed with 10 insertions and 3 deletions:

rhodecode/lib/indexers/__init__.py

rhodecode/lib/indexers/daemon.py

0 comments (0 inline, 0 general)

rhodecode/lib/indexers/__init__.py

➞

Show inline comments

@@ @@ -54,12 +54,13 @@ from rhodecode.lib.utils import BasePast @@
 # 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(),

rhodecode/lib/indexers/daemon.py

➞

Show inline comments

@@ @@ -143,16 +143,18 @@ class WhooshIndexingDaemon(object): @@
         else:
             log.debug('    >> %s' % path)
             # just index file name without it's content
             u_content = u''
             indexed += 1
         p = safe_unicode(path)
         writer.add_document(
             fileid=p,
             owner=unicode(repo.contact),
             repository=safe_unicode(repo_name),
-            path=safe_unicode(path),
+            path=p,
             content=u_content,
             modtime=self.get_node_mtime(node),
             extension=node.extension
+        )
         return indexed, indexed_w_content
@@ @@ -211,14 +213,17 @@ class WhooshIndexingDaemon(object): @@
                 # Check if this file was changed since it was indexed
                 indexed_time = fields['modtime']
                 mtime = self.get_node_mtime(node)
                 if mtime > indexed_time:
                     # The file has changed, delete it and add it to the list of
                     # files to reindex
                     log.debug('adding to reindex list %s' % indexed_path)
                     writer.delete_by_term('path', indexed_path)
                     log.debug('adding to reindex list %s mtime: %s vs %s' % (
                                     indexed_path, mtime, indexed_time)
+                    )
                     writer.delete_by_term('fileid', indexed_path)
                     to_index.add(indexed_path)
             except (ChangesetError, NodeDoesNotExistError):
                 # This file was deleted since it was indexed
                 log.debug('removing from index %s' % indexed_path)
                 writer.delete_by_term('path', indexed_path)
@@ @@ -227,12 +232,13 @@ class WhooshIndexingDaemon(object): @@
         # documents to be indexed
         ri_cnt = riwc_cnt = 0
         for repo_name, repo in self.repo_paths.items():
             for path in self.get_paths(repo):
                 path = safe_unicode(path)
                 if path in to_index or path not in indexed_paths:
                     # This is either a file that's changed, or a new file
                     # that wasn't indexed before. So index it!
                     i, iwc = self.add_doc(writer, path, repo, repo_name)
                     log.debug('re indexing %s' % path)
                     ri_cnt += i
                     riwc_cnt += iwc

0 comments (0 inline, 0 general)