fixes issue #524

- fixed search by filename
- added missing test for this search

rhodecode/lib/indexers/__init__.py

@@ -1,265 +1,271 b''
 # -*- coding: utf-8 -*-
 """
     rhodecode.lib.indexers.__init__
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
     Whoosh indexing module for RhodeCode
 
     :created_on: Aug 17, 2010
     :author: marcink
     :copyright: (C) 2010-2012 Marcin Kuzminski <[e-mail]>
     :license: GPLv3, see COPYING for more details.
 """
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
 # the Free Software Foundation, either version 3 of the License, or
 # (at your option) any later version.
 #
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 import os
 import sys
 import traceback
 import logging
 from os.path import dirname as dn, join as jn
 
 #to get the rhodecode import
 sys.path.append(dn(dn(dn(os.path.realpath(__file__)))))
 
 from string import strip
 from shutil import rmtree
 
 from whoosh.analysis import RegexTokenizer, LowercaseFilter, StopFilter
 from whoosh.fields import TEXT, ID, STORED, NUMERIC, BOOLEAN, Schema, FieldType
 from whoosh.index import create_in, open_dir
 from whoosh.formats import Characters
 from whoosh.highlight import highlight, HtmlFormatter, ContextFragmenter
 
 from webhelpers.html.builder import escape, literal
 from sqlalchemy import engine_from_config
 
 from rhodecode.model import init_model
 from rhodecode.model.scm import ScmModel
 from rhodecode.model.repo import RepoModel
 from rhodecode.config.environment import load_environment
 from rhodecode.lib.utils2 import LazyProperty
 from rhodecode.lib.utils import BasePasterCommand, Command, add_cache,\
     load_rcextensions
 
 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'
 
+
 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
         load_rcextensions(config['here'])
         #======================================================================
         # WHOOSH DAEMON
         #======================================================================
         from rhodecode.lib.pidlock import LockHeld, DaemonLock
         from rhodecode.lib.indexers.daemon import WhooshIndexingDaemon
         try:
             l = DaemonLock(file_=jn(dn(dn(index_location)), 'make_index.lock'))
             WhooshIndexingDaemon(index_location=index_location,
                                  repo_location=repo_location,
                                  repo_list=repo_list,
                                  repo_update_list=repo_update_list)\
                 .run(full_index=self.options.full_index)
             l.release()
         except LockHeld:
             sys.exit(1)
 
     def update_parser(self):
         self.parser.add_option('--repo-location',
                           action='store',
                           dest='repo_location',
                           help="Specifies repositories location to index OPTIONAL",
                           )
         self.parser.add_option('--index-only',
                           action='store',
                           dest='repo_list',
                           help="Specifies a comma separated list of repositores "
                                 "to build index on. If not given all repositories "
                                 "are scanned for indexing. OPTIONAL",
                           )
         self.parser.add_option('--update-only',
                           action='store',
                           dest='repo_update_list',
                           help="Specifies a comma separated list of repositores "
                                 "to re-build index on. OPTIONAL",
                           )
         self.parser.add_option('-f',
                           action='store_true',
                           dest='full_index',
                           help="Specifies that index should be made full i.e"
                                 " destroy old and build from scratch",
                           default=False)
 
 
 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
 
         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':
+            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)
+            res.update({'f_path': f_path})
         elif self.search_type == 'message':
             res.update({'message_hl': self.highlight(res['message'])})
 
         log.debug('result: %s' % res)
 
         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
                 end = span.endchar or 0
                 start_offseted = max(0, start - self.fragment_size)
                 end_offseted = end + self.fragment_size
 
                 if start_offseted < memory[-1][1]:
                     start_offseted = memory[-1][1]
                 memory.append((start_offseted, end_offseted,))
                 yield (start_offseted, end_offseted,)
 
     def highlight(self, content, top=5):
         if self.search_type not in ['content', 'message']:
             return ''
         hl = highlight(
             text=content,
             terms=self.highlight_items,
             analyzer=ANALYZER,
             fragmenter=FRAGMENTER,
             formatter=FORMATTER,
             top=top
         )
         return hl

rhodecode/tests/functional/test_search.py

@@ -1,92 +1,99 b''
 import os
 from rhodecode.tests import *
 from nose.plugins.skip import SkipTest
 
 
 class TestSearchController(TestController):
 
     def test_index(self):
         self.log_user()
         response = self.app.get(url(controller='search', action='index'))
 
         self.assertTrue('class="small" id="q" name="q" type="text"' in
                         response.body)
         # Test response...
 
     def test_empty_search(self):
         if os.path.isdir(self.index_location):
             raise SkipTest('skipped due to existing index')
         else:
             self.log_user()
             response = self.app.get(url(controller='search', action='index'),
                                     {'q': HG_REPO})
             self.assertTrue('There is no index to search in. '
                             'Please run whoosh indexer' in response.body)
 
     def test_normal_search(self):
         self.log_user()
         response = self.app.get(url(controller='search', action='index'),
                                 {'q': 'def repo'})
         response.mustcontain('39 results')
 
     def test_repo_search(self):
         self.log_user()
         response = self.app.get(url(controller='search', action='index'),
                                 {'q': 'repository:%s def test' % HG_REPO})
 
         response.mustcontain('4 results')
 
     def test_search_last(self):
         self.log_user()
         response = self.app.get(url(controller='search', action='index'),
                                 {'q': 'last:t', 'type': 'commit'})
 
         response.mustcontain('2 results')
 
     def test_search_commit_message(self):
         self.log_user()
         response = self.app.get(url(controller='search', action='index'),
                     {'q': 'bother to ask where to fetch repo during tests',
                      'type': 'commit'})
 
         response.mustcontain('2 results')
         response.mustcontain('a00c1b6f5d7a6ae678fd553a8b81d92367f7ecf1')
         response.mustcontain('c6eb379775c578a95dad8ddab53f963b80894850')
 
     def test_search_commit_message_hg_repo(self):
         self.log_user()
         response = self.app.get(url(controller='search', action='index',
                                     search_repo=HG_REPO),
                     {'q': 'bother to ask where to fetch repo during tests',
                      'type': 'commit'})
 
         response.mustcontain('1 results')
         response.mustcontain('a00c1b6f5d7a6ae678fd553a8b81d92367f7ecf1')
 
     def test_search_commit_changed_file(self):
         self.log_user()
         response = self.app.get(url(controller='search', action='index'),
                                 {'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',
                                  'type': 'commit'})
 
         response.mustcontain('2 results')
         #HG
         response.mustcontain('3803844fdbd3b711175fc3da9bdacfcd6d29a6fb')
         #GIT
         response.mustcontain('ff7ca51e58c505fec0dd2491de52c622bb7a806b')
 
     def test_search_author(self):
         self.log_user()
         response = self.app.get(url(controller='search', action='index'),
                     {'q': 'author:[e-mail] raw_id:b986218ba1c9b0d6a259fac9b050b1724ed8e545',
                      'type': 'commit'})
 
         response.mustcontain('1 results')
+
+    def test_search_file_name(self):
+        self.log_user()
+        response = self.app.get(url(controller='search', action='index'),
+                    {'q': 'README.rst', 'type': 'path'})
+
+        response.mustcontain('2 results')
  No newline at end of file