~~~~~~~~~~~~~~~~~~~~~~

Whoosh indexing module for Kallithea

This file was forked by the Kallithea project in July 2014.

Original author and date, and relevant copyright and licensing information is below:

:created_on: Aug 17, 2010

:author: marcink

:copyright: (c) 2013 RhodeCode GmbH, and others.

:license: GPLv3, see LICENSE.md for more details.

"""

import os

import sys

import logging

from os.path import dirname

# 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, 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

from kallithea.lib.utils2 import LazyProperty

log = logging.getLogger(__name__)

# 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()

# CUSTOM ANALYZER raw-string

#

# This is useful to:

# - avoid tokenization

# - avoid removing "stop words" from text

#

IDANALYZER = IDTokenizer()

#INDEX SCHEMA DEFINITION

SCHEMA = Schema(

    fileid=ID(unique=True),

    owner=TEXT(),

    # this field preserves case of repository name for exact matching

    repository_rawname=TEXT(analyzer=IDANALYZER),

    repository=TEXT(stored=True, analyzer=ICASEIDANALYZER),

    content=FieldType(format=Characters(), analyzer=ANALYZER,

                      scorable=True, stored=True),

    modtime=STORED(),

)

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(),

    # this field preserves case of repository name for exact matching

    # and unique-ness in index table

    repository_rawname=ID(unique=True),

    repository=ID(stored=True, analyzer=ICASEIDANALYZER),

    author=TEXT(stored=True),

    message=FieldType(format=Characters(), analyzer=ANALYZER,

                      scorable=True, stored=True),

    parents=TEXT(),

)

CHGSET_IDX_NAME = 'CHGSET_INDEX'

# used only to generate queries in journal

JOURNAL_SCHEMA = Schema(

    username=ID(),

    date=DATETIME(),

    action=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.

        (u'this-is-it'),

        (u'*-fork'),

        (u'group/*'),

    ])

    @parametrize('searchtype,query,hit', [

        ('content', 'this_should_be_unique_content', 1),

        ('commit', 'this_should_be_unique_commit_log', 1),

        ('path', 'this_should_be_unique_filename.txt', 1),

    ])

    def test_repository_tokenization(self, reponame, searchtype, query, hit):

        self.log_user()

        q = 'repository:%s %s' % (reponame, query)

        response = self.app.get(url(controller='search', action='index'),

                                {'q': q, 'type': searchtype})

        response.mustcontain('>%d results' % hit)

    @parametrize('searchtype,query,hit', [

        ('content', 'this_should_be_unique_content', 1),

        ('commit', 'this_should_be_unique_commit_log', 1),

        ('path', 'this_should_be_unique_filename.txt', 1),

    ])

    def test_repository_case_sensitivity(self, searchtype, query, hit):

        self.log_user()

        lname = u'indexing_test-foo'

        uname = u'indexing_test-FOO'

        # (1) "repository:REPONAME" condition should match against

        # repositories case-insensitively

        q = 'repository:%s %s' % (lname, query)

        response = self.app.get(url(controller='search', action='index'),

                                {'q': q, 'type': searchtype})

        response.mustcontain('>%d results' % (hit * 2))

        # (2) on the other hand, searching under the specific

        # repository should return results only for that repository,

        # even if specified name matches against another repository

        # case-insensitively.

        response = self.app.get(url(controller='search', action='index',

                                    repo_name=uname),

                                {'q': query, 'type': searchtype})

        response.mustcontain('>%d results' % hit)

        # confirm that there is no matching against lower name repository

        assert uname in response

    @parametrize('searchtype,query,hit', [

        # this condition matches against files below, because

        # "path:" condition is also applied on "repository path".

        # - "this/is/it" in "stopword_test" repo

        # - "this_should_be_unique_filename.txt" in "this-is-it" repo

    ])

    def test_filename_stopword(self, searchtype, query, hit):

        response = self.app.get(url(controller='search', action='index'),

                                {'q': query, 'type': searchtype})

        response.mustcontain('>%d results' % hit)

    @parametrize('searchtype,query,hit', [

        # matching against both 2 files

        ('content', 'owner:"this is it"', 0),

        ('content', 'owner:this-is-it', 0),

        ('path', 'owner:"this is it"', 0),

        ('path', 'owner:this-is-it', 0),

        # matching against both 2 revisions

        ('commit', 'owner:"this is it"', 0),

        ('commit', 'owner:"this-is-it"', 0),

        # matching against only 1 revision

        ('commit', 'author:"this is it"', 0),

        ('commit', 'author:"this-is-it"', 0),

    ])

    def test_mailaddr_stopword(self, searchtype, query, hit):

        response = self.app.get(url(controller='search', action='index'),

                                {'q': query, 'type': searchtype})

        response.mustcontain('>%d results' % hit)