SCHEMA, IDX_NAME

import logging

import logging.config

logging.config.fileConfig(jn(project_path, 'development.ini'))

log = logging.getLogger('whooshIndexer')

def scan_paths(root_location):

    return HgModel.repo_scan('/', root_location, None, True)

class WhooshIndexingDaemon(object):

    """Deamon for atomic jobs"""

    def __init__(self, indexname='HG_INDEX', repo_location=None):

        self.indexname = indexname

        self.repo_location = repo_location

    def get_paths(self, root_dir):

        """recursive walk in root dir and return a set of all path in that dir

        excluding files in .hg dir"""

        index_paths_ = set()

        for path, dirs, files in os.walk(root_dir):

            if path.find('.hg') == -1:

                for f in files:

                    index_paths_.add(jn(path, f))

        return index_paths_

    def add_doc(self, writer, path, repo):

        """Adding doc to writer"""

        ext = unicode(path.split('/')[-1].split('.')[-1].lower())

        #we just index the content of choosen files

        if ext in INDEX_EXTENSIONS:

            log.debug('    >> %s [WITH CONTENT]' % path)

            fobj = open(path, 'rb')

            content = fobj.read()

            fobj.close()

            try:

                u_content = unicode(content)

            except UnicodeDecodeError:

                #incase we have a decode error just represent as byte string

                u_content = unicode(str(content).encode('string_escape'))

        else:

            log.debug('    >> %s' % path)

            #just index file name without it's content

            u_content = u''

        writer.add_document(owner=unicode(repo.contact),

                            repository=u"%s" % repo.name,

                            path=u"%s" % path,

                            content=u_content,

                            modtime=os.path.getmtime(path),

                            extension=ext) 

    def build_index(self):

        if os.path.exists(IDX_LOCATION):

            log.debug('removing previos index')

            rmtree(IDX_LOCATION)

        if not os.path.exists(IDX_LOCATION):

            os.mkdir(IDX_LOCATION)

        idx = create_in(IDX_LOCATION, SCHEMA, indexname=IDX_NAME)

        writer = idx.writer()

        for cnt, repo in enumerate(scan_paths(self.repo_location).values()):

            log.debug('building index @ %s' % repo.path)

            for idx_path in self.get_paths(repo.path):

                self.add_doc(writer, idx_path, repo)

        writer.commit(merge=True)

        log.debug('>>> FINISHED BUILDING INDEX <<<')

    def update_index(self):

        log.debug('STARTING INCREMENTAL INDEXING UPDATE')

        idx = open_dir(IDX_LOCATION, indexname=self.indexname)

        # The set of all paths in the index

        indexed_paths = set()

        # The set of all paths we need to re-index

        to_index = set()

        reader = idx.reader()

        writer = idx.writer()

        # Loop over the stored fields in the index

        for fields in reader.all_stored_fields():

            indexed_path = fields['path']

            indexed_paths.add(indexed_path)

            if not os.path.exists(indexed_path):

                # This file was deleted since it was indexed

                log.debug('removing from index %s' % indexed_path)

                writer.delete_by_term('path', indexed_path)

            else:

                # Check if this file was changed since it

                # was indexed

                indexed_time = fields['modtime']