from __future__ import unicode_literals

from django.db.models.loading import get_model
from haystack.backends import BaseEngine
from haystack.backends.whoosh_backend import WhooshSearchBackend, WhooshSearchQuery
from haystack.constants import ID, DJANGO_CT, DJANGO_ID
from haystack.exceptions import MissingDependency, SearchBackendError
from haystack.models import SearchResult

try:
    import whoosh
except ImportError:
    raise MissingDependency("The 'whoosh' backend requires the installation of 'Whoosh'. Please refer to the documentation.")

from whoosh.fields import Schema, IDLIST, TEXT, KEYWORD, NUMERIC, BOOLEAN, DATETIME, NGRAM, NGRAMWORDS
from whoosh.fields import ID as WHOOSH_ID
from whoosh.analysis.analyzers import LanguageAnalyzer

if not hasattr(whoosh, '__version__') or whoosh.__version__ < (2, 5, 0):
    raise MissingDependency("The 'whoosh' backend requires version 2.5.0 or greater.")


class WhooshSearchBackendRussian(WhooshSearchBackend):

    def build_schema(self, fields):
        schema_fields = {
            ID: WHOOSH_ID(stored=True, unique=True),
            DJANGO_CT: WHOOSH_ID(stored=True),
            DJANGO_ID: WHOOSH_ID(stored=True),
        }
        # Grab the number of keys that are hard-coded into Haystack.
        # We'll use this to (possibly) fail slightly more gracefully later.
        initial_key_count = len(schema_fields)
        content_field_name = ''

        for field_name, field_class in fields.items():
            if field_class.is_multivalued:
                if field_class.indexed is False:
                    schema_fields[field_class.index_fieldname] = IDLIST(stored=True, field_boost=field_class.boost)
                else:
                    schema_fields[field_class.index_fieldname] = KEYWORD(stored=True, commas=True, scorable=True, field_boost=field_class.boost)
            elif field_class.field_type in ['date', 'datetime']:
                schema_fields[field_class.index_fieldname] = DATETIME(stored=field_class.stored, sortable=True)
            elif field_class.field_type == 'integer':
                schema_fields[field_class.index_fieldname] = NUMERIC(stored=field_class.stored, numtype=int, field_boost=field_class.boost)
            elif field_class.field_type == 'float':
                schema_fields[field_class.index_fieldname] = NUMERIC(stored=field_class.stored, numtype=float, field_boost=field_class.boost)
            elif field_class.field_type == 'boolean':
                # Field boost isn't supported on BOOLEAN as of 1.8.2.
                schema_fields[field_class.index_fieldname] = BOOLEAN(stored=field_class.stored)
            elif field_class.field_type == 'ngram':
                schema_fields[field_class.index_fieldname] = NGRAM(minsize=3, maxsize=15, stored=field_class.stored, field_boost=field_class.boost)
            elif field_class.field_type == 'edge_ngram':
                schema_fields[field_class.index_fieldname] = NGRAMWORDS(minsize=2, maxsize=15, at='start', stored=field_class.stored, field_boost=field_class.boost)
            else:
                schema_fields[field_class.index_fieldname] = TEXT(stored=True, analyzer=LanguageAnalyzer('ru'), field_boost=field_class.boost, sortable=True)

            if field_class.document is True:
                content_field_name = field_class.index_fieldname
                schema_fields[field_class.index_fieldname].spelling = True

        # Fail more gracefully than relying on the backend to die if no fields
        # are found.
        if len(schema_fields) <= initial_key_count:
            raise SearchBackendError("No fields were found in any search_indexes. Please correct this before attempting to search.")

        return (content_field_name, Schema(**schema_fields))

    def _process_results(self, raw_page, highlight=False, query_string='', spelling_query=None, result_class=None):
        from haystack import connections
        results = []

        # It's important to grab the hits first before slicing. Otherwise, this
        # can cause pagination failures.
        hits = len(raw_page)

        if result_class is None:
            result_class = SearchResult

        facets = {}
        spelling_suggestion = None
        unified_index = connections[self.connection_alias].get_unified_index()
        indexed_models = unified_index.get_indexed_models()

        for doc_offset, raw_result in enumerate(raw_page):
            score = raw_page.score(doc_offset) or 0
            app_label, model_name = raw_result[DJANGO_CT].split('.')
            additional_fields = {}
            model = get_model(app_label, model_name)

            if model and model in indexed_models:
                for key, value in raw_result.items():
                    index = unified_index.get_index(model)
                    string_key = str(key)

                    if string_key in index.fields and hasattr(index.fields[string_key], 'convert'):
                        # Special-cased due to the nature of KEYWORD fields.
                        if index.fields[string_key].is_multivalued:
                            if value is None or len(value) is 0:
                                additional_fields[string_key] = []
                            else:
                                additional_fields[string_key] = value.split(',')
                        else:
                            additional_fields[string_key] = index.fields[string_key].convert(value)
                    else:
                        additional_fields[string_key] = self._to_python(value)

                del(additional_fields[DJANGO_CT])
                del(additional_fields[DJANGO_ID])

                if highlight:
                    from whoosh import analysis
                    from whoosh.highlight import highlight, ContextFragmenter, UppercaseFormatter
                    sa = analysis.LanguageAnalyzer('ru')
                    terms = [term.replace('*', '') for term in query_string.split()]

                    additional_fields['highlighted'] = {
                        self.content_field_name: [highlight(additional_fields.get(self.content_field_name), terms, sa, ContextFragmenter(terms), UppercaseFormatter())],
                    }

                result = result_class(app_label, model_name, raw_result[DJANGO_ID], score, **additional_fields)
                results.append(result)
            else:
                hits -= 1

        if self.include_spelling:
            if spelling_query:
                spelling_suggestion = self.create_spelling_suggestion(spelling_query)
            else:
                spelling_suggestion = self.create_spelling_suggestion(query_string)

        return {
            'results': results,
            'hits': hits,
            'facets': facets,
            'spelling_suggestion': spelling_suggestion,
        }


class WhooshEngine(BaseEngine):
    backend = WhooshSearchBackendRussian
    query = WhooshSearchQuery