#!/usr/bin/env python
#encoding:utf-8
from deepdive import *
import random
from collections import namedtuple
from commonutil import *


Label = namedtuple('Label', 'entity_id, label, type')

@tsv_extractor
@returns(lambda
        entity_id   = "text",
        label   = "int",
        rule_id = "text",
    :[])
# heuristic rules for finding positive/negative examples of transaction relationship mentions
def supervise(
        entity_id="text", entity_begin="int", entity_end="int",
        doc_id="text", sentence_index="int", sentence_text="text",
        tokens="text[]",  pos_tags="text[]", ner_tags="text[]",
    ):

    # Constants
    label = Label(entity_id=entity_id,label=None,type=None)
    Bidding = frozenset(["开标"])
    TIME = frozenset(["时间"])
    SpecificTime = frozenset(["年","月"])
    MAX_DIST = 10
    TYPE_MENTION = frozenset(["org","company"])

    # Common data objects
    if entity_begin>MAX_DIST:
        begin = entity_begin-MAX_DIST
    else:
        begin = 0
    if len(tokens)-entity_end>MAX_DIST:
        end = entity_end+MAX_DIST
    else:
        end = -1
    front_tokens = tokens[begin:entity_begin]
    end_tokens = tokens[entity_end:end]
    front_ner = ner_tags[begin:entity_begin]
    end_ner = ner_tags[end:entity_end]
    
    log(sentence_text)
    

    # Rule: Candidates that are too far apart
    '''
    if len(intermediate_lemmas) > MAX_DIST:
        yield transaction._replace(label=-1, type='neg:far_apart')

    # Rule: Candidates that have a third company in between
    if 'company' in intermediate_ner_tags:
        yield transaction._replace(label=-1, type='neg:third_company_between')

    # Rule: Sentences that contain wife/husband in between
    #         (<P1>)([ A-Za-z]+)(wife|husband)([ A-Za-z]+)(<P2>)
    #if len(TRANSLATION.intersection(intermediate_lemmas)) > 0 and len(STOCK.intersection(intermediate_lemmas)) > 0:
    #    yield transaction._replace(label=1, type='A购买股权B')
    '''
    if len(TIME.intersection(front_tokens))>0:
        if len(Bidding.intersection(front_tokens))>0:
            if find_index(list(SpecificTime),"".join(tokens[entity_begin:entity_end+1]))>=0:
                yield label._replace(label=1,type="开标:time")
            else:
                yield label._replace(label=-1,type="pos:非具体时间")
        else:
            yield label._replace(label=-1,type="pos:no match 开标")
    else:
        yield label._replace(label=-1,type="pos:no match")