import click

from app.settings import types
from app.models.dataset import Dataset
from app.utils import click_utils
from app.settings import app_cfg as cfg
from app.utils.logger_utils import Logger

log = Logger.getLogger()

@click.command()
@click.option('-i', '--input', 'opt_fp_in', required=True,
  help='Face image file to lookup')
@click.option('--data_store', 'opt_data_store',
  type=cfg.DataStoreVar,
  default=click_utils.get_default(types.DataStore.HDD),
  show_default=True,
  help=click_utils.show_help(types.DataStore))
@click.option('--dataset', 'opt_dataset',
  type=cfg.DatasetVar,
  required=True,
  show_default=True,
  help=click_utils.show_help(types.Dataset))
@click.option('--results', 'opt_results', default=5, 
  help='Number of match results to display')
@click.option('--gpu', 'opt_gpu', default=0, 
  help='GPU index (use -1 for CPU')
@click.pass_context
def cli(ctx, opt_fp_in, opt_data_store, opt_dataset, opt_results, opt_gpu):
  """Display image info"""
  
  import sys
  from glob import glob
  from os.path import join
  from pathlib import Path
  import time

  import pandas as pd
  import cv2 as cv
  from tqdm import tqdm
  import imutils
  from PIL import Image, ImageOps

  from app.utils import file_utils, im_utils, display_utils, draw_utils
  from app.models.data_store import DataStore
  from app.processors import face_detector
  from app.processors import face_extractor

  log = Logger.getLogger()

  # init dataset
  dataset = Dataset(opt_data_store, opt_dataset)
  dataset.load_metadata(types.Metadata.FILE_RECORD)
  dataset.load_metadata(types.Metadata.FACE_VECTOR)
  dataset.load_metadata(types.Metadata.FACE_ROI)
  dataset.load_metadata(types.Metadata.IDENTITY)

  # init face detection
  detector = face_detector.DetectorCVDNN()

  # init face extractor
  extractor = face_extractor.ExtractorVGG()
  
  # load query image
  im_query = cv.imread(opt_fp_in)

  # get detection as BBox object
  bboxes = detector.detect(im_query, largest=True)
  bbox_norm = bboxes[0]
  dim = im_query.shape[:2][::-1]
  bbox_dim = bbox_norm.to_dim(dim)  # convert back to real dimensions

  if not bbox_norm:
    log.error('No face detected. Exiting')
    return
  
  # extract the face vectors
  vec_query = extractor.extract(im_query, bbox_norm)
  log.debug(f'len query: {len(vec_query)}')

  # find matches
  image_records = dataset.find_matches(vec_query, n_results=opt_results)

  # summary
  im_query = draw_utils.draw_bbox(im_query, bbox_norm, stroke_weight=4)
  ims_match = [im_query]

  opt_size = (256,256)

  for image_record in image_records:
    image_record.summarize()
    log.info(f'{image_record.filepath}')
    im_match = cv.imread(image_record.filepath)
    dim_match = im_match.shape[:2][::-1]
    bbox_match = image_record.bbox
    score = image_record.score
    if score < .5:
      clr = (0,255,0)
    elif score < .6:
      clr = (0,255,125)
    elif score < .65:
      clr = (0,125,125)
    elif score < .7:
      clr = (0,125,255)
    else:
      clr = (0,0,255)
      
    im_match = draw_utils.draw_bbox(im_match, bbox_match, stroke_weight=4, color=clr )
    bbox_match_dim = bbox_match.to_dim(dim_match)

    im_pil = im_utils.ensure_pil(im_match)
    center = (bbox_match_dim.cx, bbox_match_dim.cy)
    im_pil = ImageOps.fit(im_pil, opt_size, centering=center)
    im_np = im_utils.ensure_np(im_pil)
    if image_record.identity is not None:
      log.debug(f'identity: {image_record.identity.name_display}')
    else:
      log.debug('no identity info')
    log.debug(f'score: {image_record.score}')

    ims_match.append(im_np)
  # make montages of most similar faces
  montages = imutils.build_montages(ims_match, (256, 256), (3,2))

  # display 
  for i, montage in enumerate(montages):
    cv.imshow(f'{opt_dataset.name.upper()}: page {i}', montage)
    fp_out = join(Path(opt_fp_in).parent, f'{Path(opt_fp_in).stem}_{i}.png')
    cv.imwrite(fp_out, montage)
  
  display_utils.handle_keyboard()