import click

from app.utils import click_utils
from app.utils.logger_utils import Logger
from app.models.citations import Paper

log = Logger.getLogger()

fp_in_default = '../site/datasets/verified/'
fp_out_default = '../site/datasets/verified/'

@click.command()
@click.option('-i', '--input', 'opt_fp_in', default=fp_in_default,
  help='Input citation data file or folder')
@click.option('-o', '--output', 'opt_dir_out', default=fp_out_default,
  help='Output directory')
@click.pass_context
def cli(ctx, opt_fp_in, opt_dir_out):
  """Convert JSON to CSV"""
  
  import sys
  from glob import glob
  from os.path import join
  from pathlib import Path

  import json
  import pandas as pd
  from tqdm import tqdm
  
  from app.utils import file_utils, im_utils
  
  log = Logger.getLogger()
  log.info('Convert JSON to CSV')

  # load
  if Path(opt_fp_in).is_dir():
    fps_in = glob(join(opt_fp_in, '*.json'))
  else:
    fps_in = [opt_fp_in]

  log.info(f'Converting {len(fps_in)} JSON files to CSV')

  for fp_in in fps_in:
    
    log.info(f'Processing: {Path(fp_in).name}')

    with open(fp_in, 'r') as fp:
      json_data = json.load(fp)

    # parse
    papers = []
    dataset_key = json_data['paper']['key']
    dataset_name = json_data['paper']['name']
    try:
      papers_main = get_orig_paper(json_data)
      papers += papers_main
      papers_citations = get_citations(dataset_key, dataset_name, json_data)
      papers += papers_citations
      papers = [p.to_dict() for p in papers]
    except Exception as e:
      log.error(f'{e} on {Path(fp_in).name}')
      continue
    
    # save
    if not opt_dir_out:
      # save to same directory replacing ext
      fp_out = fp_in.replace('.json','.csv')
    else:
      fp_out = join(opt_dir_out, f'{Path(fp_in).stem}.csv')

    df_papers = pd.DataFrame.from_dict(papers)
    df_papers.index.name = 'id'
    df_papers.to_csv(fp_out)
    log.info(f'Wrote {len(df_papers):,} lines to {fp_out}')

  

# ----------------------------------------------------------------------------
# Helpers
# ----------------------------------------------------------------------------
def get_citations(dataset_key, dataset_name, json_data):
  papers = []
  d_type = 'citation'
  for p in json_data['citations']:
    year = 0 if p.get('year', 0) == '' else p.get('year', 0)
    addresses = p.get('addresses', '')
    if addresses:
      for a in addresses:
        pdf_url = '' if not p.get('pdf') else p.get('pdf')[0]
        paper = Paper(dataset_key, dataset_name, p['id'], p['title'], d_type,
                  year, pdf_url,
                  a['name'], a['type'], a['lat'], a['lng'], a['country'])  
        papers.append(paper)
    else:
      pdf_url = '' if not p.get('pdf') else p.get('pdf')[0]
      paper = Paper(p['key'], p['name'], d['id'], p['title'], 'main', year, pdf_url)
      papers.append(paper)
  return papers

def get_orig_paper(json_data):
  papers = []
  d = json_data
  p = d['paper']
  d_type = 'main'
  year = 0 if p.get('year', 0) == '' else p.get('year', 0)
  addresses = p.get('address','')
  if addresses:
    for a in addresses:
      if type(a) == str or a is None:
        continue
      pdf_url = '' if not p.get('pdf') else p.get('pdf')[0]
      paper = Paper(p.get('key'), p.get('name'), p.get('paper_id'), p.get('title'), d_type, year,
                  pdf_url,
                  a.get('name'), a.get('type'), a.get('lat'), a.get('lng'), a.get('country'))
      papers.append(paper)
  else:
    pdf_url = '' if not p.get('pdf') else p.get('pdf')[0]
    paper = Paper(p.get('key'), p.get('name'), p.get('paper_id'), p.get('title'), d_type, year, pdf_url)
    papers.append(paper)
  return papers