"""Read optional reference MusicXML literally, without repairing it or composing."""
from __future__ import annotations
import argparse
import hashlib
import json
from pathlib import Path
from fractions import Fraction as F
import xml.etree.ElementTree as ET


def read(path, role, form_start=None):
  raw=Path(path).read_bytes();tree=ET.fromstring(raw)
  result={'path':str(Path(path).resolve()),'sha256':hashlib.sha256(raw).hexdigest(),'validation_role':role,
    'pitch_convention':'encoded MusicXML; no inferred guitar octave','part_names':[n.text for n in tree.findall('./part-list/score-part/part-name')],
    'measures':[],'notes':[],'harmonies':[],'annotations':[],'discrepancies':[]}
  divisions=F(1);absolute=F();nominal=F(4);pending={};active=None
  for index,m in enumerate(tree.findall('./part/measure')):
    cursor=F();extent=F();last_start=F();last_duration=F()
    if (value:=m.findtext('attributes/divisions')) is not None:divisions=F(value)
    meter=m.find('attributes/time')
    if meter is not None and meter.findtext('beats'):
      nominal=sum((F(v) for v in meter.findtext('beats').split('+')),F())*4/F(meter.findtext('beat-type'))
    for item in m:
      offset=F(item.findtext('offset','0'))/divisions
      if item.tag=='backup':cursor-=F(item.findtext('duration'))/divisions
      elif item.tag=='forward':cursor+=F(item.findtext('duration'))/divisions;extent=max(extent,cursor)
      elif item.tag=='harmony':
        active={'time':str(absolute+cursor+offset),'measure':index+1,'offset':str(cursor+offset),
          'root':item.findtext('root/root-step'),'alter':item.findtext('root/root-alter','0'),
          'kind':item.findtext('kind'),'display':item.find('kind').get('text') if item.find('kind') is not None else None,
          'bass':ET.tostring(item.find('bass'),encoding='unicode') if item.find('bass') is not None else None,
          'degrees':[{'value':d.findtext('degree-value'),'alter':d.findtext('degree-alter'),'type':d.findtext('degree-type')} for d in item.findall('degree')]}
        result['harmonies'].append(active)
      elif item.tag=='direction':
        for words in item.findall('direction-type/words'):
          result['annotations'].append({'time':str(absolute+cursor+offset),'measure':index+1,'text':''.join(words.itertext()),'interpretation':'descriptive; no production permission'})
      elif item.tag=='note':
        duration=F(item.findtext('duration','0'))/divisions
        start=last_start if item.find('chord') is not None else cursor
        end=start+duration;voice=item.findtext('voice','1');p=item.find('pitch')
        encoded={'step':p.findtext('step'),'alter':p.findtext('alter','0'),'octave':int(p.findtext('octave'))} if p is not None else None
        kinds={t.get('type') for t in item.findall('tie')} | {t.get('type') for t in item.findall('notations/tied')}
        event={'start':str(absolute+start),'end':str(absolute+end),'measure':index+1,'offset':str(start),'pitch':encoded,'rest':item.find('rest') is not None,
          'written_type':item.findtext('type'),'dots':len(item.findall('dot')),'voice':voice,'ties':sorted(kinds),
          'time_modification':ET.tostring(item.find('time-modification'),encoding='unicode') if item.find('time-modification') is not None else None,
          'tuplets':[dict(t.attrib) for t in item.findall('notations/tuplet')],'grace':item.find('grace') is not None,'new_attack':'stop' not in kinds and p is not None}
        key=(voice,json.dumps(encoded,sort_keys=True))
        if 'stop' in kinds:
          old=pending.get(key)
          if old is None or result['notes'][old]['end']!=event['start']:
            result['discrepancies'].append({'measure':index+1,'issue':'unmatched/noncontiguous tie; retained literally'})
          else:event['continuation_of']=old
          if 'start' not in kinds:pending.pop(key,None)
        if 'start' in kinds:pending[key]=len(result['notes'])
        result['notes'].append(event)
        if item.find('chord') is None and item.find('grace') is None:cursor=end
        last_start,last_duration=start,duration;extent=max(extent,end,cursor)
    if extent!=nominal and m.get('implicit')!='yes':result['discrepancies'].append({'measure':index+1,'issue':f'encoded span {extent} differs from nominal {nominal}; no padding applied'})
    result['measures'].append({'number':m.get('number'),'start':str(absolute),'duration':str(extent),'implicit':m.get('implicit'),'initial_harmony_known':any(F(h['time'])<=absolute for h in result['harmonies'])})
    absolute+=extent
  if pending:result['discrepancies'].append({'issue':'unterminated ties retained'})
  # Do not run the strict score importer over these references: annotations,
  # unusual timing and high encoded pitches are evidence, not repair requests.
  from generator import harmony, model, fretboard
  def semantic(h):
    return {'root':{'letter':h['root'].lower(),'alter':model.rational(F(h['alter']))},'kind':h['kind'],
      'degrees':[{'value':int(d['value']),'alter':model.rational(F(d['alter'])),'type':d['type']} for d in h['degrees']]}
  for event in result['notes']:
    if not event['pitch']:continue
    p=event['pitch'];number=12*(p['octave']+1)+model.NATURAL[p['step'].lower()]+F(p['alter'])
    event['encoded_midi']=str(number)
    event['legal_positions_at_encoded_pitch']=len(fretboard.single_positions_for_pitch(number))
    event['harmonic_spans']=[]
    start,end=F(event['start']),F(event['end'])
    changes=[F(h['time']) for h in result['harmonies'] if start<F(h['time'])<end]
    for a,b in zip([start,*changes],[*changes,end]):
      current=next((h for h in reversed(result['harmonies']) if F(h['time'])<=a),None)
      info={'start':str(a),'end':str(b),'chord':current,'chord_degrees':[]}
      if current and current['root']:
        try:
          chord=semantic(current);root=model.NATURAL[chord['root']['letter']]+F(current['alter'])
          info['chord_degrees']=[d for d,alter in harmony.degrees(chord).items() if (root+harmony.degree_semitones(d,alter)-number)%12==0]
          info['root_relative_semitones']=str((number-root)%12)
          info['spelled_simple_degree']=(model.LETTERS.index(p['step'].lower())-model.LETTERS.index(chord['root']['letter']))%7+1
        except (ValueError,KeyError,AttributeError) as error:
          info['uncertainty']=str(error)
      else:info['uncertainty']='No written/carried harmony; none invented.'
      event['harmonic_spans'].append(info)
  sounded=[];tie_roots={}
  for i,n in enumerate(result['notes']):
    if not n['pitch']:continue
    previous=n.get('continuation_of')
    if previous is not None and previous in tie_roots:
      root=tie_roots[previous];sounded[root]['end']=n['end'];sounded[root]['notation_events'].append(i);tie_roots[i]=root
    else:
      tie_roots[i]=len(sounded);sounded.append({'start':n['start'],'end':n['end'],'pitch':n['pitch'],'notation_events':[i]})
  result['sounding_events']=sounded
  first=form_start or next((h['measure'] for h in result['harmonies']),None)
  offset=F(result['measures'][first-1]['start']) if first else None
  result['alignment']={'form_start_measure':first,'encoded_offset':str(offset) if offset is not None else None,'basis':'explicit override' if form_start else 'first written harmony; review required','preceding_material':'retained, without invented harmony'}
  for label in result['annotations']:
    t=F(label['time']); current=[h for h in result['harmonies'] if F(h['time'])<=t]
    future=next((h for h in result['harmonies'] if F(h['time'])>t),None)
    label['current_harmony']=current[-1] if current else None
    label['following_harmony']=future
    label['events']=[n for n in result['notes'] if F(n['start'])<=t<F(n['end']) or t<=F(n['start'])<t+1]
    label['uncertainty']='Label meaning must be assessed from these events and harmonic time; label preserved verbatim.'
    expected={'b9':F(1),'#9':F(3),'b13':F(8),'#11':F(6),'6':F(9)}.get(label['text'].strip())
    if expected is not None:
      relationships=[s.get('root_relative_semitones') for n in label['events'] for s in n.get('harmonic_spans',[])]
      label['literal_interval_present']=str(expected) in relationships
      if not label['literal_interval_present']:label['uncertainty']='No matching interval in the immediate annotated context; label retained, intended scope uncertain.'
    # Lead in and Bluesy stay contextual descriptions, never enclosure permits.
  return result


def main():
  p=argparse.ArgumentParser(description=__doc__)
  p.add_argument('--reference',action='append',default=[],metavar='ROLE=PATH')
  p.add_argument('--form-start',action='append',default=[],metavar='ROLE=MEASURE')
  p.add_argument('--output',type=Path,required=True)
  args=p.parse_args(); starts={k:int(v) for k,v in (x.split('=',1) for x in args.form_start)}
  results=[read(path,role,starts.get(role)) for role,path in (x.split('=',1) for x in args.reference)]
  args.output.parent.mkdir(parents=True,exist_ok=True)
  args.output.write_text(json.dumps({'optional_validation_only':True,'references':results},indent=2))

if __name__=='__main__':main()