| """Small vocabulary and deterministic candidate retrieval, without site rules.""" |
| from collections import Counter |
| import re |
| import torch |
|
|
| KINDS = ('C', 'T', 'O') |
| ROLES = {'button', 'link', 'textbox', 'searchbox', 'combobox', 'checkbox', 'radio', 'listbox', 'spinbutton'} |
|
|
|
|
| def words(text): |
| return re.findall(r'\w+', text.casefold(), flags=re.UNICODE) |
|
|
|
|
| def fit_vocab(rows, limit=4096): |
| counts = Counter() |
| for row in rows: |
| counts.update(words(row['goal'])) |
| for element in row['elements']: |
| counts.update(words(element['role'] + ' ' + element['name'])) |
| return {'<pad>':0, '<unk>':1, **{token:i+2 for i, (token, _) in enumerate(counts.most_common(limit-2))}} |
|
|
|
|
| def lexical(goal, element): |
| goal_words, name_words = set(words(goal)), set(words(element['name'])) |
| overlap = len(goal_words & name_words) |
| return [overlap / max(1,len(name_words)), overlap / max(1,len(goal_words)), |
| float(element['name'].casefold() in goal.casefold()), |
| float(element.get('visible', True)), float(element.get('enabled', True))] |
|
|
|
|
| def candidates(goal, elements, limit=40): |
| eligible = [i for i, e in enumerate(elements) if e.get('visible', True) and e.get('enabled', True) |
| and not e.get('sensitive', False) and e['role'] in ROLES] |
| return sorted(eligible, key=lambda i: (-lexical(goal,elements[i])[0], i))[:limit] |
|
|
|
|
| def encode(rows, vocab, max_tokens=24, max_candidates=40): |
| |
| maps = [candidates(row['goal'],row['elements'],max_candidates) for row in rows] |
| count = max(1, max(map(len,maps),default=0)) |
| goal = torch.zeros((len(rows),max_tokens),dtype=torch.long) |
| element = torch.zeros((len(rows),count,max_tokens),dtype=torch.long) |
| features = torch.zeros((len(rows),count,5)) |
| mask = torch.zeros((len(rows),count),dtype=torch.bool) |
| targets = torch.full((len(rows),),-100,dtype=torch.long) |
| actions = torch.full((len(rows),),-100,dtype=torch.long) |
| def tokens(text): |
| return [vocab.get(token,1) for token in words(text)[:max_tokens]] |
| for batch,row in enumerate(rows): |
| ids = tokens(row['goal']) |
| goal[batch,:len(ids)] = torch.tensor(ids,dtype=torch.long) |
| if row.get('action') in KINDS: |
| actions[batch] = KINDS.index(row['action']) |
| for j,index in enumerate(maps[batch]): |
| e = row['elements'][index] |
| ids = tokens(e['role'] + ' ' + e['name']) |
| element[batch,j,:len(ids)] = torch.tensor(ids,dtype=torch.long) |
| features[batch,j] = torch.tensor(lexical(row['goal'],e)) |
| mask[batch,j] = True |
| if row.get('target') == index: |
| targets[batch] = j |
| return (goal,element,features,mask),actions,targets,maps |
|
|
