160 lines
5.5 KiB
Python
160 lines
5.5 KiB
Python
import json
|
|
import debugpy
|
|
from django.shortcuts import render
|
|
from elasticsearch_dsl import Search, Q
|
|
from elasticsearch_dsl.connections import connections
|
|
from django.conf import settings
|
|
import re
|
|
from .documents import PDFDocument
|
|
from django.http import JsonResponse
|
|
|
|
|
|
# Configuração da conexão com o Elasticsearch
|
|
connections.create_connection(hosts=[settings.ELASTICSEARCH_HOSTS])
|
|
|
|
|
|
def spellcheck_view(request):
|
|
query = request.GET.get("q", "")
|
|
suggestions = []
|
|
|
|
if query:
|
|
s = Search(index="pdf_documents")
|
|
s = s.suggest(
|
|
"auto_correct",
|
|
query,
|
|
phrase={
|
|
"field": "suggest",
|
|
"size": 3,
|
|
"gram_size": 3,
|
|
"confidence": 2.0,
|
|
"direct_generator": [{"field": "suggest", "suggest_mode": "popular"}],
|
|
},
|
|
)
|
|
response = s.execute()
|
|
|
|
if hasattr(response.suggest, "auto_correct"):
|
|
for option in response.suggest.auto_correct[0].options:
|
|
suggestions.append(option.text)
|
|
|
|
return JsonResponse({"suggestions": suggestions})
|
|
|
|
def search_view(request):
|
|
query = request.GET.get('q', '') # Obtém o termo de pesquisa da URL
|
|
page = int(request.GET.get('page', 1))
|
|
|
|
results = []
|
|
suggestions = []
|
|
spelling_correction = None
|
|
total_hits = 0
|
|
per_page = 10
|
|
|
|
if query:
|
|
# Processamento especial para termos entre aspas
|
|
exact_phrases = re.findall(r'"([^"]*)"', query)
|
|
|
|
# Remove os termos entre aspas da consulta principal
|
|
cleaned_query = query
|
|
for phrase in exact_phrases:
|
|
cleaned_query = cleaned_query.replace(f'"{phrase}"', '')
|
|
|
|
# Remove espaços extras e pontuação desnecessária
|
|
cleaned_query = re.sub(r'\s+', ' ', cleaned_query).strip()
|
|
|
|
# Cria uma consulta no Elasticsearch
|
|
search = Search(index='diarios_oficiais')
|
|
|
|
# Lista para armazenar todas as consultas
|
|
queries = []
|
|
|
|
# Adiciona consulta para termos gerais (com fuzziness para tolerância a erros)
|
|
if cleaned_query:
|
|
queries.append(
|
|
Q('multi_match',
|
|
query=cleaned_query,
|
|
fields=['title^3', 'pages.content^2'],
|
|
fuzziness='AUTO',
|
|
boost=2)
|
|
)
|
|
|
|
# Adiciona consultas exatas para frases entre aspas (sem fuzziness)
|
|
for phrase in exact_phrases:
|
|
if phrase.strip():
|
|
queries.append(
|
|
Q('match_phrase',
|
|
pages__content={
|
|
'query': phrase,
|
|
'boost': 2,
|
|
'slop': 0 # Sem flexibilidade na ordem das palavras
|
|
})
|
|
)
|
|
|
|
# Combina as consultas com OR (se houver alguma)
|
|
if queries:
|
|
search = search.query(
|
|
Q('bool', should=queries, minimum_should_match=1)
|
|
)
|
|
|
|
# Configuração do highlight para mostrar mais contexto
|
|
search = search.highlight(
|
|
'pages.content',
|
|
fragment_size=300,
|
|
number_of_fragments=2,
|
|
pre_tags=['<mark>'],
|
|
post_tags=['</mark>']
|
|
)
|
|
|
|
# Paginação
|
|
search = search[(page-1)*per_page:page*per_page]
|
|
|
|
# Executa a consulta
|
|
response = search.execute()
|
|
total_hits = response.hits.total.value
|
|
|
|
# Processa os resultados
|
|
for hit in response:
|
|
# Extrai o conteúdo destacado ou usa o original
|
|
if hasattr(hit.meta, 'highlight') and hasattr(hit.meta.highlight, 'pages.content'):
|
|
highlighted_content = ' ... '.join(hit.meta.highlight['pages.content'])
|
|
else:
|
|
highlighted_content = ""
|
|
|
|
# Extrai o título destacado ou usa o original
|
|
if hasattr(hit.meta, 'highlight') and hasattr(hit.meta.highlight, 'title'):
|
|
highlighted_title = hit.meta.highlight.title[0]
|
|
else:
|
|
highlighted_title = hit.title
|
|
|
|
# Verifica se o resultado corresponde a uma frase exata
|
|
is_exact_match = any(phrase.lower() in hit.pages.content.lower() or
|
|
phrase.lower() in hit.title.lower()
|
|
for phrase in exact_phrases)
|
|
|
|
results.append({
|
|
'id': hit.meta.id,
|
|
'title': hit.title,
|
|
'highlighted_title': highlighted_title,
|
|
'highlighted_content': highlighted_content,
|
|
'data': hit.data,
|
|
'numero': hit.numero,
|
|
'link': hit.link,
|
|
'finalizado': hit.finalizado,
|
|
'is_exact_match': is_exact_match
|
|
})
|
|
|
|
# Calcula a paginação
|
|
total_pages = (total_hits + per_page - 1) // per_page if total_hits > 0 else 0
|
|
|
|
# Renderiza o template com os resultados
|
|
return render(request, 'diarios/search_results.html', {
|
|
'query': query,
|
|
'results': results,
|
|
'suggestions': suggestions[:5], # Limita a 5 sugestões
|
|
'spelling_correction': spelling_correction,
|
|
'total_hits': total_hits,
|
|
'page': page,
|
|
'total_pages': total_pages,
|
|
'page_range': range(max(1, page-2), min(total_pages+1, page+3)),
|
|
'has_exact_phrases': bool(exact_phrases)
|
|
})
|
|
|