Diarios-Oficiais-ALEMS/diarios/views.py

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 = request.GET.get("page", 1)  # Obtém o valor de "page" (padrão: 1)

    # Converte page para int
    try:
        page = int(page)
    except ValueError:
        page = 1  # Valor padrão em caso de erro

    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="pdf_documents")

        # 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", "content^2", "synonyms^1"],
                    fuzziness="AUTO",
                    boost=2,
                )
            )
            queries.append(Q("match", synonyms={"query": cleaned_query, "boost": 0.5}))

        # Adiciona consultas exatas para frases entre aspas (sem fuzziness)
        for phrase in exact_phrases:
            if phrase.strip():
                # Consulta de frase exata para o título com peso alto
                queries.append(
                    Q(
                        "match_phrase",
                        title={
                            "query": phrase,
                            "boost": 3,
                            "slop": 0,  # Sem flexibilidade na ordem das palavras
                        },
                    )
                )

                # Consulta de frase exata para o conteúdo com peso médio
                queries.append(
                    Q(
                        "match_phrase",
                        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(
                "content",
                fragment_size=300,
                number_of_fragments=2,
                pre_tags=["<mark>"],
                post_tags=["</mark>"],
            )
            search = search.highlight(
                "title",
                fragment_size=300,
                number_of_fragments=1,
                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:
                # Obter o objeto PDFDocument correspondente
                try:
                    pdf_doc = PDFDocument.objects.get(id=hit.meta.id)
                    pdf_url = pdf_doc.file.url  # URL do PDF

                    matching_pages = []
                    if hasattr(hit.meta, 'highlight') and hasattr(hit.meta.highlight, 'pages.content'):
                        for highlight in hit.meta.highlight['pages.content']:
                            page_matches = re.findall(r'page_(\d+)', highlight)
                            if page_matches:
                                matching_pages.append(int(page_matches[0]))
                    if not matching_pages and query:
                        if pdf_doc.page_content:
                            try:
                                page_data = json.loads(pdf_doc.page_content)
                                for page_d in page_data:
                                    if query.lower() in page_d['content'].lower():
                                        matching_pages.append(page_d['number'])
                            except json.JSONDecodeError as e:
                                logger.error(f"Erro ao decodificar JSON para o documento {pdf_doc.id}: {e}")
                                page_data = []
                        else:
                            page_data = []
                    
                    matching_pages = sorted(list(set(matching_pages)))
                except PDFDocument.DoesNotExist:
                    pdf_url = ""
                    matching_pages = []

                # Extrai o conteúdo destacado ou usa o original
                if hasattr(hit.meta, "highlight") and hasattr(
                    hit.meta.highlight, "content"
                ):
                    highlighted_content = " ... ".join(hit.meta.highlight.content)
                else:
                    # Se não houver highlight, pegue os primeiros 300 caracteres
                    highlighted_content = (
                        hit.content[:300] + "..."
                        if len(hit.content) > 300
                        else hit.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.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,
                        "uploaded_at": hit.uploaded_at,
                        "score": hit.meta.score,
                        "is_exact_match": is_exact_match,
                        "pdf_url": pdf_url,
                        "matching_pages": matching_pages,
                    }
                )

            # Sugestões "Você quis dizer" (apenas para termos fora de aspas)
            if total_hits < 5 and cleaned_query:
                suggestion_search = Search(index="pdf_documents")
                suggestion_search = suggestion_search.suggest(
                    "term_suggestion",
                    cleaned_query,
                    term={"field": "content", "suggest_mode": "popular", "size": 5},
                )
                suggestion_response = suggestion_search.execute()

                if hasattr(suggestion_response, "suggest") and hasattr(
                    suggestion_response.suggest, "term_suggestion"
                ):
                    for suggestion in suggestion_response.suggest.term_suggestion:
                        for option in suggestion.options:
                            suggestions.append(option.text)

                    # Cria uma correção ortográfica se necessário
                    if suggestions and total_hits == 0:
                        corrected_query = cleaned_query
                        for (
                            suggestion_term
                        ) in suggestion_response.suggest.term_suggestion:
                            if suggestion_term.options:
                                # Substitui palavras incorretas por sugestões
                                word_to_replace = suggestion_term.text
                                corrected_word = suggestion_term.options[0].text
                                corrected_query = re.sub(
                                    r"\b" + re.escape(word_to_replace) + r"\b",
                                    corrected_word,
                                    corrected_query,
                                    flags=re.IGNORECASE,
                                )

                        # Reconstrói a consulta original mantendo as frases entre aspas
                        if corrected_query != cleaned_query:
                            spelling_correction = corrected_query
                            for phrase in exact_phrases:
                                spelling_correction += f' "{phrase}"'
                            spelling_correction = spelling_correction.strip()

            # Busca por termos relacionados (apenas se houver poucos resultados)
            if total_hits < 3 and cleaned_query:
                related_terms = Search(index="pdf_documents")
                related_terms = related_terms.query(
                    "more_like_this",
                    fields=["content", "title"],
                    like=cleaned_query,
                    min_term_freq=1,
                    max_query_terms=10,
                    min_doc_freq=1,
                )
                related_terms = related_terms[:5]
                related_response = related_terms.execute()

                for hit in related_response:
                    # Verifica se este documento já está nos resultados
                    if not any(r.get("id") == hit.meta.id for r in results):
                        results.append(
                            {
                                "id": hit.meta.id,
                                "title": hit.title,
                                "highlighted_title": hit.title,
                                "highlighted_content": (
                                    hit.content[:300] + "..."
                                    if len(hit.content) > 300
                                    else hit.content
                                ),
                                "uploaded_at": hit.uploaded_at,
                                "score": hit.meta.score,
                                "is_related": True,
                                "pdf_url": pdf_url,
                            }
                        )

    # 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),
        },
    )