spb/trouve-ka Public

1# Trouve-KA — mapping OpenSearch bilingue2# Author: Simon-Pierre Boucher3# Contact: contact@spboucher.ai45"""Mapping et settings de l'index documents.67- Analyzers français ET anglais sur les champs texte (bilingue dès le départ).8- Filtre de synonymes bilingues (thermopompe ↔ heat pump) appliqué à la recherche9  seulement : pas de traduction à l'ingestion.10- Refresh 1 s : une page indexée est cherchable en ~1 seconde (principe cardinal).11"""1213# Synonymes bilingues de départ — extensibles sans réindexation (search-time)14BILINGUAL_SYNONYMS = [15    "thermopompe, heat pump",16    "subvention, grant, subsidy",17    "emploi, job, employment",18    "entreprise, company, business",19    "université, university",20    "cégep, cegep, college",21    "garderie, daycare, cpe",22    "impôt, tax, taxes",23    "santé, health",24    "plombier, plumber",25    "électricien, electrician",26    "déneigement, snow removal",27    "assurance, insurance",28    "logement, housing, apartment",29    "ville, city, municipalité, municipality",30    "gouvernement, government",31    "permis, permit, license, licence",32]3334INDEX_SETTINGS = {35    "settings": {36        "number_of_shards": 1,37        "number_of_replicas": 0,38        "refresh_interval": "1s",39        "analysis": {40            "filter": {41                "french_elision": {42                    "type": "elision",43                    "articles_case": True,44                    "articles": ["l", "m", "t", "qu", "n", "s", "j", "d", "c", "jusqu", "quoiqu", "lorsqu", "puisqu"],45                },46                "french_stop": {"type": "stop", "stopwords": "_french_"},47                "french_stemmer": {"type": "stemmer", "language": "light_french"},48                "english_stop": {"type": "stop", "stopwords": "_english_"},49                "english_stemmer": {"type": "stemmer", "language": "light_english"},50                "bilingual_synonyms": {51                    "type": "synonym_graph",52                    "lenient": True,53                    "synonyms": BILINGUAL_SYNONYMS,54                },55            },56            "analyzer": {57                "fr_text": {58                    "tokenizer": "standard",59                    "filter": ["french_elision", "lowercase", "asciifolding", "french_stop", "french_stemmer"],60                },61                "fr_search": {62                    "tokenizer": "standard",63                    "filter": ["french_elision", "lowercase", "asciifolding", "bilingual_synonyms",64                               "french_stop", "french_stemmer"],65                },66                "en_text": {67                    "tokenizer": "standard",68                    "filter": ["lowercase", "asciifolding", "english_stop", "english_stemmer"],69                },70                "en_search": {71                    "tokenizer": "standard",72                    "filter": ["lowercase", "asciifolding", "bilingual_synonyms",73                               "english_stop", "english_stemmer"],74                },75            },76        },77    },78    "mappings": {79        "properties": {80            "url": {"type": "keyword"},81            "canonical_url": {"type": "keyword"},82            "domain": {"type": "keyword"},83            "title": {84                "type": "text",85                "analyzer": "fr_text",86                "search_analyzer": "fr_search",87                "fields": {"en": {"type": "text", "analyzer": "en_text", "search_analyzer": "en_search"}},88            },89            "description": {90                "type": "text",91                "analyzer": "fr_text",92                "search_analyzer": "fr_search",93                "fields": {"en": {"type": "text", "analyzer": "en_text", "search_analyzer": "en_search"}},94            },95            "body": {96                "type": "text",97                "analyzer": "fr_text",98                "search_analyzer": "fr_search",99                "fields": {"en": {"type": "text", "analyzer": "en_text", "search_analyzer": "en_search"}},100            },101            "headings": {102                "type": "text",103                "analyzer": "fr_text",104                "search_analyzer": "fr_search",105                "fields": {"en": {"type": "text", "analyzer": "en_text", "search_analyzer": "en_search"}},106            },107            "language": {"type": "keyword"},108            "image_url": {"type": "keyword", "index": False},109            "page_quebec_score": {"type": "float"},110            "domain_quebec_score": {"type": "float"},111            "locations": {"type": "keyword"},112            "organizations": {"type": "keyword"},113            "people": {"type": "keyword"},114            "categories": {"type": "keyword"},115            "published_at": {"type": "date"},116            "crawled_at": {"type": "date"},117            "authority_score": {"type": "float"},118            "freshness_score": {"type": "float"},119            "quality_score": {"type": "float"},120            "spam_score": {"type": "float"},121            # embedding (dense_vector/knn) ajouté à l'étape sémantique (§17.7),122            # le mapping est extensible sans réindexation pour un nouveau champ.123        }124    },125}126