Exemple #1
0
def check_load_taxonomy_data(max_items=None):
    """Load the tables from the source archives

    Leave max_items to None for processing the complete dumps.
    """
    updated = pg.check_link_table(
        "redirects", "redirects",
        predicate_filter="http://dbpedia.org/ontology/wikiPageRedirects",
        max_items=max_items)

    updated &= pg.check_link_table(
        "skos_categories", "categories",
        predicate_filter="http://www.w3.org/2004/02/skos/core#broader",
        columns=(
            ('id', True),
            ('broader', True),
            ('candidate_article', True),
        ),
        processor=candidate_article_processor,
        max_items=max_items)

    updated &= pg.check_link_table(
        "article_categories", "article_categories",
        predicate_filter="http://purl.org/dc/terms/subject")

    if updated:
        pg.execute("ANALYZE")
def check_load_examples_data(max_items):
    """Load the abstract data

    Leave max_items to None for processing the complete dumps.
    """
    updated = pg.check_text_table("long_abstracts", "long_abstracts", max_items=max_items)
    if updated:
        pg.execute("ANALYZE")
Exemple #3
0
def check_load_examples_data(max_items):
    """Load the abstract data

    Leave max_items to None for processing the complete dumps.
    """
    updated = pg.check_text_table(
        "long_abstracts", "long_abstracts", max_items=max_items)
    if updated:
        pg.execute("ANALYZE")
def check_load_taxonomy_data(max_items=None):
    """Load the tables from the source archives

    Leave max_items to None for processing the complete dumps.
    """
    updated = pg.check_link_table(
        "redirects", "redirects", predicate_filter="http://dbpedia.org/ontology/wikiPageRedirects", max_items=max_items
    )

    updated &= pg.check_link_table(
        "skos_categories",
        "categories",
        predicate_filter="http://www.w3.org/2004/02/skos/core#broader",
        columns=(("id", True), ("broader", True), ("candidate_article", True)),
        processor=candidate_article_processor,
        max_items=max_items,
    )

    updated &= pg.check_link_table(
        "article_categories", "article_categories", predicate_filter="http://purl.org/dc/terms/subject"
    )

    if updated:
        pg.execute("ANALYZE")