Exemple #1
0
def run():

    # Bootstrap logging
    boot_logging()

    # Load configuration
    configFile = LoadConfig()

    # Run this step only if enabled
    if configFile.FormateExportCountryCartography:

        # Get some paths from configuration
        storage_path = configFile.ResultBiblioPath
        output_path = configFile.ResultPath

        # Compute prefixes
        prefixes = [""]
        if configFile.GatherFamilly:
            prefixes.append("Families")

        # Build maps for all prefixes
        for prefix in prefixes:

            # Status message
            label = label_from_prefix(prefix)
            logger.info(
                "Generating maps about patent issuing countries for {}. ".
                format(label))

            # Compute storage slot
            storage_name = prefix + configFile.ndf

            # Generate map
            generate_map(storage_path, storage_name, output_path)

        # Due to limit of D3, countries resources are necessary placed
        # in same working directory... other solution is to start an http server
        # http://stackoverflow.com/questions/17077931/d3-samples-in-a-microsoft-stack

        # Clone required resources into result directory
        shutil.copy('countries.json',
                    os.path.join(output_path, "countries.json"))
Exemple #2
0
def run():

    # Bootstrap logging
    boot_logging()

    # Load configuration
    config = LoadConfig()

    # Run this only if enabled
    if not config.GatherImages:
        return

    # Get some information from configuration
    expression = config.requete
    storage_basedir = config.ResultBiblioPath
    storage_dirname = config.ndf
    output_path = config.ResultPathImages

    # Compute prefixes
    prefixes = [""]
    if config.GatherFamilly:
        prefixes.append("Families")

    # Build maps for all prefixes
    for prefix in prefixes:

        # Status message
        label = label_from_prefix(prefix)
        logger.info("Generating gallery of drawings for {}. ".format(label))

        # Compute storage slot using prefix and DataDirectory
        # e.g. "Lentille" vs. "FamiliesLentille"
        storage_name = prefix + storage_dirname

        # Load bibliographic data
        biblio_file = LoadBiblioFile(storage_basedir, storage_name)

        # Generate thumbnails
        gallery = []
        patents = biblio_file['brevets']
        cpt = 0
        for patent in patents:
            cpt + 1
            AnnonceProgres(Appli='p2n_image',
                           valMax=100,
                           valActu=90 + cpt * 10 / len(patents))
            patent_label = get_patent_label(patent)
            i = 1
            logger.info('Processing patent {}'.format(patent_label))
            path_img_base = '{}//{}-{}.tiff'.format(output_path, patent_label,
                                                    '{}')
            path = path_img_base.format(i)
            while os.path.exists(path):
                thumb, orig, tiff = generate_thumbnails(path)
                gallery.append({
                    "_id": '{}-{}'.format(patent_label, i),
                    'thumb': thumb,
                    'orig': orig,
                    'label': patent['title'],
                    'ipcr7': patent['IPCR7'],
                    'code': patent_label,
                    'tiff': tiff,
                })
                i += 1
                path = path_img_base.format(i)

        # Render gallery
        AnnonceProgres(Appli='p2n_image', valMax=100, valActu=100)
        RenderTemplate(
            'ModeleImages.html',
            output_path + '/index' + prefix + '.html',
            request=expression.replace('"', ''),
            gallery=gallery,
            json=json.dumps(gallery),
        )
Exemple #3
0
def run():
    """
    Usage:
      p2n ops init --key=<ops-oauth-key> --secret=<ops-oauth-secret>
      p2n run [--config=requete.cql] [--with-family]
      p2n acquire [--config=requete.cql] [--with-family]
      p2n normalisation [--config=requete.cql]
      p2n maps [--config=requete.cql]
      p2n networks [--config=requete.cql]
      p2n tables [--config=requete.cql]
      p2n bibfile [--config=requete.cql]
      p2n iramuteq [--config=requete.cql]
      p2n freeplane [--config=requete.cql]
      p2n carrot [--config=requete.cql]
      p2n images [--config=requete.cql]
      p2n cluster [--config=requete.cql]
      p2n interface [--config=requete.cql]
      p2n adhoc search --expression=<expression>
      p2n adhoc dump --expression=<expression> [--format=<format>] [--with-family] [--with-register]
      p2n adhoc list --expression=<expression> [--with-family] [--field=<field>] [--with-register]
      p2n adhoc worldmap --expression=<expression> --country-field=<country-field> [--with-family] [--with-register]
      p2n adhoc pivot --expression=<expression> [--format=<format>] [--with-family] [--with-register]
      p2n --version
      p2n (-h | --help)


    ------------
    Classic mode
    ------------
      p2n ops init                          Initialize Patent2Net with OPS OAuth credentials
      p2n run                               Run data acquisition and all formatters
      p2n acquire                           Run document acquisition
        --with-family                       Also run family data acquisition with "p2n acquire"
      p2n normalisation                     Suppress multiples equivalents, operates cleaning process in names (applicants and inventors). this is just for retrocompatibility as these steps are included in acquire process
      p2n maps                              Build maps of country coverage of patents, as well as applicants and inventors
      p2n networks                          Build various artefacts for data exploration based on network graphs
      p2n tables                            Export various artefacts for tabular data exploration
      p2n bibfile                           Export data in bibfile format
      p2n iramuteq                          Fetch more data and export it to suitable format for using in Iramuteq
      p2n freeplane                         Build mind map for Freeplane
      p2n carrot                            Export data to XML suitable for using in Carrot
      p2n images                            Fetch images and build thumbnails
      p2n cluster                           Build a double clusterer interface mixing abstracts and IPC description
      p2n interface                         Build main Patent2Net html interface
    Options:
      --config=<config>                     Path to requete.cql. Will fall back to environment variable "P2N_CONFIG".

    Examples:

      # Initialize Patent2Net with OPS OAuth credentials
      p2n ops init --key=ScirfedyifJiashwOckNoupNecpainLo --secret=degTefyekDevgew1

      # Run query and gather data
      p2n acquire --config=/path/to/RequestsSets/Lentille.cql --with-family

      # Build all world maps
      export P2N_CONFIG=/path/to/RequestsSets/Lentille.cql
      p2n maps

      # Run data acquisition and all targets
      p2n run


    -----------
    Ad hoc mode
    -----------
      p2n ops init                          Initialize Patent2Net with OPS OAuth credentials
      p2n adhoc search                      Display search results for given query expression in raw OPS format (JSON)
      p2n adhoc dump                        Display full results for given query expression in OpsExchangeDocument or Patent2NetBrevet format (JSON)
      p2n adhoc list                        Display list of values from single field for given query expression
      p2n adhoc worldmap                    Generate world map for given query expression over given field
      p2n adhoc pivot                       Generate data for pivot table

    Options:
      --expression=<expression>             Search expression in CQL format, e.g. "TA=lentille"
      --format=<format>                     Control output format for "p2n adhoc dump",
                                            Choose from "ops" or "brevet" [default: ops].
      --field=<field>                       Which field name to use with "p2n adhoc list" [default: document_number].
      --with-register                       Also acquire register information for each result hit.
                                            Required for "--country-field=register.designated_states".
      --country-field=<country-field>       Field name of country code for "p2n adhoc worldmap"
                                            e.g. "country", "applicants", "inventors", "register.designated_states"

    Examples:

      # Initialize Patent2Net with OPS OAuth credentials
      p2n ops init --key=ScirfedyifJiashwOckNoupNecpainLo --secret=degTefyekDevgew1

      # Run query and output results in OpsExchangeDocument format (JSON)
      p2n adhoc dump --expression='TA=lentille'

      # Run query and output results in Patent2NetBrevet format (JSON)
      p2n adhoc dump --expression='TA=lentille' --format=brevet

      # Run query and output list of document numbers, including family members (JSON)
      p2n adhoc list --expression='TA=lentille' --with-family

      # Run query and output list of application numbers in epodoc format
      p2n adhoc list --expression='TA=lentille' --field='application_number_epodoc'

      # Generate data for world maps using d3plus/geo_map (JSON)
      p2n adhoc worldmap --expression='TA=lentille' --country-field='country'
      p2n adhoc worldmap --expression='TA=lentille' --country-field='applicants'
      p2n adhoc worldmap --expression='TA=lentille' --country-field='inventors'
      p2n adhoc worldmap --expression='TA=lentille' --country-field='register.designated_states' --with-register

      # Generate data suitable for PivotTable.js (JSON)
      p2n adhoc pivot --expression='TA=lentille' --with-family

    """

    # Use generic commandline options schema and amend with current program name
    commandline_schema = (run.__doc__).format(program=APP_NAME)

    # Read commandline options
    options = docopt.docopt(commandline_schema,
                            version=APP_NAME + ' ' + __version__)

    # Start logging subsystem
    boot_logging(options)

    # Clean option names
    options = normalize_docopt_options(options)

    # Debugging
    #print('Options:\n{}'.format(pformat(options)))

    # Patent2Net ad-hoc mode interface
    if options['adhoc']:
        adhoc_interface(options)

    # Patent2Net classic interface
    else:
        classic_interface(options)