ricgraph 2.8__tar.gz → 2.9__tar.gz

{ricgraph-2.8/ricgraph.egg-info → ricgraph-2.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ricgraph
-Version: 2.8
+Version: 2.9
 Summary: Ricgraph - Research in context graph
 Author: Rik D.T. Janssen
 Project-URL: Website, https://www.ricgraph.eu

{ricgraph-2.8 → ricgraph-2.9}/pyproject.toml

@@ -7,7 +7,7 @@ packages = ["ricgraph"]
 
 [project]
 name = "ricgraph"
-version = "2.8"
+version = "2.9"
 authors = [
   { name="Rik D.T. Janssen" },
 ]

{ricgraph-2.8 → ricgraph-2.9}/ricgraph/__init__.py

@@ -33,6 +33,4 @@
 #
 # ########################################################################
 
-__version__ = '2.8'
-
 from .ricgraph import *

{ricgraph-2.8 → ricgraph-2.9}/ricgraph/ricgraph.py

@@ -66,7 +66,7 @@ In RICGRAPH_PROPERTIES_STANDARD:
 - name: name of the node, e.g. ISNI, ORCID, DOI, etc.
 
 - category: category of the node,
-  e.g. person, person-root, book, journal article, dataset, etc.
+  e.g. person, person-root, book, journal article, data set, etc.
 
 - value: value of the node.
 
@@ -100,6 +100,7 @@ In the default configuration of Ricgraph, the following properties are included:
 
 import os
 import sys
+import re
 from datetime import datetime
 import numpy
 import pandas
@@ -118,7 +119,11 @@ __copyright__ = 'Copyright (c) 2023, 2024, 2025 Rik D.T. Janssen'
 __email__ = ''
 __license__ = 'MIT License'
 __package__ = 'Ricgraph'
-# __version__ is in __init__.py of this module.
+
+# __version__ should be placed here instead of in __init__.py.
+# If not here, it cannot be found when executing something like
+# PYTHONPATH=../ricgraph ../bin/python ricgraph_explorer.py
+__version__ = '2.9'
 
 
 # ########################################################################
@@ -168,7 +173,7 @@ graphdb_nr_deletes = 0
 # An example mapping may look like this:
 # mapping = {
 #    'book': ROTYPE_BOOK,
-#    'dataset': ROTYPE_DATASET,
+#    'data set': ROTYPE_DATASET,
 #    'software': ROTYPE_SOFTWARE
 # }
 #
@@ -300,7 +305,7 @@ def open_ricgraph() -> Driver:
     """
     global _graph
 
-    print('Opening ricgraph.\n')
+    print('Opening Ricgraph.\n')
     try:
         _graph = GraphDatabase.driver(GRAPHDB_URL,
                                       auth=(GRAPHDB_USER, GRAPHDB_PASSWORD))
@@ -325,7 +330,7 @@ def close_ricgraph() -> None:
     """
     global _graph
 
-    print('Closing ricgraph.\n')
+    print('Closing Ricgraph.\n')
     _graph.close()
     return
 
@@ -353,28 +358,16 @@ def empty_ricgraph(answer: str = '') -> None:
     """
     global _graph
 
-    if answer == 'yes':
-        print('Emptying Ricgraph: Ricgraph will be emptied.\n')
-        # Fall through.
-    elif answer == 'no':
-        print('Emptying Ricgraph: Ricgraph will not be emptied.\n')
+    if answer != 'yes' and answer != 'no':
+        print('empty_ricgraph(): invalid answer "' + answer + '" on the question')
+        print('to empty Ricgraph, exiting.')
+        exit(1)
+
+    if answer == 'no':
+        print('empty_ricgraph(): Ricgraph will not be emptied.\n')
         return
-    else:
-        print('Do you want to empty Ricgraph? You have the following options:')
-        print('- "yes": Ricgraph will be emptied.')
-        print('- "no": Ricgraph will not be emptied.')
-        print('- any other answer: Ricgraph will not be emptied, execution of this script will abort.')
-        user_input = input('Please make a choice: ')
-        if user_input.lower() == 'yes':
-            print('\nRicgraph will be emptied.\n')
-            # Fall through.
-        elif user_input.lower() == 'no':
-            print('\nRicgraph has not been emptied.\n')
-            return
-        else:
-            print('\nRicgraph has not been emptied, exiting.\n')
-            exit(1)
 
+    print('empty_ricgraph(): Ricgraph will be emptied.\n')
     graphdb_name = ricgraph_database()
     graphdb_databasename = ricgraph_databasename()
 
@@ -755,6 +748,14 @@ def cypher_create_edge_if_not_exists(left_node_element_id: str, right_node_eleme
 # ##############################################################################
 # General Ricgraph functions.
 # ##############################################################################
+def get_ricgraph_version() -> str:
+    """Get the version Ricgraph.
+
+    :return: the version string.
+    """
+    return __version__
+
+
 def get_ricgraph_ini_file() -> str:
     """Get the location of the ricgraph ini file.
 
@@ -927,6 +928,184 @@ def create_well_known_url(name: str, value: str) -> str:
         return ''
 
 
+def normalize_doi(identifier: str) -> str:
+    """Normalize DOI.
+
+    :param identifier: identifier to normalize.
+    :return: Result of normalizing.
+    """
+    if identifier == '':
+        return ''
+    identifier = identifier.lower()
+    identifier = re.sub(pattern=r'https|http', repl='', string=identifier)
+    identifier = re.sub(pattern=r'://', repl='', string=identifier)
+    identifier = re.sub(pattern=r'www.', repl='', string=identifier)
+    identifier = re.sub(pattern=r'doi.org/', repl='', string=identifier)
+    identifier = re.sub(pattern=r'doi', repl='', string=identifier)
+    identifier = re.sub(pattern=r'.proxy.uu.nl/', repl='', string=identifier)
+    return identifier
+
+
+def normalize_ror(identifier: str) -> str:
+    """Normalize ROR.
+
+    :param identifier: identifier to normalize.
+    :return: Result of normalizing.
+    """
+    if identifier == '':
+        return ''
+    identifier = identifier.lower()
+    identifier = re.sub(pattern=r'https|http', repl='', string=identifier)
+    identifier = re.sub(pattern=r'://', repl='', string=identifier)
+    identifier = re.sub(pattern=r'www.', repl='', string=identifier)
+    identifier = re.sub(pattern=r'ror.org/', repl='', string=identifier)
+    return identifier
+
+
+def normalize_orcid(identifier: str) -> str:
+    """Normalize ORCID.
+
+    :param identifier: identifier to normalize.
+    :return: Result of normalizing.
+    """
+    if identifier == '':
+        return ''
+    identifier = identifier.lower()
+    identifier = re.sub(pattern=r'https|http', repl='', string=identifier)
+    identifier = re.sub(pattern=r'://', repl='', string=identifier)
+    identifier = re.sub(pattern=r'www.', repl='', string=identifier)
+    identifier = re.sub(pattern=r'orcid.org/', repl='', string=identifier)
+    identifier = identifier.upper()
+    return identifier
+
+
+def normalize_isni(identifier: str) -> str:
+    """Normalize ISNI.
+
+    :param identifier: identifier to normalize.
+    :return: Result of normalizing.
+    """
+    if identifier == '':
+        return ''
+    identifier = identifier.lower()
+    identifier = re.sub(pattern=r'https|http', repl='', string=identifier)
+    identifier = re.sub(pattern=r'://', repl='', string=identifier)
+    identifier = re.sub(pattern=r'www.', repl='', string=identifier)
+    identifier = re.sub(pattern=r'isni.org/isni/', repl='', string=identifier)
+    identifier = identifier.upper()
+    return identifier
+
+
+def normalize_openalex(identifier: str) -> str:
+    """Normalize OpenAlex identifier.
+
+    :param identifier: identifier to normalize.
+    :return: Result of normalizing.
+    """
+    if identifier == '':
+        return ''
+    identifier = identifier.lower()
+    identifier = re.sub(pattern=r'https|http', repl='', string=identifier)
+    identifier = re.sub(pattern=r'://', repl='', string=identifier)
+    identifier = re.sub(pattern=r'www.', repl='', string=identifier)
+    identifier = re.sub(pattern=r'openalex.org/', repl='', string=identifier)
+    identifier = identifier.upper()
+    return identifier
+
+
+def normalize_scopus_author_id(identifier: str) -> str:
+    """Normalize SCOPUS_AUTHOR_ID. Return a uniform value.
+
+    :param identifier: identifier to normalize.
+    :return: Result of normalizing.
+    """
+    if identifier == '':
+        return ''
+    identifier = identifier.lower()
+    identifier = re.sub(pattern=r'https|http', repl='', string=identifier)
+    identifier = re.sub(pattern=r'://', repl='', string=identifier)
+    identifier = re.sub(pattern=r'www.', repl='', string=identifier)
+    identifier = re.sub(pattern=r'scopus.com/authid/detail.uri', repl='', string=identifier)
+    identifier = re.sub(pattern=r'\?authorid\=', repl='', string=identifier)
+    return identifier
+
+
+def normalize_researcher_id(identifier: str) -> str:
+    """Normalize RESEARCHER_ID.
+
+    :param identifier: identifier to normalize.
+    :return: Result of normalizing.
+    """
+    if identifier == '':
+        return ''
+    identifier = identifier.lower()
+    identifier = re.sub(pattern=r'https|http', repl='', string=identifier)
+    identifier = re.sub(pattern=r'://', repl='', string=identifier)
+    identifier = re.sub(pattern=r'www.', repl='', string=identifier)
+    identifier = re.sub(pattern=r'researcherid.com/rid/', repl='', string=identifier)
+    identifier = identifier.upper()
+    return identifier
+
+
+def normalize_digital_author_id(identifier: str) -> str:
+    """Normalize DIGITAL_AUTHOR_ID.
+
+    :param identifier: identifier to normalize.
+    :return: Result of normalizing.
+    """
+    if identifier == '':
+        return ''
+    identifier = identifier.lower()
+    identifier = re.sub(pattern=r'urn:nbn:nl:ui:', repl='', string=identifier)
+    identifier = re.sub(pattern=r'info:eu-repo/dai/nl/', repl='', string=identifier)
+    identifier = identifier.upper()
+    return identifier
+
+
+def normalize_email(identifier: str) -> str:
+    """Normalize email address.
+
+    :param identifier: identifier to normalize.
+    :return: Result of normalizing.
+    """
+    if identifier == '':
+        return ''
+    identifier = identifier.lower()
+    return identifier
+
+
+def normalize_identifiers(df: pandas.DataFrame) -> pandas.DataFrame:
+    """Normalize selected identifiers in the dataframe.
+    Delete empty rows and duplicates.
+
+    :param df: dataframe with identifiers.
+    :return: Result of normalizing.
+    """
+    df_mod = df.copy(deep=True)
+
+    # Ensure that all '' values are NaN, so that those rows can be easily removed with dropna()
+    df_mod.replace('', numpy.nan, inplace=True)
+    # dropna(how='all'): drop row if all row values contain NaN
+    df_mod.dropna(axis=0, how='all', inplace=True)
+    df_mod.drop_duplicates(keep='first', inplace=True, ignore_index=True)
+
+    # The values in this list correspond to the normalize functions above,
+    # such as normalize_doi(), normalize_ror(), etc.
+    for identifier in ['DOI', 'ROR', 'ORCID', 'ISNI', 'OPENALEX',
+                       'SCOPUS_AUTHOR_ID', 'RESEARCHER_ID', 'DIGITAL_AUTHOR_ID',
+                       'EMAIL']:
+        function_name = f'normalize_{identifier.lower()}'
+        if not callable(globals().get(function_name)):
+            print('normalize_identifiers(): Error, function "' + function_name + '"')
+            print('  does not exist, exiting.')
+            exit(1)
+
+        if identifier in df_mod.columns:
+            df_mod[identifier] = df_mod[identifier].apply(
+                lambda x: globals()[function_name](x) if isinstance(x, str) else x)
+    return df_mod
+
+
 def create_history_line(property_name: str, old_value: str, new_value: str) -> str:
     """Create a line to be used in the 'history' property of a node.
     """
@@ -2798,69 +2977,154 @@ def get_commandline_argument(argument: str, argument_list: list) -> str:
     return ''
 
 
+def get_commandline_argument_organization(argument_list: list) -> str:
+    """Get the value of a command line argument '--organization'.
+    Prompt if no argument is given.
+
+    :param argument_list: the argument list.
+    :return: the organization, or '' if no answer is given.
+    """
+    answer = get_commandline_argument(argument='--organization',
+                                      argument_list=argument_list)
+    if answer == '':
+        print('\nYou need to specify an organization abbreviation.')
+        print('This script will be run for that organization.')
+        print('The organization abbreviation you enter will determine')
+        print('which parameters will be read from the Ricgraph ini file')
+        print('"' + get_ricgraph_ini_file() + '".')
+        print('If you make a typo, you can run this script again.')
+        print('If you enter an empty value, this script will exit.')
+        answer = input('For what organization do you want to run this script? ')
+        if answer == '':
+            return ''
+
+    answer = answer.upper()
+    return answer
+
+
+def get_commandline_argument_empty_ricgraph(argument_list: list) -> str:
+    """Get the value of a command line argument '--empty_ricgraph'.
+    Prompt if no argument is given.
+
+    :param argument_list: the argument list.
+    :return: 'yes' or 'no', the answer whether to empty Ricgraph,
+      or '' if no answer is given.
+    """
+    answer = get_commandline_argument(argument='--empty_ricgraph',
+                                      argument_list=argument_list)
+    if answer == '':
+        print('\nDo you want to empty Ricgraph? You have the following options:')
+        print('- "yes": Ricgraph will be emptied.')
+        print('- "no": Ricgraph will not be emptied.')
+        print('- any other answer: Ricgraph will not be emptied,')
+        print('  execution of this script will abort.')
+        answer = input('Please make a choice: ')
+        if answer == '':
+            return ''
+
+    answer = answer.lower()
+    if answer != 'yes' and answer != 'no':
+        return ''
+    return answer
+
+
+def get_commandline_argument_harvest_projects(argument_list: list) -> str:
+    """Get the value of a command line argument '--harvest_projects'.
+    Prompt if no argument is given.
+
+    :param argument_list: the argument list.
+    :return: 'yes' or 'no', the answer whether to harvest projects,
+      or '' if no answer is given.
+    """
+    answer = get_commandline_argument(argument='--harvest_projects',
+                                      argument_list=argument_list)
+    if answer == '':
+        print('\nYou can specify whether you want to harvest projects.')
+        print('Only if enter "yes", this script will harvest projects.')
+        answer = input('Do you want to harvest projects? ')
+        if answer == '':
+            return ''
+
+    answer = answer.lower()
+    if answer != 'yes' and answer != 'no':
+        return ''
+    return answer
+
+
+def get_configfile_key(section: str, key: str) -> str:
+    """Get the value of a key in the Ricgraph config file.
+
+    :param section: the section where the key is to be read from.
+    :param key: the name of the key.
+    :return: the value of the key (can be ''), or '' if absent.
+    """
+    config = configparser.ConfigParser()
+    config.read(get_ricgraph_ini_file())
+    try:
+        value = config[section][key]
+    except KeyError:
+        return ''
+
+    return value
+
+
 # ############################################
 # ################### main ###################
 # ############################################
 # This will be executed on module initialization
-config = configparser.ConfigParser()
-config.read(get_ricgraph_ini_file())
-try:
-    RICGRAPH_PROPERTIES_STANDARD = tuple(config['Ricgraph']['ricgraph_properties_standard'].split(','))
-    RICGRAPH_PROPERTIES_HIDDEN = tuple(config['Ricgraph']['ricgraph_properties_hidden'].split(','))
-    RICGRAPH_PROPERTIES_ADDITIONAL = tuple(config['Ricgraph']['ricgraph_properties_additional'].split(','))
-    if len(RICGRAPH_PROPERTIES_STANDARD) == 0 \
-       or len(RICGRAPH_PROPERTIES_HIDDEN) == 0 \
-       or len(RICGRAPH_PROPERTIES_ADDITIONAL) == 0:
-        print('Ricgraph initialization: error, ricgraph_properties_standard and/or')
-        print('  ricgraph_properties_hidden and/or ricgraph_properties_additional')
-        print('  are empty in Ricgraph ini file, exiting.')
-        exit(1)
-
-    if RICGRAPH_PROPERTIES_STANDARD[0] == '' \
-       or RICGRAPH_PROPERTIES_HIDDEN[0] == '' \
-       or RICGRAPH_PROPERTIES_ADDITIONAL[0] == '':
-        print('Ricgraph initialization: error, ricgraph_properties_standard and/or')
-        print('  ricgraph_properties_hidden and/or ricgraph_properties_additional')
-        print('  are empty in Ricgraph ini file, exiting.')
-        exit(1)
+RICGRAPH_PROPERTIES_STANDARD = tuple(get_configfile_key(section='Ricgraph',
+                                                        key='ricgraph_properties_standard').split(','))
+RICGRAPH_PROPERTIES_HIDDEN = tuple(get_configfile_key(section='Ricgraph',
+                                                      key='ricgraph_properties_hidden').split(','))
+RICGRAPH_PROPERTIES_ADDITIONAL = tuple(get_configfile_key(section='Ricgraph',
+                                                          key='ricgraph_properties_additional').split(','))
+if len(RICGRAPH_PROPERTIES_STANDARD) == 0 \
+   or len(RICGRAPH_PROPERTIES_HIDDEN) == 0 \
+   or len(RICGRAPH_PROPERTIES_ADDITIONAL) == 0 \
+   or RICGRAPH_PROPERTIES_STANDARD[0] == '' \
+   or RICGRAPH_PROPERTIES_HIDDEN[0] == '' \
+   or RICGRAPH_PROPERTIES_ADDITIONAL[0] == '':
+    print('Ricgraph initialization: error, "ricgraph_properties_standard" and/or')
+    print('  "ricgraph_properties_hidden" and/or "ricgraph_properties_additional"')
+    print('  are not existing or empty in Ricgraph ini')
+    print('  file "' + get_ricgraph_ini_file() + '", exiting.')
+    exit(1)
 
-    # For more explanation, see file docs/ricgraph_install_configure.md,
-    # section RICGRAPH_NODEADD_MODE.
-    RICGRAPH_NODEADD_MODE = config['Ricgraph']['ricgraph_nodeadd_mode']
-    if RICGRAPH_NODEADD_MODE != 'strict' and RICGRAPH_NODEADD_MODE != 'lenient':
-        print('Ricgraph initialization: error, unknown value "' + RICGRAPH_NODEADD_MODE
-              + '" for ricgraph_nodeadd_mode in Ricgraph ini file, exiting.')
-        exit(1)
-    else:
-        print('Ricgraph is using "' + RICGRAPH_NODEADD_MODE + '" for ricgraph_nodeadd_mode.')
-except KeyError:
-    print('Ricgraph initialization: error, ricgraph_properties_standard and/or')
-    print('  ricgraph_properties_hidden and/or ricgraph_properties_additional and/or ricgraph_nodeadd_mode')
-    print('  not found in Ricgraph ini file, exiting.')
+# For more explanation, see file docs/ricgraph_install_configure.md,
+# section RICGRAPH_NODEADD_MODE.
+RICGRAPH_NODEADD_MODE = get_configfile_key(section='Ricgraph', key='ricgraph_nodeadd_mode')
+if RICGRAPH_NODEADD_MODE != 'strict' and RICGRAPH_NODEADD_MODE != 'lenient':
+    print('Ricgraph initialization: error, not existing or unknown value "' + RICGRAPH_NODEADD_MODE + '"')
+    print('  for "ricgraph_nodeadd_mode" in Ricgraph ini')
+    print('  file "' + get_ricgraph_ini_file() + '", exiting.')
     exit(1)
 
-try:
-    GRAPHDB = config['GraphDB']['graphdb']
-    GRAPHDB_HOSTNAME = config['GraphDB']['graphdb_hostname']
-    GRAPHDB_DATABASENAME = config['GraphDB']['graphdb_databasename']
-    GRAPHDB_USER = config['GraphDB']['graphdb_user']
-    GRAPHDB_PASSWORD = config['GraphDB']['graphdb_password']
-    GRAPHDB_SCHEME = config['GraphDB']['graphdb_scheme']
-    GRAPHDB_PORT = config['GraphDB']['graphdb_port']
-    if GRAPHDB == '' or GRAPHDB_HOSTNAME == '' or GRAPHDB_DATABASENAME == '' \
-       or GRAPHDB_USER == '' \
-       or GRAPHDB_PASSWORD == '' or GRAPHDB_SCHEME == '' or GRAPHDB_PORT == '':
-        print('Ricgraph initialization: error, one or more of the GraphDB parameters '
-              + 'empty in Ricgraph ini file, exiting.')
-        exit(1)
-    GRAPHDB_URL = '{scheme}://{hostname}:{port}'.format(scheme=GRAPHDB_SCHEME,
-                                                        hostname=GRAPHDB_HOSTNAME,
-                                                        port=GRAPHDB_PORT)
-except KeyError:
-    print('Ricgraph initialization: error, one or more of GraphDB parameters '
-          + 'not found in Ricgraph ini file, exiting.')
+print('Ricgraph is using "' + RICGRAPH_NODEADD_MODE + '" for "ricgraph_nodeadd_mode".')
+
+GRAPHDB = get_configfile_key(section='GraphDB', key='graphdb')
+GRAPHDB_HOSTNAME = get_configfile_key(section='GraphDB', key='graphdb_hostname')
+GRAPHDB_DATABASENAME = get_configfile_key(section='GraphDB', key='graphdb_databasename')
+GRAPHDB_USER = get_configfile_key(section='GraphDB', key='graphdb_user')
+GRAPHDB_PASSWORD = get_configfile_key(section='GraphDB', key='graphdb_password')
+GRAPHDB_SCHEME = get_configfile_key(section='GraphDB', key='graphdb_scheme')
+GRAPHDB_PORT = get_configfile_key(section='GraphDB', key='graphdb_port')
+if GRAPHDB == '' or GRAPHDB_HOSTNAME == '' or GRAPHDB_DATABASENAME == '' \
+   or GRAPHDB_USER == '' or GRAPHDB_PASSWORD == '' \
+   or GRAPHDB_SCHEME == '' or GRAPHDB_PORT == '':
+    print('Ricgraph initialization: error, one or more of the GraphDB parameters')
+    print('  not existing or empty in Ricgraph ini')
+    print('  file "' + get_ricgraph_ini_file() + '", exiting.')
     exit(1)
 
+GRAPHDB_URL = '{scheme}://{hostname}:{port}'.format(scheme=GRAPHDB_SCHEME,
+                                                    hostname=GRAPHDB_HOSTNAME,
+                                                    port=GRAPHDB_PORT)
+
 # Make sure DataFrames are printed with all columns on full width
 pandas.set_option('display.max_columns', None)
 pandas.set_option('display.width', 500)
+# To prevent warning
+# "FutureWarning: Downcasting behavior in `replace` is deprecated and will be removed
+# in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`.
+# To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`"
+pandas.set_option('future.no_silent_downcasting', True)

{ricgraph-2.8 → ricgraph-2.9/ricgraph.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ricgraph
-Version: 2.8
+Version: 2.9
 Summary: Ricgraph - Research in context graph
 Author: Rik D.T. Janssen
 Project-URL: Website, https://www.ricgraph.eu