""" invenio_tools.inveniostore """ import requests from .exception import CdsException from requests.adapters import HTTPAdapter CDS_SEARCH_KEYS = ("req", "cc", "c", "ec", "p", "f", "rg", "sf", "so", "sp", "rm", "of", "ot", "as", "p1", "f1", "m1", "op1", "p2", "f2", "m2", "op2", "p3", "f3", "m3", "sc", "jrec", "recid", "recidb", "sysno", "id", "idb", "sysnb", "action", "d1", "d1y", "d1m", "d1d", "d2", "d2y", "d2m", "d2d", "dt", "verbose", "ap", "ln", "ec") CDS = ("cds", "cds.cern.ch") INS = ("inspirehep", "inspirehep.net") MSG_HTTP_DECODE = "Fail to decode HTTP response" MSG_HTTP_ERROR = "HTTP Error" MSG_NO_IDS = "Invalid list of record identifiers" MSG_NO_SHELF = "No shelf %s for store %s" MSG_NOT_IMPLEMENTED = "Method '%' not implemented for store '%' and shelf '%'<" MSG_WRONG_KEYWORD = "Invalid keyword argument" # maximum number of identifiers to be collected at once. # The value of 200 is the maximum value authorised using cds.cern.ch N_IDS = 200 class InvenioStore(object): """Class to dialogue with `invenio `_ store. The class provides methods to request: * a list of identifier satisfying search criteria. * a record identified by its id. Args: host (str): possible values are ``cds``, ``cds.cern.ch``,``inspirehep`` or ``inspirehep.net`` shelf (str): section of the store. It depends on the host. Possible values are ``None``, ``literature``, ``conferences`` and ``institutions`` +----------------+--------------+-----------------------------+ | host | shelf | base API | +----------------+--------------+-----------------------------+ | cds.cern.ch | None | https://cds.cern.ch/ | +----------------+--------------+-----------------------------+ | inspirehep.net | None | https://old.inspirehep.net/ | | inspirehep.net | literature | https://old.inspirehep.net/ | | inspirehep.net | conferences | https://inspirehep.net/ | | inspirehep.net | institutions | https://old.inspirehep.net/ | +----------------+--------------+-----------------------------+ """ def __init__(self, host="cds", shelf=None): self._shelf = shelf self._url = None # base url for the API if host in CDS and shelf is None: api_search = "https://cds.cern.ch/search" api_record = "https://cds.cern.ch/record" host = "cds.cern.ch" elif host in INS and shelf in (None, "literature", "institutions"): api_search = "https://old.inspirehep.net/search" api_record = "https://old.inspirehep.net/record" host = "old.inspirehep.net" elif host in INS and shelf in ("conferences",): api_search = None api_record = "https://inspirehep.net/api/conferences" host = "inspirehep.net" else: raise CdsException(MSG_NO_SHELF % (shelf, host)) # start a session, a persistent connection with the server # let the session handle the number of retry session = requests.Session() session.mount(f"https://{host}", HTTPAdapter(max_retries=3)) self._api_search = api_search self._api_record = api_record self._host = host self._session = session def __del__(self): # close the session self._session.close() def interogate(self, url, timeout=10, **kwargs): """Interrogate the store using the *URL*. It is retry several time when the service is not available. Args: url (str): the URL string depends on the store and on the invenio version which is ruuning, *e.g.*:: * ``https://cds.cern.ch/record/123456/of=recjson`` * ``https://cds.cern.ch/search?of=id&.... timeout (float): timeout for the HTTP request Keyword Args: The keyword arguments are those of the invenio web interface. Details are in https://inspirehep.net/help/hacking/search-engine-api Examples how to use the old invenio API: https://inspirehep.net/info/hep/api?ln=fr#json_fnames List of keyword in the JSON record: https://github.com/inspirehep/invenio/blob/prod/modules/bibfield/etc/atlantis.cfg req (str): mod_python Request class instance. cc (str): current collection (*e.g.* "ATLAS"). The collection the user started to search/browse from. c (str): collection list (*e.g.* ["Theses", "Books"]). The collections user may have selected/deselected when starting to search from **cc**. ec (str): external collection list (*e.g.* ["CiteSeer", "Google"]). The external collections may have been selected/deselected by the user. p (str): pattern to search for (*e.g.* "ellis and muon or kaon"). f (str): field to search within (*e.g.* "author"). rg (int): records in groups of (*e.g.* "10"). Defines how many hits per collection in the search results page are displayed. sf (str): sort field (*e.g*. "title"). so (str): sort order ("a"=ascending, "d"=descending). sp (str): sort pattern (*e.g.* "CERN-") -- in case there are more values in a sort field, this argument tells which one to prefer. rm (str): ranking method (*e.g.* "jif"). Defines whether results should be ranked by some known ranking method. of (str): output format (*e.g.* "hb"). Usually starting "h" means HTML output (and "hb" for HTML brief, "hd" for HTML detailed), "x" means XML output, "t" means plain text output, "id" means no output at all but to return list of recIDs found. (Suitable for high-level API.). ot (str): output only these MARC tags (*e.g.* "100,700,909C0b"). Useful if only some fields are to be shown in the output, e.g. for library to control some fields. as (int): advanced search ("0" means no, "1" means yes). Whether search was called from within the advanced search interface. p1 (str): first pattern to search for in the advanced search interface. Much like **p**. f1 (str): first field to search within in the advanced search interface. Much like **f**. m1 (str): first matching type in the advanced search interface. ("a" all of the words, "o" any of the words, "e" exact phrase, "p" partial phrase, "r" regular expression). op1 (str): first operator, to join the first and the second unit in the advanced search interface. ("a" add, "o" or, "n" not). p2 (str): second pattern to search for in the advanced search interface. Much like **p**. f2 (str): second field to search within in the advanced search interface. Much like **f**. m2 (str): second matching type in the advanced search interface. ("a" all of the words, "o" any of the words, "e" exact phrase, "p" partial phrase, "r" regular expression). op2 (str): second operator, to join the second and the third unit in the advanced search interface. ("a" add, "o" or, "n" not). p3 (str): third pattern to search for in the advanced search interface. Much like **p**. f3 (str): third field to search within in the advanced search interface. Much like **f**. m3 (str): third matching type in the advanced search interface. ("a" all of the words, "o" any of the words, "e" exact phrase, "p" partial phrase, "r" regular expression). sc (int): split by collection ("0" no, "1" yes). Governs whether we want to present the results in a single huge list, or splitted by collection. jrec (int): jump to record (*e.g.* "234"). Used for navigation inside the search results. recid (int): display record ID (*e.g.* "20000"). Do not search/browse but go straight away to the Detailed record page for the given recID. recidb (int): display record ID bis (*e.g.* "20010"). If greater than "recid", then display records from recid to recidb. Useful for example for dumping records from the database for reformatting. sysno (str): display old system SYS number (*e.g.* ""). If you migrate to Invenio from another system, and store your old SYS call numbers, you can use them instead of recid if you wish so. id (int): the same as recid, in case recid is not set. For backwards compatibility. idb (int): the same as recid, in case recidb is not set. For backwards compatibility. sysnb (str): the same as sysno, in case sysno is not set. For backwards compatibility. action (str): action to do. "SEARCH" for searching, "Browse" for browsing. Default is to search. d1 (str): first datetime in full YYYY-mm-dd HH:MM:DD format (*e.g.* "1998-08-23 12:34:56"). Useful for search limits on creation/modification date (see "dt" argument below). Note that "d1" takes precedence over d1y, d1m, d1d if these are defined. d1y (int): first date's year (*e.g.* "1998"). Useful for search limits on creation/modification date. d1m (int): first date's month (*e.g.* "08"). Useful for search limits on creation/modification date. d1d (int): first date's day (*e.g.* "23"). Useful for search limits on creation/modification date. d2 (str): second datetime in full YYYY-mm-dd HH:MM:DD format (*e.g.* "1998-09-02 12:34:56"). Useful for search limits on creation/modification date (see "dt" argument below). Note that "d2" takes precedence over d2y, d2m, d2d if these are defined. d2y (int): second date's year (*e.g.* "1998"). Useful for search limits on creation/modification date. d2m (int): second date's month (*e.g.* "09"). Useful for search limits on creation/modification date. d2d (int): second date's day (*e.g.* "02"). Useful for search limits on creation/modification date. dt (str): first and second date's type (*e.g.* "c"). Specifies whether to search in creation dates ("c") or in modification dates ("m"). When dt is not set and d1* and d2* are set, the default is "c". verbose (int): verbose level (0=min, 9=max). Useful to print some internal information on the searching process in case something goes wrong. ap (int): alternative patterns (0=no, 1=yes). In case no exact match is found, the search engine can try alternative patterns e.g. to replace non-alphanumeric characters by a boolean query. ap defines if this is wanted. ln (str): language of the search interface (*e.g.* "en"). Useful for internationalization. timeout (float): timeout for the HTTP request Returns: requests.Response: Raises: RequestException: something went wrong within the HTTP dialog """ self._url = url r = self._session.get(url, timeout=timeout, params=kwargs) r.raise_for_status() return r def get_ids(self, **kwargs): """Return a list of *record id* matching search criteria. Search criteria are defined by the keywords arguments. The complete list of keyword arguments can be found at https://inspirehep.net/help/hacking/search-engine-api Examples how to use the invenio API: https://inspirehep.net/info/hep/api?ln=fr#json_fnames List of keyword in the JSON record: https://github.com/inspirehep/invenio/blob/prod/modules/bibfield/etc/atlantis.cfg Keyword Args: cc (str): current collection (e.g. "ATLAS Papers"). The collection the user started to search/browse from. p (str): pattern to search for (e.g. "ellis and muon or kaon"). f (str): field to search within (e.g. "author"). p1 (str): first pattern to search for in the advanced search interface. Much like **p**. f1 (str): first field to search within in the advanced search interface. Much like **f**. m1 (str): first matching type in the advanced search interface. ("a" all of the words, "o" any of the words, "e" exact phrase, "p" partial phrase, "r" regular expression). op1 (str): first operator, to join the first and the second unit in the advanced search interface. ("a" add, "o" or, "n" not). p2 (str): s econd pattern to search for in the advanced search interface. Much like **p**. f2 (str): second field to search within in the advanced search interface. Much like **f**. m2 (str): second matching type in the advanced search interface. ("a" all of the words, "o" any of the words, "e" exact phrase, "p" partial phrase, "r" regular expression). op2 (str): second operator, to join the second and the third unit in the advanced search interface. ("a" add, "o" or,"n" not). p3 (str): third pattern to search for in the advanced search interface. Much like **p**. f3 (str): third field to search within in the advanced search interface. Much like **f**. m3 (str): third matching type in the advanced search interface. ("a" all of the words, "o" any of the words, "e" exact phrase, "p" partial phrase, "r" regular expression). Returns: list: * A list of numbers. * The list is empty when the request failed on the server. Raises: CdsException:: * keyword argument is invalid; * the server return an HTTP error; * JSON object can't be decoded * not well formed list of ids. """ host = self._host if host != "old.inspirehep.net": msg = MSG_NOT_IMPLEMENTED % ("get_ids", host, self._shelf) raise CdsException(msg) for k in kwargs: if k not in CDS_SEARCH_KEYS: raise CdsException(MSG_WRONG_KEYWORD, k) ids = [] scan = True # NOTE: the number of ids which can be collected at once is limited # to 10 on cds.cern.ch since the invenio version 1.1.3.1106 (Jun 2014) # Therefore to get the complete list of ids we have to scan them # by block of 200. The later is the maximum value allowed by cds. # We use the parameter rg and jrec to steer the scan. # They have no effect on inspirehep.net. kwargs["of"] = "id" kwargs["rg"] = N_IDS kwargs["jrec"] = -N_IDS while scan: kwargs["jrec"] += N_IDS rep = self.interogate(self._api_search, timeout=30, **kwargs) try: li = rep.json() # check that the list of identifier is well form # [1291068, 1352722, 1376692] or [1493820] or [] if len(list(filter(lambda x: not isinstance(x, int), li))) > 0: raise CdsException(MSG_NO_IDS) ids.extend(li) # trigger when the JSON object cannot be decoded except ValueError as e: raise CdsException(e) if len(li) != N_IDS: scan = False return ids def get_record(self, rec_id): """Retrieve a record defined by its *record id*. Args: rec_id (int): record identifier in the store. Returns: dict: the record data (recjson). Raises: CdsException:: * the server return an HTTP error. * no JSON object could be decoded. """ url = "%s/%s" % (self._api_record, rec_id) kwargs = {} if self._host in ("cds.cern.ch", "old.inspirehep.net"): kwargs = {"of": "recjson"} rep = self.interogate(url, timeout=30, **kwargs) try: li = rep.json() except ValueError: raise CdsException(MSG_HTTP_DECODE) return li[0] def last_search_url(self): """ Returns: str: the URL used in the last search. """ return self._url