# -*- coding: utf-8 -*- """ invenio_tools.inveniostore """ import httplib import json import re import time import urllib from exception import CdsException 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") MSG_HTTP_ERROR = "HTTP Error" MSG_NO_IDS = "Invalid list of record identifiers" MSG_WRONG_KEYWORD = "Invalid keyword argument" # maximum number of ids to be collected at once. # The value of 200 is the maximum value authorized using cds.cern.ch N_IDS = 200 REG_IDS_OK = re.compile("^\[[\d, ]*\]$") class InvenioStore(object): """Class to dialogue with `invenio `_ store. The basic ingredients of the dialogue are: * the *request* which is an URL. * the *response* which is an XML string compliant with the `MARC `_ standard. """ def __init__(self, host="cds.cern.ch"): """ Args: host (str): possible values are ``cds.cern.ch`` or ``inspirehep.net``. """ self._host = host self._url = None self._try = 0 def interogate(self, url): """Interrogate the store using the *URL*. Args: url (unicode): URL string Returns: unicode: the HTTP response Raises: CdsException: when the server return an HTTP error five consecutive time. """ self._url = url self._try += 1 fi = urllib.urlopen(url) code = fi.getcode() data = fi.read() # the server is busy or return error wait one minute an retry. # the number of trial is limited to 5 if code == httplib.SERVICE_UNAVAILABLE or code != httplib.OK: if self._try == 5: raise CdsException("%s %s" % (MSG_HTTP_ERROR, code)) time.sleep(60) self.interogate(url) return data def get_ids(self, **kwargs): """Return a list of *record id* matching search criteria. Search criteria are defined by the keywords arguments: 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): 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). The complete list of keyword arguments can be found at http://invenio-demo.cern.ch/help/hacking/search-engine-api. Returns: list: a list of numbers. The list is empty when the request failed on the server. Raises: CdsException: when a keyword argument is invalid or when the server return an invalid list of ids. """ 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 recuperate the complete list of ids we have to get 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. # Thy have no effect on inspirehep.net. kwargs["of"] = "id" kwargs["rg"] = N_IDS kwargs["jrec"] = -N_IDS while scan: self._try = 0 kwargs["jrec"] += N_IDS params = urllib.urlencode(kwargs) url = "http://%s/search?%s" % (self._host, params) rep = self.interogate(url) # check that the list of ids is well form # [1291068, 1352722, 1376692, 1454870, 1492807] or [1493820] or [] if REG_IDS_OK.match(rep): li = json.loads(rep) ids.extend(li) else: raise CdsException(MSG_NO_IDS) 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: unicode: the XML string is compliant with the `MARC `_ standard. Use Marc12.__call__ to decode it. Raises: CdsException: when the server return an HTTP error. """ self._try = 0 url = "http://%s/record/%s/export/xm" % (self._host, rec_id) return self.interogate(url) def last_search_url(self): """ Returns: unicode: the URL used in the last search. """ return self._url def search(self, **kwargs): """Return records matching the keyword arguments. Keyword Args: 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. The keyword arguments are those of the invenio web interface. Details are in http://invenio-demo.cern.ch/help/hacking/search-engine-api. Returns: unicode: the format of the string (HTML, XML) depend on the keyword **of**. For MARC12 format use **xm**. Deprecated: the method get_ids coupled with get_record is much more efficient. """ for k in kwargs: if k not in CDS_SEARCH_KEYS: raise CdsException(MSG_WRONG_KEYWORD, k) kwargs["action_search"] = "Search" params = urllib.urlencode(kwargs) url = "http://%s/search?%s" % (self._host, params) return self.interogate(url) def search_year(self, collection, year, of="xm", rg=10, so="d"): """Search records for given *collection* and for a given *year*. Args: collection (str): year (int): 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, "xm" means MARC XML format, "t" means plain text output, "id" means no output at all but to return list of recIDs found. (Suitable for high-level API.) rg (int): limit on the number of output records. so (str): sort order ("a"=ascending, "d"=descending). Returns: unicode): the format of the string HTML, XML depends on the keyword **of**. Use **xm** for MARC XML. """ return self.search(c=collection, f="year", ln="en", of=of, p=year, rg=rg, sf="year", so=so)