eightysteele

STOP_WORDS = ['a', 'able', 'about', 'across', 'after', 'all', 'almost', 'also', 'am', 'among', 'an', 'and', 'any', 'are', 'as', 'at', 'be', 'because', 'been', 'but', 'by', 'can', 'cannot', 'could', 'dear', 'did', 'do', 'does', 'either', 'else', 'ever', 'every', 'for', 'from', 'get', 'got', 'had', 'has', 'have', 'he', 'her', 'hers', 'him', 'his', 'how', 'however', 'i', 'if', 'in', 'into', 'is', 'it', 'its', 'just', 'least', 'let', 'like', 'likely', 'may', 'me', 'might', 'most', 'must', 'my', 'neither', 'no', 'nor', 'not', 'of', 'off', 'often', 'on', 'only', 'or', 'other', 'our', 'own', 'rather', 'said', 'say', 'says', 'she', 'should', 'since', 'so', 'some', 'than', 'that', 'the', 'their', 'them', 'then', 'there', 'these', 'they', 'this', 'tis', 'to', 'too', 'twas', 'us', 'wants', 'was', 'we', 'were', 'what', 'when', 'where', 'which', 'while', 'who', 'whom', 'why', 'will', 'with', 'would', 'yet', 'you', 'your']

eightysteele

STOP_CONCEPTS = ['acceptednameusageid', 'accessrights', 'basisofrecord', 'collectionid', 'coordinateprecision', 'coordinateuncertaintyinmeters', 'datasetid', 'dateidentified', 'day', 'decimallatitude', 'decimallongitude', 'disposition', 'enddayofyear', 'eventdate', 'eventid', 'eventtime', 'fieldnotes', 'footprintspatialfit', 'footprintsrs', 'footprintwkt', 'geologicalcontextid', 'georeferenceremarks', 'georeferenceverificationstatus', 'highergeographyid', 'identificationid', 'individualcount', 'individualid', 'institutionid', 'language', 'locationid', 'maximumdepthinmeters', 'maximumdistanceabovesurfaceinmeters', 'maximumelevationinmeters', 'minimumdepthinmeters', 'minimumdistanceabovesurfaceinmeters', 'minimumelevationinmeters', 'modified', 'month', 'nameaccordingtoid', 'namepublishedinid', 'nomenclaturalcode', 'occurrencedetails', 'occurrenceid', 'originalnameusageid', 'parentnameusageid', 'pointradiusspatialfit', 'rights', 'rightsholder', 'scientificnameid', 'startdayofyear', 'taxonconceptid', 'taxonid', '

eightysteele

>>> sp = []
>>> for x in props.split('\n'):
...     if x.split()[0] == 'X':
...             sp.append(x.split()[1].lower())
... 
>>> sp.sort()
>>> sp

eightysteele

def add_dynamic_properties(input_dict, instance, bulkload_state_copy):    
    for key,value in input_dict.iteritems():
        if key in PROPERTIES_STOP_CONCEPTS:
            continue
        try:
            instance[key] = value.lower()
        except:
            pass
    instance.pop('rechash')
    instance.pop('reckey')

eightysteele

def get_corpus_list():
    def wrapper(value, bulkload_state):
        """Returns list of unique words in the entire record.
        
        Arguments:
            value - the JSON encoded record
        """
        d = bulkload_state.current_dictionary
        recjson = simplejson.loads(value)
        d.update(recjson)

eightysteele

# Stop words not to index
STOP_WORDS = [
    'a', 'able', 'about', 'across', 'after', 'all', 'almost', 'also', 'am', 
    'among', 'an', 'and', 'any', 'are', 'as', 'at', 'be', 'because', 'been', 
    'but', 'by', 'can', 'cannot', 'could', 'dear', 'did', 'do', 'does', 'either', 
    'else', 'ever', 'every', 'for', 'from', 'get', 'got', 'had', 'has', 'have', 
    'he', 'her', 'hers', 'him', 'his', 'how', 'however', 'i', 'if', 'in', 'into', 
    'is', 'it', 'its', 'just', 'least', 'let', 'like', 'likely', 'may', 'me', 
    'might', 'most', 'must', 'my', 'neither', 'no', 'nor', 'not', 'of', 'off', 
    'often', 'on', 'only', 'or', 'other', 'our', 'own', 'rather', 'said', 'say', 

eightysteele

DWC_ALIAS = dict(
   acceptedNameUsage='anu',
   acceptedNameUsageID='anuid',
   accessRights='ar',
   associatedMedia='am',
   associatedOccurrences='ao',
   associatedReferences='ar',
   associatedSequences='as',
   associatedTaxa='at',
   basisOfRecord='br',

eightysteele

$ fdisk -l

WARNING: GPT (GUID Partition Table) detected on '/dev/sda'! The util fdisk doesn't support GPT. Use GNU Parted.


Disk /dev/sda: 250.1 GB, 250059350016 bytes
255 heads, 63 sectors/track, 30401 cylinders
Units = cylinders of 16065 * 512 = 8225280 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
I/O size (minimum/optimal): 512 bytes / 512 bytes

eightysteele

class Cell(model.Model):
    """Models a CouchDB cell document.

    key_name - The cell key (e.g., 1-2).
    """
    rev = model.StringProperty('r')
    coords = model.StringProperty('c')
    varvals = model.TextProperty('v')

    def __eq__(self, other):

eightysteele

 @classmethod
 def create(cls, xmin, ymax, xmax, ymin):
     return cls(Point(xmin, ymax), Point(xmax, ymin))