eightysteele

[ERROR   ] [WorkerThread-0] WorkerThread:
Traceback (most recent call last):
  File "/home/eighty/Dropbox/projects/lib/python/google_appengine/google/appengine/tools/adaptive_thread_pool.py", line 176, in WorkOnItems
    status, instruction = item.PerformWork(self.__thread_pool)
  File "/home/eighty/Dropbox/projects/lib/python/google_appengine/google/appengine/tools/bulkloader.py", line 764, in PerformWork
    transfer_time = self._TransferItem(thread_pool)
  File "/home/eighty/Dropbox/projects/lib/python/google_appengine/google/appengine/tools/bulkloader.py", line 933, in _TransferItem
    self.content = self.request_manager.EncodeContent(self.rows)
  File "/home/eighty/Dropbox/projects/lib/python/google_appengine/google/appengine/tools/bulkloader.py", line 1392, in EncodeContent
    entity = loader.create_entity(values, key_name=key, parent=parent)

eightysteele

simplejson.dumps(dict(a=1,b=2))
'{"a": 1, "b": 2}'

eightysteele

[dict(cellkey=k, doc=simplejson.dumps(cells[k])) for k in cells.keys()]

eightysteele

cells = dict((k, simplejson.dumps(v)) for k,v in cells.iteritems())

eightysteele

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

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

$ 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

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

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

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)