def _crawl_tree (self, parse_node):
"""
Recursively crawls the tree building a unique list of terms and the
node
"""
# Build our list of term contexts that point to a term. Once done,
# uniqify the list by looking at the term values.
#
# NOTE: There must be a better way to do this, also, so we can
# create more contexts easily without making a large amount of
# modifications.
terms = [
[TermModel.get_word_id(token), context_id_map['docstring']] \
for token in list(set(tokenize(parse_node.docstring)))
]
terms.extend([
[TermModel.get_word_id(token), context_id_map['comment']] \
for token in list(set(tokenize(parse_node.comments)))
])
terms.extend([
[TermModel.get_word_id(token), context_id_map['library']] \
for token in parse_node.imports
])
if parse_node.type == 'Class':
terms.append([
TermModel.get_word_id(token),
context_id_map['class']
])
terms = uniqify_terms(terms)
# NOTE: We copy the list of terms so that we dont modify the list
# of terms for this treenode as we navigate upwards. Therefore,
# unique terms from other nodes wont end up in the unique terms for
# this node.
node = dict(
name=parse_node.name,
type=parse_node.type,
source=parse_node.source,
signals=parse_node.signals,
terms=terms[:],
children = [],
)
for child in parse_node.children:
child_node, child_terms = self._crawl_tree(child)
node['children'].append(child_node)
terms.extend(child_terms)
return node, uniqify_terms(terms)
def update (self):
"""
The final phase is to save all relationships between the created
documents and terms.
NOTE: We don't have transactional support, so, if this fails, we
will have a bunch fo documents with missing Term->Document
pointers.
"""
for term, docs in self.terms.iteritems():
TermModel.update_doclist(term, docs)
logging.debug('Updated doc_list for term id %s with %d docs' % (
term,
len(docs)
))
logging.info('Completed updating Term->Document list')
def _get_documents (self, tokens):
"""
Returns a list of unique documents that are sorted by their score
from highest to lowest.
"""
# Transform our list of token pairs (context_id, term_id) into a
# map of term_id -> context_id. We do this for optimizations
# further down the road.
token_map = dict()
for context_id, term_id in tokens:
token_map[term_id] = context_id
# Retrieve our dictionary of Term -> [(doc,context), ...] from the
# database
start_time = time.time()
term_doc_map = TermModel.get_term_doc_map(token_map.keys())
logging.debug('Took %.4fs to retrieve data structure for %d terms' % (
time.time() - start_time,
len(term_doc_map)
))
# Once we have our dictionary mapping we need to group based on
# document id's and their terms. We will build a dictionary mapping
# document id to a list of terms and the context in which those
# terms occur. map[DOC_ID] = [[context_id, term_id], ...]
#
# At this point we will also remove all document ids if given
# contexts are specified in our token list. This will handle the
# case were a user has specified that a term must occur in a
# certain context.
start_time = time.time()
doc_term_map = self._organize(token_map, term_doc_map)
logging.debug('Took %.4fs to rearrange data into structure for %d docs' % (
time.time() - start_time,
len(doc_term_map)
))
# Recall document data for each document relevant to our query,
# then we build a map structure for mapping doc_id -> doc_data
start_time = time.time()
docs = self._retrieve_documents(doc_term_map)
logging.debug('Took %.4fs to retrieve %d document data from database' % (
time.time() - start_time,
len(docs)
))
return docs
def translate (query):
"""
Returns a list of pairs (token-type-id, token-id) using the lexicon
provided through the TermModel class. Takes in a non-sanitized query
string.
Uses process and match functionality of this module.
"""
# Convert query stirng into list of term type and their sanitized
# values
sanitized = process(query)
logging.debug('Tokenized query "%s" into %s' % (
query,
sanitized
))
# Converts term types and terms into their corresponding integer values
# from the database and lexicon.
return map(
lambda x: (context_id_map[x[0]], TermModel.get_word_id(x[1])),
sanitized
)
