def get_file_content():
if len(G_file_no_dict) == 0:
print convert("索引号列表为空")
conn = get_connection()
if conn != 0:
cursor = conn.cursor()
result_file_name = (G_path_prefix + r"result.txt").decode('utf-8').encode('cp936')
file = open( result_file_name, "a+" )
for file_uniq_no in G_file_no_dict.keys():
sql = "select d.mr_content from jhmr_file_content_TEXT d where d.file_unique_id = '%s'" % file_uniq_no
#print sql
try:
cursor.execute(sql)
content_list = get_content_from_lob(cursor)
except cx_Oracle.DatabaseError:
print convert("获取病历内容失败")
return 0
for item in content_list:
print G_file_no_dict[file_uniq_no]
file.write(G_file_no_dict[file_uniq_no])
file.write("\r\n")
item = item.decode('cp936').encode('utf-8')
file.write(item)
file.write("\r\n")
close_connection(conn)
file.close()
def loadAnagrams():
print("Loading Anagrams...")
stime = time.time()
file = open(anagramsFile, "r")
for line in file:
words = re.split("[^a-zA-Z0-9]", line)
n = len(words)
key = words[0]
l = set()
for i in xrange(2, n):
l.add(words[i])
anagrams[key] = filter(None, l)
file.close()
print("Anagrams loaded: %d" % len(anagrams))
print("Time taken: %s" % (time.time() - stime))
def export_ramp_color_library(library, library_rules):
dir_path = tempfile.mkdtemp(suffix='', prefix='tmp-library-')
for library_rule in library_rules:
try:
resource_path = dir_path + "/" + library_rule + "/"
os.makedirs(resource_path)
i = 0
for color_ramp in library_rules[library_rule]:
file = open(
resource_path + "/color_ramp-" + color_ramp.name + "-" +
str(i) + ".rmf", 'w+')
file.write(
build_library_color_ramp(color_ramp.name,
color_ramp.definition))
file.close()
i = i + 1
except Exception as e:
raise e
buffer = StringIO.StringIO()
z = zipfile.ZipFile(buffer, "w")
relroot = dir_path
for root, dirs, files in os.walk(dir_path):
rel_path = os.path.relpath(root, relroot)
if rel_path != ".":
z.write(root, os.path.relpath(root, relroot))
for file in files:
filename = os.path.join(root, file)
if os.path.isfile(filename):
arcname = os.path.join(os.path.relpath(root, relroot), file)
z.write(filename, arcname)
z.close()
buffer.seek(0)
response = HttpResponse(content_type='application/zip; charset=utf-8')
response[
'Content-Disposition'] = 'attachment; filename=' + library.name + '.zip'
response.write(buffer.read())
utils.__delete_temporaries(dir_path)
return response
def precomputeFromNLTK():
"""
precompute with nltk's corpus as wordbase
"""
language = set()
print(len(words.words()))
for word in words.words():
word = word.lower()
sortW = "".join(char for char in sorted(word))
if sortW[0] >= "a" and sortW[0] <= "z":
word = word + ":" + sortW
language.add(word)
print("Loaded %d words from NLTK wordnet" % (len(language)))
buckets = [set() for x in xrange(25)]
for word in language:
buckets[len(word) / 2].add(word)
count = 0
for word in language:
if count % 1000 == 0:
print("Done for %d words" % count)
count += 1
sortedW = word.split(":")[1]
if sortedW not in nltkHashMap:
nltkHashMap[sortedW] = set()
for word2 in buckets[len(sortedW)]:
sortedW2 = word2.split(":")[1]
if sortedW == sortedW2:
nltkHashMap[sortedW].add(word2.split(":")[0])
file = open(nltkAnagramsFile, "w")
file.truncate()
count = 0
for anagrams, listOfAnagrams in nltkHashMap.items():
if count % 1000 == 0:
print("%d anagram lists written" % count)
file.flush()
count += 1
file.write("%s:%s\n" % (anagrams, listOfAnagrams))
file.close()
print("Precomputation with NLTK done")
def close(self):
file.close(self)
self.__class__.open_files.remove(self)
yesterday_emails = list()
#gather emails of yesterday
file = open(log_path, 'r')
for line in file.readlines():
date = line.split(" ")[0].strip()
if (date == yesterday_date.strip()):
yesterday_emails.append(line)
if (date == today_date.strip()):
break
file.close()
# write yesterday emails to a file
yesterday_emails_path = tmp_path + '_yesterday_mails'
file = open(yesterday_emails_path, 'w')
for line in yesterday_emails:
file.write(line + "\n")
file.close()
# now its time to find spammers
possible_spammers_file_path = tmp_path + '_spammers'
cmd = "awk \'$3 ~ /^cwd/{print $3}\' /tmp/_yesterday_mails | sort | uniq -c | sed \"s|^ *||g\"| sort -nr "
def spider_closed(self, spider):
self.exporter.finish_exporting()
file = self.files.pop(spider)
file.close()
pass
def close(self):
file.close(self)
self.__class__.open_files.remove(self)
