def add_info(files_path, core, core_http):
core.delete(os.path.abspath(files_path))
id_List.Delete_list_path(files_path)
with open(files_path, 'rb') as f:
dicts = []
url = 'http://localhost:8983/solr/info/schema'
text = f.readline()
words = text.strip().split()
# print words
for word in words:
add_field(url, word)
fields = [n.decode('utf-8') for n in text.strip().split()]
# print fields
fields.extend([u'path', u'content', u'id'])
# print fields
for line in f.readlines():
words = [s.decode('utf-8') for s in line.strip().split()]
id_num = id_List.Create_id()
words.extend([
os.path.abspath(files_path).decode('utf-8'),
line.decode('utf-8'), id_num
])
dicts.append(dict(zip(fields, words)))
id_List.Create_list(files_path, id_num, core_http)
core.add(dicts)
def add_desc(files_path, core, core_http):
id_List.Delete_list_path(files_path)
with open(files_path, 'rb') as f:
text = f.read().decode('utf-8')
id_num = id_List.Create_desc_id(files_path)
core.add([{'id': id_num,
'path': os.path.abspath(files_path),
'context': text}])
id_List.Create_list(files_path, id_num, core_http)
def add_txt(files_path, core, core_http):
core.delete(os.path.abspath(files_path))
id_List.Delete_list_path(files_path)
dicts = []
with open(files_path, 'rb') as f:
for i, line in enumerate(f):
words = [s.decode('utf-8') for s in line.strip().split()]
if i == 0:
if len(words) == 4:
fields = ('wav', 'start', 'end', 'text', 'path', 'id')
elif len(words) == 2:
fields = ('wav', 'text', 'path', 'id')
else:
print 'ERROR! ' + files_path + ' is not the correct format!'
return
id_num = id_List.Create_id()
words.extend([os.path.abspath(files_path), id_num])
dicts.append(dict(zip(fields, words)))
id_List.Create_list(files_path, id_num, core_http)
core.add(dicts)
def Delete_info(file_path):
core = pysolr.Solr('http://localhost:8983/solr/info')
core.delete(q='path:"' + file_path +'"')
# find_line = [s for s in id_List if s[1] == file_path]
id_List.Delete_list_path(file_path)