Blame view
egs/sprakbanken/s5/local/sprakparser.py
6.58 KB
8dcb6dfcb
first commit
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 |
#!/usr/bin/env python
'''
# Copyright 2013-2014 Mirsk Digital ApS (Author: Andreas Kirkedal)
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# THIS CODE IS PROVIDED *AS IS* BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, EITHER EXPRESS OR IMPLIED, INCLUDING WITHOUT LIMITATION ANY IMPLIED
# WARRANTIES OR CONDITIONS OF TITLE, FITNESS FOR A PARTICULAR PURPOSE,
# MERCHANTABLITY OR NON-INFRINGEMENT.
# See the Apache 2 License for the specific language governing permissions and
# limitations under the License.
Created on Jan 18, 2013
@author: andreas
'''
from __future__ import print_function
import codecs
import os
class Session(object):
delimit = ">-<"
def __init__(self, topfolder, splfile):
self.filestem = splfile.split(".")[0]
self.source = topfolder+ "/" +splfile
splhandle = codecs.open(self.source, "r", "latin-1")
self.set_system_vars(splhandle)
self.set_channel_vars(splhandle)
self.speaker_id = None
self.set_speaker_vars(splhandle)
self. wavdir = False
self.set_path_vars(topfolder, splhandle)
if self.wavdir:
self.extract_record_states(splhandle)
self.extract_validation_states(splhandle)
def extract_record_states(self, handle):
self.record_states = []
for input in handle:
if input.strip() == "":
return
line = input.split(">-<")
if len(line) < 4:
continue
self.record_states.append((line[2],line[5].lower()))
def extract_validation_states(self, handle):
self.validation_states = []
for input in handle:
if input.strip() == "":
return
line = input.split(">-<")
if len(line) < 4:
continue
text = line[0].split("=")[-1]
qua = line[3]
noi = line[4]
snd = line[5]
spc = line[6]
utt = line[7]
dst = line[8]
self.validation_states.append((text, qua, noi, snd, spc, utt, dst))
def set_system_vars(self, handle):
for input in handle:
line = input.strip()
#print("sys")
if "Coding" in line:
self.coding = self.get_vars(line)
elif "Frequency" in line:
self.frequency = self.get_vars(line)
elif "Channels" in line:
self.channels = self.get_vars(line)
elif line == "":
return
else:
pass
def set_speaker_vars(self, handle):
for input in handle:
line = input.strip()
#print("speaker")
if "Speaker" in line:
self.speaker_id = self.get_speaker_vars(line).strip()
elif "Name" in line:
self.name = self.get_speaker_vars(line)
elif "Age" in line:
self.age = self.get_speaker_vars(line)
elif "Sex" in line:
self.gender = self.get_speaker_vars(line)
elif "Youth" in line:
self.youth = self.get_speaker_vars(line)
elif "Dialect" in line:
self.dialect = self.get_speaker_vars(line)
elif line == "":
return
else:
pass
def print_speaker_info(self, path):
filename = self.filestem+ ".speaker_info"
dest = os.path.join(path, filename)
fout = codecs.open(dest, "w", "utf8")
fout.write("Original .spl file:\t" +self.source)
fout.write("
ID:\t" +self.speaker_id)
fout.write("
Name:\t" +self.name)
fout.write("
Age:\t" +self.age)
fout.write("
Gender:\t" +self.gender)
fout.write("
Dialect:\t" +self.dialect)
fout.write("
Origin:\t" +self.youth)
fout.close()
def set_path_vars(self, topfolder, handle):
for input in handle:
#print("path")
line = input.strip()
if "recordings" in line:
self.recordings = self.get_vars(line)
elif "Directory" in line:
self.splpath = self.get_vars(line)[3:].replace("\\", "/") # removes "c:\"
self.wavdir = self.wavpath(topfolder)
elif line == "":
return
else:
pass
def set_channel_vars(self, handle):
for input in handle:
line = input.strip()
if line == "":
return
else:
pass
def create_filename(self, uid, file_ending):
return "{}.{}.{}.{}".format(self.filestem, self.speaker_id, uid, file_ending)
def wavpath(self, topfolder):
prefix, suffix = topfolder.rsplit('/data/', 1)
testpath = os.path.join(prefix, 'speech', suffix)
#testpath = topfolder.replace("data", "speech")
if os.path.exists(testpath):
return os.path.join(testpath, self.filestem)
else:
testpath = os.path.join(prefix, 'Speech', suffix)
return os.path.join(testpath, self.filestem)
def get_vars(self, line):
return line.split("=")[-1]
def get_speaker_vars(self, line) :
vals = self.get_vars(line).split(self.delimit)
return vals[-2]
if __name__ == '__main__':
s = Session("/home/andreas/Desktop/aligned_corpus/da.16kHz.0565-2",
"adb_0565/data/scr0565/06/05650606/r5650555.spl")
print(s)
print(os.getcwd())
print(s.name)
print(s.splpath)
print(s.record_states)
print(s.validation_states)
pass
|