Skip to content

Potential fix for code scanning alert no. 2: Uncontrolled data used in path expression #36

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
ilesinge wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

Potential fix for code scanning alert no. 2: Uncontrolled data used in path expression #36

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 9 additions & 6 deletions shabda/dj.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
from functools import partial
import random
import os
import re
import asyncio
import urllib

Expand Down Expand Up @@ -81,8 +82,10 @@ def list(

async def speak(self, word, language, gender):
"""Speak a word"""
# Only allow safe characters: letters, digits, underscore, dash
language_sanitized = re.sub(r'[^\w\-]', '', language)
sampleset = SampleSet(word, TTS, self.speech_samples_path)
existing_samples = sampleset.list(language=language, gender=gender)
existing_samples = sampleset.list(language=language_sanitized, gender=gender)
if len(existing_samples) > 0:
return True
word_dir = sampleset.dir()
Expand All @@ -94,10 +97,10 @@ async def speak(self, word, language, gender):
else:
ssml_gender = texttospeech.SsmlVoiceGender.MALE

voice_name = chatter.pick_voice(language, ssml_gender, client)
voice_name = chatter.pick_voice(language_sanitized, ssml_gender, client)

# mini hack
if language == "en-GB" and gender == "f":
if language_sanitized == "en-GB" and gender == "f":
voice = texttospeech.VoiceSelectionParams(
name="en-GB-Neural2-A",
language_code="en-GB",
Expand All @@ -107,21 +110,21 @@ async def speak(self, word, language, gender):
# pitch=-4
else:
voice = texttospeech.VoiceSelectionParams(
name=voice_name, language_code=language
name=voice_name, language_code=language_sanitized
)
audio_config = texttospeech.AudioConfig(
audio_encoding=texttospeech.AudioEncoding.LINEAR16,
)
response = client.synthesize_speech(
input=synthesis_input, voice=voice, audio_config=audio_config
)
filepath = word_dir + "/" + word + "_" + language + "_" + gender + ".wav"
filepath = word_dir + "/" + word + "_" + language_sanitized + "_" + gender + ".wav"
with open(filepath, "wb") as out:
out.write(response.audio_content)
sound = Sound(
speechsound={
"gender": gender,
"language": language,
"language": language_sanitized,
"file": filepath,
}
)
Expand Down