Upload 2 files

urls.py

@@ -0,0 +1,6 @@
+# -*- coding: utf-8 -*-
+"""
+Predefined URLs used to make google translate requests.
+"""
+BASE = 'https://translate.google.com'
+TRANSLATE = 'https://{host}/translate_a/single'

utils.py

@@ -1,37 +1,79 @@
-from pydub import AudioSegment
-#from pydub.utils import mediainfo
-from pydub.utils import make_chunks
-import math
-#flac_audio = AudioSegment.from_file("sample.flac", "flac")
-#flac_audio.export("audio.wav", format="wav")
-def split_audio_wav(filename):
-    myaudio = AudioSegment.from_file(filename , "wav")
-    channel_count = myaudio.channels    #Get channels
-    sample_width = myaudio.sample_width #Get sample width
-    duration_in_sec = len(myaudio) / 1000#Length of audio in sec
-    sample_rate = myaudio.frame_rate
-    print("sample_width=", sample_width) 
-    print("channel_count=", channel_count)
-    print("duration_in_sec=", duration_in_sec) 
-    print("frame_rate=", sample_rate)
-    bit_rate =16  #assumption , you can extract from mediainfo("test.wav") dynamically
-    wav_file_size = (sample_rate * bit_rate * channel_count * duration_in_sec) / 8
-    print("wav_file_size = ",wav_file_size)
-    file_split_size = 40000000  # 40mb OR 40, 000, 000 bytes
-    total_chunks =  wav_file_size // file_split_size
-    #Get chunk size by following method #There are more than one ofcourse
-    #for  duration_in_sec (X) -->  wav_file_size (Y)
-    #So   whats duration in sec  (K) --> for file size of 40Mb
-    #  K = X * 40Mb / Y
-    chunk_length_in_sec = math.ceil((duration_in_sec * 40000000 ) /wav_file_size)   #in sec
-    chunk_length_ms = chunk_length_in_sec * 1000
-    chunks = make_chunks(myaudio, chunk_length_ms)
-    number_chunks=len(chunks)
-    chunks_list=[]
-    #Export all of the individual chunks as wav files
-    for i, chunk in enumerate(chunks):
-        chunk_name = "chunk{0}.wav".format(i)
-        print("exporting", chunk_name)
-        chunk.export(chunk_name, format="wav")
-        chunks_list.append(chunk_name)
-    return chunks_list
+"""A conversion module for googletrans"""
+import json
+import re
+
+
+def build_params(query, src, dest, token, override):
+    params = {
+        'client': 'webapp',
+        'sl': src,
+        'tl': dest,
+        'hl': dest,
+        'dt': ['at', 'bd', 'ex', 'ld', 'md', 'qca', 'rw', 'rm', 'ss', 't'],
+        'ie': 'UTF-8',
+        'oe': 'UTF-8',
+        'otf': 1,
+        'ssel': 0,
+        'tsel': 0,
+        'tk': token,
+        'q': query,
+    }
+
+    if override is not None:
+        for key, value in get_items(override):
+            params[key] = value
+
+    return params
+
+
+def legacy_format_json(original):
+    # save state
+    states = []
+    text = original
+
+    # save position for double-quoted texts
+    for i, pos in enumerate(re.finditer('"', text)):
+        # pos.start() is a double-quote
+        p = pos.start() + 1
+        if i % 2 == 0:
+            nxt = text.find('"', p)
+            states.append((p, text[p:nxt]))
+
+    # replace all weired characters in text
+    while text.find(',,') > -1:
+        text = text.replace(',,', ',null,')
+    while text.find('[,') > -1:
+        text = text.replace('[,', '[null,')
+
+    # recover state
+    for i, pos in enumerate(re.finditer('"', text)):
+        p = pos.start() + 1
+        if i % 2 == 0:
+            j = int(i / 2)
+            nxt = text.find('"', p)
+            # replacing a portion of a string
+            # use slicing to extract those parts of the original string to be kept
+            text = text[:p] + states[j][1] + text[nxt:]
+
+    converted = json.loads(text)
+    return converted
+
+
+def get_items(dict_object):
+    for key in dict_object:
+        yield key, dict_object[key]
+
+
+def format_json(original):
+    try:
+        converted = json.loads(original)
+    except ValueError:
+        converted = legacy_format_json(original)
+
+    return converted
+
+
+def rshift(val, n):
+    """python port for '>>>'(right shift with padding)
+    """
+    return (val % 0x100000000) >> n