python 3 compatibility

collect-fingerprints-of-songs.py

@@ -30,33 +30,33 @@
         colored('channels=%d', 'white', attrs=['dark']), # channels
         colored('%s', 'white', attrs=['bold'])           # filename
       )
-      print msg % (song_id, len(audio['channels']), filename)
+      print(msg % (song_id, len(audio['channels']), filename))
 
       if song:
         hash_count = db.get_song_hashes_count(song_id)
 
         if hash_count > 0:
           msg = '   already exists (%d hashes), skip' % hash_count
-          print colored(msg, 'red')
+          print(colored(msg, 'red'))
 
           continue
 
-      print colored('   new song, going to analyze..', 'green')
+      print(colored('   new song, going to analyze..', 'green'))
 
       hashes = set()
       channel_amount = len(audio['channels'])
 
       for channeln, channel in enumerate(audio['channels']):
         msg = '   fingerprinting channel %d/%d'
-        print colored(msg, attrs=['dark']) % (channeln+1, channel_amount)
+        print(colored(msg, attrs=['dark']) % (channeln+1, channel_amount))
 
         channel_hashes = fingerprint.fingerprint(channel, Fs=audio['Fs'], plots=config['fingerprint.show_plots'])
         channel_hashes = set(channel_hashes)
 
         msg = '   finished channel %d/%d, got %d hashes'
-        print colored(msg, attrs=['dark']) % (
+        print(colored(msg, attrs=['dark']) % (
           channeln+1, channel_amount, len(channel_hashes)
-        )
+        ))
 
         hashes |= channel_hashes
 
@@ -67,7 +67,7 @@
         values.append((song_id, hash, offset))
 
       msg = '   storing %d hashes in db' % len(values)
-      print colored(msg, 'green')
+      print(colored(msg, 'green'))
 
       db.store_fingerprints(values)
 

libs/db_sqlite.py

@@ -1,8 +1,8 @@
-from db import Database
-from config import get_config
-import sqlite3
 import sys
-from itertools import izip_longest
+import sqlite3
+from libs.db import Database
+from libs.config import get_config
+from itertools import zip_longest
 from termcolor import colored
 
 class SqliteDatabase(Database):
@@ -66,11 +66,11 @@ def findAll(self, table, params):
 
   def insert(self, table, params):
     keys = ', '.join(params.keys())
-    values = params.values()
+    values = list(params.values())
 
-    query = "INSERT INTO songs (%s) VALUES (?, ?)" % (keys);
+    query = "INSERT INTO songs (%s) VALUES ('%s','%s')" % (keys, values[0], values[1]);
 
-    self.cur.execute(query, values)
+    self.cur.execute(query)
     self.conn.commit()
 
     return self.cur.lastrowid
@@ -79,7 +79,7 @@ def insertMany(self, table, columns, values):
     def grouper(iterable, n, fillvalue=None):
       args = [iter(iterable)] * n
       return (filter(None, values) for values
-          in izip_longest(fillvalue=fillvalue, *args))
+          in zip_longest(fillvalue=fillvalue, *args))
 
     for split_values in grouper(values, 1000):
       query = "INSERT OR IGNORE INTO %s (%s) VALUES (?, ?, ?)" % (table, ", ".join(columns))

libs/fingerprint.py

@@ -1,6 +1,8 @@
 import hashlib
 import numpy as np
 import matplotlib.mlab as mlab
+# import matplotlib
+# matplotlib.use('TKAgg')
 import matplotlib.pyplot as plt
 
 from termcolor import colored
@@ -95,7 +97,8 @@ def fingerprint(channel_samples, Fs=DEFAULT_FS,
     local_maxima = get_2D_peaks(arr2D, plot=plots, amp_min=amp_min)
 
     msg = '   local_maxima: %d of frequency & time pairs'
-    print colored(msg, attrs=['dark']) % len(local_maxima)
+    local_maxima = list(local_maxima)
+    print(colored(msg, attrs=['dark']) % len(local_maxima))
 
     # return hashes
     return generate_hashes(local_maxima, fan_value=fan_value)
@@ -164,5 +167,6 @@ def generate_hashes(peaks, fan_value=DEFAULT_FAN_VALUE):
 
           # check if delta is between min & max
           if t_delta >= MIN_HASH_TIME_DELTA and t_delta <= MAX_HASH_TIME_DELTA:
-            h = hashlib.sha1("%s|%s|%s" % (str(freq1), str(freq2), str(t_delta)))
+            full_code = "%s|%s|%s" %(str(freq1), str(freq2), str(t_delta))
+            h = hashlib.sha1(full_code.encode('utf-8'))
             yield (h.hexdigest()[0:FINGERPRINT_REDUCTION], t1)

libs/reader_file.py

@@ -1,11 +1,11 @@
-from reader import BaseReader
 import os
+import numpy as np
+from reader import Reader
 from pydub import AudioSegment
 from pydub.utils import audioop
-import numpy as np
 from hashlib import sha1
 
-class FileReader(BaseReader):
+class FileReader(Reader):
   def __init__(self, filename):
     # super(FileReader, self).__init__(a)
     self.filename = filename
@@ -37,7 +37,7 @@ def parse_audio(self):
       data = np.fromstring(audiofile._data, np.int16)
 
       channels = []
-      for chn in xrange(audiofile.channels):
+      for chn in range(audiofile.channels):
         channels.append(data[chn::audiofile.channels])
 
       fs = audiofile.frame_rate

libs/reader_microphone.py

@@ -1,9 +1,14 @@
 import pyaudio
 import numpy
 import wave
-from reader import BaseReader
+from reader import Reader
+from reader._search import Search
+from reader._storage import Storage
+from reader._parser import Parser
+from reader._types import NameScheme
 
-class MicrophoneReader(BaseReader):
+
+class MicrophoneReader(Reader):
   default_chunksize = 8192
   default_format = pyaudio.paInt16
   default_channels = 2
@@ -12,7 +17,7 @@ class MicrophoneReader(BaseReader):
 
   # set default
   def __init__(self, a):
-    super(MicrophoneReader, self).__init__(a)
+    super(MicrophoneReader, self).__init__(a, Storage, Search, Parser, NameScheme)
     self.audio = pyaudio.PyAudio()
     self.stream = None
     self.data = []

recognize-from-microphone.py

@@ -6,7 +6,7 @@
 import argparse
 
 from argparse import RawTextHelpFormatter
-from itertools import izip_longest
+from itertools import zip_longest
 from termcolor import colored
 from libs.config import get_config
 from libs.reader_microphone import MicrophoneReader
@@ -44,7 +44,7 @@
     channels=channels)
 
   msg = ' * started recording..'
-  print colored(msg, attrs=['dark'])
+  print(colored(msg, attrs=['dark']))
 
   while True:
     bufferSize = int(reader.rate / reader.chunksize * seconds)
@@ -54,10 +54,10 @@
 
       if visualise_console:
         msg = colored('   %05d', attrs=['dark']) + colored(' %s', 'green')
-        print msg  % visual_peak.calc(nums)
+        print(msg  % visual_peak.calc(nums))
       else:
         msg = '   processing %d of %d..' % (i, bufferSize)
-        print colored(msg, attrs=['dark'])
+        print(colored(msg, attrs=['dark']))
 
     if not record_forever: break
 
@@ -68,19 +68,19 @@
   reader.stop_recording()
 
   msg = ' * recording has been stopped'
-  print colored(msg, attrs=['dark'])
+  print(colored(msg, attrs=['dark']))
 
 
 
   def grouper(iterable, n, fillvalue=None):
     args = [iter(iterable)] * n
-    return (filter(None, values) for values
-            in izip_longest(fillvalue=fillvalue, *args))
+    return (list(filter(None, values)) for values
+            in zip_longest(fillvalue=fillvalue, *args))
 
   data = reader.get_recorded_data()
 
   msg = ' * recorded %d samples'
-  print colored(msg, attrs=['dark']) % len(data[0])
+  print(colored(msg, attrs=['dark']) % len(data[0]))
 
   # reader.save_recorded('test.wav')
 
@@ -108,40 +108,41 @@ def return_matches(hashes):
         FROM fingerprints
         WHERE upper(hash) IN (%s)
       """
-      query = query % ', '.join('?' * len(split_values))
+      list_leng = len(list(split_values))
+      query = query % ', '.join('?' * list_leng)
 
       x = db.executeAll(query, split_values)
       matches_found = len(x)
 
       if matches_found > 0:
         msg = '   ** found %d hash matches (step %d/%d)'
-        print colored(msg, 'green') % (
+        print(colored(msg, 'green') % (
           matches_found,
           len(split_values),
           len(values)
-        )
+        ))
       else:
         msg = '   ** not matches found (step %d/%d)'
-        print colored(msg, 'red') % (
+        print(colored(msg, 'red') % (
           len(split_values),
           len(values)
-        )
+        ))
 
       for hash, sid, offset in x:
         # (sid, db_offset - song_sampled_offset)
-        yield (sid, offset - mapper[hash])
+        yield (sid, mapper[hash])
 
   for channeln, channel in enumerate(data):
     # TODO: Remove prints or change them into optional logging.
     msg = '   fingerprinting channel %d/%d'
-    print colored(msg, attrs=['dark']) % (channeln+1, channel_amount)
+    print(colored(msg, attrs=['dark']) % (channeln+1, channel_amount))
 
     matches.extend(find_matches(channel))
 
     msg = '   finished channel %d/%d, got %d hashes'
-    print colored(msg, attrs=['dark']) % (
+    print(colored(msg, attrs=['dark']) % (
       channeln+1, channel_amount, len(matches)
-    )
+    ))
 
   def align_matches(matches):
     diff_counter = {}
@@ -181,23 +182,23 @@ def align_matches(matches):
 
   total_matches_found = len(matches)
 
-  print ''
+  print('')
 
   if total_matches_found > 0:
     msg = ' ** totally found %d hash matches'
-    print colored(msg, 'green') % total_matches_found
+    print(colored(msg, 'green') % total_matches_found)
 
     song = align_matches(matches)
 
     msg = ' => song: %s (id=%d)\n'
     msg += '    offset: %d (%d secs)\n'
     msg += '    confidence: %d'
 
-    print colored(msg, 'green') % (
+    print(colored(msg, 'green') % (
       song['SONG_NAME'], song['SONG_ID'],
       song['OFFSET'], song['OFFSET_SECS'],
       song['CONFIDENCE']
-    )
+    ))
   else:
     msg = ' ** not matches found at all'
-    print colored(msg, 'red')
+    print(colored(msg, 'red'))

requirements.txt

@@ -1,5 +1,8 @@
 numpy>=1
+matplotlib
 termcolor
 pyaudio
 wave
 pydub
+reader
+scipy

tests/sqlite.py

@@ -11,4 +11,4 @@
   row = db.executeOne("SELECT 2+3 as x;")
 
   assert row[0] == 5, "failed simple sql execution"
-  print ' * %s' % colored('ok', 'green')
+  print(' * %s' % colored('ok', 'green'))