Help wanted

[Henry-ZHR]

E:\tmp\AudioCompare-master>python main.py -f 1.wav -f 2.wav
ERROR: 'gbk' codec can't decode byte 0xb8 in position 5: illegal multibyte sequence
ERROR: 'gbk' codec can't decode byte 0xac in position 25: illegal multibyte sequence

(I run it on Windows)

[Henry-ZHR]

I ran 2to3 before running main.py

E:\tmp>2to3 AudioCompare-master -w
RefactoringTool: Skipping optional fixer: buffer
RefactoringTool: Skipping optional fixer: idioms
RefactoringTool: Skipping optional fixer: set_literal
RefactoringTool: Skipping optional fixer: ws_comma
RefactoringTool: Refactored AudioCompare-master\FFT.py
--- AudioCompare-master\FFT.py  (original)
+++ AudioCompare-master\FFT.py  (refactored)
@@ -63,7 +63,7 @@
         Pxx = np.zeros((numFreqs, n), np.complex_)

         # do the ffts of the slices
-        for i in xrange(n):
+        for i in range(n):
             thisX = x[ind[i]:ind[i]+NFFT]
             thisX = windowVals * thisX
             fx = np.fft.fft(thisX, n=NFFT)
RefactoringTool: No changes to AudioCompare-master\InputFile.py
RefactoringTool: Refactored AudioCompare-master\Matcher.py
--- AudioCompare-master\Matcher.py      (original)
+++ AudioCompare-master\Matcher.py      (refactored)
@@ -79,7 +79,7 @@
     chunks = len(freq_chunks)
     fingerprints = np.zeros(chunks, dtype=np.uint32)
     # Examine each chunk independently
-    for chunk in xrange(chunks):
+    for chunk in range(chunks):
         fingerprint = 0
         for bucket in range(BUCKETS):
             start_index = bucket * BUCKET_SIZE
@@ -197,7 +197,7 @@
         to ChunkInfo objects."""
         master = defaultdict(list)
         for f in files:
-            for chunk in xrange(len(f.fingerprints)):
+            for chunk in range(len(f.fingerprints)):
                 hash = f.fingerprints[chunk]
                 master[hash].append(ChunkInfo(chunk, f.filename))

@@ -239,7 +239,7 @@
             file_match_offsets[f] = defaultdict(lambda: 0)

         # For each chunk in the query file
-        for query_chunk_index in xrange(len(file.fingerprints)):
+        for query_chunk_index in range(len(file.fingerprints)):
             # See if that chunk's fingerprint is in our master hash
             chunk_fingerprint = file.fingerprints[query_chunk_index]
             if chunk_fingerprint in master_hash:
@@ -262,7 +262,7 @@
             # hash keys were found with the same time difference
             # relative to each other.
             if len(offsets) != 0:
-                max_offset = max(offsets.viewvalues())
+                max_offset = max(offsets.values())
             else:
                 max_offset = 0

@@ -326,19 +326,19 @@

         # If there was an error in fingerprinting a file,
         # add a special ErrorResult to our results list
-        results.extend(filter(lambda x: not x.success, dir1_results))
-        results.extend(filter(lambda x: not x.success, dir2_results))
+        results.extend([x for x in dir1_results if not x.success])
+        results.extend([x for x in dir2_results if not x.success])

         # Proceed only with fingerprints that were computed
         # successfully
-        dir1_successes = filter(lambda x: x.success and x.file_len > 0, dir1_results)
-        dir2_successes = filter(lambda x: x.success and x.file_len > 0, dir2_results)
+        dir1_successes = [x for x in dir1_results if x.success and x.file_len > 0]
+        dir2_successes = [x for x in dir2_results if x.success and x.file_len > 0]

         # Empty files should match other empty files
         # Our matching algorithm will not report these as a match,
         # so we have to make a special case for it.
-        dir1_empty_files = filter(lambda x: x.success and x.file_len == 0, dir1_results)
-        dir2_empty_files = filter(lambda x: x.success and x.file_len == 0, dir2_results)
+        dir1_empty_files = [x for x in dir1_results if x.success and x.file_len == 0]
+        dir2_empty_files = [x for x in dir2_results if x.success and x.file_len == 0]

         # Every empty file should match every other empty file
         for empty_file1, empty_file2 in itertools.product(dir1_empty_files, dir2_empty_files):
@@ -350,8 +350,8 @@

         # Get the combined sizes of the files in our two search
         # paths
-        dir1_size = sum(dir1_file_lengths.viewvalues())
-        dir2_size = sum(dir2_file_lengths.viewvalues())
+        dir1_size = sum(dir1_file_lengths.values())
+        dir2_size = sum(dir2_file_lengths.values())

         # Whichever search path has more data in it is the
         # one we want to put in the master hash, and then query
RefactoringTool: No changes to AudioCompare-master\common.py
RefactoringTool: Refactored AudioCompare-master\error.py
--- AudioCompare-master\error.py        (original)
+++ AudioCompare-master\error.py        (refactored)
@@ -2,11 +2,11 @@


 def die(msg):
-    print >> sys.stderr, "ERROR: {e}".format(e=msg)
+    print("ERROR: {e}".format(e=msg), file=sys.stderr)
     exit(1)


 def warn(msg):
-    print >> sys.stderr, "ERROR: {e}".format(e=msg)
+    print("ERROR: {e}".format(e=msg), file=sys.stderr)


RefactoringTool: Refactored AudioCompare-master\main.py
--- AudioCompare-master\main.py (original)
+++ AudioCompare-master\main.py (refactored)
@@ -37,7 +37,7 @@
             code = 1
             warn(match.message)
         else:
-            print match
+            print(match)

     return code

RefactoringTool: No changes to AudioCompare-master\test\A5Test.py
RefactoringTool: No changes to AudioCompare-master\test\BlackBox.py
RefactoringTool: No changes to AudioCompare-master\test\InputFileTest.py
RefactoringTool: No changes to AudioCompare-master\test\ProfTest.py
RefactoringTool: Refactored AudioCompare-master\test\TestCommon.py
--- AudioCompare-master\test\TestCommon.py      (original)
+++ AudioCompare-master\test\TestCommon.py      (refactored)
@@ -93,7 +93,7 @@
             foundRegex = -1
             currRegex = 0
             for errRegex in errRegexes:
-                if(not isinstance(errRegex, basestring)):
+                if(not isinstance(errRegex, str)):
                     compiledErrRegexes = [re.compile(errRegex[0]), re.compile(errRegex[1])]
                 else:
                     compiledErrRegexes = [re.compile(errRegex)]
@@ -122,7 +122,7 @@
             foundRegex = -1
             currRegex = 0
             for outRegex in outRegexes:
-                if(isinstance(outRegex, basestring)):
+                if(isinstance(outRegex, str)):
                     outRegex = [outRegex]

                 compiledOutRegexes = []
@@ -172,7 +172,7 @@
             currLine += 1

         #Check for extraneous output
-        self.assertEquals(len(callOut), 0,
+        self.assertEqual(len(callOut), 0,
                             msg=name + " - should_produce_errors: STDOUT nonempty (Output line 0) (Expected: Actual:" + callOut + ")");

         #Check return code
@@ -215,10 +215,10 @@
             currLine += 1

         #Check for extraneous output
-        self.assertEquals(len(callErr), 0,
+        self.assertEqual(len(callErr), 0,
                             msg=name + " - should_not_produce_errors: STDERR nonempty (Output line 0) (Expected: Actual:" + callErr + ")");

         #Check return code
-        self.assertEquals(returnCode, 0,
+        self.assertEqual(returnCode, 0,
                           msg=name + " - should_not_produce_errors: Return Code Incorrect (Expected:0 Actual:" + str(
                               returnCode) + ")")
RefactoringTool: Refactored AudioCompare-master\test\scores.py
--- AudioCompare-master\test\scores.py  (original)
+++ AudioCompare-master\test\scores.py  (refactored)
@@ -10,7 +10,7 @@
             msg = "SHOULD NOT MATCH:"
         else:
             msg = "SHOULD MATCH:    "
-        print "{m} score:{s}\tlength:{l}\tratio:{r} \t{f}".format(m=msg, s=score, l=length, r=score/length, f=map(os.path.basename, test))
+        print("{m} score:{s}\tlength:{l}\tratio:{r} \t{f}".format(m=msg, s=score, l=length, r=score/length, f=list(map(os.path.basename, test))))

 def scores():
     testSuiteDir = os.path.dirname(os.path.abspath(__file__)) + "/../test_data/"
RefactoringTool: Refactored AudioCompare-master\test\similaritywav.py
--- AudioCompare-master\test\similaritywav.py   (original)
+++ AudioCompare-master\test\similaritywav.py   (refactored)
@@ -42,9 +42,9 @@
 chunks_x = len(x)/chunksize
 chunks_y = len(y)/chunksize

-for i in xrange((chunks_x-1)):
+for i in range((chunks_x-1)):
        a.append(np.fft.rfft(x[i*chunksize:(i+1)*chunksize]))
-for i in xrange((chunks_y-1)):
+for i in range((chunks_y-1)):
        b.append(np.fft.rfft(y[i*chunksize:(i+1)*chunksize]))

 a = np.array(a)
@@ -60,8 +60,8 @@
 # so this loop run entire two files compare between the chunks (O(n^2)??)
 # if there are over 10 matches of two chunks's similarity is over 90%, we deduce as a match

-for i in xrange(cx):
-       for j in xrange(cy):
+for i in range(cx):
+       for j in range(cy):
                cor = np.corrcoef(a[i],b[j])
                if cor[0][1] >=0.9:

@@ -70,10 +70,10 @@
                                diffs[diff] += 1
                                if diffs[diff] >=10:
                                        ok = 1
-                                       print 'match'
+                                       print('match')
                                        sys.exit()

                        else:
                                diffs[diff] = 1

-print 'no match'
+print('no match')
RefactoringTool: Refactored AudioCompare-master\test\visualizer.py
--- AudioCompare-master\test\visualizer.py      (original)
+++ AudioCompare-master\test\visualizer.py      (refactored)
@@ -1,6 +1,6 @@
 import sys
 from InputFile import InputFile
-from Tkinter import *
+from tkinter import *
 from Matcher import *
 import Matcher
 from FFT import FFT
@@ -28,8 +28,8 @@
     """
     try:
         input_file = InputFile(sys.argv[1])
-    except IOError, e:
-        print ("ERROR: {e}".format(e=e))
+    except IOError as e:
+        print(("ERROR: {e}".format(e=e)))
         return

     sample_rate_adjust_factor = int(NORMAL_SAMPLE_RATE / input_file.get_sample_rate())
@@ -52,7 +52,7 @@
     w.pack()
     # for each chunk (which will be the X axis)
     for i in range(chunks):
-        print i
+        print(i)
         # for each line (the Y axis)
         for line in range(1, lines):
             # compute what color this frequency should
RefactoringTool: Files that were modified:
RefactoringTool: AudioCompare-master\FFT.py
RefactoringTool: AudioCompare-master\InputFile.py
RefactoringTool: AudioCompare-master\Matcher.py
RefactoringTool: AudioCompare-master\common.py
RefactoringTool: AudioCompare-master\error.py
RefactoringTool: AudioCompare-master\main.py
RefactoringTool: AudioCompare-master\test\A5Test.py
RefactoringTool: AudioCompare-master\test\BlackBox.py
RefactoringTool: AudioCompare-master\test\InputFileTest.py
RefactoringTool: AudioCompare-master\test\ProfTest.py
RefactoringTool: AudioCompare-master\test\TestCommon.py
RefactoringTool: AudioCompare-master\test\scores.py
RefactoringTool: AudioCompare-master\test\similaritywav.py
RefactoringTool: AudioCompare-master\test\visualizer.py

[Dongbox]

open(file,'rb')

[charlesconnell]

I'm sorry, I don't know what's going on here. I haven't attempted to support Python 3 since numpy only worked with Python 2 at the time that I made this program.