Merge pull request #171 from readbeyond/devel

Fix bug #168
readbeyond · Mar 16, 2017 · 9d95535 · 9d95535
2 parents fb1e315 + 66948d9
commit 9d95535
Show file tree

Hide file tree

Showing 35 changed files with 107 additions and 35 deletions.
diff --git a/README.md b/README.md
@@ -2,8 +2,8 @@
 
 **aeneas** is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment).
 
-* Version: 1.7.2
-* Date: 2017-03-03
+* Version: 1.7.3
+* Date: 2017-03-15
 * Developed by: [ReadBeyond](http://www.readbeyond.it/)
 * Lead Developer: [Alberto Pettarin](http://www.albertopettarin.it/)
 * License: the GNU Affero General Public License Version 3 (AGPL v3)
@@ -316,7 +316,7 @@ No copy rights were harmed in the making of this project.
 
 * **April 2016**: the Fruch Foundation kindly sponsored the development and documentation of v1.5.0
 
-* **December 2016**: the [Centro Internazionale Del Libro Parlato "Adriano Sernagiotto"](http://www.libroparlato.org/) (Feltre, Italy) partially sponsored the development of v1.7.0, v1.7.1, and v1.7.2
+* **December 2016**: the [Centro Internazionale Del Libro Parlato "Adriano Sernagiotto"](http://www.libroparlato.org/) (Feltre, Italy) partially sponsored the development of the v1.7 series
 
 ### Supporting
 

diff --git a/README.rst b/README.rst
@@ -4,8 +4,8 @@ aeneas
 **aeneas** is a Python/C library and a set of tools to automagically
 synchronize audio and text (aka forced alignment).
 
--  Version: 1.7.2
--  Date: 2017-03-03
+-  Version: 1.7.3
+-  Date: 2017-03-15
 -  Developed by: `ReadBeyond <http://www.readbeyond.it/>`__
 -  Lead Developer: `Alberto Pettarin <http://www.albertopettarin.it/>`__
 -  License: the GNU Affero General Public License Version 3 (AGPL v3)
@@ -359,8 +359,7 @@ Sponsors
 
 -  **December 2016**: the `Centro Internazionale Del Libro Parlato
    "Adriano Sernagiotto" <http://www.libroparlato.org/>`__ (Feltre,
-   Italy) partially sponsored the development of v1.7.0, v1.7.1, and
-   v1.7.2
+   Italy) partially sponsored the development of the v1.7 series
 
 Supporting
 ~~~~~~~~~~

diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-1.7.2
+1.7.3
diff --git a/aeneas/__init__.py b/aeneas/__init__.py
@@ -35,4 +35,4 @@
     """
 __license__ = "GNU AGPL v3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
diff --git a/aeneas/audiofile.py b/aeneas/audiofile.py
@@ -209,9 +209,12 @@ def __init__(self, file_path=None, file_format=None, rconf=None, logger=None):
         self.__samples = None
 
     def __unicode__(self):
+        fmt = self.file_format
+        if isinstance(fmt, tuple):
+            fmt = u"%s %d %d" % fmt
         msg = [
             u"File path:         %s" % self.file_path,
-            u"File format:       %s" % self.file_format,
+            u"File format:       %s" % fmt,
             u"File size (bytes): %s" % gf.safe_int(self.file_size),
             u"Audio length (s):  %s" % gf.safe_float(self.audio_length),
             u"Audio format:      %s" % self.audio_format,
@@ -644,4 +647,7 @@ def _update_length(self):
         This function fails silently if one of the two is ``None``.
         """
         if (self.audio_sample_rate is not None) and (self.__samples is not None):
-            self.audio_length = TimeValue(self.__samples_length / self.audio_sample_rate)
+            # NOTE computing TimeValue (... / ...) yields wrong results,
+            #      see issue #168
+            #      self.audio_length = TimeValue(self.__samples_length / self.audio_sample_rate)
+            self.audio_length = TimeValue(self.__samples_length) / TimeValue(self.audio_sample_rate)
diff --git a/aeneas/cdtw/cdtw_setup.py b/aeneas/cdtw/cdtw_setup.py
@@ -49,7 +49,7 @@
 
 setup(
     name="cdtw",
-    version="1.7.2",
+    version="1.7.3",
     description="Python C Extension for computing the DTW as fast as your bare metal allows.",
     ext_modules=[CMODULE],
     include_dirs=[misc_util.get_numpy_include_dirs()]

diff --git a/aeneas/cew/cew_setup.py b/aeneas/cew/cew_setup.py
@@ -47,7 +47,7 @@
 
 setup(
     name="cew",
-    version="1.7.2",
+    version="1.7.3",
     description="Python C Extension for synthesizing text with eSpeak.",
     ext_modules=[CMODULE]
 )

diff --git a/aeneas/cfw/cfw_setup.py b/aeneas/cfw/cfw_setup.py
@@ -54,7 +54,7 @@
 
 setup(
     name="cfw",
-    version="1.7.2",
+    version="1.7.3",
     description="Python C Extension for synthesizing text with Festival.",
     ext_modules=[CMODULE]
 )

diff --git a/aeneas/cmfcc/cmfcc_setup.py b/aeneas/cmfcc/cmfcc_setup.py
@@ -50,7 +50,7 @@
 
 setup(
     name="cmfcc",
-    version="1.7.2",
+    version="1.7.3",
     description="Python C Extension for computing the MFCCs as fast as your bare metal allows.",
     ext_modules=[CMODULE],
     include_dirs=[misc_util.get_numpy_include_dirs()]

diff --git a/aeneas/cwave/cwave_setup.py b/aeneas/cwave/cwave_setup.py
@@ -49,7 +49,7 @@
 
 setup(
     name="cwave",
-    version="1.7.2",
+    version="1.7.3",
     description="Python C Extension for for reading WAVE files.",
     ext_modules=[CMODULE],
     include_dirs=[misc_util.get_numpy_include_dirs()]

diff --git a/aeneas/tests/long_test_task_parameters.py b/aeneas/tests/long_test_task_parameters.py
@@ -354,6 +354,14 @@ def test_exec_os_task_file_levels_123(self):
             ("out", "sonnet.json")
         ], 0)
 
+    def test_exec_exact_5600_16000_munparsed_issue_168(self):
+        self.execute([
+            ("in", "../tests/res/audioformats/exact.5600.16000.wav"),
+            ("in", "../tests/res/inputtext/exact.5600.16000.munparsed.xhtml"),
+            ("", "task_language=eng|is_text_type=munparsed|os_task_file_format=json|is_text_munparsed_l1_id_regex=p[0-9]+|is_text_munparsed_l2_id_regex=p[0-9]+s[0-9]+|is_text_munparsed_l3_id_regex=p[0-9]+s[0-9]+w[0-9]+"),
+            ("out", "sonnet.json")
+        ], 0)
+
 
 if __name__ == "__main__":
     unittest.main()
diff --git a/aeneas/tests/res/audioformats/exact.5600.16000.wav b/aeneas/tests/res/audioformats/exact.5600.16000.wav
diff --git a/aeneas/tests/res/inputtext/exact.5600.16000.munparsed.xhtml b/aeneas/tests/res/inputtext/exact.5600.16000.munparsed.xhtml
@@ -0,0 +1,32 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops" lang="en" xml:lang="en">
+ <head>
+  <meta charset="utf-8"/>
+  <meta name="viewport" content="width=768,height=1024"/>
+  <link rel="stylesheet" href="../Styles/style.css" type="text/css"/>
+  <title>Sonnet I</title>
+ </head>
+ <body>
+  <div id="divSonnet">
+   <p class="stanza" id="p000002">
+    <span id="p000002s000001">
+     <span id="p000002s000001w000000">1</span>
+     <span id="p000002s000001w000001">From</span>
+     <span id="p000002s000001w000002">fairest</span>
+     <span id="p000002s000001w000003">creatures</span>
+     <span id="p000002s000001w000004">we</span>
+     <span id="p000002s000001w000005">desire</span>
+     <span id="p000002s000001w000006">increase,</span>
+     <span id="p000002s000001w000007">That</span>
+     <span id="p000002s000001w000008">thereby</span>
+     <span id="p000002s000001w000009">beauty’s</span>
+     <span id="p000002s000001w000010">rose</span>
+     <span id="p000002s000001w000011">might</span>
+     <span id="p000002s000001w000012">never</span>
+     <span id="p000002s000001w000013">die,</span>
+    </span>
+   </p>
+  </div>
+ </body>
+</html>
+
diff --git a/aeneas/tests/test_audiofile.py b/aeneas/tests/test_audiofile.py
@@ -36,6 +36,7 @@ class TestAudioFile(unittest.TestCase):
     AUDIO_FILE_WAVE = "res/audioformats/mono.16000.wav"
     AUDIO_FILE_EMPTY = "res/audioformats/p001.empty"
     AUDIO_FILE_NOT_WAVE = "res/audioformats/p001.mp3"
+    AUDIO_FILE_EXACT = "res/audioformats/exact.5600.16000.wav"
     NOT_EXISTING_FILE = "res/audioformats/x/y/z/not_existing.wav"
     FILES = [
         {
@@ -163,6 +164,11 @@ def test_length(self):
         audiofile.clear_data()
         self.assertAlmostEqual(audiofile.audio_length, TimeValue("53.3"), places=1)     # 53.266
 
+    def test_length_exact(self):
+        audiofile = self.load(self.AUDIO_FILE_EXACT, rs=True)
+        audiofile.clear_data()
+        self.assertAlmostEqual(audiofile.audio_length, TimeValue("5.600"), places=3)     # 5.600
+
     def test_add_samples_file(self):
         audiofile = self.load(self.AUDIO_FILE_WAVE, rs=True)
         data = audiofile.audio_samples

diff --git a/aeneas/tests/tool_test_read_audio.py b/aeneas/tests/tool_test_read_audio.py
@@ -56,11 +56,23 @@ def test_read_audio(self):
             ("in", "../tools/res/audio.wav")
         ], 0)
 
+    def test_read_audio_full(self):
+        self.execute([
+            ("in", "../tools/res/audio.wav"),
+            ("", "-f")
+        ], 0)
+
     def test_read_audio_mp3(self):
         self.execute([
             ("in", "../tools/res/audio.mp3")
         ], 0)
 
+    def test_read_audio_mp3_full(self):
+        self.execute([
+            ("in", "../tools/res/audio.mp3"),
+            ("", "-f")
+        ], 0)
+
     def test_read_audio_path(self):
         path = os.path.expanduser("~")
         path = os.path.join(path, ".bin/myffprobe")

diff --git a/aeneas/tools/read_audio.py b/aeneas/tools/read_audio.py
@@ -51,6 +51,7 @@ class ReadAudioCLI(AbstractCLIProgram):
             (u"AUDIO_FILE", True)
         ],
         "options": [
+            u"-f, --full : load samples from file, possibly converting to WAVE"
         ],
         "parameters": [
         ],
@@ -72,6 +73,8 @@ def perform_command(self):
         try:
             audiofile = AudioFile(audio_file_path, rconf=self.rconf, logger=self.logger)
             audiofile.read_properties()
+            if self.has_option([u"-f", u"--full"]):
+                audiofile.read_samples_from_file()
             self.print_generic(audiofile.__unicode__())
             return self.NO_ERROR_EXIT_CODE
         except OSError:

diff --git a/aeneas_check_setup.py b/aeneas_check_setup.py
@@ -44,7 +44,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 ANSI_ERROR = u"\033[91m"
 ANSI_OK = u"\033[92m"

diff --git a/bin/aeneas_check_setup.py b/bin/aeneas_check_setup.py
@@ -44,7 +44,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 ANSI_ERROR = u"\033[91m"
 ANSI_OK = u"\033[92m"

diff --git a/bin/aeneas_convert_syncmap.py b/bin/aeneas_convert_syncmap.py
@@ -40,7 +40,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 
 def main():

diff --git a/bin/aeneas_download.py b/bin/aeneas_download.py
@@ -40,7 +40,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 
 def main():

diff --git a/bin/aeneas_execute_job.py b/bin/aeneas_execute_job.py
@@ -42,7 +42,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 
 def main():

diff --git a/bin/aeneas_execute_task.py b/bin/aeneas_execute_task.py
@@ -41,7 +41,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 
 def main():

diff --git a/bin/aeneas_plot_waveform.py b/bin/aeneas_plot_waveform.py
@@ -40,7 +40,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 
 def main():

diff --git a/bin/aeneas_synthesize_text.py b/bin/aeneas_synthesize_text.py
@@ -41,7 +41,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 
 def main():

diff --git a/bin/aeneas_validate.py b/bin/aeneas_validate.py
@@ -47,7 +47,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 
 def main():

diff --git a/check_dependencies.py b/check_dependencies.py
@@ -44,7 +44,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 ANSI_ERROR = u"\033[91m"
 ANSI_OK = u"\033[92m"

diff --git a/docs/source/changelog.rst b/docs/source/changelog.rst
@@ -1,6 +1,12 @@
 Changelog
 =========
 
+v1.7.3 (2017-03-15)
+-------------------
+
+#. Fixed bug #168 and added a regression test for it
+#. Added option ``-f, --full`` to ``aeneas.tools.read_audio`` and tests for it
+
 v1.7.2 (2017-03-03)
 -------------------
 

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -60,7 +60,7 @@
 # The short X.Y version.
 version = '1.7'
 # The full version, including alpha/beta/rc tags.
-release = '1.7.2'
+release = '1.7.3'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

diff --git a/install_dependencies.sh b/install_dependencies.sh
@@ -7,7 +7,7 @@
 #     Copyright 2015-2017, Alberto Pettarin (www.albertopettarin.it)
 #     """
 # __license__ = "GNU AGPL 3"
-# __version__ = "1.7.2"
+# __version__ = "1.7.3"
 # __email__ = "aeneas@readbeyond.it"
 # __status__ = "Production"
 

diff --git a/pyinstaller-aeneas-cli.py b/pyinstaller-aeneas-cli.py
@@ -42,7 +42,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 
 def main():

diff --git a/pyinstaller-onedir.spec b/pyinstaller-onedir.spec
@@ -9,7 +9,7 @@
 #"""
 #__license__ = "GNU AGPL 3"
 #__status__ = "Production"
-#__version__ = "1.7.2"
+#__version__ = "1.7.3"
 
 datas = [
     # required

diff --git a/pyinstaller-onefile.spec b/pyinstaller-onefile.spec
@@ -9,7 +9,7 @@
 #"""
 #__license__ = "GNU AGPL 3"
 #__status__ = "Production"
-#__version__ = "1.7.2"
+#__version__ = "1.7.3"
 
 datas = [
     # required

diff --git a/run_all_unit_tests.py b/run_all_unit_tests.py
@@ -41,7 +41,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 TEST_DIRECTORY = "aeneas/tests"
 MAP = {

diff --git a/setup.py b/setup.py
@@ -57,7 +57,7 @@
 """
 __license__ = "GNU AGPL 3"
 __status__ = "Production"
-__version__ = "1.7.2"
+__version__ = "1.7.3"
 
 
 ##############################################################################