Merge pull request #131 from pettarin/devel

Doc review and two bugs fixed

Author: readbeyond

README.md

@@ -269,8 +269,9 @@ for languages with good ASR models,
 **aeneas** offers some options to improve
 the quality of the alignment at word-level:
 
-* multilevel text (since v1.5.1), and/or
-* MFCC nonspeech masking (since v1.7.0, disabled by default).
+* multilevel text (since v1.5.1),
+* MFCC nonspeech masking (since v1.7.0, disabled by default),
+* use better TTS engines, like Festival or AWS/Nuance TTS API (since v1.5.0).
 
 If you use the ``aeneas.tools.execute_task`` command line tool,
 you can add ``--presets-word`` switch to enable MFCC nonspeech masking, for example:

README.rst

@@ -299,8 +299,10 @@ aligners <https://github.com/pettarin/forced-alignment-tools>`__ for
 languages with good ASR models, **aeneas** offers some options to
 improve the quality of the alignment at word-level:
 
--  multilevel text (since v1.5.1), and/or
--  MFCC nonspeech masking (since v1.7.0, disabled by default).
+-  multilevel text (since v1.5.1),
+-  MFCC nonspeech masking (since v1.7.0, disabled by default),
+-  use better TTS engines, like Festival or AWS/Nuance TTS API (since
+   v1.5.0).
 
 If you use the ``aeneas.tools.execute_task`` command line tool, you can
 add ``--presets-word`` switch to enable MFCC nonspeech masking, for

aeneas/syncmap/format.py

@@ -108,7 +108,7 @@ class SyncMapFormat(object):
     * Multiple lines: no
 
     Please note that the text is assumed to be contained
-    in double quotes (``"..."``),
+    in double quotes ("..."),
     which are stripped when reading from file,
     and added back when writing to file.
 
@@ -128,7 +128,7 @@ class SyncMapFormat(object):
     * Multiple lines: no
 
     Please note that the text is assumed to be contained
-    in double quotes (``"..."``),
+    in double quotes ("..."),
     which are stripped when reading from file,
     and added back when writing to file.
 
@@ -180,7 +180,7 @@ class SyncMapFormat(object):
     * Multiple levels: no
     * Multiple lines: no
 
-    See also https://tla.mpi.nl/tla-news/documentation-of-eaf-elan-annotation-format/https://tla.mpi.nl/tla-news/documentation-of-eaf-elan-annotation-format/
+    See also https://tla.mpi.nl/tla-news/documentation-of-eaf-elan-annotation-format/
 
     .. versionadded:: 1.5.0
     """
@@ -252,7 +252,7 @@ class SyncMapFormat(object):
     * Multiple levels: no
     * Multiple lines: no
 
-    See also https://github.com/pettarin/rb_smil_emulatorhttps://github.com/pettarin/rb_smil_emulator
+    See also https://github.com/pettarin/rb_smil_emulator
 
     Deprecated, it will be removed in v2.0.0.
 
@@ -750,7 +750,7 @@ class = "IntervalTier"
     * Multiple lines: no
 
     Deprecated, it will be removed in v2.0.0.
-    Use XML instead.
+    Use ``XML`` instead.
 
     .. deprecated:: 1.2.0
     """

aeneas/syncmap/fragmentlist.py

@@ -459,9 +459,18 @@ def fragments_ending_inside_nonspeech_intervals(
                         #      | *********** | nsi
                         #      |   ***X      | frag (X=frag.end)
                         #
+                        # NOTE this case might happen as the following:
+                        #
+                        #      *************** nsi shadow
+                        #      |     ***     | nsi
+                        #      | **X         | frag (X=frag.end)
+                        #
+                        #      so we must invalidate the nsi if this happens
+                        #
+                        nsi_counter[nsi_index] = (None, []) 
                         nsi_index += 1
                         frag_index += 1
-                        self.log(u"    nsi_shadow entirely contains frag => skip to next fragment, nsi")
+                        self.log(u"    nsi_shadow entirely contains frag => invalidate nsi, and skip to next fragment, nsi")
                     else:
                         #
                         #      *************** nsi shadow

aeneas/syncmap/smfaudacity.py

@@ -21,17 +21,16 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 
 from aeneas.syncmap.smfgtabular import SyncMapFormatGenericTabular
 
 
 class SyncMapFormatAudacity(SyncMapFormatGenericTabular):
+    """
+    Handler for Audacity I/O format.
+    """
 
     TAG = u"SyncMapFormatAudacity"
 

aeneas/syncmap/smfbase.py

@@ -21,10 +21,6 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 
@@ -34,6 +30,9 @@
 
 
 class SyncMapFormatBase(Loggable):
+    """
+    Base class for I/O handlers.
+    """
 
     TAG = u"SyncMapFormatBase"
 

aeneas/syncmap/smfcsv.py

@@ -21,17 +21,16 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 
 from aeneas.syncmap.smfgtabular import SyncMapFormatGenericTabular
 
 
 class SyncMapFormatCSV(SyncMapFormatGenericTabular):
+    """
+    Handler for comma-separated values (CSV) I/O format.
+    """
 
     TAG = u"SyncMapFormatCSV"
 

aeneas/syncmap/smfeaf.py

@@ -21,10 +21,6 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 
@@ -36,6 +32,9 @@
 
 
 class SyncMapFormatEAF(SyncMapFormatGenericXML):
+    """
+    Handler for ELAN I/O format (EAF).
+    """
 
     TAG = u"SyncMapFormatEAF"
 

aeneas/syncmap/smfgsubtitles.py

@@ -21,10 +21,6 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 
@@ -33,6 +29,9 @@
 
 
 class SyncMapFormatGenericSubtitles(SyncMapFormatBase):
+    """
+    Base class for subtitles-like I/O format handlers.
+    """
 
     TAG = u"SyncMapFormatGenericSubtitles"
 

aeneas/syncmap/smfgtabular.py

@@ -21,10 +21,6 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 
@@ -33,6 +29,9 @@
 
 
 class SyncMapFormatGenericTabular(SyncMapFormatBase):
+    """
+    Base class for tabular-like I/O format handlers.
+    """
 
     TAG = u"SyncMapFormatGenericTabular"
 

aeneas/syncmap/smfgxml.py

@@ -21,10 +21,6 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 from itertools import chain
@@ -34,6 +30,9 @@
 
 
 class SyncMapFormatGenericXML(SyncMapFormatBase):
+    """
+    Base class for XML-like I/O format handlers.
+    """
 
     TAG = u"SyncMapFormatGenericTabular"
 

aeneas/syncmap/smfjson.py

@@ -21,10 +21,6 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 import json
@@ -34,6 +30,9 @@
 
 
 class SyncMapFormatJSON(SyncMapFormatBase):
+    """
+    Handler for JSON I/O format.
+    """
 
     TAG = u"SyncMapFormatJSON"
 

aeneas/syncmap/smfrbse.py

@@ -21,10 +21,6 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 import json
@@ -34,6 +30,11 @@
 
 
 class SyncMapFormatRBSE(SyncMapFormatBase):
+    """
+    Handler for RBSE
+    (i.e., JSON compatible with ``rb_smil_emulator.js``)
+    I/O format.
+    """
 
     TAG = u"SyncMapFormatRBSE"
 

aeneas/syncmap/smfsmil.py

@@ -21,10 +21,6 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 
@@ -35,6 +31,9 @@
 
 
 class SyncMapFormatSMIL(SyncMapFormatGenericXML):
+    """
+    Handler for SMIL for EPUB 3 I/O format.
+    """
 
     TAG = u"SyncMapFormatSMIL"
 
@@ -70,12 +69,16 @@ def parse(self, input_text, syncmap):
                 if child.tag == (smil_ns + "text"):
                     identifier = gf.safe_unicode(gf.split_url(child.get("src"))[1])
                 elif child.tag == (smil_ns + "audio"):
-                    begin = gf.time_from_hhmmssmmm(child.get("clipBegin"))
-                    if begin is None:
-                        begin = gf.time_from_ssmmm(child.get("clipBegin"))
-                    end = gf.time_from_hhmmssmmm(child.get("clipEnd"))
-                    if end is None:
-                        end = gf.time_from_ssmmm(child.get("clipEnd"))
+                    begin_text = child.get("clipBegin")
+                    if ":" in begin_text:
+                        begin = gf.time_from_hhmmssmmm(begin_text)
+                    else:
+                        begin = gf.time_from_ssmmm(begin_text)
+                    end_text = child.get("clipEnd")
+                    if ":" in end_text:
+                        end = gf.time_from_hhmmssmmm(end_text)
+                    else:
+                        end = gf.time_from_ssmmm(end_text)
             # TODO read text from additional text_file?
             self._add_fragment(
                 syncmap=syncmap,

aeneas/syncmap/smfsrt.py

@@ -21,10 +21,6 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 
@@ -33,6 +29,9 @@
 
 
 class SyncMapFormatSRT(SyncMapFormatGenericSubtitles):
+    """
+    Handler for SubRip (SRT) I/O format.
+    """
 
     TAG = u"SyncMapFormatSRT"
 

aeneas/syncmap/smfssv.py

@@ -21,17 +21,16 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 
 from aeneas.syncmap.smfgtabular import SyncMapFormatGenericTabular
 
 
 class SyncMapFormatSSV(SyncMapFormatGenericTabular):
+    """
+    Handler for space-separated plain text (SSV) I/O format.
+    """
 
     TAG = u"SyncMapFormatSSV"
 

aeneas/syncmap/smfsub.py

@@ -21,10 +21,6 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-"""
-TBW
-"""
-
 from __future__ import absolute_import
 from __future__ import print_function
 
@@ -33,6 +29,9 @@
 
 
 class SyncMapFormatSUB(SyncMapFormatGenericSubtitles):
+    """
+    Handler for SubViewer (SUB) I/O format.
+    """
 
     TAG = u"SyncMapFormatSUB"