auto-tagging script added, signature updated, --version added

SLTev/SLTev.py

@@ -25,6 +25,7 @@ def main():
     parser.add_argument("-T", "--elitr-testset", metavar="DIR", help="use DIR as git clone of elitr-testset instead of elitr-testset", default= "elitr-testset", type=str)
     parser.add_argument("-e", metavar="EVALDIR", help="evaluate evaluation directory EVALDIR", type=str)
     parser.add_argument("--commitid", help="use elitr-testset at commit COMMITID", default= "HEAD", type=str)
+    parser.add_argument("--version", help="report the SLTev version", action='store_true', default='False')
     args = parser.parse_args()
 
     #-----------add SLTev home to the path 
@@ -33,6 +34,21 @@ def main():
     except:
         sltev_home = os.path.dirname(os.path.realpath(sys.argv[0]))
     sys.path.insert(1, sltev_home)
+
+    #print SLTev version
+    if args.version != "False":
+        try:
+            __version__ = pkg_resources.get_distribution("SLTev").version
+            eprint(__version__)
+        except:
+            try:
+                repo = git.Repo(os.path.split(sltev_home)[0])
+                commit_id = repo.head.commit
+                eprint("The commit id is: ", commit_id)
+            except:
+                eprint("SLTev is not installed, you can use the following command for installation:\n pip install SLTev")
+        sys.exit(1)
+
     #sacremoses checking
     try:
         tokenize = MosesTokenizer().tokenize
@@ -48,7 +64,10 @@ def main():
         sha = repo.head.object.hexsha
         SLTev_commit_id = 'SLTev_' + repo.git.rev_parse(sha, short=True) + '-'
     except:
-        SLTev_commit_id = ''
+        try:
+            SLTev_commit_id = 'SLTev_version_' + pkg_resources.get_distribution("SLTev").version + '-'
+        except:
+            SLTev_commit_id = 'SLTev_NONE' + '-'
     #-----------check output directory 
     if args.e is None and args.g is None:
         parser.print_help()
@@ -137,7 +156,9 @@ def main():
             elitr_commit_id = 'elitrtestset_' + repo.git.rev_parse(sha, short=True)
             signature = signature +  elitr_commit_id
         except:
-            pass
+            signature = signature + 'elitrtestset_NONE'
+    else:
+        signature = signature + 'elitrtestset_NONE'
 
     """
     Naming template:
@@ -239,3 +260,4 @@ def main():
 
 if __name__ == "__main__":
     main()
+

SLTev/__init__.py

@@ -5,3 +5,5 @@
 sltev_home = pkg_resources.resource_filename('SLTev', '')
 sys.path.insert(1, sltev_home)
 
+__version__ = "1.1.6"
+

SLTev/delay_modules.py

@@ -326,3 +326,4 @@ def evaluate_segmenter(Ts, MT, MovedWords, language, SLTev_home, temp_folder):
         sum_missing_words += temp_list[0][1]
         sum_delay += temp_list[0][0]            
     return sum_delay, sum_missing_words, mWERQuality
+

SLTev/evaluator.py

@@ -25,7 +25,7 @@ def evaluator(ostt=None, asr=False, tt=[], align=[], mt=None, b_time=3000, SLTev
 
     #----------------------------------------
     if simple == 'False':
-        eprint("P ... considering Partial segments in delay and quality calculation (in addition to Complete segments)")
+        eprint("P ... considering Partial segments in delay and quality calculation(in addition to Complete segments)")
         eprint("T ... considering source Timestamps supplied with MT output")
         eprint("W ... segmenting by mWER segmenter (i.e. not segmenting by MT source timestamps)")
         eprint("A ... considering word alignment (by GIZA) to relax word delay (i.e. relaxing more than just linear delay calculation)")
@@ -142,17 +142,7 @@ def evaluator(ostt=None, asr=False, tt=[], align=[], mt=None, b_time=3000, SLTev
             print("tot      MissedTokens  PWA                   ", missing_words)
         except:
             os.chdir(current_path)
-            shutil.rmtree(temp_folder, ignore_errors=True)
-
-    if simple == 'False' and time_stamp == "True":    
-        print("tot      Flicker       count_changed_Tokens  ", int(calc_revise(MT)))
-
-    if  time_stamp == "True":
-        print("tot      Flicker       count_changed_content ", int(calc_flicker(MT)))
-
-    if simple == 'False' and time_stamp == "True":
-        print("macroavg Flicker       count_changed_content ", str("{0:.3f}".format(round(calc_average_flickers_per_sentence(MT), 3)))  )
-        print("microavg Flicker       count_changed_content ",  str("{0:.3f}".format(round(calc_average_flickers_per_document(MT), 3))))
+            shutil.rmtree(temp_folder, ignore_errors=True)           
 
 
     sacre_score = calc_bleu_score_document(references, MT)
@@ -177,6 +167,16 @@ def evaluator(ostt=None, asr=False, tt=[], align=[], mt=None, b_time=3000, SLTev
             pass
 
 
+    if simple == 'False' and time_stamp == "True":    
+        print("tot      Flicker       count_changed_Tokens  ", int(calc_revise(MT)))
+
+    if  time_stamp == "True":
+        print("tot      Flicker       count_changed_content ", int(calc_flicker(MT)))
+
+    if simple == 'False' and time_stamp == "True":
+        print("mean     flicker across sentences            ", str("{0:.3f}".format(round(calc_average_flickers_per_sentence(MT), 3)))  )
+
+        print("mean     flicker across whole documents      ",  str("{0:.3f}".format(round(calc_average_flickers_per_document(MT), 3))))
 
 
 

SLTev/utilities.py

@@ -412,3 +412,4 @@ def submissionArgument():
     parser.add_argument("--simple", help="report a simplified set of scores", action='store_true', default='False')
     args = parser.parse_args()
     return args
+

auto-tagging.py

@@ -0,0 +1,9 @@
+# tagging into the SLTev repo (https://github.com/ELITR/SLTev.git)
+
+import git
+from SLTev import __version__
+
+repo = git.Repo(".")
+new_tag = repo.create_tag(__version__, message='Tagging version "{0}"'.format(__version__))
+
+repo.remotes.origin.push(new_tag)

setup.py

@@ -1,9 +1,7 @@
 from setuptools import setup, find_packages
+from SLTev import __version__ 
 import sys
 
-with open("README.md", "r", encoding="utf-8") as fh:
-    long_description = fh.read()
-
 if sys.version_info[:2] >= (3,7):
     numpy_version = "numpy"
 else:
@@ -12,11 +10,10 @@
 
 setup(
     name='SLTev',
-    version='1.1.5',
+    version=__version__,
     author="Mohammad Mahmoudi",
     author_email="zaribar2928@gmail.com",
     description="a tool for evaluation",
-    long_description=long_description,
     packages=['SLTev',],
     data_files = [ ('SLTev', ['SLTev/mwerSegmenter']) ],
     include_package_data=True,
@@ -39,3 +36,5 @@
 
 )
 
+
+