Bump hardrules requirement, fix compat issues

bitextor · Feb 9, 2024 · 2b728c1 · 2b728c1
1 parent 386baf4
commit 2b728c1
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 10 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,6 @@
+Bicleaner 0.17.4:
+* Bump bicleaner-hardrules requirement  to 2.10.3 and fix compatibility issues.
+
 Bicleaner 0.17.3:
 * Bump bicleaner-hardrules requirement to 2.8.1 to avoid hunspell installation issues.
 

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "bicleaner"
-version = "0.17.3"
+version = "0.17.4"
 description = "Parallel corpus classifier, indicating the likelihood of a pair of sentences being mutual translations or not"
 readme = "README.md"
 maintainers = [
@@ -19,7 +19,7 @@ dependencies = [ "regex",
     "toolwrapper>=0.4.1,<=2.1.0",
     "joblib",
     "sacremoses==0.0.53",
-    "bicleaner-hardrules==2.8.1",
+    "bicleaner-hardrules==2.10.3",
 ]
 classifiers = [ "Environment :: Console",
     "Intended Audience :: Science/Research",

diff --git a/src/bicleaner/classify.py b/src/bicleaner/classify.py
@@ -73,8 +73,8 @@ def load_metadata(args, parser):
     try:
         # Load YAML
         metadata_yaml = yaml.safe_load(args.metadata)
-        yamlpath = os.path.dirname(os.path.abspath(args.metadata.name))
-        metadata_yaml["yamlpath"] = yamlpath
+        yamldir = os.path.dirname(os.path.abspath(args.metadata.name))
+        metadata_yaml["yamldir"] = yamldir
 
         # Read language pair and tokenizers
         args.source_lang=metadata_yaml["source_lang"]
@@ -86,32 +86,32 @@ def load_metadata(args, parser):
 
         # Load classifier
         try:
-            args.clf=joblib.load( os.path.join( yamlpath , metadata_yaml["classifier"]))
+            args.clf=joblib.load( os.path.join( yamldir , metadata_yaml["classifier"]))
         except:
             args.clf=joblib.load(metadata_yaml["classifier"])
         args.clf.n_jobs = 1
         args.classifier_type=metadata_yaml["classifier_type"]
 
         # Load probabilistic dictionaries
         try:
-            args.dict_sl_tl = ProbabilisticDictionary( os.path.join(yamlpath , metadata_yaml["source_dictionary"]))
+            args.dict_sl_tl = ProbabilisticDictionary( os.path.join(yamldir , metadata_yaml["source_dictionary"]))
         except:
             args.dict_sl_tl = ProbabilisticDictionary(metadata_yaml["source_dictionary"])
         try:
-            args.dict_tl_sl = ProbabilisticDictionary( os.path.join(yamlpath , metadata_yaml["target_dictionary"]))
+            args.dict_tl_sl = ProbabilisticDictionary( os.path.join(yamldir , metadata_yaml["target_dictionary"]))
         except:
             args.dict_tl_sl = ProbabilisticDictionary(metadata_yaml["target_dictionary"])
 
         # Load wordfreqs
         try:
-            args.sl_word_freqs = WordZipfFreqDist( os.path.join( yamlpath, metadata_yaml["source_word_freqs"]))
+            args.sl_word_freqs = WordZipfFreqDist( os.path.join( yamldir, metadata_yaml["source_word_freqs"]))
         except:
             try:
                 args.sl_word_freqs = WordZipfFreqDist(metadata_yaml["source_word_freqs"])
             except:
                 args.sl_word_freqs = None
         try:
-            args.tl_word_freqs = WordZipfFreqDist( os.path.join( yamlpath , metadata_yaml["target_word_freqs"]))
+            args.tl_word_freqs = WordZipfFreqDist( os.path.join( yamldir , metadata_yaml["target_word_freqs"]))
         except:
             try:
                 args.tl_word_freqs = WordZipfFreqDist(metadata_yaml["target_word_freqs"])
@@ -153,7 +153,7 @@ def load_metadata(args, parser):
                 logging.warning("Porn removal not present in metadata, disabling.")
             else:
                 try:
-                    args.porn_removal = fasttext.load_model(os.path.join(yamlpath, metadata_yaml['porn_removal_file']))
+                    args.porn_removal = fasttext.load_model(os.path.join(yamldir, metadata_yaml['porn_removal_file']))
                 except:
                     args.porn_removal = fasttext.load_model(args.metadata_yaml['porn_removal_file'])
         else: