Use safe_print everywhere

Author: bact

pythainlp/cli/benchmark.py

@@ -11,6 +11,7 @@
 
 from pythainlp import cli
 from pythainlp.benchmarks import word_tokenization
+from pythainlp.tools import safe_print
 
 
 def _read_file(path):
@@ -81,7 +82,7 @@ def __init__(self, name, argv):
             expected
         ), "Input and test files do not have the same number of samples"
 
-        print(
+        safe_print(
             "Benchmarking %s against %s with %d samples in total"
             % (args.input_file, args.test_file, len(actual))
         )
@@ -121,12 +122,12 @@ def __init__(self, name, argv):
             / statistics["word_level:total_words_in_ref_sample"]
         )
 
-        print("============== Benchmark Result ==============")
+        safe_print("============== Benchmark Result ==============")
 
         for c in ["tp", "fn", "tn", "fp", "precision", "recall"]:
             c = f"char_level:{c}"
             v = statistics[c]
-            print(f"{c:>40s} {v:.4f}")
+            safe_print(f"{c:>40s} {v:.4f}")
 
         for c in [
             "total_words_in_sample",
@@ -137,20 +138,20 @@ def __init__(self, name, argv):
         ]:
             c = f"word_level:{c}"
             v = statistics[c]
-            print(f"{c:>40s} {v:.4f}")
+            safe_print(f"{c:>40s} {v:.4f}")
 
         if args.save_details:
             dir_name = os.path.dirname(args.input_file)
             file_name = args.input_file.split("/")[-1].split(".")[0]
 
             res_path = "%s/eval-%s.yml" % (dir_name, file_name)
-            print("Evaluation result is saved to %s" % res_path)
+            safe_print("Evaluation result is saved to %s" % res_path)
 
             with open(res_path, "w", encoding="utf-8") as outfile:
                 yaml.dump(statistics, outfile, default_flow_style=False)
 
             res_path = "%s/eval-details-%s.json" % (dir_name, file_name)
-            print("Details of comparisons is saved to %s" % res_path)
+            safe_print("Details of comparisons is saved to %s" % res_path)
 
             with open(res_path, "w", encoding="utf-8") as f:
                 samples = []
@@ -160,7 +161,12 @@ def __init__(self, name, argv):
                     del r["actual"]
 
                     samples.append(
-                        {"metrics": r, "expected": expected, "actual": actual, "id": i}
+                        {
+                            "metrics": r,
+                            "expected": expected,
+                            "actual": actual,
+                            "id": i,
+                        }
                     )
 
                 details = {"metrics": statistics, "samples": samples}

pythainlp/cli/data.py

@@ -4,10 +4,11 @@
 """
 Command line for PyThaiNLP's dataset/corpus management.
 """
+
 import argparse
 
 from pythainlp import corpus
-from pythainlp.tools import get_pythainlp_data_path
+from pythainlp.tools import get_pythainlp_data_path, safe_print
 
 
 class App:
@@ -55,9 +56,9 @@ def get(self, argv):
         )
         args = parser.parse_args(argv[3:])
         if corpus.download(args.dataset_name):
-            print("Downloaded successfully.")
+            safe_print("Downloaded successfully.")
         else:
-            print("Not found.")
+            safe_print("Not found.")
 
     def rm(self, argv):
         parser = argparse.ArgumentParser(
@@ -71,9 +72,9 @@ def rm(self, argv):
         )
         args = parser.parse_args(argv[3:])
         if corpus.remove(args.dataset_name):
-            print("Removed successfully.")
+            safe_print("Removed successfully.")
         else:
-            print("Not found.")
+            safe_print("Not found.")
 
     def info(self, argv):
         parser = argparse.ArgumentParser(
@@ -88,29 +89,29 @@ def info(self, argv):
         args = parser.parse_args(argv[3:])
         info = corpus.get_corpus_db_detail(args.dataset_name)
         if info:
-            print(info)
+            safe_print(info)
         else:
-            print("Not found.")
+            safe_print("Not found.")
 
     def catalog(self, argv):
         """Print dataset/corpus available for download."""
         corpus_db = corpus.get_corpus_db(corpus.corpus_db_url())
         corpus_db = corpus_db.json()
         corpus_names = sorted(corpus_db.keys())
-        print("Dataset/corpus available for download:")
+        safe_print("Dataset/corpus available for download:")
         for name in corpus_names:
-            print(f"- {name} {corpus_db[name]['latest_version']}", end="")
+            safe_print(f"- {name} {corpus_db[name]['latest_version']}", end="")
             corpus_info = corpus.get_corpus_db_detail(name)
             if corpus_info:
-                print(f"  (Local: {corpus_info['version']})")
+                safe_print(f"  (Local: {corpus_info['version']})")
             else:
-                print()
+                safe_print()
 
-        print(
+        safe_print(
             "\nUse subcommand 'get' to download a dataset.\n\n"
             "Example: thainlp data get crfcut\n"
         )
 
     def path(self, argv):
         """Print path of local dataset."""
-        print(get_pythainlp_data_path())
+        safe_print(get_pythainlp_data_path())

pythainlp/cli/tag.py

@@ -4,10 +4,12 @@
 """
 Command line for PyThaiNLP's taggers.
 """
+
 import argparse
 
 from pythainlp import cli
 from pythainlp.tag import pos_tag
+from pythainlp.tools import safe_print
 
 
 class SubAppBase:
@@ -34,7 +36,7 @@ def __init__(self, name, argv):
         result = self.run(tokens)
 
         for word, tag in result:
-            print(word, "/", tag)
+            safe_print(word, "/", tag)
 
 
 class POSTaggingApp(SubAppBase):
@@ -73,4 +75,4 @@ def __init__(self, argv):
         if tag_type == "pos":
             POSTaggingApp("Part-of-Speech tagging", argv)
         else:
-            print(f"Tag type not available: {tag_type}")
+            safe_print(f"Tag type not available: {tag_type}")