Retire pylint and isort in favor of ruff

.github/workflows/ruff.yml

@@ -0,0 +1,10 @@
+name: Ruff
+on:
+  - pull_request
+
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: chartboost/ruff-action@v1

README.md

@@ -13,7 +13,6 @@
 [![Downloads](https://static.pepy.tech/badge/chat-miner/month)](https://pepy.tech/project/chat-miner)
 [![codecov](https://codecov.io/gh/joweich/chat-miner/branch/main/graph/badge.svg?token=6EQF0YNGLK)](https://codecov.io/gh/joweich/chat-miner)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
-[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
 
 **chat-miner** provides lean parsers for every major platform transforming chats into pandas dataframes. Artistic visualizations allow you to explore your data and create artwork from your chats.
 
@@ -127,4 +126,4 @@ options:
                         Input file to be processed
   -o OUTPUT, --output OUTPUT
                         Output file for the results
-```
+```

chatminer/chatparsers.py

@@ -68,7 +68,7 @@ def __init__(self, filepath: str):
     def parse_file(self):
         self._logger.info("Starting reading raw messages...")
         self._read_raw_messages_from_file()
-        self._logger.info(f"Finished reading %i raw messages.", len(self._raw_messages))
+        self._logger.info("Finished reading %i raw messages.", len(self._raw_messages))
 
         self._logger.info("Starting parsing raw messages...")
         self._parse_raw_messages()
@@ -191,7 +191,7 @@ def _parse_message(self, mess: Dict[str, Any]):
         elif "content" in mess:
             body = mess["content"]
         else:
-            self._logger.warning(f"Skipped message with unknown format: %s", mess)
+            self._logger.warning("Skipped message with unknown format: %s", mess)
             return None
 
         time = dt.datetime.fromtimestamp(mess["timestamp_ms"] / 1000)
@@ -233,7 +233,7 @@ def _parse_message(self, mess: Dict[str, Any]):
         elif any(key == "is_unsent" for key in mess):
             return None
         else:
-            self._logger.warning(f"Skipped message with unknown format: %s", mess)
+            self._logger.warning("Skipped message with unknown format: %s", mess)
             return None
 
         time = dt.datetime.fromtimestamp(mess["timestamp_ms"] / 1000)

chatminer/cli.py

@@ -14,74 +14,61 @@
 
 def get_args():
     try:
-        parser = argparse.ArgumentParser(
+        cliparser = argparse.ArgumentParser(
             description="chat-miner provides lean parsers for every major platform transforming chats into pandas dataframes.\
              Artistic visualizations allow you to explore your data and create artwork from your chats."
         )
 
-        parser.add_argument(
+        cliparser.add_argument(
             "-p",
             "--parser",
             type=str,
             help="The platform from which the chats are imported",
             choices=["whatsapp", "instagram", "facebook", "signal", "telegram"],
         )
 
-        parser.add_argument(
+        cliparser.add_argument(
             "-i", "--input", type=str, help="Input file to be processed"
         )
 
-        parser.add_argument(
+        cliparser.add_argument(
             "-o", "--output", type=str, help="Output file for the results"
         )
 
-        return parser.parse_args(), parser
-    except:
+        return cliparser.parse_args(), cliparser
+    except KeyboardInterrupt:
         sys.exit()
 
 
 def main():
     try:
-        args, parser = get_args()
+        args, cliparser = get_args()
 
-        parser_type = args.parser
-        INPUT_FILE = args.input
-        OUTPUT_FILE = args.output
-
-        if INPUT_FILE == None or OUTPUT_FILE == None or parser_type == None:
+        if args.input is None or args.output is None or args.parser is None:
             raise ValueError
 
-        if (parser_type).lower() == "whatsapp":
-            parser_type = WhatsAppParser(INPUT_FILE)
-            parser_type.parse_file()
-            output = parser_type.parsed_messages.get_df()
-
-        elif (parser_type).lower() == "facebook":
-            parser_type = FacebookMessengerParser(INPUT_FILE)
-            parser_type.parse_file()
-            output = parser_type.parsed_messages.get_df()
-
-        elif (parser_type).lower() == "instagram":
-            parser_type = InstagramJsonParser(INPUT_FILE)
-            parser_type.parse_file()
-            output = parser_type.parsed_messages.get_df()
-
-        elif (parser_type).lower() == "signal":
-            parser_type = SignalParser(INPUT_FILE)
-            parser_type.parse_file()
-            output = parser_type.parsed_messages.get_df()
-
-        elif (parser_type).lower() == "telegram":
-            parser_type = TelegramJsonParser(INPUT_FILE)
-            parser_type.parse_file()
-            output = parser_type.parsed_messages.get_df()
+        if (args.parser).lower() == "whatsapp":
+            chatparser = WhatsAppParser(args.input)
+
+        elif (args.parser).lower() == "facebook":
+            chatparser = FacebookMessengerParser(args.input)
+        elif (args.parser).lower() == "instagram":
+            chatparser = InstagramJsonParser(args.input)
+        elif (args.parser).lower() == "signal":
+            chatparser = SignalParser(args.input)
+        elif (args.parser).lower() == "telegram":
+            chatparser = TelegramJsonParser(args.input)
+        else:
+            raise ValueError
 
-        output.to_csv(OUTPUT_FILE, index=False)
+        chatparser.parse_file()
+        df = chatparser.parsed_messages.get_df()
+        df.to_csv(args.output, index=False)
 
     except ValueError:
-        parser.print_usage()
+        cliparser.print_usage()
 
-    except:
+    except KeyboardInterrupt:
         sys.exit()
 
 

chatminer/nlp.py

@@ -39,8 +39,8 @@ def extract_sentiment(message: str) -> Optional[str]:
         """
         try:
             return str(sentiment_pipeline(message)[0]["label"])
-        except:
-            print(f"Error processing message: {message}")
+        except Exception as e:
+            print(f"Error processing message: {message}: {e}")
             return None
 
     df["sentiment"] = df["message"].apply(extract_sentiment)

pyproject.toml

@@ -1,6 +1,3 @@
 [build-system]
 requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
-
-[tool.isort]
-profile = "black"

test/vis/test_smoketest.py

@@ -4,5 +4,10 @@
 def test_visualization_import():
     try:
         import chatminer.visualizations as vis
+
+        assert hasattr(vis, "sunburst")
+        assert hasattr(vis, "wordcloud")
+        assert hasattr(vis, "calendar_heatmap")
+        assert hasattr(vis, "radar")
     except ImportError as e:
         pytest.fail(f"Error importing visualizations: {e}")