♻️refactor(project): adapt to new naming of parsing methods

adapt to new naming of parsing methods, remove unused paths in parser module, all module import logwatcher.config instead of importing logwatcher, rename test functions

src/logwatcher/__init__.py

@@ -2,7 +2,5 @@ from importlib.metadata import version
 
 from dotenv import load_dotenv
 
-from logwatcher.config import *
-
 __version__ = version("logwatcher")
 load_dotenv()

src/logwatcher/config.py

@@ -3,12 +3,12 @@ from enum import Enum
 from pathlib import Path
 
 ### GENERAL DATA
-# output path
+# output paths
 OUTPUT_PATH = Path("output")
 RESULT_PATH = OUTPUT_PATH / "results"
 LOGGING_PATH = OUTPUT_PATH / "logs"
 
-# test path
+# test paths
 TEST_PATH = Path("tests")
 FIXTURE_PATH = TEST_PATH / "fixtures"
 

src/logwatcher/logging_config.py

@@ -1,10 +1,12 @@
 import logging
 from pathlib import Path
 
+from logwatcher.config import DATETIME_FORMAT
+
 
 def _setup_formatter(
     format: str = "[%(asctime)s] - %(levelname)s: %(message)s",
-    datefmt: str = "%d/%m/%Y %H:%M:%S",
+    datefmt: str = DATETIME_FORMAT,
 ) -> logging.Formatter:
     return logging.Formatter(fmt=format, datefmt=datefmt)
 
@@ -22,26 +24,6 @@ def _setup_handler(
     return handler
 
 
-def _convert_string_to_log_level(log_level: str) -> int:
-    """
-    Get a log_level that contains one or three 'v' characters.
-    'v' = ERROR = 40
-    'vv' = WARNING = 30
-    'vvv' = DEBUG = 10
-    Args:
-        log_level:
-
-    Returns:
-
-    """
-    if log_level == "v":
-        return logging.ERROR
-    elif log_level == "vv":
-        return logging.WARNING
-    else:
-        return logging.DEBUG
-
-
 def setup_logging(
     formatter: logging.Formatter | None = None,
     file_path: Path = Path("output/logs/logwatcher.log"),

src/logwatcher/models.py

@@ -1,7 +1,7 @@
 from dataclasses import dataclass
 from datetime import datetime
 
-from logwatcher import DATETIME_FORMAT
+from logwatcher.config import DATETIME_FORMAT
 
 
 @dataclass()
@@ -9,6 +9,7 @@ class LogEntry:
     """
     Represents a line in log file.
     """
+
     server_ip: str
     mdc_server_name: str
     start_time: datetime
@@ -36,4 +37,6 @@ class LogEntry:
         """
         # error time cannot be earlier than start time
         if self.start_time > self.error_time:
-            raise ValueError(f"Error in date-times : error_time '{self.error_time}' cannot be earlier than start_time '{self.start_time}")
+            raise ValueError(
+                f"Error in date-times : error_time '{self.error_time}' cannot be earlier than start_time '{self.start_time}"
+            )

src/logwatcher/parser.py

@@ -4,7 +4,7 @@ from collections.abc import Iterable
 from datetime import datetime
 from pathlib import Path
 
-from logwatcher import DATETIME_FORMAT, FRENCH_TIMEZONE
+from logwatcher.config import DATETIME_FORMAT, FRENCH_TIMEZONE
 from logwatcher.models import LogEntry
 
 logger = logging.getLogger(__name__)
@@ -29,12 +29,6 @@ LOG_PATTERN = re.compile(
     rf"(?P<error_message>{ERROR_MESSAGE_PATTERN})"
 )
 
-# misc log file
-misc_file_path = Path.cwd() / "output/misc.log"
-
-# effective logs
-effective_file_path = Path.cwd() / "output/effective.log"
-
 
 def parse_line(log_line: str) -> LogEntry | None:
     """

tests/test_classifier.py

@@ -6,7 +6,7 @@ import pytest
 
 from logwatcher.classifier import N2_PATTERNS, classify_log_entries
 from logwatcher.config import FIXTURE_PATH
-from logwatcher.parser import parse_log_file
+from logwatcher.parser import parse_file
 
 
 def _pattern_name_to_filename(name: str) -> str:
@@ -15,6 +15,7 @@ def _pattern_name_to_filename(name: str) -> str:
     """
     return f"CR_{name.lower()}.txt"
 
+
 def _read_fixture(path: Path) -> str:
     """
     Read a file with fallback Windows-1252.
@@ -27,6 +28,7 @@ def _read_fixture(path: Path) -> str:
         return content
     return path.read_text(encoding="windows-1252")  # TODO: improve coverage score
 
+
 @pytest.mark.parametrize("name, pattern", N2_PATTERNS.items())
 def test_pattern_matches_fixture(valid_log_dir, name, pattern):
     """
@@ -39,10 +41,7 @@ def test_pattern_matches_fixture(valid_log_dir, name, pattern):
         warnings.warn(msg)
         pytest.skip(msg)
 
-    lignes = [
+    lignes = [l for l in _read_fixture(fixture).splitlines() if l.strip()]
-        l for l in _read_fixture(fixture).splitlines()
-        if l.strip()
-    ]
 
     assert lignes, f"empty fixture file : {fixture}"
 
@@ -54,8 +53,7 @@ def test_pattern_matches_fixture(valid_log_dir, name, pattern):
             match_count += 1
 
     assert match_count > 0, (
-        f"{name} : no match in file {fixture.name}\n"
+        f"{name} : no match in file {fixture.name}\npattern: {pattern}"
-        f"pattern: {pattern}"
     )
 
 
@@ -65,10 +63,13 @@ def test_patterns_do_not_overlap():
     """
     fixtures_dir = FIXTURE_PATH
     for fixture in fixtures_dir.glob("CR_*.txt"):
-        line_list = [line for line in _read_fixture(fixture).splitlines() if line.strip()]  # TODO: improve coverage score
+        line_list = [
+            line for line in _read_fixture(fixture).splitlines() if line.strip()
+        ]  # TODO: improve coverage score
         for line in line_list:  # TODO: improve coverage score
             matching = [  # TODO: improve coverage score
-                name for name, raw in N2_PATTERNS.items()
+                name
+                for name, raw in N2_PATTERNS.items()
                 if re.compile(raw).search(line)
             ]
             assert len(matching) <= 1, (  # TODO: improve coverage score
@@ -76,6 +77,7 @@ def test_patterns_do_not_overlap():
                 f"{matching} match line : {line[:80]}"
             )
 
+
 def test_no_orphan_fixtures():
     """
     Assert that a fixture exist only if its associated pattern exists.
@@ -92,7 +94,7 @@ def test_classify_log_entries_all_relevant(valid_log_dir: Path):
     Must return an empty irrelevant log entry list
     """
     log_file = valid_log_dir / "only_relevant_logs.txt"
-    log_entries = parse_log_file(log_file)
+    log_entries = parse_file(log_file)
 
     # all entries are relevant
     relevant, irrelevant = classify_log_entries(log_entries)
@@ -105,7 +107,7 @@ def test_classify_log_entries_none_relevant(valid_log_dir: Path):
     Must return an empty relevant log entry list
     """
     log_file = valid_log_dir / "no_relevant_logs.txt"
-    log_entries = parse_log_file(log_file)
+    log_entries = parse_file(log_file)
 
     # all entries are relevant
     relevant, irrelevant = classify_log_entries(log_entries)
@@ -118,7 +120,7 @@ def test_classify_log_entries_mixed(valid_log_dir: Path):
     Test classification on relevant and irrelevant log entry list
     """
     log_file = valid_log_dir / "mixed_logs.txt"
-    log_entries = parse_log_file(log_file)
+    log_entries = parse_file(log_file)
 
     relevant, irrelevant = classify_log_entries(log_entries)
 
@@ -131,7 +133,7 @@ def test_classify_log_entries_empty_log_entries(invalid_log_dir: Path):
     Test classification on an empty log entry list
     """
     empty_file = invalid_log_dir / "empty_file.txt"
-    log_entries = parse_log_file(empty_file)
+    log_entries = parse_file(empty_file)
 
     relevant, irrelevant = classify_log_entries(log_entries)
 

tests/test_logging.py

@@ -15,6 +15,7 @@ from logging import DEBUG, ERROR, INFO, WARNING, FileHandler, StreamHandler, get
 
 import pytest
 
+from logwatcher.config import DATETIME_FORMAT
 from logwatcher.logging_config import _setup_formatter, _setup_handler, setup_logging
 
 
@@ -54,7 +55,7 @@ def test_type_of_handlers():
         else:
             pytest.fail("handlers must be either a file or a stream handler")
         assert handler.formatter._fmt == "[%(asctime)s] - %(levelname)s: %(message)s"
-        assert handler.formatter.datefmt == "%d/%m/%Y %H:%M:%S"
+        assert handler.formatter.datefmt == DATETIME_FORMAT
 
 
 def test_modified_format():

tests/test_models.py

@@ -2,7 +2,7 @@ from datetime import datetime
 
 import pytest
 
-from logwatcher import DATETIME_FORMAT, FRENCH_TIMEZONE
+from logwatcher.config import DATETIME_FORMAT, FRENCH_TIMEZONE
 from logwatcher.models import LogEntry
 
 

tests/test_parser.py

@@ -57,7 +57,7 @@ def test_parse_line(specific_logs: list[str]):
         assert log_entry.raw_line != ""
 
 
-def test_parse_empty_log_line():
+def test_parse_empty_line():
     """
     An empty or structurally invalid line returns None.
     Covered cases:
@@ -71,7 +71,15 @@ def test_parse_empty_log_line():
     assert not log_entry
 
 
-def test_parse_valid_log_file(original_log_dir: Path):
+def test_parse_lines():
+    pass
+
+
+def test_parse_empty_lines():
+    pass
+
+
+def test_parse_valid_file(original_log_dir: Path):
     """
     Each real log file produces at least one valid LogEntry.
     Integration test: files provided by technicians contain
@@ -86,7 +94,7 @@ def test_parse_valid_log_file(original_log_dir: Path):
             assert isinstance(log_entry, LogEntry)
 
 
-def test_parse_empty_log_file(empty_log_file):
+def test_parse_empty_file(empty_log_file):
     """
     An empty log file can be parsed and must returns an
     empty LogEntry list.
@@ -95,7 +103,7 @@ def test_parse_empty_log_file(empty_log_file):
     assert len(log_list) == 0
 
 
-def test_parse_bad_log_file(bad_log_file):
+def test_parse_bad_file(bad_log_file):
     """
     A file containing only invalid lines produces nothing.
     Any line that does not match the LAME MDC structure

tests/test_reporter.py

@@ -6,7 +6,7 @@ import pytest
 from logwatcher.classifier import classify_log_entries
 from logwatcher.config import DATETIME_FORMAT, FIXTURE_PATH, SourceType
 from logwatcher.models import LogEntry
-from logwatcher.parser import parse_log_file
+from logwatcher.parser import parse_file
 from logwatcher.reporter import (
     N2_SUPPORT_TEMPLATE,
     OTHER_TEMPLATE,
@@ -25,7 +25,7 @@ def _get_classified_log_entries(
     log_file: Path,
 ) -> tuple[list[LogEntry], list[LogEntry]]:
     """Parse a log file and split its entries into relevant and irrelevant lists."""
-    log_entries = parse_log_file(log_file)
+    log_entries = parse_file(log_file)
     return classify_log_entries(log_entries)
 
 
@@ -40,7 +40,7 @@ def get_all_log_entries_fixture() -> tuple[list[LogEntry], list[LogEntry]]:
     """Parse and classify every CR_* fixture, returning (relevant, irrelevant)."""
     all_entries = []
     for log_file in CR_LOG_FILES:
-        all_entries.extend(parse_log_file(log_file))
+        all_entries.extend(parse_file(log_file))
     relevant_list, irrelevant_list = classify_log_entries(all_entries)
     return relevant_list, irrelevant_list