style: Fix code formatting with ruff format

Applied ruff formatting to ensure code style consistency.
No functional changes.

Author: florath

src/aletheia_probe/bibtex_parser.py

@@ -378,7 +378,7 @@ def _remove_nested_braces(value: str) -> str:
 
         # Remove nested curly braces iteratively until none remain
         # This handles multiple levels like {{{text}}} -> {{text}} -> {text} -> text
-        while re.search(r'\{[^{}]*\}', value):
-            value = re.sub(r'\{([^{}]*)\}', r'\1', value)
+        while re.search(r"\{[^{}]*\}", value):
+            value = re.sub(r"\{([^{}]*)\}", r"\1", value)
 
         return value.strip()

src/aletheia_probe/normalizer.py

@@ -21,13 +21,61 @@ def __init__(self) -> None:
 
         # Common acronyms that should remain uppercase
         self.acronyms = {
-            "IEEE", "ACM", "SIGCOMM", "SIGCHI", "SIGKDD", "SIGMOD", "SIGPLAN",
-            "VLDB", "ICML", "NIPS", "NEURIPS", "ICLR", "AAAI", "IJCAI", "CIKM",
-            "WWW", "KDD", "ICDM", "SDM", "PAKDD", "ECML", "PKDD", "CLOUD",
-            "NASA", "NIH", "NSF", "DARPA", "NIST", "ISO", "IEC", "ITU",
-            "RFC", "HTTP", "TCP", "IP", "UDP", "DNS", "SSL", "TLS",
-            "AI", "ML", "NLP", "CV", "HCI", "DB", "OS", "SE", "PL",
-            "UK", "USA", "US", "EU", "UN", "WHO", "NATO"
+            "IEEE",
+            "ACM",
+            "SIGCOMM",
+            "SIGCHI",
+            "SIGKDD",
+            "SIGMOD",
+            "SIGPLAN",
+            "VLDB",
+            "ICML",
+            "NIPS",
+            "NEURIPS",
+            "ICLR",
+            "AAAI",
+            "IJCAI",
+            "CIKM",
+            "WWW",
+            "KDD",
+            "ICDM",
+            "SDM",
+            "PAKDD",
+            "ECML",
+            "PKDD",
+            "CLOUD",
+            "NASA",
+            "NIH",
+            "NSF",
+            "DARPA",
+            "NIST",
+            "ISO",
+            "IEC",
+            "ITU",
+            "RFC",
+            "HTTP",
+            "TCP",
+            "IP",
+            "UDP",
+            "DNS",
+            "SSL",
+            "TLS",
+            "AI",
+            "ML",
+            "NLP",
+            "CV",
+            "HCI",
+            "DB",
+            "OS",
+            "SE",
+            "PL",
+            "UK",
+            "USA",
+            "US",
+            "EU",
+            "UN",
+            "WHO",
+            "NATO",
         }
 
         # Common abbreviation expansions
@@ -135,19 +183,19 @@ def _remove_bracketed_content(self, text: str) -> str:
         """
         # Remove nested curly braces (BibTeX formatting) - handle multiple levels
         # This handles cases like {{IEEE}} -> IEEE
-        while re.search(r'\{[^{}]*\}', text):
-            text = re.sub(r'\{([^{}]*)\}', r'\1', text)
+        while re.search(r"\{[^{}]*\}", text):
+            text = re.sub(r"\{([^{}]*)\}", r"\1", text)
 
         # Remove content within square brackets [...]
         # This handles abbreviations and annotations like [2023], [Online]
-        text = re.sub(r'\[[^\]]*\]', '', text)
+        text = re.sub(r"\[[^\]]*\]", "", text)
 
         # Remove content within parentheses (...)
         # This handles journal/conference abbreviations like (NeurIPS), (CLOUD)
-        text = re.sub(r'\([^)]*\)', '', text)
+        text = re.sub(r"\([^)]*\)", "", text)
 
         # Clean up multiple spaces left by bracket removal
-        text = re.sub(r'\s+', ' ', text)
+        text = re.sub(r"\s+", " ", text)
 
         return text.strip()
 

tests/unit/test_bibtex_parser.py

@@ -727,7 +727,9 @@ def test_nested_brace_removal(self):
         assert result == "CLOUD"
 
         # Mixed content with multiple braced sections
-        result = BibtexParser._remove_nested_braces("{{IEEE}} {{International Conference}} on {{Cloud Computing}}")
+        result = BibtexParser._remove_nested_braces(
+            "{{IEEE}} {{International Conference}} on {{Cloud Computing}}"
+        )
         assert result == "IEEE International Conference on Cloud Computing"
 
         # Text without braces should remain unchanged
@@ -761,11 +763,15 @@ def test_parse_bibtex_conference_with_nested_braces(self, tmp_path):
         entry = entries[0]
 
         # Title should have nested braces removed
-        expected_title = "Software Greenability: A Case Study of Cloud-Based Applications"
+        expected_title = (
+            "Software Greenability: A Case Study of Cloud-Based Applications"
+        )
         assert entry.title == expected_title
 
         # Conference name should have nested braces removed
-        expected_conference = "2018 IEEE 11th International Conference on Cloud Computing (CLOUD)"
+        expected_conference = (
+            "2018 IEEE 11th International Conference on Cloud Computing (CLOUD)"
+        )
         assert entry.journal_name == expected_conference
 
     def test_parse_bibtex_journal_with_nested_braces(self, tmp_path):

tests/unit/test_normalizer.py

@@ -143,12 +143,22 @@ def test_bracket_removal_parentheses(self):
         normalizer = InputNormalizer()
 
         # Test journal name with abbreviation in parentheses
-        result = normalizer.normalize("Advances in Neural Information Processing Systems (NeurIPS)")
-        assert result.normalized_name == "Advances in Neural Information Processing Systems"
-        assert result.raw_input == "Advances in Neural Information Processing Systems (NeurIPS)"
+        result = normalizer.normalize(
+            "Advances in Neural Information Processing Systems (NeurIPS)"
+        )
+        assert (
+            result.normalized_name
+            == "Advances in Neural Information Processing Systems"
+        )
+        assert (
+            result.raw_input
+            == "Advances in Neural Information Processing Systems (NeurIPS)"
+        )
 
         # Test conference name with abbreviation in parentheses
-        result2 = normalizer.normalize("International Conference on Cloud Computing (CLOUD)")
+        result2 = normalizer.normalize(
+            "International Conference on Cloud Computing (CLOUD)"
+        )
         assert result2.normalized_name == "International Conference on CLOUD Computing"
 
     def test_bracket_removal_square_brackets(self):
@@ -172,8 +182,13 @@ def test_bracket_removal_curly_braces(self):
         assert result.normalized_name == "IEEE Conference"
 
         # Test nested braces (BibTeX style)
-        result2 = normalizer.normalize("{{IEEE}} {{International Conference}} on {{Cloud Computing}}")
-        assert result2.normalized_name == "IEEE International Conference on CLOUD Computing"
+        result2 = normalizer.normalize(
+            "{{IEEE}} {{International Conference}} on {{Cloud Computing}}"
+        )
+        assert (
+            result2.normalized_name
+            == "IEEE International Conference on CLOUD Computing"
+        )
 
         # Test triple nested braces
         result3 = normalizer.normalize("{{{CLOUD}}} Conference")
@@ -184,12 +199,16 @@ def test_bracket_removal_mixed_brackets(self):
         normalizer = InputNormalizer()
 
         # Test combination of all bracket types
-        result = normalizer.normalize("2018 {{IEEE}} 11th {International Conference} on [Cloud] Computing (CLOUD)")
+        result = normalizer.normalize(
+            "2018 {{IEEE}} 11th {International Conference} on [Cloud] Computing (CLOUD)"
+        )
         expected = "2018 IEEE 11th International Conference on Computing"  # IEEE preserved as acronym
         assert result.normalized_name == expected
 
         # Test real BibTeX example
-        result2 = normalizer.normalize("2018 {{IEEE}} 11th {{International Conference}} on {{Cloud Computing}} ({{CLOUD}})")
+        result2 = normalizer.normalize(
+            "2018 {{IEEE}} 11th {{International Conference}} on {{Cloud Computing}} ({{CLOUD}})"
+        )
         expected2 = "2018 IEEE 11th International Conference on CLOUD Computing"  # IEEE and CLOUD preserved as acronyms
         assert result2.normalized_name == expected2