pystylometry 1.0.0__py3-none-any.whl → 1.3.0__py3-none-any.whl

pystylometry/README.md

@@ -0,0 +1,42 @@
+# pystylometry
+
+![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue)
+![License: MIT](https://img.shields.io/badge/license-MIT-green)
+
+Core package for stylometric analysis and authorship attribution.
+
+## Module Map
+
+| Module | Purpose | Key Functions |
+|--------|---------|---------------|
+| [`lexical/`](lexical/) | Vocabulary diversity & richness | `compute_mtld`, `compute_yule`, `compute_ttr`, `compute_hapax_ratios` |
+| [`readability/`](readability/) | Text readability scoring | `compute_flesch`, `compute_gunning_fog`, `compute_ari`, `compute_smog` |
+| [`syntactic/`](syntactic/) | Sentence & parse structure | `compute_pos_ratios`, `compute_sentence_types`, `compute_advanced_syntactic` |
+| [`authorship/`](authorship/) | Author attribution & comparison | `compute_burrows_delta`, `compute_kilgarriff`, `compute_compression_distance` |
+| [`stylistic/`](stylistic/) | Style markers & vocabulary overlap | `compute_stylistic_markers`, `compute_vocabulary_overlap`, `compute_genre_register` |
+| [`character/`](character/) | Character-level features | `compute_character_metrics` |
+| [`ngrams/`](ngrams/) | N-gram entropy & sequences | `compute_extended_ngrams`, `compute_ngram_entropy` |
+| [`dialect/`](dialect/) | Regional dialect detection | `compute_dialect` |
+| [`consistency/`](consistency/) | Intra-document drift detection | `compute_kilgarriff_drift` |
+| [`prosody/`](prosody/) | Rhythm & stress patterns | `compute_rhythm_prosody` |
+| [`viz/`](viz/) | Visualization (PNG & interactive HTML) | `plot_drift_timeline`, `export_drift_report_jsx` |
+
+## Shared Internals
+
+| File | Purpose |
+|------|---------|
+| `_types.py` | All dataclass result types (e.g. `FleschResult`, `MTLDResult`, `KilgarriffDriftResult`) |
+| `_normalize.py` | Text normalization for readability and stylometry pipelines |
+| `_utils.py` | Shared tokenization and helper functions |
+| `tokenizer.py` | Configurable tokenizer with sentence/word splitting |
+| `cli.py` | Command-line interface (`pystylometry analyze`) |
+
+## Installation Extras
+
+```
+pip install pystylometry                  # Core (lexical only)
+pip install pystylometry[readability]     # + readability
+pip install pystylometry[syntactic]       # + syntactic (requires spaCy)
+pip install pystylometry[authorship]      # + authorship attribution
+pip install pystylometry[all]             # Everything
+```

pystylometry/__init__.py

@@ -2,7 +2,7 @@
 pystylometry - Comprehensive Python package for stylometric analysis.
 
 A modular package for text analysis with lexical, readability, syntactic,
-authorship, and n-gram metrics.
+authorship, n-gram, dialect detection, and consistency analysis metrics.
 
 Installation:
     pip install pystylometry                    # Core (lexical only)
@@ -16,7 +16,9 @@ Usage:
     from pystylometry.lexical import compute_mtld, compute_yule
     from pystylometry.readability import compute_flesch
     from pystylometry.syntactic import compute_pos_ratios
-    from pystylometry.authorship import compute_burrows_delta
+    from pystylometry.authorship import compute_burrows_delta, compute_kilgarriff
+    from pystylometry.consistency import compute_kilgarriff_drift
+    from pystylometry.dialect import compute_dialect
 
     # Or use the unified analyze() function
     from pystylometry import analyze
@@ -24,6 +26,18 @@ Usage:
     results = analyze(text, lexical=True, readability=True)
     print(results.lexical['mtld'].mtld_average)
     print(results.readability['flesch'].reading_ease)
+
+    # Dialect detection
+    result = compute_dialect("The colour of the programme was brilliant.")
+    print(result.dialect)  # 'british'
+    print(result.british_score)  # 0.85
+
+    # Consistency analysis (Style Drift Detector - Issue #36)
+    from pystylometry.consistency import compute_kilgarriff_drift
+
+    result = compute_kilgarriff_drift(long_document)
+    print(result.pattern)  # 'consistent', 'sudden_spike', 'suspiciously_uniform', etc.
+    print(result.pattern_confidence)
 """
 
 from ._types import AnalysisResult
@@ -49,14 +63,28 @@ try:
 except ImportError:
     _SYNTACTIC_AVAILABLE = False
 
-# Authorship and ngrams use only stdlib (no external dependencies)
+# Prosody requires pronouncing (CMU dictionary) - same dependency as readability
+try:
+    from . import prosody  # noqa: F401 - Rhythm and prosody metrics (Issue #25)
+
+    _PROSODY_AVAILABLE = True
+except ImportError:
+    _PROSODY_AVAILABLE = False
+
+# Authorship, ngrams, dialect, consistency, and stylistic use only stdlib (no external dependencies)
 from . import (
     authorship,  # noqa: F401
+    consistency,  # noqa: F401 - Style drift detection (Issue #36)
+    dialect,  # noqa: F401
     ngrams,  # noqa: F401
+    stylistic,  # noqa: F401 - Vocabulary overlap and similarity (Issue #21)
 )
 
 _AUTHORSHIP_AVAILABLE = True
 _NGRAMS_AVAILABLE = True
+_DIALECT_AVAILABLE = True
+_CONSISTENCY_AVAILABLE = True
+_STYLISTIC_AVAILABLE = True
 
 
 def analyze(
@@ -177,6 +205,8 @@ def get_available_modules() -> dict[str, bool]:
         >>> available = get_available_modules()
         >>> if available['readability']:
         ...     from pystylometry.readability import compute_flesch
+        >>> if available['consistency']:
+        ...     from pystylometry.consistency import compute_kilgarriff_drift
     """
     return {
         "lexical": True,  # Always available
@@ -184,6 +214,10 @@ def get_available_modules() -> dict[str, bool]:
         "syntactic": _SYNTACTIC_AVAILABLE,
         "authorship": _AUTHORSHIP_AVAILABLE,
         "ngrams": _NGRAMS_AVAILABLE,
+        "dialect": _DIALECT_AVAILABLE,
+        "consistency": _CONSISTENCY_AVAILABLE,  # Style drift detection (Issue #36)
+        "stylistic": _STYLISTIC_AVAILABLE,  # Vocabulary overlap (Issue #21)
+        "prosody": _PROSODY_AVAILABLE,  # Rhythm and prosody (Issue #25)
     }
 
 
@@ -203,3 +237,11 @@ if _AUTHORSHIP_AVAILABLE:
     __all__.append("authorship")
 if _NGRAMS_AVAILABLE:
     __all__.append("ngrams")
+if _DIALECT_AVAILABLE:
+    __all__.append("dialect")
+if _CONSISTENCY_AVAILABLE:
+    __all__.append("consistency")
+if _STYLISTIC_AVAILABLE:
+    __all__.append("stylistic")
+if _PROSODY_AVAILABLE:
+    __all__.append("prosody")