pystylometry 1.3.0__py3-none-any.whl → 1.3.5__py3-none-any.whl

pystylometry/lexical/ttr.py

@@ -1,149 +1,340 @@
-"""Type-Token Ratio (TTR) analysis using stylometry-ttr package.
+"""Type-Token Ratio (TTR) analysis with native chunked computation.
 
-This module provides a facade wrapper around the stylometry-ttr package,
-maintaining consistent API patterns with other pystylometry metrics.
+Computes multiple TTR variants for measuring lexical diversity (vocabulary
+richness). All metrics are computed per-chunk and wrapped in Distribution
+objects for stylometric fingerprinting.
 
-Related GitHub Issue:
+Previously delegated to the external ``stylometry-ttr`` package; now
+computed inline using only the Python standard library (``math`` and
+``statistics``).
+
+Related GitHub Issues:
     #27 - Native chunked analysis with Distribution dataclass
     https://github.com/craigtrim/pystylometry/issues/27
+
+    #43 - Inline stylometry-ttr into pystylometry (remove external dependency)
+    https://github.com/craigtrim/pystylometry/issues/43
+
+References:
+    Guiraud, P. (1960). Problèmes et méthodes de la statistique linguistique.
+    Herdan, G. (1960). Type-token Mathematics: A Textbook of Mathematical
+        Linguistics. Mouton.
+    Johnson, W. (1944). Studies in language behavior: I. A program of research.
+        Psychological Monographs, 56(2), 1-15.
 """
 
 from __future__ import annotations
 
-from .._types import Distribution, TTRResult, make_distribution
+import math
+import statistics
+from typing import Optional
+
+from .._types import Distribution, TTRAggregateResult, TTRResult, make_distribution
+from ..tokenizer import Tokenizer
+
+# ---------------------------------------------------------------------------
+# Internal helpers
+# ---------------------------------------------------------------------------
+
+# Minimum words required before STTR computation is meaningful.
+# With fewer words we cannot form at least two full chunks, so the
+# standardised metric would be unreliable.
+_MIN_WORDS_FOR_STTR = 2000
+
+
+def _compute_chunk_ttrs(tokens: list[str], chunk_size: int) -> list[float]:
+    """Compute per-chunk raw TTR values for non-overlapping chunks.
+
+    Only full-sized chunks are included so that every TTR is measured on the
+    same token count, keeping the standardised metric unbiased.
+
+    Args:
+        tokens: Full token list.
+        chunk_size: Number of tokens per chunk.
+
+    Returns:
+        List of per-chunk TTR values (may be empty if too few tokens).
+    """
+    total = len(tokens)
+    chunk_ttrs: list[float] = []
+    for i in range(0, total - chunk_size + 1, chunk_size):
+        chunk = tokens[i : i + chunk_size]
+        chunk_ttrs.append(len(set(chunk)) / chunk_size)
+    return chunk_ttrs
+
 
+def _compute_deltas(
+    chunk_ttrs: list[float],
+) -> tuple[Optional[float], Optional[float], Optional[float], Optional[float]]:
+    """Compute delta metrics: TTR(n) - TTR(n-1) for consecutive chunks.
 
-def compute_ttr(text: str, text_id: str | None = None, chunk_size: int = 1000) -> TTRResult:
+    Delta metrics capture chunk-to-chunk vocabulary variability:
+    - delta_mean: average change (positive = expanding vocabulary)
+    - delta_std: volatility of change (stylometric fingerprint)
+    - delta_min: largest negative swing
+    - delta_max: largest positive swing
+
+    Args:
+        chunk_ttrs: Per-chunk TTR values (needs >= 2 values).
+
+    Returns:
+        Tuple of (delta_mean, delta_std, delta_min, delta_max).
+        All ``None`` when fewer than 2 chunks are available.
     """
-    Compute Type-Token Ratio (TTR) metrics for vocabulary richness.
+    if len(chunk_ttrs) < 2:
+        return None, None, None, None
+
+    deltas = [chunk_ttrs[i] - chunk_ttrs[i - 1] for i in range(1, len(chunk_ttrs))]
+    d_mean = statistics.mean(deltas)
+    d_std = statistics.stdev(deltas) if len(deltas) > 1 else 0.0
+    return d_mean, d_std, min(deltas), max(deltas)
+
+
+# ---------------------------------------------------------------------------
+# Public API
+# ---------------------------------------------------------------------------
+
 
-    This is a facade wrapper around the stylometry-ttr package that provides
-    multiple TTR variants for measuring lexical diversity. TTR measures the
-    ratio of unique words (types) to total words (tokens).
+def compute_ttr(
+    text: str,
+    text_id: str | None = None,
+    chunk_size: int = 1000,
+) -> TTRResult:
+    """Compute Type-Token Ratio (TTR) metrics for vocabulary richness.
+
+    Tokenises the input with pystylometry's ``Tokenizer`` (lowercase, words
+    only), then computes five TTR-family metrics.  Each metric is computed
+    per-chunk and the full per-chunk distribution is exposed via a
+    ``Distribution`` object for stylometric fingerprinting.
 
     Metrics computed:
-    - Raw TTR: unique_words / total_words
-    - Root TTR (Guiraud's index): unique_words / sqrt(total_words)
-    - Log TTR (Herdan's C): log(unique_words) / log(total_words)
-    - STTR: Standardized TTR across fixed-size chunks (reduces length bias)
-    - Delta Std: Standard deviation of TTR across chunks (vocabulary consistency)
+        - **Raw TTR**: ``unique_words / total_words``
+        - **Root TTR** (Guiraud's index): ``unique_words / sqrt(total_words)``
+        - **Log TTR** (Herdan's C): ``log(unique_words) / log(total_words)``
+        - **STTR**: Mean TTR across fixed-size chunks (reduces length bias).
+          Only computed when the text has >= 2000 words.
+        - **Delta Std**: Std-dev of chunk-to-chunk TTR change (vocabulary
+          consistency).  Only computed when >= 2 chunks are available.
 
-    Related GitHub Issue:
+    Related GitHub Issues:
         #27 - Native chunked analysis with Distribution dataclass
         https://github.com/craigtrim/pystylometry/issues/27
 
+        #43 - Inline stylometry-ttr into pystylometry
+        https://github.com/craigtrim/pystylometry/issues/43
+
     References:
-        Guiraud, P. (1960). Problèmes et méthodes de la statistique linguistique.
+        Guiraud, P. (1960). Problèmes et méthodes de la statistique
+            linguistique.
         Herdan, G. (1960). Type-token Mathematics: A Textbook of Mathematical
             Linguistics. Mouton.
-        Johnson, W. (1944). Studies in language behavior: I. A program of research.
-            Psychological Monographs, 56(2), 1-15.
+        Johnson, W. (1944). Studies in language behavior: I. A program of
+            research. Psychological Monographs, 56(2), 1-15.
 
     Args:
-        text: Input text to analyze
-        text_id: Optional identifier for the text (for tracking purposes)
-        chunk_size: Number of words per chunk (default: 1000).
-            Note: The stylometry-ttr package handles its own internal chunking,
-            so this parameter is included for API consistency but actual chunking
-            behavior is delegated to stylometry-ttr.
+        text: Input text to analyse.
+        text_id: Optional identifier for the text (stored in metadata).
+        chunk_size: Number of words per chunk for STTR and per-chunk
+            distributions (default: 1000).
 
     Returns:
-        TTRResult with all TTR variants and metadata, including Distribution
-        objects for stylometric fingerprinting.
+        TTRResult with all TTR variants, Distribution objects, and metadata.
 
     Example:
         >>> result = compute_ttr("The quick brown fox jumps over the lazy dog.")
         >>> print(f"Raw TTR: {result.ttr:.3f}")
-        Raw TTR: 0.900
+        Raw TTR: 1.000
         >>> print(f"Root TTR: {result.root_ttr:.3f}")
-        Root TTR: 2.846
-        >>> print(f"STTR: {result.sttr:.3f}")
-        STTR: 1.000
+        Root TTR: 3.000
 
         >>> # With text identifier
         >>> result = compute_ttr("Sample text here.", text_id="sample-001")
         >>> print(result.metadata["text_id"])
         sample-001
     """
-    try:
-        from stylometry_ttr import compute_ttr as _compute_ttr
-    except ImportError as e:
-        raise ImportError(
-            "TTR metrics require the stylometry-ttr package. "
-            "This should have been installed as a core dependency. "
-            "Install with: pip install stylometry-ttr"
-        ) from e
-
-    # Call the stylometry-ttr compute_ttr function
-    # Note: stylometry-ttr requires text_id to be a string, not None
-    ttr_result = _compute_ttr(text, text_id=text_id or "")
-
-    # Extract values, handling None for short texts
-    ttr_val = ttr_result.ttr
-    root_ttr_val = ttr_result.root_ttr
-    log_ttr_val = ttr_result.log_ttr
-    sttr_val = ttr_result.sttr if ttr_result.sttr is not None else 0.0
-    delta_std_val = ttr_result.delta_std if ttr_result.delta_std is not None else 0.0
-
-    # Create single-value distributions from stylometry-ttr results
-    # The stylometry-ttr package handles its own internal chunking for STTR
-    # so we wrap the aggregate results in Distribution objects
-    ttr_dist = (
-        make_distribution([ttr_val])
-        if ttr_val is not None
-        else Distribution(
-            values=[], mean=float("nan"), median=float("nan"), std=0.0, range=0.0, iqr=0.0
+    # Tokenise using pystylometry's own tokenizer (lowercase, words only)
+    tokenizer = Tokenizer(lowercase=True, strip_punctuation=True)
+    tokens = tokenizer.tokenize(text)
+
+    total_words = len(tokens)
+
+    # --- empty / trivial text --------------------------------------------------
+    if total_words == 0:
+        empty_dist = Distribution(
+            values=[],
+            mean=float("nan"),
+            median=float("nan"),
+            std=0.0,
+            range=0.0,
+            iqr=0.0,
         )
-    )
-    root_ttr_dist = (
-        make_distribution([root_ttr_val])
-        if root_ttr_val is not None
-        else Distribution(
-            values=[], mean=float("nan"), median=float("nan"), std=0.0, range=0.0, iqr=0.0
+        return TTRResult(
+            total_words=0,
+            unique_words=0,
+            ttr=0.0,
+            root_ttr=0.0,
+            log_ttr=0.0,
+            sttr=0.0,
+            delta_std=0.0,
+            ttr_dist=empty_dist,
+            root_ttr_dist=empty_dist,
+            log_ttr_dist=empty_dist,
+            sttr_dist=empty_dist,
+            delta_std_dist=empty_dist,
+            chunk_size=chunk_size,
+            chunk_count=0,
+            metadata={
+                "text_id": text_id or "",
+                "sttr_available": False,
+                "delta_std_available": False,
+            },
         )
-    )
-    log_ttr_dist = (
-        make_distribution([log_ttr_val])
-        if log_ttr_val is not None
-        else Distribution(
-            values=[], mean=float("nan"), median=float("nan"), std=0.0, range=0.0, iqr=0.0
-        )
-    )
-    sttr_dist = (
-        make_distribution([sttr_val])
-        if ttr_result.sttr is not None
-        else Distribution(
-            values=[], mean=float("nan"), median=float("nan"), std=0.0, range=0.0, iqr=0.0
+
+    # --- global metrics --------------------------------------------------------
+    unique_words = len(set(tokens))
+    ttr_val = unique_words / total_words
+    root_ttr_val = unique_words / math.sqrt(total_words)
+    log_ttr_val = math.log(unique_words) / math.log(total_words) if total_words > 1 else 0.0
+
+    # --- per-chunk metrics -----------------------------------------------------
+    chunk_ttrs = _compute_chunk_ttrs(tokens, chunk_size)
+    chunk_count = len(chunk_ttrs)
+
+    # STTR: mean TTR across chunks (only meaningful with enough text)
+    sttr_available = total_words >= _MIN_WORDS_FOR_STTR and chunk_count >= 1
+    if sttr_available:
+        sttr_val = statistics.mean(chunk_ttrs)
+    else:
+        sttr_val = 0.0
+
+    # Delta metrics
+    delta_mean, delta_std_val, delta_min, delta_max = _compute_deltas(chunk_ttrs)
+    delta_std_available = delta_std_val is not None
+    if delta_std_val is None:
+        delta_std_val = 0.0
+
+    # --- build Distribution objects --------------------------------------------
+    # For per-chunk distributions: compute root_ttr and log_ttr per chunk as well
+    if chunk_count >= 1:
+        ttr_dist = make_distribution(chunk_ttrs)
+
+        # Root TTR per chunk: for each chunk of chunk_size tokens,
+        # root_ttr = unique / sqrt(chunk_size)
+        root_ttr_chunks = [
+            len(set(tokens[i : i + chunk_size])) / math.sqrt(chunk_size)
+            for i in range(0, total_words - chunk_size + 1, chunk_size)
+        ]
+        root_ttr_dist = make_distribution(root_ttr_chunks)
+
+        # Log TTR per chunk
+        log_ttr_chunks = []
+        for i in range(0, total_words - chunk_size + 1, chunk_size):
+            chunk = tokens[i : i + chunk_size]
+            u = len(set(chunk))
+            t = len(chunk)
+            val = math.log(u) / math.log(t) if t > 1 else 0.0
+            log_ttr_chunks.append(val)
+        log_ttr_dist = make_distribution(log_ttr_chunks)
+
+        sttr_dist = (
+            make_distribution(chunk_ttrs) if sttr_available else make_distribution([sttr_val])
         )
-    )
-    delta_std_dist = (
-        make_distribution([delta_std_val])
-        if ttr_result.delta_std is not None
-        else Distribution(
-            values=[], mean=float("nan"), median=float("nan"), std=0.0, range=0.0, iqr=0.0
+        delta_std_dist = (
+            make_distribution([delta_std_val]) if delta_std_available else make_distribution([0.0])
         )
-    )
+    else:
+        # Not enough text for any chunks — wrap globals in single-value dists
+        ttr_dist = make_distribution([ttr_val])
+        root_ttr_dist = make_distribution([root_ttr_val])
+        log_ttr_dist = make_distribution([log_ttr_val])
+        sttr_dist = make_distribution([sttr_val])
+        delta_std_dist = make_distribution([0.0])
 
-    # Convert to our TTRResult dataclass
     return TTRResult(
-        total_words=ttr_result.total_words,
-        unique_words=ttr_result.unique_words,
-        ttr=ttr_val if ttr_val is not None else float("nan"),
-        root_ttr=root_ttr_val if root_ttr_val is not None else float("nan"),
-        log_ttr=log_ttr_val if log_ttr_val is not None else float("nan"),
-        sttr=sttr_val,
-        delta_std=delta_std_val,
+        total_words=total_words,
+        unique_words=unique_words,
+        ttr=round(ttr_val, 6),
+        root_ttr=round(root_ttr_val, 4),
+        log_ttr=round(log_ttr_val, 6),
+        sttr=round(sttr_val, 6),
+        delta_std=round(delta_std_val, 6),
         ttr_dist=ttr_dist,
         root_ttr_dist=root_ttr_dist,
         log_ttr_dist=log_ttr_dist,
         sttr_dist=sttr_dist,
         delta_std_dist=delta_std_dist,
         chunk_size=chunk_size,
-        chunk_count=1,  # stylometry-ttr returns aggregate results
+        chunk_count=chunk_count if chunk_count >= 1 else 1,
         metadata={
             "text_id": text_id or "",
-            "source": "stylometry-ttr",
-            "sttr_available": ttr_result.sttr is not None,
-            "delta_std_available": ttr_result.delta_std is not None,
+            "sttr_available": sttr_available,
+            "delta_std_available": delta_std_available,
         },
     )
+
+
+# ---------------------------------------------------------------------------
+# Aggregation
+# ---------------------------------------------------------------------------
+
+
+class TTRAggregator:
+    """Aggregate per-text TTR results into group-level statistics.
+
+    Useful for comparing vocabulary richness across authors, genres, or
+    time periods by computing summary statistics (mean, std, min, max,
+    median) over a collection of ``TTRResult`` objects.
+
+    Related GitHub Issue:
+        #43 - Inline stylometry-ttr into pystylometry
+        https://github.com/craigtrim/pystylometry/issues/43
+
+    Example:
+        >>> from pystylometry.lexical import compute_ttr, TTRAggregator
+        >>> results = [compute_ttr(t) for t in texts]
+        >>> agg = TTRAggregator()
+        >>> stats = agg.aggregate(results, group_id="Shakespeare")
+        >>> print(stats.ttr_mean)
+        0.412
+    """
+
+    def aggregate(self, results: list[TTRResult], group_id: str) -> TTRAggregateResult:
+        """Compute aggregate statistics from multiple TTR results.
+
+        Args:
+            results: List of per-text ``TTRResult`` objects.
+            group_id: Identifier for the group (e.g. author name).
+
+        Returns:
+            ``TTRAggregateResult`` with group-level statistics.
+
+        Raises:
+            ValueError: If *results* is empty.
+        """
+        if not results:
+            raise ValueError("Cannot aggregate empty results list")
+
+        ttrs = [r.ttr for r in results]
+        root_ttrs = [r.root_ttr for r in results]
+        log_ttrs = [r.log_ttr for r in results]
+        sttrs = [r.sttr for r in results if r.metadata.get("sttr_available")]
+        delta_stds = [r.delta_std for r in results if r.metadata.get("delta_std_available")]
+
+        return TTRAggregateResult(
+            group_id=group_id,
+            text_count=len(results),
+            total_words=sum(r.total_words for r in results),
+            ttr_mean=round(statistics.mean(ttrs), 6),
+            ttr_std=round(statistics.stdev(ttrs), 6) if len(ttrs) > 1 else 0.0,
+            ttr_min=round(min(ttrs), 6),
+            ttr_max=round(max(ttrs), 6),
+            ttr_median=round(statistics.median(ttrs), 6),
+            root_ttr_mean=round(statistics.mean(root_ttrs), 4),
+            root_ttr_std=round(statistics.stdev(root_ttrs), 4) if len(root_ttrs) > 1 else 0.0,
+            log_ttr_mean=round(statistics.mean(log_ttrs), 6),
+            log_ttr_std=round(statistics.stdev(log_ttrs), 6) if len(log_ttrs) > 1 else 0.0,
+            sttr_mean=round(statistics.mean(sttrs), 6) if sttrs else None,
+            sttr_std=round(statistics.stdev(sttrs), 6) if len(sttrs) > 1 else None,
+            delta_std_mean=round(statistics.mean(delta_stds), 6) if delta_stds else None,
+            metadata={"group_id": group_id, "text_count": len(results)},
+        )

pystylometry-1.3.5.dist-info/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Craig Trim
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

pystylometry-1.3.5.dist-info/METADATA

@@ -0,0 +1,78 @@
+Metadata-Version: 2.1
+Name: pystylometry
+Version: 1.3.5
+Summary: Comprehensive Python package for stylometric analysis
+License: MIT
+Keywords: stylometry,nlp,text-analysis,authorship,readability,lexical-diversity,readability-metrics
+Author: Craig Trim
+Author-email: craigtrim@gmail.com
+Requires-Python: >=3.9,<4.0
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Typing :: Typed
+Project-URL: Homepage, https://github.com/craigtrim/pystylometry
+Project-URL: Issues, https://github.com/craigtrim/pystylometry/issues
+Project-URL: Repository, https://github.com/craigtrim/pystylometry
+Description-Content-Type: text/markdown
+
+# pystylometry
+
+[![PyPI version](https://badge.fury.io/py/pystylometry.svg)](https://badge.fury.io/py/pystylometry)
+[![Downloads](https://static.pepy.tech/badge/pystylometry)](https://pepy.tech/project/pystylometry)
+[![Downloads/Month](https://static.pepy.tech/badge/pystylometry/month)](https://pepy.tech/project/pystylometry)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9%2B-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
+[![Tests](https://img.shields.io/badge/tests-1022%20passed-brightgreen)]()
+
+Stylometric analysis and authorship attribution for Python. 50+ metrics across 11 modules, from vocabulary diversity to AI-generation detection.
+
+## Install
+
+```bash
+pip install pystylometry              # Core (lexical metrics)
+pip install pystylometry[all]         # Everything
+```
+
+## Modules
+
+| Module | Metrics | Description |
+|--------|---------|-------------|
+| [**lexical**](https://github.com/craigtrim/pystylometry/tree/master/pystylometry/lexical) | TTR, MTLD, Yule's K/I, Hapax, MATTR, VocD-D, HD-D, MSTTR, function words, word frequency | Vocabulary diversity and richness |
+| [**readability**](https://github.com/craigtrim/pystylometry/tree/master/pystylometry/readability) | Flesch, Flesch-Kincaid, SMOG, Gunning Fog, Coleman-Liau, ARI, Dale-Chall, Fry, FORCAST, Linsear Write, Powers-Sumner-Kearl | Grade-level and difficulty scoring |
+| [**syntactic**](https://github.com/craigtrim/pystylometry/tree/master/pystylometry/syntactic) | POS ratios, sentence types, parse tree depth, clausal density, passive voice, T-units, dependency distance | Sentence and parse structure (requires spaCy) |
+| [**authorship**](https://github.com/craigtrim/pystylometry/tree/master/pystylometry/authorship) | Burrows' Delta, Cosine Delta, Zeta, Kilgarriff chi-squared, MinMax, John's Delta, NCD | Author attribution and text comparison |
+| [**stylistic**](https://github.com/craigtrim/pystylometry/tree/master/pystylometry/stylistic) | Contractions, hedges, intensifiers, modals, punctuation, vocabulary overlap (Jaccard/Dice/Cosine/KL), cohesion, genre/register | Style markers and text similarity |
+| [**character**](https://github.com/craigtrim/pystylometry/tree/master/pystylometry/character) | Letter frequencies, digit/uppercase ratios, special characters, whitespace | Character-level fingerprinting |
+| [**ngrams**](https://github.com/craigtrim/pystylometry/tree/master/pystylometry/ngrams) | Word/character/POS n-grams, Shannon entropy, skipgrams | N-gram profiles and entropy |
+| [**dialect**](https://github.com/craigtrim/pystylometry/tree/master/pystylometry/dialect) | British/American classification, spelling/grammar/vocabulary markers, markedness | Regional dialect detection |
+| [**consistency**](https://github.com/craigtrim/pystylometry/tree/master/pystylometry/consistency) | Sliding-window chi-squared drift, pattern classification | Intra-document style analysis |
+| [**prosody**](https://github.com/craigtrim/pystylometry/tree/master/pystylometry/prosody) | Syllable stress, rhythm regularity | Prose rhythm (requires spaCy) |
+| [**viz**](https://github.com/craigtrim/pystylometry/tree/master/pystylometry/viz) | Timeline, scatter, report (PNG + interactive HTML) | Drift detection visualization |
+
+## Development
+
+```bash
+git clone https://github.com/craigtrim/pystylometry && cd pystylometry
+pip install -e ".[dev,all]"
+make test       # 1022 tests
+make lint       # ruff + mypy
+make all        # lint + test + build
+```
+
+## License
+
+MIT
+
+## Author
+
+Craig Trim -- craigtrim@gmail.com
+

{pystylometry-1.3.0.dist-info → pystylometry-1.3.5.dist-info}/RECORD

@@ -1,7 +1,7 @@
 pystylometry/README.md,sha256=WFOtCAF3qtDTgGG3a_jTjNSwVgpQEXI1PKqbVBfyo1M,2366
-pystylometry/__init__.py,sha256=Z6zkHlX05SUeObDca9dL1Gkfq4UPBWbU2M4sp4fVj78,9220
+pystylometry/__init__.py,sha256=bZ8xk66Mx7gj3K_I6594DoqATIGv1FtLFSJmF6Dz1g4,10462
 pystylometry/_normalize.py,sha256=7tdfgAKg5CI2d4eoDypmFqOVByoxpwgUUZD6vyBH86A,8679
-pystylometry/_types.py,sha256=HddTq-8kGeXyTXFkUd26HmOlOhCOdIgEVULHp168ais,76563
+pystylometry/_types.py,sha256=_YCkVyvHulmKkvmjzb73dcCOWJwiJZVhkV7sJcMr4YY,83618
 pystylometry/_utils.py,sha256=CXTx4KDJ_6iiHcc2OXqOYs-izhLf_ZEmJFKdHyd7q34,5282
 pystylometry/authorship/README.md,sha256=zNXCpLj7nczPnYykJnCUw3y-kxfC9mWZmngi3nfw6us,1016
 pystylometry/authorship/__init__.py,sha256=D7m38hWi_62o1ZDSrghLCfob9YsykTht4K37wiVgHfg,1530
@@ -13,7 +13,7 @@ pystylometry/authorship/zeta.py,sha256=oOi9Y6ZPq15ILLVl6So9O9ERvzig26en6_dpQJWeo
 pystylometry/character/README.md,sha256=poQwhbI8MabVD_626CWjEL87IOX5YDGS0ZJTH1hNwEE,607
 pystylometry/character/__init__.py,sha256=CiiKJmZ10UJE8qAecavpOKyw-vGonsOew_mFH34ZOC0,371
 pystylometry/character/character_metrics.py,sha256=OCIGP_ivtwtzcifcxcbmp2R5SIKh2tKyvKcHAv64S8g,14029
-pystylometry/cli.py,sha256=z0yx2O_E05tHT9_BHgSaQ2zq5_fBERXfhbYHcuQ2y-A,15477
+pystylometry/cli.py,sha256=HvzBZxFSiS5AAXCb6N9Eo3QonkH-ucRFp6xDF1kJTQ0,26380
 pystylometry/consistency/README.md,sha256=HG_Rd6WRBnIz3M7J11dVDv1S2ARkMABFYrTn-VV8xRY,1058
 pystylometry/consistency/__init__.py,sha256=l7nzpS7M4yHDBbM2LGAtW0XGT2n7YjSey_1xKf45224,2181
 pystylometry/consistency/_thresholds.py,sha256=5fZwdJ_cnDy0ED7CCYs6V_zP6kIAR1p0h0NYkbZ0HRg,6381
@@ -24,12 +24,13 @@ pystylometry/dialect/_data/dialect_markers.json,sha256=DthluOA6q0rG_8IrCrFIYWh_E
 pystylometry/dialect/_loader.py,sha256=M2ATp-5754v_yX9EWvBP0r5qgNf8xlL8XadVsVb_Hco,12989
 pystylometry/dialect/detector.py,sha256=9x0ZuIfTIjsmdNSx0Ezy5AC0SAFtC4kVw11iOSBd9gQ,20147
 pystylometry/lexical/README.md,sha256=cFQ7KRZV4ubsQwIlOH3YHTbhhNl5X91Sr3zcn-3x0HI,1185
-pystylometry/lexical/__init__.py,sha256=HTncnGVZgpktZqpf-r4_HI_9Jq42WkZZKXn8nho3y3s,751
+pystylometry/lexical/__init__.py,sha256=ib_F-NGVydLNGT_HgaWurBT25AadTE4eNcAN1lGMKmQ,934
 pystylometry/lexical/advanced_diversity.py,sha256=rL1hlNqTnaEFcA2v4oBJlojHZMTqdvvm4jYXTFGVpYE,25664
 pystylometry/lexical/function_words.py,sha256=eel9bq_qWgWlvG0NtDiouilMt9kaFqz2rh3add2UC4U,17832
 pystylometry/lexical/hapax.py,sha256=djTqZyZIYXa3GRiPoy6TTGHPm0wCRNJ9U0Rwnf5NoDk,12173
 pystylometry/lexical/mtld.py,sha256=XpeCF8sOXZhWbaazHGuqm08mrOf_DYfkfGGAltWnyy4,7101
-pystylometry/lexical/ttr.py,sha256=iEsXkoSPyZEyiiFwKatKA8KhLRukD7RDRvyRkRQOTsk,5848
+pystylometry/lexical/repetition.py,sha256=A9L0oNwfnCepVkWy57kjHV47Pw4M6fZXEl25hBVdq2s,18318
+pystylometry/lexical/ttr.py,sha256=igS8gnvIv57zvjQPtmIgkB5Wj7jdaKSMRpJ1WvMfKtw,13091
 pystylometry/lexical/word_frequency_sophistication.py,sha256=OHOS0fBvd1Bz8zsJk-pJbWLTgImmBd-aewQnp_kq8BY,38828
 pystylometry/lexical/yule.py,sha256=NXggha8jmQCu4i-qKZpISwyJBqNpuPHyVR86BLDLgio,5192
 pystylometry/ngrams/README.md,sha256=50wyaWcLGbosLzTPR1cXdE_xAVU8jVY7fd3ReEk9KnY,802
@@ -70,7 +71,8 @@ pystylometry/viz/jsx/_base.py,sha256=nd7kEc13fUcRMom3A5jqjGyTy-djIeydq2k3oPHZIHY
 pystylometry/viz/jsx/report.py,sha256=DbbHnnNAEi5tmVg4PmiHb17vkBBXujyE4x1CfVBiOBw,25857
 pystylometry/viz/jsx/timeline.py,sha256=hor-xnBa6oVkSqN0AEZUCQFBOB-iTfHSFZHiEfeakPA,30716
 pystylometry/viz/jsx/viewer.py,sha256=3LO49d_2bRf_P-P-2oSKpKx4N8Ugo4oCLb3DtvyNxXI,43716
-pystylometry-1.3.0.dist-info/METADATA,sha256=wsQ5QTEH7i6hpePEnlfDgJFKVHJi1m-HpMcHuznQt3c,5706
-pystylometry-1.3.0.dist-info/WHEEL,sha256=3ny-bZhpXrU6vSQ1UPG34FoxZBp3lVcvK0LkgUz6VLk,88
-pystylometry-1.3.0.dist-info/entry_points.txt,sha256=iHOaFXlyiwcQM1LlID2gWGmN4DBLdTSpKGjttU8tgm8,113
-pystylometry-1.3.0.dist-info/RECORD,,
+pystylometry-1.3.5.dist-info/LICENSE,sha256=vou5JCLAT5nHcsUv-AkjUYAihYfN9mwPDXxV2DHyHBo,1067
+pystylometry-1.3.5.dist-info/METADATA,sha256=DEFzNf_ZQd3mulwOnFMRSyc1s30alGM6UtO-L7nloPc,4779
+pystylometry-1.3.5.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+pystylometry-1.3.5.dist-info/entry_points.txt,sha256=XsJvKgKs3LRDuzdF45JO7ZnS0wGKg1f5qsxVYSZzLp8,165
+pystylometry-1.3.5.dist-info/RECORD,,

{pystylometry-1.3.0.dist-info → pystylometry-1.3.5.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.3.0
+Generator: poetry-core 1.9.0
 Root-Is-Purelib: true
 Tag: py3-none-any

{pystylometry-1.3.0.dist-info → pystylometry-1.3.5.dist-info}/entry_points.txt

@@ -1,4 +1,5 @@
 [console_scripts]
 pystylometry-drift=pystylometry.cli:drift_cli
+pystylometry-tokenize=pystylometry.cli:tokenize_cli
 pystylometry-viewer=pystylometry.cli:viewer_cli