wavelet-matrix 2.1.8__tar.gz → 2.2.1__tar.gz

{wavelet_matrix-2.1.8 → wavelet_matrix-2.2.1}/.github/workflows/CI.yml

@@ -233,6 +233,7 @@ jobs:
           - "3.12"
           - "3.13"
           - "3.14"
+          - "3.15.0-beta.3"
           - "pypy3.11"
     steps:
       - uses: actions/checkout@v6
@@ -244,7 +245,20 @@ jobs:
           python -m pip install --upgrade pip
           python -m pip install -e .[test]
       - name: Run benchmarks
-        run: pytest --benchmark-only
+        run: pytest --benchmark-only --db .pymon
+      - name: Display benchmark results
+        run: |
+          sqlite3 -header -column .pymon '
+            SELECT
+              ITEM_PATH AS path,
+              COALESCE(ITEM_VARIANT, ITEM) AS test,
+              printf("%.3f", TOTAL_TIME) AS time_sec,
+              printf("%.2f", CPU_USAGE) AS cpu_usage,
+              printf("%.2f", MEM_USAGE) AS mem_mb
+            FROM TEST_METRICS
+            WHERE KIND = "function"
+            ORDER BY MEM_USAGE DESC;
+          '
 
   release:
     name: Release

{wavelet_matrix-2.1.8 → wavelet_matrix-2.2.1}/.gitignore

@@ -74,4 +74,5 @@ docs/_build/
 target/
 Cargo.lock
 .ruff_cache/
-.benchmarks/
+.benchmarks/
+.pymon

{wavelet_matrix-2.1.8 → wavelet_matrix-2.2.1}/Cargo.lock

@@ -4,9 +4,15 @@ version = 4
 
 [[package]]
 name = "autocfg"
-version = "1.5.0"
+version = "1.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
+checksum = "f2032f911046de80f0a198e0901378627c33f59ea0ac00e363d481118bd70a53"
+
+[[package]]
+name = "bytemuck"
+version = "1.25.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c8efb64bd706a16a1bdde310ae86b351e4d21550d98d056f22f8a7f7a2183fec"
 
 [[package]]
 name = "crossbeam-deque"
@@ -35,9 +41,9 @@ checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
 
 [[package]]
 name = "either"
-version = "1.15.0"
+version = "1.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
+checksum = "91622ff5e7162018101f2fea40d6ebf4a78bbe5a49736a2020649edf9693679e"
 
 [[package]]
 name = "heck"
@@ -45,28 +51,19 @@ version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
 
-[[package]]
-name = "indoc"
-version = "2.0.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "79cf5c93f93228cf8efb3ba362535fb11199ac548a09ce117c9b1adc3030d706"
-dependencies = [
- "rustversion",
-]
-
 [[package]]
 name = "libc"
-version = "0.2.183"
+version = "0.2.186"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b5b646652bf6661599e1da8901b3b9522896f01e736bad5f723fe7a3a27f899d"
+checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"
 
 [[package]]
-name = "memoffset"
-version = "0.9.1"
+name = "memmap2"
+version = "0.9.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "488016bfae457b036d996092f6cb448677611ce4449e970ceaf42695203f218a"
+checksum = "d1219ed1b7f229ee7104d281dd01d6802fe28bb6e95d292942c4daacdeb798c0"
 dependencies = [
- "autocfg",
+ "libc",
 ]
 
 [[package]]
@@ -120,13 +117,11 @@ dependencies = [
 
 [[package]]
 name = "pyo3"
-version = "0.27.2"
+version = "0.28.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ab53c047fcd1a1d2a8820fe84f05d6be69e9526be40cb03b73f86b6b03e6d87d"
+checksum = "91fd8e38a3b50ed1167fb981cd6fd60147e091784c427b8f7183a7ee32c31c12"
 dependencies = [
- "indoc",
  "libc",
- "memoffset",
  "num-bigint",
  "num-traits",
  "once_cell",
@@ -134,23 +129,22 @@ dependencies = [
  "pyo3-build-config",
  "pyo3-ffi",
  "pyo3-macros",
- "unindent",
 ]
 
 [[package]]
 name = "pyo3-build-config"
-version = "0.27.2"
+version = "0.28.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b455933107de8642b4487ed26d912c2d899dec6114884214a0b3bb3be9261ea6"
+checksum = "e368e7ddfdeb98c9bca7f8383be1648fd84ab466bf2bc015e94008db6d35611e"
 dependencies = [
  "target-lexicon",
 ]
 
 [[package]]
 name = "pyo3-ffi"
-version = "0.27.2"
+version = "0.28.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1c85c9cbfaddf651b1221594209aed57e9e5cff63c4d11d1feead529b872a089"
+checksum = "7f29e10af80b1f7ccaf7f69eace800a03ecd13e883acfacc1e5d0988605f651e"
 dependencies = [
  "libc",
  "pyo3-build-config",
@@ -158,9 +152,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros"
-version = "0.27.2"
+version = "0.28.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0a5b10c9bf9888125d917fb4d2ca2d25c8df94c7ab5a52e13313a07e050a3b02"
+checksum = "df6e520eff47c45997d2fc7dd8214b25dd1310918bbb2642156ef66a67f29813"
 dependencies = [
  "proc-macro2",
  "pyo3-macros-backend",
@@ -170,9 +164,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros-backend"
-version = "0.27.2"
+version = "0.28.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03b51720d314836e53327f5871d4c0cfb4fb37cc2c4a11cc71907a86342c40f9"
+checksum = "c4cdc218d835738f81c2338f822078af45b4afdf8b2e33cbb5916f108b813acb"
 dependencies = [
  "heck",
  "proc-macro2",
@@ -183,18 +177,18 @@ dependencies = [
 
 [[package]]
 name = "quote"
-version = "1.0.45"
+version = "1.0.46"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
+checksum = "dfbc457d0c7a0759a614551b11a6409e5951f6c7537be1f1b7682b9ae9230368"
 dependencies = [
  "proc-macro2",
 ]
 
 [[package]]
 name = "rayon"
-version = "1.11.0"
+version = "1.12.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "368f01d005bf8fd9b1206fb6fa653e6c4a81ceb1466406b81792d87c5677a58f"
+checksum = "fb39b166781f92d482534ef4b4b1b2568f42613b53e5b6c160e24cfbfa30926d"
 dependencies = [
  "either",
  "rayon-core",
@@ -210,17 +204,11 @@ dependencies = [
  "crossbeam-utils",
 ]
 
-[[package]]
-name = "rustversion"
-version = "1.0.22"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
-
 [[package]]
 name = "syn"
-version = "2.0.117"
+version = "2.0.118"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
+checksum = "1b9ae57f904213ebb649ce6895b8a66c66f0203b9319718f69a5612a065b1422"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -239,16 +227,12 @@ version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
 
-[[package]]
-name = "unindent"
-version = "0.2.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3"
-
 [[package]]
 name = "wavelet-matrix"
-version = "2.1.8"
+version = "2.2.1"
 dependencies = [
+ "bytemuck",
+ "memmap2",
  "num-bigint",
  "num-integer",
  "num-traits",

{wavelet_matrix-2.1.8 → wavelet_matrix-2.2.1}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "wavelet-matrix"
-version = "2.1.8"
+version = "2.2.1"
 edition = "2024"
 readme = "README.md"
 
@@ -10,8 +10,10 @@ name = "wavelet_matrix"
 crate-type = ["cdylib"]
 
 [dependencies]
+bytemuck = "1.25.0"
+memmap2 = "0.9.10"
 num-bigint = "0.4.6"
 num-integer = "0.1.46"
 num-traits = "0.2.19"
-pyo3 = { version = "0.27.2", features = ["num-bigint"] }
-rayon = "1.11.0"
+pyo3 = { version = "0.28.3", features = ["num-bigint"] }
+rayon = "1.12.0"

{wavelet_matrix-2.1.8 → wavelet_matrix-2.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wavelet-matrix
-Version: 2.1.8
+Version: 2.2.1
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: Information Technology
@@ -12,6 +12,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
@@ -22,6 +23,7 @@ Requires-Dist: pdoc>=16.0 ; extra == 'dev'
 Requires-Dist: ruff>=0.14 ; extra == 'dev'
 Requires-Dist: pytest>=7.0 ; extra == 'test'
 Requires-Dist: pytest-benchmark>=4.0 ; extra == 'test'
+Requires-Dist: pytest-monitor>=1.6 ; extra == 'test'
 Provides-Extra: dev
 Provides-Extra: test
 License-File: LICENSE
@@ -59,6 +61,7 @@ supporting fast rank / select / range queries over indexed sequences
 ## Features:
 - Fast rank, select, quantile
 - Rich range queries (freq / sum / top-k / min / max)
+- Optional disk-backed storage for static WaveletMatrix (`on_disk=True`)
 - Optional dynamic updates (insert / remove / update)
 - Safe Rust (no unsafe)
 
@@ -75,6 +78,12 @@ from wavelet_matrix import WaveletMatrix
 
 data = [5, 4, 5, 5, 2, 1, 5, 6, 1, 3, 5, 0]
 wm = WaveletMatrix(data)
+```  
+
+WaveletMatrix also supports disk-backed storage for large static sequences.  
+Set `on_disk=True` to keep its internal data on disk instead of holding it all in memory.  
+```python
+wm = WaveletMatrix(data, on_disk=True)
 ```
 
 ### Frequency Queries

{wavelet_matrix-2.1.8 → wavelet_matrix-2.2.1}/README.md

@@ -24,6 +24,7 @@ supporting fast rank / select / range queries over indexed sequences
 ## Features:
 - Fast rank, select, quantile
 - Rich range queries (freq / sum / top-k / min / max)
+- Optional disk-backed storage for static WaveletMatrix (`on_disk=True`)
 - Optional dynamic updates (insert / remove / update)
 - Safe Rust (no unsafe)
 
@@ -40,6 +41,12 @@ from wavelet_matrix import WaveletMatrix
 
 data = [5, 4, 5, 5, 2, 1, 5, 6, 1, 3, 5, 0]
 wm = WaveletMatrix(data)
+```  
+
+WaveletMatrix also supports disk-backed storage for large static sequences.  
+Set `on_disk=True` to keep its internal data on disk instead of holding it all in memory.  
+```python
+wm = WaveletMatrix(data, on_disk=True)
 ```
 
 ### Frequency Queries

wavelet_matrix-2.2.1/benchmarks/bench_disk_wavelet_matrix.py

@@ -0,0 +1,91 @@
+import random
+
+import pytest
+
+from wavelet_matrix import WaveletMatrix
+
+
+@pytest.fixture
+def random_data(size: int, max_bit: int):
+    """Helper function to create random data"""
+    random.seed(42)
+    base = [random.randint(0, (1 << max_bit) - 1) for _ in range(size // 100)]
+    return base * 100
+
+
+@pytest.fixture
+def random_disk_wavelet_matrix(random_data: list[int]) -> WaveletMatrix:
+    """Helper function to create a DiskWaveletMatrix with random data"""
+    return WaveletMatrix(random_data, on_disk=True)
+
+
+@pytest.mark.parametrize("size", [500, 10000, 200000])
+@pytest.mark.parametrize("max_bit", [8, 32, 128])
+class BenchDiskWaveletMatrix:
+    def bench_construction(self, benchmark, random_data):
+        """Benchmark DiskWaveletMatrix construction"""
+        benchmark(WaveletMatrix, random_data, on_disk=True)
+
+    def bench_values(self, benchmark, random_disk_wavelet_matrix):
+        """Benchmark DiskWaveletMatrix values retrieval"""
+        benchmark(random_disk_wavelet_matrix.values)
+
+    def bench_access(self, benchmark, random_disk_wavelet_matrix, size):
+        """Benchmark DiskWaveletMatrix access"""
+        index = random.randint(0, size - 1)
+        benchmark(random_disk_wavelet_matrix.access, index)
+
+    def bench_rank(self, benchmark, random_disk_wavelet_matrix, size):
+        """Benchmark DiskWaveletMatrix rank"""
+        value = random_disk_wavelet_matrix[random.randint(0, size - 1)]
+        end = random.randint(0, size)
+        benchmark(random_disk_wavelet_matrix.rank, value, end)
+
+    def bench_select(self, benchmark, random_disk_wavelet_matrix, size):
+        """Benchmark DiskWaveletMatrix select"""
+        value = random_disk_wavelet_matrix[random.randint(0, size - 1)]
+        kth = random_disk_wavelet_matrix.rank(value, size)
+        benchmark(random_disk_wavelet_matrix.select, value, kth)
+
+    def bench_quantile(self, benchmark, random_disk_wavelet_matrix, size):
+        """Benchmark DiskWaveletMatrix quantile"""
+        start = size // 4
+        end = size * 3 // 4
+        kth = random.randint(1, end - start)
+        benchmark(random_disk_wavelet_matrix.quantile, start, end, kth)
+
+    def bench_range_freq(self, benchmark, random_disk_wavelet_matrix, size, max_bit):
+        """Benchmark DiskWaveletMatrix range_freq"""
+        start = size // 4
+        end = size * 3 // 4
+        lower = (1 << max_bit) // 4
+        upper = (1 << max_bit) * 3 // 4
+        benchmark(random_disk_wavelet_matrix.range_freq, start, end, lower, upper)
+
+    def bench_range_maxk(self, benchmark, random_disk_wavelet_matrix, size):
+        """Benchmark DiskWaveletMatrix range_maxk"""
+        start = size // 4
+        end = size * 3 // 4
+        k = 10
+        benchmark(random_disk_wavelet_matrix.range_maxk, start, end, k)
+
+    def bench_range_mink(self, benchmark, random_disk_wavelet_matrix, size):
+        """Benchmark DiskWaveletMatrix range_mink"""
+        start = size // 4
+        end = size * 3 // 4
+        k = 10
+        benchmark(random_disk_wavelet_matrix.range_mink, start, end, k)
+
+    def bench_prev_value(self, benchmark, random_disk_wavelet_matrix, size, max_bit):
+        """Benchmark DiskWaveletMatrix prev_value"""
+        start = size // 4
+        end = size * 3 // 4
+        upper = 1 << (max_bit - 1)
+        benchmark(random_disk_wavelet_matrix.prev_value, start, end, upper)
+
+    def bench_next_value(self, benchmark, random_disk_wavelet_matrix, size, max_bit):
+        """Benchmark DiskWaveletMatrix next_value"""
+        start = size // 4
+        end = size * 3 // 4
+        lower = 1 << (max_bit - 1)
+        benchmark(random_disk_wavelet_matrix.next_value, start, end, lower)

{wavelet_matrix-2.1.8 → wavelet_matrix-2.2.1}/docs/wavelet_matrix.html

@@ -222,7 +222,7 @@ wavelet_matrix    </h1>
 
 <div class="pdoc-code codehilite">
 <pre><span></span><code><span class="kn">from</span><span class="w"> </span><span class="nn">wavelet_matrix</span><span class="w"> </span><span class="kn">import</span> <span class="n">WaveletMatrix</span>
-<span class="n">wm</span> <span class="o">=</span> <span class="n">WaveletMatrix</span><span class="p">([</span><span class="mi">5</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">6</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">0</span><span class="p">])</span>
+<span class="n">wm</span> <span class="o">=</span> <span class="n">WaveletMatrix</span><span class="p">([</span><span class="mi">5</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">6</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span> <span class="n">on_disk</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>  <span class="c1"># in-memory</span>
 </code></pre>
 </div>
 </div>
@@ -231,7 +231,7 @@ wavelet_matrix    </h1>
                             <div id="WaveletMatrix.__init__" class="classattr">
                                 <div class="attr function">
             
-        <span class="name">WaveletMatrix</span><span class="signature pdoc-code condensed">(<span class="param"><span class="n">data</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span></span>)</span>
+        <span class="name">WaveletMatrix</span><span class="signature pdoc-code condensed">(<span class="param"><span class="n">data</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span>, </span><span class="param"><span class="n">on_disk</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span></span>)</span>
 
         
     </div>

{wavelet_matrix-2.1.8 → wavelet_matrix-2.2.1}/pyproject.toml

@@ -38,6 +38,7 @@ classifiers = [
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
     "Programming Language :: Python :: 3.14",
+    "Programming Language :: Python :: 3.15",
     "Programming Language :: Python :: Implementation :: CPython",
     "Programming Language :: Python :: Implementation :: PyPy",
     "Topic :: Software Development :: Libraries :: Python Modules",
@@ -50,6 +51,7 @@ classifiers = [
 test = [
     "pytest>=7.0",
     "pytest-benchmark>=4.0",
+    "pytest-monitor>=1.6"
 ]
 dev = [
     "pdoc>=16.0",
@@ -73,7 +75,7 @@ addopts = [
     "--strict-markers",
     "--tb=short",
     "--benchmark-columns=mean,stddev,min,max",
-    "--benchmark-group-by=func",
+    "--benchmark-group-by=fullfunc",
 ]
 
 [tool.ruff]