blys 0.1.0__tar.gz

blys-0.1.0/.github/workflows/publish-release.yml

@@ -0,0 +1,82 @@
+on:
+  push:
+    tags:
+      - "v*" # Push events to matching `v*` version srings. e.g. v1.0, v20.15.10
+
+name: Create and Publish Release
+
+jobs:
+  build:
+    name: Build distribution
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+          fetch-depth: 0
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.x'
+
+      - name: Install release dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install --upgrade setuptools wheel build
+
+      - name: Get release notes
+        id: release_notes
+        run: |
+          # By default, GH Actions checkout will only fetch a single commit.
+          # For us to extract the release notes, we need to fetch the tags
+          # and tag annotations as well.
+          # https://github.com/actions/checkout/issues/290
+          git fetch --tags --force
+          TAG_NAME=${GITHUB_REF/refs\/tags\//}
+          echo "$(git tag -l --format='%(contents)' $TAG_NAME)" > "${{ runner.temp }}/CHANGELOG.md"
+
+      - name: Create GitHub release
+        id: create_release
+        uses: actions/create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          tag_name: ${{ github.ref }}
+          release_name: ${{ github.ref }}
+          body_path: "${{ runner.temp }}/CHANGELOG.md"
+          draft: false
+          prerelease: false
+
+      - name: Build a binary wheel and a source tarball
+        run: python3 -m build
+      - name: Store the distribution packages
+        uses: actions/upload-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+  publish-to-pypi:
+    name: >-
+      Publish Python 🐍 distribution 📦 to PyPI
+    if: startsWith(github.ref, 'refs/tags/')  # only publish to PyPI on tag pushes
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/torchfont
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+    steps:
+      - name: Download all the dists
+        uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Publish distribution 📦 to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          # repository-url: https://test.pypi.org/legacy/ # for testing purposes
+          verify-metadata: false # twine previously didn't verify metadata when uploading

blys-0.1.0/.github/workflows/test.yml

@@ -0,0 +1,45 @@
+name: Test
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  build:
+    runs-on: ${{ matrix.platform }}
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11", "3.12", "3.13"]
+        platform: [ubuntu-latest, windows-latest]
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+          fetch-depth: 0
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install packages
+        run: |
+          pip install '.[test]'
+          pip install black
+      - name: lint
+        run: |
+          black . --check --diff --color
+      - name: Check out Google Fonts
+        uses: actions/checkout@v6
+        with:
+          repository: google/fonts
+          submodules: recursive
+          fetch-depth: 0
+          path: google-fonts
+      - name: Run Tests
+        run: |
+          pytest tests/*.py
+        shell: bash
+        env:
+          GOOGLE_FONTS_DIR: ${{ github.workspace }}/google-fonts

blys-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

blys-0.1.0/Lib/blys/__init__.py

@@ -0,0 +1,10 @@
+"""blys package.
+
+Utilities for loading fonts, building PyTorch datasets, rendering glyph rasters,
+and running repeatable training loops for font-focused ML tasks.
+"""
+
+from .utils import TrainingLoop
+from .googlefonts import GoogleFonts
+
+__all__ = ["TrainingLoop", "GoogleFonts"]

blys-0.1.0/Lib/blys/dataset.py

@@ -0,0 +1,318 @@
+"""Dataset construction helpers for font ML tasks.
+
+This module provides train/test splitting at the family level and dataset/sampler
+utilities that emit either codepoint-level items or glyph-index-level items.
+"""
+
+from collections import defaultdict
+import math
+import random
+from typing import Callable, Optional, Sequence, Set
+
+import torch
+import uharfbuzz as hb
+from glyphsets import GlyphSet, unicodes_per_glyphset
+from sklearn.model_selection import train_test_split
+from torch.utils.data import BatchSampler, DataLoader
+from torch.utils.data import Dataset as TorchDataset
+
+from blys.googlefonts import GoogleFonts
+
+LATIN_CORE = [x for x in GlyphSet("GF_Latin_Core").get_characters() if x != 32]
+# Skip combining characters
+LATIN_CORE = [x for x in LATIN_CORE if not (0x0300 <= x <= 0x036F)]
+
+kernel_glyphs = unicodes_per_glyphset("GF_Latin_Kernel")
+assert kernel_glyphs is not None
+LATIN_KERNEL = [x for x in kernel_glyphs if x != 32]
+# Skip combining characters
+LATIN_KERNEL = [x for x in LATIN_KERNEL if not (0x0300 <= x <= 0x036F)]
+
+
+def _hb_font_for_face(face):
+    """Construct a HarfBuzz Font object for a face."""
+    return getattr(hb, "Font")(face)
+
+
+class DatasetMaker:
+    """Create train/test splits and loaders over glyph rendering items."""
+
+    def __init__(
+        self,
+        repo_url: str,
+        batch_size: int,
+        having: Optional[Set[int]] = None,
+        target_codepoints: Optional[Set[int]] = None,
+        canary_size: Optional[int] = None,
+        image_size: int = 128,
+        split_seed: int = 1234,
+    ):
+        self.target_codepoints = set(target_codepoints) if target_codepoints else None
+        having_filter: Optional[Set[int]] = None
+        if having is not None:
+            having_filter = set(having)
+        if self.target_codepoints is not None:
+            having_filter = (
+                set(self.target_codepoints)
+                if having_filter is None
+                else having_filter | self.target_codepoints
+            )
+
+        self.googlefonts = GoogleFonts(repo_url, having=having_filter)
+        self.batch_size = batch_size
+        self.image_size = image_size
+        self.split_seed = split_seed
+        # Keep data-order randomization reproducible without forcing fixed batches.
+        self._train_loader_generator = torch.Generator()
+        self._train_loader_generator.manual_seed(self.split_seed + 1)
+        self._test_loader_generator = torch.Generator()
+        self._test_loader_generator.manual_seed(self.split_seed + 2)
+
+        # Test chars are a random split from GF Latin Core.
+        _, self.test_latincore_chars = train_test_split(
+            LATIN_CORE,
+            random_state=self.split_seed,
+        )
+
+        if canary_size is not None:
+            fonts = self.googlefonts.fonts[:canary_size]
+        else:
+            fonts = self.googlefonts.fonts
+
+        self.train_fonts, self.test_fonts = self._split_fonts_by_family(
+            fonts,
+            split_seed=self.split_seed,
+        )
+        print("Train fonts:", len(self.train_fonts))
+        print("Test fonts:", len(self.test_fonts))
+
+    @staticmethod
+    def _split_fonts_by_family(fonts, *, split_seed: int):
+        """Split fonts into train/test by family to avoid cross-style leakage."""
+        if len(fonts) < 2:
+            return list(fonts), []
+
+        family_to_fonts = defaultdict(list)
+        for font in fonts:
+            family_to_fonts[font.family].append(font)
+
+        families = sorted(family_to_fonts.keys())
+        if len(families) < 2:
+            # If only one family is available, keep current behaviour and avoid empty train.
+            return list(fonts), []
+
+        train_families, test_families = train_test_split(
+            families,
+            random_state=split_seed,
+        )
+
+        train_family_set = set(train_families)
+        test_family_set = set(test_families)
+
+        train_fonts = [
+            font for family in train_family_set for font in family_to_fonts[family]
+        ]
+        test_fonts = [
+            font for family in test_family_set for font in family_to_fonts[family]
+        ]
+        return train_fonts, test_fonts
+
+    def train_set(self):
+        """Return the training dataset for this maker.
+
+        Subclasses can override this to emit task-specific item structures.
+        """
+        return Dataset(
+            self.train_fonts, codepoint_filter_fn=self.train_codepoint_filter
+        )
+
+    def test_set(self):
+        """Return the test/validation dataset for this maker."""
+        return Dataset(self.test_fonts, codepoint_filter_fn=self.test_codepoint_filter)
+
+    def train_codepoint_filter(self, font_codepoints: Set[int]) -> Set[int]:
+        """Filter a font's codepoints for training.
+
+        By default this excludes the held-out Latin Core split, unless
+        ``target_codepoints`` was provided, in which case only those are kept.
+        """
+        if self.target_codepoints is not None:
+            return set(font_codepoints) & self.target_codepoints
+        return set(font_codepoints) - set(self.test_latincore_chars)
+
+    def test_codepoint_filter(self, font_codepoints: Set[int]) -> Set[int]:
+        """Filter a font's codepoints for testing.
+
+        By default this keeps only the held-out Latin Core split, unless
+        ``target_codepoints`` was provided, in which case only those are kept.
+        """
+        if self.target_codepoints is not None:
+            return set(font_codepoints) & self.target_codepoints
+        return set(font_codepoints) & set(self.test_latincore_chars)
+
+    def train_loader(self):
+        """Build the shuffled training ``DataLoader`` with deterministic RNG."""
+        return DataLoader(
+            self.train_set(),
+            batch_size=self.batch_size,
+            shuffle=True,
+            generator=self._train_loader_generator,
+            drop_last=True,
+            collate_fn=self.collate_fn,
+        )
+
+    def test_loader(self):
+        """Build the shuffled test ``DataLoader`` with deterministic RNG."""
+        return DataLoader(
+            self.test_set(),
+            batch_size=self.batch_size,
+            shuffle=True,
+            generator=self._test_loader_generator,
+            drop_last=True,
+            collate_fn=self.collate_fn,
+        )
+
+    def collate_fn(self, batch):
+        """Collate a batch into model inputs/targets.
+
+        Must be implemented by subclasses that know the task-specific tensor
+        layout and metadata packing.
+        """
+        raise NotImplementedError("Base DatasetMaker does not implement collate_fn")
+
+
+class Dataset(TorchDataset):
+    """Dataset over (font, char) pairs for codepoint-level tasks.
+
+    Returns items of the form {"font": font, "char": char} where char is a Unicode
+    codepoint integer. The dataset is filtered by the provided codepoint_filter_fn,
+    which takes the set of codepoints available in a font and returns the subset to
+    include in the dataset.
+    """
+
+    def __init__(self, fonts, codepoint_filter_fn: Callable[[Set[int]], Set[int]]):
+        """Initialize a codepoint-level dataset over the provided fonts."""
+        self.fonts = fonts
+        self.codepoint_filter_fn = codepoint_filter_fn
+        self.order = []
+        for font in self.fonts:
+            chars = self.codepoint_filter_fn(set(font.codepoints))
+            for char in chars:
+                # Skip empty glyphs; they can destabilize training targets.
+                if font.has_non_empty_codepoint(char):
+                    self.order.append((font, char))
+
+    def __len__(self):
+        """Return number of (font, codepoint) items."""
+        return len(self.order)
+
+    def __getitem__(self, idx):
+        """Return one sample dictionary containing ``char`` and ``font``."""
+        font, char = self.order[idx]
+        return {
+            "char": char,
+            "font": font,
+        }
+
+
+class AllGidsDataset(TorchDataset):
+    """Dataset over all GIDs in the font, used for glyph-level tasks.
+
+    Returns items of the form {"font": font, "gid": gid} where gid is a glyph index. The
+    dataset includes all GIDs for which the font has a non-empty outline, regardless of
+    codepoint coverage.
+    """
+
+    def __init__(self, fonts):
+        """Initialize a glyph-index dataset over all non-empty outlines."""
+        self.fonts = fonts
+        self.order = []
+        for font in self.fonts:
+            for gid in range(1, font.hb_face.glyph_count):
+                # Skip empty glyphs; they can destabilize training targets.
+                if font.has_non_empty_gid(gid):
+                    self.order.append((font, gid))
+
+    def __len__(self):
+        """Return number of (font, gid) items."""
+        return len(self.order)
+
+    def __getitem__(self, idx):
+        """Return one sample dictionary containing ``gid`` and ``font``."""
+        font, gid = self.order[idx]
+        return {
+            "gid": gid,
+            "font": font,
+        }
+
+
+class ClassBalancedBatchSampler(BatchSampler):
+    """Batch sampler that balances font classes within each emitted batch."""
+
+    def __init__(
+        self,
+        order: Sequence[tuple],
+        *,
+        batch_size: int,
+        drop_last: bool,
+    ) -> None:
+        if batch_size <= 0:
+            raise ValueError(f"batch_size must be positive, got {batch_size}")
+        if len(order) == 0:
+            raise ValueError("Cannot build class-balanced sampler for empty dataset")
+
+        self.batch_size = batch_size
+        self.drop_last = drop_last
+        self.dataset_size = len(order)
+
+        class_to_indices: dict[str, list[int]] = {}
+        for idx, (font, _char) in enumerate(order):
+            cls = font.classification()
+            class_to_indices.setdefault(cls, []).append(idx)
+
+        if not class_to_indices:
+            raise ValueError("No classes found for class-balanced sampling")
+
+        self.class_to_indices = class_to_indices
+        self.classes = sorted(class_to_indices.keys())
+
+    def __len__(self) -> int:
+        """Return the number of batches emitted per epoch-like pass."""
+        if self.drop_last:
+            return self.dataset_size // self.batch_size
+        return math.ceil(self.dataset_size / self.batch_size)
+
+    def __iter__(self):
+        """Yield index batches with near-uniform class presence per batch."""
+        num_classes = len(self.classes)
+        num_batches = len(self)
+
+        class_cursor = random.randrange(num_classes)
+
+        for _ in range(num_batches):
+            batch_indices: list[int] = []
+
+            if num_classes <= self.batch_size:
+                base = self.batch_size // num_classes
+                remainder = self.batch_size % num_classes
+                class_order = self.classes[:]
+                random.shuffle(class_order)
+
+                for cls in class_order:
+                    indices = self.class_to_indices[cls]
+                    for _ in range(base):
+                        batch_indices.append(random.choice(indices))
+
+                for cls in class_order[:remainder]:
+                    batch_indices.append(random.choice(self.class_to_indices[cls]))
+            else:
+                selected_classes = [
+                    self.classes[(class_cursor + i) % num_classes]
+                    for i in range(self.batch_size)
+                ]
+                class_cursor = (class_cursor + self.batch_size) % num_classes
+                for cls in selected_classes:
+                    batch_indices.append(random.choice(self.class_to_indices[cls]))
+
+            random.shuffle(batch_indices)
+            yield batch_indices