nafrec 0.3.0__tar.gz

nafrec-0.3.0/.github/workflows/publish.yml

@@ -0,0 +1,60 @@
+name: "Publish release to PyPI"
+
+on:
+  push:
+    tags:
+      # Publish on version tags, e.g. v0.1.0
+      - "v[0-9]+.[0-9]+.[0-9]+"
+      - "v[0-9]+.[0-9]+.[0-9]+rc[0-9]+"
+      - "v[0-9]+.[0-9]+.[0-9]+[ab][0-9]+"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - name: Checkout
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+        with:
+          enable-cache: false
+
+      - name: Build
+        run: uv build
+
+      - name: Upload distributions as artifacts
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+    permissions:
+      id-token: write
+    steps:
+      - name: Install uv
+        uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+        with:
+          enable-cache: false
+
+      - name: Download distributions artifact
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          name: dist
+          path: dist/
+
+      - name: Generate PEP 740 attestations
+        uses: astral-sh/attest-action@f589a42a7efb6fe400b4f400de60b4bc90390027 # v0.0.6
+
+      - name: Publish
+        run: uv publish

nafrec-0.3.0/.gitignore

@@ -0,0 +1,213 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# own
+xmls/
+test_data/
+plots/
+0*.py

nafrec-0.3.0/ARGS.md

@@ -0,0 +1,116 @@
+# Arguments
+
+The options below are grouped by purpose. Paths marked "conditionally required" depend on which models you configure (see [Choosing models](README.md#choosing-models)).
+
+#### Input, models and output
+
+| Argument | Type | Default | Description |
+|----------|------|---------|-------------|
+| `--input_folder` | str | **required** | Path to folder containing input images |
+| `--detection_model_path` | str | `/path/to/detection_model.pth` | Path to the RF-DETR detection model file (used with `--detector rfdetr`) |
+| `--recognition_model_path` | str | None | Path to the (latin-script / main) TrOCR recognition model folder. Optional if only the cyrillic model is used, or if `--use_ppocr` is set |
+| `--cyrillic_recognition_model_path` | str | None | Path to the cyrillic TrOCR recognition model folder. Optional |
+| `--processor_path` | str | None | Path to the TrOCR processor folder. Required with `--recognition_model_path` (not needed with `--use_ppocr`) |
+| `--cyrillic_processor_path` | str | None | Path to the cyrillic TrOCR processor folder. Required with `--cyrillic_recognition_model_path` |
+| `--script_classification_model_path` | str | None | Path to the script classification model file (`.pt`/`.pth`). Required when both the main and the cyrillic recognition models are configured |
+| `--region_model_name` | str | `Default` | Region detection model name (recorded in the XML metadata) |
+| `--line_model_name` | str | `Default` | Line detection model name (recorded in the XML metadata) |
+| `--script_classification_model_name` | str | `naf_script_classifier_202610` | Script classification model name (recorded in the XML metadata) |
+| `--text_rec_model_name` | str | `Default` | Latin text recognition model name (recorded in the XML metadata) |
+| `--cyrillic_text_rec_model_name` | str | `Default` | Cyrillic text recognition model name (recorded in the XML metadata) |
+| `--trocr_batch_size` | int | 8 | Batch size for TrOCR text recognition |
+| `--classifier_batch_size` | int | 32 | Batch size for script type classification |
+| `--classifier_default_label` | str | latin | Default label used by script type classifier in cases where all line classifications fail |
+| `--page_xml` | int | 0 | Whether to save output as PAGE XML (0 = no, 1 = yes) |
+| `--alto_xml` | int | 1 | Whether to save output as ALTO XML (0 = no, 1 = yes) |
+| `--output_json` | int | 1 | Whether to save output as .json file (0 = no, 1 = yes) |
+| `--xml_folder` | str | None | Custom path for XML output. If None, saves to `<image folder>/alto` or `<image folder>/page` |
+| `--json_folder` | str | None | Custom path for .json output. If None, saves to `<xml_folder>/json` (or `<image folder>/json` if `--xml_folder` is not set) |
+
+#### Detection thresholds and post-processing
+
+| Argument | Type | Default | Description |
+|----------|------|---------|-------------|
+| `--confidence_threshold` | float | 0.15 | Detection confidence threshold for filtering detections (RF-DETR only; the Paddle detector uses the `--paddle_*` thresholds) |
+| `--line_percentage_threshold` | float | 7e-05 | Threshold value for filtering out small line polygons, as a fraction of the image area (applies to both `rfdetr` and `paddle` detectors) |
+| `--region_percentage_threshold` | float | 7e-05 | Threshold value for filtering out small region polygons, as a fraction of the image area (applies to both detectors) |
+| `--line_iou` | float | 0.3 | Threshold value for merging lines based on intersection over union (IoU) (applies to both detectors) |
+| `--region_iou` | float | 0.3 | Threshold value for merging regions based on intersection over union (IoU) (applies to both detectors) |
+| `--line_overlap_threshold` | float | 0.5 | Threshold value for merging lines based on overlapping area (applies to both detectors) |
+| `--region_overlap_threshold` | float | 0.5 | Threshold value for merging regions based on overlapping area (applies to both detectors) |
+| `--sliver_threshold` | float | 0.01 | Given as a proportion of the smaller dimension of the image, so 0.01 would be 1% of the shorter side. Text lines thinner than this threshold will be discarded. |
+
+#### Tiled detection (SAHI)
+
+Slicing Aided Hyper Inference runs the RF-DETR detector on overlapping tiles of the page instead of on the whole downscaled image, which helps with large images and small text. It is disabled by default and only applies to the RF-DETR detector.
+
+| Argument | Type | Default | Description |
+|----------|------|---------|-------------|
+| `--tile_size` | int | 0 | Tile size in pixels. 768 is usually a good value for RF-DETR segmentation models. 0 disables tiling |
+| `--tile_overlap` | int | 128 | Tile overlap in pixels |
+| `--tiles_across` | int | 2 | The number of tiles across the shorter dimension of the image. The size the image is resized to before tiling is `tile_size * tiles_across - tile_overlap` (768 without tiling) |
+| `--tile_iou_threshold` | float | 0.85 | IoU threshold for suppressing overlapping detections when tiling is used. 0.85 for general material, 0.5 is sometimes better for tables |
+| `--tile_batch_size` | int | 3 | Batch size for tiled detection. 6 is a reasonable value |
+
+#### Devices, parallelism and precision
+
+nafrec runs *model workers* (processes that hold the models and run inference on a CPU or GPU) and *CPU workers* (processes that do image loading, cropping, polygon post-processing and writing the output). Pages are processed in parallel by the CPU workers, which send detection and recognition requests to the model workers.
+
+| Argument | Type | Default | Description |
+|----------|------|---------|-------------|
+| `--device` | str | `cuda` | Device to use for inference: `cuda` or `cpu`. If `cuda` is requested but no CUDA device is available, nafrec warns and falls back to `cpu` |
+| `--gpu_ids` | int (one or more) | None | GPU indices to use, as seen after `CUDA_VISIBLE_DEVICES` (e.g. `--gpu_ids 0 2`). Default: all visible GPUs. Ignored with `--device cpu` |
+| `--workers_per_gpu` | int | 1 | Number of model worker processes per GPU. Each holds a full copy of all models in VRAM, so 2 takes twice the VRAM for a possible small speedup. `--split_workers` is generally a better option than 2 here |
+| `--split_workers` | flag | off | Start two model worker processes per device, one for detection and one for recognition/classification, so that detection and recognition run in parallel on the same device. By default each worker does both. Takes about as much VRAM as `--workers_per_gpu 1` (each model is only loaded once per device) |
+| `--cpu_processes` | int | 0 (auto) | Number of CPU pre/postprocessing workers. Default: half of the physical cores when running on CPU, otherwise min(physical cores, 6 × number of model workers) |
+| `--inference_in_flight_limit` | int | 16 | Maximum number of model requests queued or in flight at once. Requests carry cropped line images, so keep this modest |
+| `--fp16_rec` | flag | off | Run the recognition models (TrOCR, PP-OCR) in fp16. PP-OCR ONNX models are converted in memory at load time. Only applies on GPUs (CUDA/ROCm); ignored on CPU |
+| `--fp16_det` | flag | off | Run the detection/segmentation models (RF-DETR, Paddle layout and text detection) in fp16. Paddle ONNX models are converted in memory at load time. Only applies on GPUs (CUDA/ROCm); ignored on CPU |
+
+#### PP-OCRv6 recognition
+
+PP-OCRv6 (ONNX) can be used instead of TrOCR for latin-script lines. The cyrillic model is always TrOCR.
+
+| Argument | Type | Default | Description |
+|----------|------|---------|-------------|
+| `--use_ppocr` | flag | off | Use a PP-OCRv6 ONNX recognition model instead of TrOCR for latin-script lines. Requires `--ppocr_model_path` (and then `--recognition_model_path` / `--processor_path` are not used) |
+| `--ppocr_model_path` | str | None | Path to the PP-OCRv6 recognition ONNX model |
+| `--ppocr_char_dict_path` | str | None | Path to the character dictionary the PP-OCRv6 model was trained with. If None, the default dictionary is used |
+| `--ppocr_img_height` | int | 96 | PP-OCR input height. Must match training (e.g. 96 for a custom NAF model) |
+| `--ppocr_img_width_min` | int | 320 | PP-OCR minimum input width |
+| `--ppocr_img_width_max` | int | 3200 | PP-OCR maximum input width. Text lines that would be wider are squeezed to this width. Must be >= `--ppocr_img_width_min`. With TensorRT this is also the maximum width of the shape profile |
+| `--ppocr_width_buckets` | int (one or more) | None | Pad each batch's input width up to the smallest of these bucket widths (e.g. `320 640 1280 1536 3200`), so that the model sees only a few distinct input shapes. Batches wider than the largest bucket keep their natural width. Default: no bucketing |
+| `--ppocr_batch_size` | int | 32 | Batch size for PP-OCR text recognition |
+| `--ppocr_pad_batch` | str | `auto` | Pad every PP-OCR batch (including the last partial one and single-line retries) to `--ppocr_batch_size`, so that the model always sees the same batch shape. Choices: `auto`, `on`, `off`. MIGraphX compiles for one fixed shape and fails on others; `auto` turns padding on only when MIGraphX is the active execution provider |
+
+#### TensorRT
+
+TensorRT applies to the PP-OCR recognition model and to the Paddle layout and text detection models. TrOCR does not use TensorRT even in optimum-onnx mode. See also the [notes](README.md#notes) on TensorRT.
+
+| Argument | Type | Default | Description |
+|----------|------|---------|-------------|
+| `--enable_tensorrt` | flag | off | Use the TensorRT execution provider if available. By default GPUs use CUDA/ROCm/MIGraphX. Engines are cached per model in `./trt_enginecache` (relative to the working directory), so the first run builds them and is slow |
+| `--no_trt_dynamic_shapes` | flag | off | Don't pass min/opt/max shape profiles to the TensorRT provider for PP-OCR / Paddle models. TensorRT then rebuilds engines whenever a new input shape appears, which for the Paddle text detector means for nearly every page size |
+| `--ppocr_trt_opt_width` | int | 1536 | PP-OCR with TensorRT: optimal input width for the shape profile |
+| `--paddle_det_trt_opt_shape` | int int (H W) | None | Paddle text detection with TensorRT: optimal input size (height and width) for the shape profile, e.g. `1536 1152`. Default: a 3:4 portrait page at the `--paddle_det_limit_side_len` resize limit. The minimum and maximum sizes of the profile are derived from the detection resize settings automatically |
+
+#### Detector selection and Paddle detection
+
+| Argument | Type | Default | Description |
+|----------|------|---------|-------------|
+| `--detector` | str | `rfdetr` | Segmentation backend. `rfdetr`: RF-DETR model for both regions and lines (`--detection_model_path`). `paddle`: ONNX DB text detection model for lines (`--paddle_det_model_path`) plus an optional PP-DocLayout layout model for regions (`--paddle_layout_model_path`). `none`: no detection model is loaded (library use with caller-supplied lines only, see [USAGE.md](USAGE.md)) |
+| `--paddle_det_model_path` | str | None | Paddle DB text detection model (ONNX, e.g. PP-OCRv6 det) giving the text lines. Required with `--detector paddle` |
+| `--paddle_layout_model_path` | str | None | Optional Paddle layout model (ONNX, e.g. PP-DocLayout) giving the text regions. Without it, each page is treated as one full-page region |
+| `--paddle_layout_threshold` | float | 0.3 | Minimum score for layout regions |
+| `--paddle_layout_input_size` | int | 0 | Layout model input size for models with a dynamic input shape (0 = 800). Ignored for fixed-size models |
+| `--paddle_layout_mean` | float float float | `0 0 0` | Layout model input normalization mean (RGB, after scaling to 0-1). PP-DocLayout-L/plus-L: `0 0 0` |
+| `--paddle_layout_std` | float float float | `1 1 1` | Layout model input normalization standard deviation (RGB). PP-DocLayout-L/plus-L: `1 1 1`; PicoDet-based S/M models typically use ImageNet values `0.229 0.224 0.225` |
+| `--paddle_layout_boxes_in_input_space` | flag | off | Set if the layout model returns boxes in resized-input pixels instead of original-image pixels |
+| `--paddle_layout_labels_path` | str | None | Text file with one layout class name per line (class id = line number). Default: the built-in PP-DocLayout_plus-L class names |
+| `--paddle_layout_ignore_classes` | str (zero or more) | none | Layout classes (ids, or names if `--paddle_layout_labels_path` is given) to drop as regions. Text lines inside them are dropped too (e.g. `image chart seal`) |
+| `--paddle_det_limit_side_len` | int | 1536 | Text detection input resize limit in pixels (see `--paddle_det_limit_type`) |
+| `--paddle_det_limit_type` | str | `max` | `max`: downscale so that the longer side is at most the limit. `min`: upscale so that the shorter side is at least the limit |
+| `--paddle_det_max_side_limit` | int | 4000 | Hard cap for the longer side of the text detection input |
+| `--paddle_det_thresh` | float | 0.3 | DB binarization threshold |
+| `--paddle_det_box_thresh` | float | 0.6 | DB minimum box score (also used as the line confidence) |
+| `--paddle_det_unclip_ratio` | float | 1.5 | DB box expansion ratio |

nafrec-0.3.0/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.