musaw commited on
Commit ·
7d9f55b
1
Parent(s): 9003457
release(v1): clean docs structure and modernize search UX
Browse files- .github/release_template.md +8 -3
- CHANGELOG.md +21 -8
- CITATION.cff +2 -2
- README.md +39 -84
- docs/README.md +23 -27
- docs/discoverability_seo.md +9 -9
- docs/index.md +16 -32
- docs/platform_sync_policy.md +8 -2
- docs/release_checklist.md +6 -1
- docs/release_process.md +22 -11
- docs/release_v0.1.1.md +0 -38
- docs/release_v0.1.2.md +0 -33
- docs/releases/README.md +12 -0
- docs/releases/v1.0.0.md +33 -0
- docs/search/index.html +501 -168
- pyproject.toml +2 -1
.github/release_template.md
CHANGED
|
@@ -1,23 +1,28 @@
|
|
| 1 |
## Summary
|
|
|
|
| 2 |
- What changed in this release.
|
| 3 |
|
| 4 |
## Highlights
|
|
|
|
| 5 |
- Data:
|
| 6 |
- ASR:
|
| 7 |
- TTS:
|
| 8 |
- Benchmarks:
|
| 9 |
-
- Docs
|
| 10 |
|
| 11 |
## Validation
|
|
|
|
| 12 |
- Link check: `python scripts/check_links.py`
|
| 13 |
- Normalization check: `python scripts/validate_normalization.py data/processed/normalization_seed_v0.1.tsv`
|
|
|
|
| 14 |
- Tests: `python -m pytest -q` (if available)
|
| 15 |
|
| 16 |
## Known Limitations
|
|
|
|
| 17 |
- List current caveats.
|
| 18 |
|
| 19 |
## References
|
|
|
|
| 20 |
- Changelog: [CHANGELOG.md](../CHANGELOG.md)
|
| 21 |
- Release checklist: [docs/release_checklist.md](../docs/release_checklist.md)
|
| 22 |
-
- Release notes
|
| 23 |
-
- Release notes draft v0.1.2: [docs/release_v0.1.2.md](../docs/release_v0.1.2.md)
|
|
|
|
| 1 |
## Summary
|
| 2 |
+
|
| 3 |
- What changed in this release.
|
| 4 |
|
| 5 |
## Highlights
|
| 6 |
+
|
| 7 |
- Data:
|
| 8 |
- ASR:
|
| 9 |
- TTS:
|
| 10 |
- Benchmarks:
|
| 11 |
+
- Docs and Tooling:
|
| 12 |
|
| 13 |
## Validation
|
| 14 |
+
|
| 15 |
- Link check: `python scripts/check_links.py`
|
| 16 |
- Normalization check: `python scripts/validate_normalization.py data/processed/normalization_seed_v0.1.tsv`
|
| 17 |
+
- Resource catalog check: `python scripts/validate_resource_catalog.py`
|
| 18 |
- Tests: `python -m pytest -q` (if available)
|
| 19 |
|
| 20 |
## Known Limitations
|
| 21 |
+
|
| 22 |
- List current caveats.
|
| 23 |
|
| 24 |
## References
|
| 25 |
+
|
| 26 |
- Changelog: [CHANGELOG.md](../CHANGELOG.md)
|
| 27 |
- Release checklist: [docs/release_checklist.md](../docs/release_checklist.md)
|
| 28 |
+
- Release notes index: [docs/releases/README.md](../docs/releases/README.md)
|
|
|
CHANGELOG.md
CHANGED
|
@@ -3,21 +3,33 @@
|
|
| 3 |
All notable changes to this project will be documented in this file.
|
| 4 |
|
| 5 |
The format is inspired by [Keep a Changelog](https://keepachangelog.com/en/1.1.0/)
|
| 6 |
-
and this project uses
|
| 7 |
|
| 8 |
## [Unreleased]
|
| 9 |
### Added
|
| 10 |
-
-
|
| 11 |
-
- GitHub topics checklist (`docs/github_topics_checklist.md`).
|
| 12 |
-
- Backlink strategy plan (`docs/backlink_strategy.md`).
|
| 13 |
-
- SEO intent landing pages for Pashto datasets, ASR, and TTS.
|
| 14 |
-
- Release note drafts for `v0.1.1` and `v0.1.2`.
|
| 15 |
|
| 16 |
### Changed
|
| 17 |
-
-
|
| 18 |
|
| 19 |
### Fixed
|
| 20 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## [v0.1] - 2026-02-14
|
| 23 |
### Added
|
|
@@ -25,3 +37,4 @@ and this project uses milestone-style tags (for example `v0.1`, `v0.2`).
|
|
| 25 |
- Structured `resources/` folder for datasets, models, benchmarks, and tools.
|
| 26 |
- Link-check script and normalization-validator tests.
|
| 27 |
- Documentation hub and model/release/process guidance.
|
|
|
|
|
|
| 3 |
All notable changes to this project will be documented in this file.
|
| 4 |
|
| 5 |
The format is inspired by [Keep a Changelog](https://keepachangelog.com/en/1.1.0/)
|
| 6 |
+
and this project uses semantic version tags (for example `v1.0.0`, `v1.0.1`).
|
| 7 |
|
| 8 |
## [Unreleased]
|
| 9 |
### Added
|
| 10 |
+
- None yet.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
### Changed
|
| 13 |
+
- None yet.
|
| 14 |
|
| 15 |
### Fixed
|
| 16 |
+
- None yet.
|
| 17 |
+
|
| 18 |
+
## [v1.0.0] - 2026-02-18
|
| 19 |
+
### Added
|
| 20 |
+
- Release notes index under `docs/releases/` with `docs/releases/v1.0.0.md`.
|
| 21 |
+
- Improved discoverability assets: topics checklist, backlink strategy, and intent landing pages.
|
| 22 |
+
- Hugging Face model-card metadata in `README.md`.
|
| 23 |
+
|
| 24 |
+
### Changed
|
| 25 |
+
- Cleaned and restructured README and docs navigation for lower redundancy.
|
| 26 |
+
- Modernized `docs/search/index.html` with stronger UI/UX and interaction patterns.
|
| 27 |
+
- Standardized release process and checklist around semantic versioning.
|
| 28 |
+
- Updated package and citation metadata to `1.0.0`.
|
| 29 |
+
|
| 30 |
+
### Fixed
|
| 31 |
+
- Removed stale draft release-note references from documentation and templates.
|
| 32 |
+
- Finalized hardcoded URL usage for the `pashto-language-resources` slug.
|
| 33 |
|
| 34 |
## [v0.1] - 2026-02-14
|
| 35 |
### Added
|
|
|
|
| 37 |
- Structured `resources/` folder for datasets, models, benchmarks, and tools.
|
| 38 |
- Link-check script and normalization-validator tests.
|
| 39 |
- Documentation hub and model/release/process guidance.
|
| 40 |
+
|
CITATION.cff
CHANGED
|
@@ -2,7 +2,8 @@ cff-version: 1.2.0
|
|
| 2 |
message: "If you use this repository, please cite it."
|
| 3 |
title: "Pashto Language Resources Hub (Pukhto/Pashto)"
|
| 4 |
type: software
|
| 5 |
-
version:
|
|
|
|
| 6 |
license: Apache-2.0
|
| 7 |
repository-code: "https://github.com/Musawer1214/pashto-language-resources"
|
| 8 |
url: "https://github.com/Musawer1214/pashto-language-resources"
|
|
@@ -18,4 +19,3 @@ keywords:
|
|
| 18 |
- NLP
|
| 19 |
- machine translation
|
| 20 |
- language resources
|
| 21 |
-
|
|
|
|
| 2 |
message: "If you use this repository, please cite it."
|
| 3 |
title: "Pashto Language Resources Hub (Pukhto/Pashto)"
|
| 4 |
type: software
|
| 5 |
+
version: 1.0.0
|
| 6 |
+
date-released: 2026-02-18
|
| 7 |
license: Apache-2.0
|
| 8 |
repository-code: "https://github.com/Musawer1214/pashto-language-resources"
|
| 9 |
url: "https://github.com/Musawer1214/pashto-language-resources"
|
|
|
|
| 19 |
- NLP
|
| 20 |
- machine translation
|
| 21 |
- language resources
|
|
|
README.md
CHANGED
|
@@ -18,111 +18,66 @@ tags:
|
|
| 18 |
|
| 19 |
# Pashto Language Resources Hub (Pukhto/Pashto)
|
| 20 |
|
| 21 |
-
Open-source
|
| 22 |
|
| 23 |
-
This
|
| 24 |
|
| 25 |
-
##
|
| 26 |
|
| 27 |
-
-
|
| 28 |
- Project site: [Pashto Language Resources Hub](https://musawer1214.github.io/pashto-language-resources/)
|
| 29 |
-
-
|
|
|
|
| 30 |
- Hugging Face mirror: [Musawer14/pashto-language-resources](https://huggingface.co/Musawer14/pashto-language-resources)
|
| 31 |
|
| 32 |
-
##
|
| 33 |
|
| 34 |
-
|
|
|
|
|
|
|
| 35 |
|
| 36 |
-
|
| 37 |
-
- Pashto ASR model
|
| 38 |
-
- Pashto TTS resources
|
| 39 |
-
- Pashto NLP benchmark
|
| 40 |
-
- Pashto machine translation resources
|
| 41 |
-
- Pukhto language technology
|
| 42 |
-
- Pushto AI resources
|
| 43 |
|
| 44 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
-
|
| 47 |
-
- Track practical tools, apps, and academic papers for Pashto integration in technology.
|
| 48 |
-
- Keep everything transparent, reproducible, and contribution-friendly.
|
| 49 |
|
| 50 |
-
|
|
|
|
|
|
|
| 51 |
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
- Canonical catalog: [resources/catalog/resources.json](resources/catalog/resources.json)
|
| 55 |
-
- Catalog schema: [resources/schema/resource.schema.json](resources/schema/resource.schema.json)
|
| 56 |
-
- Candidate feed (auto-generated): [resources/catalog/pending_candidates.json](resources/catalog/pending_candidates.json)
|
| 57 |
-
- Search UI source: [docs/search/index.html](docs/search/index.html)
|
| 58 |
-
- Search data export: [docs/search/resources.json](docs/search/resources.json)
|
| 59 |
-
- Resource index docs: [docs/resource_catalog.md](docs/resource_catalog.md)
|
| 60 |
-
- Automation docs: [docs/resource_automation.md](docs/resource_automation.md)
|
| 61 |
-
- Cycle runbook: [docs/resource_cycle_runbook.md](docs/resource_cycle_runbook.md)
|
| 62 |
-
|
| 63 |
-
## How New Resources Are Added
|
| 64 |
-
|
| 65 |
-
1. Auto discovery runs daily from `.github/workflows/resource_sync.yml` and updates `resources/catalog/pending_candidates.json` in a review PR.
|
| 66 |
-
2. Manual review checks quality, Pashto evidence, and license compatibility before promoting entries into `resources/catalog/resources.json` with `status: verified`.
|
| 67 |
-
3. Regeneration and validation runs `python scripts/validate_resource_catalog.py` and `python scripts/generate_resource_views.py`, then commits generated updates.
|
| 68 |
-
|
| 69 |
-
Shortcut wrapper:
|
| 70 |
-
- `python scripts/run_resource_cycle.py --limit 25`
|
| 71 |
-
|
| 72 |
-
## Quickstart
|
| 73 |
|
| 74 |
```bash
|
| 75 |
-
python -m pip install -e ".[dev]"
|
| 76 |
python scripts/validate_resource_catalog.py
|
| 77 |
python scripts/generate_resource_views.py
|
| 78 |
python scripts/check_links.py
|
| 79 |
python -m pytest -q
|
| 80 |
```
|
| 81 |
|
| 82 |
-
##
|
| 83 |
|
| 84 |
-
-
|
| 85 |
-
- Docs hub: [docs/README.md](docs/README.md)
|
| 86 |
-
- Resource search page: [docs/search/index.html](docs/search/index.html)
|
| 87 |
-
- Citation metadata: [CITATION.cff](CITATION.cff)
|
| 88 |
-
- Platform sync policy: [docs/platform_sync_policy.md](docs/platform_sync_policy.md)
|
| 89 |
- GitHub topics checklist: [docs/github_topics_checklist.md](docs/github_topics_checklist.md)
|
| 90 |
- Backlink strategy: [docs/backlink_strategy.md](docs/backlink_strategy.md)
|
| 91 |
-
-
|
| 92 |
-
-
|
| 93 |
-
-
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
- Purpose: [PROJECT_PURPOSE.md](PROJECT_PURPOSE.md)
|
| 100 |
-
- Contributing: [CONTRIBUTING.md](CONTRIBUTING.md)
|
| 101 |
-
- Roadmap: [ROADMAP.md](ROADMAP.md)
|
| 102 |
-
- Governance: [GOVERNANCE.md](GOVERNANCE.md)
|
| 103 |
-
- License policy: [LICENSE_POLICY.md](LICENSE_POLICY.md)
|
| 104 |
- Changelog: [CHANGELOG.md](CHANGELOG.md)
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
- Datasets: [resources/datasets/README.md](resources/datasets/README.md)
|
| 113 |
-
- Models: [resources/models/README.md](resources/models/README.md)
|
| 114 |
-
- Benchmarks: [resources/benchmarks/README.md](resources/benchmarks/README.md)
|
| 115 |
-
- Tools: [resources/tools/README.md](resources/tools/README.md)
|
| 116 |
-
- Papers: [resources/papers/README.md](resources/papers/README.md)
|
| 117 |
-
- Projects: [resources/projects/README.md](resources/projects/README.md)
|
| 118 |
-
- Code: [resources/codes/README.md](resources/codes/README.md)
|
| 119 |
-
|
| 120 |
-
## Workspaces
|
| 121 |
-
|
| 122 |
-
- [data/](data/README.md): datasets, curation, metadata, quality
|
| 123 |
-
- [asr/](asr/README.md): ASR baselines and experiments
|
| 124 |
-
- [tts/](tts/README.md): TTS baselines and experiments
|
| 125 |
-
- [benchmarks/](benchmarks/README.md): benchmark sets and evaluation
|
| 126 |
-
- [experiments/](experiments/README.md): reproducible run cards
|
| 127 |
-
- [apps/desktop/](apps/desktop/README.md): user-facing integration references
|
| 128 |
-
- [models/](models/README.md): model layout and release conventions
|
|
|
|
| 18 |
|
| 19 |
# Pashto Language Resources Hub (Pukhto/Pashto)
|
| 20 |
|
| 21 |
+
Open-source Pashto language technology hub for datasets, models, benchmarks, ASR, TTS, NLP, and machine translation.
|
| 22 |
|
| 23 |
+
This repository curates verified Pashto resources and keeps validation and publishing workflows reproducible.
|
| 24 |
|
| 25 |
+
## Quick Links
|
| 26 |
|
| 27 |
+
- Search page: [Pashto Resource Search](https://musawer1214.github.io/pashto-language-resources/search/)
|
| 28 |
- Project site: [Pashto Language Resources Hub](https://musawer1214.github.io/pashto-language-resources/)
|
| 29 |
+
- Documentation hub: [docs/README.md](docs/README.md)
|
| 30 |
+
- GitHub: [Musawer1214/pashto-language-resources](https://github.com/Musawer1214/pashto-language-resources)
|
| 31 |
- Hugging Face mirror: [Musawer14/pashto-language-resources](https://huggingface.co/Musawer14/pashto-language-resources)
|
| 32 |
|
| 33 |
+
## High-Intent Pages
|
| 34 |
|
| 35 |
+
- [Pashto datasets](docs/pashto_datasets.md)
|
| 36 |
+
- [Pashto ASR resources](docs/pashto_asr.md)
|
| 37 |
+
- [Pashto TTS resources](docs/pashto_tts.md)
|
| 38 |
|
| 39 |
+
## Repository Structure
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
+
- `resources/`: verified external resources with structured categories.
|
| 42 |
+
- `data/`: normalization seeds, metadata, and data workflows.
|
| 43 |
+
- `asr/`: ASR notes, baselines, and references.
|
| 44 |
+
- `tts/`: TTS notes, baselines, and references.
|
| 45 |
+
- `benchmarks/`: schemas, result templates, and evaluation guidance.
|
| 46 |
+
- `experiments/`: reproducible run-card templates.
|
| 47 |
+
- `docs/`: SEO, release, platform, and contribution documentation.
|
| 48 |
|
| 49 |
+
## Resource Workflow
|
|
|
|
|
|
|
| 50 |
|
| 51 |
+
1. Discovery job (`.github/workflows/resource_sync.yml`) updates candidate feed.
|
| 52 |
+
2. Maintainer review promotes high-quality entries to `resources/catalog/resources.json`.
|
| 53 |
+
3. Regeneration and validation updates derived views and search index.
|
| 54 |
|
| 55 |
+
Core commands:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
|
| 57 |
```bash
|
|
|
|
| 58 |
python scripts/validate_resource_catalog.py
|
| 59 |
python scripts/generate_resource_views.py
|
| 60 |
python scripts/check_links.py
|
| 61 |
python -m pytest -q
|
| 62 |
```
|
| 63 |
|
| 64 |
+
## SEO and Discoverability
|
| 65 |
|
| 66 |
+
- SEO playbook: [docs/discoverability_seo.md](docs/discoverability_seo.md)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
- GitHub topics checklist: [docs/github_topics_checklist.md](docs/github_topics_checklist.md)
|
| 68 |
- Backlink strategy: [docs/backlink_strategy.md](docs/backlink_strategy.md)
|
| 69 |
+
- Platform sync policy: [docs/platform_sync_policy.md](docs/platform_sync_policy.md)
|
| 70 |
+
- Search UI source: [docs/search/index.html](docs/search/index.html)
|
| 71 |
+
- Citation metadata: [CITATION.cff](CITATION.cff)
|
| 72 |
+
|
| 73 |
+
## Releases
|
| 74 |
+
|
| 75 |
+
- Release notes index: [docs/releases/README.md](docs/releases/README.md)
|
| 76 |
+
- Latest release notes: [v1.0.0](docs/releases/v1.0.0.md)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
- Changelog: [CHANGELOG.md](CHANGELOG.md)
|
| 78 |
+
|
| 79 |
+
## Contributing
|
| 80 |
+
|
| 81 |
+
- Contribution guide: [CONTRIBUTING.md](CONTRIBUTING.md)
|
| 82 |
+
- Community communication: [community/COMMUNICATION.md](community/COMMUNICATION.md)
|
| 83 |
+
- Resource guidelines: [docs/dataset_guidelines.md](docs/dataset_guidelines.md)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/README.md
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
# Documentation Hub
|
| 2 |
|
| 3 |
-
This folder is the main documentation entry point for contributors.
|
|
|
|
|
|
|
| 4 |
|
| 5 |
-
## Start here
|
| 6 |
- Project purpose: [../PROJECT_PURPOSE.md](../PROJECT_PURPOSE.md)
|
| 7 |
- Contributing guide: [../CONTRIBUTING.md](../CONTRIBUTING.md)
|
| 8 |
- Governance: [../GOVERNANCE.md](../GOVERNANCE.md)
|
|
@@ -10,45 +11,40 @@ This folder is the main documentation entry point for contributors.
|
|
| 10 |
- Roadmap: [../ROADMAP.md](../ROADMAP.md)
|
| 11 |
- Changelog: [../CHANGELOG.md](../CHANGELOG.md)
|
| 12 |
|
| 13 |
-
##
|
| 14 |
-
|
| 15 |
-
-
|
| 16 |
-
- Pashto normalization policy: [pashto_normalization_v0.1.md](pashto_normalization_v0.1.md)
|
| 17 |
-
- Common Voice Pashto integration: [common_voice_pashto_24.md](common_voice_pashto_24.md)
|
| 18 |
-
- Discoverability and SEO playbook: [discoverability_seo.md](discoverability_seo.md)
|
| 19 |
-
- Platform sync policy: [platform_sync_policy.md](platform_sync_policy.md)
|
| 20 |
- GitHub topics checklist: [github_topics_checklist.md](github_topics_checklist.md)
|
| 21 |
- Backlink strategy: [backlink_strategy.md](backlink_strategy.md)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
- Release process: [release_process.md](release_process.md)
|
| 23 |
- Release checklist: [release_checklist.md](release_checklist.md)
|
|
|
|
| 24 |
- Platforms and publish flow: [platforms.md](platforms.md)
|
|
|
|
| 25 |
- GitHub operations: [github_operations.md](github_operations.md)
|
| 26 |
-
- Resource automation: [resource_automation.md](resource_automation.md)
|
| 27 |
-
- Resource cycle runbook: [resource_cycle_runbook.md](resource_cycle_runbook.md)
|
| 28 |
|
| 29 |
-
##
|
| 30 |
-
- Pashto datasets page: [pashto_datasets.md](pashto_datasets.md)
|
| 31 |
-
- Pashto ASR page: [pashto_asr.md](pashto_asr.md)
|
| 32 |
-
- Pashto TTS page: [pashto_tts.md](pashto_tts.md)
|
| 33 |
|
| 34 |
-
|
| 35 |
-
-
|
| 36 |
-
- v0.1.2 draft notes: [release_v0.1.2.md](release_v0.1.2.md)
|
| 37 |
-
|
| 38 |
-
## Resource tracking
|
| 39 |
-
- Master resource index: [resource_catalog.md](resource_catalog.md)
|
| 40 |
-
- GitHub Pages search: [search/index.html](search/index.html)
|
| 41 |
- Structured resources folder: [../resources/README.md](../resources/README.md)
|
| 42 |
|
| 43 |
## Tooling
|
|
|
|
| 44 |
- Scripts overview: [../scripts/README.md](../scripts/README.md)
|
| 45 |
- Link checker: [../scripts/check_links.py](../scripts/check_links.py)
|
| 46 |
- Resource catalog validator: [../scripts/validate_resource_catalog.py](../scripts/validate_resource_catalog.py)
|
| 47 |
- Resource view generator: [../scripts/generate_resource_views.py](../scripts/generate_resource_views.py)
|
| 48 |
- Candidate sync script: [../scripts/sync_resources.py](../scripts/sync_resources.py)
|
| 49 |
- Normalization validator: [../scripts/validate_normalization.py](../scripts/validate_normalization.py)
|
| 50 |
-
|
| 51 |
-
## Evaluation and experiments
|
| 52 |
-
- Benchmark result format: [../benchmarks/results/README.md](../benchmarks/results/README.md)
|
| 53 |
-
- Benchmark schema: [../benchmarks/schema/benchmark_result.schema.json](../benchmarks/schema/benchmark_result.schema.json)
|
| 54 |
-
- Experiment run cards: [../experiments/README.md](../experiments/README.md)
|
|
|
|
| 1 |
# Documentation Hub
|
| 2 |
|
| 3 |
+
This folder is the main documentation entry point for contributors and maintainers.
|
| 4 |
+
|
| 5 |
+
## Project Foundations
|
| 6 |
|
|
|
|
| 7 |
- Project purpose: [../PROJECT_PURPOSE.md](../PROJECT_PURPOSE.md)
|
| 8 |
- Contributing guide: [../CONTRIBUTING.md](../CONTRIBUTING.md)
|
| 9 |
- Governance: [../GOVERNANCE.md](../GOVERNANCE.md)
|
|
|
|
| 11 |
- Roadmap: [../ROADMAP.md](../ROADMAP.md)
|
| 12 |
- Changelog: [../CHANGELOG.md](../CHANGELOG.md)
|
| 13 |
|
| 14 |
+
## Discovery and SEO
|
| 15 |
+
|
| 16 |
+
- Discoverability playbook: [discoverability_seo.md](discoverability_seo.md)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
- GitHub topics checklist: [github_topics_checklist.md](github_topics_checklist.md)
|
| 18 |
- Backlink strategy: [backlink_strategy.md](backlink_strategy.md)
|
| 19 |
+
- Search UI: [search/index.html](search/index.html)
|
| 20 |
+
- Resource catalog docs: [resource_catalog.md](resource_catalog.md)
|
| 21 |
+
|
| 22 |
+
## Intent Landing Pages
|
| 23 |
+
|
| 24 |
+
- Pashto datasets: [pashto_datasets.md](pashto_datasets.md)
|
| 25 |
+
- Pashto ASR resources: [pashto_asr.md](pashto_asr.md)
|
| 26 |
+
- Pashto TTS resources: [pashto_tts.md](pashto_tts.md)
|
| 27 |
+
|
| 28 |
+
## Release and Platform Operations
|
| 29 |
+
|
| 30 |
- Release process: [release_process.md](release_process.md)
|
| 31 |
- Release checklist: [release_checklist.md](release_checklist.md)
|
| 32 |
+
- Release notes index: [releases/README.md](releases/README.md)
|
| 33 |
- Platforms and publish flow: [platforms.md](platforms.md)
|
| 34 |
+
- Platform sync policy: [platform_sync_policy.md](platform_sync_policy.md)
|
| 35 |
- GitHub operations: [github_operations.md](github_operations.md)
|
|
|
|
|
|
|
| 36 |
|
| 37 |
+
## Resource Automation
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
+
- Resource automation: [resource_automation.md](resource_automation.md)
|
| 40 |
+
- Resource cycle runbook: [resource_cycle_runbook.md](resource_cycle_runbook.md)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
- Structured resources folder: [../resources/README.md](../resources/README.md)
|
| 42 |
|
| 43 |
## Tooling
|
| 44 |
+
|
| 45 |
- Scripts overview: [../scripts/README.md](../scripts/README.md)
|
| 46 |
- Link checker: [../scripts/check_links.py](../scripts/check_links.py)
|
| 47 |
- Resource catalog validator: [../scripts/validate_resource_catalog.py](../scripts/validate_resource_catalog.py)
|
| 48 |
- Resource view generator: [../scripts/generate_resource_views.py](../scripts/generate_resource_views.py)
|
| 49 |
- Candidate sync script: [../scripts/sync_resources.py](../scripts/sync_resources.py)
|
| 50 |
- Normalization validator: [../scripts/validate_normalization.py](../scripts/validate_normalization.py)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/discoverability_seo.md
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
This playbook focuses on making the repository easier to find in:
|
| 4 |
|
| 5 |
- GitHub search
|
| 6 |
-
- Google
|
| 7 |
- Academic and resource discovery channels
|
| 8 |
|
| 9 |
## 1) Repository Slug Status
|
|
@@ -28,7 +28,7 @@ Set these in repository `Settings -> General` and About panel:
|
|
| 28 |
- Description:
|
| 29 |
- `Open-source Pashto (Pukhto/Pashto) datasets, ASR, TTS, NLP, MT, models, and benchmark resources.`
|
| 30 |
- Website:
|
| 31 |
-
- [GitHub Pages home](https://musawer1214.github.io/pashto-language-resources/)
|
| 32 |
- Topics:
|
| 33 |
- `pashto`
|
| 34 |
- `pukhto`
|
|
@@ -45,7 +45,7 @@ Set these in repository `Settings -> General` and About panel:
|
|
| 45 |
|
| 46 |
- Keep the first 160 characters of `README.md` keyword clear.
|
| 47 |
- Use consistent terminology across pages: `Pashto (Pukhto/Pushto)`.
|
| 48 |
-
- Publish
|
| 49 |
- Keep `CITATION.cff` updated for scholarly reuse and citation.
|
| 50 |
|
| 51 |
## 4) Pages SEO and Crawlability
|
|
@@ -61,19 +61,21 @@ Keep these updated when renaming slug or domain.
|
|
| 61 |
## 5) External Discovery Boost
|
| 62 |
|
| 63 |
- Add the GitHub Pages search URL to:
|
| 64 |
-
- Hugging Face model
|
| 65 |
- Relevant community profiles and README links
|
| 66 |
-
- Conference
|
| 67 |
- Ask contributors to link specific resource pages in blog posts or papers.
|
| 68 |
|
| 69 |
-
## SEO Operation Assets
|
| 70 |
|
| 71 |
- GitHub topics checklist: [github_topics_checklist.md](github_topics_checklist.md)
|
| 72 |
- Backlink strategy: [backlink_strategy.md](backlink_strategy.md)
|
| 73 |
- Intent page: [Pashto datasets](pashto_datasets.md)
|
| 74 |
- Intent page: [Pashto ASR](pashto_asr.md)
|
| 75 |
- Intent page: [Pashto TTS](pashto_tts.md)
|
| 76 |
-
|
|
|
|
|
|
|
| 77 |
|
| 78 |
1. Push all changes to `main`.
|
| 79 |
2. Verify GitHub Pages is serving:
|
|
@@ -88,5 +90,3 @@ Keep these updated when renaming slug or domain.
|
|
| 88 |
- Home page
|
| 89 |
- Search page
|
| 90 |
6. Recheck search visibility after 1 to 3 weeks.
|
| 91 |
-
|
| 92 |
-
|
|
|
|
| 3 |
This playbook focuses on making the repository easier to find in:
|
| 4 |
|
| 5 |
- GitHub search
|
| 6 |
+
- Google and Bing search
|
| 7 |
- Academic and resource discovery channels
|
| 8 |
|
| 9 |
## 1) Repository Slug Status
|
|
|
|
| 28 |
- Description:
|
| 29 |
- `Open-source Pashto (Pukhto/Pashto) datasets, ASR, TTS, NLP, MT, models, and benchmark resources.`
|
| 30 |
- Website:
|
| 31 |
+
- [GitHub Pages home](https://musawer1214.github.io/pashto-language-resources/)
|
| 32 |
- Topics:
|
| 33 |
- `pashto`
|
| 34 |
- `pukhto`
|
|
|
|
| 45 |
|
| 46 |
- Keep the first 160 characters of `README.md` keyword clear.
|
| 47 |
- Use consistent terminology across pages: `Pashto (Pukhto/Pushto)`.
|
| 48 |
+
- Publish updates through `CHANGELOG.md` and release notes in `docs/releases/`.
|
| 49 |
- Keep `CITATION.cff` updated for scholarly reuse and citation.
|
| 50 |
|
| 51 |
## 4) Pages SEO and Crawlability
|
|
|
|
| 61 |
## 5) External Discovery Boost
|
| 62 |
|
| 63 |
- Add the GitHub Pages search URL to:
|
| 64 |
+
- Hugging Face model and dataset cards
|
| 65 |
- Relevant community profiles and README links
|
| 66 |
+
- Conference or demo pages for Pashto language technology
|
| 67 |
- Ask contributors to link specific resource pages in blog posts or papers.
|
| 68 |
|
| 69 |
+
## 6) SEO Operation Assets
|
| 70 |
|
| 71 |
- GitHub topics checklist: [github_topics_checklist.md](github_topics_checklist.md)
|
| 72 |
- Backlink strategy: [backlink_strategy.md](backlink_strategy.md)
|
| 73 |
- Intent page: [Pashto datasets](pashto_datasets.md)
|
| 74 |
- Intent page: [Pashto ASR](pashto_asr.md)
|
| 75 |
- Intent page: [Pashto TTS](pashto_tts.md)
|
| 76 |
+
- Release notes index: [releases/README.md](releases/README.md)
|
| 77 |
+
|
| 78 |
+
## 7) Indexing Checklist (After Push)
|
| 79 |
|
| 80 |
1. Push all changes to `main`.
|
| 81 |
2. Verify GitHub Pages is serving:
|
|
|
|
| 90 |
- Home page
|
| 91 |
- Search page
|
| 92 |
6. Recheck search visibility after 1 to 3 weeks.
|
|
|
|
|
|
docs/index.md
CHANGED
|
@@ -8,35 +8,25 @@ description: Open-source Pashto (Pukhto/Pashto) datasets, models, benchmarks, AS
|
|
| 8 |
|
| 9 |
`pashto-language-resources` is a community-led open-source project focused on making Pashto (also written as Pukhto/Pushto) a first-class language in speech and language AI.
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
## Mission
|
| 12 |
|
| 13 |
- Build open Pashto datasets and resource indexes for ASR, TTS, NLP, and MT.
|
| 14 |
- Publish reproducible baseline models, benchmark schemas, and evaluation workflows.
|
| 15 |
- Keep progress transparent, contributor-friendly, and public-benefit oriented.
|
| 16 |
|
| 17 |
-
## What Is In This Repository
|
| 18 |
-
|
| 19 |
-
- `data/`: dataset workflows, metadata, and normalization seeds.
|
| 20 |
-
- `asr/`: ASR baselines and experiment notes.
|
| 21 |
-
- `tts/`: TTS baselines and quality tracking.
|
| 22 |
-
- `benchmarks/`: benchmark schema, result format, and metric guidance.
|
| 23 |
-
- `experiments/`: reproducible run cards and experiment records.
|
| 24 |
-
- `docs/`: policies, roadmap, release process, and operating guides.
|
| 25 |
-
- `resources/`: verified external Pashto datasets, models, tools, benchmarks, and papers.
|
| 26 |
-
|
| 27 |
-
## Search Pashto Resources
|
| 28 |
-
|
| 29 |
-
- Search UI: [Pashto Resource Search](search/)
|
| 30 |
-
- Resource index docs: [resource_catalog.md](resource_catalog.md)
|
| 31 |
-
- Machine-readable catalog (GitHub): [resources.json source](https://github.com/Musawer1214/pashto-language-resources/blob/main/resources/catalog/resources.json)
|
| 32 |
-
|
| 33 |
## Intent Pages
|
| 34 |
|
| 35 |
- Pashto datasets: [pashto_datasets.md](pashto_datasets.md)
|
| 36 |
- Pashto ASR resources: [pashto_asr.md](pashto_asr.md)
|
| 37 |
- Pashto TTS resources: [pashto_tts.md](pashto_tts.md)
|
| 38 |
|
| 39 |
-
##
|
| 40 |
|
| 41 |
- Repository: [Musawer1214/pashto-language-resources](https://github.com/Musawer1214/pashto-language-resources)
|
| 42 |
- Hugging Face: [Musawer14/pashto-language-resources](https://huggingface.co/Musawer14/pashto-language-resources)
|
|
@@ -46,30 +36,24 @@ description: Open-source Pashto (Pukhto/Pashto) datasets, models, benchmarks, AS
|
|
| 46 |
|
| 47 |
## SEO Operations
|
| 48 |
|
|
|
|
| 49 |
- GitHub topics checklist: [github_topics_checklist.md](github_topics_checklist.md)
|
| 50 |
- Backlink strategy: [backlink_strategy.md](backlink_strategy.md)
|
| 51 |
-
- Release notes v0.1.1: [release_v0.1.1.md](release_v0.1.1.md)
|
| 52 |
-
- Release notes v0.1.2: [release_v0.1.2.md](release_v0.1.2.md)
|
| 53 |
|
| 54 |
-
##
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
You can help by improving documentation, validating normalization rows, sharing verified resources, or contributing data, model, and evaluation workflows.
|
| 57 |
|
| 58 |
-
|
| 59 |
- [docs/README.md](README.md)
|
| 60 |
- [community/COMMUNICATION.md](../community/COMMUNICATION.md)
|
| 61 |
|
| 62 |
-
## Search Terms
|
| 63 |
-
|
| 64 |
-
This project is relevant to searches like:
|
| 65 |
-
|
| 66 |
-
- Pashto datasets
|
| 67 |
-
- Pashto ASR model
|
| 68 |
-
- Pashto TTS resources
|
| 69 |
-
- Pashto NLP benchmark
|
| 70 |
-
- Pashto language technology
|
| 71 |
-
- Pukhto language resources
|
| 72 |
-
|
| 73 |
## License
|
| 74 |
|
| 75 |
This project is released under Apache 2.0. See [LICENSE](../LICENSE).
|
|
|
|
| 8 |
|
| 9 |
`pashto-language-resources` is a community-led open-source project focused on making Pashto (also written as Pukhto/Pushto) a first-class language in speech and language AI.
|
| 10 |
|
| 11 |
+
## Quick Actions
|
| 12 |
+
|
| 13 |
+
- Search resources: [Pashto Resource Search](search/)
|
| 14 |
+
- Browse all docs: [Documentation Hub](README.md)
|
| 15 |
+
- Browse verified resource catalog: [resource_catalog.md](resource_catalog.md)
|
| 16 |
+
|
| 17 |
## Mission
|
| 18 |
|
| 19 |
- Build open Pashto datasets and resource indexes for ASR, TTS, NLP, and MT.
|
| 20 |
- Publish reproducible baseline models, benchmark schemas, and evaluation workflows.
|
| 21 |
- Keep progress transparent, contributor-friendly, and public-benefit oriented.
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
## Intent Pages
|
| 24 |
|
| 25 |
- Pashto datasets: [pashto_datasets.md](pashto_datasets.md)
|
| 26 |
- Pashto ASR resources: [pashto_asr.md](pashto_asr.md)
|
| 27 |
- Pashto TTS resources: [pashto_tts.md](pashto_tts.md)
|
| 28 |
|
| 29 |
+
## Repository References
|
| 30 |
|
| 31 |
- Repository: [Musawer1214/pashto-language-resources](https://github.com/Musawer1214/pashto-language-resources)
|
| 32 |
- Hugging Face: [Musawer14/pashto-language-resources](https://huggingface.co/Musawer14/pashto-language-resources)
|
|
|
|
| 36 |
|
| 37 |
## SEO Operations
|
| 38 |
|
| 39 |
+
- Discoverability playbook: [discoverability_seo.md](discoverability_seo.md)
|
| 40 |
- GitHub topics checklist: [github_topics_checklist.md](github_topics_checklist.md)
|
| 41 |
- Backlink strategy: [backlink_strategy.md](backlink_strategy.md)
|
|
|
|
|
|
|
| 42 |
|
| 43 |
+
## Releases
|
| 44 |
+
|
| 45 |
+
- Release notes index: [releases/README.md](releases/README.md)
|
| 46 |
+
- Current release notes: [v1.0.0](releases/v1.0.0.md)
|
| 47 |
+
- Changelog: [../CHANGELOG.md](../CHANGELOG.md)
|
| 48 |
+
|
| 49 |
+
## Contribution
|
| 50 |
|
| 51 |
You can help by improving documentation, validating normalization rows, sharing verified resources, or contributing data, model, and evaluation workflows.
|
| 52 |
|
| 53 |
+
Start here:
|
| 54 |
- [docs/README.md](README.md)
|
| 55 |
- [community/COMMUNICATION.md](../community/COMMUNICATION.md)
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
## License
|
| 58 |
|
| 59 |
This project is released under Apache 2.0. See [LICENSE](../LICENSE).
|
docs/platform_sync_policy.md
CHANGED
|
@@ -28,12 +28,19 @@ Use a lowest-common-denominator style in shared docs:
|
|
| 28 |
- Relative links for internal files whenever possible.
|
| 29 |
- YAML front matter only where needed (`README.md` for HF metadata, docs pages for Jekyll SEO).
|
| 30 |
- Avoid GitHub-only HTML widgets and avoid HF-specific custom blocks in shared files.
|
|
|
|
| 31 |
## Known Platform Differences
|
| 32 |
|
| 33 |
- GitHub accepts regular Git binary blobs in many repos.
|
| 34 |
-
- Hugging Face may reject binary blobs unless stored with Xet
|
| 35 |
- Hugging Face may warn about missing model-card metadata in README; this is a warning, not a push blocker.
|
| 36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
## Safe Update Checklist
|
| 38 |
|
| 39 |
1. Run checks:
|
|
@@ -57,4 +64,3 @@ If GitHub and Hugging Face histories diverge:
|
|
| 57 |
- Keep GitHub `main` as canonical source history.
|
| 58 |
- Sync Hugging Face using a content snapshot commit based on `hf/main`.
|
| 59 |
- Do not rewrite remote history unless explicitly required.
|
| 60 |
-
|
|
|
|
| 28 |
- Relative links for internal files whenever possible.
|
| 29 |
- YAML front matter only where needed (`README.md` for HF metadata, docs pages for Jekyll SEO).
|
| 30 |
- Avoid GitHub-only HTML widgets and avoid HF-specific custom blocks in shared files.
|
| 31 |
+
|
| 32 |
## Known Platform Differences
|
| 33 |
|
| 34 |
- GitHub accepts regular Git binary blobs in many repos.
|
| 35 |
+
- Hugging Face may reject binary blobs unless stored with Xet or LFS-compatible flow.
|
| 36 |
- Hugging Face may warn about missing model-card metadata in README; this is a warning, not a push blocker.
|
| 37 |
|
| 38 |
+
## Tagging Strategy
|
| 39 |
+
|
| 40 |
+
- Create annotated tags on GitHub release commits.
|
| 41 |
+
- If Hugging Face rejects a tag because of blocked binary history, create the same tag name on the HF-safe `hf/main` commit.
|
| 42 |
+
- Keep release notes content identical even when commit hashes differ across platforms.
|
| 43 |
+
|
| 44 |
## Safe Update Checklist
|
| 45 |
|
| 46 |
1. Run checks:
|
|
|
|
| 64 |
- Keep GitHub `main` as canonical source history.
|
| 65 |
- Sync Hugging Face using a content snapshot commit based on `hf/main`.
|
| 66 |
- Do not rewrite remote history unless explicitly required.
|
|
|
docs/release_checklist.md
CHANGED
|
@@ -3,14 +3,19 @@
|
|
| 3 |
Use this checklist before tagging a new release.
|
| 4 |
|
| 5 |
## Required
|
|
|
|
| 6 |
- [ ] Update [CHANGELOG.md](../CHANGELOG.md).
|
|
|
|
| 7 |
- [ ] Run `python scripts/check_links.py`.
|
| 8 |
- [ ] Run `python scripts/validate_normalization.py data/processed/normalization_seed_v0.1.tsv`.
|
|
|
|
| 9 |
- [ ] Confirm benchmark snapshots are stored in [../benchmarks/results/README.md](../benchmarks/results/README.md) format.
|
| 10 |
- [ ] Confirm docs reflect the release scope.
|
| 11 |
|
| 12 |
## Recommended
|
|
|
|
| 13 |
- [ ] Run tests (`python -m pytest -q`).
|
| 14 |
- [ ] Re-check key external resource links in [resource_catalog.md](resource_catalog.md).
|
| 15 |
- [ ] Verify README rendering on GitHub and Hugging Face after push.
|
| 16 |
-
|
|
|
|
|
|
| 3 |
Use this checklist before tagging a new release.
|
| 4 |
|
| 5 |
## Required
|
| 6 |
+
|
| 7 |
- [ ] Update [CHANGELOG.md](../CHANGELOG.md).
|
| 8 |
+
- [ ] Add release notes under [releases/README.md](releases/README.md).
|
| 9 |
- [ ] Run `python scripts/check_links.py`.
|
| 10 |
- [ ] Run `python scripts/validate_normalization.py data/processed/normalization_seed_v0.1.tsv`.
|
| 11 |
+
- [ ] Run `python scripts/validate_resource_catalog.py`.
|
| 12 |
- [ ] Confirm benchmark snapshots are stored in [../benchmarks/results/README.md](../benchmarks/results/README.md) format.
|
| 13 |
- [ ] Confirm docs reflect the release scope.
|
| 14 |
|
| 15 |
## Recommended
|
| 16 |
+
|
| 17 |
- [ ] Run tests (`python -m pytest -q`).
|
| 18 |
- [ ] Re-check key external resource links in [resource_catalog.md](resource_catalog.md).
|
| 19 |
- [ ] Verify README rendering on GitHub and Hugging Face after push.
|
| 20 |
+
- [ ] Verify GitHub and Hugging Face `main` trees are content-equivalent.
|
| 21 |
+
- [ ] Push release tag to both platforms.
|
docs/release_process.md
CHANGED
|
@@ -1,21 +1,32 @@
|
|
| 1 |
-
#
|
| 2 |
|
| 3 |
-
##
|
| 4 |
-
|
| 5 |
-
-
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
-
## ✅ Required for release
|
| 8 |
- Changelog summary in [../CHANGELOG.md](../CHANGELOG.md)
|
| 9 |
- Benchmark snapshot in [../benchmarks/results/README.md](../benchmarks/results/README.md) format
|
| 10 |
- Known limitations section in release notes
|
| 11 |
-
- Reproducible commands
|
| 12 |
-
-
|
| 13 |
- `python scripts/check_links.py`
|
| 14 |
- `python scripts/validate_normalization.py data/processed/normalization_seed_v0.1.tsv`
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
-
##
|
| 17 |
-
- Use semantic-style tags for major milestones (e.g., `v0.1`, `v0.2`)
|
| 18 |
|
| 19 |
-
## 🧾 Templates
|
| 20 |
- Release checklist: [release_checklist.md](release_checklist.md)
|
| 21 |
-
- Release
|
|
|
|
| 1 |
+
# Release Process
|
| 2 |
|
| 3 |
+
## Cadence
|
| 4 |
+
|
| 5 |
+
- Scheduled release: monthly milestone or when a major quality threshold is met.
|
| 6 |
+
- Hotfix release: any urgent fixes that should not wait for the next milestone.
|
| 7 |
+
|
| 8 |
+
## Required for Release
|
| 9 |
|
|
|
|
| 10 |
- Changelog summary in [../CHANGELOG.md](../CHANGELOG.md)
|
| 11 |
- Benchmark snapshot in [../benchmarks/results/README.md](../benchmarks/results/README.md) format
|
| 12 |
- Known limitations section in release notes
|
| 13 |
+
- Reproducible commands or scripts
|
| 14 |
+
- Validation checks:
|
| 15 |
- `python scripts/check_links.py`
|
| 16 |
- `python scripts/validate_normalization.py data/processed/normalization_seed_v0.1.tsv`
|
| 17 |
+
- `python scripts/validate_resource_catalog.py`
|
| 18 |
+
|
| 19 |
+
## Versioning
|
| 20 |
+
|
| 21 |
+
- Use semantic version tags: `vMAJOR.MINOR.PATCH`.
|
| 22 |
+
- Example: `v1.0.0`, `v1.0.1`, `v1.1.0`, `v2.0.0`.
|
| 23 |
+
|
| 24 |
+
## Release Notes Location
|
| 25 |
+
|
| 26 |
+
- Store release notes in [releases/README.md](releases/README.md).
|
| 27 |
+
- Add one file per release tag under `docs/releases/`.
|
| 28 |
|
| 29 |
+
## Templates
|
|
|
|
| 30 |
|
|
|
|
| 31 |
- Release checklist: [release_checklist.md](release_checklist.md)
|
| 32 |
+
- Release template: [../.github/release_template.md](../.github/release_template.md)
|
docs/release_v0.1.1.md
DELETED
|
@@ -1,38 +0,0 @@
|
|
| 1 |
-
# Release Notes Draft: v0.1.1
|
| 2 |
-
|
| 3 |
-
Status: draft
|
| 4 |
-
Target date: TBD
|
| 5 |
-
|
| 6 |
-
## Summary
|
| 7 |
-
|
| 8 |
-
v0.1.1 focuses on discoverability improvements and cross-platform consistency between GitHub and Hugging Face.
|
| 9 |
-
|
| 10 |
-
## Highlights
|
| 11 |
-
|
| 12 |
-
- Added HF model-card YAML metadata to `README.md`.
|
| 13 |
-
- Added SEO operations docs:
|
| 14 |
-
- `docs/github_topics_checklist.md`
|
| 15 |
-
- `docs/backlink_strategy.md`
|
| 16 |
-
- Added intent landing pages:
|
| 17 |
-
- `docs/pashto_datasets.md`
|
| 18 |
-
- `docs/pashto_asr.md`
|
| 19 |
-
- `docs/pashto_tts.md`
|
| 20 |
-
- Expanded docs hub and index references for new SEO content.
|
| 21 |
-
|
| 22 |
-
## Validation Checklist
|
| 23 |
-
|
| 24 |
-
- [ ] `python scripts/check_links.py`
|
| 25 |
-
- [ ] `python scripts/validate_resource_catalog.py`
|
| 26 |
-
- [ ] `python -m pytest -q`
|
| 27 |
-
|
| 28 |
-
## Release Commands
|
| 29 |
-
|
| 30 |
-
```bash
|
| 31 |
-
git tag v0.1.1
|
| 32 |
-
git push origin v0.1.1
|
| 33 |
-
```
|
| 34 |
-
|
| 35 |
-
## Compare
|
| 36 |
-
|
| 37 |
-
- GitHub compare: [v0.1...v0.1.1](https://github.com/Musawer1214/pashto-language-resources/compare/v0.1...v0.1.1)
|
| 38 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/release_v0.1.2.md
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
# Release Notes Draft: v0.1.2
|
| 2 |
-
|
| 3 |
-
Status: draft
|
| 4 |
-
Target date: TBD
|
| 5 |
-
|
| 6 |
-
## Summary
|
| 7 |
-
|
| 8 |
-
v0.1.2 is reserved for post-indexing improvements after monitoring search performance and backlink growth.
|
| 9 |
-
|
| 10 |
-
## Planned Scope
|
| 11 |
-
|
| 12 |
-
- Refine high-intent docs based on Search Console query data.
|
| 13 |
-
- Expand verified resource coverage with citation-quality metadata.
|
| 14 |
-
- Publish first KPI review for backlinks and discoverability metrics.
|
| 15 |
-
- Tighten internal linking between docs hub, search page, and resource sections.
|
| 16 |
-
|
| 17 |
-
## Validation Checklist
|
| 18 |
-
|
| 19 |
-
- [ ] `python scripts/check_links.py`
|
| 20 |
-
- [ ] `python scripts/validate_resource_catalog.py`
|
| 21 |
-
- [ ] `python -m pytest -q`
|
| 22 |
-
|
| 23 |
-
## Release Commands
|
| 24 |
-
|
| 25 |
-
```bash
|
| 26 |
-
git tag v0.1.2
|
| 27 |
-
git push origin v0.1.2
|
| 28 |
-
```
|
| 29 |
-
|
| 30 |
-
## Compare
|
| 31 |
-
|
| 32 |
-
- GitHub compare: [v0.1.1...v0.1.2](https://github.com/Musawer1214/pashto-language-resources/compare/v0.1.1...v0.1.2)
|
| 33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/releases/README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Releases
|
| 2 |
+
|
| 3 |
+
This directory stores versioned release notes for the project.
|
| 4 |
+
|
| 5 |
+
## Current
|
| 6 |
+
|
| 7 |
+
- [v1.0.0](v1.0.0.md)
|
| 8 |
+
|
| 9 |
+
## Notes
|
| 10 |
+
|
| 11 |
+
- `v1.0.0` is the first official stable release tag.
|
| 12 |
+
- Earlier bootstrap history (`v0.1`) remains documented in [../../CHANGELOG.md](../../CHANGELOG.md).
|
docs/releases/v1.0.0.md
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Release Notes: v1.0.0
|
| 2 |
+
|
| 3 |
+
Release date: 2026-02-18
|
| 4 |
+
Tag: `v1.0.0`
|
| 5 |
+
|
| 6 |
+
## Summary
|
| 7 |
+
|
| 8 |
+
First stable release of `pashto-language-resources` with cleaned structure, stronger discoverability, and upgraded web usability for resource exploration.
|
| 9 |
+
|
| 10 |
+
## Highlights
|
| 11 |
+
|
| 12 |
+
- Unified release documentation under `docs/releases/`.
|
| 13 |
+
- Removed stale draft release pages and redundant references.
|
| 14 |
+
- Refined docs structure for clearer navigation and lower duplication.
|
| 15 |
+
- Upgraded search page UX with faster exploration patterns and clearer controls.
|
| 16 |
+
- Hardened platform-sync guidance for GitHub and Hugging Face parity.
|
| 17 |
+
|
| 18 |
+
## Validation
|
| 19 |
+
|
| 20 |
+
- `python scripts/check_links.py`
|
| 21 |
+
- `python scripts/validate_resource_catalog.py`
|
| 22 |
+
- `python scripts/validate_normalization.py data/processed/normalization_seed_v0.1.tsv`
|
| 23 |
+
- `python -m pytest -q`
|
| 24 |
+
|
| 25 |
+
## Platform State
|
| 26 |
+
|
| 27 |
+
- GitHub repository: `Musawer1214/pashto-language-resources`
|
| 28 |
+
- Hugging Face mirror: `Musawer14/pashto-language-resources`
|
| 29 |
+
- Main-branch content is kept equivalent across both platforms.
|
| 30 |
+
|
| 31 |
+
## Compare
|
| 32 |
+
|
| 33 |
+
- [GitHub compare: v0.1...v1.0.0](https://github.com/Musawer1214/pashto-language-resources/compare/v0.1...v1.0.0)
|
docs/search/index.html
CHANGED
|
@@ -41,79 +41,152 @@ permalink: /search/
|
|
| 41 |
</script>
|
| 42 |
<link rel="preconnect" href="https://fonts.googleapis.com">
|
| 43 |
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
| 44 |
-
<link href="https://fonts.googleapis.com/css2?family=
|
| 45 |
<style>
|
| 46 |
:root {
|
| 47 |
-
--bg: #
|
| 48 |
-
--panel: #
|
| 49 |
-
--ink: #
|
| 50 |
-
--muted: #
|
| 51 |
-
--line: #
|
| 52 |
-
--brand: #
|
| 53 |
-
--brand-soft: #
|
| 54 |
-
--accent: #
|
| 55 |
-
--accent-soft: #
|
| 56 |
-
--shadow: 0
|
|
|
|
|
|
|
|
|
|
| 57 |
}
|
| 58 |
|
| 59 |
* { box-sizing: border-box; }
|
| 60 |
|
| 61 |
body {
|
| 62 |
margin: 0;
|
| 63 |
-
font-family: "IBM Plex Sans Arabic", "Segoe UI", sans-serif;
|
| 64 |
color: var(--ink);
|
|
|
|
|
|
|
| 65 |
background:
|
| 66 |
-
radial-gradient(circle at 8%
|
| 67 |
-
radial-gradient(circle at 92%
|
| 68 |
var(--bg);
|
| 69 |
-
min-height: 100vh;
|
| 70 |
}
|
| 71 |
|
| 72 |
-
|
| 73 |
-
|
|
|
|
|
|
|
| 74 |
margin: 0 auto;
|
| 75 |
-
padding:
|
| 76 |
}
|
| 77 |
|
| 78 |
.hero {
|
| 79 |
-
background: linear-gradient(
|
| 80 |
border: 1px solid var(--line);
|
|
|
|
| 81 |
box-shadow: var(--shadow);
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
}
|
| 89 |
|
| 90 |
.eyebrow {
|
| 91 |
-
|
|
|
|
|
|
|
| 92 |
text-transform: uppercase;
|
| 93 |
color: var(--accent);
|
| 94 |
-
font-
|
| 95 |
-
font-weight: 700;
|
| 96 |
-
font-size: 12px;
|
| 97 |
-
margin-bottom: 6px;
|
| 98 |
}
|
| 99 |
|
| 100 |
h1 {
|
| 101 |
-
margin: 0
|
| 102 |
-
font-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
}
|
| 106 |
|
| 107 |
-
.
|
| 108 |
-
margin: 0;
|
| 109 |
color: var(--muted);
|
| 110 |
-
line-height: 1.
|
|
|
|
| 111 |
}
|
| 112 |
|
| 113 |
-
.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
margin-top: 14px;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
display: grid;
|
| 116 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
gap: 10px;
|
| 118 |
}
|
| 119 |
|
|
@@ -124,110 +197,158 @@ permalink: /search/
|
|
| 124 |
}
|
| 125 |
|
| 126 |
.field label {
|
| 127 |
-
font-size:
|
| 128 |
-
|
| 129 |
-
color: var(--muted);
|
| 130 |
-
letter-spacing: 0.04em;
|
| 131 |
text-transform: uppercase;
|
| 132 |
-
font-
|
|
|
|
| 133 |
}
|
| 134 |
|
| 135 |
input, select {
|
| 136 |
width: 100%;
|
| 137 |
border: 1px solid var(--line);
|
| 138 |
-
|
|
|
|
| 139 |
color: var(--ink);
|
| 140 |
-
|
| 141 |
-
padding: 10px 11px;
|
| 142 |
font: inherit;
|
| 143 |
}
|
| 144 |
|
| 145 |
-
input:focus, select:focus {
|
| 146 |
-
outline: 2px solid #
|
| 147 |
-
|
|
|
|
| 148 |
}
|
| 149 |
|
| 150 |
-
.
|
| 151 |
-
margin:
|
| 152 |
display: flex;
|
|
|
|
| 153 |
justify-content: space-between;
|
|
|
|
| 154 |
align-items: center;
|
| 155 |
-
gap: 12px;
|
| 156 |
-
color: var(--muted);
|
| 157 |
-
font-size: 14px;
|
| 158 |
}
|
| 159 |
|
| 160 |
-
.
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 165 |
border-radius: 999px;
|
| 166 |
-
|
|
|
|
|
|
|
|
|
|
| 167 |
}
|
| 168 |
|
| 169 |
-
.
|
| 170 |
-
|
| 171 |
-
|
| 172 |
-
|
| 173 |
-
|
|
|
|
| 174 |
}
|
| 175 |
|
| 176 |
-
.
|
| 177 |
-
|
|
|
|
|
|
|
| 178 |
}
|
| 179 |
|
| 180 |
-
.
|
| 181 |
-
|
| 182 |
-
|
|
|
|
| 183 |
}
|
| 184 |
|
| 185 |
-
.
|
| 186 |
-
margin:
|
|
|
|
|
|
|
|
|
|
| 187 |
}
|
| 188 |
|
| 189 |
-
.
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 193 |
list-style: none;
|
| 194 |
-
padding: 0;
|
| 195 |
margin: 0;
|
|
|
|
|
|
|
|
|
|
| 196 |
}
|
| 197 |
|
|
|
|
|
|
|
|
|
|
| 198 |
.card {
|
| 199 |
border: 1px solid var(--line);
|
| 200 |
-
border-radius:
|
| 201 |
background: var(--panel);
|
| 202 |
box-shadow: var(--shadow);
|
| 203 |
-
padding: 13px
|
| 204 |
display: flex;
|
| 205 |
flex-direction: column;
|
| 206 |
gap: 9px;
|
| 207 |
-
|
| 208 |
-
animation: rise 420ms ease forwards;
|
| 209 |
}
|
| 210 |
|
| 211 |
.chips {
|
| 212 |
display: flex;
|
| 213 |
-
gap: 6px;
|
| 214 |
flex-wrap: wrap;
|
|
|
|
| 215 |
}
|
| 216 |
|
| 217 |
.chip {
|
| 218 |
border-radius: 999px;
|
| 219 |
-
|
| 220 |
-
font-
|
| 221 |
-
|
| 222 |
-
font-family: "Space Grotesk", sans-serif;
|
| 223 |
-
letter-spacing: 0.03em;
|
| 224 |
text-transform: uppercase;
|
|
|
|
| 225 |
border: 1px solid transparent;
|
| 226 |
}
|
| 227 |
|
| 228 |
.chip.category { background: var(--brand-soft); color: var(--brand); border-color: #b7dccc; }
|
| 229 |
-
.chip.source { background: var(--accent-soft); color: #
|
| 230 |
-
.chip.status { background: #
|
| 231 |
|
| 232 |
.title {
|
| 233 |
margin: 0;
|
|
@@ -241,68 +362,115 @@ permalink: /search/
|
|
| 241 |
border-bottom: 1px solid transparent;
|
| 242 |
}
|
| 243 |
|
| 244 |
-
.title a:hover {
|
| 245 |
-
border-bottom-color: currentColor;
|
| 246 |
-
}
|
| 247 |
|
| 248 |
-
.
|
|
|
|
| 249 |
color: var(--muted);
|
|
|
|
| 250 |
font-size: 13px;
|
| 251 |
-
line-height: 1.45;
|
| 252 |
-
margin: 0;
|
| 253 |
}
|
| 254 |
|
| 255 |
-
.
|
| 256 |
margin-top: auto;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 257 |
font-size: 12px;
|
| 258 |
color: var(--muted);
|
|
|
|
| 259 |
}
|
| 260 |
|
| 261 |
.empty {
|
| 262 |
border: 1px dashed #b9c4bd;
|
| 263 |
-
border-radius:
|
| 264 |
-
padding:
|
| 265 |
background: #fcfcfa;
|
| 266 |
color: var(--muted);
|
| 267 |
text-align: center;
|
| 268 |
}
|
| 269 |
|
| 270 |
-
|
| 271 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 272 |
to { opacity: 1; transform: translateY(0); }
|
| 273 |
}
|
| 274 |
|
| 275 |
-
@media (max-width:
|
| 276 |
-
.controls {
|
| 277 |
-
|
| 278 |
-
|
| 279 |
|
| 280 |
-
|
| 281 |
-
|
| 282 |
-
}
|
|
|
|
|
|
|
|
|
|
| 283 |
}
|
| 284 |
|
| 285 |
-
@media (max-width:
|
| 286 |
-
h1 { font-size: 28px; }
|
| 287 |
.controls { grid-template-columns: 1fr; }
|
| 288 |
-
.controls .field
|
| 289 |
-
|
| 290 |
}
|
| 291 |
</style>
|
| 292 |
</head>
|
| 293 |
<body>
|
| 294 |
-
<main class="
|
| 295 |
-
<
|
| 296 |
-
<div class="
|
| 297 |
-
|
| 298 |
-
|
| 299 |
-
|
| 300 |
-
|
| 301 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 302 |
<div class="controls">
|
| 303 |
-
<div class="field">
|
| 304 |
<label for="q">Search</label>
|
| 305 |
-
<input id="q" type="search" placeholder="Try:
|
| 306 |
</div>
|
| 307 |
<div class="field">
|
| 308 |
<label for="category">Category</label>
|
|
@@ -320,22 +488,46 @@ permalink: /search/
|
|
| 320 |
<label for="status">Status</label>
|
| 321 |
<select id="status"></select>
|
| 322 |
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 323 |
</div>
|
| 324 |
</section>
|
| 325 |
|
| 326 |
-
<div class="summary">
|
| 327 |
<span id="countText">Loading resources...</span>
|
| 328 |
<span class="badge" id="generatedAt">Catalog timestamp: -</span>
|
| 329 |
</div>
|
| 330 |
|
| 331 |
-
<section class="crawl" aria-label="
|
| 332 |
-
|
| 333 |
-
|
| 334 |
-
</p>
|
| 335 |
-
<p>
|
| 336 |
-
Project overview: <a href="https://github.com/Musawer1214/pashto-language-resources">Musawer1214/pashto-language-resources</a>
|
| 337 |
-
</p>
|
| 338 |
-
<ul class="crawl-links">
|
| 339 |
<li><a href="https://github.com/Musawer1214/pashto-language-resources/blob/main/resources/datasets/README.md">Pashto datasets</a></li>
|
| 340 |
<li><a href="https://github.com/Musawer1214/pashto-language-resources/blob/main/resources/models/README.md">Pashto models</a></li>
|
| 341 |
<li><a href="https://github.com/Musawer1214/pashto-language-resources/blob/main/resources/benchmarks/README.md">Pashto benchmarks</a></li>
|
|
@@ -345,16 +537,17 @@ permalink: /search/
|
|
| 345 |
</section>
|
| 346 |
|
| 347 |
<noscript>
|
| 348 |
-
JavaScript is needed for filtering
|
| 349 |
</noscript>
|
| 350 |
|
| 351 |
-
<ul id="results" class="grid"></ul>
|
| 352 |
</main>
|
| 353 |
|
| 354 |
<script>
|
| 355 |
const state = {
|
| 356 |
all: [],
|
| 357 |
-
filtered: []
|
|
|
|
| 358 |
};
|
| 359 |
|
| 360 |
const els = {
|
|
@@ -363,11 +556,29 @@ permalink: /search/
|
|
| 363 |
source: document.getElementById("source"),
|
| 364 |
task: document.getElementById("task"),
|
| 365 |
status: document.getElementById("status"),
|
|
|
|
| 366 |
results: document.getElementById("results"),
|
| 367 |
countText: document.getElementById("countText"),
|
| 368 |
-
generatedAt: document.getElementById("generatedAt")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 369 |
};
|
| 370 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 371 |
function uniqSorted(values) {
|
| 372 |
return [...new Set(values.filter(Boolean))].sort((a, b) => a.localeCompare(b));
|
| 373 |
}
|
|
@@ -379,13 +590,30 @@ permalink: /search/
|
|
| 379 |
allOption.textContent = allLabel;
|
| 380 |
select.appendChild(allOption);
|
| 381 |
for (const opt of options) {
|
| 382 |
-
const
|
| 383 |
-
|
| 384 |
-
|
| 385 |
-
select.appendChild(
|
| 386 |
}
|
| 387 |
}
|
| 388 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 389 |
function matchesQuery(resource, query) {
|
| 390 |
if (!query) return true;
|
| 391 |
const hay = [
|
|
@@ -403,6 +631,26 @@ permalink: /search/
|
|
| 403 |
return hay.includes(query);
|
| 404 |
}
|
| 405 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 406 |
function applyFilters() {
|
| 407 |
const q = els.q.value.trim().toLowerCase();
|
| 408 |
const category = els.category.value;
|
|
@@ -410,20 +658,21 @@ permalink: /search/
|
|
| 410 |
const task = els.task.value;
|
| 411 |
const status = els.status.value;
|
| 412 |
|
| 413 |
-
state.filtered = state.all.filter((resource) => {
|
| 414 |
if (!matchesQuery(resource, q)) return false;
|
| 415 |
if (category && resource.category !== category) return false;
|
| 416 |
if (source && resource.source !== source) return false;
|
| 417 |
if (status && resource.status !== status) return false;
|
| 418 |
if (task && !(resource.tasks || []).includes(task)) return false;
|
| 419 |
return true;
|
| 420 |
-
});
|
| 421 |
|
| 422 |
renderResults();
|
|
|
|
| 423 |
}
|
| 424 |
|
| 425 |
function chip(label, cls) {
|
| 426 |
-
return `<span class="chip ${cls}">${label}</span>`;
|
| 427 |
}
|
| 428 |
|
| 429 |
function renderResults() {
|
|
@@ -431,26 +680,104 @@ permalink: /search/
|
|
| 431 |
els.countText.textContent = `${items.length} result${items.length === 1 ? "" : "s"} of ${state.all.length}`;
|
| 432 |
|
| 433 |
if (!items.length) {
|
| 434 |
-
els.results.innerHTML =
|
| 435 |
return;
|
| 436 |
}
|
| 437 |
|
| 438 |
-
els.results.innerHTML = items.map((resource
|
| 439 |
-
|
| 440 |
-
|
| 441 |
-
|
| 442 |
-
|
| 443 |
-
|
| 444 |
-
|
| 445 |
-
|
| 446 |
-
|
| 447 |
-
|
| 448 |
-
<
|
| 449 |
-
|
| 450 |
-
|
| 451 |
-
|
| 452 |
-
|
| 453 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 454 |
}
|
| 455 |
|
| 456 |
async function load() {
|
|
@@ -458,37 +785,43 @@ permalink: /search/
|
|
| 458 |
const res = await fetch("./resources.json", { cache: "no-store" });
|
| 459 |
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
| 460 |
const payload = await res.json();
|
|
|
|
| 461 |
state.all = payload.resources || [];
|
| 462 |
-
state.filtered = [...state.all];
|
| 463 |
|
| 464 |
fillSelect(els.category, uniqSorted(state.all.map((r) => r.category)), "All categories");
|
| 465 |
fillSelect(els.source, uniqSorted(state.all.map((r) => r.source)), "All sources");
|
| 466 |
fillSelect(els.status, uniqSorted(state.all.map((r) => r.status)), "All statuses");
|
| 467 |
-
fillSelect(
|
| 468 |
-
|
| 469 |
-
|
| 470 |
-
"All tasks"
|
| 471 |
-
);
|
| 472 |
|
| 473 |
const generated = payload.generated_on ? new Date(payload.generated_on) : null;
|
| 474 |
els.generatedAt.textContent = generated && !Number.isNaN(generated.getTime())
|
| 475 |
? `Catalog timestamp: ${generated.toISOString()}`
|
| 476 |
: "Catalog timestamp: unknown";
|
| 477 |
|
|
|
|
| 478 |
applyFilters();
|
| 479 |
} catch (err) {
|
| 480 |
els.countText.textContent = "Failed to load resources";
|
| 481 |
-
els.results.innerHTML = `<li class="empty">Could not load search data. ${String(err)}</li>`;
|
| 482 |
}
|
| 483 |
}
|
| 484 |
|
| 485 |
-
[els.q, els.category, els.source, els.task, els.status].forEach((el) => {
|
| 486 |
el.addEventListener("input", applyFilters);
|
| 487 |
el.addEventListener("change", applyFilters);
|
| 488 |
});
|
| 489 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 490 |
load();
|
| 491 |
</script>
|
| 492 |
</body>
|
| 493 |
</html>
|
| 494 |
-
|
|
|
|
| 41 |
</script>
|
| 42 |
<link rel="preconnect" href="https://fonts.googleapis.com">
|
| 43 |
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
| 44 |
+
<link href="https://fonts.googleapis.com/css2?family=Manrope:wght@400;600;700;800&family=Noto+Naskh+Arabic:wght@500;700&display=swap" rel="stylesheet">
|
| 45 |
<style>
|
| 46 |
:root {
|
| 47 |
+
--bg: #f3f2ea;
|
| 48 |
+
--panel: #fffdf7;
|
| 49 |
+
--ink: #1d2628;
|
| 50 |
+
--muted: #55656a;
|
| 51 |
+
--line: #d5ddd8;
|
| 52 |
+
--brand: #0f6f61;
|
| 53 |
+
--brand-soft: #dcf2ee;
|
| 54 |
+
--accent: #b9621f;
|
| 55 |
+
--accent-soft: #f8e6d7;
|
| 56 |
+
--shadow: 0 14px 36px rgba(16, 29, 35, 0.12);
|
| 57 |
+
--radius-lg: 18px;
|
| 58 |
+
--radius-md: 12px;
|
| 59 |
+
--radius-sm: 9px;
|
| 60 |
}
|
| 61 |
|
| 62 |
* { box-sizing: border-box; }
|
| 63 |
|
| 64 |
body {
|
| 65 |
margin: 0;
|
|
|
|
| 66 |
color: var(--ink);
|
| 67 |
+
font-family: "Manrope", "Segoe UI", sans-serif;
|
| 68 |
+
min-height: 100vh;
|
| 69 |
background:
|
| 70 |
+
radial-gradient(circle at 8% 8%, #ffe0bf 0, rgba(255, 224, 191, 0) 30%),
|
| 71 |
+
radial-gradient(circle at 92% 7%, #d2ece4 0, rgba(210, 236, 228, 0) 35%),
|
| 72 |
var(--bg);
|
|
|
|
| 73 |
}
|
| 74 |
|
| 75 |
+
a { color: var(--brand); }
|
| 76 |
+
|
| 77 |
+
.container {
|
| 78 |
+
max-width: 1180px;
|
| 79 |
margin: 0 auto;
|
| 80 |
+
padding: 22px 18px 42px;
|
| 81 |
}
|
| 82 |
|
| 83 |
.hero {
|
| 84 |
+
background: linear-gradient(130deg, #fffef9, #f5faf8);
|
| 85 |
border: 1px solid var(--line);
|
| 86 |
+
border-radius: var(--radius-lg);
|
| 87 |
box-shadow: var(--shadow);
|
| 88 |
+
padding: 20px;
|
| 89 |
+
margin-bottom: 14px;
|
| 90 |
+
}
|
| 91 |
+
|
| 92 |
+
.hero-top {
|
| 93 |
+
display: flex;
|
| 94 |
+
justify-content: space-between;
|
| 95 |
+
align-items: flex-start;
|
| 96 |
+
gap: 14px;
|
| 97 |
+
flex-wrap: wrap;
|
| 98 |
}
|
| 99 |
|
| 100 |
.eyebrow {
|
| 101 |
+
margin: 0 0 8px;
|
| 102 |
+
font-size: 12px;
|
| 103 |
+
letter-spacing: 0.08em;
|
| 104 |
text-transform: uppercase;
|
| 105 |
color: var(--accent);
|
| 106 |
+
font-weight: 800;
|
|
|
|
|
|
|
|
|
|
| 107 |
}
|
| 108 |
|
| 109 |
h1 {
|
| 110 |
+
margin: 0;
|
| 111 |
+
font-size: 34px;
|
| 112 |
+
line-height: 1.08;
|
| 113 |
+
letter-spacing: -0.02em;
|
| 114 |
}
|
| 115 |
|
| 116 |
+
.subtitle {
|
| 117 |
+
margin: 10px 0 0;
|
| 118 |
color: var(--muted);
|
| 119 |
+
line-height: 1.55;
|
| 120 |
+
max-width: 760px;
|
| 121 |
}
|
| 122 |
|
| 123 |
+
.stat-row {
|
| 124 |
+
display: grid;
|
| 125 |
+
grid-template-columns: repeat(3, minmax(120px, 1fr));
|
| 126 |
+
gap: 8px;
|
| 127 |
+
width: min(380px, 100%);
|
| 128 |
+
}
|
| 129 |
+
|
| 130 |
+
.stat {
|
| 131 |
+
border: 1px solid var(--line);
|
| 132 |
+
border-radius: var(--radius-md);
|
| 133 |
+
background: var(--panel);
|
| 134 |
+
padding: 10px;
|
| 135 |
+
text-align: center;
|
| 136 |
+
}
|
| 137 |
+
|
| 138 |
+
.stat strong {
|
| 139 |
+
display: block;
|
| 140 |
+
font-size: 20px;
|
| 141 |
+
line-height: 1;
|
| 142 |
+
color: var(--brand);
|
| 143 |
+
}
|
| 144 |
+
|
| 145 |
+
.stat span {
|
| 146 |
+
display: block;
|
| 147 |
+
margin-top: 4px;
|
| 148 |
+
color: var(--muted);
|
| 149 |
+
font-size: 12px;
|
| 150 |
+
font-weight: 700;
|
| 151 |
+
text-transform: uppercase;
|
| 152 |
+
letter-spacing: 0.04em;
|
| 153 |
+
}
|
| 154 |
+
|
| 155 |
+
.quick-links {
|
| 156 |
margin-top: 14px;
|
| 157 |
+
display: flex;
|
| 158 |
+
flex-wrap: wrap;
|
| 159 |
+
gap: 8px;
|
| 160 |
+
}
|
| 161 |
+
|
| 162 |
+
.pill-link {
|
| 163 |
+
border: 1px solid #b8cec6;
|
| 164 |
+
border-radius: 999px;
|
| 165 |
+
background: #f8fcfa;
|
| 166 |
+
color: var(--brand);
|
| 167 |
+
text-decoration: none;
|
| 168 |
+
font-size: 13px;
|
| 169 |
+
font-weight: 700;
|
| 170 |
+
padding: 7px 12px;
|
| 171 |
+
}
|
| 172 |
+
|
| 173 |
+
.toolbar {
|
| 174 |
+
margin-bottom: 12px;
|
| 175 |
display: grid;
|
| 176 |
+
gap: 12px;
|
| 177 |
+
}
|
| 178 |
+
|
| 179 |
+
.panel {
|
| 180 |
+
border: 1px solid var(--line);
|
| 181 |
+
border-radius: var(--radius-lg);
|
| 182 |
+
background: var(--panel);
|
| 183 |
+
box-shadow: var(--shadow);
|
| 184 |
+
padding: 16px;
|
| 185 |
+
}
|
| 186 |
+
|
| 187 |
+
.controls {
|
| 188 |
+
display: grid;
|
| 189 |
+
grid-template-columns: 2fr repeat(5, minmax(140px, 1fr));
|
| 190 |
gap: 10px;
|
| 191 |
}
|
| 192 |
|
|
|
|
| 197 |
}
|
| 198 |
|
| 199 |
.field label {
|
| 200 |
+
font-size: 11px;
|
| 201 |
+
letter-spacing: 0.05em;
|
|
|
|
|
|
|
| 202 |
text-transform: uppercase;
|
| 203 |
+
font-weight: 800;
|
| 204 |
+
color: var(--muted);
|
| 205 |
}
|
| 206 |
|
| 207 |
input, select {
|
| 208 |
width: 100%;
|
| 209 |
border: 1px solid var(--line);
|
| 210 |
+
border-radius: var(--radius-sm);
|
| 211 |
+
background: #fff;
|
| 212 |
color: var(--ink);
|
| 213 |
+
padding: 10px;
|
|
|
|
| 214 |
font: inherit;
|
| 215 |
}
|
| 216 |
|
| 217 |
+
input:focus, select:focus, button:focus {
|
| 218 |
+
outline: 2px solid #7bc7b8;
|
| 219 |
+
outline-offset: 1px;
|
| 220 |
+
border-color: #7bc7b8;
|
| 221 |
}
|
| 222 |
|
| 223 |
+
.action-row {
|
| 224 |
+
margin-top: 10px;
|
| 225 |
display: flex;
|
| 226 |
+
flex-wrap: wrap;
|
| 227 |
justify-content: space-between;
|
| 228 |
+
gap: 10px;
|
| 229 |
align-items: center;
|
|
|
|
|
|
|
|
|
|
| 230 |
}
|
| 231 |
|
| 232 |
+
.group {
|
| 233 |
+
display: flex;
|
| 234 |
+
flex-wrap: wrap;
|
| 235 |
+
gap: 7px;
|
| 236 |
+
align-items: center;
|
| 237 |
+
}
|
| 238 |
+
|
| 239 |
+
.btn {
|
| 240 |
+
border: 1px solid var(--line);
|
| 241 |
+
background: #fff;
|
| 242 |
+
color: var(--ink);
|
| 243 |
border-radius: 999px;
|
| 244 |
+
padding: 7px 12px;
|
| 245 |
+
font-size: 13px;
|
| 246 |
+
font-weight: 700;
|
| 247 |
+
cursor: pointer;
|
| 248 |
}
|
| 249 |
|
| 250 |
+
.btn:hover { border-color: #98b9ae; }
|
| 251 |
+
|
| 252 |
+
.btn.brand {
|
| 253 |
+
background: var(--brand);
|
| 254 |
+
color: #fff;
|
| 255 |
+
border-color: var(--brand);
|
| 256 |
}
|
| 257 |
|
| 258 |
+
.btn.light {
|
| 259 |
+
background: #f6faf8;
|
| 260 |
+
color: var(--brand);
|
| 261 |
+
border-color: #b9d8cf;
|
| 262 |
}
|
| 263 |
|
| 264 |
+
.btn.active {
|
| 265 |
+
background: var(--accent-soft);
|
| 266 |
+
border-color: #efc08f;
|
| 267 |
+
color: #915117;
|
| 268 |
}
|
| 269 |
|
| 270 |
+
.intent-row {
|
| 271 |
+
margin-top: 10px;
|
| 272 |
+
display: flex;
|
| 273 |
+
flex-wrap: wrap;
|
| 274 |
+
gap: 7px;
|
| 275 |
}
|
| 276 |
|
| 277 |
+
.intent {
|
| 278 |
+
border: 1px solid #cfdad4;
|
| 279 |
+
background: #fbfdfc;
|
| 280 |
+
border-radius: 999px;
|
| 281 |
+
padding: 6px 11px;
|
| 282 |
+
font-size: 13px;
|
| 283 |
+
font-weight: 700;
|
| 284 |
+
cursor: pointer;
|
| 285 |
+
color: var(--muted);
|
| 286 |
+
}
|
| 287 |
+
|
| 288 |
+
.intent:hover { border-color: #9cb8af; color: var(--ink); }
|
| 289 |
+
|
| 290 |
+
.summary {
|
| 291 |
+
margin: 0 2px 12px;
|
| 292 |
+
display: flex;
|
| 293 |
+
justify-content: space-between;
|
| 294 |
+
align-items: center;
|
| 295 |
+
gap: 10px;
|
| 296 |
+
color: var(--muted);
|
| 297 |
+
font-size: 14px;
|
| 298 |
+
}
|
| 299 |
+
|
| 300 |
+
.badge {
|
| 301 |
+
background: var(--brand-soft);
|
| 302 |
+
color: var(--brand);
|
| 303 |
+
border: 1px solid #b7dccc;
|
| 304 |
+
padding: 4px 9px;
|
| 305 |
+
border-radius: 999px;
|
| 306 |
+
font-weight: 700;
|
| 307 |
+
font-size: 12px;
|
| 308 |
+
}
|
| 309 |
+
|
| 310 |
+
.results {
|
| 311 |
list-style: none;
|
|
|
|
| 312 |
margin: 0;
|
| 313 |
+
padding: 0;
|
| 314 |
+
display: grid;
|
| 315 |
+
gap: 12px;
|
| 316 |
}
|
| 317 |
|
| 318 |
+
.results.grid { grid-template-columns: repeat(auto-fill, minmax(270px, 1fr)); }
|
| 319 |
+
.results.list { grid-template-columns: 1fr; }
|
| 320 |
+
|
| 321 |
.card {
|
| 322 |
border: 1px solid var(--line);
|
| 323 |
+
border-radius: var(--radius-md);
|
| 324 |
background: var(--panel);
|
| 325 |
box-shadow: var(--shadow);
|
| 326 |
+
padding: 13px;
|
| 327 |
display: flex;
|
| 328 |
flex-direction: column;
|
| 329 |
gap: 9px;
|
| 330 |
+
animation: cardIn 360ms ease;
|
|
|
|
| 331 |
}
|
| 332 |
|
| 333 |
.chips {
|
| 334 |
display: flex;
|
|
|
|
| 335 |
flex-wrap: wrap;
|
| 336 |
+
gap: 6px;
|
| 337 |
}
|
| 338 |
|
| 339 |
.chip {
|
| 340 |
border-radius: 999px;
|
| 341 |
+
font-size: 10px;
|
| 342 |
+
font-weight: 800;
|
| 343 |
+
letter-spacing: 0.04em;
|
|
|
|
|
|
|
| 344 |
text-transform: uppercase;
|
| 345 |
+
padding: 3px 8px;
|
| 346 |
border: 1px solid transparent;
|
| 347 |
}
|
| 348 |
|
| 349 |
.chip.category { background: var(--brand-soft); color: var(--brand); border-color: #b7dccc; }
|
| 350 |
+
.chip.source { background: var(--accent-soft); color: #915117; border-color: #efc89f; }
|
| 351 |
+
.chip.status { background: #edf2ff; color: #3f4f86; border-color: #d0dbf6; }
|
| 352 |
|
| 353 |
.title {
|
| 354 |
margin: 0;
|
|
|
|
| 362 |
border-bottom: 1px solid transparent;
|
| 363 |
}
|
| 364 |
|
| 365 |
+
.title a:hover { border-bottom-color: currentColor; }
|
|
|
|
|
|
|
| 366 |
|
| 367 |
+
.text {
|
| 368 |
+
margin: 0;
|
| 369 |
color: var(--muted);
|
| 370 |
+
line-height: 1.48;
|
| 371 |
font-size: 13px;
|
|
|
|
|
|
|
| 372 |
}
|
| 373 |
|
| 374 |
+
.meta-links {
|
| 375 |
margin-top: auto;
|
| 376 |
+
display: flex;
|
| 377 |
+
flex-wrap: wrap;
|
| 378 |
+
gap: 8px;
|
| 379 |
+
align-items: center;
|
| 380 |
+
}
|
| 381 |
+
|
| 382 |
+
.mini-link {
|
| 383 |
+
font-size: 12px;
|
| 384 |
+
font-weight: 700;
|
| 385 |
+
color: var(--brand);
|
| 386 |
+
text-decoration: none;
|
| 387 |
+
}
|
| 388 |
+
|
| 389 |
+
.tasks {
|
| 390 |
font-size: 12px;
|
| 391 |
color: var(--muted);
|
| 392 |
+
margin: 0;
|
| 393 |
}
|
| 394 |
|
| 395 |
.empty {
|
| 396 |
border: 1px dashed #b9c4bd;
|
| 397 |
+
border-radius: var(--radius-md);
|
| 398 |
+
padding: 26px;
|
| 399 |
background: #fcfcfa;
|
| 400 |
color: var(--muted);
|
| 401 |
text-align: center;
|
| 402 |
}
|
| 403 |
|
| 404 |
+
.crawl {
|
| 405 |
+
margin: 0 2px 12px;
|
| 406 |
+
color: var(--muted);
|
| 407 |
+
line-height: 1.5;
|
| 408 |
+
font-size: 14px;
|
| 409 |
+
}
|
| 410 |
+
|
| 411 |
+
.crawl ul {
|
| 412 |
+
margin: 8px 0 0;
|
| 413 |
+
padding-left: 18px;
|
| 414 |
+
}
|
| 415 |
+
|
| 416 |
+
@keyframes cardIn {
|
| 417 |
+
from { opacity: 0; transform: translateY(5px); }
|
| 418 |
to { opacity: 1; transform: translateY(0); }
|
| 419 |
}
|
| 420 |
|
| 421 |
+
@media (max-width: 1020px) {
|
| 422 |
+
.controls { grid-template-columns: repeat(3, minmax(140px, 1fr)); }
|
| 423 |
+
.controls .field.search { grid-column: span 3; }
|
| 424 |
+
}
|
| 425 |
|
| 426 |
+
@media (max-width: 720px) {
|
| 427 |
+
h1 { font-size: 30px; }
|
| 428 |
+
.controls { grid-template-columns: 1fr 1fr; }
|
| 429 |
+
.controls .field.search { grid-column: span 2; }
|
| 430 |
+
.summary { flex-direction: column; align-items: flex-start; }
|
| 431 |
+
.stat-row { width: 100%; }
|
| 432 |
}
|
| 433 |
|
| 434 |
+
@media (max-width: 520px) {
|
|
|
|
| 435 |
.controls { grid-template-columns: 1fr; }
|
| 436 |
+
.controls .field.search { grid-column: span 1; }
|
| 437 |
+
h1 { font-size: 28px; }
|
| 438 |
}
|
| 439 |
</style>
|
| 440 |
</head>
|
| 441 |
<body>
|
| 442 |
+
<main class="container">
|
| 443 |
+
<header class="hero">
|
| 444 |
+
<div class="hero-top">
|
| 445 |
+
<div>
|
| 446 |
+
<p class="eyebrow">Pukhto / Pashto Resources</p>
|
| 447 |
+
<h1>Pashto Technology Resource Search</h1>
|
| 448 |
+
<p class="subtitle">
|
| 449 |
+
Filter verified and candidate resources for ASR, TTS, NLP, translation, tools, and benchmark work.
|
| 450 |
+
Share search states with URL parameters and jump quickly to high-intent pages.
|
| 451 |
+
</p>
|
| 452 |
+
</div>
|
| 453 |
+
<div class="stat-row" aria-label="Catalog metrics">
|
| 454 |
+
<div class="stat"><strong id="statTotal">-</strong><span>Total</span></div>
|
| 455 |
+
<div class="stat"><strong id="statVerified">-</strong><span>Verified</span></div>
|
| 456 |
+
<div class="stat"><strong id="statTasks">-</strong><span>Task Tags</span></div>
|
| 457 |
+
</div>
|
| 458 |
+
</div>
|
| 459 |
+
<nav class="quick-links" aria-label="Quick links">
|
| 460 |
+
<a class="pill-link" href="../">Docs Home</a>
|
| 461 |
+
<a class="pill-link" href="../pashto_datasets.md">Datasets Page</a>
|
| 462 |
+
<a class="pill-link" href="../pashto_asr.md">ASR Page</a>
|
| 463 |
+
<a class="pill-link" href="../pashto_tts.md">TTS Page</a>
|
| 464 |
+
<a class="pill-link" href="https://github.com/Musawer1214/pashto-language-resources">GitHub</a>
|
| 465 |
+
<a class="pill-link" href="https://huggingface.co/Musawer14/pashto-language-resources">Hugging Face</a>
|
| 466 |
+
</nav>
|
| 467 |
+
</header>
|
| 468 |
+
|
| 469 |
+
<section class="toolbar panel" aria-label="Search controls">
|
| 470 |
<div class="controls">
|
| 471 |
+
<div class="field search">
|
| 472 |
<label for="q">Search</label>
|
| 473 |
+
<input id="q" type="search" placeholder="Try: asr, pbt_arab, translation, speech, benchmark" autocomplete="off">
|
| 474 |
</div>
|
| 475 |
<div class="field">
|
| 476 |
<label for="category">Category</label>
|
|
|
|
| 488 |
<label for="status">Status</label>
|
| 489 |
<select id="status"></select>
|
| 490 |
</div>
|
| 491 |
+
<div class="field">
|
| 492 |
+
<label for="sort">Sort</label>
|
| 493 |
+
<select id="sort">
|
| 494 |
+
<option value="relevance">Relevance</option>
|
| 495 |
+
<option value="title_asc">Title (A-Z)</option>
|
| 496 |
+
<option value="title_desc">Title (Z-A)</option>
|
| 497 |
+
<option value="source_asc">Source (A-Z)</option>
|
| 498 |
+
</select>
|
| 499 |
+
</div>
|
| 500 |
+
</div>
|
| 501 |
+
|
| 502 |
+
<div class="action-row">
|
| 503 |
+
<div class="group" role="group" aria-label="Result view mode">
|
| 504 |
+
<button type="button" class="btn active" id="viewGrid">Grid view</button>
|
| 505 |
+
<button type="button" class="btn" id="viewList">List view</button>
|
| 506 |
+
</div>
|
| 507 |
+
<div class="group">
|
| 508 |
+
<button type="button" class="btn light" id="clearFilters">Clear filters</button>
|
| 509 |
+
<button type="button" class="btn brand" id="copyLink">Copy search link</button>
|
| 510 |
+
</div>
|
| 511 |
+
</div>
|
| 512 |
+
|
| 513 |
+
<div class="intent-row" aria-label="Quick intent filters">
|
| 514 |
+
<button type="button" class="intent" data-intent="datasets">Datasets</button>
|
| 515 |
+
<button type="button" class="intent" data-intent="asr">ASR</button>
|
| 516 |
+
<button type="button" class="intent" data-intent="tts">TTS</button>
|
| 517 |
+
<button type="button" class="intent" data-intent="nlp">NLP</button>
|
| 518 |
+
<button type="button" class="intent" data-intent="mt">Translation</button>
|
| 519 |
+
<button type="button" class="intent" data-intent="verified">Verified only</button>
|
| 520 |
</div>
|
| 521 |
</section>
|
| 522 |
|
| 523 |
+
<div class="summary" aria-live="polite">
|
| 524 |
<span id="countText">Loading resources...</span>
|
| 525 |
<span class="badge" id="generatedAt">Catalog timestamp: -</span>
|
| 526 |
</div>
|
| 527 |
|
| 528 |
+
<section class="crawl" aria-label="Resource categories and crawlable links">
|
| 529 |
+
Browse Pashto resource categories directly:
|
| 530 |
+
<ul>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 531 |
<li><a href="https://github.com/Musawer1214/pashto-language-resources/blob/main/resources/datasets/README.md">Pashto datasets</a></li>
|
| 532 |
<li><a href="https://github.com/Musawer1214/pashto-language-resources/blob/main/resources/models/README.md">Pashto models</a></li>
|
| 533 |
<li><a href="https://github.com/Musawer1214/pashto-language-resources/blob/main/resources/benchmarks/README.md">Pashto benchmarks</a></li>
|
|
|
|
| 537 |
</section>
|
| 538 |
|
| 539 |
<noscript>
|
| 540 |
+
JavaScript is needed for filtering. Category links above remain fully accessible.
|
| 541 |
</noscript>
|
| 542 |
|
| 543 |
+
<ul id="results" class="results grid"></ul>
|
| 544 |
</main>
|
| 545 |
|
| 546 |
<script>
|
| 547 |
const state = {
|
| 548 |
all: [],
|
| 549 |
+
filtered: [],
|
| 550 |
+
view: "grid"
|
| 551 |
};
|
| 552 |
|
| 553 |
const els = {
|
|
|
|
| 556 |
source: document.getElementById("source"),
|
| 557 |
task: document.getElementById("task"),
|
| 558 |
status: document.getElementById("status"),
|
| 559 |
+
sort: document.getElementById("sort"),
|
| 560 |
results: document.getElementById("results"),
|
| 561 |
countText: document.getElementById("countText"),
|
| 562 |
+
generatedAt: document.getElementById("generatedAt"),
|
| 563 |
+
statTotal: document.getElementById("statTotal"),
|
| 564 |
+
statVerified: document.getElementById("statVerified"),
|
| 565 |
+
statTasks: document.getElementById("statTasks"),
|
| 566 |
+
viewGrid: document.getElementById("viewGrid"),
|
| 567 |
+
viewList: document.getElementById("viewList"),
|
| 568 |
+
clearFilters: document.getElementById("clearFilters"),
|
| 569 |
+
copyLink: document.getElementById("copyLink"),
|
| 570 |
+
intents: [...document.querySelectorAll(".intent")]
|
| 571 |
};
|
| 572 |
|
| 573 |
+
function esc(value) {
|
| 574 |
+
return String(value || "")
|
| 575 |
+
.replace(/&/g, "&")
|
| 576 |
+
.replace(/</g, "<")
|
| 577 |
+
.replace(/>/g, ">")
|
| 578 |
+
.replace(/"/g, """)
|
| 579 |
+
.replace(/'/g, "'");
|
| 580 |
+
}
|
| 581 |
+
|
| 582 |
function uniqSorted(values) {
|
| 583 |
return [...new Set(values.filter(Boolean))].sort((a, b) => a.localeCompare(b));
|
| 584 |
}
|
|
|
|
| 590 |
allOption.textContent = allLabel;
|
| 591 |
select.appendChild(allOption);
|
| 592 |
for (const opt of options) {
|
| 593 |
+
const entry = document.createElement("option");
|
| 594 |
+
entry.value = opt;
|
| 595 |
+
entry.textContent = opt;
|
| 596 |
+
select.appendChild(entry);
|
| 597 |
}
|
| 598 |
}
|
| 599 |
|
| 600 |
+
function updateMetrics() {
|
| 601 |
+
const verified = state.all.filter((r) => r.status === "verified").length;
|
| 602 |
+
const tasks = uniqSorted(state.all.flatMap((r) => r.tasks || [])).length;
|
| 603 |
+
els.statTotal.textContent = String(state.all.length);
|
| 604 |
+
els.statVerified.textContent = String(verified);
|
| 605 |
+
els.statTasks.textContent = String(tasks);
|
| 606 |
+
}
|
| 607 |
+
|
| 608 |
+
function setView(view) {
|
| 609 |
+
state.view = view === "list" ? "list" : "grid";
|
| 610 |
+
els.results.classList.toggle("grid", state.view === "grid");
|
| 611 |
+
els.results.classList.toggle("list", state.view === "list");
|
| 612 |
+
els.viewGrid.classList.toggle("active", state.view === "grid");
|
| 613 |
+
els.viewList.classList.toggle("active", state.view === "list");
|
| 614 |
+
syncUrl();
|
| 615 |
+
}
|
| 616 |
+
|
| 617 |
function matchesQuery(resource, query) {
|
| 618 |
if (!query) return true;
|
| 619 |
const hay = [
|
|
|
|
| 631 |
return hay.includes(query);
|
| 632 |
}
|
| 633 |
|
| 634 |
+
function sortItems(items) {
|
| 635 |
+
const mode = els.sort.value;
|
| 636 |
+
const sorted = [...items];
|
| 637 |
+
if (mode === "title_asc") {
|
| 638 |
+
sorted.sort((a, b) => (a.title || "").localeCompare(b.title || ""));
|
| 639 |
+
} else if (mode === "title_desc") {
|
| 640 |
+
sorted.sort((a, b) => (b.title || "").localeCompare(a.title || ""));
|
| 641 |
+
} else if (mode === "source_asc") {
|
| 642 |
+
sorted.sort((a, b) => (a.source || "").localeCompare(b.source || "") || (a.title || "").localeCompare(b.title || ""));
|
| 643 |
+
} else {
|
| 644 |
+
sorted.sort((a, b) => {
|
| 645 |
+
const av = a.status === "verified" ? 0 : 1;
|
| 646 |
+
const bv = b.status === "verified" ? 0 : 1;
|
| 647 |
+
if (av !== bv) return av - bv;
|
| 648 |
+
return (a.title || "").localeCompare(b.title || "");
|
| 649 |
+
});
|
| 650 |
+
}
|
| 651 |
+
return sorted;
|
| 652 |
+
}
|
| 653 |
+
|
| 654 |
function applyFilters() {
|
| 655 |
const q = els.q.value.trim().toLowerCase();
|
| 656 |
const category = els.category.value;
|
|
|
|
| 658 |
const task = els.task.value;
|
| 659 |
const status = els.status.value;
|
| 660 |
|
| 661 |
+
state.filtered = sortItems(state.all.filter((resource) => {
|
| 662 |
if (!matchesQuery(resource, q)) return false;
|
| 663 |
if (category && resource.category !== category) return false;
|
| 664 |
if (source && resource.source !== source) return false;
|
| 665 |
if (status && resource.status !== status) return false;
|
| 666 |
if (task && !(resource.tasks || []).includes(task)) return false;
|
| 667 |
return true;
|
| 668 |
+
}));
|
| 669 |
|
| 670 |
renderResults();
|
| 671 |
+
syncUrl();
|
| 672 |
}
|
| 673 |
|
| 674 |
function chip(label, cls) {
|
| 675 |
+
return `<span class="chip ${cls}">${esc(label)}</span>`;
|
| 676 |
}
|
| 677 |
|
| 678 |
function renderResults() {
|
|
|
|
| 680 |
els.countText.textContent = `${items.length} result${items.length === 1 ? "" : "s"} of ${state.all.length}`;
|
| 681 |
|
| 682 |
if (!items.length) {
|
| 683 |
+
els.results.innerHTML = '<li class="empty">No matches. Try broadening filters or clearing one filter at a time.</li>';
|
| 684 |
return;
|
| 685 |
}
|
| 686 |
|
| 687 |
+
els.results.innerHTML = items.map((resource) => {
|
| 688 |
+
const title = esc(resource.title || "Untitled resource");
|
| 689 |
+
const url = esc(resource.url || "#");
|
| 690 |
+
const summary = esc(resource.summary || "No summary provided.");
|
| 691 |
+
const primaryUse = esc(resource.primary_use || "n/a");
|
| 692 |
+
const evidenceText = esc(resource.evidence_text || "evidence link");
|
| 693 |
+
const evidenceUrl = esc(resource.evidence_url || resource.url || "#");
|
| 694 |
+
const tasks = (resource.tasks || []).map((t) => esc(t)).join(", ") || "n/a";
|
| 695 |
+
|
| 696 |
+
return `
|
| 697 |
+
<li class="card">
|
| 698 |
+
<div class="chips">
|
| 699 |
+
${chip(resource.category || "unknown", "category")}
|
| 700 |
+
${chip(resource.source || "unknown", "source")}
|
| 701 |
+
${chip(resource.status || "unknown", "status")}
|
| 702 |
+
</div>
|
| 703 |
+
<h2 class="title"><a href="${url}" target="_blank" rel="noreferrer">${title}</a></h2>
|
| 704 |
+
<p class="text">${summary}</p>
|
| 705 |
+
<p class="text"><strong>Primary use:</strong> ${primaryUse}</p>
|
| 706 |
+
<p class="tasks"><strong>Tasks:</strong> ${tasks}</p>
|
| 707 |
+
<div class="meta-links">
|
| 708 |
+
<a class="mini-link" href="${url}" target="_blank" rel="noreferrer">Open resource</a>
|
| 709 |
+
<a class="mini-link" href="${evidenceUrl}" target="_blank" rel="noreferrer">Pashto evidence: ${evidenceText}</a>
|
| 710 |
+
</div>
|
| 711 |
+
</li>
|
| 712 |
+
`;
|
| 713 |
+
}).join("");
|
| 714 |
+
}
|
| 715 |
+
|
| 716 |
+
function syncUrl() {
|
| 717 |
+
const params = new URLSearchParams();
|
| 718 |
+
if (els.q.value.trim()) params.set("q", els.q.value.trim());
|
| 719 |
+
if (els.category.value) params.set("category", els.category.value);
|
| 720 |
+
if (els.source.value) params.set("source", els.source.value);
|
| 721 |
+
if (els.task.value) params.set("task", els.task.value);
|
| 722 |
+
if (els.status.value) params.set("status", els.status.value);
|
| 723 |
+
if (els.sort.value && els.sort.value !== "relevance") params.set("sort", els.sort.value);
|
| 724 |
+
if (state.view !== "grid") params.set("view", state.view);
|
| 725 |
+
|
| 726 |
+
const next = `${window.location.pathname}${params.toString() ? `?${params.toString()}` : ""}`;
|
| 727 |
+
window.history.replaceState({}, "", next);
|
| 728 |
+
}
|
| 729 |
+
|
| 730 |
+
function applyUrlState() {
|
| 731 |
+
const params = new URLSearchParams(window.location.search);
|
| 732 |
+
if (params.get("q")) els.q.value = params.get("q");
|
| 733 |
+
if (params.get("category")) els.category.value = params.get("category");
|
| 734 |
+
if (params.get("source")) els.source.value = params.get("source");
|
| 735 |
+
if (params.get("task")) els.task.value = params.get("task");
|
| 736 |
+
if (params.get("status")) els.status.value = params.get("status");
|
| 737 |
+
if (params.get("sort")) els.sort.value = params.get("sort");
|
| 738 |
+
if (params.get("view")) setView(params.get("view"));
|
| 739 |
+
}
|
| 740 |
+
|
| 741 |
+
function clearFilters() {
|
| 742 |
+
els.q.value = "";
|
| 743 |
+
els.category.value = "";
|
| 744 |
+
els.source.value = "";
|
| 745 |
+
els.task.value = "";
|
| 746 |
+
els.status.value = "";
|
| 747 |
+
els.sort.value = "relevance";
|
| 748 |
+
setView("grid");
|
| 749 |
+
applyFilters();
|
| 750 |
+
}
|
| 751 |
+
|
| 752 |
+
function applyIntent(intent) {
|
| 753 |
+
if (intent === "datasets") {
|
| 754 |
+
els.category.value = "dataset";
|
| 755 |
+
els.task.value = "";
|
| 756 |
+
els.q.value = "";
|
| 757 |
+
} else if (intent === "asr") {
|
| 758 |
+
els.task.value = "asr";
|
| 759 |
+
} else if (intent === "tts") {
|
| 760 |
+
els.task.value = "tts";
|
| 761 |
+
} else if (intent === "nlp") {
|
| 762 |
+
els.task.value = "nlp";
|
| 763 |
+
} else if (intent === "mt") {
|
| 764 |
+
els.task.value = "";
|
| 765 |
+
els.q.value = "translation";
|
| 766 |
+
} else if (intent === "verified") {
|
| 767 |
+
els.status.value = "verified";
|
| 768 |
+
}
|
| 769 |
+
applyFilters();
|
| 770 |
+
}
|
| 771 |
+
|
| 772 |
+
async function copySearchLink() {
|
| 773 |
+
try {
|
| 774 |
+
await navigator.clipboard.writeText(window.location.href);
|
| 775 |
+
els.copyLink.textContent = "Link copied";
|
| 776 |
+
setTimeout(() => { els.copyLink.textContent = "Copy search link"; }, 1200);
|
| 777 |
+
} catch (_error) {
|
| 778 |
+
els.copyLink.textContent = "Copy failed";
|
| 779 |
+
setTimeout(() => { els.copyLink.textContent = "Copy search link"; }, 1200);
|
| 780 |
+
}
|
| 781 |
}
|
| 782 |
|
| 783 |
async function load() {
|
|
|
|
| 785 |
const res = await fetch("./resources.json", { cache: "no-store" });
|
| 786 |
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
| 787 |
const payload = await res.json();
|
| 788 |
+
|
| 789 |
state.all = payload.resources || [];
|
|
|
|
| 790 |
|
| 791 |
fillSelect(els.category, uniqSorted(state.all.map((r) => r.category)), "All categories");
|
| 792 |
fillSelect(els.source, uniqSorted(state.all.map((r) => r.source)), "All sources");
|
| 793 |
fillSelect(els.status, uniqSorted(state.all.map((r) => r.status)), "All statuses");
|
| 794 |
+
fillSelect(els.task, uniqSorted(state.all.flatMap((r) => r.tasks || [])), "All tasks");
|
| 795 |
+
|
| 796 |
+
updateMetrics();
|
|
|
|
|
|
|
| 797 |
|
| 798 |
const generated = payload.generated_on ? new Date(payload.generated_on) : null;
|
| 799 |
els.generatedAt.textContent = generated && !Number.isNaN(generated.getTime())
|
| 800 |
? `Catalog timestamp: ${generated.toISOString()}`
|
| 801 |
: "Catalog timestamp: unknown";
|
| 802 |
|
| 803 |
+
applyUrlState();
|
| 804 |
applyFilters();
|
| 805 |
} catch (err) {
|
| 806 |
els.countText.textContent = "Failed to load resources";
|
| 807 |
+
els.results.innerHTML = `<li class="empty">Could not load search data. ${esc(String(err))}</li>`;
|
| 808 |
}
|
| 809 |
}
|
| 810 |
|
| 811 |
+
[els.q, els.category, els.source, els.task, els.status, els.sort].forEach((el) => {
|
| 812 |
el.addEventListener("input", applyFilters);
|
| 813 |
el.addEventListener("change", applyFilters);
|
| 814 |
});
|
| 815 |
|
| 816 |
+
els.viewGrid.addEventListener("click", () => setView("grid"));
|
| 817 |
+
els.viewList.addEventListener("click", () => setView("list"));
|
| 818 |
+
els.clearFilters.addEventListener("click", clearFilters);
|
| 819 |
+
els.copyLink.addEventListener("click", copySearchLink);
|
| 820 |
+
els.intents.forEach((button) => {
|
| 821 |
+
button.addEventListener("click", () => applyIntent(button.dataset.intent));
|
| 822 |
+
});
|
| 823 |
+
|
| 824 |
load();
|
| 825 |
</script>
|
| 826 |
</body>
|
| 827 |
</html>
|
|
|
pyproject.toml
CHANGED
|
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|
| 4 |
|
| 5 |
[project]
|
| 6 |
name = "pashto-language-resources"
|
| 7 |
-
version = "
|
| 8 |
description = "Open Pashto language resources for ASR, TTS, NLP, and benchmarks"
|
| 9 |
requires-python = ">=3.10"
|
| 10 |
readme = "README.md"
|
|
@@ -35,3 +35,4 @@ python_files = ["test_*.py"]
|
|
| 35 |
packages = []
|
| 36 |
|
| 37 |
|
|
|
|
|
|
| 4 |
|
| 5 |
[project]
|
| 6 |
name = "pashto-language-resources"
|
| 7 |
+
version = "1.0.0"
|
| 8 |
description = "Open Pashto language resources for ASR, TTS, NLP, and benchmarks"
|
| 9 |
requires-python = ">=3.10"
|
| 10 |
readme = "README.md"
|
|
|
|
| 35 |
packages = []
|
| 36 |
|
| 37 |
|
| 38 |
+
|