From 8c846b7d1ce400bccd158ad1a1c18abe7565edca Mon Sep 17 00:00:00 2001 From: Claude Date: Sat, 27 Dec 2025 10:06:34 +0000 Subject: [PATCH] Rename validate hooks to install hooks - Rename 13 on_Crawl__00_validate_* hooks to on_Crawl__00_install_* - This better reflects what these hooks actually do (check/install binaries) - Update TODO_hook_architecture.md to reflect renamed hooks --- TODO_hook_architecture.md | 26 ++++++++++--------- ...rome.py => on_Crawl__00_install_chrome.py} | 0 ... => on_Crawl__00_install_chrome_config.py} | 0 ...mdl.py => on_Crawl__00_install_forumdl.py} | 0 ...l.py => on_Crawl__00_install_gallerydl.py} | 0 ...ate_git.py => on_Crawl__00_install_git.py} | 0 ...ytdlp.py => on_Crawl__00_install_ytdlp.py} | 0 ...ury.py => on_Crawl__00_install_mercury.py} | 0 ...dl.py => on_Crawl__00_install_papersdl.py} | 0 ...py => on_Crawl__00_install_readability.py} | 0 ...rep.py => on_Crawl__00_install_ripgrep.py} | 0 ....py => on_Crawl__00_install_singlefile.py} | 0 ...e_wget.py => on_Crawl__00_install_wget.py} | 0 ...py => on_Crawl__00_install_wget_config.py} | 0 14 files changed, 14 insertions(+), 12 deletions(-) rename archivebox/plugins/chrome_session/{on_Crawl__00_validate_chrome.py => on_Crawl__00_install_chrome.py} (100%) rename archivebox/plugins/chrome_session/{on_Crawl__00_validate_chrome_config.py => on_Crawl__00_install_chrome_config.py} (100%) rename archivebox/plugins/forumdl/{on_Crawl__00_validate_forumdl.py => on_Crawl__00_install_forumdl.py} (100%) rename archivebox/plugins/gallerydl/{on_Crawl__00_validate_gallerydl.py => on_Crawl__00_install_gallerydl.py} (100%) rename archivebox/plugins/git/{on_Crawl__00_validate_git.py => on_Crawl__00_install_git.py} (100%) rename archivebox/plugins/media/{on_Crawl__00_validate_ytdlp.py => on_Crawl__00_install_ytdlp.py} (100%) rename archivebox/plugins/mercury/{on_Crawl__00_validate_mercury.py => on_Crawl__00_install_mercury.py} (100%) rename archivebox/plugins/papersdl/{on_Crawl__00_validate_papersdl.py => on_Crawl__00_install_papersdl.py} (100%) rename archivebox/plugins/readability/{on_Crawl__00_validate_readability.py => on_Crawl__00_install_readability.py} (100%) rename archivebox/plugins/search_backend_ripgrep/{on_Crawl__00_validate_ripgrep.py => on_Crawl__00_install_ripgrep.py} (100%) rename archivebox/plugins/singlefile/{on_Crawl__00_validate_singlefile.py => on_Crawl__00_install_singlefile.py} (100%) rename archivebox/plugins/wget/{on_Crawl__00_validate_wget.py => on_Crawl__00_install_wget.py} (100%) rename archivebox/plugins/wget/{on_Crawl__00_validate_wget_config.py => on_Crawl__00_install_wget_config.py} (100%) diff --git a/TODO_hook_architecture.md b/TODO_hook_architecture.md index 2504ca38..951b6ccd 100644 --- a/TODO_hook_architecture.md +++ b/TODO_hook_architecture.md @@ -1854,21 +1854,23 @@ Updated `archivebox/core/statemachines.py`: | npm | `on_Dependency__install_using_npm_provider.py` | ✅ OK | Emits `{type: 'InstalledBinary'}` JSONL | | pip | `on_Dependency__install_using_pip_provider.py` | ✅ OK | Emits `{type: 'InstalledBinary'}` JSONL | -### Crawl Validate Hooks (on_Crawl__00_validate_*) - ALL COMPLIANT ✅ +### Crawl Install Hooks (on_Crawl__00_install_*) - ALL RENAMED ✅ | Plugin | Hook | Status | Notes | |--------|------|--------|-------| -| chrome_session | `on_Crawl__00_validate_chrome.py` | ✅ OK | Emits InstalledBinary/Dependency JSONL | -| wget | `on_Crawl__00_validate_wget.py` | ✅ OK | Emits InstalledBinary/Dependency JSONL | -| singlefile | `on_Crawl__00_validate_singlefile.py` | ✅ OK | Emits InstalledBinary/Dependency JSONL | -| readability | `on_Crawl__00_validate_readability.py` | ✅ OK | Emits InstalledBinary/Dependency JSONL | -| media | `on_Crawl__00_validate_ytdlp.py` | ✅ OK | Emits InstalledBinary/Dependency JSONL | -| git | `on_Crawl__00_validate_git.py` | ✅ OK | Emits InstalledBinary/Dependency JSONL | -| forumdl | `on_Crawl__00_validate_forumdl.py` | ✅ OK | Emits InstalledBinary/Dependency JSONL | -| gallerydl | `on_Crawl__00_validate_gallerydl.py` | ✅ OK | Emits InstalledBinary/Dependency JSONL | -| mercury | `on_Crawl__00_validate_mercury.py` | ✅ OK | Emits InstalledBinary/Dependency JSONL | -| papersdl | `on_Crawl__00_validate_papersdl.py` | ✅ OK | Emits InstalledBinary/Dependency JSONL | -| search_backend_ripgrep | `on_Crawl__00_validate_ripgrep.py` | ✅ OK | Emits InstalledBinary/Dependency JSONL | +| chrome_session | `on_Crawl__00_install_chrome.py` | ✅ RENAMED | Emits InstalledBinary/Dependency JSONL | +| chrome_session | `on_Crawl__00_install_chrome_config.py` | ✅ RENAMED | Emits config JSONL | +| wget | `on_Crawl__00_install_wget.py` | ✅ RENAMED | Emits InstalledBinary/Dependency JSONL | +| wget | `on_Crawl__00_install_wget_config.py` | ✅ RENAMED | Emits config JSONL | +| singlefile | `on_Crawl__00_install_singlefile.py` | ✅ RENAMED | Emits InstalledBinary/Dependency JSONL | +| readability | `on_Crawl__00_install_readability.py` | ✅ RENAMED | Emits InstalledBinary/Dependency JSONL | +| media | `on_Crawl__00_install_ytdlp.py` | ✅ RENAMED | Emits InstalledBinary/Dependency JSONL | +| git | `on_Crawl__00_install_git.py` | ✅ RENAMED | Emits InstalledBinary/Dependency JSONL | +| forumdl | `on_Crawl__00_install_forumdl.py` | ✅ RENAMED | Emits InstalledBinary/Dependency JSONL | +| gallerydl | `on_Crawl__00_install_gallerydl.py` | ✅ RENAMED | Emits InstalledBinary/Dependency JSONL | +| mercury | `on_Crawl__00_install_mercury.py` | ✅ RENAMED | Emits InstalledBinary/Dependency JSONL | +| papersdl | `on_Crawl__00_install_papersdl.py` | ✅ RENAMED | Emits InstalledBinary/Dependency JSONL | +| search_backend_ripgrep | `on_Crawl__00_install_ripgrep.py` | ✅ RENAMED | Emits InstalledBinary/Dependency JSONL | ### Snapshot Hooks (on_Snapshot__*) - Python Hooks UPDATED ✅ diff --git a/archivebox/plugins/chrome_session/on_Crawl__00_validate_chrome.py b/archivebox/plugins/chrome_session/on_Crawl__00_install_chrome.py similarity index 100% rename from archivebox/plugins/chrome_session/on_Crawl__00_validate_chrome.py rename to archivebox/plugins/chrome_session/on_Crawl__00_install_chrome.py diff --git a/archivebox/plugins/chrome_session/on_Crawl__00_validate_chrome_config.py b/archivebox/plugins/chrome_session/on_Crawl__00_install_chrome_config.py similarity index 100% rename from archivebox/plugins/chrome_session/on_Crawl__00_validate_chrome_config.py rename to archivebox/plugins/chrome_session/on_Crawl__00_install_chrome_config.py diff --git a/archivebox/plugins/forumdl/on_Crawl__00_validate_forumdl.py b/archivebox/plugins/forumdl/on_Crawl__00_install_forumdl.py similarity index 100% rename from archivebox/plugins/forumdl/on_Crawl__00_validate_forumdl.py rename to archivebox/plugins/forumdl/on_Crawl__00_install_forumdl.py diff --git a/archivebox/plugins/gallerydl/on_Crawl__00_validate_gallerydl.py b/archivebox/plugins/gallerydl/on_Crawl__00_install_gallerydl.py similarity index 100% rename from archivebox/plugins/gallerydl/on_Crawl__00_validate_gallerydl.py rename to archivebox/plugins/gallerydl/on_Crawl__00_install_gallerydl.py diff --git a/archivebox/plugins/git/on_Crawl__00_validate_git.py b/archivebox/plugins/git/on_Crawl__00_install_git.py similarity index 100% rename from archivebox/plugins/git/on_Crawl__00_validate_git.py rename to archivebox/plugins/git/on_Crawl__00_install_git.py diff --git a/archivebox/plugins/media/on_Crawl__00_validate_ytdlp.py b/archivebox/plugins/media/on_Crawl__00_install_ytdlp.py similarity index 100% rename from archivebox/plugins/media/on_Crawl__00_validate_ytdlp.py rename to archivebox/plugins/media/on_Crawl__00_install_ytdlp.py diff --git a/archivebox/plugins/mercury/on_Crawl__00_validate_mercury.py b/archivebox/plugins/mercury/on_Crawl__00_install_mercury.py similarity index 100% rename from archivebox/plugins/mercury/on_Crawl__00_validate_mercury.py rename to archivebox/plugins/mercury/on_Crawl__00_install_mercury.py diff --git a/archivebox/plugins/papersdl/on_Crawl__00_validate_papersdl.py b/archivebox/plugins/papersdl/on_Crawl__00_install_papersdl.py similarity index 100% rename from archivebox/plugins/papersdl/on_Crawl__00_validate_papersdl.py rename to archivebox/plugins/papersdl/on_Crawl__00_install_papersdl.py diff --git a/archivebox/plugins/readability/on_Crawl__00_validate_readability.py b/archivebox/plugins/readability/on_Crawl__00_install_readability.py similarity index 100% rename from archivebox/plugins/readability/on_Crawl__00_validate_readability.py rename to archivebox/plugins/readability/on_Crawl__00_install_readability.py diff --git a/archivebox/plugins/search_backend_ripgrep/on_Crawl__00_validate_ripgrep.py b/archivebox/plugins/search_backend_ripgrep/on_Crawl__00_install_ripgrep.py similarity index 100% rename from archivebox/plugins/search_backend_ripgrep/on_Crawl__00_validate_ripgrep.py rename to archivebox/plugins/search_backend_ripgrep/on_Crawl__00_install_ripgrep.py diff --git a/archivebox/plugins/singlefile/on_Crawl__00_validate_singlefile.py b/archivebox/plugins/singlefile/on_Crawl__00_install_singlefile.py similarity index 100% rename from archivebox/plugins/singlefile/on_Crawl__00_validate_singlefile.py rename to archivebox/plugins/singlefile/on_Crawl__00_install_singlefile.py diff --git a/archivebox/plugins/wget/on_Crawl__00_validate_wget.py b/archivebox/plugins/wget/on_Crawl__00_install_wget.py similarity index 100% rename from archivebox/plugins/wget/on_Crawl__00_validate_wget.py rename to archivebox/plugins/wget/on_Crawl__00_install_wget.py diff --git a/archivebox/plugins/wget/on_Crawl__00_validate_wget_config.py b/archivebox/plugins/wget/on_Crawl__00_install_wget_config.py similarity index 100% rename from archivebox/plugins/wget/on_Crawl__00_validate_wget_config.py rename to archivebox/plugins/wget/on_Crawl__00_install_wget_config.py