forks/archivebox
1
0
Fork 0
Code Releases Activity

add quick-init option to skip reimporting all snapshot dirs on init

Browse source
This commit is contained in:
Nick Sweeting 2021-02-15 14:52:10 -05:00
parent e61e12c889
commit 3c3bae02d2
4 changed files with 56 additions and 42 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
archivebox/cli/archivebox_init.py
View file

@ -27,11 +27,17 @@ def main(args: Optional[List[str]]=None, stdin: Optional[IO]=None, pwd: Optional
action='store_true', action='store_true',
help='Ignore unrecognized files in current directory and initialize anyway', help='Ignore unrecognized files in current directory and initialize anyway',
) )
parser.add_argument(
'--quick', '-q',
action='store_true',
help='Run any updates or migrations without rechecking all snapshot dirs',
)
command = parser.parse_args(args or ()) command = parser.parse_args(args or ())
reject_stdin(__command__, stdin) reject_stdin(__command__, stdin)
init( init(
force=command.force, force=command.force,
quick=command.quick,
out_dir=pwd or OUTPUT_DIR, out_dir=pwd or OUTPUT_DIR,
) )

8
archivebox/cli/archivebox_server.py
View file

@ -41,7 +41,12 @@ def main(args: Optional[List[str]]=None, stdin: Optional[IO]=None, pwd: Optional
parser.add_argument( parser.add_argument(
'--init', '--init',
action='store_true', action='store_true',
help='Run archivebox init before starting the server', help='Run a full archivebox init/upgrade before starting the server',
)
parser.add_argument(
'--quick-init', '-i',
action='store_true',
help='Run quick archivebox init/upgrade before starting the server',
) )
parser.add_argument( parser.add_argument(
'--createsuperuser', '--createsuperuser',
@ -56,6 +61,7 @@ def main(args: Optional[List[str]]=None, stdin: Optional[IO]=None, pwd: Optional
reload=command.reload, reload=command.reload,
debug=command.debug, debug=command.debug,
init=command.init, init=command.init,
quick_init=command.quick_init,
createsuperuser=command.createsuperuser, createsuperuser=command.createsuperuser,
out_dir=pwd or OUTPUT_DIR, out_dir=pwd or OUTPUT_DIR,
) )

82
archivebox/main.py
View file

@ -263,7 +263,7 @@ def run(subcommand: str,
@enforce_types @enforce_types
def init(force: bool=False, out_dir: Path=OUTPUT_DIR) -> None: def init(force: bool=False, quick: bool=False, out_dir: Path=OUTPUT_DIR) -> None:
"""Initialize a new ArchiveBox collection in the current directory""" """Initialize a new ArchiveBox collection in the current directory"""
from core.models import Snapshot from core.models import Snapshot
@ -345,48 +345,49 @@ def init(force: bool=False, out_dir: Path=OUTPUT_DIR) -> None:
all_links = load_main_index(out_dir=out_dir, warn=False) all_links = load_main_index(out_dir=out_dir, warn=False)
print(' √ Loaded {} links from existing main index.'.format(all_links.count())) print(' √ Loaded {} links from existing main index.'.format(all_links.count()))
# Links in data folders that dont match their timestamp if not quick:
fixed, cant_fix = fix_invalid_folder_locations(out_dir=out_dir) # Links in data folders that dont match their timestamp
if fixed: fixed, cant_fix = fix_invalid_folder_locations(out_dir=out_dir)
print(' {lightyellow}√ Fixed {} data directory locations that didn\'t match their link timestamps.{reset}'.format(len(fixed), **ANSI)) if fixed:
if cant_fix: print(' {lightyellow}√ Fixed {} data directory locations that didn\'t match their link timestamps.{reset}'.format(len(fixed), **ANSI))
print(' {lightyellow}! Could not fix {} data directory locations due to conflicts with existing folders.{reset}'.format(len(cant_fix), **ANSI)) if cant_fix:
print(' {lightyellow}! Could not fix {} data directory locations due to conflicts with existing folders.{reset}'.format(len(cant_fix), **ANSI))
# Links in JSON index but not in main index # Links in JSON index but not in main index
orphaned_json_links = { orphaned_json_links = {
link.url: link link.url: link
for link in parse_json_main_index(out_dir) for link in parse_json_main_index(out_dir)
if not all_links.filter(url=link.url).exists() if not all_links.filter(url=link.url).exists()
} }
if orphaned_json_links: if orphaned_json_links:
pending_links.update(orphaned_json_links) pending_links.update(orphaned_json_links)
print(' {lightyellow}√ Added {} orphaned links from existing JSON index...{reset}'.format(len(orphaned_json_links), **ANSI)) print(' {lightyellow}√ Added {} orphaned links from existing JSON index...{reset}'.format(len(orphaned_json_links), **ANSI))
# Links in data dir indexes but not in main index # Links in data dir indexes but not in main index
orphaned_data_dir_links = { orphaned_data_dir_links = {
link.url: link link.url: link
for link in parse_json_links_details(out_dir) for link in parse_json_links_details(out_dir)
if not all_links.filter(url=link.url).exists() if not all_links.filter(url=link.url).exists()
} }
if orphaned_data_dir_links: if orphaned_data_dir_links:
pending_links.update(orphaned_data_dir_links) pending_links.update(orphaned_data_dir_links)
print(' {lightyellow}√ Added {} orphaned links from existing archive directories.{reset}'.format(len(orphaned_data_dir_links), **ANSI)) print(' {lightyellow}√ Added {} orphaned links from existing archive directories.{reset}'.format(len(orphaned_data_dir_links), **ANSI))
# Links in invalid/duplicate data dirs # Links in invalid/duplicate data dirs
invalid_folders = { invalid_folders = {
folder: link folder: link
for folder, link in get_invalid_folders(all_links, out_dir=out_dir).items() for folder, link in get_invalid_folders(all_links, out_dir=out_dir).items()
} }
if invalid_folders: if invalid_folders:
print(' {lightyellow}! Skipped adding {} invalid link data directories.{reset}'.format(len(invalid_folders), **ANSI)) print(' {lightyellow}! Skipped adding {} invalid link data directories.{reset}'.format(len(invalid_folders), **ANSI))
print(' X ' + '\n X '.join(f'{folder} {link}' for folder, link in invalid_folders.items())) print(' X ' + '\n X '.join(f'{folder} {link}' for folder, link in invalid_folders.items()))
print() print()
print(' {lightred}Hint:{reset} For more information about the link data directories that were skipped, run:'.format(**ANSI)) print(' {lightred}Hint:{reset} For more information about the link data directories that were skipped, run:'.format(**ANSI))
print(' archivebox status') print(' archivebox status')
print(' archivebox list --status=invalid') print(' archivebox list --status=invalid')
write_main_index(list(pending_links.values()), out_dir=out_dir) write_main_index(list(pending_links.values()), out_dir=out_dir)
print('\n{green}------------------------------------------------------------------{reset}'.format(**ANSI)) print('\n{green}------------------------------------------------------------------{reset}'.format(**ANSI))
if existing_index: if existing_index:
@ -1063,14 +1064,15 @@ def server(runserver_args: Optional[List[str]]=None,
reload: bool=False, reload: bool=False,
debug: bool=False, debug: bool=False,
init: bool=False, init: bool=False,
quick_init: bool=False,
createsuperuser: bool=False, createsuperuser: bool=False,
out_dir: Path=OUTPUT_DIR) -> None: out_dir: Path=OUTPUT_DIR) -> None:
"""Run the ArchiveBox HTTP server""" """Run the ArchiveBox HTTP server"""
runserver_args = runserver_args or [] runserver_args = runserver_args or []
if init: if init or quick_init:
run_subcommand('init', stdin=None, pwd=out_dir) run_subcommand('init', quick=quick_init, stdin=None, pwd=out_dir)
if createsuperuser: if createsuperuser:
run_subcommand('manage', subcommand_args=['createsuperuser'], pwd=out_dir) run_subcommand('manage', subcommand_args=['createsuperuser'], pwd=out_dir)

2
docker-compose.yml
View file

@ -13,7 +13,7 @@ services:
archivebox: archivebox:
# build: . # build: .
image: ${DOCKER_IMAGE:-archivebox/archivebox:latest} image: ${DOCKER_IMAGE:-archivebox/archivebox:latest}
command: server 0.0.0.0:8000 command: server --quick-init 0.0.0.0:8000
stdin_open: true stdin_open: true
tty: true tty: true
ports: ports: