forks/archivebox
1
0
Fork 0
Code Releases Activity

Merge pull request #571 from cdvv7788/remove-walrus

Browse source
This commit is contained in:
Nick Sweeting 2020-12-06 15:17:53 -05:00 committed by GitHub
commit 60f5b94d74
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 9 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
archivebox/core/models.py
View file

@ -60,6 +60,7 @@ class Tag(models.Model):
else: else:
return super().save(*args, **kwargs) return super().save(*args, **kwargs)
class Snapshot(models.Model): class Snapshot(models.Model):
id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False) id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)
@ -158,6 +159,7 @@ class Snapshot(models.Model):
self.tags.clear() self.tags.clear()
self.tags.add(*tags_id) self.tags.add(*tags_id)
class ArchiveResultManager(models.Manager): class ArchiveResultManager(models.Manager):
def indexable(self, sorted: bool = True): def indexable(self, sorted: bool = True):
INDEXABLE_METHODS = [ r[0] for r in ARCHIVE_METHODS_INDEXING_PRECEDENCE ] INDEXABLE_METHODS = [ r[0] for r in ARCHIVE_METHODS_INDEXING_PRECEDENCE ]
@ -167,6 +169,8 @@ class ArchiveResultManager(models.Manager):
precedence = [ When(extractor=method, then=Value(precedence)) for method, precedence in ARCHIVE_METHODS_INDEXING_PRECEDENCE ] precedence = [ When(extractor=method, then=Value(precedence)) for method, precedence in ARCHIVE_METHODS_INDEXING_PRECEDENCE ]
qs = qs.annotate(indexing_precedence=Case(*precedence, default=Value(1000),output_field=IntegerField())).order_by('indexing_precedence') qs = qs.annotate(indexing_precedence=Case(*precedence, default=Value(1000),output_field=IntegerField())).order_by('indexing_precedence')
return qs return qs
class ArchiveResult(models.Model): class ArchiveResult(models.Model):
snapshot = models.ForeignKey(Snapshot, on_delete=models.CASCADE) snapshot = models.ForeignKey(Snapshot, on_delete=models.CASCADE)
cmd = models.JSONField() cmd = models.JSONField()

2
archivebox/logging_util.py
View file

@ -443,7 +443,7 @@ def log_shell_welcome_msg():
from .cli import list_subcommands from .cli import list_subcommands
print('{green}# ArchiveBox Imports{reset}'.format(**ANSI)) print('{green}# ArchiveBox Imports{reset}'.format(**ANSI))
print('{green}from archivebox.core.models import Snapshot, User{reset}'.format(**ANSI)) print('{green}from core.models import Snapshot, User{reset}'.format(**ANSI))
print('{green}from archivebox import *\n {}{reset}'.format("\n ".join(list_subcommands().keys()), **ANSI)) print('{green}from archivebox import *\n {}{reset}'.format("\n ".join(list_subcommands().keys()), **ANSI))
print() print()
print('[i] Welcome to the ArchiveBox Shell!') print('[i] Welcome to the ArchiveBox Shell!')

3
archivebox/search/__init__.py
View file

@ -95,7 +95,8 @@ def index_links(links: Union[List[Link],None], out_dir: Path=OUTPUT_DIR):
from core.models import Snapshot, ArchiveResult from core.models import Snapshot, ArchiveResult
for link in links: for link in links:
if snap := Snapshot.objects.filter(url=link.url).first(): snap = Snapshot.objects.filter(url=link.url).first()
if snap:
results = ArchiveResult.objects.indexable().filter(snapshot=snap) results = ArchiveResult.objects.indexable().filter(snapshot=snap)
log_index_started(link.url) log_index_started(link.url)
try: try:

3
archivebox/search/backends/ripgrep.py
View file

@ -38,7 +38,8 @@ def search(text: str) -> List[str]:
file_paths = [p.decode() for p in rg.stdout.splitlines()] file_paths = [p.decode() for p in rg.stdout.splitlines()]
timestamps = set() timestamps = set()
for path in file_paths: for path in file_paths:
if ts := ts_regex.findall(path): ts = ts_regex.findall(path)
if ts:
timestamps.add(ts[0]) timestamps.add(ts[0])
snap_ids = [str(id) for id in Snapshot.objects.filter(timestamp__in=timestamps).values_list('pk', flat=True)] snap_ids = [str(id) for id in Snapshot.objects.filter(timestamp__in=timestamps).values_list('pk', flat=True)]