Skip to content

Scan files for packages faster #2000

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
AyanSinhaMahapatra wants to merge 1 commit into
base: main
Choose a base branch
from
+12 −5
Draft

Scan files for packages faster #2000

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 3 additions & 5 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,9 +58,9 @@ dependencies = [
# Docker
"container-inspector==33.0.0",
# ScanCode-toolkit
"scancode-toolkit[packages]==32.4.1",
"scancode-toolkit[packages]@git+https://github.com/aboutcode-org/scancode-toolkit.git@6b6a79b8a1c0b9789a466df4c5623ab723890a76",
"extractcode[full]==31.0.0",
"commoncode==32.3.0",
"commoncode==32.4.0",
"Beautifulsoup4[chardet]==4.13.4",
"packageurl-python==0.17.6",
# Workaround issue https://github.com/aboutcode-org/scancode.io/issues/1795
Expand Down Expand Up @@ -101,9 +101,7 @@ dependencies = [
# AboutCode pipeline
"aboutcode.pipeline==0.2.1",
# ScoreCode
"scorecode==0.0.4",
# Workaround issue https://github.com/aboutcode-org/scancode.io/issues/1885
"click==8.2.1"
"scorecode==0.0.4"
]

[project.optional-dependencies]
Expand Down
7 changes: 7 additions & 0 deletions scanpipe/pipelines/inspect_packages.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,10 +49,16 @@ def steps(cls):
cls.collect_and_create_codebase_resources,
cls.flag_empty_files,
cls.flag_ignored_resources,
cls.scan_binaries,
cls.scan_for_application_packages,
cls.resolve_dependencies,
)

@optional_step("Binary")
def scan_binaries(self):
"""Scan binaries for package and dependency information."""
self.scan_binaries = True

def scan_for_application_packages(self):
"""
Scan resources for package information to add DiscoveredPackage
Expand All @@ -61,6 +67,7 @@ def scan_for_application_packages(self):
scancode.scan_for_application_packages(
project=self.project,
assemble=True,
binary=self.scan_binaries or False,
package_only=True,
progress_logger=self.log,
)
Expand Down
2 changes: 2 additions & 0 deletions scanpipe/pipes/scancode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -409,6 +409,7 @@ def scan_for_files(project, resource_qs=None, progress_logger=None):
def scan_for_application_packages(
project,
assemble=True,
binary=False,
package_only=False,
resource_qs=None,
progress_logger=logger.info,
Expand All @@ -431,6 +432,7 @@ def scan_for_application_packages(

scan_func_kwargs = {
"package_only": package_only,
"binary": binary,
}

# Collect detected Package data and save it to the CodebaseResource it was
Expand Down