ci: ostree wip #29
Draft
ci: ostree wip #29
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Show how to configure package repos for use with ostree image building and linux-system-roles/tox-lsr#213 Signed-off-by: Rich Megginson <rmeggins@redhat.com>
Reviewer's GuideThis PR extends get_ostree_data.sh to support collecting and formatting repository definitions in addition to packages, refactors suffix handling into a reusable list, and updates usage documentation accordingly. Class diagram for new repo formatting functions in get_ostree_data.shclassDiagram
class get_repos {
+get_repos(ostree_dir)
}
class format_repos_json {
+format_repos_json()
}
class format_repos_raw {
+format_repos_raw()
}
class format_repos_yaml {
+format_repos_yaml()
}
get_repos --> format_repos_json
get_repos --> format_repos_raw
get_repos --> format_repos_yaml
Flow diagram for new repo data collection in get_ostree_data.shflowchart TD
A["User calls get_ostree_data.sh with 'repos' argument"] --> B["get_repos() called"]
B --> C["Iterate repotype in pkgtypes"]
C --> D["Iterate suff in suffix_list"]
D --> E["Check for repos-<repotype><suff>.repo file"]
E -->|If exists| F["cat repo file contents"]
C --> G["Check for roles-<repotype>.txt file"]
G -->|If exists| H["Iterate roles in file"]
H --> I["get_rolepath for each role"]
I -->|If found| J["Recursively call get_repos on rolepath"]
File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hey there - I've reviewed your changes and they look great!
Prompt for AI Agents
Please address the comments from this code review:
## Individual Comments
### Comment 1
<location> `.ostree/get_ostree_data.sh:141` </location>
<code_context>
+ for role in $roles; do
+ rolepath="$(get_rolepath "$ostree_dir" "$role")"
+ if [ -z "$rolepath" ]; then
+ 1>&2 echo ERROR - could not find role "$role" - please use ANSIBLE_COLLECTIONS_PATH
+ exit 2
+ fi
+ get_repos "$rolepath"
</code_context>
<issue_to_address>
**suggestion:** Error message could be more actionable for users.
Consider updating the error message to include specific steps or an example for setting ANSIBLE_COLLECTIONS_PATH, so users know how to resolve the issue.
```suggestion
1>&2 echo "ERROR - could not find role \"$role\". Please set ANSIBLE_COLLECTIONS_PATH to include the directory containing your Ansible roles. Example: export ANSIBLE_COLLECTIONS_PATH=/path/to/collections"
```
</issue_to_address>
### Comment 2
<location> `.ostree/get_ostree_data.sh:150` </location>
<code_context>
+ done
+}
+
+format_repos_json() {
+ python -c 'import sys; import json; import configparser
+cp = configparser.ConfigParser()
</code_context>
<issue_to_address>
**question:** Potential risk with shell variable expansion in repo_str.replace.
Review whether escaping dollar signs in repo_str is required, as it may affect legitimate values. If necessary, clarify the reasoning in the documentation.
</issue_to_address>
### Comment 3
<location> `.ostree/get_ostree_data.sh:177` </location>
<code_context>
+}
+
+format_repos_yaml() {
+ python -c 'import sys; import yaml; import configparser
+cp = configparser.ConfigParser()
+cp.read_file(sys.stdin)
</code_context>
<issue_to_address>
**suggestion:** yaml.safe_dump may not preserve ordering of repo fields.
If field order matters for downstream use, consider using OrderedDict or sorting keys before dumping.
Suggested implementation:
```
+ python -c 'import sys; import yaml; import configparser; from collections import OrderedDict
+cp = configparser.ConfigParser()
+cp.read_file(sys.stdin)
```
```
ret = []
# supported is from osbuild-mpp
supported = ["baseurl", "metalink", "mirrorlist",
"enabled", "metadata_expire", "gpgcheck", "username", "password", "priority",
"sslverify", "sslcacert", "sslclientkey", "sslclientcert",
"skip_if_unavailable"]
for section in cp.sections():
repo = OrderedDict()
repo["id"] = section
for option in supported:
if cp.has_option(section, option):
```
```
repo = {"id": section}
for option in supported:
if cp.has_option(section, option):
repo[option] = cp.get(section, option)
ret.append(repo)
print(yaml.safe_dump(ret, sort_keys=False))
'
```
</issue_to_address>Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
| done | ||
| } | ||
|
|
||
| format_repos_json() { |
There was a problem hiding this comment.
question: Potential risk with shell variable expansion in repo_str.replace.
Review whether escaping dollar signs in repo_str is required, as it may affect legitimate values. If necessary, clarify the reasoning in the documentation.
| } | ||
|
|
||
| format_repos_yaml() { | ||
| python -c 'import sys; import yaml; import configparser |
There was a problem hiding this comment.
suggestion: yaml.safe_dump may not preserve ordering of repo fields.
If field order matters for downstream use, consider using OrderedDict or sorting keys before dumping.
Suggested implementation:
+ python -c 'import sys; import yaml; import configparser; from collections import OrderedDict
+cp = configparser.ConfigParser()
+cp.read_file(sys.stdin)
ret = []
# supported is from osbuild-mpp
supported = ["baseurl", "metalink", "mirrorlist",
"enabled", "metadata_expire", "gpgcheck", "username", "password", "priority",
"sslverify", "sslcacert", "sslclientkey", "sslclientcert",
"skip_if_unavailable"]
for section in cp.sections():
repo = OrderedDict()
repo["id"] = section
for option in supported:
if cp.has_option(section, option):
repo = {"id": section}
for option in supported:
if cp.has_option(section, option):
repo[option] = cp.get(section, option)
ret.append(repo)
print(yaml.safe_dump(ret, sort_keys=False))
'
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Show how to configure package repos for use with ostree
image building and linux-system-roles/tox-lsr#213
Signed-off-by: Rich Megginson rmeggins@redhat.com
Summary by Sourcery
Enhance get_ostree_data.sh to not only list packages but also collect and format repository configurations in various formats (json, yaml, raw, toml) using shared suffix logic.
New Features:
Enhancements: