6316007eb1
- Convert handleResponse to package-level function (unused receiver) [#17955] - Add clarifying comment for nil resp on transport error [#17956] - Use consistent %w wrapping in dual-unmarshal error path [#17957] - Add SafeError() method to APIError for safe logging [#17964] - Enforce safe CheckRedirect policy in SetHTTPClient [#17965] - Add tests for SafeError and SetHTTPClient enforcement
136 lines
4.9 KiB
Go
136 lines
4.9 KiB
Go
package github
|
|
|
|
import (
|
|
"context"
|
|
"encoding/base64"
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/url"
|
|
"strings"
|
|
|
|
"gitea.weiker.me/rodin/review-bot/vcs"
|
|
)
|
|
|
|
// GetFileContent fetches a file from a repo at the given ref.
|
|
// Delegates to GetFileContentAtRef with the provided ref.
|
|
func (c *Client) GetFileContent(ctx context.Context, owner, repo, path, ref string) (string, error) {
|
|
return c.GetFileContentAtRef(ctx, owner, repo, path, ref)
|
|
}
|
|
|
|
// GetFileContentAtRef fetches a file at a specific ref from a repo.
|
|
// If ref is empty, the query parameter is omitted (uses default branch).
|
|
//
|
|
// Note: dot-segments ("." and "..") in the path are silently removed to
|
|
// prevent path traversal. This means a path like "foo/../bar" resolves
|
|
// to "foo/bar" rather than "bar".
|
|
func (c *Client) GetFileContentAtRef(ctx context.Context, owner, repo, path, ref string) (string, error) {
|
|
reqURL := fmt.Sprintf("%s/repos/%s/%s/contents/%s",
|
|
c.baseURL, url.PathEscape(owner), url.PathEscape(repo), escapePath(path))
|
|
if ref != "" {
|
|
reqURL += "?ref=" + url.QueryEscape(ref)
|
|
}
|
|
body, err := c.doGet(ctx, reqURL)
|
|
if err != nil {
|
|
return "", fmt.Errorf("fetch file %s: %w", path, err)
|
|
}
|
|
var resp struct {
|
|
Content string `json:"content"`
|
|
Encoding string `json:"encoding"`
|
|
}
|
|
if err := json.Unmarshal(body, &resp); err != nil {
|
|
return "", fmt.Errorf("parse file content JSON: %w", err)
|
|
}
|
|
if resp.Encoding != "base64" {
|
|
return "", fmt.Errorf("unexpected encoding %q for file %s", resp.Encoding, path)
|
|
}
|
|
decoded, err := decodeBase64Content(resp.Content)
|
|
if err != nil {
|
|
return "", fmt.Errorf("decode base64 content for %s: %w", path, err)
|
|
}
|
|
return decoded, nil
|
|
}
|
|
|
|
// ListContents lists files and directories at a given path in a repo.
|
|
// Returns the directory listing from the GitHub contents API.
|
|
// If the path points to a single file (not a directory), the API returns
|
|
// a JSON object instead of an array; this is handled by returning a
|
|
// single-element slice.
|
|
//
|
|
// Note: dot-segments ("." and "..") in the path are silently removed to
|
|
// prevent path traversal. This means a path like "foo/../bar" resolves
|
|
// to "foo/bar" rather than "bar".
|
|
func (c *Client) ListContents(ctx context.Context, owner, repo, path string) ([]vcs.ContentEntry, error) {
|
|
reqURL := fmt.Sprintf("%s/repos/%s/%s/contents/%s",
|
|
c.baseURL, url.PathEscape(owner), url.PathEscape(repo), escapePath(path))
|
|
body, err := c.doGet(ctx, reqURL)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("list contents %s: %w", path, err)
|
|
}
|
|
|
|
type entry struct {
|
|
Name string `json:"name"`
|
|
Path string `json:"path"`
|
|
Type string `json:"type"`
|
|
}
|
|
|
|
// The GitHub contents API returns an array for directories and an object
|
|
// for single files. Try array first (common case), then fall back to object.
|
|
// An empty array ([]) is valid — it represents an empty directory — and
|
|
// results in a zero-length slice returned without error.
|
|
var entries []entry
|
|
if err := json.Unmarshal(body, &entries); err != nil {
|
|
var single entry
|
|
if err2 := json.Unmarshal(body, &single); err2 != nil {
|
|
return nil, fmt.Errorf("parse contents JSON: as array: %w; as object: %w", err, err2)
|
|
}
|
|
// Guard against empty objects ({}) or unexpected shapes that
|
|
// unmarshal successfully but carry no useful data.
|
|
if single.Name == "" && single.Path == "" && single.Type == "" {
|
|
return nil, fmt.Errorf("parse contents JSON: unexpected response format")
|
|
}
|
|
entries = []entry{single}
|
|
}
|
|
|
|
result := make([]vcs.ContentEntry, len(entries))
|
|
for i, e := range entries {
|
|
result[i] = vcs.ContentEntry{
|
|
Name: e.Name,
|
|
Path: e.Path,
|
|
Type: e.Type,
|
|
}
|
|
}
|
|
return result, nil
|
|
}
|
|
|
|
// escapePath escapes each segment of a relative file path for use in URLs.
|
|
// Slashes are preserved as path separators; other special characters are escaped.
|
|
// Dot-segments ("." and "..") and empty segments (from consecutive slashes like
|
|
// "a//b") are silently removed to prevent path traversal and produce canonical
|
|
// paths. This is intentional: callers may receive a different path than requested
|
|
// without error. The function is package-private, and all callers
|
|
// (GetFileContentAtRef, ListContents) already handle missing-file errors from the
|
|
// API if the cleaned path doesn't match what the caller intended.
|
|
func escapePath(p string) string {
|
|
parts := strings.Split(p, "/")
|
|
var clean []string
|
|
for _, part := range parts {
|
|
if part == "." || part == ".." || part == "" {
|
|
continue
|
|
}
|
|
clean = append(clean, url.PathEscape(part))
|
|
}
|
|
return strings.Join(clean, "/")
|
|
}
|
|
|
|
// decodeBase64Content decodes base64-encoded content from the GitHub contents API.
|
|
// GitHub returns base64 content with line breaks for formatting; we strip \r and \n before decoding.
|
|
func decodeBase64Content(encoded string) (string, error) {
|
|
// GitHub inserts newlines in base64 content
|
|
cleaned := strings.NewReplacer("\n", "", "\r", "").Replace(encoded)
|
|
decoded, err := base64.StdEncoding.DecodeString(cleaned)
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
return string(decoded), nil
|
|
}
|