Files
review-bot/github/files.go
T
aweiker 921599542d
PR Ready Gate / clear-labels (pull_request) Successful in 2s
CI / test (pull_request) Successful in 21s
CI / review (anthropic--claude-4.6-sonnet, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 34s
CI / review (gpt-5, security, ., rodin/security-patterns, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m6s
CI / review (gpt-5, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 2m53s
feat(github): implement FileReader interface (#80)
Implement FileReader conformance on the GitHub client: GetFileContent,
ListContents, path helpers, base64 decode. Includes compile-time
conformance checks for both PRReader and FileReader.

Requires PR B (#102). Part 3 of 3 for #80.
2026-05-13 05:33:30 +00:00

161 lines
5.6 KiB
Go

package github
import (
"context"
"encoding/base64"
"encoding/json"
"fmt"
"net/url"
"path"
"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, filePath, ref string) (string, error) {
return c.GetFileContentAtRef(ctx, owner, repo, filePath, ref)
}
// GetFileContentAtRef fetches a file at a specific ref from a repo.
// If ref is empty, the query parameter is omitted (uses default branch).
//
// Returns an error if the path contains dot-segments (".", "..") or
// attempts to traverse above the repository root.
func (c *Client) GetFileContentAtRef(ctx context.Context, owner, repo, filePath, ref string) (string, error) {
escaped, err := escapePath(filePath)
if err != nil {
return "", fmt.Errorf("invalid file path: %w", err)
}
reqURL := fmt.Sprintf("%s/repos/%s/%s/contents/%s",
c.baseURL, url.PathEscape(owner), url.PathEscape(repo), escaped)
if ref != "" {
reqURL += "?ref=" + url.QueryEscape(ref)
}
body, err := c.doGet(ctx, reqURL)
if err != nil {
return "", fmt.Errorf("fetch file %s: %w", filePath, 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, filePath)
}
decoded, err := decodeBase64Content(resp.Content)
if err != nil {
return "", fmt.Errorf("decode base64 content for %s: %w", filePath, 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.
func (c *Client) ListContents(ctx context.Context, owner, repo, filePath string) ([]vcs.ContentEntry, error) {
escaped, err := escapePath(filePath)
if err != nil {
return nil, fmt.Errorf("invalid file path: %w", err)
}
reqURL := fmt.Sprintf("%s/repos/%s/%s/contents/%s",
c.baseURL, url.PathEscape(owner), url.PathEscape(repo), escaped)
body, err := c.doGet(ctx, reqURL)
if err != nil {
return nil, fmt.Errorf("list contents %s: %w", filePath, 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: %v; 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 validates and encodes a slash-separated file path for use in
// GitHub API URLs. Returns an error if the path contains dot-segments ("."
// or "..") or resolves to a path outside the repository root.
func escapePath(p string) (string, error) {
// Reject paths containing dot-segments rather than silently rewriting them.
for _, seg := range strings.Split(p, "/") {
if seg == "." || seg == ".." {
return "", fmt.Errorf("path contains dot-segment %q: %s", seg, p)
}
}
// Use path.Clean for canonical form, then verify it doesn't escape root.
cleaned := path.Clean(p)
if cleaned == "." || strings.HasPrefix(cleaned, "..") {
return "", fmt.Errorf("path resolves outside repository root: %s", p)
}
// Encode each segment individually.
parts := strings.Split(cleaned, "/")
var encoded []string
for _, part := range parts {
if part == "" {
continue
}
encoded = append(encoded, url.PathEscape(part))
}
return strings.Join(encoded, "/"), nil
}
// maxFileContentSize is the maximum decoded file size (10 MB) to prevent
// resource exhaustion when decoding base64 content from the API.
const maxFileContentSize = 10 * 1024 * 1024
// 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.
// Returns an error if the decoded content exceeds maxFileContentSize.
func decodeBase64Content(encoded string) (string, error) {
cleaned := strings.NewReplacer("\n", "", "\r", "").Replace(encoded)
// Check estimated decoded size before allocating.
// Base64 encodes 3 bytes into 4 chars, so decoded ~ len*3/4.
if len(cleaned)*3/4 > maxFileContentSize {
return "", fmt.Errorf("file content too large: estimated %d bytes exceeds limit of %d", len(cleaned)*3/4, maxFileContentSize)
}
decoded, err := base64.StdEncoding.DecodeString(cleaned)
if err != nil {
return "", err
}
if len(decoded) > maxFileContentSize {
return "", fmt.Errorf("file content too large: %d bytes exceeds limit of %d", len(decoded), maxFileContentSize)
}
return string(decoded), nil
}