diff --git a/AGENTS.md b/AGENTS.md index 6382595..404a758 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -41,7 +41,8 @@ bin/chats/ sync.go import.go facts.go apply.go; libs in internal/chats bin/mail/ sync.go import.go (index_mail → brain/index.go) bin/markdown/ import.go (mistune leafs) bin/postgres/ query.go (read-only YAML) -internal/ shared Go (brain/rank is cgo-free; chats parsers too) +bin/git/ import.go (go-git history; Python shim execs it) +internal/ shared Go (brain/rank is cgo-free; chats parsers; gitlog) bin/watch/ corpus watcher (used by bin/brain/watch.go) bin/tools/ vendored python libs behind bin/* (kblib, yamlout, websearch) bin/docker-entrypoint container entrypoint (brain index|search|serve|watch) @@ -81,6 +82,7 @@ bin/kb/search "query" [--repo X] # deprecated wrapper → bin/b bin/brain/search.go "query" [--root facts|info] # deduction search → YAML bin/brain/get.go [--body] bin/markdown/import.go [dir] # mistune leaves → YAML +bin/git/import.go [REPO] [--json] [--limit N] # go-git history → commit leafs bin/postgres/query.go --profile onlyoffice -c 'SELECT 1' bin/md/tables # what the graph holds → YAML bin/brain/deduce "question" # thinking wrapper diff --git a/PLAN.md b/PLAN.md index 666245c..4f4052d 100644 --- a/PLAN.md +++ b/PLAN.md @@ -42,6 +42,7 @@ detective method: **a fact needs ≥2 independent sources or it is | D16 | contradictions | ≥2 yes vs ≥2 no → unrelated sources conflict → hypothesis → `(not confirmed)`. Resolution (authority, staleness adjudication) = **v2**, tracked as open question. | | D17 | assertion gate | Fact-check every *claim* (facts → info → live sources → web), not every edit. Missing graph ≠ “does not exist”. | | D18 | reasoner | Pluggable OpenAI-compatible URL. RAM: Qwen3.5-9B. Quality: Bonsai-27B or Qwen3.6-27B. No official Qwen3.6-9B. | +| D19 | git history | [go-git](https://github.com/go-git/go-git) via `bin/git/import.go`. No subprocess of the git binary. Conversion prints commit leafs; brain write is `bin/brain/index.go`. | ## Architecture @@ -61,6 +62,7 @@ detective method: **a fact needs ≥2 independent sources or it is mail/import.go JSON → markdown (no brain write) markdown/import.go mistune leaves postgres/query.go read-only YAML (wraps bin/db/psql-yq) + git/import.go go-git history (no git binary; conversion only) chats/sync.go import.go facts.go apply.go (libs in internal/chats; no chats index) md/import (deprecated; bin/markdown/import.go) diff --git a/README.md b/README.md index ce46bad..6a92435 100644 --- a/README.md +++ b/README.md @@ -95,6 +95,15 @@ bin/brain/eval.go # recall@5 gate `--hop` is not implemented (needs File/FROM_FILE edges); the flag errors instead of walking. `bin/kb/search` is a deprecated wrapper around `bin/brain/search.go`. +Git history is read with [go-git](https://github.com/go-git/go-git) (no git binary): + +```bash +bin/git/import.go --json --limit 100 # commit leafs for this repo +bin/git/import.go --root "$PROJECTS_ROOT" --json # one pass per .git under root +``` + +Conversion only. Graph write (`File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person`) stays with `bin/brain/index.go`. + Mail is a first-class corpus (retrievable through the same search): ```bash diff --git a/bin/git/import b/bin/git/import index 7f5caa1..2fbb7d8 100755 --- a/bin/git/import +++ b/bin/git/import @@ -1,154 +1,26 @@ #!/usr/bin/env python3 -"""git/import - import git history (commits, authors, files) into the brain. +"""git/import — deprecated. Use bin/git/import.go (go-git, no git binary). - bin/git/import [REPO] import all commits -> leafs + graph - bin/git/import --json emit import leafs as JSON, no write - bin/git/import --limit 100 cap commits processed - bin/git/import --since 2026-01-01 only recent commits - bin/git/import --root DIR run per repo dir under DIR - bin/git/import --no-env never read .env anywhere (default: true) - -Reads `git log --no-merges --name-only` from the repo, maps commits to -`info` leafs (root=info, type=commit) and writes the version graph -`File -[:HAS_VERSION]-> Commit -[:AUTHORED]-> Person` into var/kb.lbug. -Idempotent: leaf MERGE by (source,text via leaf_id), graph MERGE by sha. + bin/git/import.go [REPO] [--json] [--limit N] [--since DATE] """ from __future__ import annotations -import json -import subprocess +import os import sys from pathlib import Path ROOT = Path(__file__).resolve().parents[2] -sys.path.insert(0, str(ROOT / "bin" / "tools")) - -from kblib import ( # noqa: E402 - connect, ensure_indexes, init_schema, upsert_leaf, -) -from gitimport import commits_to_leafs, ensure_git_schema, index_commits, parse_log # noqa: E402 - -LOG_FMT = "--format=%x1e%H%x1f%an%x1f%ae%x1f%aI%x1f%s" - - -def git_log(repo: Path, limit: int = 0, since: str = "") -> str: - cmd = ["git", "-C", str(repo), "log", "--no-merges", "--name-only", LOG_FMT] - if since: - cmd += ["--since", since] - if limit: - cmd += ["-n", str(limit)] - try: - out = subprocess.run(cmd, capture_output=True, text=True, timeout=120) - except (FileNotFoundError, subprocess.TimeoutExpired): - return "" - if out.returncode != 0: - print(f"git/import: {repo}: {out.stderr.strip()}", file=sys.stderr) - return "" - return out.stdout - - -def repo_name(repo: Path) -> str: - try: - out = subprocess.run( - ["git", "-C", str(repo), "remote", "get-url", "origin"], - capture_output=True, text=True, timeout=20) - url = out.stdout.strip() - return url.rstrip("/").split("/")[-1].removesuffix(".git") if url else repo.name - except (FileNotFoundError, subprocess.TimeoutExpired): - return repo.name - - -def embedder(): - from model2vec import StaticModel - model = StaticModel.from_pretrained("minishlab/potion-multilingual-128M") - return lambda text: model.encode([text])[0].astype(float).tolist() - - -def import_repo(conn, repo: Path, embed, limit: int, since: str, - no_write: bool = False) -> tuple[int, int]: - raw = git_log(repo, limit, since) - commits = parse_log(raw) - leafs = commits_to_leafs(commits, repo_name(repo)) - if no_write: - return len(commits), 0 - written = 0 - for lf in leafs: - query = f"{lf['heading']}\n\n{lf['text']}" - emb = embed(lf["text"]) if lf["text"] else None - upsert_leaf(conn, text=query, root="info", confidence="confirmed", - source=lf["source"], source_rev="git", how="git/import", - loc=lf["source"], type_=lf.get("type", "commit"), - embedding=emb) - written += 1 - index_commits(conn, commits, repo_name(repo)) - return len(commits), written def main(argv: list[str]) -> int: - import argparse - p = argparse.ArgumentParser(description="import git history into the brain") - p.add_argument("repo", nargs="?", default=None) - p.add_argument("--root", default=None, help="directory of repos to import (each git dir separately)") - p.add_argument("--limit", type=int, default=0) - p.add_argument("--since", default="") - p.add_argument("--json", action="store_true") - p.add_argument("--dry-run", action="store_true", help="parse + report, no db write") - a = p.parse_args(argv) - - repos: list[Path] = [] - if a.repo: - repos = [Path(a.repo)] - elif a.root: - root = Path(a.root) - if root.is_file(): - repos = [root] - else: - repos = [dp for dp in sorted(root.iterdir()) if (dp / ".git").exists() or dp.is_file()] - else: - repos = [ROOT] - - total_commits = 0 - results: list[dict] = [] - if a.dry_run: - for repo in repos: - if not repo.exists(): - continue - commits = parse_log(git_log(repo, a.limit, a.since)) - name = repo_name(repo) - total_commits += len(commits) - results.append({"repo": name, "commits": len(commits), - "leafs": len(commits_to_leafs(commits, name)), "path": str(repo)}) - if a.json: - print(json.dumps(results, indent=2)) - else: - for r in results: - print(f"{r['repo']:<24} {r['commits']:>5} commits -> {r['leafs']} leafs {r['path']}") - return 0 - - # Never DROP FTS/VECTOR (ghost catalog). Upsert while indexes exist is OK; - # ensure_indexes only CREATEs when missing. - db, conn = connect(ROOT / "var" / "kb.lbug", read_only=False) - init_schema(conn) - embed = embedder() - rows: list[dict] = [] - for repo in repos: - if not repo.exists(): - continue - reached, written = import_repo(conn, repo, embed, a.limit, a.since) - total_commits += reached - rows.append({"repo": repo_name(repo), "commits": reached, "written": written}) - ensure_indexes(conn) - conn.close() - db.close() - - if a.json: - print(json.dumps(rows, indent=2)) - else: - for r in rows: - print(f"imported {r['commits']:>5} commits -> {r['written']} leafs {r['repo']}") - print(f"total: {total_commits} commits") - return 0 + print( + "bin/git/import is deprecated; use bin/git/import.go (go-git)", + file=sys.stderr, + ) + target = ROOT / "bin" / "git" / "import.go" + os.execvp("go", ["go", "run", str(target), *argv]) + return 1 if __name__ == "__main__": - sys.exit(main(sys.argv[1:])) \ No newline at end of file + sys.exit(main(sys.argv[1:])) diff --git a/bin/git/import.go b/bin/git/import.go new file mode 100755 index 0000000..8ea339e --- /dev/null +++ b/bin/git/import.go @@ -0,0 +1,143 @@ +//usr/bin/env go run "$0" "$@"; exit +// +// bin/git/import.go - read git history with go-git (no git binary). +// +// ./bin/git/import.go [REPO] +// ./bin/git/import.go --json +// ./bin/git/import.go --limit 100 --since 2026-01-01 +// ./bin/git/import.go --root DIR +// +// Conversion only: prints commit leafs. Brain write is bin/brain/index.go. +// NOTE: never run `gofmt -w` on this file — it breaks the shebang. +package main + +import ( + "encoding/json" + "fmt" + "os" + "path/filepath" + "strconv" + "time" + + "github.com/eSlider/2dph/internal/cmdbin" + "github.com/eSlider/2dph/internal/gitlog" +) + +func main() { + os.Exit(run(os.Args[1:])) +} + +func run(args []string) int { + var repo, root, since string + limit := 0 + jsonOut := false + i := 0 + for i < len(args) { + a := args[i] + switch { + case a == "--json": + jsonOut = true + case a == "--limit" && i+1 < len(args): + i++ + n, err := strconv.Atoi(args[i]) + if err != nil || n < 0 { + fmt.Fprintf(os.Stderr, "git/import: --limit must be a non-negative integer\n") + return 2 + } + limit = n + case a == "--since" && i+1 < len(args): + i++ + since = args[i] + case a == "--root" && i+1 < len(args): + i++ + root = args[i] + case a == "-h" || a == "--help": + fmt.Fprintln(os.Stderr, `usage: bin/git/import.go [REPO] [--json] [--limit N] [--since DATE] [--root DIR]`) + return 0 + case len(a) > 0 && a[0] != '-': + repo = a + default: + fmt.Fprintf(os.Stderr, "git/import: unknown flag %s\n", a) + return 2 + } + i++ + } + + var sinceT time.Time + if since != "" { + var err error + sinceT, err = parseSince(since) + if err != nil { + fmt.Fprintf(os.Stderr, "git/import: %v\n", err) + return 2 + } + } + + repos := []string{} + if repo != "" { + repos = []string{repo} + } else if root != "" { + entries, err := os.ReadDir(root) + if err != nil { + fmt.Fprintf(os.Stderr, "git/import: %v\n", err) + return 1 + } + for _, e := range entries { + p := filepath.Join(root, e.Name()) + if _, err := os.Stat(filepath.Join(p, ".git")); err == nil { + repos = append(repos, p) + } + } + } else { + repos = []string{cmdbin.Root()} + } + + opt := gitlog.Options{Limit: limit, Since: sinceT} + type row struct { + Repo string `json:"repo"` + Path string `json:"path"` + Commits int `json:"commits"` + Leafs []gitlog.Leaf `json:"leafs,omitempty"` + } + var rows []row + for _, p := range repos { + name, err := gitlog.RepoName(p) + if err != nil && name == "" { + fmt.Fprintf(os.Stderr, "git/import: %s: %v\n", p, err) + continue + } + cs, err := gitlog.Log(p, opt) + if err != nil { + fmt.Fprintf(os.Stderr, "git/import: %s: %v\n", p, err) + return 1 + } + leafs := make([]gitlog.Leaf, 0, len(cs)) + for _, c := range cs { + leafs = append(leafs, gitlog.ToLeaf(c, name)) + } + rows = append(rows, row{Repo: name, Path: p, Commits: len(cs), Leafs: leafs}) + } + + if jsonOut { + enc := json.NewEncoder(os.Stdout) + enc.SetIndent("", " ") + enc.SetEscapeHTML(false) + if err := enc.Encode(rows); err != nil { + return 1 + } + return 0 + } + for _, r := range rows { + fmt.Printf("%-24s %5d commits %s\n", r.Repo, r.Commits, r.Path) + } + return 0 +} + +func parseSince(s string) (time.Time, error) { + for _, layout := range []string{time.RFC3339, "2006-01-02"} { + if t, err := time.Parse(layout, s); err == nil { + return t, nil + } + } + return time.Time{}, fmt.Errorf("cannot parse --since %q", s) +} diff --git a/bin/tools/gitimport.py b/bin/tools/gitimport.py index 6c71780..0409e88 100644 --- a/bin/tools/gitimport.py +++ b/bin/tools/gitimport.py @@ -1,21 +1,12 @@ -"""gitimport - parse `git log` output and turn commits into brain leafs. +"""gitimport - Ladybug graph writes for Commit/File/Person (no git binary). -Pure, testable functions. Field grammar (see bin/git/import): - - git log --no-merges --name-only \ - --format='%x1e%H%x1f%an%x1f%ae%x1f%aI%x1f%s' - - 0x1e = record separator, 0x1f = field separator. - Files: newline-separated lines following each record's subject. +Commit records come from bin/git/import.go (go-git). This module only MERGEs +the version graph File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person. """ - from __future__ import annotations from dataclasses import dataclass, field -REC_SEP = "\x1e" -FIELD_SEP = "\x1f" - @dataclass class Commit: @@ -26,54 +17,6 @@ class Commit: subject: str files: list[str] = field(default_factory=list) - def leaf_text(self, repo: str) -> str: - head = f"commit {self.sha[:12]} in {repo} — {self.subject}" - body = [head, f"Author: {self.author} <{self.email}>", f"Date: {self.date}"] - if self.files: - body.append("Changing: " + ", ".join(self.files)) - return "\n".join(body) - - -def parse_log(text: str) -> list[Commit]: - """Parse `git log` output into Commit records. - - Records are separated by 0x1e. A record is fields joined by 0x1f, - followed by optional newline-separated file paths inside the next - segment (git emits blank line + files after each record). - """ - commits: list[Commit] = [] - # field records and file lists alternate; simpler: split on REC_SEP, - # each chunk = header line, possibly followed by newline + files. - for chunk in text.split(REC_SEP): - chunk = chunk.strip("\n") - if not chunk: - continue - lines = chunk.split("\n", 1) - header = lines[0].split(FIELD_SEP) - if len(header) < 5: - continue - sha, author, email, date, subject = header[:5] - files = [ln.strip() for ln in lines[1].splitlines() if ln.strip()] if len(lines) > 1 else [] - commits.append(Commit(sha=sha, author=author, email=email, - date=date, subject=subject, files=files)) - return commits - - -def commits_to_leafs(commits: list[Commit], repo: str) -> list[dict]: - """Map commits to the leaf shape bin/kb/index expects (source/repo/...).""" - out: list[dict] = [] - for c in commits: - out.append({ - "source": f"{repo}@{c.sha}", - "repo": repo, - "heading": f"commit {c.sha[:12]} — {c.subject}", - "text": c.leaf_text(repo), - "type": "commit", - "status": "current", - "related": ",".join(c.files), - }) - return out - GIT_SCHEMA = ( "CREATE NODE TABLE IF NOT EXISTS Commit (id STRING, repo STRING, subject STRING, " @@ -114,4 +57,4 @@ def index_commits(conn, commits: list[Commit], repo: str) -> int: conn.execute("MATCH (f:File {id:$fid}), (c:Commit {id:$sha}) " "MERGE (f)-[:HAS_VERSION]->(c)", parameters={"fid": f"{repo}:{path}", "sha": c.sha}) - return len(commits) \ No newline at end of file + return len(commits) diff --git a/bin/tools/test_bin_layout.py b/bin/tools/test_bin_layout.py index 4f3deff..b239dfb 100644 --- a/bin/tools/test_bin_layout.py +++ b/bin/tools/test_bin_layout.py @@ -91,3 +91,26 @@ class BinLayoutTest(unittest.TestCase): def test_postgres_query_is_shebang(self) -> None: self._assert_shebang("bin/postgres/query.go") + + def test_git_import_is_gogit_shebang(self) -> None: + self._assert_shebang("bin/git/import.go") + py = (ROOT / "bin" / "git" / "import").read_text() + self.assertNotIn( + '["git"', + py, + "Python git/import must not subprocess the git binary", + ) + self.assertIn("bin/git/import.go", py) + + def test_gitimport_py_has_no_git_binary(self) -> None: + py = (ROOT / "bin" / "tools" / "gitimport.py").read_text() + self.assertNotIn("subprocess", py) + self.assertNotIn("git log", py) + + def test_gogit_is_direct_go_mod_require(self) -> None: + text = (ROOT / "go.mod").read_text() + first = text.split("require (")[1].split(")")[0] + self.assertRegex(first, r"github.com/go-git/go-git/v5\s+v") + for line in first.splitlines(): + if "go-git/go-git" in line: + self.assertNotIn("indirect", line) diff --git a/bin/tools/test_gitgraph.py b/bin/tools/test_gitgraph.py index a5a19eb..9172e79 100644 --- a/bin/tools/test_gitgraph.py +++ b/bin/tools/test_gitgraph.py @@ -9,12 +9,6 @@ sys.path.insert(0, str(Path(__file__).resolve().parent)) import kblib # noqa: E402 import gitimport # noqa: E402 -SAMPLE = ( - "\x1e" + "a1b2c3d" + "\x1f" + "Ada Lovelace" + "\x1f" + "ada@example.com" - + "\x1f" + "2026-08-10T12:00:00+01:00" + "\x1f" + "feat: first commit" - + "\n\nREADME.md\nsrc/main.c\n" -) - COMMIT_PERSON_SCHEMA = ( "CREATE NODE TABLE IF NOT EXISTS Commit (id STRING, repo STRING, subject STRING, " "author STRING, email STRING, date STRING, PRIMARY KEY(id))" @@ -26,6 +20,17 @@ HAS_VERSION_SCHEMA = "CREATE REL TABLE IF NOT EXISTS HAS_VERSION (FROM File TO C AUTHORED_SCHEMA = "CREATE REL TABLE IF NOT EXISTS AUTHORED (FROM Commit TO Person)" +def sample_commit() -> gitimport.Commit: + return gitimport.Commit( + sha="a1b2c3d", + author="Ada Lovelace", + email="ada@example.com", + date="2026-08-10T12:00:00+01:00", + subject="feat: first commit", + files=["README.md", "src/main.c"], + ) + + class GitGraphTest(unittest.TestCase): def setUp(self): self.dir = tempfile.mkdtemp() @@ -42,14 +47,12 @@ class GitGraphTest(unittest.TestCase): self.db.close() def test_index_commits_creates_nodes_and_edges(self): - cs = gitimport.parse_log(SAMPLE) - gitimport.index_commits(self.conn, cs, "sample-repo") + gitimport.index_commits(self.conn, [sample_commit()], "sample-repo") rp = self.conn.execute("MATCH (p:Person) RETURN p.name, p.email").get_all() self.assertEqual([tuple(r) for r in rp], [("Ada Lovelace", "ada@example.com")]) rc = self.conn.execute("MATCH (c:Commit) RETURN c.id, c.repo").get_all() self.assertEqual(len(rc), 1) self.assertEqual(rc[0][1], "sample-repo") - # File -[:HAS_VERSION]-> Commit -[:AUTHORED]-> Person rf = self.conn.execute( "MATCH (f:File)-[:HAS_VERSION]->(c:Commit)-[:AUTHORED]->(p:Person) " "RETURN f.path, c.id, p.email").get_all() @@ -58,7 +61,7 @@ class GitGraphTest(unittest.TestCase): self.assertTrue(all(r[2] == "ada@example.com" for r in rf)) def test_index_commits_idempotent(self): - cs = gitimport.parse_log(SAMPLE) + cs = [sample_commit()] gitimport.index_commits(self.conn, cs, "sample-repo") gitimport.index_commits(self.conn, cs, "sample-repo") n = self.conn.execute("MATCH (c:Commit) RETURN count(*)").get_all()[0][0] @@ -68,4 +71,4 @@ class GitGraphTest(unittest.TestCase): if __name__ == "__main__": - unittest.main() \ No newline at end of file + unittest.main() diff --git a/bin/tools/test_gitimport.py b/bin/tools/test_gitimport.py deleted file mode 100644 index 14d8883..0000000 --- a/bin/tools/test_gitimport.py +++ /dev/null @@ -1,57 +0,0 @@ -import sys -import unittest -from pathlib import Path - -sys.path.insert(0, str(Path(__file__).resolve().parent)) - -import gitimport # noqa: E402 - -SAMPLE = ( - "\x1e" + "a1b2c3d" + "\x1f" + "Ada Lovelace" + "\x1f" + "ada@example.com" - + "\x1f" + "2026-08-10T12:00:00+01:00" + "\x1f" + "feat: first commit" - + "\n\nREADME.md\nsrc/main.c\n" - + "\x1e" + "e4f5a6b" + "\x1f" + "Bob Babbage" + "\x1f" + "bob@example.com" - + "\x1f" + "2026-08-11T09:30:00+01:00" + "\x1f" + "fix: typo" - + "\n\ndocs/notes.md" -) - - -class GitparseTest(unittest.TestCase): - def test_parses_records(self): - cs = gitimport.parse_log(SAMPLE) - self.assertEqual(len(cs), 2) - - def test_parses_commit_fields(self): - cs = gitimport.parse_log(SAMPLE) - c = cs[0] - self.assertEqual(c.sha, "a1b2c3d") - self.assertEqual(c.author, "Ada Lovelace") - self.assertEqual(c.email, "ada@example.com") - self.assertEqual(c.date, "2026-08-10T12:00:00+01:00") - self.assertEqual(c.subject, "feat: first commit") - - def test_parses_changed_files(self): - cs = gitimport.parse_log(SAMPLE) - self.assertEqual(cs[0].files, ["README.md", "src/main.c"]) - self.assertEqual(cs[1].files, ["docs/notes.md"]) - - def test_ignores_empty(self): - self.assertEqual(gitimport.parse_log(""), []) - - def test_skip_malformed_record(self): - self.assertEqual(gitimport.parse_log("\x1eweird\x1e"), []) - - def test_commit_leaf_shape(self): - leafs = gitimport.commits_to_leafs(gitimport.parse_log(SAMPLE), "sample-repo") - self.assertEqual(len(leafs), 2) - lf = leafs[0] - self.assertEqual(lf["type"], "commit") - self.assertEqual(lf["repo"], "sample-repo") - self.assertEqual(lf["source"], "sample-repo@a1b2c3d") - self.assertIn("Ada Lovelace", lf["text"]) - self.assertIn("README.md", lf["related"]) - self.assertIn("feat: first commit", lf["heading"]) - - -if __name__ == "__main__": - unittest.main() \ No newline at end of file diff --git a/bin/tools/test_published_docs.py b/bin/tools/test_published_docs.py index 02dca93..ef4408f 100644 --- a/bin/tools/test_published_docs.py +++ b/bin/tools/test_published_docs.py @@ -39,6 +39,12 @@ class PublishedDocsTest(unittest.TestCase): "mail index is a brain write; README must name bin/brain/index.go", ) + def test_readme_git_import_is_gogit(self) -> None: + text = (ROOT / "README.md").read_text() + self.assertIn("bin/git/import.go", text) + self.assertIn("go-git", text) + self.assertIn("D19", (ROOT / "PLAN.md").read_text()) + def test_docs_do_not_claim_hop_walks(self) -> None: paths = [ ROOT / "README.md", diff --git a/docs/design.md b/docs/design.md index 1de4020..8e330e5 100644 --- a/docs/design.md +++ b/docs/design.md @@ -46,7 +46,8 @@ Every assertion edge carries: Content leafs: `sha256`, `observed_at`, `source_rev`, `confidence`. Stale = a file changed on disk (git HEAD/mtime) after its last observed `source_rev`. `File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person` records the history of every -content leaf. +content leaf. Commit records come from `bin/git/import.go` (go-git, no git +binary); conversion prints leafs, brain write is `bin/brain/index.go`. `bin/facts/audit stale` flags leafs whose observed revision is behind the corpus HEAD. diff --git a/go.mod b/go.mod index 79ccecf..0a8e6a7 100644 --- a/go.mod +++ b/go.mod @@ -7,19 +7,38 @@ require ( github.com/arran4/golang-ical v0.3.5 github.com/chewxy/math32 v1.11.2 github.com/daulet/tokenizers v1.27.0 + github.com/go-git/go-git/v5 v5.19.2 golang.org/x/text v0.40.0 ) require ( + dario.cat/mergo v1.0.0 // indirect + github.com/Microsoft/go-winio v0.6.2 // indirect + github.com/ProtonMail/go-crypto v1.1.6 // indirect github.com/apache/arrow-go/v18 v18.6.0 // indirect + github.com/cloudflare/circl v1.6.3 // indirect + github.com/cyphar/filepath-securejoin v0.6.1 // indirect + github.com/emirpasic/gods v1.18.1 // indirect + github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect + github.com/go-git/go-billy/v5 v5.9.0 // indirect github.com/goccy/go-json v0.10.6 // indirect + github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 // indirect github.com/google/flatbuffers v25.12.19+incompatible // indirect github.com/google/uuid v1.6.0 // indirect + github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect + github.com/kevinburke/ssh_config v1.2.0 // indirect github.com/klauspost/compress v1.18.5 // indirect github.com/klauspost/cpuid/v2 v2.3.0 // indirect github.com/pierrec/lz4/v4 v4.1.26 // indirect + github.com/pjbgf/sha1cd v0.6.0 // indirect + github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 // indirect github.com/shopspring/decimal v1.4.0 // indirect + github.com/skeema/knownhosts v1.3.1 // indirect + github.com/xanzy/ssh-agent v0.3.3 // indirect github.com/zeebo/xxh3 v1.1.0 // indirect - golang.org/x/exp v0.0.0-20260112195511-716be5621a96 // indirect - golang.org/x/sys v0.43.0 // indirect + golang.org/x/crypto v0.53.0 // indirect + golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f // indirect + golang.org/x/net v0.56.0 // indirect + golang.org/x/sys v0.46.0 // indirect + gopkg.in/warnings.v0 v0.1.2 // indirect ) diff --git a/go.sum b/go.sum index e7bf4ab..0bee964 100644 --- a/go.sum +++ b/go.sum @@ -1,50 +1,138 @@ +dario.cat/mergo v1.0.0 h1:AGCNq9Evsj31mOgNPcLyXc+4PNABt905YmuqPYYpBWk= +dario.cat/mergo v1.0.0/go.mod h1:uNxQE+84aUszobStD9th8a29P2fMDhsBdgRYvZOxGmk= github.com/LadybugDB/go-ladybug v0.17.0 h1:RXDbkBjrbRmLdEbhGl4CLOIEzSt09gbP0n9UbKDEfwI= github.com/LadybugDB/go-ladybug v0.17.0/go.mod h1:GeIXmE8XyF5TFS94NAuTag7vgCC+no/HTBMRA6Rd5Cs= +github.com/Microsoft/go-winio v0.5.2/go.mod h1:WpS1mjBmmwHBEWmogvA2mj8546UReBk4v8QkMxJ6pZY= +github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY= +github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU= +github.com/ProtonMail/go-crypto v1.1.6 h1:ZcV+Ropw6Qn0AX9brlQLAUXfqLBc7Bl+f/DmNxpLfdw= +github.com/ProtonMail/go-crypto v1.1.6/go.mod h1:rA3QumHc/FZ8pAHreoekgiAbzpNsfQAosU5td4SnOrE= github.com/andybalholm/brotli v1.2.1 h1:R+f5xP285VArJDRgowrfb9DqL18yVK0gKAW/F+eTWro= github.com/andybalholm/brotli v1.2.1/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY= +github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be h1:9AeTilPcZAjCFIImctFaOjnTIavg87rW78vTPkQqLI8= +github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be/go.mod h1:ySMOLuWl6zY27l47sB3qLNK6tF2fkHG55UZxx8oIVo4= github.com/apache/arrow-go/v18 v18.6.0 h1:GX/Jyd3R7mCLiECAwY9FWbbaYblie2WXBSz4Sw8fNpM= github.com/apache/arrow-go/v18 v18.6.0/go.mod h1:gm3MiPpY82fLYK5VKPB3WoJbsiLVDfT7flD5/vHReKw= github.com/apache/thrift v0.22.0 h1:r7mTJdj51TMDe6RtcmNdQxgn9XcyfGDOzegMDRg47uc= github.com/apache/thrift v0.22.0/go.mod h1:1e7J/O1Ae6ZQMTYdy9xa3w9k+XHWPfRvdPyJeynQ+/g= +github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5 h1:0CwZNZbxp69SHPdPJAN/hZIm0C4OItdklCFmMRWYpio= +github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5/go.mod h1:wHh0iHkYZB8zMSxRWpUBQtwG5a7fFgvEO+odwuTv2gs= github.com/arran4/golang-ical v0.3.5 h1:bbz6ld4dC+MmCKiFfOd6SkmIGnhNMBACZ485ULh7p9A= github.com/arran4/golang-ical v0.3.5/go.mod h1:OnguFgjN0Hmx8jzpmWcC+AkHio94ujmLHKoaef7xQh8= github.com/chewxy/math32 v1.11.2 h1:IufN08Zwr1NKuWfY+4Tz55BcwKmyKKNdOP7KtumehnM= github.com/chewxy/math32 v1.11.2/go.mod h1:dOB2rcuFrCn6UHrze36WSLVPKtzPMRAQvBvUwkSsLqs= +github.com/cloudflare/circl v1.6.3 h1:9GPOhQGF9MCYUeXyMYlqTR6a5gTrgR/fBLXvUgtVcg8= +github.com/cloudflare/circl v1.6.3/go.mod h1:2eXP6Qfat4O/Yhh8BznvKnJ+uzEoTQ6jVKJRn81BiS4= +github.com/cyphar/filepath-securejoin v0.6.1 h1:5CeZ1jPXEiYt3+Z6zqprSAgSWiggmpVyciv8syjIpVE= +github.com/cyphar/filepath-securejoin v0.6.1/go.mod h1:A8hd4EnAeyujCJRrICiOWqjS1AX0a9kM5XL+NwKoYSc= github.com/daulet/tokenizers v1.27.0 h1:MmFYAEDFz69s/nNQfHg59DWqHz3v94m99kEZ/JbL+s4= github.com/daulet/tokenizers v1.27.0/go.mod h1:YjFY1o1HGMyWkQgbXJDghhvke/yFDp2vGdIO2hYs4MQ= +github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM= github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/elazarl/goproxy v1.7.2 h1:Y2o6urb7Eule09PjlhQRGNsqRfPmYI3KKQLFpCAV3+o= +github.com/elazarl/goproxy v1.7.2/go.mod h1:82vkLNir0ALaW14Rc399OTTjyNREgmdL2cVoIbS6XaE= +github.com/emirpasic/gods v1.18.1 h1:FXtiHYKDGKCW2KzwZKx0iC0PQmdlorYgdFG9jPXJ1Bc= +github.com/emirpasic/gods v1.18.1/go.mod h1:8tpGGwCnJ5H4r6BWwaV6OrWmMoPhUl5jm/FMNAnJvWQ= +github.com/gliderlabs/ssh v0.3.8 h1:a4YXD1V7xMF9g5nTkdfnja3Sxy1PVDCj1Zg4Wb8vY6c= +github.com/gliderlabs/ssh v0.3.8/go.mod h1:xYoytBv1sV0aL3CavoDuJIQNURXkkfPA/wxQ1pL1fAU= +github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 h1:+zs/tPmkDkHx3U66DAb0lQFJrpS6731Oaa12ikc+DiI= +github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376/go.mod h1:an3vInlBmSxCcxctByoQdvwPiA7DTK7jaaFDBTtu0ic= +github.com/go-git/go-billy/v5 v5.9.0 h1:jItGXszUDRtR/AlferWPTMN4j38BQ88XnXKbilmmBPA= +github.com/go-git/go-billy/v5 v5.9.0/go.mod h1:jCnQMLj9eUgGU7+ludSTYoZL/GGmii14RxKFj7ROgHw= +github.com/go-git/go-git-fixtures/v4 v4.3.2-0.20231010084843-55a94097c399 h1:eMje31YglSBqCdIqdhKBW8lokaMrL3uTkpGYlE2OOT4= +github.com/go-git/go-git-fixtures/v4 v4.3.2-0.20231010084843-55a94097c399/go.mod h1:1OCfN199q1Jm3HZlxleg+Dw/mwps2Wbk9frAWm+4FII= +github.com/go-git/go-git/v5 v5.19.2 h1:wkfn7vOlUBu8ivAWKBWisTiwJK4jYHzTF8Ndv1LyGqY= +github.com/go-git/go-git/v5 v5.19.2/go.mod h1:QqCBE1EFN5ddFmrliLQ3/ntRCUjZU3EJuwuB/jWEHjk= github.com/goccy/go-json v0.10.6 h1:p8HrPJzOakx/mn/bQtjgNjdTcN+/S6FcG2CTtQOrHVU= github.com/goccy/go-json v0.10.6/go.mod h1:oq7eo15ShAhp70Anwd5lgX2pLfOS3QCiwU/PULtXL6M= +github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 h1:f+oWsMOmNPc8JmEHVZIycC7hBoQxHH9pNKQORJNozsQ= +github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8/go.mod h1:wcDNUvekVysuuOpQKo3191zZyTpiI6se1N1ULghS0sw= github.com/google/flatbuffers v25.12.19+incompatible h1:haMV2JRRJCe1998HeW/p0X9UaMTK6SDo0ffLn2+DbLs= github.com/google/flatbuffers v25.12.19+incompatible/go.mod h1:1AeVuKshWv4vARoZatz6mlQ0JxURH0Kv5+zNeJKJCa8= -github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI= -github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY= +github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8= +github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU= github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0= github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= +github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 h1:BQSFePA1RWJOlocH6Fxy8MmwDt+yVQYULKfN0RoTN8A= +github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99/go.mod h1:1lJo3i6rXxKeerYnT8Nvf0QmHCRC1n8sfWVwXF2Frvo= +github.com/kevinburke/ssh_config v1.2.0 h1:x584FjTGwHzMwvHx18PXxbBVzfnxogHaAReU4gf13a4= +github.com/kevinburke/ssh_config v1.2.0/go.mod h1:CT57kijsi8u/K/BOFA39wgDQJ9CxiF4nAY/ojJ6r6mM= github.com/klauspost/compress v1.18.5 h1:/h1gH5Ce+VWNLSWqPzOVn6XBO+vJbCNGvjoaGBFW2IE= github.com/klauspost/compress v1.18.5/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ= github.com/klauspost/cpuid/v2 v2.3.0 h1:S4CRMLnYUhGeDFDqkGriYKdfoFlDnMtqTiI/sFzhA9Y= github.com/klauspost/cpuid/v2 v2.3.0/go.mod h1:hqwkgyIinND0mEev00jJYCxPNVRVXFQeu1XKlok6oO0= +github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo= +github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE= +github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk= +github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ= +github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI= +github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY= +github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE= +github.com/onsi/gomega v1.34.1 h1:EUMJIKUjM8sKjYbtxQI9A4z2o+rruxnzNvpknOXie6k= +github.com/onsi/gomega v1.34.1/go.mod h1:kU1QgUvBDLXBJq618Xvm2LUX6rSAfRaFRTcdOeDLwwY= github.com/pierrec/lz4/v4 v4.1.26 h1:GrpZw1gZttORinvzBdXPUXATeqlJjqUG/D87TKMnhjY= github.com/pierrec/lz4/v4 v4.1.26/go.mod h1:EoQMVJgeeEOMsCqCzqFm2O0cJvljX2nGZjcRIPL34O4= +github.com/pjbgf/sha1cd v0.6.0 h1:3WJ8Wz8gvDz29quX1OcEmkAlUg9diU4GxJHqs0/XiwU= +github.com/pjbgf/sha1cd v0.6.0/go.mod h1:lhpGlyHLpQZoxMv8HcgXvZEhcGs0PG/vsZnEJ7H0iCM= +github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4= +github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= +github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U= github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= +github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ= +github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc= +github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 h1:n661drycOFuPLCN3Uc8sB6B/s6Z4t2xvBgU1htSHuq8= +github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3/go.mod h1:A0bzQcvG0E7Rwjx0REVgAGH58e96+X0MeOfepqsbeW4= github.com/shopspring/decimal v1.4.0 h1:bxl37RwXBklmTi0C79JfXCEBD1cqqHt0bbgBAGFp81k= github.com/shopspring/decimal v1.4.0/go.mod h1:gawqmDU56v4yIKSwfBSFip1HdCCXN8/+DMd9qYNcwME= +github.com/sirupsen/logrus v1.7.0/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0= +github.com/skeema/knownhosts v1.3.1 h1:X2osQ+RAjK76shCbvhHHHVl3ZlgDm8apHEHFqRjnBY8= +github.com/skeema/knownhosts v1.3.1/go.mod h1:r7KTdC8l4uxWRyK2TpQZ/1o5HaSzh06ePQNxPwTcfiY= +github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= +github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs= +github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4= github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U= github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U= +github.com/xanzy/ssh-agent v0.3.3 h1:+/15pJfg/RsTxqYcX6fHqOXZwwMP+2VyYWJeWM2qQFM= +github.com/xanzy/ssh-agent v0.3.3/go.mod h1:6dzNDKs0J9rVPHPhaGCukekBHKqfl+L3KghI1Bc68Uw= github.com/zeebo/assert v1.3.0 h1:g7C04CbJuIDKNPFHmsk4hwZDO5O+kntRxzaUoNXj+IQ= github.com/zeebo/assert v1.3.0/go.mod h1:Pq9JiuJQpG8JLJdtkwrJESF0Foym2/D9XMU5ciN/wJ0= github.com/zeebo/xxh3 v1.1.0 h1:s7DLGDK45Dyfg7++yxI0khrfwq9661w9EN78eP/UZVs= github.com/zeebo/xxh3 v1.1.0/go.mod h1:IisAie1LELR4xhVinxWS5+zf1lA4p0MW4T+w+W07F5s= -golang.org/x/exp v0.0.0-20260112195511-716be5621a96 h1:Z/6YuSHTLOHfNFdb8zVZomZr7cqNgTJvA8+Qz75D8gU= -golang.org/x/exp v0.0.0-20260112195511-716be5621a96/go.mod h1:nzimsREAkjBCIEFtHiYkrJyT+2uy9YZJB7H1k68CXZU= -golang.org/x/sys v0.43.0 h1:Rlag2XtaFTxp19wS8MXlJwTvoh8ArU6ezoyFsMyCTNI= -golang.org/x/sys v0.43.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw= +golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4= +golang.org/x/crypto v0.53.0 h1:QZ4Muo8THX6CizN2vPPd5fBGHyogrdK9fG4wLPFUsto= +golang.org/x/crypto v0.53.0/go.mod h1:DNLU434OwVakk9PzuwV8w62mAJpRJL3vsgcfp4Qnsio= +golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f h1:W3F4c+6OLc6H2lb//N1q4WpJkhzJCK5J6kUi1NTVXfM= +golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f/go.mod h1:J1xhfL/vlindoeF/aINzNzt2Bket5bjo9sdOYzOsU80= +golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y= +golang.org/x/net v0.56.0 h1:Rw8j/hFzGvJUZwNBXnAtf5sVDVt+65SK2C7IxCxZt5o= +golang.org/x/net v0.56.0/go.mod h1:D3Ku6r+V6JROoZK144D2XfMHFcMq/0zSfLelVTCFKec= +golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.46.0 h1:noSf2Fq6F8DBgS+LysIkx7rIExoNHJsxOAtPp4rthXw= +golang.org/x/sys v0.46.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw= +golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= +golang.org/x/term v0.44.0 h1:0rLvDRCtNj0gZkyIXhCyOb2OAzEhLVqc4B+hrsBhrmc= +golang.org/x/term v0.44.0/go.mod h1:7ze4MdzUzLXpSAoFP1H0bOI9aXDqveSvatT5vKcFh2Y= +golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= golang.org/x/text v0.40.0 h1:Ub2Z6/xjgF1WrYQz2nuITOEegKFtiIy+rieRJ5lHZKs= golang.org/x/text v0.40.0/go.mod h1:hpnzDAfGV753zIKo+wk3u1bVKCGPbrnF7+7LBF/UHVY= +golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= gonum.org/v1/gonum v0.17.0 h1:VbpOemQlsSMrYmn7T2OUvQ4dqxQXU+ouZFQsZOx50z4= gonum.org/v1/gonum v0.17.0/go.mod h1:El3tOrEuMpv2UdMrbNlKEh9vd86bmQ6vqIcDwxEOc1E= +gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk= +gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q= +gopkg.in/warnings.v0 v0.1.2 h1:wFXVbFY8DY5/xOe1ECiWdKCzZlxgshcYVNkBHstARME= +gopkg.in/warnings.v0 v0.1.2/go.mod h1:jksf8JmL6Qr/oQM2OXTHunEvvTAsrWBLb6OOjuVWRNI= +gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= +gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= diff --git a/internal/gitlog/gitlog.go b/internal/gitlog/gitlog.go new file mode 100644 index 0000000..12f219c --- /dev/null +++ b/internal/gitlog/gitlog.go @@ -0,0 +1,180 @@ +// Package gitlog reads commit history with go-git (no git binary). +package gitlog + +import ( + "errors" + "fmt" + "path" + "path/filepath" + "sort" + "strings" + "time" + + "github.com/go-git/go-git/v5" + "github.com/go-git/go-git/v5/plumbing/object" +) + +type Options struct { + Limit int + Since time.Time +} + +type Commit struct { + SHA string `json:"sha"` + Author string `json:"author"` + Email string `json:"email"` + Date string `json:"date"` + Subject string `json:"subject"` + Files []string `json:"files"` +} + +type Leaf struct { + Source string `json:"source"` + Repo string `json:"repo"` + Heading string `json:"heading"` + Text string `json:"text"` + Type string `json:"type"` + Status string `json:"status"` + Related string `json:"related"` +} + +// Log walks commits from HEAD, newest first, skipping merges. +func Log(repo string, opt Options) ([]Commit, error) { + r, err := git.PlainOpen(repo) + if err != nil { + return nil, err + } + logOpt := &git.LogOptions{Order: git.LogOrderCommitterTime} + if !opt.Since.IsZero() { + t := opt.Since + logOpt.Since = &t + } + iter, err := r.Log(logOpt) + if err != nil { + return nil, err + } + defer iter.Close() + + var out []Commit + err = iter.ForEach(func(c *object.Commit) error { + if c.NumParents() > 1 { + return nil + } + if opt.Limit > 0 && len(out) >= opt.Limit { + return Stop + } + files, ferr := changedFiles(c) + if ferr != nil { + return ferr + } + out = append(out, Commit{ + SHA: c.Hash.String(), + Author: c.Author.Name, + Email: c.Author.Email, + Date: c.Author.When.Format(time.RFC3339), + Subject: firstLine(c.Message), + Files: files, + }) + return nil + }) + if errors.Is(err, Stop) { + err = nil + } + return out, err +} + +// Stop ends a log walk early (limit reached). +var Stop = fmt.Errorf("gitlog: stop") + +func changedFiles(c *object.Commit) ([]string, error) { + var names []string + if c.NumParents() == 0 { + t, err := c.Tree() + if err != nil { + return nil, err + } + err = t.Files().ForEach(func(f *object.File) error { + names = append(names, f.Name) + return nil + }) + sort.Strings(names) + return names, err + } + parent, err := c.Parent(0) + if err != nil { + return nil, err + } + from, err := parent.Tree() + if err != nil { + return nil, err + } + to, err := c.Tree() + if err != nil { + return nil, err + } + changes, err := object.DiffTree(from, to) + if err != nil { + return nil, err + } + for _, ch := range changes { + name := ch.To.Name + if name == "" { + name = ch.From.Name + } + if name != "" { + names = append(names, name) + } + } + sort.Strings(names) + return names, nil +} + +func firstLine(msg string) string { + msg = strings.ReplaceAll(msg, "\r\n", "\n") + if i := strings.IndexByte(msg, '\n'); i >= 0 { + return strings.TrimSpace(msg[:i]) + } + return strings.TrimSpace(msg) +} + +func ToLeaf(c Commit, repo string) Leaf { + short := c.SHA + if len(short) > 12 { + short = short[:12] + } + head := fmt.Sprintf("commit %s — %s", short, c.Subject) + body := []string{ + fmt.Sprintf("commit %s in %s — %s", short, repo, c.Subject), + fmt.Sprintf("Author: %s <%s>", c.Author, c.Email), + fmt.Sprintf("Date: %s", c.Date), + } + if len(c.Files) > 0 { + body = append(body, "Changing: "+strings.Join(c.Files, ", ")) + } + return Leaf{ + Source: repo + "@" + c.SHA, + Repo: repo, + Heading: head, + Text: strings.Join(body, "\n"), + Type: "commit", + Status: "current", + Related: strings.Join(c.Files, ","), + } +} + +func RepoName(repo string) (string, error) { + r, err := git.PlainOpen(repo) + if err != nil { + return filepath.Base(repo), err + } + rem, err := r.Remote("origin") + if err != nil { + return filepath.Base(repo), nil + } + urls := rem.Config().URLs + if len(urls) == 0 { + return filepath.Base(repo), nil + } + u := strings.TrimSuffix(strings.TrimSuffix(urls[0], "/"), ".git") + return path.Base(strings.ReplaceAll(u, "\\", "/")), nil +} diff --git a/internal/gitlog/gitlog_test.go b/internal/gitlog/gitlog_test.go new file mode 100644 index 0000000..9467086 --- /dev/null +++ b/internal/gitlog/gitlog_test.go @@ -0,0 +1,243 @@ +package gitlog + +import ( + "os" + "path/filepath" + "sort" + "strings" + "testing" + "time" + + "github.com/go-git/go-git/v5" + "github.com/go-git/go-git/v5/config" + "github.com/go-git/go-git/v5/plumbing" + "github.com/go-git/go-git/v5/plumbing/object" +) + +func TestLogReadsCommitsWithoutGitBinary(t *testing.T) { + dir := initRepo(t, []commitSpec{ + { + when: time.Date(2026, 8, 10, 12, 0, 0, 0, time.FixedZone("CEST", 3600)), + name: "Ada Lovelace", + email: "ada@example.com", + subject: "feat: first commit", + files: map[string]string{"README.md": "hi\n", "src/main.c": "int main(){}\n"}, + }, + { + when: time.Date(2026, 8, 11, 9, 30, 0, 0, time.FixedZone("CEST", 3600)), + name: "Bob Babbage", + email: "bob@example.com", + subject: "fix: typo", + files: map[string]string{"docs/notes.md": "note\n"}, + }, + }) + + cs, err := Log(dir, Options{}) + if err != nil { + t.Fatal(err) + } + if len(cs) != 2 { + t.Fatalf("commits = %d, want 2", len(cs)) + } + if cs[0].Subject != "fix: typo" { + t.Fatalf("head subject = %q, want fix: typo", cs[0].Subject) + } + if cs[1].Author != "Ada Lovelace" || cs[1].Email != "ada@example.com" { + t.Fatalf("author = %s <%s>", cs[1].Author, cs[1].Email) + } + sort.Strings(cs[1].Files) + if got := cs[1].Files; len(got) != 2 || got[0] != "README.md" || got[1] != "src/main.c" { + t.Fatalf("first commit files = %v", got) + } + if cs[0].Files[0] != "docs/notes.md" { + t.Fatalf("second commit files = %v", cs[0].Files) + } +} + +func TestLogSkipsMerges(t *testing.T) { + dir := initRepo(t, []commitSpec{{ + when: time.Now(), name: "Ada Lovelace", email: "ada@example.com", + subject: "base", files: map[string]string{"a.txt": "a\n"}, + }}) + r, err := git.PlainOpen(dir) + if err != nil { + t.Fatal(err) + } + head, err := r.Head() + if err != nil { + t.Fatal(err) + } + c, err := r.CommitObject(head.Hash()) + if err != nil { + t.Fatal(err) + } + // Second parent: duplicate the same tree so we do not need a real branch. + merge := &object.Commit{ + Author: object.Signature{Name: "Ada Lovelace", Email: "ada@example.com", When: time.Now()}, + Committer: object.Signature{Name: "Ada Lovelace", Email: "ada@example.com", When: time.Now()}, + Message: "merge", + TreeHash: c.TreeHash, + ParentHashes: []plumbing.Hash{c.Hash, c.Hash}, + } + obj := r.Storer.NewEncodedObject() + if err := merge.Encode(obj); err != nil { + t.Fatal(err) + } + h, err := r.Storer.SetEncodedObject(obj) + if err != nil { + t.Fatal(err) + } + if err := r.Storer.SetReference(plumbing.NewHashReference(head.Name(), h)); err != nil { + t.Fatal(err) + } + + cs, err := Log(dir, Options{}) + if err != nil { + t.Fatal(err) + } + for _, x := range cs { + if x.Subject == "merge" { + t.Fatal("merge commit was not skipped") + } + } + if len(cs) != 1 || cs[0].Subject != "base" { + t.Fatalf("after skip merges: %+v", subjects(cs)) + } +} + +func TestLogSinceAndLimit(t *testing.T) { + old := time.Date(2025, 1, 1, 0, 0, 0, 0, time.UTC) + neu := time.Date(2026, 6, 1, 0, 0, 0, 0, time.UTC) + dir := initRepo(t, []commitSpec{ + {when: old, name: "Ada Lovelace", email: "ada@example.com", subject: "old", files: map[string]string{"old.md": "x"}}, + {when: neu, name: "Ada Lovelace", email: "ada@example.com", subject: "new", files: map[string]string{"new.md": "y"}}, + }) + cs, err := Log(dir, Options{Since: neu.Add(-time.Hour)}) + if err != nil { + t.Fatal(err) + } + if len(cs) != 1 || cs[0].Subject != "new" { + t.Fatalf("since filter: %v", subjects(cs)) + } + cs, err = Log(dir, Options{Limit: 1}) + if err != nil { + t.Fatal(err) + } + if len(cs) != 1 { + t.Fatalf("limit=1 got %d", len(cs)) + } +} + +func TestLeafShape(t *testing.T) { + c := Commit{ + SHA: "a1b2c3d4e5f6aaaa", + Author: "Ada Lovelace", + Email: "ada@example.com", + Date: "2026-08-10T12:00:00+01:00", + Subject: "feat: first commit", + Files: []string{"README.md", "src/main.c"}, + } + lf := ToLeaf(c, "sample-repo") + if lf.Type != "commit" || lf.Repo != "sample-repo" { + t.Fatalf("leaf meta = %+v", lf) + } + if lf.Source != "sample-repo@a1b2c3d4e5f6aaaa" { + t.Fatalf("source = %s", lf.Source) + } + if lf.Related != "README.md,src/main.c" { + t.Fatalf("related = %s", lf.Related) + } + if lf.Heading != "commit a1b2c3d4e5f6 — feat: first commit" { + t.Fatalf("heading = %q", lf.Heading) + } + if !strings.Contains(lf.Text, "Ada Lovelace") || !strings.Contains(lf.Text, "README.md") { + t.Fatalf("text = %s", lf.Text) + } +} + +func TestRepoNameFromOrigin(t *testing.T) { + dir := initRepo(t, []commitSpec{{ + when: time.Now(), name: "Ada Lovelace", email: "ada@example.com", + subject: "init", files: map[string]string{"README.md": "x"}, + }}) + r, err := git.PlainOpen(dir) + if err != nil { + t.Fatal(err) + } + if _, err := r.CreateRemote(&config.RemoteConfig{ + Name: "origin", + URLs: []string{"https://git.example.com/eSlider/sample-repo.git"}, + }); err != nil { + t.Fatal(err) + } + name, err := RepoName(dir) + if err != nil { + t.Fatal(err) + } + if name != "sample-repo" { + t.Fatalf("RepoName = %q, want sample-repo", name) + } +} + +func TestRepoNameFallsBackToDir(t *testing.T) { + dir := initRepo(t, []commitSpec{{ + when: time.Now(), name: "Ada Lovelace", email: "ada@example.com", + subject: "init", files: map[string]string{"README.md": "x"}, + }}) + name, err := RepoName(dir) + if err != nil { + t.Fatal(err) + } + if name != filepath.Base(dir) { + t.Fatalf("RepoName = %q, want %s", name, filepath.Base(dir)) + } +} + +type commitSpec struct { + when time.Time + name string + email string + subject string + files map[string]string +} + +func initRepo(t *testing.T, specs []commitSpec) string { + t.Helper() + dir := t.TempDir() + r, err := git.PlainInit(dir, false) + if err != nil { + t.Fatal(err) + } + w, err := r.Worktree() + if err != nil { + t.Fatal(err) + } + for _, s := range specs { + for path, body := range s.files { + full := filepath.Join(dir, path) + if err := os.MkdirAll(filepath.Dir(full), 0o755); err != nil && !os.IsExist(err) { + t.Fatal(err) + } + if err := os.WriteFile(full, []byte(body), 0o644); err != nil { + t.Fatal(err) + } + if _, err := w.Add(path); err != nil { + t.Fatal(err) + } + } + if _, err := w.Commit(s.subject, &git.CommitOptions{ + Author: &object.Signature{Name: s.name, Email: s.email, When: s.when}, + }); err != nil { + t.Fatal(err) + } + } + return dir +} + +func subjects(cs []Commit) []string { + out := make([]string, len(cs)) + for i, c := range cs { + out[i] = c.Subject + } + return out +}