feat: markdown import splits H2 leafs in Go (#26)
Tests / Test (push) Skipped
Tests / Release (semver) (push) Skipped

Drop the Python ExecFile wrapper. Conversion still does not write
Ladybug; add a dry-run fixture check for the index adapter split.
This commit is contained in:
2026-08-13 23:27:42 +01:00
committed by GitHub
co-authored by GitHub
parent b317968a4c
commit 85caff90b9
9 changed files with 406 additions and 10 deletions
+85 -5
View File
@@ -1,20 +1,100 @@
//usr/bin/env go run -tags=markdown_import "$0" "$@"; exit
//go:build markdown_import
//usr/bin/env go run "$0" "$@"; exit
//
// bin/markdown/import.go - split markdown into leafs (mistune).
// bin/markdown/import.go - split markdown into leafs (H2 boundaries).
//
// ./bin/markdown/import.go [dir]
// ./bin/markdown/import.go --files a.md,b.md --json
//
// Conversion only. Brain write is bin/brain/index.go.
// Python bin/md/import remains as a fallback.
// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
package main
import (
"fmt"
"os"
"strings"
"github.com/eSlider/2dph/internal/cmdbin"
"github.com/eSlider/2dph/internal/mdleaves"
)
func main() {
os.Exit(cmdbin.ExecFile("bin/md/import", os.Args[1:]))
os.Exit(run(os.Args[1:]))
}
func run(args []string) int {
jsonOut := false
files := ""
root := "."
for i := 0; i < len(args); i++ {
a := args[i]
switch {
case a == "--json":
jsonOut = true
case a == "--files" && i+1 < len(args):
i++
files = args[i]
case strings.HasPrefix(a, "--files="):
files = strings.TrimPrefix(a, "--files=")
case a == "-h" || a == "--help":
fmt.Fprintln(os.Stderr, "bin/markdown/import.go [dir] [--files a.md,b.md] [--json]")
return 0
case strings.HasPrefix(a, "-"):
fmt.Fprintln(os.Stderr, "unknown arg:", a)
return 2
default:
root = a
}
}
var paths []string
if files != "" {
for _, f := range strings.Split(files, ",") {
f = strings.TrimSpace(f)
if f != "" {
paths = append(paths, f)
}
}
} else {
st, err := os.Stat(root)
if err != nil {
fmt.Fprintf(os.Stderr, "md/import: no such path %s\n", root)
return 2
}
if !st.IsDir() {
paths = []string{root}
} else {
var err error
paths, err = mdleaves.WalkMarkdown(root)
if err != nil {
fmt.Fprintf(os.Stderr, "md/import: %v\n", err)
return 1
}
}
}
if len(paths) == 0 {
fmt.Fprintln(os.Stderr, "md/import: no markdown files")
return 1
}
var all []mdleaves.Leaf
for _, p := range paths {
raw, err := os.ReadFile(p)
if err != nil {
fmt.Fprintf(os.Stderr, "md/import: %s: %v\n", p, err)
continue
}
all = append(all, mdleaves.ToAll(string(raw), p, "")...)
}
if jsonOut {
s, err := mdleaves.EncodeJSON(all)
if err != nil {
fmt.Fprintln(os.Stderr, err)
return 1
}
fmt.Print(s)
return 0
}
fmt.Print(mdleaves.EncodeYAML(all))
return 0
}
+21 -1
View File
@@ -125,8 +125,28 @@ class BinLayoutTest(unittest.TestCase):
"index_mail must point at bin/brain/index.go",
)
def test_markdown_import_is_shebang(self) -> None:
def test_markdown_import_is_go_not_python_exec(self) -> None:
self._assert_shebang("bin/markdown/import.go")
text = (ROOT / "bin" / "markdown" / "import.go").read_text()
self.assertNotIn("ExecFile", text)
self.assertNotIn("cmdbin", text)
self.assertIn("internal/mdleaves", text)
self.assertNotIn("kb.lbug", text)
def test_import_adapters_do_not_write_ladybug(self) -> None:
for rel in (
"bin/mail/import.go",
"bin/mail/import",
"bin/markdown/import.go",
"bin/chats/import.go",
"bin/git/import.go",
):
text = (ROOT / rel).read_text()
self.assertNotIn("upsert_leaf", text, rel)
self.assertNotIn("kb.lbug", text, rel)
self.assertNotIn("var/brain.lbug", text, rel)
index = (ROOT / "bin" / "brain" / "index.go").read_text()
self.assertIn("bin/kb/index", index)
def test_postgres_query_is_shebang(self) -> None:
self._assert_shebang("bin/postgres/query.go")
+41
View File
@@ -0,0 +1,41 @@
"""Import adapters write files only. Index rebuild is brain/index (D14 / Gitea #7)."""
from __future__ import annotations
import json
import os
import subprocess
import sys
import tempfile
import unittest
from pathlib import Path
ROOT = Path(__file__).resolve().parents[2]
class IndexAdapterTest(unittest.TestCase):
def test_dry_run_fixture_corpus_does_not_write_lbug(self) -> None:
tmp = Path(tempfile.mkdtemp())
(tmp / "note.md").write_text("# Fixture\n\n## Leaf\n\nhello corpus\n", encoding="utf-8")
lbug = tmp / "kb.lbug"
try:
import ladybug # noqa: F401
except ImportError:
venv_py = ROOT / ".venv" / "bin" / "python"
if not venv_py.is_file():
self.skipTest("ladybug missing")
py = str(venv_py)
else:
py = sys.executable
proc = subprocess.run(
[py, str(ROOT / "bin" / "kb" / "index"), "--dry-run", "--json", "--corpus", str(tmp)],
cwd=ROOT,
capture_output=True,
text=True,
env=os.environ.copy(),
check=False,
)
self.assertEqual(proc.returncode, 0, proc.stderr)
msg = json.loads(proc.stdout)
self.assertTrue(msg.get("dry_run"))
self.assertGreaterEqual(msg.get("corpus_total", 0), 1)
self.assertFalse(lbug.exists(), "dry-run must not create a Ladybug file")