edify-agents-cli 0.2.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- edify/__init__.py +19 -0
- edify/__main__.py +6 -0
- edify/_toml.py +286 -0
- edify/agents.py +261 -0
- edify/anim.py +499 -0
- edify/assets/commands/build.md +64 -0
- edify/assets/commands/plan.md +68 -0
- edify/assets/commands/spec.md +63 -0
- edify/assets/commands/tasks.md +65 -0
- edify/assets/commands/verify.md +67 -0
- edify/assets/formats/plan.example.md +455 -0
- edify/assets/formats/plan.format.md +128 -0
- edify/assets/formats/spec.example.md +483 -0
- edify/assets/formats/spec.format.md +116 -0
- edify/assets/formats/tasks.example.md +712 -0
- edify/assets/formats/tasks.format.md +199 -0
- edify/assets/harvest/harvest.md +91 -0
- edify/assets/harvest/sources.md +295 -0
- edify/assets/harvest/vocab.md +52 -0
- edify/assets/manifest.md +30 -0
- edify/assets/mcp/default-registry.md +66 -0
- edify/assets/skills/adversary.md +61 -0
- edify/assets/skills/debugger.md +64 -0
- edify/assets/skills/implementer-general.md +53 -0
- edify/assets/skills/implementer-go.md +63 -0
- edify/assets/skills/implementer-node.md +61 -0
- edify/assets/skills/implementer-postgres.md +63 -0
- edify/assets/skills/implementer-python.md +65 -0
- edify/assets/skills/implementer-react.md +65 -0
- edify/assets/skills/planner.md +58 -0
- edify/assets/skills/test-writer-node.md +64 -0
- edify/assets/skills/test-writer-python.md +60 -0
- edify/assets/skills/verifier.md +67 -0
- edify/assets/templates/CLAUDE.md +18 -0
- edify/assets.py +77 -0
- edify/cli.py +681 -0
- edify/commands/__init__.py +1 -0
- edify/commands/check_cmd.py +72 -0
- edify/commands/doctor_cmd.py +206 -0
- edify/commands/feedback_cmd.py +90 -0
- edify/commands/governance_cmd.py +65 -0
- edify/commands/graph_cmd.py +156 -0
- edify/commands/harvest_cmd.py +538 -0
- edify/commands/init_cmd.py +333 -0
- edify/commands/init_new_cmd.py +151 -0
- edify/commands/license_cmd.py +80 -0
- edify/commands/mcp_cmd.py +159 -0
- edify/commands/self_cmd.py +185 -0
- edify/commands/setup_cmd.py +79 -0
- edify/commands/skills_cmd.py +177 -0
- edify/commands/upgrade_cmd.py +178 -0
- edify/context.py +57 -0
- edify/conventions.py +275 -0
- edify/detect.py +313 -0
- edify/distribution.py +40 -0
- edify/errors.py +66 -0
- edify/feedback.py +207 -0
- edify/formats/__init__.py +11 -0
- edify/formats/check.py +573 -0
- edify/formats/document.py +238 -0
- edify/formats/finding.py +50 -0
- edify/formats/fix.py +114 -0
- edify/formats/mcp.py +126 -0
- edify/formats/plan.py +151 -0
- edify/formats/skill.py +139 -0
- edify/formats/spec.py +164 -0
- edify/formats/tasks.py +321 -0
- edify/governance.py +316 -0
- edify/graph/__init__.py +11 -0
- edify/graph/extract.py +351 -0
- edify/graph/ignore.py +107 -0
- edify/graph/langs/__init__.py +93 -0
- edify/graph/langs/ctags.py +145 -0
- edify/graph/langs/markdown.py +41 -0
- edify/graph/langs/patterns.py +361 -0
- edify/graph/langs/python_ast.py +154 -0
- edify/graph/langs/sqlish.py +86 -0
- edify/graph/model.py +102 -0
- edify/graph/queries.py +211 -0
- edify/graph/store.py +157 -0
- edify/harvest/__init__.py +28 -0
- edify/harvest/ledger.py +191 -0
- edify/harvest/screen.py +236 -0
- edify/harvest/sources.py +298 -0
- edify/host.py +345 -0
- edify/interview.py +354 -0
- edify/library.py +176 -0
- edify/licensing/__init__.py +30 -0
- edify/licensing/ed25519.py +154 -0
- edify/licensing/projects.py +223 -0
- edify/licensing/tier.py +172 -0
- edify/licensing/token.py +149 -0
- edify/paths.py +282 -0
- edify/selfinstall.py +244 -0
- edify/skills.py +108 -0
- edify/tsv.py +109 -0
- edify/ui.py +334 -0
- edify_agents_cli-0.2.0.dist-info/METADATA +408 -0
- edify_agents_cli-0.2.0.dist-info/RECORD +102 -0
- edify_agents_cli-0.2.0.dist-info/WHEEL +4 -0
- edify_agents_cli-0.2.0.dist-info/entry_points.txt +2 -0
- edify_agents_cli-0.2.0.dist-info/licenses/LICENSE +21 -0
edify/graph/ignore.py
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
1
|
+
"""What the walk does not descend into.
|
|
2
|
+
|
|
3
|
+
Three sources, in order: a built-in list of directories that are never source, the
|
|
4
|
+
repository's `.gitignore` (the common subset — directory names, suffix globs, and
|
|
5
|
+
anchored paths), and `.edifyignore` when a repository needs to say something the
|
|
6
|
+
first two do not.
|
|
7
|
+
"""
|
|
8
|
+
|
|
9
|
+
from __future__ import annotations
|
|
10
|
+
|
|
11
|
+
import fnmatch
|
|
12
|
+
from pathlib import Path
|
|
13
|
+
|
|
14
|
+
# Directories that are never source in any stack we cover. Matched by exact name
|
|
15
|
+
# at any depth, which is the only rule that stays correct in a monorepo.
|
|
16
|
+
ALWAYS_SKIP_DIRS = frozenset(
|
|
17
|
+
{
|
|
18
|
+
".git", ".hg", ".svn", ".edify", ".idea", ".vscode", ".vs",
|
|
19
|
+
"node_modules", "bower_components", "vendor", "third_party",
|
|
20
|
+
"__pycache__", ".mypy_cache", ".ruff_cache", ".pytest_cache", ".tox",
|
|
21
|
+
".venv", "venv", "env", "virtualenv", ".eggs",
|
|
22
|
+
"dist", "build", "out", "target", "bin", "obj", ".next", ".nuxt",
|
|
23
|
+
".svelte-kit", ".turbo", ".parcel-cache", ".cache", "coverage",
|
|
24
|
+
".gradle", ".terraform", "Pods", "DerivedData", ".dart_tool",
|
|
25
|
+
"site-packages", ".pnpm-store", ".yarn",
|
|
26
|
+
"__MACOSX", "Carthage",
|
|
27
|
+
}
|
|
28
|
+
)
|
|
29
|
+
|
|
30
|
+
# macOS bundle directories. They are named by suffix rather than by name, and a
|
|
31
|
+
# `.app` or `.framework` is a build product whose innards are not anybody's source.
|
|
32
|
+
ALWAYS_SKIP_DIR_SUFFIXES = (".dSYM", ".app", ".framework", ".xcassets", ".lproj")
|
|
33
|
+
|
|
34
|
+
# Files the operating system writes into a source tree without being asked.
|
|
35
|
+
ALWAYS_SKIP_NAMES = frozenset({".DS_Store", "Thumbs.db", "desktop.ini", ".localized", "Icon\r"})
|
|
36
|
+
|
|
37
|
+
ALWAYS_SKIP_SUFFIXES = frozenset(
|
|
38
|
+
{
|
|
39
|
+
".min.js", ".min.css", ".map", ".lock", ".pyc", ".pyo", ".so", ".dll",
|
|
40
|
+
".dylib", ".exe", ".class", ".jar", ".war", ".o", ".a", ".wasm",
|
|
41
|
+
".png", ".jpg", ".jpeg", ".gif", ".webp", ".svg", ".ico", ".pdf",
|
|
42
|
+
".zip", ".gz", ".tar", ".7z", ".mp4", ".mp3", ".woff", ".woff2", ".ttf",
|
|
43
|
+
".eot", ".bin", ".db", ".sqlite", ".sqlite3", ".parquet",
|
|
44
|
+
}
|
|
45
|
+
)
|
|
46
|
+
|
|
47
|
+
# Anything larger than this is generated, vendored, or data. Indexing it costs
|
|
48
|
+
# more than it returns and pollutes the map with names nobody wrote.
|
|
49
|
+
MAX_FILE_BYTES = 1_500_000
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
class IgnoreRules:
|
|
53
|
+
def __init__(self, root: Path):
|
|
54
|
+
self.root = root
|
|
55
|
+
self.dir_names: set[str] = set(ALWAYS_SKIP_DIRS)
|
|
56
|
+
self.globs: list[str] = []
|
|
57
|
+
self.anchored: list[str] = []
|
|
58
|
+
self._load(root / ".gitignore")
|
|
59
|
+
self._load(root / ".edifyignore")
|
|
60
|
+
|
|
61
|
+
def _load(self, path: Path) -> None:
|
|
62
|
+
if not path.is_file():
|
|
63
|
+
return
|
|
64
|
+
try:
|
|
65
|
+
text = path.read_text(encoding="utf-8", errors="replace")
|
|
66
|
+
except OSError:
|
|
67
|
+
return
|
|
68
|
+
for raw in text.splitlines():
|
|
69
|
+
line = raw.strip()
|
|
70
|
+
if not line or line.startswith("#") or line.startswith("!"):
|
|
71
|
+
continue
|
|
72
|
+
if line.endswith("/"):
|
|
73
|
+
stripped = line.rstrip("/")
|
|
74
|
+
if "/" not in stripped:
|
|
75
|
+
self.dir_names.add(stripped)
|
|
76
|
+
else:
|
|
77
|
+
self.anchored.append(stripped.lstrip("/"))
|
|
78
|
+
continue
|
|
79
|
+
if line.startswith("/"):
|
|
80
|
+
self.anchored.append(line.lstrip("/"))
|
|
81
|
+
elif "/" in line:
|
|
82
|
+
self.anchored.append(line)
|
|
83
|
+
else:
|
|
84
|
+
self.globs.append(line)
|
|
85
|
+
|
|
86
|
+
def skip_dir(self, name: str, rel: str) -> bool:
|
|
87
|
+
if name in self.dir_names:
|
|
88
|
+
return True
|
|
89
|
+
if name.endswith(ALWAYS_SKIP_DIR_SUFFIXES):
|
|
90
|
+
return True
|
|
91
|
+
# `.claude/` holds generated command pointers, not source. `.github/` holds
|
|
92
|
+
# the CI job whose real commands the conventions scrape reads, so it stays.
|
|
93
|
+
if name.startswith(".") and name != ".github":
|
|
94
|
+
return True
|
|
95
|
+
return any(fnmatch.fnmatch(rel, pattern) for pattern in self.anchored)
|
|
96
|
+
|
|
97
|
+
def skip_file(self, name: str, rel: str, size: int) -> bool:
|
|
98
|
+
if name in ALWAYS_SKIP_NAMES:
|
|
99
|
+
return True
|
|
100
|
+
lowered = name.lower()
|
|
101
|
+
if any(lowered.endswith(suffix) for suffix in ALWAYS_SKIP_SUFFIXES):
|
|
102
|
+
return True
|
|
103
|
+
if size > MAX_FILE_BYTES:
|
|
104
|
+
return True
|
|
105
|
+
if any(fnmatch.fnmatch(name, pattern) for pattern in self.globs):
|
|
106
|
+
return True
|
|
107
|
+
return any(fnmatch.fnmatch(rel, pattern) for pattern in self.anchored)
|
|
@@ -0,0 +1,93 @@
|
|
|
1
|
+
"""Per-language extraction.
|
|
2
|
+
|
|
3
|
+
Two backends ship. `python_ast` parses with the standard library's syntax tree and
|
|
4
|
+
is exact. `patterns` is a declarative line scanner covering the rest, and it is
|
|
5
|
+
honest about being a scanner: `meta.method_<lang>` records which one produced a
|
|
6
|
+
language's nodes, so nobody mistakes a scan for a parse.
|
|
7
|
+
|
|
8
|
+
A third backend, `ctags`, wraps a pinned external extractor when one is installed.
|
|
9
|
+
Whichever runs, the output is the same TSV contract — the contract is the asset.
|
|
10
|
+
"""
|
|
11
|
+
|
|
12
|
+
from __future__ import annotations
|
|
13
|
+
|
|
14
|
+
from pathlib import Path
|
|
15
|
+
|
|
16
|
+
from ..model import Extraction
|
|
17
|
+
from . import markdown, patterns, python_ast, sqlish
|
|
18
|
+
|
|
19
|
+
# extension → language id. A language absent from this table produces a file node
|
|
20
|
+
# and nothing else, which is the visible-gap behaviour the design requires.
|
|
21
|
+
EXTENSIONS: dict[str, str] = {
|
|
22
|
+
".py": "python",
|
|
23
|
+
".pyi": "python",
|
|
24
|
+
".js": "javascript",
|
|
25
|
+
".jsx": "javascript",
|
|
26
|
+
".mjs": "javascript",
|
|
27
|
+
".cjs": "javascript",
|
|
28
|
+
".ts": "typescript",
|
|
29
|
+
".tsx": "typescript",
|
|
30
|
+
".mts": "typescript",
|
|
31
|
+
".cts": "typescript",
|
|
32
|
+
".vue": "vue",
|
|
33
|
+
".svelte": "svelte",
|
|
34
|
+
".go": "go",
|
|
35
|
+
".rs": "rust",
|
|
36
|
+
".java": "java",
|
|
37
|
+
".kt": "kotlin",
|
|
38
|
+
".kts": "kotlin",
|
|
39
|
+
".cs": "csharp",
|
|
40
|
+
".swift": "swift",
|
|
41
|
+
".rb": "ruby",
|
|
42
|
+
".php": "php",
|
|
43
|
+
".sql": "sql",
|
|
44
|
+
".c": "c",
|
|
45
|
+
".h": "c",
|
|
46
|
+
".cc": "cpp",
|
|
47
|
+
".cpp": "cpp",
|
|
48
|
+
".cxx": "cpp",
|
|
49
|
+
".hpp": "cpp",
|
|
50
|
+
".hh": "cpp",
|
|
51
|
+
".m": "objc",
|
|
52
|
+
".scala": "scala",
|
|
53
|
+
".dart": "dart",
|
|
54
|
+
".lua": "lua",
|
|
55
|
+
".ex": "elixir",
|
|
56
|
+
".exs": "elixir",
|
|
57
|
+
".sh": "shell",
|
|
58
|
+
".bash": "shell",
|
|
59
|
+
".md": "markdown",
|
|
60
|
+
".markdown": "markdown",
|
|
61
|
+
}
|
|
62
|
+
|
|
63
|
+
# Which backend owns which language. Everything not listed falls to `patterns`.
|
|
64
|
+
_EXACT = {"python": "ast", "markdown": "structural", "sql": "structural"}
|
|
65
|
+
|
|
66
|
+
|
|
67
|
+
def language_for(path: Path) -> str | None:
|
|
68
|
+
return EXTENSIONS.get(path.suffix.lower())
|
|
69
|
+
|
|
70
|
+
|
|
71
|
+
def method_for(language: str) -> str:
|
|
72
|
+
"""`ast`, `structural`, or `scan` — recorded in meta so the gap is visible."""
|
|
73
|
+
if language in _EXACT:
|
|
74
|
+
return _EXACT[language]
|
|
75
|
+
if language in patterns.RULES:
|
|
76
|
+
return "scan"
|
|
77
|
+
return "none"
|
|
78
|
+
|
|
79
|
+
|
|
80
|
+
def extract_file(rel_path: str, source: str, language: str) -> Extraction:
|
|
81
|
+
"""Run the right backend over one file's text."""
|
|
82
|
+
if language == "python":
|
|
83
|
+
return python_ast.extract(rel_path, source)
|
|
84
|
+
if language == "markdown":
|
|
85
|
+
return markdown.extract(rel_path, source)
|
|
86
|
+
if language == "sql":
|
|
87
|
+
return sqlish.extract(rel_path, source)
|
|
88
|
+
return patterns.extract(rel_path, source, language)
|
|
89
|
+
|
|
90
|
+
|
|
91
|
+
def covered_languages() -> list[str]:
|
|
92
|
+
covered = set(_EXACT) | set(patterns.RULES)
|
|
93
|
+
return sorted(covered)
|
|
@@ -0,0 +1,145 @@
|
|
|
1
|
+
"""Adapter for a pinned external extractor.
|
|
2
|
+
|
|
3
|
+
The design's preferred extractor is a third-party static binary with syntax-tree
|
|
4
|
+
parsing and broad language coverage, wrapped so it emits our TSV contract. This is
|
|
5
|
+
that wrapper. The contract is the asset; the extractor is replaceable by
|
|
6
|
+
construction, and this module is the only thing that has to change when it is
|
|
7
|
+
replaced.
|
|
8
|
+
|
|
9
|
+
Nothing here is required. With no external extractor present the built-in backends
|
|
10
|
+
run and `meta` records which one produced each language.
|
|
11
|
+
"""
|
|
12
|
+
|
|
13
|
+
from __future__ import annotations
|
|
14
|
+
|
|
15
|
+
import json
|
|
16
|
+
import shutil
|
|
17
|
+
import subprocess
|
|
18
|
+
from pathlib import Path
|
|
19
|
+
|
|
20
|
+
from ..model import Edge, Extraction, Node, fingerprint, node_id
|
|
21
|
+
|
|
22
|
+
# ctags kinds → our node kinds. Anything unmapped is dropped rather than guessed.
|
|
23
|
+
_KIND_MAP = {
|
|
24
|
+
"function": "symbol",
|
|
25
|
+
"func": "symbol",
|
|
26
|
+
"method": "symbol",
|
|
27
|
+
"class": "symbol",
|
|
28
|
+
"struct": "symbol",
|
|
29
|
+
"interface": "symbol",
|
|
30
|
+
"trait": "symbol",
|
|
31
|
+
"enum": "symbol",
|
|
32
|
+
"enumerator": "symbol",
|
|
33
|
+
"constant": "symbol",
|
|
34
|
+
"variable": "symbol",
|
|
35
|
+
"member": "symbol",
|
|
36
|
+
"typedef": "symbol",
|
|
37
|
+
"type": "symbol",
|
|
38
|
+
"module": "module",
|
|
39
|
+
"namespace": "module",
|
|
40
|
+
"package": "package",
|
|
41
|
+
"table": "table",
|
|
42
|
+
}
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
def available(binary: str = "ctags") -> str | None:
|
|
46
|
+
"""The resolved path of the external extractor, or None."""
|
|
47
|
+
path = shutil.which(binary)
|
|
48
|
+
if not path:
|
|
49
|
+
return None
|
|
50
|
+
try:
|
|
51
|
+
out = subprocess.run(
|
|
52
|
+
[path, "--version"], capture_output=True, text=True, timeout=10, check=False
|
|
53
|
+
)
|
|
54
|
+
except (OSError, subprocess.SubprocessError):
|
|
55
|
+
return None
|
|
56
|
+
# Only the Universal variant emits the JSON we parse. The exuberant one does
|
|
57
|
+
# not, and quietly producing nothing would be worse than declining.
|
|
58
|
+
if "Universal Ctags" not in (out.stdout or "") + (out.stderr or ""):
|
|
59
|
+
return None
|
|
60
|
+
return path
|
|
61
|
+
|
|
62
|
+
|
|
63
|
+
def version(binary: str = "ctags") -> str:
|
|
64
|
+
path = shutil.which(binary)
|
|
65
|
+
if not path:
|
|
66
|
+
return "-"
|
|
67
|
+
try:
|
|
68
|
+
out = subprocess.run(
|
|
69
|
+
[path, "--version"], capture_output=True, text=True, timeout=10, check=False
|
|
70
|
+
)
|
|
71
|
+
except (OSError, subprocess.SubprocessError):
|
|
72
|
+
return "-"
|
|
73
|
+
first = (out.stdout or out.stderr or "").splitlines()
|
|
74
|
+
return first[0].strip() if first else "-"
|
|
75
|
+
|
|
76
|
+
|
|
77
|
+
def extract_tree(root: Path, files: list[str], binary: str = "ctags") -> Extraction:
|
|
78
|
+
"""Run the external extractor over an explicit file list.
|
|
79
|
+
|
|
80
|
+
The file list comes from our own walk, so the extractor never decides what is
|
|
81
|
+
in scope — ignore rules stay in one place.
|
|
82
|
+
"""
|
|
83
|
+
out = Extraction()
|
|
84
|
+
path = available(binary)
|
|
85
|
+
if not path or not files:
|
|
86
|
+
return out
|
|
87
|
+
|
|
88
|
+
# A file list on stdin keeps the command line under every platform's limit.
|
|
89
|
+
listing = "\n".join(files)
|
|
90
|
+
try:
|
|
91
|
+
proc = subprocess.run(
|
|
92
|
+
[
|
|
93
|
+
path,
|
|
94
|
+
"--output-format=json",
|
|
95
|
+
"--fields=+nKz",
|
|
96
|
+
"--extras=",
|
|
97
|
+
"-L",
|
|
98
|
+
"-",
|
|
99
|
+
"-f",
|
|
100
|
+
"-",
|
|
101
|
+
],
|
|
102
|
+
input=listing,
|
|
103
|
+
capture_output=True,
|
|
104
|
+
text=True,
|
|
105
|
+
cwd=str(root),
|
|
106
|
+
timeout=600,
|
|
107
|
+
check=False,
|
|
108
|
+
)
|
|
109
|
+
except (OSError, subprocess.SubprocessError):
|
|
110
|
+
return out
|
|
111
|
+
|
|
112
|
+
seen_files: set[str] = set()
|
|
113
|
+
for line in proc.stdout.splitlines():
|
|
114
|
+
line = line.strip()
|
|
115
|
+
if not line or not line.startswith("{"):
|
|
116
|
+
continue
|
|
117
|
+
try:
|
|
118
|
+
tag = json.loads(line)
|
|
119
|
+
except json.JSONDecodeError:
|
|
120
|
+
continue
|
|
121
|
+
if tag.get("_type") != "tag":
|
|
122
|
+
continue
|
|
123
|
+
rel = Path(tag.get("path", "")).as_posix().lstrip("./")
|
|
124
|
+
name = tag.get("name")
|
|
125
|
+
kind = _KIND_MAP.get(str(tag.get("kind", "")).lower())
|
|
126
|
+
if not rel or not name or not kind:
|
|
127
|
+
continue
|
|
128
|
+
lineno = int(tag.get("line", 1) or 1)
|
|
129
|
+
scope = tag.get("scope")
|
|
130
|
+
qualified = f"{scope}.{name}" if scope else name
|
|
131
|
+
|
|
132
|
+
file_id = node_id("file", rel, ".")
|
|
133
|
+
if rel not in seen_files:
|
|
134
|
+
seen_files.add(rel)
|
|
135
|
+
module_id = node_id("module", rel, ".")
|
|
136
|
+
out.nodes.append(Node(module_id, "module", rel, 1, rel.rsplit("/", 1)[-1]))
|
|
137
|
+
out.edges.append(Edge(file_id, "defines", module_id))
|
|
138
|
+
|
|
139
|
+
sym_id = node_id(kind, rel, qualified)
|
|
140
|
+
signature = tag.get("signature") or tag.get("pattern") or qualified
|
|
141
|
+
out.nodes.append(Node(sym_id, kind, rel, lineno, qualified, fingerprint(str(signature))))
|
|
142
|
+
out.edges.append(Edge(node_id("module", rel, "."), "defines", sym_id))
|
|
143
|
+
if tag.get("language"):
|
|
144
|
+
out.languages.add(str(tag["language"]).lower())
|
|
145
|
+
return out
|
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
"""Markdown headings as `doc-section` nodes.
|
|
2
|
+
|
|
3
|
+
Structural rather than scanned: a heading is a heading. This is what lets a spec's
|
|
4
|
+
`## Assertions` block be cited as `file:line` and what makes `documents` edges
|
|
5
|
+
possible between a document section and the module it describes.
|
|
6
|
+
"""
|
|
7
|
+
|
|
8
|
+
from __future__ import annotations
|
|
9
|
+
|
|
10
|
+
import re
|
|
11
|
+
|
|
12
|
+
from ..model import Edge, Extraction, Node, fingerprint, node_id
|
|
13
|
+
|
|
14
|
+
_HEADING = re.compile(r"^(?P<hashes>#{1,6})\s+(?P<title>.+?)\s*#*\s*$")
|
|
15
|
+
_FENCE = re.compile(r"^\s*(```|~~~)")
|
|
16
|
+
|
|
17
|
+
|
|
18
|
+
def extract(rel_path: str, source: str) -> Extraction:
|
|
19
|
+
out = Extraction(languages={"markdown"})
|
|
20
|
+
file_id = node_id("file", rel_path, ".")
|
|
21
|
+
in_fence = False
|
|
22
|
+
stack: list[str] = []
|
|
23
|
+
|
|
24
|
+
for lineno, raw in enumerate(source.splitlines(), start=1):
|
|
25
|
+
if _FENCE.match(raw):
|
|
26
|
+
in_fence = not in_fence
|
|
27
|
+
continue
|
|
28
|
+
if in_fence:
|
|
29
|
+
continue
|
|
30
|
+
m = _HEADING.match(raw)
|
|
31
|
+
if not m:
|
|
32
|
+
continue
|
|
33
|
+
depth = len(m.group("hashes"))
|
|
34
|
+
title = m.group("title").strip()
|
|
35
|
+
del stack[depth - 1 :]
|
|
36
|
+
stack.append(title)
|
|
37
|
+
name = " > ".join(stack)
|
|
38
|
+
sec_id = node_id("doc-section", rel_path, name)
|
|
39
|
+
out.nodes.append(Node(sec_id, "doc-section", rel_path, lineno, name, fingerprint(title)))
|
|
40
|
+
out.edges.append(Edge(file_id, "defines", sec_id))
|
|
41
|
+
return out
|