"""Shared OKF v0.1 parsing utilities (Python standard library only)."""
from __future__ import annotations

import re
from pathlib import Path

RESERVED = {"index.md", "log.md"}
_LINK_RE = re.compile(r"\[[^\]]*\]\(([^)]+)\)")


class FrontmatterError(ValueError):
    """Raised when a frontmatter block is present but cannot be parsed."""


def split_frontmatter(text):
    """Return (raw_frontmatter, body). raw is None if there is no leading '---' block."""
    if not text.startswith("---"):
        return None, text
    lines = text.splitlines()
    if lines[0].strip() != "---":
        return None, text
    for i in range(1, len(lines)):
        if lines[i].strip() == "---":
            return "\n".join(lines[1:i]), "\n".join(lines[i + 1:])
    raise FrontmatterError("opening '---' without a closing '---'")


def _scalar(value):
    value = value.strip()
    if len(value) >= 2 and value[0] == value[-1] and value[0] in "\"'":
        return value[1:-1]
    return value


def parse_yaml_subset(raw):
    """Parse the small YAML subset OKF uses: `key: value` and `key: [a, b]`."""
    meta = {}
    for line in raw.splitlines():
        stripped = line.strip()
        if not stripped or stripped.startswith("#"):
            continue
        if ":" not in line:
            raise FrontmatterError("unparseable frontmatter line: %r" % line)
        key, _, value = line.partition(":")
        key, value = key.strip(), value.strip()
        if value.startswith("[") and value.endswith("]"):
            inner = value[1:-1].strip()
            meta[key] = [s for s in (_scalar(x) for x in inner.split(",")) if s] if inner else []
        else:
            meta[key] = _scalar(value)
    return meta


def parse_frontmatter(text):
    """Return (meta, body). meta is None when no frontmatter block is present."""
    raw, body = split_frontmatter(text)
    if raw is None:
        return None, text
    return parse_yaml_subset(raw), body


def iter_concepts(bundle_dir):
    """Yield Path for every non-reserved .md file under bundle_dir, sorted."""
    root = Path(bundle_dir)
    for path in sorted(root.rglob("*.md")):
        if path.name not in RESERVED:
            yield path


def concept_id(bundle_dir, path):
    """Concept ID = bundle-relative path with the .md suffix removed."""
    rel = Path(path).relative_to(Path(bundle_dir)).as_posix()
    return rel[:-3] if rel.endswith(".md") else rel


def extract_links(body):
    """Return the list of link targets from markdown links in body."""
    return _LINK_RE.findall(body)