feat(content-build): scaffold package + Markdown yaml-block parser

tools/content_build/parse.py

@@ -0,0 +1,40 @@
+"""Markdown bible -> raw yaml-block entries. Knows only fences + YAML; nothing
+about the schema's meaning. A block is opened by a line that is exactly ```yaml
+(after strip) and closed by a line that is exactly ```."""
+
+from dataclasses import dataclass
+from pathlib import Path
+
+import yaml
+
+from .errors import BuildError
+
+
+@dataclass
+class RawEntry:
+    data: dict
+    source: str  # "duncarrow.md:53"
+
+
+def parse_bible(path: Path) -> list[RawEntry]:
+    lines = path.read_text().splitlines()
+    entries: list[RawEntry] = []
+    i, n = 0, len(lines)
+    while i < n:
+        if lines[i].strip() == "```yaml":
+            fence_line = i + 1  # 1-based line of the opening fence
+            i += 1
+            block: list[str] = []
+            while i < n and lines[i].strip() != "```":
+                block.append(lines[i])
+                i += 1
+            if i >= n:
+                raise BuildError("unterminated ```yaml block",
+                                 source=f"{path.name}:{fence_line}")
+            data = yaml.safe_load("\n".join(block))
+            if not isinstance(data, dict):
+                raise BuildError("yaml block is not a mapping",
+                                 source=f"{path.name}:{fence_line}")
+            entries.append(RawEntry(data=data, source=f"{path.name}:{fence_line}"))
+        i += 1
+    return entries