mdscrub: residual html, control characters, headings, page markers

parity/oracle/mdscrub.py

@@ -0,0 +1,26 @@
+"""Clean converted markdown the way the Python pipeline does.
+
+Reads markdown on stdin, writes the cleaned markdown on stdout.
+
+    CATENA_PARITY_PYTHONPATH=/path/to/book-pipeline/src \
+        python3 oracle/mdscrub.py < case.md
+"""
+
+import os
+import sys
+
+for path in os.environ.get("CATENA_PARITY_PYTHONPATH", "").split(os.pathsep):
+    if path:
+        sys.path.insert(0, path)
+
+from book_pipeline.convert import _epub_postprocess  # noqa: E402
+
+
+def main() -> int:
+    markdown = sys.stdin.buffer.read().decode("utf-8")
+    sys.stdout.write(_epub_postprocess(markdown))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())