dataconvert updates

soleprint/station/tools/dataconvert/README.md

@@ -46,6 +46,8 @@ Every key is optional.
 
 - **out_dir, max_rows, schema** are the run settings: the same as `--out-dir`,
   `--max-rows` and `--no-schema`, and a flag on the command line wins over the file.
+  There is no default output directory: without `--out-dir` or an `out_dir` in the
+  config, the run stops before writing anything.
   `out_dir` is relative to the folder the config is in, so `"sample"` beside the data
   means `<source>/sample`. Inputs whose configs name different `out_dir`s each get
   their own `SCHEMA.md`.

soleprint/station/tools/dataconvert/dataconvert.py

@@ -44,7 +44,7 @@ def main():
     parser = argparse.ArgumentParser(description="Convert data sources into schema-agnostic SQL seed files.")
     parser.add_argument("--input", nargs="+", required=True, help="Input file(s), directory, wildcard pattern(s), or ZIP archive(s)")
     parser.add_argument("--out-dir", default=None,
-                        help="Directory where individual .sql files will be written (default: the config's out_dir, else ./seed)")
+                        help="Directory where individual .sql files will be written (default: the config's out_dir; one of the two is required)")
     parser.add_argument("--max-rows", type=positive_int, default=None,
                         help="Write at most N rows per table; the header and SCHEMA.md note the full row count and size (default: the config's max_rows, else all)")
     parser.add_argument("--no-schema", action="store_true", help="Do not write SCHEMA.md, whatever the config says")
@@ -81,6 +81,17 @@ def main():
                 parser.error(str(e))
         plan.append((in_path, loaded[found] if found is not None else cfg.Config(forced=forced)))
 
+    # No silent default directory. A run whose config was not found would
+    # otherwise write, unlaid-out, into ./seed wherever it was started, and look
+    # like it worked. Checked for every input before anything is written.
+    if not args.out_dir:
+        for in_path, config in plan:
+            if config.out_dir is not None:
+                continue
+            where = (f"{config.source} sets no out_dir" if config.source is not None
+                     else f"no {cfg.FILENAME} found in its folder")
+            parser.error(f"no output directory for {in_path} ({where}): pass --out-dir, or set out_dir in the config")
+
     # One report per output directory: inputs whose configs name different
     # out_dirs each get their own SCHEMA.md, beside their own .sql files.
     reports = {}
@@ -91,12 +102,11 @@ def main():
             said = config.settings()
             print(f"[dataconvert] config: {config.source}" + (f" ({said})" if said else ""))
 
-        # The command line wins, then the config, then the built-in default.
-        out_dir = Path(args.out_dir) if args.out_dir else (config.out_dir or Path("seed"))
+        # The command line wins, then the config.
+        out_dir = Path(args.out_dir) if args.out_dir else config.out_dir
         max_rows = args.max_rows if args.max_rows is not None else config.max_rows
         schema = not args.no_schema and config.schema is not False
 
-        out_dir.mkdir(parents=True, exist_ok=True)
         key = out_dir.resolve()
         if key not in reports:
             reports[key] = (out_dir, SchemaReport(), set())
@@ -107,7 +117,7 @@ def main():
             write_tables(dfs, out_dir, source_name, max_rows, report if schema else None, config.bare_sheet_prefixes)
 
     for out_dir, report, caps in reports.values():
-        if report.entries:
+        if report.entries and out_dir.is_dir():
             # The sampling note names the cap only when every input here used
             # the same one; otherwise each table's row still says what it kept.
             cap = next(iter(caps)) if len(caps) == 1 else None

soleprint/station/tools/dataconvert/output.py

@@ -29,6 +29,9 @@ def write_tables(dfs: dict, out_dir: Path, source_name: str, max_rows=None, repo
         filename = table_filename(raw_name, source_name, len(dfs), bare_prefixes)
         sql, total, full_bytes, exact = render_table(df, table, max_rows)
         out_file = out_dir / filename
+        # Created on the first file, so a run that finds nothing to convert
+        # leaves no empty directory behind.
+        out_dir.mkdir(parents=True, exist_ok=True)
 
         # Several sources can feed the same table; they accumulate in one file.
         mode = "a" if out_file.exists() else "w"