From 17d17038067d9abf02d74f02040a8fcff6abc237 Mon Sep 17 00:00:00 2001 From: Lilleman auf Larv Date: Fri, 18 Sep 2026 22:03:09 +0200 Subject: [PATCH] Match the loader's two-row floor, and record that an extension may name two media types --- README.md | 9 +++++++-- data-import/mimetype.py | 1 - data-import/tsv.py | 6 +++--- 3 files changed, 10 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 94ed628..ad915dc 100644 --- a/README.md +++ b/README.md @@ -163,8 +163,8 @@ Each locale carries `address`, `color`, `company`, `date`, `email`, `first-name` `personnummer` and `samordningsnummer`, `en_US` adds `ssn` and `itin`. `misc` carries `car`, `coordinate`, `country` (ISO 3166), `creditcard` (Luhn-valid), `currency` (ISO 4217), `datetime` (RFC 3339), `emoji`, `httpstatus`, `language` -(ISO 639-1, with its 639-2/T code), `mac`, `mimetype`, `objectid`, `timezone` (IANA), -`useragent` and `uuid` (v4). Many carry sub-fields — `misc.currency.symbol`, +(ISO 639-1, with its 639-2/T code), `mac`, `mimetype`, `objectid`, `timezone` +(IANA), `useragent` and `uuid` (v4). Many carry sub-fields — `misc.currency.symbol`, `misc.country.alpha2`, `misc.httpstatus.code` — which `--list` shows. `country`, `currency`, `httpstatus`, `language` and `mimetype` are [tables](#table), so `misc.country[SE].capital` and `misc.currency[Euro].symbol` select a row; @@ -1130,6 +1130,11 @@ App developers writing tests and fixtures, in Go and at a shell: and VED beside VES, both Venezuela's, of which a country row names one. Linking would trade the register for the link, and `misc.country.currency` already pairs a country with its currency in one draw. +- **An extension may name two media types.** `.xml`, `.rtf`, `.sub`, `.mpp` and `.ac` + each name two rows of `misc.mimetype`. Separating them would mean dropping a + registered type, or naming one by an extension that is not its own — `.mpt` is + Project's template, not its document. Selecting such a name is an error listing + both keys; select by type instead. - **The Swedish ids draw Skatteverket's test series.** A Luhn-valid personnummer over a random birth number may be a living person's; 238 and 239 after any date are blocked from assignment, so the shipped `personnummer` and diff --git a/data-import/mimetype.py b/data-import/mimetype.py index 1ac4fc2..b749f66 100644 --- a/data-import/mimetype.py +++ b/data-import/mimetype.py @@ -16,7 +16,6 @@ SOURCE = "https://raw.githubusercontent.com/jshttp/mime-db/master/db.json" OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "mimetype.tsv" CACHE = Path(__file__).resolve().parent / "cache" COLUMNS = ["ext", "type"] -# mime-db lists extensions in no particular order, so where the everyday one is not first, name it. FIXUPS = {"application/mp4": "mp4s", "audio/mpeg": "mp3", "audio/ogg": "ogg", "video/quicktime": "mov"} diff --git a/data-import/tsv.py b/data-import/tsv.py index f46fcc9..51ea6ea 100644 --- a/data-import/tsv.py +++ b/data-import/tsv.py @@ -5,14 +5,14 @@ from pathlib import Path def write(path, columns, rows): - """Write the rows as a TSV; the table needs a row, and every cell must be non-empty and free of tabs, newlines and braces.""" + """Write the rows as a TSV; the table needs two rows, and every cell must be non-empty and free of tabs, newlines and braces.""" lines = ["\t".join(columns)] for row in rows: cells = [str(row[c]) for c in columns] if not all(cells) or any(re.search(r"[\t\n{}]", c) for c in cells): raise ValueError(f"{path}: a cell is empty or holds a tab, newline or brace: {row}") lines.append("\t".join(cells)) - if len(lines) < 2: - raise ValueError(f"{path}: has no rows below its header; a table is at least two rows") + if len(lines) < 3: + raise ValueError(f"{path}: has {len(lines) - 1} rows below its header; a table is at least two rows") Path(path).write_text("\n".join(lines) + "\n", encoding="utf-8") print(f"{path}: {len(lines) - 1} rows", file=sys.stderr)