feat: Add parquet file detection (#578)

Adds parquet file detection. See [docs](https://parquet.apache.org/docs/file-format/) for specification Co-authored-by: Keith Kelly <kkelly@morningconsult.com>
gabriel-vasile · Sep 26, 2024 · c4abedc · c4abedc
1 parent 4cc383c
commit c4abedc
Show file tree

Hide file tree

Showing 4 changed files with 7 additions and 2 deletions.
diff --git a/internal/magic/binary.go b/internal/magic/binary.go
@@ -21,6 +21,8 @@ var (
 	SWF = prefix([]byte("CWS"), []byte("FWS"), []byte("ZWS"))
 	// Torrent has bencoded text in the beginning.
 	Torrent = prefix([]byte("d8:announce"))
+	// PAR1 matches a parquet file.
+	Par1 = prefix([]byte{0x50, 0x41, 0x52, 0x31})
 )
 
 // Java bytecode and Mach-O binaries share the same magic number.

diff --git a/supported_mimes.md b/supported_mimes.md
@@ -1,4 +1,4 @@
-## 175 Supported MIME types
+## 176 Supported MIME types
 This file is automatically generated when running tests. Do not edit manually.
 
 Extension | MIME type | Aliases
@@ -143,6 +143,7 @@ Extension | MIME type | Aliases
 **.glb** | model/gltf-binary | -
 **.cab** | application/x-installshield | -
 **.jxr** | image/jxr | image/vnd.ms-photo
+**.parquet** | application/vnd.apache.parquet | application/x-parquet
 **.txt** | text/plain | -
 **.html** | text/html | -
 **.svg** | image/svg+xml | -

diff --git a/testdata/parquet.parquet b/testdata/parquet.parquet
diff --git a/tree.go b/tree.go
@@ -23,7 +23,7 @@ var root = newMIME("application/octet-stream", "",
 	avi, flv, mkv, asf, aac, voc, m3u, rmvb, gzip, class, swf, crx, ttf, woff,
 	woff2, otf, ttc, eot, wasm, shx, dbf, dcm, rar, djvu, mobi, lit, bpg,
 	sqlite3, dwg, nes, lnk, macho, qcp, icns, hdr, mrc, mdb, accdb, zstd, cab,
-	rpm, xz, lzip, torrent, cpio, tzif, xcf, pat, gbr, glb, cabIS, jxr,
+	rpm, xz, lzip, torrent, cpio, tzif, xcf, pat, gbr, glb, cabIS, jxr, parquet,
 	// Keep text last because it is the slowest check.
 	text,
 )
@@ -258,4 +258,6 @@ var (
 	xfdf    = newMIME("application/vnd.adobe.xfdf", ".xfdf", magic.Xfdf)
 	glb     = newMIME("model/gltf-binary", ".glb", magic.Glb)
 	jxr     = newMIME("image/jxr", ".jxr", magic.Jxr).alias("image/vnd.ms-photo")
+	parquet = newMIME("application/vnd.apache.parquet", ".parquet", magic.Par1).
+		alias("application/x-parquet")
 )