Merge pull request #1372 from jqnatividad/sniff-just-mime

`sniff` add `--just-mime` option

README.md

@@ -228,6 +228,11 @@ The `to` command converts CSVs to `.xlsx`, [Parquet](https://parquet.apache.org)
 
 The `sqlp` command returns query results in CSV, JSON, Parquet & [Arrow IPC](https://arrow.apache.org/docs/format/Columnar.html#ipc-file-format) formats. Polars SQL also supports reading external files directly in various formats with its `read_ndjson`, `read_csv`, `read_parquet` & `read_ipc` [table functions](https://github.com/pola-rs/polars/blob/c7fa66a1340418789ec66bdedad6654281afa0ab/polars/polars-sql/src/table_functions.rs#L9-L36).
 
+The `sniff` command can also detect the mime type of any file with the `--no-infer` or `--just-mime` options, may it be local or remote (http and https schemes supported).
+It can detect more than 120 file formats, including MS Office/Open Document files, JSON, XML, 
+PDF, PNG, JPEG and specialized geospatial formats like GPX, GML, KML, TML, TMX, TSX, TTML.
+See https://docs.rs/file-format/latest/file_format/#reader-features for a complete list.
+
 ### Snappy Compression/Decompression
 
 qsv supports *automatic compression/decompression* using the [Snappy frame format](https://github.com/google/snappy/blob/main/framing_format.txt). Snappy was chosen instead of more popular compression formats like gzip because it was designed for [high-performance streaming compression & decompression](https://github.com/google/snappy/tree/main/docs#readme) (up to 2.58 gb/sec compression, 0.89 gb/sec decompression).

src/cmd/sniff.rs

@@ -84,6 +84,10 @@ sniff options:
                              (Unsigned, Signed => Integer, Text => String, everything else the same)
     --no-infer               Do not infer the schema. Only return the file's mime type, size and
                              last modified date. Use this to use sniff as a general mime type detector.
+                             Note that CSV and TSV files will only be detected as mime type plain/text
+                             in this mode.
+    --just-mime              Only return the file's mime type. Use this to use sniff as a general
+                             mime type detector. Synonym for --no-infer.
     --quick                  When sniffing a non-CSV remote file, only download the first chunk of the file
                              before attempting to detect the mime type. This is faster but less accurate as
                              some mime types cannot be detected with just the first downloaded chunk.
@@ -139,6 +143,7 @@ struct Args {
     flag_user_agent:     Option<String>,
     flag_stats_types:    bool,
     flag_no_infer:       bool,
+    flag_just_mime:      bool,
     flag_quick:          bool,
     flag_harvest_mode:   bool,
 }
@@ -714,6 +719,10 @@ async fn sniff_main(mut args: Args) -> CliResult<()> {
             Some("CKAN-harvest/$QSV_VERSION ($QSV_TARGET; $QSV_BIN_NAME)".to_string());
     }
 
+    if args.flag_just_mime {
+        args.flag_no_infer = true;
+    }
+
     let mut sample_size = args.flag_sample;
     if sample_size < 0.0 {
         if args.flag_json || args.flag_pretty_json {

tests/test_sniff.rs

@@ -100,6 +100,35 @@ fn sniff_notcsv() {
     assert!(got_error.starts_with(expected));
 }
 
+#[test]
+fn sniff_justmime() {
+    let wrk = Workdir::new("sniff_justmime");
+
+    let test_file = wrk.load_test_file("excel-xls.xls");
+
+    let mut cmd = wrk.command("sniff");
+    cmd.arg("--just-mime").arg(test_file);
+
+    let got: String = wrk.stdout(&mut cmd);
+
+    let expected = "Detected mime type: application/vnd.ms-excel";
+    assert!(got.starts_with(expected));
+}
+
+#[test]
+fn sniff_justmime_remote() {
+    let wrk = Workdir::new("sniff_justmime_remote");
+
+    let mut cmd = wrk.command("sniff");
+    cmd.arg("--just-mime")
+        .arg("https://github.com/jqnatividad/qsv/raw/master/resources/test/excel-xls.xls");
+
+    let got: String = wrk.stdout(&mut cmd);
+
+    let expected = "Detected mime type: application/vnd.ms-excel";
+    assert!(got.starts_with(expected));
+}
+
 #[test]
 fn sniff_url_snappy() {
     let wrk = Workdir::new("sniff_url_snappy");