xsv: add reverse command

reverse command to reverse rows of CSV data.
Unlike sort command, it preserves order of rows with the same key.

PR #134 

6 files changed, 97 insertions, 0 deletions

diff --git a/README.md b/README.md
index ca0264b..faf0e5f 100644
--- a/README.md
+++ b/README.md
@@ -38,6 +38,7 @@ Dual-licensed under MIT or the [UNLICENSE](http://unlicense.org).
 * **partition** - Partition CSV data based on a column value.
 * **sample** - Randomly draw rows from CSV data using reservoir sampling (i.e.,
   use memory proportional to the size of the sample).
+* **reverse** - Reverse order of rows in CSV data.
 * **search** - Run a regex over CSV data. Applies the regex to each field
   individually and shows only matching rows.
 * **select** - Select or re-order columns from CSV data.
diff --git a/src/cmd/mod.rs b/src/cmd/mod.rs
index a3fb63a..921ad00 100644
--- a/src/cmd/mod.rs
+++ b/src/cmd/mod.rs
@@ -9,6 +9,7 @@ pub mod index;
 pub mod input;
 pub mod join;
 pub mod partition;
+pub mod reverse;
 pub mod sample;
 pub mod search;
 pub mod select;
diff --git a/src/cmd/reverse.rs b/src/cmd/reverse.rs
new file mode 100644
index 0000000..a04ff3a
--- /dev/null
+++ b/src/cmd/reverse.rs
@@ -0,0 +1,52 @@
+use CliResult;
+use config::{Config, Delimiter};
+use util;
+
+static USAGE: &'static str = "
+Reverses rows of CSV data.
+
+Useful for cases when there is no column that can be used for sorting in reverse order,
+or when keys are not unique and order of rows with the same key needs to be preserved.
+
+Note that this requires reading all of the CSV data into memory.
+
+Usage:
+    xsv reverse [options] [<input>]
+
+Common options:
+    -h, --help             Display this message
+    -o, --output <file>    Write output to <file> instead of stdout.
+    -n, --no-headers       When set, the first row will not be interpreted
+                           as headers. Namely, it will be reversed with the rest
+                           of the rows. Otherwise, the first row will always
+                           appear as the header row in the output.
+    -d, --delimiter <arg>  The field delimiter for reading CSV data.
+                           Must be a single character. (default: ,)
+";
+
+#[derive(Deserialize)]
+struct Args {
+    arg_input: Option<String>,
+    flag_output: Option<String>,
+    flag_no_headers: bool,
+    flag_delimiter: Option<Delimiter>,
+}
+
+pub fn run(argv: &[&str]) -> CliResult<()> {
+    let args: Args = util::get_args(USAGE, argv)?;
+    let rconfig = Config::new(&args.arg_input)
+        .delimiter(args.flag_delimiter)
+        .no_headers(args.flag_no_headers);
+
+    let mut rdr = rconfig.reader()?;
+
+    let mut all = rdr.byte_records().collect::<Result<Vec<_>, _>>()?;
+    all.reverse();
+
+    let mut wtr = Config::new(&args.flag_output).writer()?;
+    rconfig.write_headers(&mut rdr, &mut wtr)?;
+    for r in all.into_iter() {
+        wtr.write_byte_record(&r)?;
+    }
+    Ok(wtr.flush()?)
+}
diff --git a/src/main.rs b/src/main.rs
index 31c9958..c1465a3 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -56,6 +56,7 @@ macro_rules! command_list {
     join        Join CSV files
     partition   Partition CSV data based on a column value
     sample      Randomly sample CSV data
+    reverse     Reverse rows of CSV data
     search      Search CSV data with regexes
     select      Select columns from CSV
     slice       Slice records from CSV
@@ -150,6 +151,7 @@ enum Command {
     Input,
     Join,
     Partition,
+    Reverse,
     Sample,
     Search,
     Select,
@@ -178,6 +180,7 @@ impl Command {
             Command::Input => cmd::input::run(argv),
             Command::Join => cmd::join::run(argv),
             Command::Partition => cmd::partition::run(argv),
+            Command::Reverse => cmd::reverse::run(argv),
             Command::Sample => cmd::sample::run(argv),
             Command::Search => cmd::search::run(argv),
             Command::Select => cmd::select::run(argv),
diff --git a/tests/test_reverse.rs b/tests/test_reverse.rs
new file mode 100644
index 0000000..c0bce3f
--- /dev/null
+++ b/tests/test_reverse.rs
@@ -0,0 +1,39 @@
+use workdir::Workdir;
+
+use {Csv, CsvData, qcheck};
+
+fn prop_reverse(name: &str, rows: CsvData, headers: bool) -> bool {
+    let wrk = Workdir::new(name);
+    wrk.create("in.csv", rows.clone());
+
+    let mut cmd = wrk.command("reverse");
+    cmd.arg("in.csv");
+    if !headers { cmd.arg("--no-headers"); }
+
+    let got: Vec<Vec<String>> = wrk.read_stdout(&mut cmd);
+    let mut expected = rows.to_vecs();
+    let headers = if headers && !expected.is_empty() {
+        expected.remove(0)
+    } else {
+        vec![]
+    };
+    expected.reverse();
+    if !headers.is_empty() { expected.insert(0, headers); }
+    rassert_eq!(got, expected)
+}
+
+#[test]
+fn prop_reverse_headers() {
+    fn p(rows: CsvData) -> bool {
+        prop_reverse("prop_reverse_headers", rows, true)
+    }
+    qcheck(p as fn(CsvData) -> bool);
+}
+
+#[test]
+fn prop_reverse_no_headers() {
+    fn p(rows: CsvData) -> bool {
+        prop_reverse("prop_reverse_no_headers", rows, false)
+    }
+    qcheck(p as fn(CsvData) -> bool);
+}
diff --git a/tests/tests.rs b/tests/tests.rs
index afd2832..db2f3b3 100644
--- a/tests/tests.rs
+++ b/tests/tests.rs
@@ -43,6 +43,7 @@ mod test_headers;
 mod test_index;
 mod test_join;
 mod test_partition;
+mod test_reverse;
 mod test_search;
 mod test_select;
 mod test_slice;