avplan: paths an encoder can actually read, and a pipeline that runs

parity/KNOWN.md

@@ -268,3 +268,29 @@ sheet.
 and the contract gives them different numbers. A caller that wants the
 Python's behaviour treats both as no; a caller that wants to know which files
 it failed on can now find out.
+
+## avplan — separators in a path, and a destination that starts with a dash
+
+**Original:** builds the destination by byte arithmetic — the path, minus as
+many bytes as the extension is long, plus `.h264.mp4`. Its extension function
+ignores trailing separators while the subtraction does not, so `x.mp4//`
+becomes `x.m.h264.mp4`. Duplicate separators are carried through, and a
+destination beginning with `-` is emitted bare.
+
+**Rust:** takes the path apart properly. `film.mp4/.` is a directory and has
+no extension rather than an `mp4` one; `/talk.webm` becomes `/talk.h264.mp4`
+rather than `//talk.h264.mp4`; `x.mp4//` becomes `x.h264.mp4`. A destination
+beginning with `-` is written `./-name`, which is the same file and cannot be
+read as an option.
+
+**Why this is acceptable:** every one of these is a path the original gets
+wrong. A double leading separator is left to the system to interpret and some
+systems interpret it as something else; `x.m.h264.mp4` names a file nobody
+asked for; a directory reported as a playable MP4 is a wrong answer outright;
+and a command line whose destination is read as an option fails on a file
+that was otherwise fine. The original never met any of them because its paths
+were always joined onto an absolute root.
+
+**Measured:** 32 cases, including a file at the root, a name beginning with a
+dash, a name that is only a dot, a non-ASCII name and an extension that is
+only a dot. Ordinary paths — the overwhelming majority — are byte-identical.

parity/cases/avplan/cases.ndjson

@@ -22,3 +22,11 @@
 {"name":"codec-merely-containing-h264","path":"/media/x.mp4","video":"prores_h264ish","audio":"aac","encoder":"libx264"}
 {"name":"mpeg4-in-avi","path":"/media/old.avi","video":"mpeg4","audio":"mp3","encoder":"h264_nvenc"}
 {"name":"hevc-in-mkv-aac","path":"/media/film.mkv","video":"hev1.1.6.L93","audio":"aac","encoder":"h264_nvenc"}
+{"name":"at-the-filesystem-root","path":"/talk.webm","video":"vp9","audio":"opus","encoder":"libx264"}
+{"name":"a-name-beginning-with-a-dash","path":"/media/-clip.webm","video":"vp9","audio":"opus","encoder":"libx264"}
+{"name":"a-name-that-is-only-a-dot","path":"/media/.hidden.webm","video":"vp9","audio":"opus","encoder":"libx264"}
+{"name":"an-upper-case-codec","path":"/media/x.mkv","video":"H264","audio":"AAC","encoder":"libx264"}
+{"name":"a-codec-with-a-profile-suffix","path":"/media/x.mp4","video":"hev1.2.4.L120.B0","audio":"mp4a.40.5","encoder":"libx264"}
+{"name":"a-non-ascii-name","path":"/media/Καλημέρα.webm","video":"vp9","audio":"opus","encoder":"libx264"}
+{"name":"an-extension-that-is-only-a-dot","path":"/media/talk.","video":"vp9","audio":"opus","encoder":"libx264"}
+{"name":"a-relative-name-beginning-with-a-dash","path":"-clip.webm","video":"vp9","audio":"opus","encoder":"libx264"}

parity/golden/avplan/cases.ndjson

@@ -22,3 +22,11 @@
 {"path":"/media/x.mp4","playable":false,"encoder":"libx264","copies_audio":true,"argv":["-nostdin","-y","-i","/media/x.mp4","-c:v","libx264","-preset","veryfast","-crf","23","-pix_fmt","yuv420p","-c:a","copy","-movflags","+faststart","/media/x.h264.mp4"]}
 {"path":"/media/old.avi","playable":false,"encoder":"h264_nvenc","copies_audio":false,"argv":["-nostdin","-y","-i","/media/old.avi","-c:v","h264_nvenc","-preset","p5","-rc","vbr","-cq","23","-b:v","0","-c:a","aac","-b:a","160k","-ac","2","-movflags","+faststart","/media/old.h264.mp4"]}
 {"path":"/media/film.mkv","playable":false,"encoder":"copy","copies_audio":true,"argv":["-nostdin","-y","-i","/media/film.mkv","-c:v","copy","-c:a","copy","-movflags","+faststart","/media/film.h264.mp4"]}
+{"path":"/talk.webm","playable":false,"encoder":"libx264","copies_audio":false,"argv":["-nostdin","-y","-i","/talk.webm","-c:v","libx264","-preset","veryfast","-crf","23","-pix_fmt","yuv420p","-c:a","aac","-b:a","160k","-ac","2","-movflags","+faststart","/talk.h264.mp4"]}
+{"path":"/media/-clip.webm","playable":false,"encoder":"libx264","copies_audio":false,"argv":["-nostdin","-y","-i","/media/-clip.webm","-c:v","libx264","-preset","veryfast","-crf","23","-pix_fmt","yuv420p","-c:a","aac","-b:a","160k","-ac","2","-movflags","+faststart","/media/-clip.h264.mp4"]}
+{"path":"/media/.hidden.webm","playable":false,"encoder":"libx264","copies_audio":false,"argv":["-nostdin","-y","-i","/media/.hidden.webm","-c:v","libx264","-preset","veryfast","-crf","23","-pix_fmt","yuv420p","-c:a","aac","-b:a","160k","-ac","2","-movflags","+faststart","/media/.hidden.h264.mp4"]}
+{"path":"/media/x.mkv","playable":false,"encoder":"copy","copies_audio":true,"argv":["-nostdin","-y","-i","/media/x.mkv","-c:v","copy","-c:a","copy","-movflags","+faststart","/media/x.h264.mp4"]}
+{"path":"/media/x.mp4","playable":true,"encoder":null,"copies_audio":true,"argv":[]}
+{"path":"/media/Καλημέρα.webm","playable":false,"encoder":"libx264","copies_audio":false,"argv":["-nostdin","-y","-i","/media/Καλημέρα.webm","-c:v","libx264","-preset","veryfast","-crf","23","-pix_fmt","yuv420p","-c:a","aac","-b:a","160k","-ac","2","-movflags","+faststart","/media/Καλημέρα.h264.mp4"]}
+{"path":"/media/talk.","playable":false,"encoder":"libx264","copies_audio":false,"argv":["-nostdin","-y","-i","/media/talk.","-c:v","libx264","-preset","veryfast","-crf","23","-pix_fmt","yuv420p","-c:a","aac","-b:a","160k","-ac","2","-movflags","+faststart","/media/talk.h264.mp4"]}
+{"path":"-clip.webm","playable":false,"encoder":"libx264","copies_audio":false,"argv":["-nostdin","-y","-i","-clip.webm","-c:v","libx264","-preset","veryfast","-crf","23","-pix_fmt","yuv420p","-c:a","aac","-b:a","160k","-ac","2","-movflags","+faststart","-clip.h264.mp4"]}

parity/tests/avplan.rs

@@ -12,6 +12,12 @@ use serde_json::Value;
 /// The encoder the server defaults to when nothing names one.
 const DEFAULT_ENCODER: &str = "h264_nvenc";
 
+/// Answers that are meant to differ, each argued for in `KNOWN.md`.
+///
+/// The original emits a destination beginning with a dash bare, and an
+/// encoder reads it as an option rather than a file.
+const DIVERGENT: &[(&str, &str)] = &[("a-relative-name-beginning-with-a-dash", "argv")];
+
 fn named(name: &str) -> avplan::Encoder {
     *avplan::encoder::PREFERRED
         .iter()
@@ -60,6 +66,9 @@ fn every_verdict_matches_the_original() {
         let ours = avplan::plan(path, &streams, Some(chosen), &output, device);
 
         let mut note = |field: &str, ours: String, theirs: &Value| {
+            if DIVERGENT.contains(&(name, field)) {
+                return;
+            }
             wrong.push(format!("{name}.{field}: original {theirs}, rust {ours}"));
         };
 
@@ -99,6 +108,34 @@ fn every_verdict_matches_the_original() {
     );
 }
 
+/// A divergence that has quietly gone away is a note in `KNOWN.md` that is no
+/// longer true, which is worth knowing about.
+#[test]
+fn the_documented_divergence_is_exactly_what_was_argued_for() {
+    let case = cases()
+        .into_iter()
+        .find(|case| case["name"] == "a-relative-name-beginning-with-a-dash")
+        .expect("the case exists");
+    let path = case["path"].as_str().expect("a path");
+    let streams = avplan::Streams {
+        video: case["video"].as_str().map(str::to_string),
+        audio: case["audio"].as_str().map(str::to_string),
+        container: avplan::container_of(path),
+    };
+    let ours = avplan::plan(
+        path,
+        &streams,
+        Some(named("libx264")),
+        &avplan::output_beside(path),
+        avplan::DEFAULT_VAAPI_DEVICE,
+    );
+    assert_eq!(
+        ours.argv.last().map(String::as_str),
+        Some("./-clip.h264.mp4"),
+        "the destination is no longer named so an encoder reads it as a file"
+    );
+}
+
 /// Every branch of the encoder table has to be exercised, or the parity test
 /// proves nothing about the three encoders nobody's laptop happens to have.
 #[test]