From bb7a485c0932375b888a61966970696c06851a15 Mon Sep 17 00:00:00 2001
From: Mohammad AlSaleh <CE.Mohammad.AlSaleh@gmail.com>
Date: Thu, 4 Apr 2024 10:23:00 +0300
Subject: [PATCH] stream: don't try to read from all-sparse/no-data files

 ```
 dd if=/dev/zero of=/tmp/10g.empty bs=1 seek=10G count=0
 dd if=/dev/zero of=/tmp/10m.empty bs=1 seek=10M count=0
 time mpv /tmp/10{g,m}.empty
 ```

 I keep files with the name format `${name}-${hash}.${ext}.empty`
 around, where the original is removed, and a sparse file with
 the size of the original is created instead.

 A lot of time is wasted on such files when going through
 playlists/directories that include some of them.

 This admittedly may not be that common of a use-case.

Signed-off-by: Mohammad AlSaleh <CE.Mohammad.AlSaleh@gmail.com>
---
 meson.build          |  3 +++
 stream/stream_file.c | 11 +++++++++++
 2 files changed, 14 insertions(+)

diff --git a/meson.build b/meson.build
index b0283c87b3..20b5af2d81 100644
--- a/meson.build
+++ b/meson.build
@@ -438,6 +438,9 @@ endif
 features += {'ppoll': cc.has_function('ppoll', args: '-D_GNU_SOURCE',
                                       prefix: '#include <poll.h>')}
 
+features += {'seek-data': cc.has_header_symbol('errno.h', 'ENXIO') and
+    cc.has_header_symbol('unistd.h', 'SEEK_DATA', args: '-D_GNU_SOURCE')}
+
 cd_devices = {
     'windows': 'D:',
     'cygwin': 'D:',
diff --git a/stream/stream_file.c b/stream/stream_file.c
index 1744fc13a4..0a6a697ff6 100644
--- a/stream/stream_file.c
+++ b/stream/stream_file.c
@@ -358,6 +358,17 @@ static int open_f(stream_t *stream, const struct stream_open_args *args)
     setmode(p->fd, O_BINARY);
 #endif
 
+#if HAVE_SEEK_DATA
+    if (stream->mode == STREAM_READ) {
+        off_t first_data = lseek(p->fd, 0, SEEK_DATA);
+        if (first_data == (off_t)-1 && errno == ENXIO) {
+            MP_ERR(stream, "File is empty or all sparse (has no data).\n");
+            s_close(stream);
+            return STREAM_ERROR;
+        }
+    }
+#endif
+
     off_t len = lseek(p->fd, 0, SEEK_END);
     lseek(p->fd, 0, SEEK_SET);
     if (len != (off_t)-1) {