From aa7ad950590dffef2a7dc37135c763e9890a5b9e Mon Sep 17 00:00:00 2001
From: Lars Wirzenius <lars.wirzenius@codethink.co.uk>
Date: Tue, 20 May 2014 14:35:59 +0100
Subject: Initial commit

---
 mk-test-data |  32 ++++++++++++++++++
 recv-hole    |  41 +++++++++++++++++++++++
 test.sh      |  12 +++++++
 xfer-hole.py | 107 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 192 insertions(+)
 create mode 100755 mk-test-data
 create mode 100755 recv-hole
 create mode 100755 test.sh
 create mode 100755 xfer-hole.py

diff --git a/mk-test-data b/mk-test-data
new file mode 100755
index 0000000..57a3213
--- /dev/null
+++ b/mk-test-data
@@ -0,0 +1,32 @@
+#!/bin/sh
+
+data()
+{
+    echo -n "foobar" >> "$1"
+}
+
+hole()
+{
+    truncate --size +10240 "$1"
+}
+
+
+touch test.empty
+
+data test.data
+
+hole test.hole
+
+data test.data-hole
+hole test.data-hole
+
+hole test.hole-data
+data test.hole-data
+
+data test.data-hole-data
+hole test.data-hole-data
+data test.data-hole-data
+
+hole test.hole-data-hole
+data test.hole-data-hole
+hole test.hole-data-hole
diff --git a/recv-hole b/recv-hole
new file mode 100755
index 0000000..cd54233
--- /dev/null
+++ b/recv-hole
@@ -0,0 +1,41 @@
+#!/bin/sh
+
+set -eu
+
+
+die()
+{
+    echo "$@" 1>&2
+    exit 1
+}
+
+
+recv_hole()
+{
+    local n
+
+    read n
+    truncate --size "+$n" "$1"
+}
+
+
+recv_data()
+{
+    local n
+
+    read n
+    dd of="$1" conv=notrunc oflag=append bs=1 count="$n" status=noxfer 2>&1 | grep -Ev ' records (in|out)$' || true
+}
+
+
+output="$1"
+
+touch "$output"
+while read what
+do
+    case "$what" in
+        DATA) recv_data "$output" ;;
+        HOLE) recv_hole "$output" ;;
+        *) die "Unknown instruction: $what" ;;
+    esac
+done
diff --git a/test.sh b/test.sh
new file mode 100755
index 0000000..04f2d3f
--- /dev/null
+++ b/test.sh
@@ -0,0 +1,12 @@
+#!/bin/sh
+
+set -eu
+
+rm -rf result
+mkdir result
+for x in test.*
+do
+    echo "============== $x ================="
+    ./xfer-hole.py "$x" | ./recv-hole "result/$x"
+    cmp "$x" "result/$x"
+done
diff --git a/xfer-hole.py b/xfer-hole.py
new file mode 100755
index 0000000..0822232
--- /dev/null
+++ b/xfer-hole.py
@@ -0,0 +1,107 @@
+#!/usr/bin/env python
+
+
+import errno
+import os
+import sys
+
+
+SEEK_DATA = 3
+SEEK_HOLE = 4
+
+
+filename = sys.argv[1]
+fd = os.open(filename, os.O_RDONLY)
+pos = 0
+
+
+DATA = 'data'
+HOLE = 'hole'
+EOF = 'eof'
+
+
+def safe_lseek(fd, pos, whence):
+    try:
+        return os.lseek(fd, pos, whence)
+    except OSError as e:
+        if e.errno == errno.ENXIO:
+            return -1
+        raise
+
+
+def current_data_or_pos(fd, pos):
+    length = safe_lseek(fd, 0, os.SEEK_END)
+    next_data = safe_lseek(fd, pos, SEEK_DATA)
+    next_hole = safe_lseek(fd, pos, SEEK_HOLE)
+
+    if pos == length:
+        return EOF, pos
+    elif pos == next_data:
+        return DATA, pos
+    elif pos == next_hole:
+        return HOLE, pos
+    else:
+        assert False, \
+            ("Do not understand: pos=%d next_data=%d next_hole=%d" %
+             (pos, next_data, next_hole))
+
+
+def next_data_or_hole(fd, pos):
+    length = safe_lseek(fd, 0, os.SEEK_END)
+    next_data = safe_lseek(fd, pos, SEEK_DATA)
+    next_hole = safe_lseek(fd, pos, SEEK_HOLE)
+
+    if pos == length:
+        return EOF, pos
+    elif pos == next_data:
+        # We are at data.
+        if next_hole == -1 or next_hole == length:
+            return EOF, length
+        else:
+            return HOLE, next_hole
+    elif pos == next_hole:
+        # We are at a hole.
+        if next_data == -1 or next_data == length:
+            return EOF, length
+        else:
+            return DATA, next_data
+    else:
+        assert False, \
+            ("Do not understand: pos=%d next_data=%d next_hole=%d" %
+             (pos, next_data, next_hole))
+
+
+def find_data_and_holes(fd):
+    pos = safe_lseek(fd, 0, os.SEEK_CUR)
+
+    kind, pos = current_data_or_pos(fd, pos)
+    while kind != EOF:
+        yield kind, pos
+        kind, pos = next_data_or_hole(fd, pos)
+    yield kind, pos
+
+
+def make_xfer_instructions(fd):
+    prev_kind = None
+    prev_pos = None
+    for kind, pos in find_data_and_holes(fd):
+        if prev_kind == DATA:
+            yield (DATA, prev_pos, pos)
+        elif prev_kind == HOLE:
+            yield (HOLE, prev_pos, pos)
+        prev_kind = kind
+        prev_pos = pos
+
+
+def copy_slice_from_file(to, fd, start, end):
+    safe_lseek(fd, start, os.SEEK_SET)
+    data = os.read(fd, end - start)
+    to.write(data)
+    
+
+for kind, start, end in make_xfer_instructions(fd):
+    if kind == HOLE:
+        sys.stdout.write('HOLE\n%d\n' % (end - start))
+    elif kind == DATA:
+        sys.stdout.write('DATA\n%d\n' % (end - start))
+        copy_slice_from_file(sys.stdout, fd, start, end)
-- 
cgit v1.2.1