Auto merge of #36807 - brson:pal, r=brson

Restrict where in the tree platform-specific cfgs may be mentioned

With the ports of Rust never ending, it's important that we keep things tidy. The main thing this PR does is introduce  a new "pal" (platform abstraction layer) tidy check that limits where platform-specific CFGs may appear.

This is intended to maintain existing standards of code organization
in hopes that the standard library will continue to be refactored to
isolate platform-specific bits, making porting easier; where "standard
library" roughly means "all the dependencies of the std and test
crates".

This generally means placing restrictions on where `cfg(unix)`,
`cfg(windows)`, `cfg(target_os)` and `cfg(target_env)` may appear,
the basic objective being to isolate platform-specific code to the
platform-specific `std::sys` modules, and to the allocation,
unwinding, and libc crates.

Following are the basic rules, though there are currently
exceptions:

- core may not have platform-specific code
- liballoc_system may have platform-specific code
- liballoc_jemalloc may have platform-specific code
- libpanic_abort may have platform-specific code
- libpanic_unwind may have platform-specific code
- other crates in the std facade may not
- std may have platform-specific code in the following places
  - sys/unix/
  - sys/windows/
  - os/

There are plenty of exceptions today though, noted in the whitelist.

The end-state, IMO, is for the standard library to be portable by porting only `std::sys` (possibly extracted to its own crate), an allocator crate, an unwinder crate, and possibly a libc crate (if std depends on it); but that outcome is far off and independent of the utility of enforcing where such code lives today.

cc @rust-lang/libs

7 files changed, 224 insertions, 56 deletions

diff --git a/src/libstd/sys/windows/args.rs b/src/libstd/sys/windows/args.rs
new file mode 100644
index 00000000000..aa61f9adb82
--- /dev/null
+++ b/src/libstd/sys/windows/args.rs
@@ -0,0 +1,76 @@
+// Copyright 2012-2015 The Rust Project Developers. See the COPYRIGHT
+// file at the top-level directory of this distribution and at
+// http://rust-lang.org/COPYRIGHT.
+//
+// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+
+#![allow(dead_code)] // runtime init functions not used during testing
+
+use os::windows::prelude::*;
+use sys::c;
+use slice;
+use ops::Range;
+use ffi::OsString;
+use libc::{c_int, c_void};
+
+pub unsafe fn init(_argc: isize, _argv: *const *const u8) { }
+
+pub unsafe fn cleanup() { }
+
+pub fn args() -> Args {
+    unsafe {
+        let mut nArgs: c_int = 0;
+        let lpCmdLine = c::GetCommandLineW();
+        let szArgList = c::CommandLineToArgvW(lpCmdLine, &mut nArgs);
+
+        // szArcList can be NULL if CommandLinToArgvW failed,
+        // but in that case nArgs is 0 so we won't actually
+        // try to read a null pointer
+        Args { cur: szArgList, range: 0..(nArgs as isize) }
+    }
+}
+
+pub struct Args {
+    range: Range<isize>,
+    cur: *mut *mut u16,
+}
+
+unsafe fn os_string_from_ptr(ptr: *mut u16) -> OsString {
+    let mut len = 0;
+    while *ptr.offset(len) != 0 { len += 1; }
+
+    // Push it onto the list.
+    let ptr = ptr as *const u16;
+    let buf = slice::from_raw_parts(ptr, len as usize);
+    OsStringExt::from_wide(buf)
+}
+
+impl Iterator for Args {
+    type Item = OsString;
+    fn next(&mut self) -> Option<OsString> {
+        self.range.next().map(|i| unsafe { os_string_from_ptr(*self.cur.offset(i)) } )
+    }
+    fn size_hint(&self) -> (usize, Option<usize>) { self.range.size_hint() }
+}
+
+impl DoubleEndedIterator for Args {
+    fn next_back(&mut self) -> Option<OsString> {
+        self.range.next_back().map(|i| unsafe { os_string_from_ptr(*self.cur.offset(i)) } )
+    }
+}
+
+impl ExactSizeIterator for Args {
+    fn len(&self) -> usize { self.range.len() }
+}
+
+impl Drop for Args {
+    fn drop(&mut self) {
+        // self.cur can be null if CommandLineToArgvW previously failed,
+        // but LocalFree ignores NULL pointers
+        unsafe { c::LocalFree(self.cur as *mut c_void); }
+    }
+}
diff --git a/src/libstd/sys/windows/env.rs b/src/libstd/sys/windows/env.rs
new file mode 100644
index 00000000000..e6d74895774
--- /dev/null
+++ b/src/libstd/sys/windows/env.rs
@@ -0,0 +1,19 @@
+// Copyright 2012-2015 The Rust Project Developers. See the COPYRIGHT
+// file at the top-level directory of this distribution and at
+// http://rust-lang.org/COPYRIGHT.
+//
+// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+
+pub mod os {
+    pub const FAMILY: &'static str = "windows";
+    pub const OS: &'static str = "windows";
+    pub const DLL_PREFIX: &'static str = "";
+    pub const DLL_SUFFIX: &'static str = ".dll";
+    pub const DLL_EXTENSION: &'static str = "dll";
+    pub const EXE_SUFFIX: &'static str = ".exe";
+    pub const EXE_EXTENSION: &'static str = "exe";
+}
diff --git a/src/libstd/sys/windows/memchr.rs b/src/libstd/sys/windows/memchr.rs
new file mode 100644
index 00000000000..5a5386acaa5
--- /dev/null
+++ b/src/libstd/sys/windows/memchr.rs
@@ -0,0 +1,15 @@
+// Copyright 2015 The Rust Project Developers. See the COPYRIGHT
+// file at the top-level directory of this distribution and at
+// http://rust-lang.org/COPYRIGHT.
+//
+// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+//
+// Original implementation taken from rust-memchr
+// Copyright 2015 Andrew Gallant, bluss and Nicolas Koch
+
+// Fallback memchr is fastest on windows
+pub use sys_common::memchr::fallback::{memchr, memrchr};
diff --git a/src/libstd/sys/windows/mod.rs b/src/libstd/sys/windows/mod.rs
index 9741a704e8f..9cd6e6ca176 100644
--- a/src/libstd/sys/windows/mod.rs
+++ b/src/libstd/sys/windows/mod.rs
@@ -18,17 +18,21 @@ use time::Duration;
 
 #[macro_use] pub mod compat;
 
+pub mod args;
 pub mod backtrace;
 pub mod c;
 pub mod condvar;
 pub mod dynamic_lib;
+pub mod env;
 pub mod ext;
 pub mod fs;
 pub mod handle;
+pub mod memchr;
 pub mod mutex;
 pub mod net;
 pub mod os;
 pub mod os_str;
+pub mod path;
 pub mod pipe;
 pub mod process;
 pub mod rand;
diff --git a/src/libstd/sys/windows/os.rs b/src/libstd/sys/windows/os.rs
index 260fc3c4db6..7e28dd1e259 100644
--- a/src/libstd/sys/windows/os.rs
+++ b/src/libstd/sys/windows/os.rs
@@ -18,8 +18,6 @@ use error::Error as StdError;
 use ffi::{OsString, OsStr};
 use fmt;
 use io;
-use libc::{c_int, c_void};
-use ops::Range;
 use os::windows::ffi::EncodeWide;
 use path::{self, PathBuf};
 use ptr;
@@ -272,60 +270,6 @@ pub fn unsetenv(n: &OsStr) -> io::Result<()> {
     }).map(|_| ())
 }
 
-pub struct Args {
-    range: Range<isize>,
-    cur: *mut *mut u16,
-}
-
-unsafe fn os_string_from_ptr(ptr: *mut u16) -> OsString {
-    let mut len = 0;
-    while *ptr.offset(len) != 0 { len += 1; }
-
-    // Push it onto the list.
-    let ptr = ptr as *const u16;
-    let buf = slice::from_raw_parts(ptr, len as usize);
-    OsStringExt::from_wide(buf)
-}
-
-impl Iterator for Args {
-    type Item = OsString;
-    fn next(&mut self) -> Option<OsString> {
-        self.range.next().map(|i| unsafe { os_string_from_ptr(*self.cur.offset(i)) } )
-    }
-    fn size_hint(&self) -> (usize, Option<usize>) { self.range.size_hint() }
-}
-
-impl DoubleEndedIterator for Args {
-    fn next_back(&mut self) -> Option<OsString> {
-        self.range.next_back().map(|i| unsafe { os_string_from_ptr(*self.cur.offset(i)) } )
-    }
-}
-
-impl ExactSizeIterator for Args {
-    fn len(&self) -> usize { self.range.len() }
-}
-
-impl Drop for Args {
-    fn drop(&mut self) {
-        // self.cur can be null if CommandLineToArgvW previously failed,
-        // but LocalFree ignores NULL pointers
-        unsafe { c::LocalFree(self.cur as *mut c_void); }
-    }
-}
-
-pub fn args() -> Args {
-    unsafe {
-        let mut nArgs: c_int = 0;
-        let lpCmdLine = c::GetCommandLineW();
-        let szArgList = c::CommandLineToArgvW(lpCmdLine, &mut nArgs);
-
-        // szArcList can be NULL if CommandLinToArgvW failed,
-        // but in that case nArgs is 0 so we won't actually
-        // try to read a null pointer
-        Args { cur: szArgList, range: 0..(nArgs as isize) }
-    }
-}
-
 pub fn temp_dir() -> PathBuf {
     super::fill_utf16_buf(|buf, sz| unsafe {
         c::GetTempPathW(sz, buf)
diff --git a/src/libstd/sys/windows/path.rs b/src/libstd/sys/windows/path.rs
new file mode 100644
index 00000000000..2b47808451b
--- /dev/null
+++ b/src/libstd/sys/windows/path.rs
@@ -0,0 +1,108 @@
+// Copyright 2015 The Rust Project Developers. See the COPYRIGHT
+// file at the top-level directory of this distribution and at
+// http://rust-lang.org/COPYRIGHT.
+//
+// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+
+use ascii::*;
+
+use path::Prefix;
+use ffi::OsStr;
+use mem;
+
+fn os_str_as_u8_slice(s: &OsStr) -> &[u8] {
+    unsafe { mem::transmute(s) }
+}
+unsafe fn u8_slice_as_os_str(s: &[u8]) -> &OsStr {
+    mem::transmute(s)
+}
+
+#[inline]
+pub fn is_sep_byte(b: u8) -> bool {
+    b == b'/' || b == b'\\'
+}
+
+#[inline]
+pub fn is_verbatim_sep(b: u8) -> bool {
+    b == b'\\'
+}
+
+pub fn parse_prefix<'a>(path: &'a OsStr) -> Option<Prefix> {
+    use path::Prefix::*;
+    unsafe {
+        // The unsafety here stems from converting between &OsStr and &[u8]
+        // and back. This is safe to do because (1) we only look at ASCII
+        // contents of the encoding and (2) new &OsStr values are produced
+        // only from ASCII-bounded slices of existing &OsStr values.
+        let mut path = os_str_as_u8_slice(path);
+
+        if path.starts_with(br"\\") {
+            // \\
+            path = &path[2..];
+            if path.starts_with(br"?\") {
+                // \\?\
+                path = &path[2..];
+                if path.starts_with(br"UNC\") {
+                    // \\?\UNC\server\share
+                    path = &path[4..];
+                    let (server, share) = match parse_two_comps(path, is_verbatim_sep) {
+                        Some((server, share)) =>
+                            (u8_slice_as_os_str(server), u8_slice_as_os_str(share)),
+                        None => (u8_slice_as_os_str(path), u8_slice_as_os_str(&[])),
+                    };
+                    return Some(VerbatimUNC(server, share));
+                } else {
+                    // \\?\path
+                    let idx = path.iter().position(|&b| b == b'\\');
+                    if idx == Some(2) && path[1] == b':' {
+                        let c = path[0];
+                        if c.is_ascii() && (c as char).is_alphabetic() {
+                            // \\?\C:\ path
+                            return Some(VerbatimDisk(c.to_ascii_uppercase()));
+                        }
+                    }
+                    let slice = &path[..idx.unwrap_or(path.len())];
+                    return Some(Verbatim(u8_slice_as_os_str(slice)));
+                }
+            } else if path.starts_with(b".\\") {
+                // \\.\path
+                path = &path[2..];
+                let pos = path.iter().position(|&b| b == b'\\');
+                let slice = &path[..pos.unwrap_or(path.len())];
+                return Some(DeviceNS(u8_slice_as_os_str(slice)));
+            }
+            match parse_two_comps(path, is_sep_byte) {
+                Some((server, share)) if !server.is_empty() && !share.is_empty() => {
+                    // \\server\share
+                    return Some(UNC(u8_slice_as_os_str(server), u8_slice_as_os_str(share)));
+                }
+                _ => (),
+            }
+        } else if path.get(1) == Some(& b':') {
+            // C:
+            let c = path[0];
+            if c.is_ascii() && (c as char).is_alphabetic() {
+                return Some(Disk(c.to_ascii_uppercase()));
+            }
+        }
+        return None;
+    }
+
+    fn parse_two_comps(mut path: &[u8], f: fn(u8) -> bool) -> Option<(&[u8], &[u8])> {
+        let first = match path.iter().position(|x| f(*x)) {
+            None => return None,
+            Some(x) => &path[..x],
+        };
+        path = &path[(first.len() + 1)..];
+        let idx = path.iter().position(|x| f(*x));
+        let second = &path[..idx.unwrap_or(path.len())];
+        Some((first, second))
+    }
+}
+
+pub const MAIN_SEP_STR: &'static str = "\\";
+pub const MAIN_SEP: char = '\\';
diff --git a/src/libstd/sys/windows/stdio.rs b/src/libstd/sys/windows/stdio.rs
index 01249f05f62..5f097d2631d 100644
--- a/src/libstd/sys/windows/stdio.rs
+++ b/src/libstd/sys/windows/stdio.rs
@@ -205,3 +205,5 @@ impl Output {
 fn invalid_encoding() -> io::Error {
     io::Error::new(io::ErrorKind::InvalidData, "text was not valid unicode")
 }
+
+pub const EBADF_ERR: i32 = ::sys::c::ERROR_INVALID_HANDLE as i32;