Merge branch 'master' into redox

Author: jackpot51

configure

@@ -856,7 +856,7 @@ probe_need CFG_CMAKE cmake
 if [ -n "$CFG_ANTLR4" ]
 then
    CFG_ANTLR4_JAR="\"$(find /usr/ -name antlr-complete.jar 2>/dev/null | head -n 1)\""
-   if [ "x" -eq "x$CFG_ANTLR4_JAR" ]
+   if [ "x" = "x$CFG_ANTLR4_JAR" ]
    then
      CFG_ANTLR4_JAR="\"$(find ~ -name antlr-complete.jar 2>/dev/null | head -n 1)\""
    fi

src/doc/book/lifetimes.md

@@ -352,7 +352,7 @@ to it.
 Rust supports powerful local type inference in the bodies of functions but not in their item signatures. 
 It's forbidden to allow reasoning about types based on the item signature alone. 
 However, for ergonomic reasons, a very restricted secondary inference algorithm called 
-“lifetime elision” does apply when judging lifetimes. Lifetime elision is concerned solely to infer 
+“lifetime elision” does apply when judging lifetimes. Lifetime elision is concerned solely with inferring 
 lifetime parameters using three easily memorizable and unambiguous rules. This means lifetime elision 
 acts as a shorthand for writing an item signature, while not hiding
 away the actual types involved as full local inference would if applied to it.

src/doc/reference.md

@@ -2474,18 +2474,19 @@ The currently implemented features of the reference compiler are:
                               internally without imposing on callers
                               (i.e. making them behave like function calls in
                               terms of encapsulation).
-* - `default_type_parameter_fallback` - Allows type parameter defaults to
-                                        influence type inference.
 
-* - `stmt_expr_attributes` - Allows attributes on expressions.
+* `default_type_parameter_fallback` - Allows type parameter defaults to
+                                      influence type inference.
 
-* - `type_ascription` - Allows type ascription expressions `expr: Type`.
+* `stmt_expr_attributes` - Allows attributes on expressions.
 
-* - `abi_vectorcall` - Allows the usage of the vectorcall calling convention
-                             (e.g. `extern "vectorcall" func fn_();`)
+* `type_ascription` - Allows type ascription expressions `expr: Type`.
 
-* - `abi_sysv64` - Allows the usage of the system V AMD64 calling convention
-                             (e.g. `extern "sysv64" func fn_();`)
+* `abi_vectorcall` - Allows the usage of the vectorcall calling convention
+                     (e.g. `extern "vectorcall" func fn_();`)
+
+* `abi_sysv64` - Allows the usage of the system V AMD64 calling convention
+                 (e.g. `extern "sysv64" func fn_();`)
 
 If a feature is promoted to a language feature, then all existing programs will
 start to receive compilation warnings about `#![feature]` directives which enabled

src/etc/char_private.py

@@ -11,11 +11,16 @@
 # except according to those terms.
 
 # This script uses the following Unicode tables:
-# - Categories.txt
+# - UnicodeData.txt
 
+
+from collections import namedtuple
+import csv
 import os
 import subprocess
 
+NUM_CODEPOINTS=0x110000
+
 def to_ranges(iter):
     current = None
     for i in iter:
@@ -28,10 +33,10 @@ def to_ranges(iter):
     if current is not None:
         yield tuple(current)
 
-def get_escaped(dictionary):
-    for i in range(0x110000):
-        if dictionary.get(i, "Cn") in "Cc Cf Cs Co Cn Zl Zp Zs".split() and i != ord(' '):
-            yield i
+def get_escaped(codepoints):
+    for c in codepoints:
+        if (c.class_ or "Cn") in "Cc Cf Cs Co Cn Zl Zp Zs".split() and c.value != ord(' '):
+            yield c.value
 
 def get_file(f):
     try:
@@ -40,10 +45,41 @@ def get_file(f):
         subprocess.run(["curl", "-O", f], check=True)
         return open(os.path.basename(f))
 
+Codepoint = namedtuple('Codepoint', 'value class_')
+
+def get_codepoints(f):
+    r = csv.reader(f, delimiter=";")
+    prev_codepoint = 0
+    class_first = None
+    for row in r:
+        codepoint = int(row[0], 16)
+        name = row[1]
+        class_ = row[2]
+
+        if class_first is not None:
+            if not name.endswith("Last>"):
+                raise ValueError("Missing Last after First")
+
+        for c in range(prev_codepoint + 1, codepoint):
+            yield Codepoint(c, class_first)
+
+        class_first = None
+        if name.endswith("First>"):
+            class_first = class_
+
+        yield Codepoint(codepoint, class_)
+        prev_codepoint = codepoint
+
+    if class_first != None:
+        raise ValueError("Missing Last after First")
+
+    for c in range(prev_codepoint + 1, NUM_CODEPOINTS):
+        yield Codepoint(c, None)
+
 def main():
-    file = get_file("http://www.unicode.org/notes/tn36/Categories.txt")
+    file = get_file("http://www.unicode.org/Public/UNIDATA/UnicodeData.txt")
 
-    dictionary = {int(line.split()[0], 16): line.split()[1] for line in file}
+    codepoints = get_codepoints(file)
 
     CUTOFF=0x10000
     singletons0 = []
@@ -52,7 +88,7 @@ def main():
     normal1 = []
     extra = []
 
-    for a, b in to_ranges(get_escaped(dictionary)):
+    for a, b in to_ranges(get_escaped(codepoints)):
         if a > 2 * CUTOFF:
             extra.append((a, b - a))
         elif a == b - 1:

src/libcollectionstest/str.rs

@@ -767,6 +767,7 @@ fn test_iterator() {
         pos += 1;
     }
     assert_eq!(pos, v.len());
+    assert_eq!(s.chars().count(), v.len());
 }
 
 #[test]
@@ -814,6 +815,14 @@ fn test_iterator_clone() {
     assert!(it.clone().zip(it).all(|(x,y)| x == y));
 }
 
+#[test]
+fn test_iterator_last() {
+    let s = "ศไทย中华Việt Nam";
+    let mut it = s.chars();
+    it.next();
+    assert_eq!(it.last(), Some('m'));
+}
+
 #[test]
 fn test_bytesator() {
     let s = "ศไทย中华Việt Nam";
@@ -911,6 +920,14 @@ fn test_char_indices_revator() {
     assert_eq!(pos, p.len());
 }
 
+#[test]
+fn test_char_indices_last() {
+    let s = "ศไทย中华Việt Nam";
+    let mut it = s.char_indices();
+    it.next();
+    assert_eq!(it.last(), Some((27, 'm')));
+}
+
 #[test]
 fn test_splitn_char_iterator() {
     let data = "\nMäry häd ä little lämb\nLittle lämb\n";