Mercurial > hg > CbC > CbC_llvm

annotate unittests/Support/UnicodeTest.cpp @ 56:bdef5c940791

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
copy the previous function's return type to return value
author Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
date Thu, 23 Jan 2014 23:14:57 +0900
parents 95c75e76d11b
children c2174574ed3a
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
1 //===- unittests/Support/UnicodeTest.cpp - Unicode.h tests ----------------===//
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
2 //
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
3 // The LLVM Compiler Infrastructure
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
4 //
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
5 // This file is distributed under the University of Illinois Open Source
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
6 // License. See LICENSE.TXT for details.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
7 //
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
8 //===----------------------------------------------------------------------===//
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
9
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
10 #include "llvm/Support/Unicode.h"
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
11 #include "gtest/gtest.h"
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
12
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
13 namespace llvm {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
14 namespace sys {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
15 namespace unicode {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
16 namespace {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
17
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
18 TEST(Unicode, columnWidthUTF8) {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
19 EXPECT_EQ(0, columnWidthUTF8(""));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
20 EXPECT_EQ(1, columnWidthUTF8(" "));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
21 EXPECT_EQ(1, columnWidthUTF8("a"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
22 EXPECT_EQ(1, columnWidthUTF8("~"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
23
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
24 EXPECT_EQ(6, columnWidthUTF8("abcdef"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
25
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
26 EXPECT_EQ(-1, columnWidthUTF8("\x01"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
27 EXPECT_EQ(-1, columnWidthUTF8("aaaaaaaaaa\x01"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
28 EXPECT_EQ(-1, columnWidthUTF8("\342\200\213")); // 200B ZERO WIDTH SPACE
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
29
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
30 // 00AD SOFT HYPHEN is displayed on most terminals as a space or a dash. Some
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
31 // text editors display it only when a line is broken at it, some use it as a
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
32 // line-break hint, but don't display. We choose terminal-oriented
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
33 // interpretation.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
34 EXPECT_EQ(1, columnWidthUTF8("\302\255"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
35
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
36 EXPECT_EQ(0, columnWidthUTF8("\314\200")); // 0300 COMBINING GRAVE ACCENT
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
37 EXPECT_EQ(1, columnWidthUTF8("\340\270\201")); // 0E01 THAI CHARACTER KO KAI
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
38 EXPECT_EQ(2, columnWidthUTF8("\344\270\200")); // CJK UNIFIED IDEOGRAPH-4E00
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
39
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
40 EXPECT_EQ(4, columnWidthUTF8("\344\270\200\344\270\200"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
41 EXPECT_EQ(3, columnWidthUTF8("q\344\270\200"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
42 EXPECT_EQ(3, columnWidthUTF8("\314\200\340\270\201\344\270\200"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
43
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
44 // Invalid UTF-8 strings, columnWidthUTF8 should error out.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
45 EXPECT_EQ(-2, columnWidthUTF8("\344"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
46 EXPECT_EQ(-2, columnWidthUTF8("\344\270"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
47 EXPECT_EQ(-2, columnWidthUTF8("\344\270\033"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
48 EXPECT_EQ(-2, columnWidthUTF8("\344\270\300"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
49 EXPECT_EQ(-2, columnWidthUTF8("\377\366\355"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
50
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
51 EXPECT_EQ(-2, columnWidthUTF8("qwer\344"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
52 EXPECT_EQ(-2, columnWidthUTF8("qwer\344\270"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
53 EXPECT_EQ(-2, columnWidthUTF8("qwer\344\270\033"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
54 EXPECT_EQ(-2, columnWidthUTF8("qwer\344\270\300"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
55 EXPECT_EQ(-2, columnWidthUTF8("qwer\377\366\355"));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
56
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
57 // UTF-8 sequences longer than 4 bytes correspond to unallocated Unicode
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
58 // characters.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
59 EXPECT_EQ(-2, columnWidthUTF8("\370\200\200\200\200")); // U+200000
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
60 EXPECT_EQ(-2, columnWidthUTF8("\374\200\200\200\200\200")); // U+4000000
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
61 }
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
62
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
63 TEST(Unicode, isPrintable) {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
64 EXPECT_FALSE(isPrintable(0)); // <control-0000>-<control-001F>
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
65 EXPECT_FALSE(isPrintable(0x01));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
66 EXPECT_FALSE(isPrintable(0x1F));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
67 EXPECT_TRUE(isPrintable(' '));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
68 EXPECT_TRUE(isPrintable('A'));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
69 EXPECT_TRUE(isPrintable('~'));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
70 EXPECT_FALSE(isPrintable(0x7F)); // <control-007F>..<control-009F>
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
71 EXPECT_FALSE(isPrintable(0x90));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
72 EXPECT_FALSE(isPrintable(0x9F));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
73
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
74 EXPECT_TRUE(isPrintable(0xAC));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
75 EXPECT_TRUE(isPrintable(0xAD)); // SOFT HYPHEN is displayed on most terminals
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
76 // as either a space or a dash.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
77 EXPECT_TRUE(isPrintable(0xAE));
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
78
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
79 EXPECT_TRUE(isPrintable(0x0377)); // GREEK SMALL LETTER PAMPHYLIAN DIGAMMA
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
80 EXPECT_FALSE(isPrintable(0x0378)); // <reserved-0378>..<reserved-0379>
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
81
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
82 EXPECT_FALSE(isPrintable(0x0600)); // ARABIC NUMBER SIGN
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
83
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
84 EXPECT_FALSE(isPrintable(0x1FFFF)); // <reserved-1F774>..<noncharacter-1FFFF>
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
85 EXPECT_TRUE(isPrintable(0x20000)); // CJK UNIFIED IDEOGRAPH-20000
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
86
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
87 EXPECT_FALSE(isPrintable(0x10FFFF)); // noncharacter
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
88 }
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
89
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
90 } // namespace
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
91 } // namespace unicode
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
92 } // namespace sys
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
93 } // namespace llvm