Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(26)

Side by Side Diff: source/i18n/csrutf8.cpp

Issue 845603002: Update ICU to 54.1 step 1 (Closed) Base URL: https://chromium.googlesource.com/chromium/deps/icu.git@master
Patch Set: remove unusued directories Created 5 years, 11 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View unified diff | Download patch
« no previous file with comments | « source/i18n/csrucode.cpp ('k') | source/i18n/currfmt.h » ('j') | no next file with comments »
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
OLDNEW
1 /* 1 /*
2 ********************************************************************** 2 **********************************************************************
3 * Copyright (C) 2005-2012, International Business Machines 3 * Copyright (C) 2005-2014, International Business Machines
4 * Corporation and others. All Rights Reserved. 4 * Corporation and others. All Rights Reserved.
5 ********************************************************************** 5 **********************************************************************
6 */ 6 */
7 7
8 #include "unicode/utypes.h" 8 #include "unicode/utypes.h"
9 9
10 #if !UCONFIG_NO_CONVERSION 10 #if !UCONFIG_NO_CONVERSION
11 11
12 #include "csrutf8.h" 12 #include "csrutf8.h"
13 #include "csmatch.h" 13 #include "csmatch.h"
(...skipping 34 matching lines...) Expand 10 before | Expand all | Expand 10 after
48 48
49 // Hi bit on char found. Figure out how long the sequence should be 49 // Hi bit on char found. Figure out how long the sequence should be
50 if ((b & 0x0E0) == 0x0C0) { 50 if ((b & 0x0E0) == 0x0C0) {
51 trailBytes = 1; 51 trailBytes = 1;
52 } else if ((b & 0x0F0) == 0x0E0) { 52 } else if ((b & 0x0F0) == 0x0E0) {
53 trailBytes = 2; 53 trailBytes = 2;
54 } else if ((b & 0x0F8) == 0xF0) { 54 } else if ((b & 0x0F8) == 0xF0) {
55 trailBytes = 3; 55 trailBytes = 3;
56 } else { 56 } else {
57 numInvalid += 1; 57 numInvalid += 1;
58 58 continue;
59 if (numInvalid > 5) {
60 break;
61 }
62
63 trailBytes = 0;
64 } 59 }
65 60
66 // Verify that we've got the right number of trail bytes in the sequence 61 // Verify that we've got the right number of trail bytes in the sequence
67 for (;;) { 62 for (;;) {
68 i += 1; 63 i += 1;
69 64
70 if (i >= input->fRawLength) { 65 if (i >= input->fRawLength) {
71 break; 66 break;
72 } 67 }
73 68
74 b = inputBytes[i]; 69 b = inputBytes[i];
75 70
76 if ((b & 0xC0) != 0x080) { 71 if ((b & 0xC0) != 0x080) {
77 numInvalid += 1; 72 numInvalid += 1;
78 break; 73 break;
79 } 74 }
80 75
81 if (--trailBytes == 0) { 76 if (--trailBytes == 0) {
82 numValid += 1; 77 numValid += 1;
83 break; 78 break;
84 } 79 }
85 } 80 }
86 81
87 } 82 }
88 83
89 // Cook up some sort of confidence score, based on presense of a BOM 84 // Cook up some sort of confidence score, based on presence of a BOM
90 // and the existence of valid and/or invalid multi-byte sequences. 85 // and the existence of valid and/or invalid multi-byte sequences.
91 confidence = 0; 86 confidence = 0;
92 if (hasBOM && numInvalid == 0) { 87 if (hasBOM && numInvalid == 0) {
93 confidence = 100; 88 confidence = 100;
94 } else if (hasBOM && numValid > numInvalid*10) { 89 } else if (hasBOM && numValid > numInvalid*10) {
95 confidence = 80; 90 confidence = 80;
96 } else if (numValid > 3 && numInvalid == 0) { 91 } else if (numValid > 3 && numInvalid == 0) {
97 confidence = 100; 92 confidence = 100;
98 } else if (numValid > 0 && numInvalid == 0) { 93 } else if (numValid > 0 && numInvalid == 0) {
99 confidence = 80; 94 confidence = 80;
100 } else if (numValid == 0 && numInvalid == 0) { 95 } else if (numValid == 0 && numInvalid == 0) {
101 // Plain ASCII. 96 // Plain ASCII. Confidence must be > 10, it's more likely than UTF-16, w hich
102 confidence = 10; 97 // accepts ASCII with confidence = 10.
98 confidence = 15;
103 } else if (numValid > numInvalid*10) { 99 } else if (numValid > numInvalid*10) {
104 // Probably corruput utf-8 data. Valid sequences aren't likely by chanc e. 100 // Probably corruput utf-8 data. Valid sequences aren't likely by chanc e.
105 confidence = 25; 101 confidence = 25;
106 } 102 }
107 103
108 results->set(input, this, confidence); 104 results->set(input, this, confidence);
109 return (confidence > 0); 105 return (confidence > 0);
110 } 106 }
111 107
112 U_NAMESPACE_END 108 U_NAMESPACE_END
113 #endif 109 #endif
OLDNEW
« no previous file with comments | « source/i18n/csrucode.cpp ('k') | source/i18n/currfmt.h » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698