1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
|
Description: Backport upstream changes for building with Unicode 9.0.
Origin: backport, http://source.winehq.org/git/wine.git/commit/58e0972c5ca8c82f65860733aaf3aeb41a7725bb
Origin: upstream, http://source.winehq.org/git/wine.git/commit/bbb9bbdbdb330aca21c363503274e21d558db1bc
Bug-Debian: https://bugs.debian.org/829003
Applied-Upstream: 1.9.13
--- a/dlls/dwrite/analyzer.c
+++ b/dlls/dwrite/analyzer.c
@@ -45,6 +45,7 @@ struct dwritescript_properties {
static const struct dwritescript_properties dwritescripts_properties[Script_LastId+1] = {
{ /* Zzzz */ { 0x7a7a7a5a, 999, 15, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
{ /* Zyyy */ { 0x7979795a, 998, 1, 0x0020, 0, 1, 1, 0, 0, 0, 0 } },
+ { /* Adlm */ { 0x6d6c6441, 166, 1, 0x0020, 0, 1, 1, 0, 0, 0, 0 } },
{ /* Ahom */ { 0x6d6f6841, 338, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
{ /* Hluw */ { 0x77756c48, 80, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
{ /* Arab */ { 0x62617241, 160, 8, 0x0640, 0, 1, 0, 0, 0, 1, 1 }, _OT('a','r','a','b'), 0, TRUE },
@@ -55,6 +56,7 @@ static const struct dwritescript_propert
{ /* Bass */ { 0x73736142, 259, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
{ /* Batk */ { 0x6b746142, 365, 8, 0x0020, 0, 1, 1, 0, 0, 0, 0 }, _OT('b','a','t','k') },
{ /* Beng */ { 0x676e6542, 325, 15, 0x0020, 1, 1, 0, 0, 0, 1, 0 }, _OT('b','e','n','g'), _OT('b','n','g','2'), TRUE },
+ { /* Bhks */ { 0x736b6842, 334, 1, 0x0020, 0, 1, 1, 0, 0, 0, 0 } },
{ /* Bopo */ { 0x6f706f42, 285, 1, 0x0020, 0, 0, 1, 1, 0, 0, 0 }, _OT('b','o','p','o') },
{ /* Brah */ { 0x68617242, 300, 8, 0x0020, 0, 1, 1, 0, 0, 0, 0 }, _OT('b','r','a','h') },
{ /* Brai */ { 0x69617242, 570, 1, 0x0020, 0, 1, 1, 0, 0, 0, 0 }, _OT('b','r','a','i'), 0, TRUE },
@@ -114,6 +116,7 @@ static const struct dwritescript_propert
{ /* Mlym */ { 0x6d796c4d, 347, 15, 0x0020, 1, 1, 1, 0, 0, 0, 0 }, _OT('m','l','y','m'), _OT('m','l','m','2'), TRUE },
{ /* Mand */ { 0x646e614d, 140, 8, 0x0640, 0, 1, 0, 0, 0, 1, 1 }, _OT('m','a','n','d') },
{ /* Mani */ { 0x696e614d, 139, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
+ { /* Marc */ { 0x6372614d, 332, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
{ /* Mtei */ { 0x6965744d, 337, 8, 0x0020, 1, 1, 1, 0, 0, 0, 0 }, _OT('m','t','e','i') },
{ /* Mend */ { 0x646e654d, 438, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
{ /* Merc */ { 0x6372654d, 101, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 }, _OT('m','e','r','c') },
@@ -126,6 +129,7 @@ static const struct dwritescript_propert
{ /* Mymr */ { 0x726d794d, 350, 15, 0x0020, 1, 1, 1, 0, 0, 0, 0 }, _OT('m','y','m','r'), 0, TRUE },
{ /* Nbat */ { 0x7461624e, 159, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
{ /* Talu */ { 0x756c6154, 354, 8, 0x0020, 1, 1, 1, 0, 0, 0, 0 }, _OT('t','a','l','u'), 0, TRUE },
+ { /* Newa */ { 0x6177654e, 333, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
{ /* Nkoo */ { 0x6f6f6b4e, 165, 8, 0x0020, 0, 1, 0, 0, 0, 1, 1 }, _OT('n','k','o',' '), 0, TRUE },
{ /* Ogam */ { 0x6d61674f, 212, 1, 0x1680, 0, 1, 0, 0, 0, 1, 0 }, _OT('o','g','a','m'), 0, TRUE },
{ /* Olck */ { 0x6b636c4f, 261, 1, 0x0020, 0, 1, 1, 0, 0, 0, 0 }, _OT('o','l','c','k') },
@@ -137,6 +141,7 @@ static const struct dwritescript_propert
{ /* Sarb */ { 0x62726153, 105, 1, 0x0020, 0, 1, 1, 0, 0, 0, 0 }, _OT('s','a','r','b') },
{ /* Orkh */ { 0x686b724f, 175, 1, 0x0020, 0, 1, 1, 0, 0, 0, 0 }, _OT('o','r','k','h') },
{ /* Orya */ { 0x6179724f, 327, 15, 0x0020, 1, 1, 1, 0, 0, 0, 0 }, _OT('o','r','y','a'), _OT('o','r','y','2'), TRUE },
+ { /* Osge */ { 0x6567734f, 219, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
{ /* Osma */ { 0x616d734f, 260, 8, 0x0020, 0, 1, 1, 0, 0, 0, 0 }, _OT('o','s','m','a'), 0, TRUE },
{ /* Hmng */ { 0x676e6d48, 450, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
{ /* Palm */ { 0x6d6c6150, 126, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
@@ -164,6 +169,7 @@ static const struct dwritescript_propert
{ /* Tavt */ { 0x74766154, 359, 8, 0x0020, 1, 0, 1, 0, 1, 0, 0 }, _OT('t','a','v','t') },
{ /* Takr */ { 0x726b6154, 321, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 }, _OT('t','a','k','r') },
{ /* Taml */ { 0x6c6d6154, 346, 15, 0x0020, 1, 1, 1, 0, 0, 0, 0 }, _OT('t','a','m','l'), _OT('t','m','l','2'), TRUE },
+ { /* Tang */ { 0x676e6154, 520, 1, 0x0020, 0, 0, 0, 0, 0, 0, 0 } },
{ /* Telu */ { 0x756c6554, 340, 15, 0x0020, 1, 1, 1, 0, 0, 0, 0 }, _OT('t','e','l','u'), _OT('t','e','l','2'), TRUE },
{ /* Thaa */ { 0x61616854, 170, 8, 0x0020, 1, 1, 1, 0, 0, 0, 0 }, _OT('t','h','a','a'), 0, TRUE },
{ /* Thai */ { 0x69616854, 352, 8, 0x0020, 1, 0, 1, 0, 1, 0, 0 }, _OT('t','h','a','i'), 0, TRUE },
@@ -302,7 +308,10 @@ enum linebreaking_classes {
b_B2,
b_HL,
b_CJ,
- b_RI
+ b_RI,
+ b_EB,
+ b_EM,
+ b_ZWJ,
};
/* "Can break" is a weak condition, stronger "may not break" and "must break" override it. Initially all conditions are
@@ -402,13 +411,18 @@ static HRESULT analyze_linebreaks(const
i++;
set_break_condition(i, BreakConditionBefore, DWRITE_BREAK_CONDITION_CAN_BREAK, &state);
break;
+ /* LB8a - do not break between ZWJ and an ideograph, emoji base or emoji modifier */
+ case b_ZWJ:
+ if (i < count-1 && (break_class[i+1] == b_ID || break_class[i+1] == b_EB || break_class[i+1] == b_EM))
+ set_break_condition(i, BreakConditionAfter, DWRITE_BREAK_CONDITION_MAY_NOT_BREAK, &state);
+ break;
}
}
/* LB9 - LB10 */
for (i = 0; i < count; i++)
{
- if (break_class[i] == b_CM)
+ if (break_class[i] == b_CM || break_class[i] == b_ZWJ)
{
if (i > 0)
{
@@ -541,6 +555,8 @@ static HRESULT analyze_linebreaks(const
case b_AL:
case b_HL:
case b_ID:
+ case b_EB:
+ case b_EM:
case b_IN:
case b_NU:
set_break_condition(i, BreakConditionBefore, DWRITE_BREAK_CONDITION_MAY_NOT_BREAK, &state);
@@ -551,19 +567,31 @@ static HRESULT analyze_linebreaks(const
if (i < count-1)
{
- /* LB23 */
- if ((break_class[i] == b_ID && break_class[i+1] == b_PO) ||
- (break_class[i] == b_AL && break_class[i+1] == b_NU) ||
+ /* LB23 - do not break between digits and letters */
+ if ((break_class[i] == b_AL && break_class[i+1] == b_NU) ||
(break_class[i] == b_HL && break_class[i+1] == b_NU) ||
(break_class[i] == b_NU && break_class[i+1] == b_AL) ||
(break_class[i] == b_NU && break_class[i+1] == b_HL))
set_break_condition(i, BreakConditionAfter, DWRITE_BREAK_CONDITION_MAY_NOT_BREAK, &state);
- /* LB24 */
+
+ /* LB23a - do not break between numeric prefixes and ideographs, or between ideographs and numeric postfixes */
if ((break_class[i] == b_PR && break_class[i+1] == b_ID) ||
- (break_class[i] == b_PR && break_class[i+1] == b_AL) ||
+ (break_class[i] == b_PR && break_class[i+1] == b_EB) ||
+ (break_class[i] == b_PR && break_class[i+1] == b_EM) ||
+ (break_class[i] == b_ID && break_class[i+1] == b_PO) ||
+ (break_class[i] == b_EM && break_class[i+1] == b_PO) ||
+ (break_class[i] == b_EB && break_class[i+1] == b_PO))
+ set_break_condition(i, BreakConditionAfter, DWRITE_BREAK_CONDITION_MAY_NOT_BREAK, &state);
+
+ /* LB24 - do not break between numeric prefix/postfix and letters, or letters and prefix/postfix */
+ if ((break_class[i] == b_PR && break_class[i+1] == b_AL) ||
(break_class[i] == b_PR && break_class[i+1] == b_HL) ||
(break_class[i] == b_PO && break_class[i+1] == b_AL) ||
- (break_class[i] == b_PO && break_class[i+1] == b_HL))
+ (break_class[i] == b_PO && break_class[i+1] == b_HL) ||
+ (break_class[i] == b_AL && break_class[i+1] == b_PR) ||
+ (break_class[i] == b_HL && break_class[i+1] == b_PR) ||
+ (break_class[i] == b_AL && break_class[i+1] == b_PO) ||
+ (break_class[i] == b_HL && break_class[i+1] == b_PO))
set_break_condition(i, BreakConditionAfter, DWRITE_BREAK_CONDITION_MAY_NOT_BREAK, &state);
/* LB25 */
@@ -646,8 +674,20 @@ static HRESULT analyze_linebreaks(const
(break_class[i+1] == b_AL || break_class[i] == b_HL || break_class[i] == b_NU))
set_break_condition(i, BreakConditionAfter, DWRITE_BREAK_CONDITION_MAY_NOT_BREAK, &state);
- /* LB30a */
- if (break_class[i] == b_RI && break_class[i+1] == b_RI)
+ /* LB30a - break between two RIs if and only if there are an even number of RIs preceding position of the break */
+ if (break_class[i] == b_RI && break_class[i+1] == b_RI) {
+ unsigned int c = 0;
+
+ j = i + 1;
+ while (j > 0 && break_class[--j] == b_RI)
+ c++;
+
+ if ((c & 1) == 0)
+ set_break_condition(i, BreakConditionAfter, DWRITE_BREAK_CONDITION_MAY_NOT_BREAK, &state);
+ }
+
+ /* LB30b - do not break between an emoji base and an emoji modifier */
+ if (break_class[i] == b_EB && break_class[i+1] == b_EM)
set_break_condition(i, BreakConditionAfter, DWRITE_BREAK_CONDITION_MAY_NOT_BREAK, &state);
}
}
--- a/dlls/usp10/breaking.c
+++ b/dlls/usp10/breaking.c
@@ -38,7 +38,11 @@ WINE_DEFAULT_DEBUG_CHANNEL(uniscribe);
extern const unsigned short wine_linebreak_table[];
-enum breaking_types { b_BK=1, b_CR, b_LF, b_CM, b_SG, b_GL, b_CB, b_SP, b_ZW, b_NL, b_WJ, b_JL, b_JV, b_JT, b_H2, b_H3, b_XX, b_OP, b_CL, b_CP, b_QU, b_NS, b_EX, b_SY, b_IS, b_PR, b_PO, b_NU, b_AL, b_ID, b_IN, b_HY, b_BB, b_BA, b_SA, b_AI, b_B2, b_HL, b_CJ, b_RI};
+enum breaking_types {
+ b_BK=1, b_CR, b_LF, b_CM, b_SG, b_GL, b_CB, b_SP, b_ZW, b_NL, b_WJ, b_JL, b_JV, b_JT, b_H2, b_H3, b_XX, b_OP, b_CL,
+ b_CP, b_QU, b_NS, b_EX, b_SY, b_IS, b_PR, b_PO, b_NU, b_AL, b_ID, b_IN, b_HY, b_BB, b_BA, b_SA, b_AI, b_B2, b_HL,
+ b_CJ, b_RI, b_EB, b_EM, b_ZWJ
+};
enum breaking_class {b_r=1, b_s, b_x};
--- a/tools/make_unicode
+++ b/tools/make_unicode
@@ -23,7 +23,7 @@ use strict;
# base URLs for www.unicode.org files
my $MAPPINGS = "http://www.unicode.org/Public/MAPPINGS";
-my $UNIDATA = "http://www.unicode.org/Public/8.0.0/ucd";
+my $UNIDATA = "http://www.unicode.org/Public/9.0.0/ucd";
my $REPORTS = "http://www.unicode.org/reports";
my $RFCS = "http://www.rfc-editor.org/rfc";
my $VERTICALDATA = "http://www.unicode.org/Public/vertical/revision-11";
@@ -244,6 +244,9 @@ my %break_types =
"HL" => 0x0026,
"CJ" => 0x0027,
"RI" => 0x0028,
+ "EB" => 0x0029,
+ "EM" => 0x002a,
+ "ZWJ" => 0x002b,
);
my %vertical_types =
@@ -1265,7 +1268,24 @@ sub dump_linebreak($)
next if /^\#/; # skip comments
next if /^\s*$/; # skip empty lines
next if /\x1a/; # skip ^Z
- if (/^\s*([0-9a-fA-F]+)\s*;\s*([0-9A-Z][0-9A-Z])+\s*/)
+ if (/^\s*([0-9a-fA-F]+)\s*;\s*([0-9A-Z][0-9A-Z][0-9A-Z])+\s*/)
+ {
+ my $type = $2;
+ die "unknown breaktype $type" unless defined $break_types{$type};
+ $break_table[hex $1] = $break_types{$type};
+ next;
+ }
+ elsif (/^\s*([0-9a-fA-F]+)..\s*([0-9a-fA-F]+)\s*;\s*([0-9A-Z][0-9A-Z][0-9A-Z])+\s*/)
+ {
+ my $type = $3;
+ die "unknown breaktype $type" unless defined $break_types{$type};
+ foreach my $i (hex $1 .. hex $2)
+ {
+ $break_table[$i] = $break_types{$type};
+ }
+ next;
+ }
+ elsif (/^\s*([0-9a-fA-F]+)\s*;\s*([0-9A-Z][0-9A-Z])+\s*/)
{
my $type = $2;
die "unknown breaktype $type" unless defined $break_types{$type};
|
