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
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 1999-2014, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
*/
#include "unicode/utypes.h"
#include "unicode/uclean.h"
#include "unicode/uchar.h"
#include "unicode/unistr.h"
#include "unicode/uscript.h"
#include "unicode/putil.h"
#include "unicode/ctest.h"
#include "layout/LETypes.h"
#include "layout/LEScripts.h"
#include "letsutil.h"
#include "letest.h"
#include "xmlreader.h"
#include "xmlparser.h"
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
//U_NAMESPACE_USE
#define CH_COMMA 0x002C
static le_uint32 *getHexArray(const UnicodeString &numbers, int32_t &arraySize)
{
int32_t offset = -1;
arraySize = 1;
while((offset = numbers.indexOf(CH_COMMA, offset + 1)) >= 0) {
arraySize += 1;
}
le_uint32 *array = NEW_ARRAY(le_uint32, arraySize);
char number[16];
le_int32 count = 0;
le_int32 start = 0, end = 0;
le_int32 len = 0;
// trim leading whitespace
while(u_isUWhiteSpace(numbers[start])) {
start += 1;
}
while((end = numbers.indexOf(CH_COMMA, start)) >= 0) {
len = numbers.extract(start, end - start, number, ARRAY_SIZE(number), US_INV);
number[len] = '\0';
start = end + 1;
sscanf(number, "%x", &array[count++]);
// trim whitespace following the comma
while(u_isUWhiteSpace(numbers[start])) {
start += 1;
}
}
// trim trailing whitespace
end = numbers.length();
while(u_isUWhiteSpace(numbers[end - 1])) {
end -= 1;
}
len = numbers.extract(start, end - start, number, ARRAY_SIZE(number), US_INV);
number[len] = '\0';
sscanf(number, "%x", &array[count]);
return array;
}
static float *getFloatArray(const UnicodeString &numbers, int32_t &arraySize)
{
int32_t offset = -1;
arraySize = 1;
while((offset = numbers.indexOf(CH_COMMA, offset + 1)) >= 0) {
arraySize += 1;
}
float *array = NEW_ARRAY(float, arraySize);
char number[32];
le_int32 count = 0;
le_int32 start = 0, end = 0;
le_int32 len = 0;
// trim leading whitespace
while(u_isUWhiteSpace(numbers[start])) {
start += 1;
}
while((end = numbers.indexOf(CH_COMMA, start)) >= 0) {
len = numbers.extract(start, end - start, number, ARRAY_SIZE(number), US_INV);
number[len] = '\0';
start = end + 1;
sscanf(number, "%f", &array[count++]);
// trim whiteapce following the comma
while(u_isUWhiteSpace(numbers[start])) {
start += 1;
}
}
while(u_isUWhiteSpace(numbers[start])) {
start += 1;
}
// trim trailing whitespace
end = numbers.length();
while(u_isUWhiteSpace(numbers[end - 1])) {
end -= 1;
}
len = numbers.extract(start, end - start, number, ARRAY_SIZE(number), US_INV);
number[len] = '\0';
sscanf(number, "%f", &array[count]);
return array;
}
U_CDECL_BEGIN
void readTestFile(const char *testFilePath, TestCaseCallback callback)
{
#if !UCONFIG_NO_REGULAR_EXPRESSIONS
UErrorCode status = U_ZERO_ERROR;
UXMLParser *parser = UXMLParser::createParser(status);
UXMLElement *root = parser->parseFile(testFilePath, status);
if (root == nullptr) {
log_err("Could not open the test data file: %s\n", testFilePath);
delete parser;
return;
}
UnicodeString test_case = UNICODE_STRING_SIMPLE("test-case");
UnicodeString test_text = UNICODE_STRING_SIMPLE("test-text");
UnicodeString test_font = UNICODE_STRING_SIMPLE("test-font");
UnicodeString result_glyphs = UNICODE_STRING_SIMPLE("result-glyphs");
UnicodeString result_indices = UNICODE_STRING_SIMPLE("result-indices");
UnicodeString result_positions = UNICODE_STRING_SIMPLE("result-positions");
// test-case attributes
UnicodeString id_attr = UNICODE_STRING_SIMPLE("id");
UnicodeString script_attr = UNICODE_STRING_SIMPLE("script");
UnicodeString lang_attr = UNICODE_STRING_SIMPLE("lang");
// test-font attributes
UnicodeString name_attr = UNICODE_STRING_SIMPLE("name");
UnicodeString ver_attr = UNICODE_STRING_SIMPLE("version");
UnicodeString cksum_attr = UNICODE_STRING_SIMPLE("checksum");
const UXMLElement *testCase;
int32_t tc = 0;
while((testCase = root->nextChildElement(tc)) != nullptr) {
if (testCase->getTagName().compare(test_case) == 0) {
char *id = getCString(testCase->getAttribute(id_attr));
char *script = getCString(testCase->getAttribute(script_attr));
char *lang = getCString(testCase->getAttribute(lang_attr));
char *fontName = nullptr;
char *fontVer = nullptr;
char *fontCksum = nullptr;
const UXMLElement *element;
int32_t ec = 0;
int32_t charCount = 0;
// int32_t typoFlags = 3; // kerning + ligatures...
UScriptCode scriptCode;
le_int32 languageCode = -1;
UnicodeString text, glyphs, indices, positions;
int32_t glyphCount = 0, indexCount = 0, positionCount = 0;
TestResult expected = {0, nullptr, nullptr, nullptr};
uscript_getCode(script, &scriptCode, 1, &status);
if (LE_FAILURE(status)) {
log_err("invalid script name: %s.\n", script);
goto free_c_strings;
}
if (lang != nullptr) {
languageCode = getLanguageCode(lang);
if (languageCode < 0) {
log_err("invalid language name: %s.\n", lang);
goto free_c_strings;
}
}
while((element = testCase->nextChildElement(ec)) != nullptr) {
UnicodeString tag = element->getTagName();
// TODO: make sure that each element is only used once.
if (tag.compare(test_font) == 0) {
fontName = getCString(element->getAttribute(name_attr));
fontVer = getCString(element->getAttribute(ver_attr));
fontCksum = getCString(element->getAttribute(cksum_attr));
} else if (tag.compare(test_text) == 0) {
text = element->getText(true);
charCount = text.length();
} else if (tag.compare(result_glyphs) == 0) {
glyphs = element->getText(true);
} else if (tag.compare(result_indices) == 0) {
indices = element->getText(true);
} else if (tag.compare(result_positions) == 0) {
positions = element->getText(true);
} else {
// an unknown tag...
char *cTag = getCString(&tag);
log_info("Test %s: unknown element with tag \"%s\"\n", id, cTag);
freeCString(cTag);
}
}
expected.glyphs = (LEGlyphID *) getHexArray(glyphs, glyphCount);
expected.indices = (le_int32 *) getHexArray(indices, indexCount);
expected.positions = getFloatArray(positions, positionCount);
expected.glyphCount = glyphCount;
if (glyphCount < charCount || indexCount != glyphCount || positionCount < glyphCount * 2 + 2) {
log_err("Test %s: inconsistent input data: charCount = %d, glyphCount = %d, indexCount = %d, positionCount = %d\n",
id, charCount, glyphCount, indexCount, positionCount);
goto free_expected;
};
(*callback)(id, fontName, fontVer, fontCksum, scriptCode, languageCode, text.getBuffer(), charCount, &expected);
free_expected:
DELETE_ARRAY(expected.positions);
DELETE_ARRAY(expected.indices);
DELETE_ARRAY(expected.glyphs);
free_c_strings:
freeCString(fontCksum);
freeCString(fontVer);
freeCString(fontName);
freeCString(lang);
freeCString(script);
freeCString(id);
}
}
delete root;
delete parser;
#endif
}
U_CDECL_END
|
