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
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
|
/* -*- c++ -*-
tests/lexertest.cpp
This file is part of the testsuite of KSieve,
the KDE internet mail/usenet news message filtering library.
SPDX-FileCopyrightText: 2003 Marc Mutz <mutz@kde.org>
SPDX-License-Identifier: GPL-2.0-only
*/
#include <ksieve/lexer.h>
using KSieve::Lexer;
#include <ksieve/error.h>
using KSieve::Error;
#include <QString>
#include <cstdlib>
#include <iostream>
using std::cerr;
using std::cout;
using std::endl;
static const char *token2string(Lexer::Token t)
{
switch (t) {
#define CASE(x) \
case Lexer::x: \
return #x
CASE(None);
CASE(HashComment);
CASE(BracketComment);
CASE(Identifier);
CASE(Tag);
CASE(Number);
CASE(MultiLineString);
CASE(QuotedString);
CASE(Special);
CASE(LineFeeds);
}
return "";
#undef CASE
}
struct TestCase {
const char *name;
const char *string;
struct {
Lexer::Token token;
const char *result;
} expected[16]; // end with { None, 0 }
Error::Type expectedError;
int errorLine, errorCol;
};
static const TestCase testcases[] = {
//
// Whitespace:
//
{"Null script", nullptr, {{Lexer::None, nullptr}}, Error::None, 0, 0},
{"Empty script", "", {{Lexer::None, nullptr}}, Error::None, 0, 0},
{"Whitespace-only script", " \t\n\t \n", {{Lexer::LineFeeds, "2"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Lone CR", "\r", {{Lexer::None, nullptr}}, Error::CRWithoutLF, 0, 1},
{"CR+Space", "\r ", {{Lexer::None, nullptr}}, Error::CRWithoutLF, 0, 1},
{"CRLF alone", "\r\n", {{Lexer::LineFeeds, "1"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
//
// hash comments:
//
{"Basic hash comment (no newline)", "#comment", {{Lexer::HashComment, "comment"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Basic hash comment (LF)", "#comment\n", {{Lexer::HashComment, "comment"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Basic hash comment (CRLF)", "#comment\r\n", {{Lexer::HashComment, "comment"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Basic hash comment (CR)", "#comment\r", {{Lexer::HashComment, nullptr}}, Error::CRWithoutLF, 0, 9},
{"Non-UTF-8 in hash comment", "#\xA9 copyright", {{Lexer::HashComment, nullptr}}, Error::InvalidUTF8, 0, 12},
//
// bracket comments:
//
{"Basic bracket comment", "/* comment */", {{Lexer::BracketComment, " comment "}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Basic bracket comment - missing trailing slash", "/* comment *", {{Lexer::BracketComment, nullptr}}, Error::UnfinishedBracketComment, 0, 0},
{"Basic bracket comment - missing trailing asterisk + slash", "/* comment ", {{Lexer::BracketComment, nullptr}}, Error::UnfinishedBracketComment, 0, 0},
{"Basic bracket comment - missing leading slash", "* comment */", {{Lexer::None, nullptr}}, Error::IllegalCharacter, 0, 0},
{"Basic bracket comment - missing leading asterisk + slash",
"comment */",
{{Lexer::Identifier, "comment"}, {Lexer::None, nullptr}},
Error::IllegalCharacter,
0,
8},
{"Basic multiline bracket comment (LF)",
"/* comment\ncomment */",
{{Lexer::BracketComment, " comment\ncomment "}, {Lexer::None, nullptr}},
Error::None,
0,
0},
{"Basic multiline bracket comment (CRLF)",
"/* comment\r\ncomment */",
{{Lexer::BracketComment, " comment\ncomment "}, {Lexer::None, nullptr}},
Error::None,
0,
0},
{"Basic multiline bracket comment (CR)", "/* comment\rcomment */", {{Lexer::BracketComment, nullptr}}, Error::CRWithoutLF, 0, 11},
{"Non-UTF-8 in bracket comment", "/*\xA9 copyright*/", {{Lexer::BracketComment, nullptr}}, Error::InvalidUTF8, 0, 14},
//
// numbers:
//
{"Basic number 1", "1", {{Lexer::Number, "1"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Basic number 01", "01", {{Lexer::Number, "01"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Qualified number 1k", "1k", {{Lexer::Number, "1k"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Qualified number 1M", "1M", {{Lexer::Number, "1M"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Qualified number 1G", "1G", {{Lexer::Number, "1G"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
//
// identifiers:
//
{"Basic identifier \"id\"", "id", {{Lexer::Identifier, "id"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Basic identifier \"_id\"", "_id", {{Lexer::Identifier, "_id"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
//
// tags:
//
{"Basic tag \":tag\"", ":tag", {{Lexer::Tag, "tag"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Basic tag \":_tag\"", ":_tag", {{Lexer::Tag, "_tag"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
//
// specials:
//
{"Basic special \"{}[]();,\"",
"{}[]();,",
{{Lexer::Special, "{"},
{Lexer::Special, "}"},
{Lexer::Special, "["},
{Lexer::Special, "]"},
{Lexer::Special, "("},
{Lexer::Special, ")"},
{Lexer::Special, ";"},
{Lexer::Special, ","},
{Lexer::None, nullptr}},
Error::None,
0,
0},
//
// quoted-string:
//
{"Basic quoted string \"foo\"", "\"foo\"", {{Lexer::QuotedString, "foo"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Basic quoted string, UTF-8",
"\"foo\xC3\xB1"
"foo\"", // fooäfoo
{{Lexer::QuotedString,
"foo\xC3\xB1"
"foo"},
{Lexer::None, nullptr}},
Error::None,
0,
0},
{"Quoted string, escaped '\"'", R"("foo\"bar")", {{Lexer::QuotedString, "foo\"bar"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Quoted string, escaped '\\'", R"("foo\\bar")", {{Lexer::QuotedString, "foo\\bar"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Quoted string, excessive escapes", R"("\fo\o")", {{Lexer::QuotedString, "foo"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Quoted string across lines (LF)", "\"foo\nbar\"", {{Lexer::QuotedString, "foo\nbar"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Quoted string across lines (CRLF)", "\"foo\r\nbar\"", {{Lexer::QuotedString, "foo\nbar"}, {Lexer::None, nullptr}}, Error::None, 0, 0},
//
// multiline strings:
//
{"Basic multiline string I (LF)", "text:\nfoo\n.", {{Lexer::MultiLineString, "foo" /* "foo\n" ? */}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Basic multiline string I (CRLF)", "text:\r\nfoo\r\n.", {{Lexer::MultiLineString, "foo" /* "foo\n" ? */}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Basic multiline string II (LF)", "text:\nfoo\n.\n", {{Lexer::MultiLineString, "foo" /* "foo\n" ? */}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Basic multiline string II (CRLF)", "text:\r\nfoo\r\n.\r\n", {{Lexer::MultiLineString, "foo" /* "foo\n" ? */}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Dotstuffed multiline string (LF)", "text:\n..foo\n.", {{Lexer::MultiLineString, ".foo" /* ".foo\n" ? */}, {Lexer::None, nullptr}}, Error::None, 0, 0},
{"Dotstuffed multiline string (CRLF)",
"text:\r\n..foo\r\n.",
{{Lexer::MultiLineString, ".foo" /* ".foo\n" ? */}, {Lexer::None, nullptr}},
Error::None,
0,
0},
{"Incompletely dotstuffed multiline string (LF)",
"text:\n.foo\n.",
{{Lexer::MultiLineString, ".foo" /* ".foo\n" ? */}, {Lexer::None, nullptr}},
Error::None,
0,
0},
{"Incompletely dotstuffed multiline string (CRLF)",
"text:\r\n.foo\r\n.",
{{Lexer::MultiLineString, ".foo" /* ".foo\n" ? */}, {Lexer::None, nullptr}},
Error::None,
0,
0},
{"Multiline with a line with only one '.'",
"text:\r\nfoo\r\n..\r\nbar\r\n.",
{{Lexer::MultiLineString, "foo\n.\nbar"}, {Lexer::None, nullptr}},
Error::None,
0,
0},
//
// Errors in single tokens:
//
//
// numbers:
//
{"Number, unknown qualifier", "100f", {{Lexer::Number, "100"}}, Error::UnexpectedCharacter, 0, 3},
{"Negative number", "-100", {{Lexer::None, nullptr}}, Error::IllegalCharacter, 0, 0},
//
// identifiers:
//
{"Identifier, leading digits", "0id", {{Lexer::Number, "0"}}, Error::UnexpectedCharacter, 0, 1},
{"Identifier, embedded umlaut", "idäid", {{Lexer::Identifier, "id"}}, Error::IllegalCharacter, 0, 2},
//
// tags:
//
{"Lone ':' (at end)", ":", {{Lexer::Tag, nullptr}}, Error::UnexpectedCharacter, 0, 0},
{"Lone ':' (in stream)", ": ", {{Lexer::Tag, nullptr}}, Error::UnexpectedCharacter, 0, 1},
{"Tag, leading digits", ":0tag", {{Lexer::Tag, nullptr}}, Error::NoLeadingDigits, 0, 1},
{"Tag, embedded umlaut", ":tagätag", {{Lexer::Tag, "tag"}}, Error::IllegalCharacter, 0, 4},
//
// specials: (none)
// quoted string:
//
{"Premature end of quoted string", "\"foo", {{Lexer::QuotedString, "foo"}}, Error::PrematureEndOfQuotedString, 0, 0},
{"Invalid UTF-8 in quoted string",
"\"foo\xC0\xA0"
"foo\"",
{{Lexer::QuotedString, "foo"}},
Error::InvalidUTF8,
0,
4},
//
// Whitespace / token separation: valid
//
{"Two identifiers with linebreaks",
"foo\nbar\n",
{{Lexer::Identifier, "foo"}, {Lexer::LineFeeds, "1"}, {Lexer::Identifier, "bar"}, {Lexer::LineFeeds, "1"}, {Lexer::None, nullptr}},
Error::None,
0,
0},
//
// Whitespace / token separation: invalid
//
};
static const int numTestCases = sizeof testcases / sizeof *testcases;
int main(int argc, char *argv[])
{
if (argc == 2) { // manual test
const char *scursor = argv[1];
const char *const send = argv[1] + qstrlen(argv[1]);
Lexer lexer(scursor, send);
cout << "Begin" << endl;
while (!lexer.atEnd()) {
QString result;
Lexer::Token token = lexer.nextToken(result);
if (lexer.error()) {
cout << "Error " << token2string(token) << ": \"" << lexer.error().asString().toLatin1().constData() << "\" at (" << lexer.error().line() << ","
<< lexer.error().column() << ")" << endl;
break;
} else {
cout << "Got " << token2string(token) << ": \"" << result.toUtf8().data() << "\" at (" << lexer.line() << "," << lexer.column() << ")" << endl;
}
}
cout << "End" << endl;
} else if (argc == 1) { // automated test
bool success = true;
for (int i = 0; i < numTestCases; ++i) {
bool ok = true;
const TestCase &t = testcases[i];
const char *const send = t.string + qstrlen(t.string);
Lexer lexer(t.string, send, Lexer::IncludeComments);
cerr << t.name << ":";
for (int j = 0; !lexer.atEnd(); ++j) {
QString result;
Lexer::Token token = lexer.nextToken(result);
Error error = lexer.error();
if (t.expected[j].token != token) {
ok = false;
cerr << " expected token " << token2string(t.expected[j].token) << ", got " << token2string(token);
}
if (QString::fromUtf8(t.expected[j].result) != result) {
ok = false;
if (t.expected[j].result) {
cerr << " expected string \"" << t.expected[j].result << "\"";
} else {
cerr << " expected null string";
}
if (!result.toUtf8().isNull()) {
cerr << ", got \"" << result.toUtf8().data() << "\"";
} else {
cerr << ", got null string";
}
}
if (error && error.type() != t.expectedError) {
ok = false;
cerr << " expected error #" << (int)t.expectedError << ", got #" << (int)error.type();
}
if (error && (error.line() != t.errorLine || error.column() != t.errorCol)) {
ok = false;
cerr << " expected position (" << t.errorLine << "," << t.errorCol << "), got (" << error.line() << "," << error.column() << ")";
}
if (error) {
goto ErrorOut;
}
if (t.expected[j].token == Lexer::None && t.expected[j].result == nullptr) {
break;
}
}
if (!lexer.atEnd()) {
ok = false;
cerr << " premature end of expected token list";
}
ErrorOut:
if (ok) {
cerr << " ok";
}
cerr << endl;
if (!ok) {
success = false;
}
}
if (!success) {
return 1;
}
} else { // usage error
cerr << "usage: lexertest [ <string> ]" << endl;
exit(1);
}
return 0;
}
|
