[apple/icu.git] / icuSources / test / testdata / DataDrivenCollationTest.txt

// Copyright (c) 2001-2003 International Business Machines
// Corporation and others. All Rights Reserved.
DataDrivenCollationTest {
    Info {
        Headers { "sequence" }
        Description { "These are the data driven tests" }
        LongDescription {     "The following entries are separate tests containing test data for various locales."
                      "Each entry has the following fields: "
                      "Info/Description - short descrioption of the test"
                      "Settings - settings for the test."
                      "Settings/TestLocale - locale for the collator OR"
                      "Settings/Rules - rules for the collator (can't have both)"
                      "Settings/Arguments - arguments to be passed to the collator before testing. Use rule syntax."
                      "Cases - set of test cases, which are sequences of strings that will be parsed"
                      "Sequences must not change the sign of relation, i.e. we can only have < and = or"
                      "> and = in single sequence. Cannot mix < and > in the same sequence. Whitespace is"
                      "is ignored unless quoted."
                     }
    }
    TestData {
        TestThaiPartialSortKeyProblems {
            Info {
                Description { "These are examples of strings that caused trouble in partial sort key testing." }
            }
            Settings {
                {
                    TestLocale { "th_TH" }
                }
            }
            // TODO: the tests that are commented out should be enabled when j2720 is fixed
            Cases { "\u0E01\u0E01\u0E38\u0E18\u0E20\u0E31\u0E13\u0E11\u0E4C"
                    "<\u0E01\u0E01\u0E38\u0E2A\u0E31\u0E19\u0E42\u0E18",
                    "\u0E01\u0E07\u0E01\u0E32\u0E23"
                    "<\u0E01\u0E07\u0E42\u0E01\u0E49",
                    //"\u0E01\u0E23\u0E19\u0E17\u0E32"
                    //"<\u0E01\u0E23\u0E19\u0E19\u0E40\u0E0A\u0E49\u0E32",
                    "\u0E01\u0E23\u0E30\u0E40\u0E08\u0E35\u0E22\u0E27"
                    "<\u0E01\u0E23\u0E30\u0E40\u0E08\u0E35\u0E4A\u0E22\u0E27",
                    //"\u0E01\u0E23\u0E23\u0E40\u0E0A\u0E2D"
                    //"<\u0E01\u0E23\u0E23\u0E40\u0E0A\u0E49\u0E32"
          }
        }
        TestJavaStyleRule {
            Info {
                Description { "java.text allows rules to start as '<<<x<<<y...' "
                              "we emulate this by assuming a &[first tertiary ignorable] "
                              "in this case."
                }
            }
            Settings {
                {
                    Rules { "=equal<<<z<<x<<<w<y &[first tertiary ignorable]=a &[first primary ignorable]=b" }
                }
            }
            Cases { "a = equal < z < x < w < b < y" }
        }
        TestShiftedIgnorable {
            Info {
                Description { "New UCA states that primary ignorables should be completely "
                              "ignorable when following a shifted code point."
                            }
            }
            Settings {
                {
                    TestLocale { "root" }
                    Arguments { "[alternate shifted][strength 4]" }
                }
            }
            Cases {
                "a' 'b="
                "a' '\u0300b="
                "a' '\u0301b<"
                "a_b="
                "a_\u0300b="
                "a_\u0301b<"
                "A' 'b="
                "A' '\u0300b="
                "A' '\u0301b<"
                "A_b="
                "A_\u0300b="
                "A_\u0301b<"
                "a\u0301b<"
                "A\u0301b<"
                "a\u0300b<"
                "A\u0300b"

            }
        }

        TestNShiftedIgnorable {
            Info {
                Description { "New UCA states that primary ignorables should be completely "
                              "ignorable when following a shifted code point."
                            }
            }
            Settings {
                {
                    TestLocale { "root" }
                    Arguments { "[alternate non-ignorable][strength 3]" }
                }
            }
            Cases {
                "a' 'b<"
                "A' 'b<"
                "a' '\u0301b<"
                "A' '\u0301b<"
                "a' '\u0300b<"
                "A' '\u0300b<"
                "a_b<"
                "A_b<"
                "a_\u0301b<"
                "A_\u0301b<"
                "a_\u0300b<"
                "A_\u0300b<"
                "a\u0301b<"
                "A\u0301b<"
                "a\u0300b<"
                "A\u0300b<"
            }
        }

        TestSafeSurrogates {
            Info {
                Description { "It turned out that surrogates were not skipped properly "
                              "when iterating backwards if they were in the middle of a "
                              "contraction. This test assures that this is fixed."
                            }
            }
            Settings {
                {
                    Rules {
                                "&a < x\ud800\udc00b"
                    }
                }
            }
            Cases {
                "a<x\ud800\udc00b"
            }
        }
                
        TestCIgnorableContraction {
            Info {
                Description { "Checks whether completely ignorable code points are "
                              "skipped in contractions."
                              }
            }
            Settings {
                {
                    TestLocale { "sh" }
                }
                {
                    Rules {
                                "& L < lj, Lj <<< LJ"
                                "& N < nj, Nj <<< NJ "
                    }
                }
            }
            Cases {
                "njiva=n\ud834\udd65jiva=n\uD834\uDD79jiva=n\u0000\u0000\u0000jiva=n\u0000jiva=n\ud800jiva=n\ufffejiva",
                "ljubav=l\u0000jubav=l\uD834\uDD79jubav=l\u0000\u0000\u0000jubav=l\ud800jubav=l\ufffejubav",
                "Ljubav=L\u0000jubav=L\uD834\uDD79jubav=L\u0000\u0000\u0000jubav=L\ud800jubav=L\ufffejubav",
            }
        }
                

        TestCIgnorablePrefix {
            Info {
                Description { "Checks whether completely ignorable code points are "
                              "skipped in prefix processing."
                              }
            }
            Settings {
                {
                    TestLocale { "ja" }
                }
            }
            Cases {
               "\u30A1\u30FC"
               "= \u30A1\uDB40\uDC30\u30FC"
               "= \u30A1\uD800\u30FC"
               "= \u30A1\uFFFE\u30FC"
               "= \u30A1\uD834\uDD79\u30FC"
               "= \u30A1\u0000\u0000\u0000\u30FC"
               "= \u30A1\u0000\u30FC"
               "= \u30A1\u30FC"
               "= \u30A1\u0000\u059a\u30FC"
               "= \u30A1\u30FC"
            }
        }
  
        da_TestPrimary {
            Info {
                Description { "This test goes through primary strength cases" }
            }
            Settings {
                {
                    TestLocale { "da" }
                    Arguments { "[strength 1]" }
                }
            }
            Cases {
                "Lvi=Lwi",
                "L\u00e4vi<L\u00f6wi",
                "L\u00fcbeck=Lybeck",
            }
        }
        da_TestTertiary {
            Info {
                Description { "This test goes through tertiary strength cases" }
            }
            Settings {
                {
                    TestLocale { "da" }
                    Arguments { "[strength 3]" }
                }
            }
            Cases {
                "Luc<luck",
                "luck<L\u00fcbeck",
                "L\u00fcbeck>lybeck",
                "L\u00e4vi<L\u00f6we",
                "L\u00f6ww<mast",
                // constUCharCollationDanishTest::testBugs[][CollationDanishTest::MAX_TOKEN_LEN]="
                "A/S<"
                "ANDRE<"
                "ANDR\u00c9<"
                "ANDREAS<"
                "AS<"
                "CA<"
                "\u00c7A<"
                "CB<"
                "\u00c7C<"
                "D.S.B.<"
                "DA<"
                "DB<"
                "DSB<"
                "DSC<"
                "\u00d0A<"
                "\u00d0C<"
                "EKSTRA_ARBEJDE<"
                "EKSTRABUD0<"
                "H\u00d8ST<"
                "HAAG<"
                "H\u00c5NDBOG<"
                "HAANDV\u00c6RKSBANKEN<"
                "karl<"
                "Karl<"
                "'NIELS J\u00d8RGEN'<"
                "NIELS-J\u00d8RGEN<"
                "NIELSEN<"
                "'R\u00c9E, A'<"
                "'REE, B'<"
                "'R\u00c9E, L'<"
                "'REE, V'<"
                "'SCHYTT, B'<"
                "'SCHYTT, H'<"
                "'SCH\u00dcTT, H'<"
                "'SCHYTT, L'<"
                "'SCH\u00dcTT, M'<"
                "SS<"
                "\u00df<"
                "SSA<"
                "'STORE VILDMOSE'<"
                "STOREK\u00c6R0<"
                "'STORM PETERSEN'<"
                "STORMLY<"
                "THORVALD<"
                "THORVARDUR<"
                "THYGESEN<"
                "\u00feORVAR\u00d0UR<"
                "'VESTERG\u00c5RD, A'<"
                "'VESTERGAARD, A'<"
                "'VESTERG\u00c5RD, B'<"
                "\u00c6BLE<"
                "\u00c4BLE<"
                "\u00d8BERG<"
                "\u00d6BERG",

                // constUCharCollationDanishTest::testNTList[][CollationDanishTest::MAX_TOKEN_LEN]="
                "andere<"
                "chaque<"
                "chemin<"
                "cote<"
                "cot\u00e9<"
                "c\u00f4te<"
                "c\u00f4t\u00e9<"
                "\u010du\u010d\u0113t<"
                "Czech<"
                "hi\u0161a<"
                "irdisch<"
                "lie<"
                "lire<"
                "llama<"
                "l\u00f5ug<"
                "l\u00f2za<"
                "lu\u010d<"
                "luck<"
                "L\u00fcbeck<"
                "lye<"
                "l\u00e4vi<"
                "L\u00f6wen<"
                "m\u00e0\u0161ta<"
                "m\u00eer<"
                "myndig<"
                "M\u00e4nner<"
                "m\u00f6chten<"
                "pi\u00f1a<"
                "pint<"
                "pylon<"
                "\u0161\u00e0ran<"
                "savoir<"
                "\u0160erb\u016bra<"
                "Sietla<"
                "\u015blub<"
                "subtle<"
                "symbol<"
                "s\u00e4mtlich<"
                "waffle<"
                "verkehrt<"
                "wood<"
                "vox<"
                "v\u00e4ga<"
                "yen<"
                "yuan<"
                "yucca<"
                "\u017eal<"
                "\u017eena<"
                "\u017den\u0113va<"
                "zoo0<"
                "Zviedrija<"
                "Z\u00fcrich<"
                "zysk0<"
                "\u00e4ndere"
            }
        }
    }
}
Commit	Line	Data
b75a7d8f A	1	// Copyright (c) 2001-2003 International Business Machines
	2	// Corporation and others. All Rights Reserved.
	3	DataDrivenCollationTest {
	4	Info {
	5	Headers { "sequence" }
	6	Description { "These are the data driven tests" }
	7	LongDescription { "The following entries are separate tests containing test data for various locales."
	8	"Each entry has the following fields: "
	9	"Info/Description - short descrioption of the test"
	10	"Settings - settings for the test."
	11	"Settings/TestLocale - locale for the collator OR"
	12	"Settings/Rules - rules for the collator (can't have both)"
	13	"Settings/Arguments - arguments to be passed to the collator before testing. Use rule syntax."
	14	"Cases - set of test cases, which are sequences of strings that will be parsed"
	15	"Sequences must not change the sign of relation, i.e. we can only have < and = or"
	16	"> and = in single sequence. Cannot mix < and > in the same sequence. Whitespace is"
	17	"is ignored unless quoted."
	18	}
	19	}
	20	TestData {
	21	TestThaiPartialSortKeyProblems {
	22	Info {
	23	Description { "These are examples of strings that caused trouble in partial sort key testing." }
	24	}
	25	Settings {
	26	{
	27	TestLocale { "th_TH" }
	28	}
	29	}
	30	// TODO: the tests that are commented out should be enabled when j2720 is fixed
	31	Cases { "\u0E01\u0E01\u0E38\u0E18\u0E20\u0E31\u0E13\u0E11\u0E4C"
	32	"<\u0E01\u0E01\u0E38\u0E2A\u0E31\u0E19\u0E42\u0E18",
	33	"\u0E01\u0E07\u0E01\u0E32\u0E23"
	34	"<\u0E01\u0E07\u0E42\u0E01\u0E49",
	35	//"\u0E01\u0E23\u0E19\u0E17\u0E32"
	36	//"<\u0E01\u0E23\u0E19\u0E19\u0E40\u0E0A\u0E49\u0E32",
	37	"\u0E01\u0E23\u0E30\u0E40\u0E08\u0E35\u0E22\u0E27"
	38	"<\u0E01\u0E23\u0E30\u0E40\u0E08\u0E35\u0E4A\u0E22\u0E27",
	39	//"\u0E01\u0E23\u0E23\u0E40\u0E0A\u0E2D"
	40	//"<\u0E01\u0E23\u0E23\u0E40\u0E0A\u0E49\u0E32"
	41	}
	42	}
	43	TestJavaStyleRule {
	44	Info {
	45	Description { "java.text allows rules to start as '<<<x<<<y...' "
	46	"we emulate this by assuming a &[first tertiary ignorable] "
	47	"in this case."
	48	}
	49	}
	50	Settings {
	51	{
	52	Rules { "=equal<<<z<<x<<<w<y &[first tertiary ignorable]=a &[first primary ignorable]=b" }
	53	}
	54	}
	55	Cases { "a = equal < z < x < w < b < y" }
	56	}
	57	TestShiftedIgnorable {
	58	Info {
	59	Description { "New UCA states that primary ignorables should be completely "
	60	"ignorable when following a shifted code point."
	61	}
	62	}
	63	Settings {
	64	{
65	TestLocale { "root" }
66	Arguments { "[alternate shifted][strength 4]" }
67	}
68	}
69	Cases {
70	"a' 'b="
71	"a' '\u0300b="
72	"a' '\u0301b<"
73	"a_b="
74	"a_\u0300b="
75	"a_\u0301b<"
76	"A' 'b="
77	"A' '\u0300b="
78	"A' '\u0301b<"
79	"A_b="
80	"A_\u0300b="
81	"A_\u0301b<"
82	"a\u0301b<"
83	"A\u0301b<"
84	"a\u0300b<"
85	"A\u0300b"
86
87	}
88	}
89
90	TestNShiftedIgnorable {
91	Info {
92	Description { "New UCA states that primary ignorables should be completely "
93	"ignorable when following a shifted code point."
94	}
95	}
96	Settings {
97	{
98	TestLocale { "root" }
99	Arguments { "[alternate non-ignorable][strength 3]" }
100	}
101	}
102	Cases {
103	"a' 'b<"
104	"A' 'b<"
105	"a' '\u0301b<"
106	"A' '\u0301b<"
107	"a' '\u0300b<"
108	"A' '\u0300b<"
109	"a_b<"
110	"A_b<"
111	"a_\u0301b<"
112	"A_\u0301b<"
113	"a_\u0300b<"
114	"A_\u0300b<"
115	"a\u0301b<"
116	"A\u0301b<"
117	"a\u0300b<"
118	"A\u0300b<"
119	}
120	}
121
122	TestSafeSurrogates {
123	Info {
124	Description { "It turned out that surrogates were not skipped properly "
125	"when iterating backwards if they were in the middle of a "
126	"contraction. This test assures that this is fixed."
127	}
128	}
129	Settings {
130	{
131	Rules {
132	"&a < x\ud800\udc00b"
133	}
134	}
135	}
136	Cases {
137	"a<x\ud800\udc00b"
138	}
139	}
140
141	TestCIgnorableContraction {
142	Info {
143	Description { "Checks whether completely ignorable code points are "
144	"skipped in contractions."
145	}
146	}
147	Settings {
148	{
149	TestLocale { "sh" }
150	}
151	{
152	Rules {
153	"& L < lj, Lj <<< LJ"
154	"& N < nj, Nj <<< NJ "
155	}
156	}
157	}
158	Cases {
159	"njiva=n\ud834\udd65jiva=n\uD834\uDD79jiva=n\u0000\u0000\u0000jiva=n\u0000jiva=n\ud800jiva=n\ufffejiva",
160	"ljubav=l\u0000jubav=l\uD834\uDD79jubav=l\u0000\u0000\u0000jubav=l\ud800jubav=l\ufffejubav",
161	"Ljubav=L\u0000jubav=L\uD834\uDD79jubav=L\u0000\u0000\u0000jubav=L\ud800jubav=L\ufffejubav",
162	}
163	}
164
165
166	TestCIgnorablePrefix {
167	Info {
168	Description { "Checks whether completely ignorable code points are "
169	"skipped in prefix processing."
170	}
171	}
172	Settings {
173	{
174	TestLocale { "ja" }
175	}
176	}
177	Cases {
178	"\u30A1\u30FC"
179	"= \u30A1\uDB40\uDC30\u30FC"
180	"= \u30A1\uD800\u30FC"
181	"= \u30A1\uFFFE\u30FC"
182	"= \u30A1\uD834\uDD79\u30FC"
183	"= \u30A1\u0000\u0000\u0000\u30FC"
184	"= \u30A1\u0000\u30FC"
185	"= \u30A1\u30FC"
186	"= \u30A1\u0000\u059a\u30FC"
187	"= \u30A1\u30FC"
188	}
189	}
190
191	da_TestPrimary {
192	Info {
193	Description { "This test goes through primary strength cases" }
194	}
195	Settings {
196	{
197	TestLocale { "da" }
198	Arguments { "[strength 1]" }
199	}
200	}
201	Cases {
202	"Lvi=Lwi",
203	"L\u00e4vi<L\u00f6wi",
204	"L\u00fcbeck=Lybeck",
205	}
206	}
207	da_TestTertiary {
208	Info {
209	Description { "This test goes through tertiary strength cases" }
210	}
211	Settings {
212	{
213	TestLocale { "da" }
214	Arguments { "[strength 3]" }
215	}
216	}
217	Cases {
218	"Luc<luck",
219	"luck<L\u00fcbeck",
220	"L\u00fcbeck>lybeck",
221	"L\u00e4vi<L\u00f6we",
222	"L\u00f6ww<mast",
223	// constUCharCollationDanishTest::testBugs[][CollationDanishTest::MAX_TOKEN_LEN]="
224	"A/S<"
225	"ANDRE<"
226	"ANDR\u00c9<"
227	"ANDREAS<"
228	"AS<"
229	"CA<"
230	"\u00c7A<"
231	"CB<"
232	"\u00c7C<"
233	"D.S.B.<"
234	"DA<"
235	"DB<"
236	"DSB<"
237	"DSC<"
238	"\u00d0A<"
239	"\u00d0C<"
240	"EKSTRA_ARBEJDE<"
241	"EKSTRABUD0<"
242	"H\u00d8ST<"
243	"HAAG<"
244	"H\u00c5NDBOG<"
245	"HAANDV\u00c6RKSBANKEN<"
246	"karl<"
247	"Karl<"
248	"'NIELS J\u00d8RGEN'<"
249	"NIELS-J\u00d8RGEN<"
250	"NIELSEN<"
251	"'R\u00c9E, A'<"
252	"'REE, B'<"
253	"'R\u00c9E, L'<"
254	"'REE, V'<"
255	"'SCHYTT, B'<"
256	"'SCHYTT, H'<"
257	"'SCH\u00dcTT, H'<"
258	"'SCHYTT, L'<"
259	"'SCH\u00dcTT, M'<"
260	"SS<"
261	"\u00df<"
262	"SSA<"
263	"'STORE VILDMOSE'<"
264	"STOREK\u00c6R0<"
265	"'STORM PETERSEN'<"
266	"STORMLY<"
267	"THORVALD<"
268	"THORVARDUR<"
269	"THYGESEN<"
270	"\u00feORVAR\u00d0UR<"
271	"'VESTERG\u00c5RD, A'<"
272	"'VESTERGAARD, A'<"
273	"'VESTERG\u00c5RD, B'<"
274	"\u00c6BLE<"
275	"\u00c4BLE<"
276	"\u00d8BERG<"
277	"\u00d6BERG",
278
279	// constUCharCollationDanishTest::testNTList[][CollationDanishTest::MAX_TOKEN_LEN]="
280	"andere<"
281	"chaque<"
282	"chemin<"
283	"cote<"
284	"cot\u00e9<"
285	"c\u00f4te<"
286	"c\u00f4t\u00e9<"
287	"\u010du\u010d\u0113t<"
288	"Czech<"
289	"hi\u0161a<"
290	"irdisch<"
291	"lie<"
292	"lire<"
293	"llama<"
294	"l\u00f5ug<"
295	"l\u00f2za<"
296	"lu\u010d<"
297	"luck<"
298	"L\u00fcbeck<"
299	"lye<"
300	"l\u00e4vi<"
301	"L\u00f6wen<"
302	"m\u00e0\u0161ta<"
303	"m\u00eer<"
304	"myndig<"
305	"M\u00e4nner<"
306	"m\u00f6chten<"
307	"pi\u00f1a<"
308	"pint<"
309	"pylon<"
310	"\u0161\u00e0ran<"
311	"savoir<"
312	"\u0160erb\u016bra<"
313	"Sietla<"
314	"\u015blub<"
315	"subtle<"
316	"symbol<"
317	"s\u00e4mtlich<"
318	"waffle<"
319	"verkehrt<"
320	"wood<"
321	"vox<"
322	"v\u00e4ga<"
323	"yen<"
324	"yuan<"
325	"yucca<"
326	"\u017eal<"
327	"\u017eena<"
328	"\u017den\u0113va<"
329	"zoo0<"
330	"Zviedrija<"
331	"Z\u00fcrich<"
332	"zysk0<"
333	"\u00e4ndere"
334	}
335	}
336	}
337	}