|
|
Posted on 2005-11-23 17:18 非魚 閱讀(3623) 評論(0) 編輯 收藏 所屬分類: Sybase
Sybase Adaptive Server
Enterprise在中文支持方面，提供的排序方式比較單一。如果使用CP850（支持GB2312標準），排序方式是比較多的。但GB2312的漢字
庫太小，多數情況下，我們至少要使用CP936甚至GB18030字符集。在使用CP936、GB18030字符集時，你只有BINARY方式的排序可以
選擇。 問題是，如果一個早期應該使用CP850+大小寫不敏感方式的排序，在升級到新的字符集+BINARY排序時，程序中的大小寫要改成敏感的。 類似的問題可以通過修改SYBASE的相應字符集下的排序文件解決。你甚至可以定義自己的排序方式。 首先我們來看看GB18030字符集的BINARY排序。BINARY排序對應的是$SYB_HOME/charsets/gb18030/binary.srt，用文本編輯器打開這個文件，可以看到其內容如下：
1 ; semi-colon is the comment character
2[sortorder]
3;===============================================================================
4;
5; Sort Order Overview:
6; --------------------
7; Based on the gb18030 simplified Chinese character set, this sort
8; order is a binary ordering.
9;
10;===============================================================================
11
12class = 0x01 ; Class `1' sort order
13id = 0x32 ; id = 50
14name = bin_gb18030
15menuname = "Binary ordering, for gb18030."
16charset = gb18030
17
18description = "Binary sort order for simplified Chinese using gb18030."
19
20binary = "true"
21 Class、id、name、menuname、charset、description都不用修改，而binary=true則指明使用binary方式排序，其實這句等價于對01~FF每個字符都進行定義。 其
次，看一下其他字符集中的大小寫不敏感的排序文件，如$SYB_HOME/charsets/iso_1/noaccents.srt，具體內容就不寫
了。可以發現大小寫不敏感只是設置a, A；b, B等字符相等。參考這個排序文件，我們就可以這樣定義binary.srt： 1. 設置a=A...z=Z； 2. 定義其他字符。 這樣修改之后，就支持GB18030下的大小寫不敏感排序了。 修改排序文件后，需要使用加裁該字符集和排序： charset -Usa -Ppassword -Sserver sort_order_file charset_name 然后在isql中用sp_configure 'default sortorder id', 文件中的id（十進制），兩次重啟SYBASE后修改字符集排序就完成了。
這種方法適用于ASE11.9.2~15.0各個版本，經歷了實踐考驗。
另外對于早期版本，沒有CP936和GB18030，可以從15.0拷一個過去用。 下面附上我修改的GB18030, BINARY.SRT文件內容：
1; semi-colon is the comment character
2[sortorder]
3;===============================================================================
4;
5; Sort Order Overview:
6; --------------------
7; Based on the cp936 simplified Chinese character set, this sort
8; order is a binary ordering.
9;
10;===============================================================================
11
12class = 0x01 ; Class `1' sort order
13id = 0x32 ; id = 50
14name = bin_gb18030
15menuname = "Binary ordering, for gb18030."
16charset = gb18030
17;preference = false ; Do not use preference
18
19description = "Binary sort order for simplified Chinese using gb18030."
20; Ligatures
21
22;lig = 0xC6=0xE6, after ae ; AE, ae ligature
23;lig = 0xDF, after ss ; small german letter sharp s
24
25; Control characters
26
27char = 0x01 ;(SOH) start of heading
28char = 0x02 ;(STX) start of text
29char = 0x03 ;(ETX) end of text
30char = 0x04 ;(EOT) end of transmission
31char = 0x05 ;(ENQ) enquiry
32char = 0x06 ;(ACK) acknowledge
33char = 0x07 ;(BEL) bell
34char = 0x08 ;(BS) backspace
35char = 0x09 ;(HT) horizontal tab
36char = 0x0A ;(LF) newline, or line feed
37char = 0x0B ;(VT) vertical tab
38char = 0x0C ;(FF) form feed
39char = 0x0D ;(CR) carriage return
40char = 0x0E ;(SO) shift out
41char = 0x0F ;(SI) shift in
42char = 0x10 ;(DLE) data link escape
43char = 0x11 ;(DC1) device control 1
44char = 0x12 ;(DC2) device control 2
45char = 0x13 ;(DC3) device control 3
46char = 0x14 ;(DC4) device control 4
47char = 0x15 ;(NAK) negative acknowledge
48char = 0x16 ;(SYN) synchronous idle
49char = 0x17 ;(ETB) end transmission blk
50char = 0x18 ;(CAN) cancel
51char = 0x19 ;(EM) end of medium
52char = 0x1A ;(SUB) substitute
53char = 0x1B ;(ESC) escape
54char = 0x1C ;(FS) file separator
55char = 0x1D ;(GS) group separator
56char = 0x1E ;(RS) record separator
57char = 0x1F ;(US) unit separator
58
59; All non-alphanumeric characters, including puntuation
60; These are sorted merely by their numerical ordering
61; based on the ISO 8859-1 standard for clarity and
62; consistency
63
64char = 0x20 ;( ) space
65char = 0x21 ;(!) exclamation mark
66char = 0x22 ;(") quotation mark
67char = 0x23 ;(#) number sign
68char = 0x24 ;($) dollar sign
69char = 0x25 ;(%) percent sign
70char = 0x26 ;(&) ampersand
71char = 0x27 ;(') apostrophe
72char = 0x28 ;(() left parenthesis
73char = 0x29 ;()) right parenthesis
74char = 0x2A ;(*) asterisk
75char = 0x2B ;(+) plus sign
76char = 0x2C ;(,) comma
77char = 0x2D ;(-) hyphen, minus sign
78char = 0x2E ;(.) full stop
79char = 0x2F ;(/) solidus
80char = 0x3A ;(:) colon
81char = 0x3B ;(;) semicolon
82char = 0x3C ;(<) less-than sign
83char = 0x3D ;(=) equals sign
84char = 0x3E ;(>) greater-than sign
85char = 0x3F ;(?) question mark
86char = 0x40 ;(@) commercial at
87char = 0x5B ;([) left square bracket
88char = 0x5C ;(\) reverse solidus
89char = 0x5D ;(]) right square bracket
90char = 0x5E ;(^) circumflex accent
91char = 0x5F ;(_) low line
92char = 0x60 ;(`) grave accent
93char = 0x7B ;({) left curly bracket
94char = 0x7C ;(|) vertical line
95char = 0x7D ;(}) right curly bracket
96char = 0x7E ;(~) tilde
97char = 0x7F ;delete, or rubout
98char = 0x80 ; undefined
99char = 0x81 ; undefined
100char = 0x82 ; undefined
101char = 0x83 ; undefined
102char = 0x84 ; undefined
103char = 0x85 ; undefined
104char = 0x86 ; undefined
105char = 0x87 ; undefined
106char = 0x88 ; undefined
107char = 0x89 ; undefined
108char = 0x8A ; undefined
109char = 0x8B ; undefined
110char = 0x8C ; undefined
111char = 0x8D ; undefined
112char = 0x8E ; undefined
113char = 0x8F ; undefined
114char = 0x90 ; undefined
115char = 0x91 ; undefined
116char = 0x92 ; undefined
117char = 0x93 ; undefined
118char = 0x94 ; undefined
119char = 0x95 ; undefined
120char = 0x96 ; undefined
121char = 0x97 ; undefined
122char = 0x98 ; undefined
123char = 0x99 ; undefined
124char = 0x9A ; undefined
125char = 0x9B ; undefined
126char = 0x9C ; undefined
127char = 0x9D ; undefined
128char = 0x9E ; undefined
129char = 0x9F ; undefined
130char = 0xA0 ;no-break space
131char = 0xA1 ;inverted exclamation mark
132char = 0xA2 ;cent sign
133char = 0xA3 ;pound sign
134char = 0xA4 ;currency sign
135char = 0xA5 ;yen sign
136char = 0xA6 ;broken bar
137char = 0xA7 ;paragraph sign, section sign
138char = 0xA8 ;diaeresis
139char = 0xA9 ;copyright sign
140char = 0xAA ;feminine ordinal indicator
141char = 0xAB ;left angle quotation mark
142char = 0xAC ;not sign
143char = 0xAD ;soft hyphen
144char = 0xAE ;registered trade mark sign
145char = 0xAF ;macron
146char = 0xB0 ;ring above or degree sign
147char = 0xB1 ;plus/minus (+/-) sign
148char = 0xB2 ;superscript 2
149char = 0xB3 ;superscript 3
150char = 0xB4 ;acute accent
151char = 0xB5 ;micro sign
152char = 0xB6 ;pilcrow or paragraph sign
153char = 0xB7 ;middle dot
154char = 0xB8 ;cedilla
155char = 0xB9 ;superscript 1
156char = 0xBA ;masculine ordinal indicator
157char = 0xBB ;right angle quotation mark
158char = 0xBC ;vulgar fraction one quarter
159char = 0xBD ;vulgar fraction one half
160char = 0xBE ;vulgar fraction three quarter
161char = 0xBF ;inverted question mark
162char = 0xC0
163char = 0xC1
164char = 0xC2
165char = 0xC3
166char = 0xC4
167char = 0xC5
168char = 0xC6
169char = 0xC7
170char = 0xC8
171char = 0xC9
172char = 0xCA
173char = 0xCB
174char = 0xCC
175char = 0xCD
176char = 0xCE
177char = 0xCF
178char = 0xD0
179char = 0xD1
180char = 0xD2
181char = 0xD3
182char = 0xD4
183char = 0xD5
184char = 0xD6
185char = 0xD7 ;multiplication sign
186char = 0xD8
187char = 0xD9
188char = 0xDA
189char = 0xDB
190char = 0xDC
191char = 0xDD
192char = 0xDE
193char = 0xDF
194char = 0xE0
195char = 0xE1
196char = 0xE2
197char = 0xE3
198char = 0xE4
199char = 0xE5
200char = 0xE6
201char = 0xE7
202char = 0xE8
203char = 0xE9
204char = 0xEA
205char = 0xEB
206char = 0xEC
207char = 0xED
208char = 0xEE
209char = 0xEF
210char = 0xF0
211char = 0xF1
212char = 0xF2
213char = 0xF3
214char = 0xF4
215char = 0xF5
216char = 0xF6
217char = 0xF7
218char = 0xF8
219char = 0xF9
220char = 0xFA
221char = 0xFB
222char = 0xFC
223char = 0xFD
224char = 0xFE
225char = 0xFF
226
227; Digits
228
229char = 0x30 ;(0) digit zero
230char = 0x31 ;(1) digit one
231char = 0x32 ;(2) digit two
232char = 0x33 ;(3) digit three
233char = 0x34 ;(4) digit four
234char = 0x35 ;(5) digit five
235char = 0x36 ;(6) digit six
236char = 0x37 ;(7) digit seven
237char = 0x38 ;(8) digit eight
238char = 0x39 ;(9) digit nine
239
240; Latin Alphabet
241
242char = 0x41=0x61
243 ;A, a, A-grave, a-grave, A-acute, a-acute, A-circumflex, a-circumflex,
244 ;A-tilde, a-tilde, ;A-diaeresis, a-diaeresis, A-ring, a-ring
245char = 0x42=0x62 ;letter B, b
246char = 0x43=0x63
247char = 0x44=0x64 ;letter D, d
248char = 0x45=0x65
249 ;E, e, E-grave, e-grave, E-acute, e-acute, E-circumflex, e-circumflex,
250 ;E-diaeresis, e-diaeresis
251char = 0x46=0x66 ;letter F, f
252char = 0x47=0x67 ;letter G, g
253char = 0x48=0x68 ;letter H, h
254char = 0x49=0x69
255 ;I, i, I-grave, i-grave, I-acute, i-acute, I-circumflex, i-circumflex,
256 ;I-diaeresis, i-diaeresis
257char = 0x4A=0x6A ;letter J, j
258char = 0x4B=0x6B ;letter K, k
259char = 0x4C=0x6C ;letter L, l
260char = 0x4D=0x6D ;letter M, m
261char = 0x4E=0x6E
262char = 0x4F=0x6F
263 ;O, o, O-grave, o-grave, O-acute, o-acute, O-circumflex, o-circumflex,
264 ;O-tilde, o-tilde, O-diaeresis, o-diaeresis, O-stroke, o-stroke
265char = 0x50=0x70 ;letter P, p
266char = 0x51=0x71 ;letter Q, q
267char = 0x52=0x72 ;letter R, r
268char = 0x53=0x73 ;letter S, s
269char = 0x54=0x74 ;letter T, t
270char = 0x55=0x75
271 ;U, u, U-grave, u-grave, U-acute, u-acute, U-circumflex, u-circumflex,
272 ;U-diaeresis, u-diaeresis
273char = 0x56=0x76 ;letter V, v
274char = 0x57=0x77 ;letter W, w
275char = 0x58=0x78 ;letter X, x
276char = 0x59=0x79
277char = 0x5A=0x7A ;letter Z, z
278
279; Alpha characters not used in English, French or German:
280
281;char = 0xD0=0xF0 ;icelandic capital letter eth, small letter eth
282;char = 0xDE=0xFE ;icelandic capital letter thorn, small letter thorn
283
|