Rev 7085 | Show entire file | Regard whitespace | Details | Blame | Last modification | View Log | RSS feed
Rev 7085 | Rev 9307 | ||
---|---|---|---|
Line 1... | Line 1... | ||
1 | #include |
1 | typedef unsigned int size_t; |
2 | #include |
2 | #define NULL ((void*)0) |
3 | #include |
- | |
Line 4... | Line 3... | ||
4 | 3 | ||
5 | typedef int conv_t; |
4 | typedef int conv_t; |
6 | typedef unsigned int ucs4_t; |
5 | typedef unsigned int ucs4_t; |
Line 23... | Line 22... | ||
23 | #define CP1251 1 |
22 | #define CP1251 1 |
24 | #define CP1252 2 |
23 | #define CP1252 2 |
25 | #define KOI8_RU 3 |
24 | #define KOI8_RU 3 |
26 | #define ISO8859_5 4 |
25 | #define ISO8859_5 4 |
27 | #define UTF_8 5 |
26 | #define UTF_8 5 |
28 | #define KOI8_R 6 |
- | |
- | 27 | ||
29 | #define ISO8859_1 7 |
28 | int strcmp (const char* a, const char* b) { |
- | 29 | return (*a && *b && (*a == *b)) ? ((*(a+1) || *(b+1)) ? (strcmp(a+1, b+1)) : (0)) : ((*a > *b) ? (1) : (-1)); |
|
- | 30 | } |
|
Line 30... | Line 31... | ||
30 | 31 | ||
31 | #include "cp866.h" |
32 | #include "cp866.h" |
32 | #include "cp1251.h" |
33 | #include "cp1251.h" |
33 | #include "cp1252.h" |
- | |
34 | #include "koi8_r.h" |
34 | #include "cp1252.h" |
35 | #include "koi8_ru.h" |
- | |
36 | #include "iso8859_1.h" |
35 | #include "koi8_ru.h" |
37 | #include "iso8859_5.h" |
36 | #include "iso8859_5.h" |
Line 38... | Line 37... | ||
38 | #include "utf8.h" |
37 | #include "utf8.h" |
39 | - | ||
40 | int encoding(const char *someencoding) { |
- | |
41 | - | ||
42 | char *what = strdup(someencoding); |
- | |
43 | /* Ignore //TRANSLIT or //IGNORE for now. */ |
- | |
44 | int i; |
- | |
45 | for(i = 0; i < strlen(what); i++) { |
- | |
46 | if(what[i] == '/') { |
- | |
47 | what[i] = '\0'; |
- | |
48 | break; |
- | |
49 | } |
- | |
50 | } |
38 | |
51 | 39 | int encoding(const char *what) { |
|
52 | if (!strcasecmp(what,"CP866")) return CP866; |
- | |
53 | if (!strcasecmp(what,"CP1251")) return CP1251; |
40 | if (!strcmp(what,"CP866")) return CP866; |
54 | if (!strcasecmp(what,"windows-1251")) return CP1251; |
- | |
55 | if (!strcasecmp(what,"CP1252")) return CP1252; |
- | |
56 | if (!strcasecmp(what,"windows-1252")) return CP1252; |
41 | if (!strcmp(what,"CP1251")) return CP1251; |
57 | if (!strcasecmp(what,"KOI8-R")) return KOI8_R; |
- | |
58 | if (!strcasecmp(what,"KOI8-RU")) return KOI8_RU; |
42 | if (!strcmp(what,"CP1252")) return CP1252; |
59 | if (!strcasecmp(what,"ISO8859-1")) return ISO8859_1; |
43 | if (!strcmp(what,"KOI8-RU")) return KOI8_RU; |
60 | if (!strcasecmp(what,"ISO8859-5")) return ISO8859_5; |
44 | if (!strcmp(what,"ISO8859-5")) return ISO8859_5; |
61 | if (!strcasecmp(what,"UTF-8")) return UTF_8; |
45 | if (!strcmp(what,"UTF-8")) return UTF_8; |
Line 62... | Line 46... | ||
62 | return -1; |
46 | return -1; |
63 | } |
47 | } |
64 | - | ||
65 | iconv_t iconv_open(const char *tocode, const char *fromcode) { |
48 | |
66 | int to, from; |
49 | iconv_t iconv_open(const char *tocode, const char *fromcode) { |
67 | - | ||
68 | if ((to=encoding(tocode))==-1) return -1; |
50 | int to, from; |
69 | if ((from=encoding(fromcode))==-1) return -1; |
51 | if ((to=encoding(tocode))==-1) return -1; |
70 | - | ||
71 | to=to<<16&0xFFFF0000; |
52 | if ((from=encoding(fromcode))==-1) return -1; |
72 | from=from&0xFFFF; |
53 | to=to<<16&0xFFFF0000; |
Line 73... | Line -... | ||
73 | - | ||
74 | return to+from; |
- | |
75 | } |
- | |
76 | - | ||
77 | int iconv_close(iconv_t icd) |
- | |
78 | { |
54 | from=from&0xFFFF; |
79 | return 0; |
- | |
80 | } |
- | |
81 | - | ||
82 | size_t iconv(iconv_t cd, const char **inbuf, size_t *inbytesleft, |
55 | return to+from; |
83 | char **outbuf, size_t *outbytesleft) |
- | |
84 | { |
56 | } |
85 | int n, to, from; |
57 | |
86 | size_t count1,count2; |
58 | size_t iconv(iconv_t cd, const char **inbuf, size_t *inbytesleft, char **outbuf, size_t *outbytesleft) { |
Line -... | Line 59... | ||
- | 59 | int n, to, from, count1,count2; |
|
- | 60 | int pwc, converted,written; |
|
- | 61 | int (*mbtowc)(conv_t, ucs4_t*, const unsigned char*, int); |
|
87 | unsigned int pwc; |
62 | int (*wctomb)(conv_t, unsigned char*, ucs4_t, int); |
88 | int converted,written; |
63 | |
Line 89... | Line 64... | ||
89 | int (*mbtowc)(conv_t, ucs4_t *, const unsigned char *, int); |
64 | char *str; |
90 | int (*wctomb)(conv_t, unsigned char *, ucs4_t, int); |
65 | str=*outbuf; |
91 | 66 | ||
92 | to=cd>>16; |
67 | from=cd>>16; |
93 | from=cd&0xFFFF; |
68 | to=cd&0xFFFF; |
94 | - | ||
95 | switch (from) |
69 | |
96 | { |
- | |
97 | case CP866: mbtowc=cp866_mbtowc; break; |
70 | switch (from) |
98 | case CP1251: mbtowc=cp1251_mbtowc; break; |
71 | { |
99 | case CP1252: mbtowc=cp1252_mbtowc; break; |
72 | case CP866: mbtowc=cp866_mbtowc; break; |
100 | case ISO8859_1: mbtowc=iso8859_1_mbtowc; break; |
73 | case CP1251: mbtowc=cp1251_mbtowc; break; |
Line 101... | Line 74... | ||
101 | case ISO8859_5: mbtowc=iso8859_5_mbtowc; break; |
74 | case CP1252: mbtowc=cp1252_mbtowc; break; |
102 | case KOI8_R: mbtowc=koi8_r_mbtowc; break; |
75 | case ISO8859_5: mbtowc=iso8859_5_mbtowc; break; |
103 | case KOI8_RU: mbtowc=koi8_ru_mbtowc; break; |
76 | case KOI8_RU: mbtowc=koi8_ru_mbtowc; break; |
104 | case UTF_8: mbtowc=utf8_mbtowc; break; |
77 | case UTF_8: mbtowc=utf8_mbtowc; break; |
105 | default: return (size_t)-1; |
78 | default: return -2; |
106 | } |
- | |
107 | 79 | } |
|
108 | switch (to) |
- | |
109 | { |
80 | |
110 | case CP866: wctomb=cp866_wctomb; break; |
81 | switch (to) |
111 | case CP1251: wctomb=cp1251_wctomb; break; |
82 | { |
112 | case CP1252: wctomb=cp1252_wctomb; break; |
83 | case CP866: wctomb=cp866_wctomb; break; |
Line 113... | Line 84... | ||
113 | case ISO8859_1: wctomb=iso8859_1_wctomb; break; |
84 | case CP1251: wctomb=cp1251_wctomb; break; |
114 | case ISO8859_5: wctomb=iso8859_5_wctomb; break; |
85 | case CP1252: wctomb=cp1252_wctomb; break; |
Line 115... | Line -... | ||
115 | case KOI8_R: wctomb=koi8_r_wctomb; break; |
- | |
116 | case KOI8_RU: wctomb=koi8_ru_wctomb; break; |
- | |
117 | case UTF_8: wctomb=utf8_wctomb; break; |
- | |
118 | default: return (size_t)-1; |
86 | case ISO8859_5: wctomb=iso8859_5_wctomb; break; |
119 | } |
- | |
120 | - | ||
121 | count1=0; |
- | |
122 | count2=0; |
- | |
123 | - | ||
124 | /* Convert input multibyte char to wide character by using calls to mbtowc */ |
- | |
125 | /* Convert wide character to multibyte by calls to wctomb */ |
- | |
126 | /* Handle errors as we go on converting to be as standard compliant as possible */ |
- | |
127 | while(count1 < *inbytesleft) { |
- | |
128 | unsigned char mbholder[] = { 0,0,0,0,0,0 }; |
- | |
129 | - | ||
130 | int numbytes = (mbtowc)(0, &pwc,((*inbuf)+count1), *inbytesleft - count1); |
- | |
131 | if(numbytes < 0) { |
- | |
132 | /* errno = EILSEQ if invalid multibyte sequence encountered in input */ |
- | |
133 | /* errno = EINVAL if input ends in the middle of a multibyte sequence */ |
- | |
134 | 87 | case KOI8_RU: wctomb=koi8_ru_wctomb; break; |
|
135 | switch(numbytes) { |
- | |
136 | case RET_TOOFEW(0): |
- | |
137 | errno = EINVAL; |
- | |
138 | break; |
- | |
139 | - | ||
140 | case RET_ILSEQ: |
- | |
141 | errno = EILSEQ; |
88 | case UTF_8: wctomb=utf8_wctomb; break; |
Line 142... | Line -... | ||
142 | break; |
- | |
143 | } |
- | |
144 | - | ||
145 | *inbytesleft -= count1; |
- | |
146 | *outbytesleft -= count2; |
- | |
147 | *inbuf += count1; |
- | |
148 | *outbuf += count2; |
- | |
149 | return (size_t) -1; |
- | |
150 | } |
- | |
151 | 89 | default: return -3; |
|
152 | /* Convert from wide to multibyte storing result in mbholder and num converted in numbytes2 */ |
90 | } |
153 | /* Pass the minimum amount of space we have, one from mbholder and one from remaining in outbuf */ |
91 | |
154 | int minspace = sizeof(mbholder) <= (*outbytesleft - count2) ? sizeof(mbholder) : (*outbytesleft - count2); |
92 | count1=0; |
155 | - | ||
Line 156... | Line -... | ||
156 | int numbytes2 = (wctomb)(0, &mbholder[0], pwc, minspace); |
- | |
157 | if(numbytes2 < 0) { |
- | |
158 | switch(numbytes2) { |
93 | count2=0; |
159 | case RET_ILUNI: |
94 | |
Line 160... | Line 95... | ||
160 | errno = EILSEQ; |
95 | while ( *inbytesleft>0 && *outbytesleft>1) |
- | 96 | { |
|
- | 97 | n=1; |
|
161 | break; |
98 | |
Line 162... | Line -... | ||
162 | case RET_TOOSMALL: |
- | |
163 | errno = E2BIG; |
- | |
164 | break; |
99 | do { |
165 | } |
- | |
Line -... | Line 100... | ||
- | 100 | //converted= (utf8_mbtowc)(0,&pwc,((*inbuf)+count1),n); |
|
- | 101 | // printf("%d\n",n); |
|
166 | 102 | converted = (mbtowc)(0,&pwc,((*inbuf)+count1),n); |
|
167 | *inbytesleft -= count1; |
103 | |
168 | *outbytesleft -= count2; |
104 | n++; |
- | 105 | } while (converted==RET_TOOFEW(0)); |
|
Line 169... | Line -... | ||
169 | *inbuf += count1; |
- | |
170 | *outbuf += count2; |
106 | |
171 | - | ||
172 | return (size_t) -1; |
- | |
173 | } |
- | |
174 | - | ||
175 | int i; |
107 | if (converted<0) return -10; |
176 | for(i = 0; i < numbytes2; i++) { |
108 | //written= (cp866_wctomb)(0,str+count2,pwc,1); |
Line 177... | Line -... | ||
177 | *(*outbuf + count2 + i) = mbholder[i]; |
- | |
178 | } |
- | |
179 | - | ||
180 | count1+=numbytes; |
- | |
181 | count2+=numbytes2; |
- | |
182 | } |
- | |
183 | - | ||
184 | /* Successfully converted everything, update the variables and return number of bytes converted */ |
- | |
185 | *inbytesleft -= count1; |
- | |
186 | *outbytesleft -= count2; |
- | |
187 | *inbuf += count1; |
- | |
188 | *outbuf += count2; |
- | |
189 | - | ||
190 | return count1; |
- | |
191 | } |
- | |
192 | - | ||
193 | /* int main() */ |
- | |
194 | /* { */ |
- | |
195 | /* char *s;// ="вертолет"; */ |
- | |
196 | /* char *z; */ |
- | |
197 | /* //unsigned int pwc; */ |
- | |
198 | /* iconv_t cd; */ |
- | |
199 | /* size_t in, out; */ |
- | |
200 | - | ||
201 | /* FILE *infile; */ |
- | |
202 | /* char *fname = "file3.txt"; */ |
- | |
203 | - | ||
204 | /* size_t testmax = 100; */ |
- | |
205 | /* size_t test = 0; */ |
- | |
206 | - | ||
207 | /* infile = fopen(fname,"r"); */ |
- | |
208 | - | ||
209 | /* fseek(infile, 0, SEEK_END); */ |
- | |
210 | /* size_t file_size = ftell(infile); */ |
- | |
211 | /* rewind(infile); */ |
- | |
212 | - | ||
213 | /* char *buffer = (char*)malloc(file_size * sizeof(char)); */ |
- | |
214 | /* if (buffer == NULL) */ |
- | |
215 | /* { */ |
- | |
216 | /* fclose(infile); */ |
- | |
217 | /* printf("Error allocating %d bytes.\n", file_size * sizeof(char)); */ |
- | |
218 | /* return -1; */ |
- | |
219 | /* } */ |
- | |
220 | /* size_t bytes_read = fread(buffer, sizeof(char), file_size, infile); */ |
- | |
221 | /* if (bytes_read != file_size) */ |
- | |
222 | /* { */ |
- | |
223 | /* /\* printf("Have read only %d bytes of %d.\n", bytes_read, file_size); *\/ */ |
- | |
224 | /* free(buffer); */ |
- | |
225 | /* fclose(infile); */ |
- | |
226 | /* return -1; */ |
- | |
227 | /* } */ |
- | |
228 | - | ||
229 | /* /\* in=strlen(buffer); *\/ */ |
- | |
230 | /* in = bytes_read; */ |
- | |
231 | /* z=malloc(in+12000); */ |
- | |
232 | - | ||
233 | /* out=in-1000; */ |
- | |
234 | /* cd=iconv_open("UTF-8","UTF-8"); */ |
- | |
235 | /* // printf("%x\n",cd); */ |
109 | written = (wctomb)(0,str+count2,pwc,1); |
236 | /* int t; */ |
- | |
237 | /* char *zor = z; */ |
110 | if (written<0) written=0;//return -11; |
238 | 111 | ||
239 | /* /\* for(t = 0; t < 27400; t++) *\/ */ |
112 | //printf("Conv:%d Wri:%d In:%d Out:%d UTF:%x UCS:%x 866:%s\n",converted, written, *inbytesleft,*outbytesleft,*((*inbuf)+count1),pwc, str); |
240 | /* /\* printf("0x%x,", buffer[t]); *\/ */ |
- | |
241 | - | ||
242 | /* t=iconv(cd, &buffer, &in, &z, &out); */ |
- | |
243 | /* /\* printf("\nResult after iconv(): %d", t); *\/ */ |
- | |
244 | - | ||
245 | /* /\* for(t = 0; t < 24259; t++) *\/ */ |
113 | |
246 | /* /\* printf("%c", zor[t]); *\/ */ |
114 | (*inbytesleft)-=converted; |
247 | - | ||
248 | /* //for (;s |
115 | (*outbytesleft)-=written; |
249 | /* } */ |
116 | count1+=converted; |
250 | 117 | count2+=written; |
|
251 | /* typedef struct */ |
118 | } |
252 | /* { */ |
119 | *(str+count2)='\0'; |
253 | /* char *name; */ |
120 |