6 // First some base level utility routines
13 #include "nscore.h" // for mozalloc headers
23 // default encoding and keystring
24 #define SPELL_ENCODING "ISO8859-1"
25 #define SPELL_KEYSTRING "qwertyuiop|asdfghjkl|zxcvbnm"
27 // default morphological fields
28 #define MORPH_STEM "st:"
29 #define MORPH_ALLOMORPH "al:"
30 #define MORPH_POS "po:"
31 #define MORPH_DERI_PFX "dp:"
32 #define MORPH_INFL_PFX "ip:"
33 #define MORPH_TERM_PFX "tp:"
34 #define MORPH_DERI_SFX "ds:"
35 #define MORPH_INFL_SFX "is:"
36 #define MORPH_TERM_SFX "ts:"
37 #define MORPH_SURF_PFX "sp:"
38 #define MORPH_FREQ "fr:"
39 #define MORPH_PHON "ph:"
40 #define MORPH_HYPH "hy:"
41 #define MORPH_PART "pa:"
42 #define MORPH_FLAG "fl:"
43 #define MORPH_HENTRY "_H:"
44 #define MORPH_TAG_LEN strlen(MORPH_STEM)
51 #define DEFAULTFLAGS 65510
52 #define FORBIDDENWORD 65510
53 #define ONLYUPCASEFLAG 65511
55 // convert UTF-16 characters to UTF-8
56 LIBHUNSPELL_DLL_EXPORTED char * u16_u8(char * dest, int size, const w_char * src, int srclen);
58 // convert UTF-8 characters to UTF-16
59 LIBHUNSPELL_DLL_EXPORTED int u8_u16(w_char * dest, int size, const char * src);
62 LIBHUNSPELL_DLL_EXPORTED void flag_qsort(unsigned short flags[], int begin, int end);
64 // binary search in 2-byte vector
65 LIBHUNSPELL_DLL_EXPORTED int flag_bsearch(unsigned short flags[], unsigned short flag, int right);
67 // remove end of line char(s)
68 LIBHUNSPELL_DLL_EXPORTED void mychomp(char * s);
71 LIBHUNSPELL_DLL_EXPORTED char * mystrdup(const char * s);
73 // strcat for limited length destination string
74 LIBHUNSPELL_DLL_EXPORTED char * mystrcat(char * dest, const char * st, int max);
76 // duplicate reverse of string
77 LIBHUNSPELL_DLL_EXPORTED char * myrevstrdup(const char * s);
79 // parse into tokens with char delimiter
80 LIBHUNSPELL_DLL_EXPORTED char * mystrsep(char ** sptr, const char delim);
81 // parse into tokens with char delimiter
82 LIBHUNSPELL_DLL_EXPORTED char * mystrsep2(char ** sptr, const char delim);
84 // parse into tokens with char delimiter
85 LIBHUNSPELL_DLL_EXPORTED char * mystrrep(char *, const char *, const char *);
87 // append s to ends of every lines in text
88 LIBHUNSPELL_DLL_EXPORTED void strlinecat(char * lines, const char * s);
90 // tokenize into lines with new line
91 LIBHUNSPELL_DLL_EXPORTED int line_tok(const char * text, char *** lines, char breakchar);
93 // tokenize into lines with new line and uniq in place
94 LIBHUNSPELL_DLL_EXPORTED char * line_uniq(char * text, char breakchar);
95 LIBHUNSPELL_DLL_EXPORTED char * line_uniq_app(char ** text, char breakchar);
97 // change oldchar to newchar in place
98 LIBHUNSPELL_DLL_EXPORTED char * tr(char * text, char oldc, char newc);
101 LIBHUNSPELL_DLL_EXPORTED int reverseword(char *);
104 LIBHUNSPELL_DLL_EXPORTED int reverseword_utf(char *);
107 LIBHUNSPELL_DLL_EXPORTED int uniqlist(char ** list, int n);
109 // free character array list
110 LIBHUNSPELL_DLL_EXPORTED void freelist(char *** list, int n);
112 // character encoding information
115 unsigned char clower;
116 unsigned char cupper;
119 // Unicode character encoding information
120 struct unicode_info {
122 unsigned short cupper;
123 unsigned short clower;
126 LIBHUNSPELL_DLL_EXPORTED int initialize_utf_tbl();
127 LIBHUNSPELL_DLL_EXPORTED void free_utf_tbl();
128 LIBHUNSPELL_DLL_EXPORTED unsigned short unicodetoupper(unsigned short c, int langnum);
129 LIBHUNSPELL_DLL_EXPORTED unsigned short unicodetolower(unsigned short c, int langnum);
130 LIBHUNSPELL_DLL_EXPORTED int unicodeisalpha(unsigned short c);
132 LIBHUNSPELL_DLL_EXPORTED struct cs_info * get_current_cs(const char * es);
134 // get language identifiers of language codes
135 LIBHUNSPELL_DLL_EXPORTED int get_lang_num(const char * lang);
137 // get characters of the given 8bit encoding with lower- and uppercase forms
138 LIBHUNSPELL_DLL_EXPORTED char * get_casechars(const char * enc);
140 // convert null terminated string to all caps using encoding
141 LIBHUNSPELL_DLL_EXPORTED void enmkallcap(char * d, const char * p, const char * encoding);
143 // convert null terminated string to all little using encoding
144 LIBHUNSPELL_DLL_EXPORTED void enmkallsmall(char * d, const char * p, const char * encoding);
146 // convert null terminated string to have initial capital using encoding
147 LIBHUNSPELL_DLL_EXPORTED void enmkinitcap(char * d, const char * p, const char * encoding);
149 // convert null terminated string to all caps
150 LIBHUNSPELL_DLL_EXPORTED void mkallcap(char * p, const struct cs_info * csconv);
152 // convert null terminated string to all little
153 LIBHUNSPELL_DLL_EXPORTED void mkallsmall(char * p, const struct cs_info * csconv);
155 // convert null terminated string to have initial capital
156 LIBHUNSPELL_DLL_EXPORTED void mkinitcap(char * p, const struct cs_info * csconv);
158 // convert first nc characters of UTF-8 string to little
159 LIBHUNSPELL_DLL_EXPORTED void mkallsmall_utf(w_char * u, int nc, int langnum);
161 // convert first nc characters of UTF-8 string to capital
162 LIBHUNSPELL_DLL_EXPORTED void mkallcap_utf(w_char * u, int nc, int langnum);
164 // get type of capitalization
165 LIBHUNSPELL_DLL_EXPORTED int get_captype(char * q, int nl, cs_info *);
167 // get type of capitalization (UTF-8)
168 LIBHUNSPELL_DLL_EXPORTED int get_captype_utf8(w_char * q, int nl, int langnum);
170 // strip all ignored characters in the string
171 LIBHUNSPELL_DLL_EXPORTED void remove_ignored_chars_utf(char * word, unsigned short ignored_chars[], int ignored_len);
173 // strip all ignored characters in the string
174 LIBHUNSPELL_DLL_EXPORTED void remove_ignored_chars(char * word, char * ignored_chars);
176 LIBHUNSPELL_DLL_EXPORTED int parse_string(char * line, char ** out, int ln);
178 LIBHUNSPELL_DLL_EXPORTED int parse_array(char * line, char ** out, unsigned short ** out_utf16,
179 int * out_utf16_len, int utf8, int ln);
181 LIBHUNSPELL_DLL_EXPORTED int fieldlen(const char * r);
182 LIBHUNSPELL_DLL_EXPORTED char * copy_field(char * dest, const char * morph, const char * var);
184 LIBHUNSPELL_DLL_EXPORTED int morphcmp(const char * s, const char * t);
186 LIBHUNSPELL_DLL_EXPORTED int get_sfxcount(const char * morph);
188 // conversion function for protected memory
189 LIBHUNSPELL_DLL_EXPORTED void store_pointer(char * dest, char * source);
191 // conversion function for protected memory
192 LIBHUNSPELL_DLL_EXPORTED char * get_stored_pointer(const char * s);
195 LIBHUNSPELL_DLL_EXPORTED inline char* HENTRY_DATA(struct hentry *h)
200 else if (h->var & H_OPT_ALIASM)
201 ret = get_stored_pointer(HENTRY_WORD(h) + h->blen + 1);
203 ret = HENTRY_WORD(h) + h->blen + 1;
207 // NULL-free version for warning-free OOo build
208 LIBHUNSPELL_DLL_EXPORTED inline const char* HENTRY_DATA2(const struct hentry *h)
213 else if (h->var & H_OPT_ALIASM)
214 ret = get_stored_pointer(HENTRY_WORD(h) + h->blen + 1);
216 ret = HENTRY_WORD(h) + h->blen + 1;
220 LIBHUNSPELL_DLL_EXPORTED inline char* HENTRY_FIND(struct hentry *h, const char *p)
222 return (HENTRY_DATA(h) ? strstr(HENTRY_DATA(h), p) : NULL);
225 #define w_char_eq(a,b) (((a).l == (b).l) && ((a).h == (b).h))