diff options
author | b0ric <b0risov.alexandr@rambler.ru> | 2009-08-18 20:45:05 +0300 |
---|---|---|
committer | b0ric <b0risov.alexandr@rambler.ru> | 2009-08-18 20:45:05 +0300 |
commit | 7742a666d5ac98ea3a976336cf60a5530ab29e73 (patch) | |
tree | f985cda18f15f8a13feb5c10d17c5cc7a952f23a /src/engparser.h | |
parent | e5165d9838d03963284710e6b957fe9a3b0e267a (diff) |
Diffstat (limited to 'src/engparser.h')
-rw-r--r-- | src/engparser.h | 53 |
1 files changed, 53 insertions, 0 deletions
diff --git a/src/engparser.h b/src/engparser.h new file mode 100644 index 0000000..ca0a1b5 --- /dev/null +++ b/src/engparser.h @@ -0,0 +1,53 @@ +/* + * This file is part of WordExtract. + * + * Copyright (C) 2009 Borisov Alexandr + * + * WordExtract is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * WordExtract is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with WordExtract. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef ENG_PARSER_H +#define ENG_PARSER_H + +#define WORD_INCLUDED 0 +#define WORD_NOT_INCLUDED 1 + +typedef struct { + char symbol; + int excl_symbolled; + int excl_w_starting; + int excl_w_middle; + int excl_w_ending; + int excl_word_after_symb; +} Parseoptions; + +/* Parsing options */ +extern int excl_w_capital; +extern int lower_first_capital; +extern Parseoptions hyphen; +extern Parseoptions quote; + +/* + * Recieves: line terminated by "\n\0" + * + * Words with "-" we'll be processed as a whole word + * And also we suppose that each sentence starts with capital letter + * and other words in the middle of the sentence which starts with + * capital letter is name (peoples, towns, I, etc...). + * Single quoted sentences are not allowed. It's gramatically incorrect + */ +int parseengphrase(char *); +int parse_eng_word(char *word, Parseoptions opt); + +#endif /*ENG_PARSER_H*/ |