📄 geturltermfreqs.h
字号:
/** * getUrlTermFreqs.h * API for get terms from urls * zhiyong, zhang, March, 1st, 2006 **/#ifndef GET_URL_TERMFREQS_H#define GET_URL_TERMFREQS_H#define FORGETTING_FACTOR 1 //not current visit link in the session, freq will be divided by this number#define MAX_TERMS_PER_PAGE 100 //for merger purpose, doubled, infact one page extract half this numbertypedef struct { char term[50]; int freq;} TERM_ITEM;typedef struct { int termNum; TERM_ITEM terms[MAX_TERMS_PER_PAGE];} PAGE_TERMS;#ifdef __cplusplusextern "C" {#endif/** * get terms from by url link **/int getPageTerms(char *link, PAGE_TERMS *terms, char *gdbmFname);/** * merge page terms and output result in term frequency order **/int mergePageTerms(PAGE_TERMS *terms1, PAGE_TERMS *terms2);/** * get the page similarity **/double getPageSimlarity(char *link1, char *link2, char *gdbmFname);#ifdef __cplusplus}#endif#endif
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -