---

arabic_stem.cpp File Reference

#include "arabic_stemmer.h"
#include "WordSet.hpp"

Defines
#define	STEM_TO_WORD   99
#define	STEM_WORD   0
#define	WAW   "0xe6"
#define	CHAR_WAW   0xe6
Functions
void	light_stem (char *, char *)
int	remove_diacritics (char *, char *)
void	remove_definite_articles (char *, char *)
char *	substring (const char *, int, int)
void	freeWordSets ()
void	substring_copy (char dest[], const char *word, int start, int end)
int	Str_equals (const char *s1, const char *s2)
int	is_whitespace (const char c)
void	load_static_files (const char *path)
void	check_stemmer_files ()
void	remove_all_suffixes (char *word, char *result, size_t lenlimit)
void	arabic_clean_up (void)
void	no_stem (char *word, char *result)
int	on_stop_list (char *word)
void	arabic_stop (char *word, char *result)
void	arabic_norm2 (char *word, char *result)
void	arabic_norm2_stop (char *word, char *result)
void	arabic_light10 (char *word, char *result)
void	arabic_light10_stop (char *word, char *result)
void	show_stemmer_options ()
void *	set_stemmer (char *stemval)
char *	stem_phrase (char *phrase, int *numtoks, void(*stemmer)(char *, char *))
Variables
char *	defarticles [] = {"Çá", "æÇá","ÈÇá", "ßÇá", "ÝÇá", "áá", "\0"}
char *	suffixes [] = {"åÇ","Çä","ÇÊ","æä","íä","íå","íÉ","å","É","í","\0"}
stem_info_t	stemtable [NUMSTEMMERS]
int	files_loaded = 0
const int	isWhitespace [256]
const int	NormChar [256]
const int	Norm3Char [256]
const int	ArabicVowel [256]
WordSet *	stop_words_ht
char *	arabic_stemdir

---

Define Documentation

#define CHAR_WAW   0xe6

#define STEM_TO_WORD   99

#define STEM_WORD   0

#define WAW   "0xe6"

---

Function Documentation

void arabic_clean_up (  void    )

void arabic_light10 (  char *    word, char *    result )

void arabic_light10_stop (  char *    word, char *    result )

void arabic_norm2 (  char *    word, char *    result )

void arabic_norm2_stop (  char *    word, char *    result )

void arabic_stop (  char *    word, char *    result )

void check_stemmer_files (    )

void freeWordSets (    )

int is_whitespace (  const char    c )

void light_stem (  char *   , char *    )

void load_static_files (  const char *    path )

void no_stem (  char *    word, char *    result )

int on_stop_list (  char *    word )

void remove_all_suffixes (  char *    word, char *    result, size_t    lenlimit )

void remove_definite_articles (  char *   , char *    )

int remove_diacritics (  char *   , char *    )

void* set_stemmer (  char *    stemval )

void show_stemmer_options (    )

char* stem_phrase (  char *    phrase, int *    numtoks, void(*    stemmer)(char *, char *) )

int Str_equals (  const char *    s1, const char *    s2 )

char * substring (  const char *   , int   , int    )

void substring_copy (  char    dest[], const char *    word, int    start, int    end )

---

Variable Documentation

char* arabic_stemdir

const int ArabicVowel[256]

Initial value: { 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0xc1,0xc2,0xc3,0xc4,0xc5,0xc6,0xc7, 0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0xe6,0,0,0,0,0,0xec,0xed,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0}

char* defarticles[] = {"Çá", "æÇá","ÈÇá", "ßÇá", "ÝÇá", "áá", "\0"}

int files_loaded = 0

const int isWhitespace[256]

Initial value: { 0,0,0,0,0,0,0,0,0,1,1,1,1,1,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,1,1,1,1, 1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0}

const int Norm3Char[256]

Initial value: { 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0x81,0,0,0,0,0,0,0,0,0x8a,0,0,0x8d,0x8e,0x8f, 0x90,0,0,0,0,0,0,0,0x98,0,0x9a,0,0,0,0,0x9f, 0,0,0,0,0,0,0,0,0,0,0xaa,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0xc0,0xc7,0xc7,0xc7,0xc7,0xc7,0xc7,0xc7,0xc8,0xe5,0xca,0xcb,0xcc,0xcd,0xce,0xcf, 0xd0,0xd1,0xd2,0xd3,0xd4,0xd5,0xd6, 0,0xd8,0xd9,0xda,0xdb, 0,0xdd,0xde,0xdf, 0,0xe1, 0,0xe3,0xe4,0xe5,0xe6, 0, 0, 0, 0, 0,0xed, 0xed, 0, 0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0}

const int NormChar[256]

Initial value: { 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0x81,0,0,0,0,0,0,0,0,0x8a,0,0,0x8d,0x8e,0x8f, 0x90,0,0,0,0,0,0,0,0x98,0,0x9a,0,0,0,0,0x9f, 0,0,0,0,0,0,0,0,0,0,0xaa,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0xc0,0xc1,0xc7,0xc7,0xc4,0xc7,0xc6,0xc7,0xc8,0xe5,0xca,0xcb,0xcc,0xcd,0xce,0xcf, 0xd0,0xd1,0xd2,0xd3,0xd4,0xd5,0xd6, 0,0xd8,0xd9,0xda,0xdb, 0,0xdd,0xde,0xdf, 0,0xe1, 0,0xe3,0xe4,0xe5,0xe6, 0, 0, 0, 0, 0,0xed, 0xed, 0, 0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0}

stem_info_t stemtable[NUMSTEMMERS]

Initial value: { {"none", "none", no_stem}, {"arabic_stop", "arabic_stop", arabic_stop}, {"arabic_norm2", "table normalization", arabic_norm2}, {"arabic_norm2_stop", "table normalization with stopping", arabic_norm2_stop}, {"arabic_light10", "light stemming", arabic_light10}, {"arabic_light10_stop", "light10 and remove stop words", arabic_light10_stop} }

WordSet* stop_words_ht

char* suffixes[] = {"åÇ","Çä","ÇÊ","æä","íä","íå","íÉ","å","É","í","\0"}

---