zebramap.c

harvest是一个下载html网页得机器人

    int major;
    int minor;
    Z_AttributeElement **attributeList;
    int num_attributes;
} AttrType;

static int attr_find (AttrType *src, oid_value *attributeSetP)
{
    while (src->major < src->num_attributes)
    {
        Z_AttributeElement *element;

        element = src->attributeList[src->major];
        if (src->type == *element->attributeType)
        {
            switch (element->which) 
            {
            case Z_AttributeValue_numeric:
                ++(src->major);
                if (element->attributeSet && attributeSetP)
                {
                    oident *attrset;

                    attrset = oid_getentbyoid (element->attributeSet);
                    *attributeSetP = attrset->value;
                }
                return *element->value.numeric;
                break;
            case Z_AttributeValue_complex:
                if (src->minor >= element->value.complex->num_list ||
                    element->value.complex->list[src->minor]->which !=  
                    Z_StringOrNumeric_numeric)
                    break;
                ++(src->minor);
                if (element->attributeSet && attributeSetP)
                {
                    oident *attrset;

                    attrset = oid_getentbyoid (element->attributeSet);
                    *attributeSetP = attrset->value;
                }
                return *element->value.complex->list[src->minor-1]->u.numeric;
            default:
                assert (0);
            }
        }
        ++(src->major);
    }
    return -1;
}

static void attr_init_APT (AttrType *src, Z_AttributesPlusTerm *zapt, int type)
{
    src->attributeList = zapt->attributes->attributes;
    src->num_attributes = zapt->attributes->num_attributes;
    src->type = type;
    src->major = 0;
    src->minor = 0;
}

static void attr_init_AttrList (AttrType *src, Z_AttributeList *list, int type)
{
    src->attributeList = list->attributes;
    src->num_attributes = list->num_attributes;
    src->type = type;
    src->major = 0;
    src->minor = 0;
}

/* ------------------------------------ */

int zebra_maps_is_complete (ZebraMaps zms, unsigned reg_id)
{ 
    struct zebra_map *zm = zebra_map_get (zms, reg_id);
    if (zm)
	return zm->completeness;
    return 0;
}

int zebra_maps_is_positioned (ZebraMaps zms, unsigned reg_id)
{
    struct zebra_map *zm = zebra_map_get (zms, reg_id);
    if (zm)
	return zm->positioned;
    return 0;
}
    
int zebra_maps_is_sort (ZebraMaps zms, unsigned reg_id)
{
    struct zebra_map *zm = zebra_map_get (zms, reg_id);
    if (zm)
	return zm->type == ZEBRA_MAP_TYPE_SORT;
    return 0;
}

int zebra_maps_sort (ZebraMaps zms, Z_SortAttributes *sortAttributes,
                     int *numerical)
{
    AttrType use;
    AttrType structure;
    int structure_value;
    attr_init_AttrList (&use, sortAttributes->list, 1);
    attr_init_AttrList (&structure, sortAttributes->list, 4);

    *numerical = 0;
    structure_value = attr_find (&structure, 0);
    if (structure_value == 109)
        *numerical = 1;
    return attr_find (&use, NULL);
}

int zebra_maps_attr (ZebraMaps zms, Z_AttributesPlusTerm *zapt,
		     unsigned *reg_id, char **search_type, char *rank_type,
		     int *complete_flag, int *sort_flag)
{
    AttrType completeness;
    AttrType structure;
    AttrType relation;
    AttrType sort_relation;
    AttrType weight;
    AttrType use;
    int completeness_value;
    int structure_value;
    int relation_value;
    int sort_relation_value;
    int weight_value;
    int use_value;

    attr_init_APT (&structure, zapt, 4);
    attr_init_APT (&completeness, zapt, 6);
    attr_init_APT (&relation, zapt, 2);
    attr_init_APT (&sort_relation, zapt, 7);
    attr_init_APT (&weight, zapt, 9);
    attr_init_APT (&use, zapt, 1);

    completeness_value = attr_find (&completeness, NULL);
    structure_value = attr_find (&structure, NULL);
    relation_value = attr_find (&relation, NULL);
    sort_relation_value = attr_find (&sort_relation, NULL);
    weight_value = attr_find (&weight, NULL);
    use_value = attr_find(&use, NULL);

    if (completeness_value == 2 || completeness_value == 3)
	*complete_flag = 1;
    else
	*complete_flag = 0;
    *reg_id = 0;

    *sort_flag = (sort_relation_value > 0) ? 1 : 0;
    *search_type = "phrase";
    strcpy (rank_type, "void");
    if (relation_value == 102)
    {
        if (weight_value == -1)
            weight_value = 34;
        sprintf (rank_type, "rank,w=%d,u=%d", weight_value, use_value);
    }
    if (relation_value == 103)
    {
        *search_type = "always";
        return 0;
    }
    if (*complete_flag)
	*reg_id = 'p';
    else
	*reg_id = 'w';
    switch (structure_value)
    {
    case 6:   /* word list */
	*search_type = "and-list";
	break;
    case 105: /* free-form-text */
	*search_type = "or-list";
	break;
    case 106: /* document-text */
        *search_type = "or-list";
	break;	
    case -1:
    case 1:   /* phrase */
    case 2:   /* word */
    case 108: /* string */ 
	*search_type = "phrase";
	break;
    case 107: /* local-number */
	*search_type = "local";
	*reg_id = 0;
	break;
    case 109: /* numeric string */
	*reg_id = 'n';
	*search_type = "numeric";
        break;
    case 104: /* urx */
	*reg_id = 'u';
	*search_type = "phrase";
	break;
    case 3:   /* key */
        *reg_id = '0';
        *search_type = "phrase";
        break;
    case 4:  /* year */
        *reg_id = 'y';
        *search_type = "phrase";
        break;
    case 5:  /* date */
        *reg_id = 'd';
        *search_type = "phrase";
        break;
    default:
	return -1;
    }
    return 0;
}

int zebra_replace_sub(ZebraMaps zms, unsigned reg_id, const char *ex_list,
		      const char *input_str, int input_len, WRBUF wrbuf);

WRBUF zebra_replace(ZebraMaps zms, unsigned reg_id, const char *ex_list,
		    const char *input_str, int input_len)
{
    struct zebra_map *zm = zebra_map_get (zms, reg_id);

    wrbuf_rewind(zms->wrbuf_1);
    wrbuf_write(zms->wrbuf_1, input_str, input_len);
    if (!zm || !zm->replace_tokens)
	return zms->wrbuf_1;
  
#if 0
    logf (LOG_LOG, "in:%.*s:", wrbuf_len(zms->wrbuf_1),
	  wrbuf_buf(zms->wrbuf_1));
#endif
    for (;;)
    {
	if (!zebra_replace_sub(zms, reg_id, ex_list, wrbuf_buf(zms->wrbuf_1),
			       wrbuf_len(zms->wrbuf_1), zms->wrbuf_2))
	    return zms->wrbuf_2;
	if (!zebra_replace_sub(zms, reg_id, ex_list, wrbuf_buf(zms->wrbuf_2),
			       wrbuf_len(zms->wrbuf_2), zms->wrbuf_1))
	    return zms->wrbuf_1;
    }
    return 0;
}

int zebra_replace_sub(ZebraMaps zms, unsigned reg_id, const char *ex_list,
		      const char *input_str, int input_len, WRBUF wrbuf)
{
    int i = -1;
    int no_replaces = 0;
    struct zebra_map *zm = zebra_map_get (zms, reg_id);

    wrbuf_rewind(wrbuf);
    for (i = -1; i <= input_len; )
    {
	struct zm_token *token;
	char replace_string[128];
	int replace_out;
	int replace_in = 0;

	for (token = zm->replace_tokens; !replace_in && token;
	     token = token->next)
	{
	    int j = 0;
	    int replace_done = 0;
	    replace_out = 0;
	    for (;; j++)
	    {
		int c;
		if (!token->token_from[j])
		{
		    replace_in = j;
		    break;
		}
		if (ex_list && strchr (ex_list, token->token_from[j]))
		    break;
		if (i+j < 0 || j+i >= input_len)
		    c = ' ';
		else
		    c = input_str[j+i] & 255;
		if (token->token_from[j] == ZEBRA_REPLACE_ANY)
		{
		    if (c == ' ')
			break;
		    replace_string[replace_out++] = c;
		}
		else
		{
		    if (c != token->token_from[j])
		    {
			break;
		    }
		    if (!replace_done)
		    {
			const char *cp = token->token_to;
			replace_done = 1;
			for (; cp && *cp; cp++)
			    replace_string[replace_out++] = *cp;
		    }
		}
	    }
	}
	if (!replace_in)
	{
	    if (i >= 0 && i < input_len)
		wrbuf_putc(wrbuf, input_str[i]);
	    i++;
	}
	else
	{
	    no_replaces++;
	    if (replace_out)
		wrbuf_write(wrbuf, replace_string, replace_out);
	    i += replace_in;
	}
    }
#if 0
    logf (LOG_LOG, "out:%.*s:", wrbuf_len(wrbuf), wrbuf_buf(wrbuf));
#endif
    return no_replaces;
}