1. db/catalog.gz ---> db/catalog

+ it is not sent to oook and feedback-cat via pipes, but it is read by them as a file
+ it is read in 2 passes and the URL's are identified in the 1st phase (catalog.c)

2. URL fingerprinting always uses cf/url-equiv, even in the indexer

diff --git a/lib/index.h b/lib/index.h
index bb925742f9ab77c40d888d31e7e26192cf5185c1..a56d1e694ae6c8d7f8fcdf230898d588818eb64a 100644 (file)
--- a/lib/index.h
+++ b/lib/index.h
@@ -135,7 +135,7 @@ fp_hash(struct fingerprint *fp)
 #define URL_KEY_BUF_SIZE (3*MAX_URL_SIZE)
 byte *url_key(byte *url, byte *buf);
 void url_fingerprint(byte *url, struct fingerprint *fp);
 #define URL_KEY_BUF_SIZE (3*MAX_URL_SIZE)
 byte *url_key(byte *url, byte *buf);
 void url_fingerprint(byte *url, struct fingerprint *fp);

-void url_key_init(uns load_prefixes);
+void url_key_init(void);

 
 /* Conversion of document age from seconds to our internal units */
 
 
 /* Conversion of document age from seconds to our internal units */
 

diff --git a/lib/urlkey.c b/lib/urlkey.c
index e6cc55d66fb1f55de7c9ef5c4cbdea56571bbc04..f0848015c1e1c8477849f5d9a74965c086c2a6b2 100644 (file)
--- a/lib/urlkey.c
+++ b/lib/urlkey.c
@@ -229,10 +229,10 @@ static void CONSTRUCTOR urlkey_conf_init(void)
 }
 
 void
 }
 
 void

-url_key_init(uns load_prefixes)
+url_key_init(void)

 {
   pxtab_init();
 {
   pxtab_init();

-  if (load_prefixes && urlkey_pxtab_path)
+  if (urlkey_pxtab_path)

     pxtab_load(urlkey_pxtab_path);
 }
 
     pxtab_load(urlkey_pxtab_path);
 }