X-Git-Url: http://sjero.net/git/?a=blobdiff_plain;f=src%2Fwarc.c;h=fb506a7f99aee4ad9405dd0aa0207df7130dd042;hb=3ebbd84518281f348659bf8cf2d7bdc25ec4e140;hp=6935aaf1b136144626e92a2080047d5129929e93;hpb=9cc514d21ced5b18c9db1bec418c04a99d3d6c5c;p=wget

diff --git a/src/warc.c b/src/warc.c
index 6935aaf1..fb506a7f 100644
--- a/src/warc.c
+++ b/src/warc.c
@@ -75,7 +75,7 @@ static FILE *warc_current_file;
 #ifdef HAVE_LIBZ
 /* The gzip stream for the current WARC file
    (or NULL, if WARC or gzip is disabled). */
-static gzFile *warc_current_gzfile;
+static gzFile warc_current_gzfile;
 
 /* The offset of the current gzip record in the WARC file. */
 static off_t warc_current_gzfile_offset;
@@ -245,15 +245,10 @@ static bool
 warc_write_block_from_file (FILE *data_in)
 {
   /* Add the Content-Length header. */
-  char *content_length;
+  char content_length[MAX_INT_TO_STRING_LEN(off_t)];
   fseeko (data_in, 0L, SEEK_END);
-  if (! asprintf (&content_length, "%ld", ftello (data_in)))
-    {
-      warc_write_ok = false;
-      return false;
-    }
+  number_to_string (content_length, ftello (data_in));
   warc_write_header ("Content-Length", content_length);
-  free (content_length);
 
   /* End of the WARC header section. */
   warc_write_string ("\r\n");
@@ -532,7 +527,7 @@ warc_sha1_stream_with_payload (FILE *stream, void *res_block, void *res_payload,
 static char *
 warc_base32_sha1_digest (char *sha1_digest)
 {
-  // length: "sha1:" + digest + "\0"
+  /* length: "sha1:" + digest + "\0" */
   char *sha1_base32 = malloc (BASE32_LENGTH(SHA1_DIGEST_SIZE) + 1 + 5 );
   base32_encode (sha1_digest, SHA1_DIGEST_SIZE, sha1_base32 + 5,
                  BASE32_LENGTH(SHA1_DIGEST_SIZE) + 1);
@@ -913,6 +908,12 @@ warc_process_cdx_line (char *lineptr, int field_num_original_url,
           free (record_id);
         }
     }
+  else
+    {
+      xfree_null(checksum);
+      xfree_null(original_url);
+      xfree_null(record_id);
+    }
 }
 
 /* Loads the CDX file from opt.warc_cdx_dedup_filename and fills
@@ -999,12 +1000,10 @@ warc_find_duplicate_cdx_record (char *url, char *sha1_digest_payload)
   if (warc_cdx_dedup_table == NULL)
     return NULL;
 
-  char *key;
-  struct warc_cdx_record *rec_existing;
-  hash_table_get_pair (warc_cdx_dedup_table, sha1_digest_payload, &key,
-                       &rec_existing);
+  struct warc_cdx_record *rec_existing
+    = hash_table_get (warc_cdx_dedup_table, sha1_digest_payload);
 
-  if (rec_existing != NULL && strcmp (rec_existing->url, url) == 0)
+  if (rec_existing && strcmp (rec_existing->url, url) == 0)
     return rec_existing;
   else
     return NULL;
@@ -1226,10 +1225,14 @@ warc_write_cdx_record (const char *url, const char *timestamp_str,
   if (redirect_location == NULL || strlen(redirect_location) == 0)
     redirect_location = "-";
 
+  char offset_string[MAX_INT_TO_STRING_LEN(off_t)];
+  number_to_string (offset_string, offset);
+
   /* Print the CDX line. */
-  fprintf (warc_current_cdx_file, "%s %s %s %s %d %s %s - %ld %s %s\n", url,
+  fprintf (warc_current_cdx_file, "%s %s %s %s %d %s %s - %s %s %s\n", url,
            timestamp_str_cdx, url, mime_type, response_code, checksum,
-           redirect_location, offset, warc_current_filename, response_uuid);
+           redirect_location, offset_string, warc_current_filename,
+           response_uuid);
   fflush (warc_current_cdx_file);
 
   return true;