We can dump chunks now.

diff --git a/main.c b/main.c
index 6f745c99d50a6d9b40e2a63f46cc672fbf1ad021..ab5271f272da87d3e46d6e7164871f39e087c5f8 100644 (file)
--- a/main.c
+++ b/main.c
@@ -55,7 +55,7 @@ static void filehook(struct hash_t hash, const char *file)
                                      sizeof(struct hash_t) * (chunk_count+1));
     
     hash.start = TONET(hash.start);
-    hash.end = TONET(hash.end);
+    hash.end   = TONET(hash.end);
     chunk_buffer[chunk_count++] = hash;
 }
 
@@ -104,6 +104,32 @@ static void generate_shredfile(const char *tree, FILE *ofp)
        net_chunks = TONET(chunk_count);
        fwrite((char *)&net_chunks, sizeof(linenum_t), 1, ofp);
        fwrite(chunk_buffer, sizeof(struct hash_t), chunk_count, ofp);
+       if (debug)
+       {
+           struct hash_t       *np;
+           fprintf(stderr, "Chunks for %s:\n", *place);
+           for (np = chunk_buffer; np < chunk_buffer + chunk_count; np++)
+               fprintf(stderr,
+                       "%d: %02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x %s:%d:%d\n", 
+                      np-chunk_buffer, 
+                      np->hash[0], 
+                      np->hash[1], 
+                      np->hash[2], 
+                      np->hash[3], 
+                      np->hash[4], 
+                      np->hash[5], 
+                      np->hash[6], 
+                      np->hash[7], 
+                      np->hash[8], 
+                      np->hash[9], 
+                      np->hash[10], 
+                      np->hash[11], 
+                      np->hash[12], 
+                      np->hash[13], 
+                      np->hash[14], 
+                      np->hash[15],
+                      *place, FROMNET(np->start), FROMNET(np->end));
+       }
        free(chunk_buffer);
     }
 }
@@ -175,6 +201,45 @@ static void init_scf(char *file)
     scf_head = new;
 }
 
+static void dump_array(struct sorthash_t *obarray, 
+               int hashcount, 
+               linenum_t (*fn)(linenum_t))
+/* dump the contents of a sort_hash array */
+{
+    struct sorthash_t  *np;
+
+    for (np = obarray; np < obarray + hashcount; np++)
+    {
+       struct hash_t scratch;
+
+       scratch = np->hash;
+       if (fn)
+       {
+           scratch.start = fn(np->hash.start);
+           scratch.end   = fn(np->hash.end);
+       }
+       printf("%d: %02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x %s:%d:%d\n", 
+              np-obarray, 
+              scratch.hash[0], 
+              scratch.hash[1], 
+              scratch.hash[2], 
+              scratch.hash[3], 
+              scratch.hash[4], 
+              scratch.hash[5], 
+              scratch.hash[6], 
+              scratch.hash[7], 
+              scratch.hash[8], 
+              scratch.hash[9], 
+              scratch.hash[10], 
+              scratch.hash[11], 
+              scratch.hash[12], 
+              scratch.hash[13], 
+              scratch.hash[14], 
+              scratch.hash[15],
+              np->file, scratch.start, scratch.end);
+    }
+}
+
 void report_time(char *legend, ...)
 /* report on time since last report_mark */
 {
@@ -315,7 +380,6 @@ main(int argc, char *argv[])
        /* consistency checks on the SCFs */
        for (scf = scf_head; scf->next->next; scf = scf->next)
        {
-           printf("Foo\n");
            if (strcmp(scf->normalization, scf->next->normalization))
            {
                fprintf(stderr, 
@@ -351,6 +415,12 @@ main(int argc, char *argv[])
 
     if (!compile_only)
     {
+       if (debug)
+       {
+           printf("Consolidated hash list:\n");
+           dump_array(sort_buffer, sort_count, NULL);
+       }
+
        /* now we're ready to emit the report */
        puts("#SCF-B 1.0");
        printf("Hash-Method: %s\n", scf_head->hash_method);
@@ -363,6 +433,14 @@ main(int argc, char *argv[])
        sort_hashes(sort_buffer, sort_count);
        report_time("Sort done");
 
+#ifdef DEBUG
+       if (debug)
+       {
+           puts("Chunk list before reduction.");
+           dump_array(obarray, hashcount, NULL);
+       }
+#endif /* DEBUG */
+
        emit_report(sort_buffer, sort_count);
     }
 

diff --git a/report.c b/report.c
index d86476cd90f25c304429e488f92d27acafaf5016..69aad4e0df9de6497002931d4f4fcf1dc99251dd 100644 (file)
--- a/report.c
+++ b/report.c
@@ -42,15 +42,15 @@ static struct match_t *reduced = &dummy_match;
 void merge_scf(const char *name, FILE *fp)
 /* merge hashes from specified files into an in-code list */
 {
-    u_int32_t  sectcount;
+    u_int32_t  filecount;
     int hashcount = 0;
     struct stat sb;
 
     stat(name, &sb);
     fprintf(stderr, "%% Reading hash list %s...   ", name);
-    fread(&sectcount, sizeof(u_int32_t), 1, fp);
-    sectcount = ntohl(sectcount);
-    while (sectcount--)
+    fread(&filecount, sizeof(u_int32_t), 1, fp);
+    filecount = ntohl(filecount);
+    while (filecount--)
     {
        char    buf[BUFSIZ];
        linenum_t       chunks;
@@ -59,7 +59,7 @@ void merge_scf(const char *name, FILE *fp)
        fgets(buf, sizeof(buf), fp);
        *strchr(buf, '\n') = '\0';
        new = (struct item *)malloc(sizeof(struct item));
-       new->file = strdup(name);
+       new->file = strdup(buf);
        new->next = head;
        head = new;
        fread(&chunks, sizeof(linenum_t), 1, fp);
@@ -312,33 +312,6 @@ void emit_report(struct sorthash_t *obarray, int hashcount)
     struct match_t *hitlist, *sorted, *match;
     int i, matchcount;
 
-    if (debug)
-    {
-       struct sorthash_t       *np;
-
-       puts("Chunk list before reduction.");
-       for (np = obarray; np < obarray + hashcount; np++)
-           printf("%d: %02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x %s:%d:%d\n", 
-                  np-obarray, 
-                  np->hash.hash[0], 
-                  np->hash.hash[1], 
-                  np->hash.hash[2], 
-                  np->hash.hash[3], 
-                  np->hash.hash[4], 
-                  np->hash.hash[5], 
-                  np->hash.hash[6], 
-                  np->hash.hash[7], 
-                  np->hash.hash[8], 
-                  np->hash.hash[9], 
-                  np->hash.hash[10], 
-                  np->hash.hash[11], 
-                  np->hash.hash[12], 
-                  np->hash.hash[13], 
-                  np->hash.hash[14], 
-                  np->hash.hash[15],
-                  np->file, np->hash.start, np->hash.end);
-    }
-
     hitlist = reduce_matches(obarray, hashcount);
     report_time("Reduction done");