implement variants of the hashes

FUZZY_FLAG_ELIMSEQ: The comparison operation runs eliminate_sequence
    before actually comparing two hashes on both of them. This step can
    be moved to hash generation time using this flag. Suggested by Niels
    Thykier.
FUZZY_FLAG_NOTRUNC: The second part of the hash is truncated to
    SPAMSUM_LENGTH/2 by default. When comparing two hashes with
    different blocksize this can result in a larger edit distance and
    therefore false negatives.

1 files changed, 15 insertions, 2 deletions

diff --git a/fuzzy.h b/fuzzy.h
index e08d9f1..1b3da8d 100644
--- a/fuzzy.h
+++ b/fuzzy.h
@@ -30,6 +30,17 @@ extern "C" {
 #ifndef FUZZY_H
 #define FUZZY_H
 
+/**
+ * @brief fuzzy_digest flag indicating to eliminate sequences of more than
+ *        three identical characters
+ */
+#define FUZZY_FLAG_ELIMSEQ 0x1u
+/**
+ * @brief fuzzy_digest flag indicating not to truncate the second part to
+ *        SPAMSUM_LENGTH/2 characters.
+ */
+#define FUZZY_FLAG_NOTRUNC 0x2u
+
 struct fuzzy_state;
 
 /**
@@ -60,10 +71,12 @@ extern int fuzzy_update(struct fuzzy_state *state, const unsigned char *buffer,
  * concatenation of the data previously fed using fuzzy_update. 
  * @param result Where the fuzzy hash is stored. This variable
  * must be allocated to hold at least FUZZY_MAX_RESULT bytes.
+ * @param flags is a bitwise or of FUZZY_FLAG_* macros. The absence of flags is
+ * represented by a zero.
  * @return zero on success, non-zero on error
  */
 extern int fuzzy_digest(const struct fuzzy_state *state,
-		/*@out@*/ char *result);
+		/*@out@*/ char *result, unsigned int flags);
 
 /**
  * @brief Dispose a fuzzy state.
@@ -136,7 +149,7 @@ extern int fuzzy_hash_filename(const char *filename, /*@out@*/ char * result);
 
 /** The longest possible length for a fuzzy hash signature
  * (without the filename) */
-#define FUZZY_MAX_RESULT    (SPAMSUM_LENGTH + (SPAMSUM_LENGTH/2 + 20))
+#define FUZZY_MAX_RESULT (2 * SPAMSUM_LENGTH + 20)
 
 #ifdef __cplusplus
 }