X-Git-Url: https://git.cworth.org/git?a=blobdiff_plain;f=deflate.c;fp=deflate.c;h=bc4c8d4f571982948f9fb37d64e9b7bf15dd67c6;hb=db00b4e39677b0dbf3ea6f7694e0eac7be4ef141;hp=25800e916223fa76ff36b8481170f362c7e5615e;hpb=bef5279812845d49f988580e076c0ca597078dfd;p=gzip

diff --git a/deflate.c b/deflate.c
index 25800e9..bc4c8d4 100644
--- a/deflate.c
+++ b/deflate.c
@@ -122,6 +122,14 @@ static char rcsid[] = "$Id: deflate.c,v 0.15 1993/06/24 10:53:53 jloup Exp $";
 #endif
 /* Matches of length 3 are discarded if their distance exceeds TOO_FAR */
 
+#ifndef RSYNC_WIN
+#  define RSYNC_WIN 4096
+#endif
+/* Size of rsync window, must be < MAX_DIST */
+
+#define RSYNC_SUM_MATCH(sum) ((sum) % RSYNC_WIN == 0)
+/* Whether window sum matches magic value */
+
 /* ===========================================================================
  * Local data used by the "longest match" routines.
  */
@@ -203,6 +211,8 @@ local int compr_level;
 unsigned near good_match;
 /* Use a faster search when the previous match is longer than this */
 
+local ulg rsync_sum;  /* rolling sum of rsync window */
+local ulg rsync_chunk_end; /* next rsync sequence point */
 
 /* Values for max_lazy_match, good_match and max_chain_length, depending on
  * the desired pack level (0..9). The values given below have been tuned to
@@ -301,6 +311,10 @@ void lm_init (pack_level, flags)
 #endif
     /* prev will be initialized on the fly */
 
+    /* rsync params */
+    rsync_chunk_end = 0xFFFFFFFFUL;
+    rsync_sum = 0;
+
     /* Set the default configuration parameters:
      */
     max_lazy_match   = configuration_table[pack_level].max_lazy;
@@ -537,6 +551,8 @@ local void fill_window()
         memcpy((char*)window, (char*)window+WSIZE, (unsigned)WSIZE);
         match_start -= WSIZE;
         strstart    -= WSIZE; /* we now have strstart >= MAX_DIST: */
+	if (rsync_chunk_end != 0xFFFFFFFFUL)
+	    rsync_chunk_end -= WSIZE;
 
         block_start -= (long) WSIZE;
 
@@ -564,13 +580,46 @@ local void fill_window()
     }
 }
 
+local void rsync_roll(start, num)
+    unsigned start;
+    unsigned num;
+{
+    unsigned i;
+
+    if (start < RSYNC_WIN) {
+	/* before window fills. */
+	for (i = start; i < RSYNC_WIN; i++) {
+	    if (i == start + num) return;
+	    rsync_sum += (ulg)window[i];
+	}
+	num -= (RSYNC_WIN - start);
+	start = RSYNC_WIN;
+    }
+
+    /* buffer after window full */
+    for (i = start; i < start+num; i++) {
+	/* New character in */
+	rsync_sum += (ulg)window[i];
+	/* Old character out */
+	rsync_sum -= (ulg)window[i - RSYNC_WIN];
+	if (rsync_chunk_end == 0xFFFFFFFFUL && RSYNC_SUM_MATCH(rsync_sum))
+	    rsync_chunk_end = i;
+    }
+}
+
+/* ===========================================================================
+ * Set rsync_chunk_end if window sum matches magic value.
+ */
+#define RSYNC_ROLL(s, n) \
+   do { if (rsync) rsync_roll((s), (n)); } while(0)
+
 /* ===========================================================================
  * Flush the current block, with given end-of-file flag.
  * IN assertion: strstart is set to the end of the current match.
  */
 #define FLUSH_BLOCK(eof) \
    flush_block(block_start >= 0L ? (char*)&window[(unsigned)block_start] : \
-                (char*)NULL, (long)strstart - block_start, (eof))
+                (char*)NULL, (long)strstart - block_start, flush-1, (eof))
 
 /* ===========================================================================
  * Processes a new input file and return its compressed length. This
@@ -581,7 +630,7 @@ local void fill_window()
 local off_t deflate_fast()
 {
     IPos hash_head; /* head of the hash chain */
-    int flush;      /* set if current block must be flushed */
+    int flush;      /* set if current block must be flushed, 2=>and padded  */
     unsigned match_length = 0;  /* length of best match */
 
     prev_length = MIN_MATCH-1;
@@ -594,7 +643,8 @@ local off_t deflate_fast()
         /* Find the longest match, discarding those <= prev_length.
          * At this point we have always match_length < MIN_MATCH
          */
-        if (hash_head != NIL && strstart - hash_head <= MAX_DIST) {
+        if (hash_head != NIL && strstart - hash_head <= MAX_DIST &&
+	    strstart <= window_size - MIN_LOOKAHEAD) {
             /* To simplify the code, we prevent matches with the string
              * of window index 0 (in particular we have to avoid a match
              * of the string with itself at the start of the input file).
@@ -610,6 +660,7 @@ local off_t deflate_fast()
 
             lookahead -= match_length;
 
+	    RSYNC_ROLL(strstart, match_length);
 	    /* Insert new strings in the hash table only if the match length
              * is not too large. This saves time but degrades compression.
              */
@@ -638,9 +689,14 @@ local off_t deflate_fast()
             /* No match, output a literal byte */
             Tracevv((stderr,"%c",window[strstart]));
             flush = ct_tally (0, window[strstart]);
+	    RSYNC_ROLL(strstart, 1);
             lookahead--;
 	    strstart++; 
         }
+	if (rsync && strstart > rsync_chunk_end) {
+	    rsync_chunk_end = 0xFFFFFFFFUL;
+	    flush = 2;
+	} 
         if (flush) FLUSH_BLOCK(0), block_start = strstart;
 
         /* Make sure that we always have enough lookahead, except
@@ -682,7 +738,8 @@ off_t deflate()
         match_length = MIN_MATCH-1;
 
         if (hash_head != NIL && prev_length < max_lazy_match &&
-            strstart - hash_head <= MAX_DIST) {
+            strstart - hash_head <= MAX_DIST &&
+	    strstart <= window_size - MIN_LOOKAHEAD) {
             /* To simplify the code, we prevent matches with the string
              * of window index 0 (in particular we have to avoid a match
              * of the string with itself at the start of the input file).
@@ -713,6 +770,7 @@ off_t deflate()
              */
             lookahead -= prev_length-1;
             prev_length -= 2;
+	    RSYNC_ROLL(strstart, prev_length+1);
             do {
                 strstart++;
                 INSERT_STRING(strstart, hash_head);
@@ -725,24 +783,39 @@ off_t deflate()
             match_available = 0;
             match_length = MIN_MATCH-1;
             strstart++;
-            if (flush) FLUSH_BLOCK(0), block_start = strstart;
 
+	    if (rsync && strstart > rsync_chunk_end) {
+		rsync_chunk_end = 0xFFFFFFFFUL;
+		flush = 2;
+	    }
+            if (flush) FLUSH_BLOCK(0), block_start = strstart;
         } else if (match_available) {
             /* If there was no match at the previous position, output a
              * single literal. If there was a match but the current match
              * is longer, truncate the previous match to a single literal.
              */
             Tracevv((stderr,"%c",window[strstart-1]));
-            if (ct_tally (0, window[strstart-1])) {
-                FLUSH_BLOCK(0), block_start = strstart;
-            }
+	    flush = ct_tally (0, window[strstart-1]);
+	    if (rsync && strstart > rsync_chunk_end) {
+		rsync_chunk_end = 0xFFFFFFFFUL;
+		flush = 2;
+	    }
+            if (flush) FLUSH_BLOCK(0), block_start = strstart;
+	    RSYNC_ROLL(strstart, 1);
             strstart++;
             lookahead--;
         } else {
             /* There is no previous match to compare with, wait for
              * the next step to decide.
              */
+	    if (rsync && strstart > rsync_chunk_end) {
+		/* Reset huffman tree */
+		rsync_chunk_end = 0xFFFFFFFFUL;
+		flush = 2;
+		FLUSH_BLOCK(0), block_start = strstart;
+	    }
             match_available = 1;
+	    RSYNC_ROLL(strstart, 1);
             strstart++;
             lookahead--;
         }