[debian/gzip] / debian / patches / rsyncable.diff

diff --git a/deflate.c b/deflate.c
index 0950391..1b3ac52 100644
--- a/deflate.c
+++ b/deflate.c
@@ -131,6 +131,14 @@
 #endif
 /* Matches of length 3 are discarded if their distance exceeds TOO_FAR */
 
+#ifndef RSYNC_WIN
+#  define RSYNC_WIN 8192
+#endif
+/* Size of rsync window, must be < MAX_DIST */
+
+#define RSYNC_SUM_MATCH(sum) (((sum) & (RSYNC_WIN - 1)) == 0)
+/* Whether window sum matches magic value */
+
 /* ===========================================================================
  * Local data used by the "longest match" routines.
  */
@@ -212,6 +220,8 @@ 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
@@ -307,6 +317,10 @@ 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;
@@ -324,6 +338,7 @@ void lm_init (pack_level, flags)
 
     strstart = 0;
     block_start = 0L;
+    rsync_chunk_end = 0xFFFFFFFFUL;
 #ifdef ASMV
     match_init(); /* initialize the asm code */
 #endif
@@ -543,6 +558,8 @@ 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;
 
@@ -570,6 +587,39 @@ 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.
@@ -617,6 +667,7 @@ 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.
              */
@@ -645,9 +696,18 @@ 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) {
+            ush  attr = 0;          /* ascii/binary flag */
+
+            flush = 1;
+            /* Reset huffman tree */
+            ct_init(&attr, &method);
+            rsync_chunk_end = 0xFFFFFFFFUL;
+        }
         if (flush) FLUSH_BLOCK(0), block_start = strstart;
 
         /* Make sure that we always have enough lookahead, except
@@ -721,6 +781,7 @@ off_t deflate()
              */
             lookahead -= prev_length-1;
             prev_length -= 2;
+           RSYNC_ROLL(strstart, prev_length+1);
             do {
                 strstart++;
                 INSERT_STRING(strstart, hash_head);
@@ -733,24 +794,51 @@ 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) {
+               ush  attr = 0;          /* ascii/binary flag */
+
+               /* Reset huffman tree */
+               ct_init(&attr, &method);
+               rsync_chunk_end = 0xFFFFFFFFUL;
+               flush = 1;
+           }
+            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) {
+               ush  attr = 0;          /* ascii/binary flag */
+
+               /* Reset huffman tree */
+               ct_init(&attr, &method);
+               rsync_chunk_end = 0xFFFFFFFFUL;
+
+               flush = 1;
+           }
+            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) {
+               ush  attr = 0;          /* ascii/binary flag */
+
+               /* Reset huffman tree */
+               ct_init(&attr, &method);
+               rsync_chunk_end = 0xFFFFFFFFUL;
+
+               FLUSH_BLOCK(0), block_start = strstart;
+           }
             match_available = 1;
+           RSYNC_ROLL(strstart, 1);
             strstart++;
             lookahead--;
         }
diff --git a/doc/gzip.texi b/doc/gzip.texi
index a6009d2..84887c3 100644
--- a/doc/gzip.texi
+++ b/doc/gzip.texi
@@ -353,6 +353,14 @@ specified on the command line are directories, @command{gzip} will descend
 into the directory and compress all the files it finds there (or
 decompress them in the case of @command{gunzip}).
 
+@item --rsyncable
+While compressing, synchronize the output occasionally based on the
+input.  This can reduce the compression slightly in some cases, but
+means that the @code{rsync} program can take advantage of similarities
+in the uncompressed input when syncronizing two files compressed with
+this flag.  @code{gunzip} cannot tell the difference between a
+compressed file created with this option, and one created without it.
+
 @item --suffix @var{suf}
 @itemx -S @var{suf}
 Use suffix @var{suf} instead of @samp{.gz}.  Any suffix can be
diff --git a/gzip.c b/gzip.c
index 9e2a890..b867350 100644
--- a/gzip.c
+++ b/gzip.c
@@ -218,6 +218,7 @@ int  ofd;                  /* output file descriptor */
 unsigned insize;           /* valid bytes in inbuf */
 unsigned inptr;            /* index of next byte to be processed in inbuf */
 unsigned outcnt;           /* bytes in output buffer */
+int rsync = 0;             /* make ryncable chunks */
 
 static int handled_sig[] =
   {
@@ -271,6 +272,7 @@ struct option longopts[] =
     {"best",       0, 0, '9'}, /* compress better */
     {"lzw",        0, 0, 'Z'}, /* make output compatible with old compress */
     {"bits",       1, 0, 'b'}, /* max number of bits per code (implies -Z) */
+    {"rsyncable",  0, 0, 'R'}, /* make rsync-friendly archive */
     { 0, 0, 0, 0 }
 };
 
@@ -352,6 +354,7 @@ local void help()
  "  -Z, --lzw         produce output compatible with old compress",
  "  -b, --bits=BITS   max number of bits per code (implies -Z)",
 #endif
+ "  --rsyncable       Make rsync-friendly archive",
  "",
  "With no FILE, or when FILE is -, read standard input.",
  "",
@@ -479,6 +482,9 @@ int main (int argc, char **argv)
            recursive = 1;
 #endif
            break;
+        case 'R':
+           rsync = 1; break;
+
        case 'S':
 #ifdef NO_MULTIPLE_DOTS
             if (*optarg == '.') optarg++;
diff --git a/gzip.h b/gzip.h
index 0c3dd68..5270c56 100644
--- a/gzip.h
+++ b/gzip.h
@@ -146,6 +146,7 @@ EXTERN(uch, window);         /* Sliding window and suffix table (unlzw) */
 extern unsigned insize; /* valid bytes in inbuf */
 extern unsigned inptr;  /* index of next byte to be processed in inbuf */
 extern unsigned outcnt; /* bytes in output buffer */
+extern int rsync;  /* deflate into rsyncable chunks */
 
 extern off_t bytes_in;   /* number of input bytes */
 extern off_t bytes_out;  /* number of output bytes */
diff --git a/doc/gzip.texi b/doc/gzip.texi
index 84887c3..ecd4e00 100644
--- a/doc/gzip.texi
+++ b/doc/gzip.texi
@@ -207,6 +207,7 @@ Mandatory arguments to long options are mandatory for short options too.
   -V, --version     display version number
   -1, --fast        compress faster
   -9, --best        compress better
+    --rsyncable   Make rsync-friendly archive
 
 With no FILE, or when FILE is -, read standard input.
 
@@ -361,6 +362,14 @@ in the uncompressed input when syncronizing two files compressed with
 this flag.  @code{gunzip} cannot tell the difference between a
 compressed file created with this option, and one created without it.
 
+@item --rsyncable
+While compressing, synchronize the output occasionally based on
+the input.  This increases size by less than 1 percent most
+cases, but means that the @command{rsync} program can much more efficiently
+synchronize files compressed with this flag.  @command{gunzip}
+cannot tell the difference between a compressed file created
+with this option, and one created without it.
+
 @item --suffix @var{suf}
 @itemx -S @var{suf}
 Use suffix @var{suf} instead of @samp{.gz}.  Any suffix can be