[Bug-wget] [PATCH] Make wget capable of starting download from a specified position.

[Yousong Zhou]

This patch adds an option `--start-pos' for specifying starting position
of a download, both for HTTP and FTP.  When specified, the newly added
option would override `--continue'.  Apart from that, no existing code
should be affected.

Signed-off-by: Yousong Zhou <address@hidden>
---
Hi, 

I found myself needed this feature when I was trying to tunnel the download of
big file (several gigabytes) from a remote machine back to local through a
somewhat flaky connection.  It's a pain both for the server and local network
users if we have to repeat the previously already downloaded part in case that
the connection hangs or breaks.  Specifying 'Range: ' header is not an option
for wget (integrity check in the code would fail), and curl is not fast enough.
So I decided to make this patch in hope that this can also be useful to someone
else.

        yousong

 doc/ChangeLog |    4 ++++
 doc/wget.texi |   14 ++++++++++++++
 src/ChangeLog |    9 +++++++++
 src/ftp.c     |    2 ++
 src/http.c    |    2 ++
 src/init.c    |    1 +
 src/main.c    |    1 +
 src/options.h |    1 +
 8 files changed, 34 insertions(+), 0 deletions(-)

diff --git a/doc/ChangeLog b/doc/ChangeLog
index 3b05756..df103c8 100644
--- a/doc/ChangeLog
+++ b/doc/ChangeLog
@@ -1,3 +1,7 @@
+2013-12-21  Yousong Zhou  <address@hidden>
+
+       * wget.texi: Add documentation for --start-pos.
+
 2013-10-06  Tim Ruehsen  <address@hidden>
 
        * wget.texi: add/explain quoting of wildcard patterns
diff --git a/doc/wget.texi b/doc/wget.texi
index 4a1f7f1..166ea08 100644
--- a/doc/wget.texi
+++ b/doc/wget.texi
@@ -701,6 +701,20 @@ Another instance where you'll get a garbled file if you 
try to use
 Note that @samp{-c} only works with @sc{ftp} servers and with @sc{http}
 servers that support the @code{Range} header.
 
address@hidden offset
address@hidden continue retrieval
address@hidden incomplete downloads
address@hidden resume download
address@hidden start position
address@hidden address@hidden
+Start the download at position @var{OFFSET}.  Offset may be expressed in bytes,
+kilobytes with the `k' suffix, or megabytes with the `m' suffix.
+
+When specified, it would override the behavior of @samp{--continue}.  When
+using this option, you may also want to explicitly specify an output filename
+with @samp{-O FILE} in order to not overwrite an existing partially downloaded
+file.
+
 @cindex progress indicator
 @cindex dot style
 @item address@hidden
diff --git a/src/ChangeLog b/src/ChangeLog
index 42ce3e4..ab8a496 100644
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,3 +1,12 @@
+2013-12-21  Yousong Zhou  <address@hidden>
+
+       * options.h: Add option --start-pos to specify start position of
+         a download.
+       * main.c: Same purpose as above.
+       * init.c: Same purpose as above.
+       * http.c: Utilize opt.start_pos for HTTP download.
+       * ftp.c: Utilize opt.start_pos for FTP retrieval.
+
 2013-11-02  Giuseppe Scrivano  <address@hidden>
 
        * http.c (gethttp): Increase max header value length to 512.
diff --git a/src/ftp.c b/src/ftp.c
index c2522ca..c7ab6ef 100644
--- a/src/ftp.c
+++ b/src/ftp.c
@@ -1632,6 +1632,8 @@ ftp_loop_internal (struct url *u, struct fileinfo *f, 
ccon *con, char **local_fi
       /* Decide whether or not to restart.  */
       if (con->cmd & DO_LIST)
         restval = 0;
+      else if (opt.start_pos)
+        restval = opt.start_pos;
       else if (opt.always_rest
           && stat (locf, &st) == 0
           && S_ISREG (st.st_mode))
diff --git a/src/http.c b/src/http.c
index 754b7ec..a354c6b 100644
--- a/src/http.c
+++ b/src/http.c
@@ -3098,6 +3098,8 @@ Spider mode enabled. Check if remote file exists.\n"));
       /* Decide whether or not to restart.  */
       if (force_full_retrieve)
         hstat.restval = hstat.len;
+      else if (opt.start_pos)
+        hstat.restval = opt.start_pos;
       else if (opt.always_rest
           && got_name
           && stat (hstat.local_file, &st) == 0
diff --git a/src/init.c b/src/init.c
index 84ae654..7f7a34e 100644
--- a/src/init.c
+++ b/src/init.c
@@ -271,6 +271,7 @@ static const struct {
   { "showalldnsentries", &opt.show_all_dns_entries, cmd_boolean },
   { "spanhosts",        &opt.spanhost,          cmd_boolean },
   { "spider",           &opt.spider,            cmd_boolean },
+  { "startpos",         &opt.start_pos,         cmd_bytes },
   { "strictcomments",   &opt.strict_comments,   cmd_boolean },
   { "timeout",          NULL,                   cmd_spec_timeout },
   { "timestamping",     &opt.timestamping,      cmd_boolean },
diff --git a/src/main.c b/src/main.c
index 19d7253..4fbfaee 100644
--- a/src/main.c
+++ b/src/main.c
@@ -281,6 +281,7 @@ static struct cmdline_option option_data[] =
     { "server-response", 'S', OPT_BOOLEAN, "serverresponse", -1 },
     { "span-hosts", 'H', OPT_BOOLEAN, "spanhosts", -1 },
     { "spider", 0, OPT_BOOLEAN, "spider", -1 },
+    { "start-pos", 0, OPT_VALUE, "startpos", -1 },
     { "strict-comments", 0, OPT_BOOLEAN, "strictcomments", -1 },
     { "timeout", 'T', OPT_VALUE, "timeout", -1 },
     { "timestamping", 'N', OPT_BOOLEAN, "timestamping", -1 },
diff --git a/src/options.h b/src/options.h
index ad89627..9ba1760 100644
--- a/src/options.h
+++ b/src/options.h
@@ -115,6 +115,7 @@ struct options
   bool ask_passwd;              /* Ask for password? */
 
   bool always_rest;            /* Always use REST. */
+  wgint start_pos;             /* Start position of a download. */
   char *ftp_user;              /* FTP username */
   char *ftp_passwd;            /* FTP password */
   bool netrc;                  /* Whether to read .netrc. */
-- 
1.7.2.5