Fossil

/*
** Parse a blob into a Manifest object.  The Manifest object
** takes over the input blob and will free it when the
** Manifest object is freed.  Zeros are inserted into the blob
** as string terminators so that blob should not be used again.
**
** Return a pointer to an allocated Manifest object if the content
** really is a structural artifact of some kind.  The returned Manifest 
** object needs to be freed by a subsequent call to manifest_destroy().
** Return NULL if there are syntax errors or if the input blob does
** not describe a valid structural artifact.
**
** This routine is strict about the format of a structural artifacts.
** The format must match exactly or else it is rejected.  This
** rule minimizes the risk that a content artifact will be mistaken

#define SHA1Context SHA1_CTX
#define SHA1Init SHA1DCInit
#define SHA1Update SHA1DCUpdate
#define SHA1Final SHA1DCFinal

/*
** SHA1 Implemenatation #2: use the SHA1 algorithm built into SSL
*/
#elif  defined(FOSSIL_ENABLE_SSL)

# include <openssl/sha.h>
# define SHA1Context SHA_CTX
# define SHA1Init SHA1_Init
# define SHA1Update SHA1_Update
# define SHA1Final SHA1_Final

/*
** SHA1 Implemenatation #3:  If none of the previous two SHA1 
** algorithms work, there is this built-in.  This built-in was the
** original implementation used by Fossil.
*/
#else
/*
** The SHA1 implementation below is adapted from:
**

/*
** The code in this file is the concatination of several files
** copied out of 
**
**     https://github.com/cr-marcstevens/sha1collisiondetection
**
** The copy was made on 2017-03-01.  Some minor formatting changes
** were made but otherwise the code is unchanged.  All
** original copyright claims are preserved.
**

* Distributed under the MIT Software License.
* See accompanying file LICENSE.txt or copy at
* https://opensource.org/licenses/MIT
***/
/*************** File:  LICENSE.txt ***************/
/*
** MIT License
** 
** Copyright (c) 2017:
**     Marc Stevens
**     Cryptology Group
**     Centrum Wiskunde & Informatica
**     P.O. Box 94079, 1090 GB Amsterdam, Netherlands
**     marc@marc-stevens.nl
** 
**     Dan Shumow
**     Microsoft Research
**     danshu@microsoft.com
**
** Permission is hereby granted, free of charge, to any person obtaining a copy
** of this software and associated documentation files (the "Software"), to deal
** in the Software without restriction, including without limitation the rights
** to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
** copies of the Software, and to permit persons to whom the Software is
** furnished to do so, subject to the following conditions:
** 
** The above copyright notice and this permission notice shall be included in all
** copies or substantial portions of the Software.
** 
** THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
** IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
** FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
** AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
** LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
** OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
** SOFTWARE.

#   define SHA3_BYTEORDER 0
# endif
#endif


/*
** State structure for a SHA3 hash in progress
*/ 
typedef struct SHA3Context SHA3Context;
struct SHA3Context {
  union {
    u64 s[25];                /* Keccak state. 5x5 lines of 64 bits each */
    unsigned char x[1600];    /* ... or 1600 bytes */
  } u;
  unsigned nRate;        /* Bytes of input accepted per Keccak iteration */

  @ <a name="addshun"></a>
  @ <p>To shun artifacts, enter their artifact hashes (the 40- or
  @ 64-character lowercase hexadecimal hash of the artifact content) in the
  @ following box and press the "Shun" button.  This will cause the artifacts
  @ to be removed from the repository and will prevent the artifacts from being
  @ readded to the repository by subsequent sync operation.</p>
  @
  @ <p>Note that you must enter the full 40- or 64-character artifact hashes, 
  @ not an abbreviation or a symbolic tag.</p>
  @
  @ <p>Warning:  Shunning should only be used to remove inappropriate content
  @ from the repository.  Inappropriate content includes such things as
  @ spam added to Wiki, files that violate copyright or patent agreements,
  @ or artifacts that by design or accident interfere with the processing
  @ of the repository.  Do not shun artifacts merely to remove them from

*/
#include "config.h"
#include "vfile.h"
#include <assert.h>
#include <sys/types.h>

/*
** The input is guaranteed to be a 40- or 64-character well-formed 
** artifact hash.  Find its rid.
*/
int fast_uuid_to_rid(const char *zUuid){
  static Stmt q;
  int rid;
  db_static_prepare(&q, "SELECT rid FROM blob WHERE uuid=:uuid");
  db_bind_text(&q, ":uuid", zUuid);

  }else{
    size = 0;
  }
  return size;
}

/*
** Push an error message to alert the older client that the repository 
** has SHA3 content and cannot be synced or cloned.
*/
static void xfer_cannot_send_sha3_error(Xfer *pXfer){
  blob_appendf(pXfer->pOut, 
    "error Fossil\\sversion\\s2.0\\sor\\slater\\srequired.\n"
  );
}


/*
** Send the file identified by rid.

Each artifact in the repository is named by a hash of its content.
No prefixes, suffixes, or other information is added to an artifact before
the hash is computed.  The artifact name is just the (lower-case
hexadecimal) hash of the raw artifact.

Fossil currently computes artifact names using either SHA1 or SHA3-256.  It
is relatively easy to add new algorithms in the future, but there are no
plans to do so at this time.  

When referring to artifacts in using tty commands or webpage URLs, it is 
sufficient to specify a unique prefix for the artifact name.  If the input
prefix is not unique, Fossil will show an error.  Within a structural
artifact, however, all references to other artifacts must be the complete
hash.

Prior to Fossil version 2.0, all names were formed from the SHA1 hash of
the artifact.  The key innovation in Fossil 2.0 was adding support for

Synchronization is the process of sharing artifacts between
servers so that all servers have copies of all artifacts.  Because
artifacts are unordered, the order in which artifacts are received
at a server is inconsequential.  It is assumed that the hash names
of artifacts are unique - that every artifact has a different hash.
To a first approximation, synchronization proceeds by sharing lists
hash values for available artifacts, then sharing the content of artifacts
whose names are missing from one side or the other of the connection.  
In practice, a repository might contain millions of artifacts.  The list of
hash names for this many artifacts can be large.  So optimizations are
employed that usually reduce the number of hashes that need to be
shared to a few hundred.</p>

<p>Each repository also has local state.  The local state determines
the web-page formatting preferences, authorized users, ticket formats,

<blockquote>
<b>uvigot</b> <i>name mtime hash size</i>
</blockquote>

<p>The <i>name</i> argument is the name of an unversioned file.
The <i>mtime</i> is the last modification time of the unversioned file
in seconds since 1970.
The <i>hash</i> is the SHA1 or SHA3-256 hash of the unversioned file 
content, or "<b>-</b>" if the file has been deleted.
The <i>size</i> is the uncompressed size of the file in bytes.

<p>When the server sees a "pragma uv-hash" card for which the hash
does not match, it sends uvigot cards for every unversioned file that it
holds.  The client will use this information to figure out which
unversioned files need to be synchronized.