Return-Path: X-Original-To: notmuch@notmuchmail.org Delivered-To: notmuch@notmuchmail.org Received: from localhost (localhost [127.0.0.1]) by olra.theworths.org (Postfix) with ESMTP id 853B1431FBC for ; Fri, 27 Nov 2009 19:28:16 -0800 (PST) X-Virus-Scanned: Debian amavisd-new at olra.theworths.org Received: from olra.theworths.org ([127.0.0.1]) by localhost (olra.theworths.org [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 4gcNdyZ9tN5d for ; Fri, 27 Nov 2009 19:28:14 -0800 (PST) Received: from mail-gx0-f225.google.com (mail-gx0-f225.google.com [209.85.217.225]) by olra.theworths.org (Postfix) with ESMTP id AF100431FAE for ; Fri, 27 Nov 2009 19:28:14 -0800 (PST) Received: by gxk25 with SMTP id 25so1724554gxk.0 for ; Fri, 27 Nov 2009 19:28:14 -0800 (PST) Received: by 10.90.13.39 with SMTP id 39mr2701874agm.53.1259378892889; Fri, 27 Nov 2009 19:28:12 -0800 (PST) Received: from max1.ocjtech.us ([69.57.47.215]) by mx.google.com with ESMTPS id 5sm1088504yxd.17.2009.11.27.19.28.11 (version=TLSv1/SSLv3 cipher=RC4-MD5); Fri, 27 Nov 2009 19:28:12 -0800 (PST) Received: from localhost ([127.0.0.1] helo=localhost.localdomain) by max1.ocjtech.us with esmtps (TLSv1:AES256-SHA:256) (Exim 4.69) (envelope-from ) id 1NEDyk-0002Oe-9u; Fri, 27 Nov 2009 21:28:10 -0600 From: "Jeffrey C. Ollie" To: Not Much Mail Date: Fri, 27 Nov 2009 21:28:03 -0600 Message-Id: <1259378883-9181-1-git-send-email-jeff@ocjtech.us> X-Mailer: git-send-email 1.6.5.2 Subject: [notmuch] [PATCH] Use libgcrypt for hashing. X-BeenThere: notmuch@notmuchmail.org X-Mailman-Version: 2.1.12 Precedence: list List-Id: "Use and development of the notmuch mail system." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 28 Nov 2009 03:28:16 -0000 Instead of including a private implementation of the SHA1 hash, use libgcrypt. This means less code of our own to maintain and it will be easier to switch to a different hash function like SHA256. libgcrypt was chosen because it has a fairly simple API, it's well tested (it's used in gnutls and gnupg2), and it's licensed under the LGPL. Signed-off-by: Jeffrey C. Ollie --- Makefile | 6 +- configure | 15 +++- lib/Makefile.local | 1 - lib/libsha1.c | 242 ---------------------------------------------------- lib/libsha1.h | 67 -------------- lib/sha1.c | 44 +++++----- 6 files changed, 42 insertions(+), 333 deletions(-) delete mode 100644 lib/libsha1.c delete mode 100644 lib/libsha1.h diff --git a/Makefile b/Makefile index 2cd1b1b..a5ff3e7 100644 --- a/Makefile +++ b/Makefile @@ -10,7 +10,8 @@ gzip = gzip # Additional flags that we will append to whatever the user set. # These aren't intended for the user to manipulate. -extra_cflags := $(shell pkg-config --cflags glib-2.0 gmime-2.4 talloc) +extra_cflags := $(shell pkg-config --cflags glib-2.0 gmime-2.4 talloc) \ + $(shell libgcrypt-config --cflags) extra_cxxflags := $(shell xapian-config --cxxflags) emacs_lispdir := $(shell pkg-config emacs --variable sitepkglispdir) @@ -28,7 +29,8 @@ override CXXFLAGS += $(WARN_FLAGS) $(extra_cflags) $(extra_cxxflags) override LDFLAGS += \ $(shell pkg-config --libs glib-2.0 gmime-2.4 talloc) \ - $(shell xapian-config --libs) + $(shell xapian-config --libs) \ + $(shell libgcrypt-config --libs) # Include our local Makefile.local first so that its first target is default include Makefile.local diff --git a/configure b/configure index b4770ec..22f8066 100755 --- a/configure +++ b/configure @@ -61,6 +61,15 @@ else have_valgrind= fi +if libgcrypt-config --version > /dev/null 2>&1; then + echo "Checking for libgcrypt development files... Yes." + have_libgcrypt=1 +else + echo "Checking for libgcrypt development files... No." + have_libgcrypt=0 + errors=$((errors + 1)) +fi + if [ $errors -gt 0 ]; then cat < /* for memcpy() etc. */ - -#include "libsha1.h" - -#if defined(__cplusplus) -extern "C" -{ -#endif - -#define SHA1_BLOCK_SIZE 64 - -#define rotl32(x,n) (((x) << n) | ((x) >> (32 - n))) -#define rotr32(x,n) (((x) >> n) | ((x) << (32 - n))) - -#define bswap_32(x) ((rotr32((x), 24) & 0x00ff00ff) | (rotr32((x), 8) & 0xff00ff00)) - -#if (PLATFORM_BYTE_ORDER == IS_LITTLE_ENDIAN) -#define bsw_32(p,n) \ - { int _i = (n); while(_i--) ((uint32_t*)p)[_i] = bswap_32(((uint32_t*)p)[_i]); } -#else -#define bsw_32(p,n) -#endif - -#define SHA1_MASK (SHA1_BLOCK_SIZE - 1) - -#if 0 - -#define ch(x,y,z) (((x) & (y)) ^ (~(x) & (z))) -#define parity(x,y,z) ((x) ^ (y) ^ (z)) -#define maj(x,y,z) (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z))) - -#else /* Discovered by Rich Schroeppel and Colin Plumb */ - -#define ch(x,y,z) ((z) ^ ((x) & ((y) ^ (z)))) -#define parity(x,y,z) ((x) ^ (y) ^ (z)) -#define maj(x,y,z) (((x) & (y)) | ((z) & ((x) ^ (y)))) - -#endif - -/* Compile 64 bytes of hash data into SHA1 context. Note */ -/* that this routine assumes that the byte order in the */ -/* ctx->wbuf[] at this point is in such an order that low */ -/* address bytes in the ORIGINAL byte stream will go in */ -/* this buffer to the high end of 32-bit words on BOTH big */ -/* and little endian systems */ - -#ifdef ARRAY -#define q(v,n) v[n] -#else -#define q(v,n) v##n -#endif - -#define one_cycle(v,a,b,c,d,e,f,k,h) \ - q(v,e) += rotr32(q(v,a),27) + \ - f(q(v,b),q(v,c),q(v,d)) + k + h; \ - q(v,b) = rotr32(q(v,b), 2) - -#define five_cycle(v,f,k,i) \ - one_cycle(v, 0,1,2,3,4, f,k,hf(i )); \ - one_cycle(v, 4,0,1,2,3, f,k,hf(i+1)); \ - one_cycle(v, 3,4,0,1,2, f,k,hf(i+2)); \ - one_cycle(v, 2,3,4,0,1, f,k,hf(i+3)); \ - one_cycle(v, 1,2,3,4,0, f,k,hf(i+4)) - -static void sha1_compile(sha1_ctx ctx[1]) -{ uint32_t *w = ctx->wbuf; - -#ifdef ARRAY - uint32_t v[5]; - memcpy(v, ctx->hash, 5 * sizeof(uint32_t)); -#else - uint32_t v0, v1, v2, v3, v4; - v0 = ctx->hash[0]; v1 = ctx->hash[1]; - v2 = ctx->hash[2]; v3 = ctx->hash[3]; - v4 = ctx->hash[4]; -#endif - -#define hf(i) w[i] - - five_cycle(v, ch, 0x5a827999, 0); - five_cycle(v, ch, 0x5a827999, 5); - five_cycle(v, ch, 0x5a827999, 10); - one_cycle(v,0,1,2,3,4, ch, 0x5a827999, hf(15)); \ - -#undef hf -#define hf(i) (w[(i) & 15] = rotl32( \ - w[((i) + 13) & 15] ^ w[((i) + 8) & 15] \ - ^ w[((i) + 2) & 15] ^ w[(i) & 15], 1)) - - one_cycle(v,4,0,1,2,3, ch, 0x5a827999, hf(16)); - one_cycle(v,3,4,0,1,2, ch, 0x5a827999, hf(17)); - one_cycle(v,2,3,4,0,1, ch, 0x5a827999, hf(18)); - one_cycle(v,1,2,3,4,0, ch, 0x5a827999, hf(19)); - - five_cycle(v, parity, 0x6ed9eba1, 20); - five_cycle(v, parity, 0x6ed9eba1, 25); - five_cycle(v, parity, 0x6ed9eba1, 30); - five_cycle(v, parity, 0x6ed9eba1, 35); - - five_cycle(v, maj, 0x8f1bbcdc, 40); - five_cycle(v, maj, 0x8f1bbcdc, 45); - five_cycle(v, maj, 0x8f1bbcdc, 50); - five_cycle(v, maj, 0x8f1bbcdc, 55); - - five_cycle(v, parity, 0xca62c1d6, 60); - five_cycle(v, parity, 0xca62c1d6, 65); - five_cycle(v, parity, 0xca62c1d6, 70); - five_cycle(v, parity, 0xca62c1d6, 75); - -#ifdef ARRAY - ctx->hash[0] += v[0]; ctx->hash[1] += v[1]; - ctx->hash[2] += v[2]; ctx->hash[3] += v[3]; - ctx->hash[4] += v[4]; -#else - ctx->hash[0] += v0; ctx->hash[1] += v1; - ctx->hash[2] += v2; ctx->hash[3] += v3; - ctx->hash[4] += v4; -#endif -} - -void sha1_begin(sha1_ctx ctx[1]) -{ - ctx->count[0] = ctx->count[1] = 0; - ctx->hash[0] = 0x67452301; - ctx->hash[1] = 0xefcdab89; - ctx->hash[2] = 0x98badcfe; - ctx->hash[3] = 0x10325476; - ctx->hash[4] = 0xc3d2e1f0; -} - -/* SHA1 hash data in an array of bytes into hash buffer and */ -/* call the hash_compile function as required. */ - -void sha1_hash(const unsigned char data[], unsigned long len, sha1_ctx ctx[1]) -{ uint32_t pos = (uint32_t)(ctx->count[0] & SHA1_MASK), - space = SHA1_BLOCK_SIZE - pos; - const unsigned char *sp = data; - - if((ctx->count[0] += len) < len) - ++(ctx->count[1]); - - while(len >= space) /* tranfer whole blocks if possible */ - { - memcpy(((unsigned char*)ctx->wbuf) + pos, sp, space); - sp += space; len -= space; space = SHA1_BLOCK_SIZE; pos = 0; - bsw_32(ctx->wbuf, SHA1_BLOCK_SIZE >> 2); - sha1_compile(ctx); - } - - memcpy(((unsigned char*)ctx->wbuf) + pos, sp, len); -} - -/* SHA1 final padding and digest calculation */ - -void sha1_end(unsigned char hval[], sha1_ctx ctx[1]) -{ uint32_t i = (uint32_t)(ctx->count[0] & SHA1_MASK); - - /* put bytes in the buffer in an order in which references to */ - /* 32-bit words will put bytes with lower addresses into the */ - /* top of 32 bit words on BOTH big and little endian machines */ - bsw_32(ctx->wbuf, (i + 3) >> 2); - - /* we now need to mask valid bytes and add the padding which is */ - /* a single 1 bit and as many zero bits as necessary. Note that */ - /* we can always add the first padding byte here because the */ - /* buffer always has at least one empty slot */ - ctx->wbuf[i >> 2] &= 0xffffff80 << 8 * (~i & 3); - ctx->wbuf[i >> 2] |= 0x00000080 << 8 * (~i & 3); - - /* we need 9 or more empty positions, one for the padding byte */ - /* (above) and eight for the length count. If there is not */ - /* enough space, pad and empty the buffer */ - if(i > SHA1_BLOCK_SIZE - 9) - { - if(i < 60) ctx->wbuf[15] = 0; - sha1_compile(ctx); - i = 0; - } - else /* compute a word index for the empty buffer positions */ - i = (i >> 2) + 1; - - while(i < 14) /* and zero pad all but last two positions */ - ctx->wbuf[i++] = 0; - - /* the following 32-bit length fields are assembled in the */ - /* wrong byte order on little endian machines but this is */ - /* corrected later since they are only ever used as 32-bit */ - /* word values. */ - ctx->wbuf[14] = (ctx->count[1] << 3) | (ctx->count[0] >> 29); - ctx->wbuf[15] = ctx->count[0] << 3; - sha1_compile(ctx); - - /* extract the hash value as bytes in case the hash buffer is */ - /* misaligned for 32-bit words */ - for(i = 0; i < SHA1_DIGEST_SIZE; ++i) - hval[i] = (unsigned char)(ctx->hash[i >> 2] >> (8 * (~i & 3))); -} - -void sha1(unsigned char hval[], const unsigned char data[], unsigned long len) -{ sha1_ctx cx[1]; - - sha1_begin(cx); sha1_hash(data, len, cx); sha1_end(hval, cx); -} - -#if defined(__cplusplus) -} -#endif diff --git a/lib/libsha1.h b/lib/libsha1.h deleted file mode 100644 index b4dca93..0000000 --- a/lib/libsha1.h +++ /dev/null @@ -1,67 +0,0 @@ -/* - --------------------------------------------------------------------------- - Copyright (c) 2002, Dr Brian Gladman, Worcester, UK. All rights reserved. - - LICENSE TERMS - - The free distribution and use of this software in both source and binary - form is allowed (with or without changes) provided that: - - 1. distributions of this source code include the above copyright - notice, this list of conditions and the following disclaimer; - - 2. distributions in binary form include the above copyright - notice, this list of conditions and the following disclaimer - in the documentation and/or other associated materials; - - 3. the copyright holder's name is not used to endorse products - built using this software without specific written permission. - - ALTERNATIVELY, provided that this notice is retained in full, this product - may be distributed under the terms of the GNU General Public License (GPL), - in which case the provisions of the GPL apply INSTEAD OF those given above. - - DISCLAIMER - - This software is provided 'as is' with no explicit or implied warranties - in respect of its properties, including, but not limited to, correctness - and/or fitness for purpose. - --------------------------------------------------------------------------- - Issue Date: 01/08/2005 -*/ - -#ifndef _SHA1_H -#define _SHA1_H - -#if defined(__cplusplus) -extern "C" -{ -#endif -#if 0 -} /* Appleasing Emacs */ -#endif - -#include - -/* Size of SHA1 digest */ - -#define SHA1_DIGEST_SIZE 20 - -/* type to hold the SHA1 context */ - -typedef struct -{ uint32_t count[2]; - uint32_t hash[5]; - uint32_t wbuf[16]; -} sha1_ctx; - -void sha1_begin(sha1_ctx ctx[1]); -void sha1_hash(const unsigned char data[], unsigned long len, sha1_ctx ctx[1]); -void sha1_end(unsigned char hval[], sha1_ctx ctx[1]); -void sha1(unsigned char hval[], const unsigned char data[], unsigned long len); - -#if defined(__cplusplus) -} -#endif - -#endif diff --git a/lib/sha1.c b/lib/sha1.c index cc48108..0d22cac 100644 --- a/lib/sha1.c +++ b/lib/sha1.c @@ -20,21 +20,24 @@ #include "notmuch-private.h" -#include "libsha1.h" +#include -/* Just some simple interfaces on top of libsha1 so that we can leave - * libsha1 as untouched as possible. */ +/* Just some simple interfaces on top of libgcrypt */ static char * -_hex_of_sha1_digest (const unsigned char digest[SHA1_DIGEST_SIZE]) +_hex_of_sha1_digest (gcry_md_hd_t c) { char *result, *r; + unsigned char *digest; int i; + int digest_size; - result = xcalloc (SHA1_DIGEST_SIZE * 2 + 1, 1); + digest_size = gcry_md_get_algo_dlen(gcry_md_get_algo(c)); + digest = gcry_md_read(c, 0); + result = xcalloc (digest_size * 2 + 1, 1); for (r = result, i = 0; - i < SHA1_DIGEST_SIZE; + i < digest_size; r += 2, i++) { sprintf (r, "%02x", digest[i]); @@ -52,16 +55,16 @@ _hex_of_sha1_digest (const unsigned char digest[SHA1_DIGEST_SIZE]) char * notmuch_sha1_of_string (const char *str) { - sha1_ctx sha1; - unsigned char digest[SHA1_DIGEST_SIZE]; - - sha1_begin (&sha1); - - sha1_hash ((unsigned char *) str, strlen (str) + 1, &sha1); + char *result; + gcry_md_hd_t c; - sha1_end (digest, &sha1); + gcry_md_open (&c, GCRY_MD_SHA1, 0); + gcry_md_write (c, str, strlen (str) + 1); + gcry_md_final (c); + result = _hex_of_sha1_digest (c); + gcry_md_close (c); - return _hex_of_sha1_digest (digest); + return result; } /* Create a hexadecimal string version of the SHA-1 digest of the @@ -80,15 +83,14 @@ notmuch_sha1_of_file (const char *filename) #define BLOCK_SIZE 4096 unsigned char block[BLOCK_SIZE]; size_t bytes_read; - sha1_ctx sha1; - unsigned char digest[SHA1_DIGEST_SIZE]; + gcry_md_hd_t c; char *result; file = fopen (filename, "r"); if (file == NULL) return NULL; - sha1_begin (&sha1); + gcry_md_open(&c, GCRY_MD_SHA1, 0); while (1) { bytes_read = fread (block, 1, 4096, file); @@ -100,13 +102,15 @@ notmuch_sha1_of_file (const char *filename) return NULL; } } else { - sha1_hash (block, bytes_read, &sha1); + gcry_md_write (c, block, bytes_read); } } - sha1_end (digest, &sha1); + gcry_md_final (c); + + result = _hex_of_sha1_digest (c); - result = _hex_of_sha1_digest (digest); + gcry_md_close (c); fclose (file); -- 1.6.5.2