From a5d14fe7c5285cfac5c9a9aa90b7e61664b7be3c Mon Sep 17 00:00:00 2001
From: drh <drh@noemail.net>
Date: Tue, 4 May 2004 15:00:46 +0000
Subject: [PATCH] Added template for the utf.c file containing conversion
 routines. (CVS 1313)

FossilOrigin-Name: 89b42c468f437003f74a1785370e75b2585fa9e2
---
 manifest      | 11 ++++----
 manifest.uuid |  2 +-
 src/utf.c     | 77 +++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 84 insertions(+), 6 deletions(-)
 create mode 100644 src/utf.c

diff --git a/manifest b/manifest
index b575a89a88..a17867b8c7 100644
--- a/manifest
+++ b/manifest
@@ -1,5 +1,5 @@
-C Incremental\sbtree.c\schanges.\s(CVS\s1312)
-D 2004-05-03T19:49:33
+C Added\stemplate\sfor\sthe\sutf.c\sfile\scontaining\sconversion\sroutines.\s(CVS\s1313)
+D 2004-05-04T15:00:47
 F Makefile.in ab7b0d5118e2da97bac66be8684a1034e3500f5a
 F Makefile.linux-gcc b86a99c493a5bfb402d1d9178dcdc4bd4b32f906
 F README f1de682fbbd94899d50aca13d387d1b3fd3be2dd
@@ -59,6 +59,7 @@ F src/test4.c 6e3e31acfaf21d66420fc35fda5b17dc0000cc8d
 F src/tokenize.c 6676b946fd8825b67ab52140af4fdc57a70bda48
 F src/trigger.c a9927b57c865b6f3df3fb5e40c9824d722660ded
 F src/update.c 4c50328ebc127852bde8e2950eb8933234802c21
+F src/utf.c 8d74ddbfffdc1f2e87bfc11b8c1e2a806313a715
 F src/util.c b2287b07ddf55ef7aaa8888a9473123995a69f40
 F src/vacuum.c a4e8464c9f6d60659c5343e9d62c742463227820
 F src/vdbe.c 7c33f761fdc799633468766fb53eda4301daa6b3
@@ -188,7 +189,7 @@ F www/sqlite.tcl 3c83b08cf9f18aa2d69453ff441a36c40e431604
 F www/tclsqlite.tcl b9271d44dcf147a93c98f8ecf28c927307abd6da
 F www/vdbe.tcl 9b9095d4495f37697fd1935d10e14c6015e80aa1
 F www/whentouse.tcl a8335bce47cc2fddb07f19052cb0cb4d9129a8e4
-P 0eee3b5cd400e9548437632ec1dfe625a3fca9cf
-R 4e56ff31d4947da66d5a46115140d57d
+P fdc629dbbf974024215969e0bd3def4597258812
+R 862d1dd5fd20c7467c3bdf6faef3043d
 U drh
-Z 57bf0fd86b068e3d5bb631ec9f2832d0
+Z b159d386ddf509db1096e77212da2220
diff --git a/manifest.uuid b/manifest.uuid
index ebafdbf789..e74662e46c 100644
--- a/manifest.uuid
+++ b/manifest.uuid
@@ -1 +1 @@
-fdc629dbbf974024215969e0bd3def4597258812
\ No newline at end of file
+89b42c468f437003f74a1785370e75b2585fa9e2
\ No newline at end of file
diff --git a/src/utf.c b/src/utf.c
new file mode 100644
index 0000000000..6990553e0f
--- /dev/null
+++ b/src/utf.c
@@ -0,0 +1,77 @@
+/*
+** 2004 April 13
+**
+** The author disclaims copyright to this source code.  In place of
+** a legal notice, here is a blessing:
+**
+**    May you do good and not evil.
+**    May you find forgiveness for yourself and forgive others.
+**    May you share freely, never taking more than you give.
+**
+*************************************************************************
+** This file contains routines used to translate between UTF-8, 
+** UTF-16, UTF-16BE, and UTF-16LE.
+**
+** $Id: utf.c,v 1.1 2004/05/04 15:00:47 drh Exp $
+**
+** Notes on UTF-8:
+**
+**   Byte-0    Byte-1    Byte-2    Byte-3    Value
+**  0xxxxxxx                                 00000000 00000000 0xxxxxxx
+**  110yyyyy  10xxxxxx                       00000000 00000yyy yyxxxxxx
+**  1110zzzz  10yyyyyy  10xxxxxx             00000000 zzzzyyyy yyxxxxxx
+**  11110uuu  10uuzzzz  10yyyyyy  10xxxxxx   000uuuuu zzzzyyyy yyxxxxxx
+**
+**
+** Notes on UTF-16:  (with wwww+1==uuuuu)
+**
+**      Word-0            Word-1             Value
+**  110110wwwwxxxxxx 110111yyyyyyyyyy        000uuuuu xxxxxxyy yyyyyyyy
+**  xxxxxxxxyyyyyyyy                         00000000 xxxxxxxx yyyyyyyy
+**
+** BOM or Byte Order Mark:
+**     0xff 0xfe   little-endian utf-16 follows
+**     0xfe 0xff   big-endian utf-16 follows
+*/
+
+/*
+** Convert a string in UTF-16 native byte (or with a Byte-order-mark or
+** "BOM") into a UTF-8 string.  The UTF-8 string is written into space 
+** obtained from sqlit3Malloc() and must be released by the calling function.
+**
+** The parameter N is the number of bytes in the UTF-16 string.  If N is
+** negative, the entire string up to the first \u0000 character is translated.
+**
+** The returned UTF-8 string is always \000 terminated.
+*/
+unsigned char *sqlite3utf16to8(const void *pData, int N){
+  unsigned char *in = (unsigned char *)pData;
+}
+
+/*
+** Convert a string in UTF-16 native byte or with a BOM into a UTF-16LE
+** string.  The conversion occurs in-place.  The output overwrites the
+** input.  N bytes are converted.  If N is negative everything is converted
+** up to the first \u0000 character.
+**
+** If the native byte order is little-endian and there is no BOM, then
+** this routine is a no-op.  If there is a BOM at the start of the string,
+** it is removed.
+*/
+void sqlite3utf16to16le(void *pData, int N){
+}
+void sqlite3utf16to16be(void *pData, int N){
+}
+
+/*
+** Translation from UTF-16LE to UTF-16BE and back again is accomplished
+** using the library function swab().
+*/
+
+/*
+** Translate UTF-8 to UTF-16BE or UTF-16LE
+*/
+void *sqlite3utf8to16be(const unsigned char *pIn, int N){
+}
+void *sqlite3utf8to16le(const unsigned char *pIn, int N){
+}