lib/util/charset Move source3/lib/util_unistr.c to the common code.

This file (largely) contains functions to deal with UTF16 strings.

Andrew Bartlett

Signed-off-by: Andrew Tridgell <tridge@samba.org>

5 files changed, 44 insertions, 389 deletions

diff --git a/source3/Makefile.in b/source3/Makefile.in
index b3b1de48c5..a0503278b9 100644
--- a/source3/Makefile.in
+++ b/source3/Makefile.in
@@ -451,7 +451,7 @@ LIB_OBJ = $(LIBSAMBAUTIL_OBJ) $(UTIL_OBJ) $(CRYPTO_OBJ) \
 	  lib/bitmap.o lib/dprintf.o $(UTIL_REG_OBJ) \
 	  lib/wins_srv.o \
 	  lib/util_str.o ../lib/util/base64.o lib/util_sid.o \
-	  lib/util_unistr.o ../lib/util/charset/codepoints.o ../lib/util/charset/util_str.o lib/util_file.o \
+	  ../lib/util/charset/util_unistr_w.o ../lib/util/charset/codepoints.o ../lib/util/charset/util_str.o lib/util_file.o \
 	  lib/util.o lib/util_cmdline.o lib/util_names.o \
 	  lib/util_sock.o lib/sock_exec.o lib/util_sec.o \
 	  lib/substitute.o lib/dbwrap_util.o \
diff --git a/source3/include/proto.h b/source3/include/proto.h
index 48b94aacce..3f44b949f2 100644
--- a/source3/include/proto.h
+++ b/source3/include/proto.h
@@ -126,6 +126,9 @@ size_t pull_string_talloc(TALLOC_CTX *ctx,
 			size_t src_len,
 			int flags);
 size_t align_string(const void *base_ptr, const char *p, int flags);
+size_t dos_PutUniCode(char *dst,const char *src, size_t len, bool null_terminate);
+int rpcstr_push(void *dest, const char *src, size_t dest_len, int flags);
+int rpcstr_push_talloc(TALLOC_CTX *ctx, smb_ucs2_t **dest, const char *src);
 
 /* The following definitions come from lib/conn_tdb.c  */
 
@@ -1046,29 +1049,6 @@ char *escape_shell_string(const char *src);
 char **str_list_make_v3(TALLOC_CTX *mem_ctx, const char *string, const char *sep);
 char *sanitize_username(TALLOC_CTX *mem_ctx, const char *username);
 
-/* The following definitions come from lib/util_unistr.c  */
-
-size_t dos_PutUniCode(char *dst,const char *src, size_t len, bool null_terminate);
-int rpcstr_push(void *dest, const char *src, size_t dest_len, int flags);
-int rpcstr_push_talloc(TALLOC_CTX *ctx, smb_ucs2_t **dest, const char *src);
-size_t strlen_w(const smb_ucs2_t *src);
-size_t strnlen_w(const smb_ucs2_t *src, size_t max);
-smb_ucs2_t *strchr_w(const smb_ucs2_t *s, smb_ucs2_t c);
-smb_ucs2_t *strchr_wa(const smb_ucs2_t *s, char c);
-smb_ucs2_t *strrchr_w(const smb_ucs2_t *s, smb_ucs2_t c);
-smb_ucs2_t *strnrchr_w(const smb_ucs2_t *s, smb_ucs2_t c, unsigned int n);
-smb_ucs2_t *strstr_w(const smb_ucs2_t *s, const smb_ucs2_t *ins);
-bool strlower_w(smb_ucs2_t *s);
-bool strupper_w(smb_ucs2_t *s);
-int strcmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b);
-int strcasecmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b);
-int strncasecmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b, size_t len);
-int strcmp_wa(const smb_ucs2_t *a, const char *b);
-int toupper_ascii(int c);
-int tolower_ascii(int c);
-int isupper_ascii(int c);
-int islower_ascii(int c);
-
 /* The following definitions come from lib/version.c  */
 
 const char *samba_version_string(void);
diff --git a/source3/lib/charcnv.c b/source3/lib/charcnv.c
index 6e5b606e64..edcccc25e7 100644
--- a/source3/lib/charcnv.c
+++ b/source3/lib/charcnv.c
@@ -1366,3 +1366,42 @@ size_t align_string(const void *base_ptr, const char *p, int flags)
 	return 0;
 }
 
+/*******************************************************************
+ Write a string in (little-endian) unicode format. src is in
+ the current DOS codepage. len is the length in bytes of the
+ string pointed to by dst.
+
+ if null_terminate is True then null terminate the packet (adds 2 bytes)
+
+ the return value is the length in bytes consumed by the string, including the
+ null termination if applied
+********************************************************************/
+
+size_t dos_PutUniCode(char *dst,const char *src, size_t len, bool null_terminate)
+{
+	int flags = null_terminate ? STR_UNICODE|STR_NOALIGN|STR_TERMINATE
+				   : STR_UNICODE|STR_NOALIGN;
+	return push_ucs2(NULL, dst, src, len, flags);
+}
+
+
+/* Converts a string from internal samba format to unicode
+ */
+
+int rpcstr_push(void *dest, const char *src, size_t dest_len, int flags)
+{
+	return push_ucs2(NULL, dest, src, dest_len, flags|STR_UNICODE|STR_NOALIGN);
+}
+
+/* Converts a string from internal samba format to unicode. Always terminates.
+ * Actually just a wrapper round push_ucs2_talloc().
+ */
+
+int rpcstr_push_talloc(TALLOC_CTX *ctx, smb_ucs2_t **dest, const char *src)
+{
+	size_t size;
+	if (push_ucs2_talloc(ctx, dest, src, &size))
+		return size;
+	else
+		return -1;
+}
diff --git a/source3/lib/util_unistr.c b/source3/lib/util_unistr.c
deleted file mode 100644
index 26450e319b..0000000000
--- a/source3/lib/util_unistr.c
+++ /dev/null
@@ -1,364 +0,0 @@
-/* 
-   Unix SMB/CIFS implementation.
-   Samba utility functions
-   Copyright (C) Andrew Tridgell 1992-2001
-   Copyright (C) Simo Sorce 2001
-   Copyright (C) Jeremy Allison 2005
-   
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation; either version 3 of the License, or
-   (at your option) any later version.
-   
-   This program is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-   GNU General Public License for more details.
-   
-   You should have received a copy of the GNU General Public License
-   along with this program.  If not, see <http://www.gnu.org/licenses/>.
-*/
-
-#include "includes.h"
-
-/* Copy into a smb_ucs2_t from a possibly unaligned buffer. Return the copied smb_ucs2_t */
-#define COPY_UCS2_CHAR(dest,src) (((unsigned char *)(dest))[0] = ((unsigned char *)(src))[0],\
-				((unsigned char *)(dest))[1] = ((unsigned char *)(src))[1], (dest))
-
-
-/* return an ascii version of a ucs2 character */
-#define UCS2_TO_CHAR(c) (((c) >> UCS2_SHIFT) & 0xff)
-
-static int strncmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b, size_t len);
-
-/*******************************************************************
- Write a string in (little-endian) unicode format. src is in
- the current DOS codepage. len is the length in bytes of the
- string pointed to by dst.
-
- if null_terminate is True then null terminate the packet (adds 2 bytes)
-
- the return value is the length in bytes consumed by the string, including the
- null termination if applied
-********************************************************************/
-
-size_t dos_PutUniCode(char *dst,const char *src, size_t len, bool null_terminate)
-{
-	int flags = null_terminate ? STR_UNICODE|STR_NOALIGN|STR_TERMINATE
-				   : STR_UNICODE|STR_NOALIGN;
-	return push_ucs2(NULL, dst, src, len, flags);
-}
-
-
-/* Converts a string from internal samba format to unicode
- */
-
-int rpcstr_push(void *dest, const char *src, size_t dest_len, int flags)
-{
-	return push_ucs2(NULL, dest, src, dest_len, flags|STR_UNICODE|STR_NOALIGN);
-}
-
-/* Converts a string from internal samba format to unicode. Always terminates.
- * Actually just a wrapper round push_ucs2_talloc().
- */
-
-int rpcstr_push_talloc(TALLOC_CTX *ctx, smb_ucs2_t **dest, const char *src)
-{
-	size_t size;
-	if (push_ucs2_talloc(ctx, dest, src, &size))
-		return size;
-	else
-		return -1;
-}
-
-/*******************************************************************
- Count the number of two-byte pairs in a UTF16 string.
-********************************************************************/
-
-size_t strlen_w(const smb_ucs2_t *src)
-{
-	size_t len;
-	smb_ucs2_t c;
-
-	for(len = 0; *(COPY_UCS2_CHAR(&c,src)); src++, len++) {
-		;
-	}
-
-	return len;
-}
-
-/*******************************************************************
- Count up to max number of characters in a smb_ucs2_t string.
-********************************************************************/
-
-size_t strnlen_w(const smb_ucs2_t *src, size_t max)
-{
-	size_t len;
-	smb_ucs2_t c;
-
-	for(len = 0; (len < max) && *(COPY_UCS2_CHAR(&c,src)); src++, len++) {
-		;
-	}
-
-	return len;
-}
-
-/*******************************************************************
- Wide strchr().
-********************************************************************/
-
-smb_ucs2_t *strchr_w(const smb_ucs2_t *s, smb_ucs2_t c)
-{
-	smb_ucs2_t cp;
-	while (*(COPY_UCS2_CHAR(&cp,s))) {
-		if (c == cp) {
-			return (smb_ucs2_t *)s;
-		}
-		s++;
-	}
-	if (c == cp) {
-		return (smb_ucs2_t *)s;
-	}
-
-	return NULL;
-}
-
-smb_ucs2_t *strchr_wa(const smb_ucs2_t *s, char c)
-{
-	return strchr_w(s, UCS2_CHAR(c));
-}
-
-/*******************************************************************
- Wide strrchr().
-********************************************************************/
-
-smb_ucs2_t *strrchr_w(const smb_ucs2_t *s, smb_ucs2_t c)
-{
-	smb_ucs2_t cp;
-	const smb_ucs2_t *p = s;
-	int len = strlen_w(s);
-
-	if (len == 0) {
-		return NULL;
-	}
-	p += (len - 1);
-	do {
-		if (c == *(COPY_UCS2_CHAR(&cp,p))) {
-			return (smb_ucs2_t *)p;
-		}
-	} while (p-- != s);
-	return NULL;
-}
-
-/*******************************************************************
- Wide version of strrchr that returns after doing strrchr 'n' times.
-********************************************************************/
-
-smb_ucs2_t *strnrchr_w(const smb_ucs2_t *s, smb_ucs2_t c, unsigned int n)
-{
-	smb_ucs2_t cp;
-	const smb_ucs2_t *p = s;
-	int len = strlen_w(s);
-
-	if (len == 0 || !n) {
-		return NULL;
-	}
-	p += (len - 1);
-	do {
-		if (c == *(COPY_UCS2_CHAR(&cp,p))) {
-			n--;
-		}
-
-		if (!n) {
-			return (smb_ucs2_t *)p;
-		}
-	} while (p-- != s);
-	return NULL;
-}
-
-/*******************************************************************
- Wide strstr().
-********************************************************************/
-
-smb_ucs2_t *strstr_w(const smb_ucs2_t *s, const smb_ucs2_t *ins)
-{
-	smb_ucs2_t *r;
-	size_t inslen;
-
-	if (!s || !*s || !ins || !*ins) {
-		return NULL;
-	}
-
-	inslen = strlen_w(ins);
-	r = (smb_ucs2_t *)s;
-
-	while ((r = strchr_w(r, *ins))) {
-		if (strncmp_w(r, ins, inslen) == 0) {
-			return r;
-		}
-		r++;
-	}
-
-	return NULL;
-}
-
-/*******************************************************************
- Convert a string to lower case.
- return True if any char is converted
-
- This is unsafe for any string involving a UTF16 character
-********************************************************************/
-
-bool strlower_w(smb_ucs2_t *s)
-{
-	smb_ucs2_t cp;
-	bool ret = False;
-
-	while (*(COPY_UCS2_CHAR(&cp,s))) {
-		smb_ucs2_t v = tolower_m(cp);
-		if (v != cp) {
-			COPY_UCS2_CHAR(s,&v);
-			ret = True;
-		}
-		s++;
-	}
-	return ret;
-}
-
-/*******************************************************************
- Convert a string to upper case.
- return True if any char is converted
-
- This is unsafe for any string involving a UTF16 character
-********************************************************************/
-
-bool strupper_w(smb_ucs2_t *s)
-{
-	smb_ucs2_t cp;
-	bool ret = False;
-	while (*(COPY_UCS2_CHAR(&cp,s))) {
-		smb_ucs2_t v = toupper_m(cp);
-		if (v != cp) {
-			COPY_UCS2_CHAR(s,&v);
-			ret = True;
-		}
-		s++;
-	}
-	return ret;
-}
-
-int strcmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b)
-{
-	smb_ucs2_t cpa, cpb;
-
-	while ((*(COPY_UCS2_CHAR(&cpb,b))) && (*(COPY_UCS2_CHAR(&cpa,a)) == cpb)) {
-		a++;
-		b++;
-	}
-	return (*(COPY_UCS2_CHAR(&cpa,a)) - *(COPY_UCS2_CHAR(&cpb,b)));
-	/* warning: if *a != *b and both are not 0 we return a random
-		greater or lesser than 0 number not realted to which
-		string is longer */
-}
-
-static int strncmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b, size_t len)
-{
-	smb_ucs2_t cpa, cpb;
-	size_t n = 0;
-
-	while ((n < len) && (*(COPY_UCS2_CHAR(&cpb,b))) && (*(COPY_UCS2_CHAR(&cpa,a)) == cpb)) {
-		a++;
-		b++;
-		n++;
-	}
-	return (len - n)?(*(COPY_UCS2_CHAR(&cpa,a)) - *(COPY_UCS2_CHAR(&cpb,b))):0;
-}
-
-/*******************************************************************
- Case insensitive string comparison.
-********************************************************************/
-
-int strcasecmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b)
-{
-	smb_ucs2_t cpa, cpb;
-
-	while ((*COPY_UCS2_CHAR(&cpb,b)) && toupper_m(*(COPY_UCS2_CHAR(&cpa,a))) == toupper_m(cpb)) {
-		a++;
-		b++;
-	}
-	return (tolower_m(*(COPY_UCS2_CHAR(&cpa,a))) - tolower_m(*(COPY_UCS2_CHAR(&cpb,b))));
-}
-
-/*******************************************************************
- Case insensitive string comparison, length limited.
-********************************************************************/
-
-int strncasecmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b, size_t len)
-{
-	smb_ucs2_t cpa, cpb;
-	size_t n = 0;
-
-	while ((n < len) && *COPY_UCS2_CHAR(&cpb,b) && (toupper_m(*(COPY_UCS2_CHAR(&cpa,a))) == toupper_m(cpb))) {
-		a++;
-		b++;
-		n++;
-	}
-	return (len - n)?(tolower_m(*(COPY_UCS2_CHAR(&cpa,a))) - tolower_m(*(COPY_UCS2_CHAR(&cpb,b)))):0;
-}
-
-/*
-  The *_wa() functions take a combination of 7 bit ascii
-  and wide characters They are used so that you can use string
-  functions combining C string constants with ucs2 strings
-
-  The char* arguments must NOT be multibyte - to be completely sure
-  of this only pass string constants */
-
-int strcmp_wa(const smb_ucs2_t *a, const char *b)
-{
-	smb_ucs2_t cp = 0;
-
-	while (*b && *(COPY_UCS2_CHAR(&cp,a)) == UCS2_CHAR(*b)) {
-		a++;
-		b++;
-	}
-	return (*(COPY_UCS2_CHAR(&cp,a)) - UCS2_CHAR(*b));
-}
-
-/*************************************************************
- ascii only toupper - saves the need for smbd to be in C locale.
-*************************************************************/
-
-int toupper_ascii(int c)
-{
-	smb_ucs2_t uc = toupper_m(UCS2_CHAR(c));
-	return UCS2_TO_CHAR(uc);
-}
-
-/*************************************************************
- ascii only tolower - saves the need for smbd to be in C locale.
-*************************************************************/
-
-int tolower_ascii(int c)
-{
-	smb_ucs2_t uc = tolower_m(UCS2_CHAR(c));
-	return UCS2_TO_CHAR(uc);
-}
-
-/*************************************************************
- ascii only isupper - saves the need for smbd to be in C locale.
-*************************************************************/
-
-int isupper_ascii(int c)
-{
-	return isupper_m(UCS2_CHAR(c));
-}
-
-/*************************************************************
- ascii only islower - saves the need for smbd to be in C locale.
-*************************************************************/
-
-int islower_ascii(int c)
-{
-	return islower_m(UCS2_CHAR(c));
-}
diff --git a/source3/wscript_build b/source3/wscript_build
index 300f5b3863..71d91388dd 100755
--- a/source3/wscript_build
+++ b/source3/wscript_build
@@ -963,7 +963,7 @@ bld.SAMBA3_SUBSYSTEM('tdb-wrap3',
                     vars=locals())
 
 bld.SAMBA3_SUBSYSTEM('CHARSET3',
-                    source='''lib/util_str.c lib/util_unistr.c lib/charcnv.c lib/fstring.c''',
+                    source='''lib/util_str.c lib/charcnv.c lib/fstring.c''',
                     public_deps='ICONV_WRAPPER CODEPOINTS',
                     deps='DYNCONFIG')