Worked on format support

libyal · Jul 9, 2023 · 99bc3b7 · 99bc3b7
1 parent 1c853ae
commit 99bc3b7
Show file tree

Hide file tree

Showing 36 changed files with 2,582 additions and 294 deletions.
diff --git a/.gitignore b/.gitignore
@@ -135,12 +135,14 @@ stamp-h[1-9]
 /tests/scca_test_file_header
 /tests/scca_test_file_information
 /tests/scca_test_file_metrics
+/tests/scca_test_filename_string
 /tests/scca_test_filename_strings
 /tests/scca_test_io_handle
 /tests/scca_test_notify
 /tests/scca_test_support
 /tests/scca_test_tools_info_handle
 /tests/scca_test_tools_output
+/tests/scca_test_tools_path_string
 /tests/scca_test_tools_signal
 /tests/scca_test_volume_information
 /tests/tmp*

diff --git a/documentation/Windows Prefetch File (PF) format.asciidoc b/documentation/Windows Prefetch File (PF) format.asciidoc
@@ -65,6 +65,7 @@ in the section entitled "GNU Free Documentation License".
 | 0.0.18 | J.B. Metz | February 2020 | Cleaned up notes.
 | 0.0.19 | J.B. Metz | September 2020 | Cleaned up notes.
 | 0.0.20 | N. Suthar | July 2023 | Corrections and additional information regarding unknown "hash string" section.
+| 0.0.21 | J.B. Metz | July 2023 | Additional information regarding encoding of filenames.
 |===
 
 :numbered:
@@ -237,6 +238,10 @@ The executable filename will store a maximum of 29 characters. Dependent on the
 Windows version the unused bytes of the executable filename can contain remnant
 data. Windows 8.1 seems to fill the unused bytes with 0-byte values.
 
+[NOTE]
+The filename is not strict UTF-16 since it allows for unpaired surrogates, such
+as "U+d800" and "U+dc00".
+
 ==== Format version
 
 [cols="1,5",options="header"]
@@ -557,6 +562,10 @@ The directory strings consists of:
 
 A filename string is an UTF-16 little-endian strings with end-of-string character.
 
+[NOTE]
+A filename string is not strict UTF-16 since it allows for unpaired surrogates,
+such as "U+d800" and "U+dc00".
+
 [yellow-background]*Is the the array followed by alignment padding? If so what
 is the size of the alignment,16-byte? Seen values ranging from 6 to 2 bytes.*
 
@@ -747,6 +756,10 @@ The value does not include the end-of-string character.
 | 2 | ... | | Array of UTF-16 little-endian strings with end-of-string character
 |===
 
+[NOTE]
+A directory string is not strict UTF-16 since it allows for unpaired surrogates,
+such as "U+d800" and "U+dc00".
+
 == [[calculating_prefetch_hash]]Calculating the prefetch hash
 
 There are multiple known hashing functions to be used for prefetch filename

diff --git a/include/libscca.h.in b/include/libscca.h.in
@@ -270,6 +270,7 @@ int libscca_file_get_format_version(
      libscca_error_t **error );
 
 /* Retrieves the size of a specific UTF-8 encoded executable filename
+ * This function uses UTF-8 RFC 2279 (or 6-byte UTF-8) to support characters outside Unicode
  * The returned size includes the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -280,6 +281,7 @@ int libscca_file_get_utf8_executable_filename_size(
      libscca_error_t **error );
 
 /* Retrieves a specific UTF-8 encoded executable filename
+ * This function uses UTF-8 RFC 2279 (or 6-byte UTF-8) to support characters outside Unicode
  * The size should include the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -291,6 +293,7 @@ int libscca_file_get_utf8_executable_filename(
      libscca_error_t **error );
 
 /* Retrieves the size of a specific UTF-16 encoded executable filename
+ * This function uses UCS-2 (with surrogates) to support characters outside Unicode
  * The returned size includes the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -301,6 +304,7 @@ int libscca_file_get_utf16_executable_filename_size(
      libscca_error_t **error );
 
 /* Retrieves a specific UTF-16 encoded executable filename
+ * This function uses UCS-2 (with surrogates) to support characters outside Unicode
  * The size should include the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -372,6 +376,7 @@ int libscca_file_get_number_of_filenames(
      libscca_error_t **error );
 
 /* Retrieves the size of a specific UTF-8 encoded filename
+ * This function uses UTF-8 RFC 2279 (or 6-byte UTF-8) to support characters outside Unicode
  * The returned size includes the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -383,6 +388,7 @@ int libscca_file_get_utf8_filename_size(
      libscca_error_t **error );
 
 /* Retrieves a specific UTF-8 encoded filename
+ * This function uses UTF-8 RFC 2279 (or 6-byte UTF-8) to support characters outside Unicode
  * The size should include the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -395,6 +401,7 @@ int libscca_file_get_utf8_filename(
      libscca_error_t **error );
 
 /* Retrieves the size of a specific UTF-16 encoded filename
+ * This function uses UCS-2 (with surrogates) to support characters outside Unicode
  * The returned size includes the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -406,6 +413,7 @@ int libscca_file_get_utf16_filename_size(
      libscca_error_t **error );
 
 /* Retrieves a specific UTF-16 encoded filename
+ * This function uses UCS-2 (with surrogates) to support characters outside Unicode
  * The size should include the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -449,6 +457,7 @@ int libscca_file_metrics_free(
      libscca_error_t **error );
 
 /* Retrieves the size of the UTF-8 encoded filename
+ * This function uses UTF-8 RFC 2279 (or 6-byte UTF-8) to support characters outside Unicode
  * The returned size includes the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -459,6 +468,7 @@ int libscca_file_metrics_get_utf8_filename_size(
      libscca_error_t **error );
 
 /* Retrieves the UTF-8 encoded filename
+ * This function uses UTF-8 RFC 2279 (or 6-byte UTF-8) to support characters outside Unicode
  * The size should include the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -470,6 +480,7 @@ int libscca_file_metrics_get_utf8_filename(
      libscca_error_t **error );
 
 /* Retrieves the size of the UTF-16 encoded filename
+ * This function uses UCS-2 (with surrogates) to support characters outside Unicode
  * The returned size includes the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -480,6 +491,7 @@ int libscca_file_metrics_get_utf16_filename_size(
      libscca_error_t **error );
 
 /* Retrieves the UTF-16 encoded filename
+ * This function uses UCS-2 (with surrogates) to support characters outside Unicode
  * The size should include the end of string character
  * Returns 1 if successful or -1 on error
  */

diff --git a/libscca/Makefile.am b/libscca/Makefile.am
@@ -34,6 +34,7 @@ libscca_la_SOURCES = \
 	libscca_file_header.c libscca_file_header.h \
 	libscca_file_information.c libscca_file_information.h \
 	libscca_file_metrics.c libscca_file_metrics.h \
+	libscca_filename_string.c libscca_filename_string.h \
 	libscca_filename_strings.c libscca_filename_strings.h \
 	libscca_io_handle.c libscca_io_handle.h \
 	libscca_libbfio.h \

diff --git a/libscca/libscca_file.c b/libscca/libscca_file.c
@@ -1620,6 +1620,7 @@ int libscca_file_get_format_version(
 }
 
 /* Retrieves the size of a specific UTF-8 encoded executable filename
+ * This function uses UTF-8 RFC 2279 (or 6-byte UTF-8) to support characters outside Unicode
  * The returned size includes the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -1644,30 +1645,16 @@ int libscca_file_get_utf8_executable_filename_size(
 	}
 	internal_file = (libscca_internal_file_t *) file;
 
-	if( internal_file->file_header == NULL )
-	{
-		libcerror_error_set(
-		 error,
-		 LIBCERROR_ERROR_DOMAIN_RUNTIME,
-		 LIBCERROR_RUNTIME_ERROR_VALUE_MISSING,
-		 "%s: invalid internal file - missing file header.",
-		 function );
-
-		return( -1 );
-	}
-/* TODO add function to file header */
-	if( libuna_utf8_string_size_from_utf16_stream(
-	     internal_file->file_header->executable_filename,
-	     internal_file->file_header->executable_filename_size,
-	     LIBUNA_ENDIAN_LITTLE,
+	if( libscca_file_header_get_utf8_executable_filename_size(
+	     internal_file->file_header,
 	     utf8_string_size,
 	     error ) != 1 )
 	{
 		libcerror_error_set(
 		 error,
 		 LIBCERROR_ERROR_DOMAIN_RUNTIME,
 		 LIBCERROR_RUNTIME_ERROR_GET_FAILED,
-		 "%s: unable to determine size of UTF-8 executable filename string.",
+		 "%s: unable to retrieve UTF-8 executable filename size.",
 		 function );
 
 		return( -1 );
@@ -1676,6 +1663,7 @@ int libscca_file_get_utf8_executable_filename_size(
 }
 
 /* Retrieves a specific UTF-8 encoded executable filename
+ * This function uses UTF-8 RFC 2279 (or 6-byte UTF-8) to support characters outside Unicode
  * The size should include the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -1701,31 +1689,17 @@ int libscca_file_get_utf8_executable_filename(
 	}
 	internal_file = (libscca_internal_file_t *) file;
 
-	if( internal_file->file_header == NULL )
-	{
-		libcerror_error_set(
-		 error,
-		 LIBCERROR_ERROR_DOMAIN_RUNTIME,
-		 LIBCERROR_RUNTIME_ERROR_VALUE_MISSING,
-		 "%s: invalid internal file - missing file header.",
-		 function );
-
-		return( -1 );
-	}
-/* TODO add function to file header */
-	if( libuna_utf8_string_copy_from_utf16_stream(
-	     (libuna_utf8_character_t *) utf8_string,
+	if( libscca_file_header_get_utf8_executable_filename(
+	     internal_file->file_header,
+	     utf8_string,
 	     utf8_string_size,
-	     internal_file->file_header->executable_filename,
-	     internal_file->file_header->executable_filename_size,
-	     LIBUNA_ENDIAN_LITTLE,
 	     error ) != 1 )
 	{
 		libcerror_error_set(
 		 error,
 		 LIBCERROR_ERROR_DOMAIN_RUNTIME,
-		 LIBCERROR_RUNTIME_ERROR_SET_FAILED,
-		 "%s: unable to set UTF-8 executable filename string.",
+		 LIBCERROR_RUNTIME_ERROR_GET_FAILED,
+		 "%s: unable to retrieve UTF-8 executable filename.",
 		 function );
 
 		return( -1 );
@@ -1734,6 +1708,7 @@ int libscca_file_get_utf8_executable_filename(
 }
 
 /* Retrieves the size of a specific UTF-16 encoded executable filename
+ * This function uses UCS-2 (with surrogates) to support characters outside Unicode
  * The returned size includes the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -1758,30 +1733,16 @@ int libscca_file_get_utf16_executable_filename_size(
 	}
 	internal_file = (libscca_internal_file_t *) file;
 
-	if( internal_file->file_header == NULL )
-	{
-		libcerror_error_set(
-		 error,
-		 LIBCERROR_ERROR_DOMAIN_RUNTIME,
-		 LIBCERROR_RUNTIME_ERROR_VALUE_MISSING,
-		 "%s: invalid internal file - missing file header.",
-		 function );
-
-		return( -1 );
-	}
-/* TODO add function to file header */
-	if( libuna_utf16_string_size_from_utf16_stream(
-	     internal_file->file_header->executable_filename,
-	     internal_file->file_header->executable_filename_size,
-	     LIBUNA_ENDIAN_LITTLE,
+	if( libscca_file_header_get_utf16_executable_filename_size(
+	     internal_file->file_header,
 	     utf16_string_size,
 	     error ) != 1 )
 	{
 		libcerror_error_set(
 		 error,
 		 LIBCERROR_ERROR_DOMAIN_RUNTIME,
 		 LIBCERROR_RUNTIME_ERROR_GET_FAILED,
-		 "%s: unable to determine size of UTF-16 executable filename string.",
+		 "%s: unable to retrieve UTF-16 executable filename size.",
 		 function );
 
 		return( -1 );
@@ -1790,6 +1751,7 @@ int libscca_file_get_utf16_executable_filename_size(
 }
 
 /* Retrieves a specific UTF-16 encoded executable filename
+ * This function uses UCS-2 (with surrogates) to support characters outside Unicode
  * The size should include the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -1815,31 +1777,17 @@ int libscca_file_get_utf16_executable_filename(
 	}
 	internal_file = (libscca_internal_file_t *) file;
 
-	if( internal_file->file_header == NULL )
-	{
-		libcerror_error_set(
-		 error,
-		 LIBCERROR_ERROR_DOMAIN_RUNTIME,
-		 LIBCERROR_RUNTIME_ERROR_VALUE_MISSING,
-		 "%s: invalid internal file - missing file header.",
-		 function );
-
-		return( -1 );
-	}
-/* TODO add function to file header */
-	if( libuna_utf16_string_copy_from_utf16_stream(
-	     (libuna_utf16_character_t *) utf16_string,
+	if( libscca_file_header_get_utf16_executable_filename(
+	     internal_file->file_header,
+	     utf16_string,
 	     utf16_string_size,
-	     internal_file->file_header->executable_filename,
-	     internal_file->file_header->executable_filename_size,
-	     LIBUNA_ENDIAN_LITTLE,
 	     error ) != 1 )
 	{
 		libcerror_error_set(
 		 error,
 		 LIBCERROR_ERROR_DOMAIN_RUNTIME,
-		 LIBCERROR_RUNTIME_ERROR_SET_FAILED,
-		 "%s: unable to set UTF-16 executable filename string.",
+		 LIBCERROR_RUNTIME_ERROR_GET_FAILED,
+		 "%s: unable to retrieve UTF-16 executable filename.",
 		 function );
 
 		return( -1 );
@@ -2164,6 +2112,7 @@ int libscca_file_get_number_of_filenames(
 }
 
 /* Retrieves the size of a specific UTF-8 encoded filename
+ * This function uses UTF-8 RFC 2279 (or 6-byte UTF-8) to support characters outside Unicode
  * The returned size includes the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -2209,6 +2158,7 @@ int libscca_file_get_utf8_filename_size(
 }
 
 /* Retrieves a specific UTF-8 encoded filename
+ * This function uses UTF-8 RFC 2279 (or 6-byte UTF-8) to support characters outside Unicode
  * The size should include the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -2256,6 +2206,7 @@ int libscca_file_get_utf8_filename(
 }
 
 /* Retrieves the size of a specific UTF-16 encoded filename
+ * This function uses UCS-2 (with surrogates) to support characters outside Unicode
  * The returned size includes the end of string character
  * Returns 1 if successful or -1 on error
  */
@@ -2301,6 +2252,7 @@ int libscca_file_get_utf16_filename_size(
 }
 
 /* Retrieves a specific UTF-16 encoded filename
+ * This function uses UCS-2 (with surrogates) to support characters outside Unicode
  * The size should include the end of string character
  * Returns 1 if successful or -1 on error
  */