X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=doc%2Fdev%2Fsystem-file-format.texi;h=a404d0d6ce3961eed3ca1ec134a2ff9f6140adac;hb=b5c82cc9aabe7e641011130240ae1b2e84348e23;hp=164807b80115e4796bb394c0336522b0d84344ba;hpb=d6ede2e8f16079edae2e308583f8af4f7e9daddd;p=pspp-builds.git

diff --git a/doc/dev/system-file-format.texi b/doc/dev/system-file-format.texi
index 164807b8..a404d0d6 100644
--- a/doc/dev/system-file-format.texi
+++ b/doc/dev/system-file-format.texi
@@ -97,6 +97,7 @@ Each type of record is described separately below.
 * Long Variable Names Record::
 * Very Long String Record::
 * Character Encoding Record::
+* Long String Value Labels Record::
 * Data File and Variable Attributes Records::
 * Miscellaneous Informational Records::
 * Dictionary Termination Record::
@@ -288,15 +289,20 @@ length @code{label_len}, rounded up to the nearest multiple of 32 bits.
 The first @code{label_len} characters are the variable's variable label.
 
 @item flt64 missing_values[];
-This field is present only if @code{n_missing_values} is not 0.  It has
-the same number of elements as the absolute value of
-@code{n_missing_values}.  For discrete missing values, each element
-represents one missing value.  When a range is present, the first
-element denotes the minimum value in the range, and the second element
-denotes the maximum value in the range.  When a range plus a value are
-present, the third element denotes the additional discrete missing
-value.  HIGHEST and LOWEST are indicated as described in the chapter
-introduction.
+This field is present only if @code{n_missing_values} is nonzero.  It
+has the same number of 8-byte elements as the absolute value of
+@code{n_missing_values}.  Each element is interpreted as a number for
+numeric variables (with HIGHEST and LOWEST indicated as described in
+the chapter introduction).  For string variables of width less than 8
+bytes, elements are right-padded with spaces; for string variables
+wider than 8 bytes, only the first 8 bytes of each missing value are
+specified, with the remainder implicitly all spaces.
+
+For discrete missing values, each element represents one missing
+value.  When a range is present, the first element denotes the minimum
+value in the range, and the second element denotes the maximum value
+in the range.  When a range plus a value are present, the third
+element denotes the additional discrete missing value.
 @end table
 
 The @code{print} and @code{write} members of sysfile_variable are output
@@ -398,6 +404,11 @@ Format types are defined as follows:
 @node Value Labels Records
 @section Value Labels Records
 
+The value label records documented in this section are used for
+numeric and short string variables only.  Long string variables may
+have value labels, but their value labels are recorded using a
+different record type (@pxref{Long String Value Labels Record}).
+
 The value label record has the following format:
 
 @example
@@ -458,7 +469,7 @@ A list of dictionary indexes of variables to which to apply the value
 labels (@pxref{Dictionary Index}).  There are @code{var_count}
 elements.
 
-String variables wider than 8 bytes may not have value labels.
+String variables wider than 8 bytes may not be specified in this list.
 @end table
 
 @node Document Record
@@ -837,6 +848,78 @@ See @url{http://www.iana.org/assignments/character-sets}.
 This record is not present in files generated by older software.
 See also @ref{character-code}.
 
+@node Long String Value Labels Record
+@section Long String Value Labels Record
+
+This record, if present, specifies value labels for long string
+variables.
+
+@example
+/* @r{Header.} */
+int32               rec_type;
+int32               subtype;
+int32               size;
+int32               count;
+
+/* @r{Repeated up to exactly @code{count} bytes.} */
+int32               var_name_len;
+char                var_name[];
+int32               var_width;
+int32               n_labels;
+long_string_label   labels[];
+@end example
+
+@table @code
+@item int32 rec_type;
+Record type.  Always set to 7.
+
+@item int32 subtype;
+Record subtype.  Always set to 21.
+
+@item int32 size;
+Always set to 1.
+
+@item int32 count;
+The number of bytes following the header until the next header.
+
+@item int32 var_name_len;
+@itemx char var_name[];
+The number of bytes in the name of the variable that has long string
+value labels, plus the variable name itself, which consists of exactly
+@code{var_name_len} bytes.  The variable name is not padded to any
+particular boundary, nor is it null-terminated.
+
+@item int32 var_width;
+The width of the variable, in bytes, which will be between 9 and
+32767.
+
+@item int32 n_labels;
+@itemx long_string_label labels[];
+The long string labels themselves.  The @code{labels} array contains
+exactly @code{n_labels} elements, each of which has the following
+substructure:
+
+@example
+int32               value_len;
+char                value[];
+int32               label_len;
+char                label[];
+@end example
+
+@table @code
+@item int32 value_len;
+@itemx char value[];
+The string value being labeled.  @code{value_len} is the number of
+bytes in @code{value}; it is equal to @code{var_width}.  The
+@code{value} array is not padded or null-terminated.
+
+@item int32 label_len;
+@itemx char label[];
+The label for the string value.  @code{label_len}, which must be
+between 0 and 120, is the number of bytes in @code{label}.  The
+@code{label} array is not padded or null-terminated.
+@end table
+@end table
 
 @node Data File and Variable Attributes Records
 @section Data File and Variable Attributes Records