Document ccs.

[pspp] / spv-file-format.texi

diff --git a/spv-file-format.texi b/spv-file-format.texi
index f9d698706e50acf0ba48e577f2f1647a2737a118..2ac8de6700de9a7c2f9e4eecb3067d6dbc7b5cae 100644 (file)
--- a/spv-file-format.texi
+++ b/spv-file-format.texi
@@ -400,8 +400,24 @@ styles := 00 font*8
           (i0 | i-1) (00 | 01) 00 (00 | 01)
           int
           byte[decimal] byte[grouping]
-          int[x5] string*[x5]    /* @r{custom currency} */
-          int[x6] byte*[x6]
+          int[n-ccs] string*[n-ccs]     /* @r{custom currency} */
+          styles2
+
+x2 := 00 00 00 01 00 00 00 00 00 00 00 00 00 02 00 00 00 00  /* @r{18 bytes} */
+
+styles2 := i0                           /* @r{version 1} */
+styles2 := count(count(x5) count(x6))   /* @r{version 3} */
+x5 := byte*33 int[n] int*n
+x6 := 01 00 (03 | 04) 00 00 00
+      string[command] string[subcommand]
+      string[language] string[charset] string[locale]
+      (00 | 01) 00 (00 | 01) (00 | 01)
+      int
+      byte[decimal] byte[grouping]
+      byte*8 01
+      (string[dataset] string[datafile] i0 int i0)?
+      int[n-ccs] string*[n-ccs]
+      2e (00 | 01)
 @end example
 
 In every example in the corpus, @code{x1} is 240.  The meaning of the
@@ -413,10 +429,10 @@ follow it are @code{00 00 00 01 00 00 00 00 00 00 00 00 00 02 00 00 00
 
 In every example in the corpus for version 1, @code{x3} is 16 and the
 bytes that follow it are @code{00 00 00 01 00 00 00 01 00 00 00 00 01
-01 01 01}.  In version 3, observed @code{x3} varies from 117 to 150 and
-the bytes that follow it vary somewhat and often include a readable
-text string, e.g. ``Default'' or ``Academic'', which appears to be the
-name of a ``TableLook''.
+01 01 01}.  In version 3, observed @code{x3} varies from 117 to 150,
+and its bytes include a 1-byte count at offset 0x34.  When the count
+is nonzero, a text string of that length at offset 0x35 is the name of
+a ``TableLook'', e.g. ``Default'' or ``Academic''.
 
 Observed values of @code{x4} vary from 0 to 17.  Out of 7060 examples
 in the corpus, it is nonzero only 36 times.
@@ -433,9 +449,9 @@ are @samp{.} and @samp{,}.
 @samp{,}, @samp{.}, @samp{'}, @samp{ }, and zero (presumably
 indicating that digits should not be grouped).
 
-@code{x5} is observed as either 0 or 5.  When it is 5, the following
-strings are CCA through CCE format strings.  Most commonly these are
-all @code{-,,,} but other strings occur.
+@code{n-ccs} is observed as either 0 or 5.  When it is 5, the
+following strings are CCA through CCE format strings.  Most commonly
+these are all @code{-,,,} but other strings occur.
 
 @example
 font := byte[index] 31 string[typeface]