Some minor refinements from expanding the corpus.

diff --git a/.gitignore b/.gitignore
index fba1fc27c19fea18a4f81dad98ff5249e8861add..3dd074e1cd878fc2c603c8b9805ceb4ee69d49ec 100644 (file)
--- a/.gitignore
+++ b/.gitignore
@@ -2,7 +2,9 @@ germano/
 smekens/
 williams/
 spv/
+svp2/
 unzipped/
+unzipped2/
 webold/
 dump
 parse-xml

diff --git a/dump.c b/dump.c
index 9e1bfd9f960b2f97379db046204193bcd6cdfd6a..be5139c6045a5eb2620242d9b2ca4212243e724d 100644 (file)
--- a/dump.c
+++ b/dump.c
@@ -246,6 +246,39 @@ dump_counted_string(void)
   return s;
 }
 
+static void __attribute__((unused))
+hex_dump(int ofs, int n)
+{
+  for (int i = 0; i < n; i++)
+    {
+      int c = data[ofs + i];
+#if 1
+      if (i && !(i % 16))
+        fprintf(stderr, "-");
+      else
+        fprintf(stderr, " ");
+#endif
+      fprintf(stderr, "%02x", c);
+      //fprintf(stderr, "%c", c >= 32 && c < 127 ? c : '.');
+    }
+  fprintf(stderr, "\n");
+}
+
+static void
+dump_style(void)
+{
+  match_byte(1);
+  match_byte(0);
+  match_byte(0);
+  match_byte(0);
+  match_byte_assert(1);
+  get_string();     /* foreground */
+  get_string();     /* background */
+  get_string();     /* font */
+  if (!match_byte(14))
+    match_byte_assert(12); /* size? */
+}
+
 static char *
 dump_nested_string(void)
 {
@@ -255,7 +288,10 @@ dump_nested_string(void)
   match_byte_assert (0);
   int outer_end = get_end();
   s = dump_counted_string();
-  match_byte_assert(0x58);
+  if (match_byte(0x31))
+    dump_style();
+  else
+    match_byte_assert(0x58);
   match_byte_assert(0x58);
   if (pos != outer_end)
     {
@@ -308,19 +344,7 @@ dump_optional_value(FILE *stream)
           dump_counted_string();
 
           if (match_byte(0x31))
-            {
-              /* Only one example in the corpus. */
-              match_byte(1);
-              match_byte(0);
-              match_byte(0);
-              match_byte(0);
-              match_byte_assert(1);
-              get_string();     /* foreground */
-              get_string();     /* background */
-              get_string();     /* font */
-              if (!match_byte(14))
-                match_byte_assert(12); /* size? */
-            }
+            dump_style();
           else
             match_byte_assert(0x58);
           if (match_byte(0x31))
@@ -357,7 +381,7 @@ dump_optional_value(FILE *stream)
       else if (match_u32 (2))
         {
           fprintf(stream, "(special 2)");
-          if (!match_byte(0))
+          if (!match_byte(0) && !match_byte(1))
             match_byte_assert(2);
           match_byte_assert(0);
           if (!match_u32 (2) && !match_u32(1))
@@ -792,24 +816,6 @@ dump_title(void)
     }
 }
 
-static void __attribute__((unused))
-hex_dump(int ofs, int n)
-{
-  for (int i = 0; i < n; i++)
-    {
-      int c = data[ofs + i];
-#if 1
-      if (i && !(i % 16))
-        fprintf(stderr, "-");
-      else
-        fprintf(stderr, " ");
-#endif
-      fprintf(stderr, "%02x", c);
-      //fprintf(stderr, "%c", c >= 32 && c < 127 ? c : '.');
-    }
-  fprintf(stderr, "\n");
-}
-
 static void
 dump_fonts(void)
 {
@@ -854,8 +860,8 @@ dump_fonts(void)
                 match_u32_assert(5);
               if (!match_u32(10) && !match_u32(11) && !match_u32(5))
                 match_u32_assert(9);
-              if (!match_u32(0))
-                match_u32_assert(1);
+              if (!match_u32(0) && !match_u32(1))
+                match_u32_assert(2);
             }
           else
             {
@@ -885,7 +891,7 @@ dump_fonts(void)
       assert(x3 >= 117);
       int len = data[pos + 0x34];
       if (len)
-        fprintf(stderr, "<tablelook>%.*s</tablelook>\n", len, &data[pos + 0x35]);
+        printf("<tablelook>%.*s</tablelook>\n", len, &data[pos + 0x35]);
     }
   pos += x3;
 
@@ -904,8 +910,9 @@ dump_fonts(void)
     match_byte_assert(1);
   if (version > 1)
     {
-      if (!match_byte(0x97) && !match_byte(0x98) && !match_byte(0x99))
-        match_byte_assert(0x9a);
+      if (!match_byte(0x97) && !match_byte(0x98)
+          && !match_byte(0x99) && !match_byte(0x9a))
+        match_byte_assert(0x9b);
       match_byte_assert(7);
       match_byte_assert(0);
       match_byte_assert(0);
@@ -953,8 +960,8 @@ dump_fonts(void)
 
       match_byte_assert(1);
       match_byte_assert(0);
-      if (!match_byte(3))
-        match_byte_assert(4);
+      if (!match_byte(3) && !match_byte(4))
+        match_byte_assert(5);
       match_byte_assert(0);
       match_byte_assert(0);
       match_byte_assert(0);
@@ -973,8 +980,9 @@ dump_fonts(void)
       if (!match_byte(0))
         match_byte_assert(1);
 
-      if (!match_byte(0x97) && !match_byte(0x98) && !match_byte(0x99))
-        match_byte_assert(0x9a);
+      if (!match_byte(0x97) && !match_byte(0x98)
+          && !match_byte(0x99) && !match_byte(0x9a))
+        match_byte_assert(0x9b);
       match_byte_assert(7);
       match_byte_assert(0);
       match_byte_assert(0);
@@ -1030,6 +1038,11 @@ dump_fonts(void)
       if (!match_byte(0))
         match_byte_assert(1);
 
+      if (pos < outer_end)
+        {
+          match_u32_assert(2000000);
+          match_u32_assert(0);
+        }
       assert(pos == outer_end);
 
       pos = outer_end;

diff --git a/parse-all-light b/parse-all-light
index 3925c52f8d3bbd1e60e91647f1398bd47f67f4b1..1facaec43d2bf858272a30f356862464e2d724af 100755 (executable)
--- a/parse-all-light
+++ b/parse-all-light
@@ -1,5 +1,5 @@
 #! /bin/bash
-for d in {williams,germano,smekens,unzipped}/*/*light*.bin; do
+for d in {williams,germano,smekens,unzipped,unzipped2}/*/*light*.bin; do
     if ! ./dump all < $d >/dev/null; then
        echo $d
        ./dump all < $d

diff --git a/spv-file-format.texi b/spv-file-format.texi
index 2ac8de6700de9a7c2f9e4eecb3067d6dbc7b5cae..1aef76c64750d0bef77720dadf166235531993dc 100644 (file)
--- a/spv-file-format.texi
+++ b/spv-file-format.texi
@@ -55,10 +55,12 @@ Same format used for tables, with a different name.
 The structure of a chart plus its data.  Charts do not have a
 ``light'' format.
 
-@item @var{prefix}_model.xml
-@itemx @var{prefix}_pmml.xml
-@itemx @var{prefix}_stats.xml
+@item @var{prefix}_model.scf
+@itemx @var{prefix}_pmml.scf
 Not yet investigated.  The corpus contains only one example of each.
+
+@itemx @var{prefix}_stats.xml
+Not yet investigated.  The corpus contains few examples.
 @end table
 
 The @file{@var{prefix}} in the names of the detail members is
@@ -417,7 +419,7 @@ x6 := 01 00 (03 | 04) 00 00 00
       byte*8 01
       (string[dataset] string[datafile] i0 int i0)?
       int[n-ccs] string*[n-ccs]
-      2e (00 | 01)
+      2e (00 | 01) (i2000000 i0)?
 @end example
 
 In every example in the corpus, @code{x1} is 240.  The meaning of the
@@ -632,19 +634,17 @@ substitution := i0 value
 opt-value := 31 i0 (i0 | i1 string) opt-value-i0-v1        /* @r{version 1} */
            | 31 i0 (i0 | i1 string) opt-value-i0-v3        /* @r{version 3} */
            | 31 i1 int32[footnote-number] nested-string
-           | 31 i2 (00 | 02) 00 (i1 | i2 | i3) nested-string
+           | 31 i2 (00 | 01 | 02) 00 (i1 | i2 | i3) nested-string
            | 31 i3 00 00 01 00 i2 nested-string
            | 58
 opt-value-i0-v1 := 00 (i1 | i2) 00 00 int32 00 00
 opt-value-i0-v3 := count(counted-string
-                         (58
-                          | 31 01? 00? 00? 00? 01
-                            string[fgcolor] string[bgcolor] string[typeface]
-                            byte)
+                         (58 | 31 style)
                          (58
                           | 31 i0 i0 i0 i0 01 00 (01 | 02 | 08)
                             00 08 00 0a 00))
 
-nested-string := 00 00 count(counted-string 58 58)
+style := 01? 00? 00? 00? 01 string[fgcolor] string[bgcolor] string[font] byte
+nested-string := 00 00 count(counted-string (58 | 31 style) 58)
 counted-string := count((i0 (58 | 31 string))?)
 @end example