Renamed dftables as pcre2_dftables and enable it to write the tables in binary.

Update documentation about character tables.


git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@1237 6239d852-aaf2-0410-a92c-79f79f948069

1 files changed, 21 insertions, 17 deletions

diff --git a/src/pcre2_chartables.c.dist b/src/pcre2_chartables.c.dist
index 0e07edb..861914d 100644
--- a/src/pcre2_chartables.c.dist
+++ b/src/pcre2_chartables.c.dist
@@ -2,17 +2,21 @@
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
 
-/* This file was automatically written by the dftables auxiliary
+/* This file was automatically written by the pcre2_dftables auxiliary
 program. It contains character tables that are used when no external
 tables are passed to PCRE2 by the application that calls it. The tables
 are used only for characters whose code values are less than 256. */
 
-/*The dftables program (which is distributed with PCRE2) can be used to
-build alternative versions of this file. This is necessary if you are
+/* This set of tables was written in the C locale. */
+
+/* The pcre2_ftables program (which is distributed with PCRE2) can be used
+to build alternative versions of this file. This is necessary if you are
 running in an EBCDIC environment, or if you want to default to a different
-encoding, for example ISO-8859-1. When dftables is run, it creates these
-tables in the current locale. This happens automatically if PCRE2 is
-configured with --enable-rebuild-chartables. */
+encoding, for example ISO-8859-1. When pcre2_dftables is run, it creates
+these tables in the "C" locale by default. This happens automatically if
+PCRE2 is configured with --enable-rebuild-chartables. However, you can run
+pcre2_dftables manually with the -L option to build tables using the LC_ALL
+locale. */
 
 /* The following #include is present because without it gcc 4.x may remove
 the array definition from the final binary if PCRE2 is built into a static
@@ -102,54 +106,54 @@ const uint8_t PRIV(default_tables)[] = {
 /* This table contains bit maps for various character classes. Each map is 32
 bytes long and the bits run from the least significant end of each byte. The
 classes that have their own maps are: space, xdigit, digit, upper, lower, word,
-graph print, punct, and cntrl. Other classes are built from combinations. */
+graph, print, punct, and cntrl. Other classes are built from combinations. */
 
-  0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00,
+  0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00,  /* space */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,  /* xdigit */
   0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,  /* digit */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* upper */
   0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* lower */
   0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,  /* word */
   0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff,
+  0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff,  /* graph */
   0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff,
+  0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff,  /* print */
   0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc,
+  0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc,  /* punct */
   0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00,
+  0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00,  /* cntrl */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,