From 17251f6faba4c70cf4f6241721c4bcb25dad9988 Mon Sep 17 00:00:00 2001
From: Daniel Swanson <awesomeevildudes@gmail.com>
Date: Fri, 1 Mar 2024 14:31:54 -0500
Subject: [PATCH] add <f/> as dictionary symbol for reading separator </> for
 lsx pgen

---
 configure.ac           | 2 +-
 lttoolbox/compiler.cc  | 6 ++++++
 lttoolbox/compiler.h   | 2 ++
 lttoolbox/dix.dtd      | 3 +++
 lttoolbox/transducer.h | 1 +
 5 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/configure.ac b/configure.ac
index 1a51dd15..1e83f7ec 100644
--- a/configure.ac
+++ b/configure.ac
@@ -2,7 +2,7 @@ AC_PREREQ(2.52)
 
 m4_define([PKG_VERSION_MAJOR], [3])
 m4_define([PKG_VERSION_MINOR], [7])
-m4_define([PKG_VERSION_PATCH], [7])
+m4_define([PKG_VERSION_PATCH], [8])
 
 # Bump if the ABI (not API) changed in a backwards-incompatible manner
 m4_define([PKG_VERSION_ABI], [3])
diff --git a/lttoolbox/compiler.cc b/lttoolbox/compiler.cc
index 753382a9..0d0ce3e9 100644
--- a/lttoolbox/compiler.cc
+++ b/lttoolbox/compiler.cc
@@ -385,6 +385,10 @@ Compiler::readString(std::vector<int> &result, UStringView name)
       result.push_back(word_boundary);
     }
   }
+  else if (is_separable && name == COMPILER_LSX_FORM_SEP_ELEM) {
+    requireEmptyError(name);
+    result.push_back(reading_boundary);
+  }
   else
   {
     std::cerr << "Error (" << xmlTextReaderGetParserLineNumber(reader);
@@ -966,11 +970,13 @@ Compiler::procNode()
       alphabet.includeSymbol(Transducer::LSX_BOUNDARY_SYMBOL);
       alphabet.includeSymbol(Transducer::LSX_BOUNDARY_SPACE_SYMBOL);
       alphabet.includeSymbol(Transducer::LSX_BOUNDARY_NO_SPACE_SYMBOL);
+      alphabet.includeSymbol(Transducer::READING_SEPARATOR_SYMBOL);
       any_tag          = alphabet(Transducer::ANY_TAG_SYMBOL);
       any_char         = alphabet(Transducer::ANY_CHAR_SYMBOL);
       word_boundary    = alphabet(Transducer::LSX_BOUNDARY_SYMBOL);
       word_boundary_s  = alphabet(Transducer::LSX_BOUNDARY_SPACE_SYMBOL);
       word_boundary_ns = alphabet(Transducer::LSX_BOUNDARY_NO_SPACE_SYMBOL);
+      reading_boundary = alphabet(Transducer::READING_SEPARATOR_SYMBOL);
     }
   }
   else if(name == COMPILER_ALPHABET_ELEM)
diff --git a/lttoolbox/compiler.h b/lttoolbox/compiler.h
index 9b8d42f8..e9d65e96 100644
--- a/lttoolbox/compiler.h
+++ b/lttoolbox/compiler.h
@@ -176,6 +176,7 @@ class Compiler
   int32_t word_boundary = 0;
   int32_t word_boundary_s = 0;
   int32_t word_boundary_ns = 0;
+  int32_t reading_boundary = 0;
 
   /**
    * Method to parse an XML Node
@@ -354,6 +355,7 @@ class Compiler
   static constexpr UStringView COMPILER_LSX_WB_ELEM        = u"d";
   static constexpr UStringView COMPILER_LSX_CHAR_ELEM      = u"w";
   static constexpr UStringView COMPILER_LSX_TAG_ELEM       = u"t";
+  static constexpr UStringView COMPILER_LSX_FORM_SEP_ELEM  = u"f";
   static constexpr UStringView COMPILER_LSX_SPACE_ATTR     = u"space";
   static constexpr UStringView COMPILER_LSX_SPACE_YES_VAL  = u"yes";
   static constexpr UStringView COMPILER_LSX_SPACE_NO_VAL   = u"no";
diff --git a/lttoolbox/dix.dtd b/lttoolbox/dix.dtd
index b17b52ed..6d491fe1 100644
--- a/lttoolbox/dix.dtd
+++ b/lttoolbox/dix.dtd
@@ -171,3 +171,6 @@
 
 <!ELEMENT w EMPTY>
     <!-- w: any word character -->
+
+<!ELEMENT f EMPTY>
+	<!-- f: form/reading separator -->
diff --git a/lttoolbox/transducer.h b/lttoolbox/transducer.h
index 814fe2e6..98391fe3 100644
--- a/lttoolbox/transducer.h
+++ b/lttoolbox/transducer.h
@@ -99,6 +99,7 @@ class Transducer
   static constexpr UStringView LSX_BOUNDARY_SYMBOL         = u"<$>";
   static constexpr UStringView LSX_BOUNDARY_SPACE_SYMBOL   = u"<$_>";
   static constexpr UStringView LSX_BOUNDARY_NO_SPACE_SYMBOL= u"<$->";
+  static constexpr UStringView READING_SEPARATOR_SYMBOL    = u"</>";
   static constexpr UStringView COMPOUND_ONLY_L_SYMBOL      = u"<compound-only-L>";
   static constexpr UStringView COMPOUND_R_SYMBOL           = u"<compound-R>";