INTEGRATION: CWS ooo20031216 (1.1.2); FILE ADDED

2003/12/10 14:27:02 khendricks 1.1.2.1: Issue number:  None
Submitted by:  Kevin B. Hendricks
Reviewed by:   project owner (me)

adding in the new thesaurus implementation that removes all of the
old hardcoded limits and problems with the old thesaurus

Kevin

1 files changed, 67 insertions, 0 deletions

diff --git a/lingucomponent/source/thesaurus/mythes/mythes.hxx b/lingucomponent/source/thesaurus/mythes/mythes.hxx
new file mode 100644
index 000000000000..3eebeda36393
--- /dev/null
+++ b/lingucomponent/source/thesaurus/mythes/mythes.hxx
@@ -0,0 +1,67 @@
+#ifndef _MYTHES_HXX_
+#define _MYTHES_HXX_
+
+// some maximum sizes for buffers
+#define MAX_WD_LEN 200
+#define MAX_LN_LEN 16384
+
+
+// a meaning with definition, count of synonyms and synonym list
+struct mentry {
+  char*  defn;
+  int  count;
+  char** psyns;
+};
+
+
+class MyThes
+{
+
+       int  nw;                  /* number of entries in thesaurus */
+       char**  list;               /* stores word list */
+       unsigned int* offst;              /* stores offset list */
+       char *  encoding;           /* stores text encoding; */
+
+        FILE  *pdfile;
+
+    // disallow copy-constructor and assignment-operator for now
+    MyThes();
+    MyThes(const MyThes &);
+    MyThes & operator = (const MyThes &);
+
+public:
+    MyThes(const char* idxpath, const char* datpath);
+    ~MyThes();
+
+        // lookup text in index and return number of meanings
+    // each meaning entry has a defintion, synonym count and pointer
+        // when complete return the *original* meaning entry and count via
+        // CleanUpAfterLookup to properly handle memory deallocation
+
+        int Lookup(const char * pText, int len, mentry** pme);
+
+        void CleanUpAfterLookup(mentry** pme, int nmean);
+
+        char* get_th_encoding();
+
+private:
+        // Open index and dat files and load list array
+        int thInitialize (const char* indxpath, const char* datpath);
+
+        // internal close and cleanup dat and idx files
+        int thCleanup ();
+
+        // read a text line (\n terminated) stripping off line terminator
+        int readLine(FILE * pf, char * buf, int nc);
+
+        // binary search on null terminated character strings
+        int binsearch(char * wrd, char* list[], int nlst);
+
+};
+
+#endif
+
+
+
+
+