Thesaurus Zip Attached:
thesaurus_pkg.zip

The attached thesaurus_pkg.zip contains a thesaurus.txt in the vim space-separated
format derived from the Wordnet/MyThes-1 sources.

Can the thesaurus.txt be made available on the the ftp site?

The thesaurus.pkg.zip contains these files:

A patch file to modify MyThes-1.0 and generate the thesarus.txt file
thesaurus_pkg/thesaurus-for-vim.patch
A thesaurus file in the vim format
thesaurus_pkg/thesaurus.txt
The WordNet and MyThes-1 licences
thesaurus_pkg/WordNet_license.txt
thesaurus_pkg/license.readme

Notes:

All distinct terms made of multiple words were removed because the space
between the words conflicts with the default term delimiter which is a space.
All terms that didn't have any synonyms were removed.

Patch File:
Here is the patch file thesaurus_pkg/thesaurus-for-vim.patch for MyThes-1:

diff -ruN MyThes-1.0/Makefile MyThes-1.0-vim/Makefile
--- MyThes-1.0/Makefile	2003-12-08 14:42:33.000000000 -0700
+++ MyThes-1.0-vim/Makefile	2018-11-30 07:48:21.000000000 -0700
@@ -21,7 +21,7 @@
 	-@ ($(RANLIB) $@ || true) >/dev/null 2>&1
 
 example: example.o $(LIBS)
-	$(CXX) $(CXXFLAGS) -o $@ example.o $(LDFLAGS)
+	$(CXX) -o $@ example.o $(LDFLAGS)
 
 %.o: %.cxx 
 	$(CXX) $(CXXFLAGS) -c $<
diff -ruN MyThes-1.0/README-VIM-THESAURUS MyThes-1.0-vim/README-VIM-THESAURUS
--- MyThes-1.0/README-VIM-THESAURUS	1969-12-31 17:00:00.000000000 -0700
+++ MyThes-1.0-vim/README-VIM-THESAURUS	2018-11-30 10:04:10.000000000 -0700
@@ -0,0 +1,21 @@
+To create a thesaurus file formatted for vim's thesaurus run:
+bash ./mk-vim-thesaurus.sh
+
+The file 'thesaurus.txt' will be created.
+
+Here are the steps that mk-vim-thesaurus.sh takes:
+
+1. Extract term list from MyThes-1.0 th_en_US_new.dat file:
+# Note: This will remove complex words with spaces in them because space is the
+# default delimiter for vim's thesaurus format.
+grep -v "^(" th_en_US_new.dat | awk -F"|" '{print $1}' | grep -v ' ' | grep -v 'ISO8859-1' > words-without-spaces.lst
+
+2. make example
+make
+
+3. Run mk_vim_thesaurus_format:
+# Note: While extracting synonyms, multiple word synonyms with spaces are excluded.
+./example th_en_US_new.idx th_en_US_new.dat words-without-spaces.lst  > raw-list
+
+4. Remove entries that don't have synonyms:
+grep -v "^\w\+$" raw-list > thesaurus.txt 
diff -ruN MyThes-1.0/example.cxx MyThes-1.0-vim/example.cxx
--- MyThes-1.0/example.cxx	2003-12-08 14:37:13.000000000 -0700
+++ MyThes-1.0-vim/example.cxx	2018-11-30 09:00:44.000000000 -0700
@@ -70,16 +70,20 @@
       // or count since needed for CleanUpAfterLookup routine
       mentry* pm = pmean;
       if (count) {
-        fprintf(stdout,"%s has %d meanings\n",buf,count);
-	for (int  i=0; i < count; i++) {
-          fprintf(stdout,"   meaning %d: %s\n",i,pm->defn);
+        // initial word
+        fprintf(stdout,"%s",buf);
+        for (int  i=0; i < count; i++) {
           for (int j=0; j < pm->count; j++) {
-	    fprintf(stdout,"       %s\n",pm->psyns[j]);
+            // only output the word if it doesn't have spaces
+            // because space is the standard delimiter in the 
+            // vim thesaurus file format.
+            if (strchr(pm->psyns[j], ' ') == NULL)  {
+              fprintf(stdout," %s",pm->psyns[j]);
+            }
           }
-          fprintf(stdout,"\n");
           pm++;
-	}
-        fprintf(stdout,"\n\n");
+        }
+        fprintf(stdout,"\n");
         // now clean up all allocated memory 
         pMT->CleanUpAfterLookup(&pmean,count);
       } else {
diff -ruN MyThes-1.0/mk-vim-thesaurus.sh MyThes-1.0-vim/mk-vim-thesaurus.sh
--- MyThes-1.0/mk-vim-thesaurus.sh	1969-12-31 17:00:00.000000000 -0700
+++ MyThes-1.0-vim/mk-vim-thesaurus.sh	2018-11-30 08:51:15.000000000 -0700
@@ -0,0 +1,13 @@
+
+# Extract term list from MyThes-1.0 th_en_US_new.dat file:
+grep -v "^(" th_en_US_new.dat | awk -F"|" '{print $1}' | grep -v ' ' | grep -v 'ISO8859-1' > words-without-spaces.lst
+
+# make example
+make
+
+#  Run mk_vim_thesaurus_format:
+./example th_en_US_new.idx th_en_US_new.dat words-without-spaces.lst  > raw-list
+
+#  Remove entries that don't have synonyms:
+grep -v '^\w\+$' raw-list > thesaurus.txt 
+
diff -ruN MyThes-1.0/mythes.cxx MyThes-1.0-vim/mythes.cxx
--- MyThes-1.0/mythes.cxx	2003-12-08 14:40:27.000000000 -0700
+++ MyThes-1.0-vim/mythes.cxx	2018-11-28 13:12:29.000000000 -0700
@@ -25,7 +25,7 @@
 // return index of char in string
 int mystr_indexOfChar(const char * d, int c)
 {
-  char * p = strchr(d,c);
+  const char * p = strchr(d,c);
   if (p) return (int)(p-d);
   return -1;
 }

Uh oh!

Broken link on :h thesaurus #629

Description

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions