remove IANA language collisions

Luther Tychonievich · Luther Tychonievich · commit 7f34bd6e2886 · 2021-07-12T13:21:52.000-04:00
diff --git a/DownloadDefinitions.java b/DownloadDefinitions.java
@@ -36,6 +36,8 @@ private static void downloadIANALanguageSubtagRegistery(String filename) {
                     else if (line.startsWith("Subtag: ")) tag = line.substring(8);
                     else if (isLang && line.startsWith("Description: ")) {
                         String key = line.substring(13);
+                        // key = key.replaceAll(" \\(.*", ""); // change "Modern Greek (1453-)" to "Modern Greek" but also conflates arr "Karo (Brazil)" and kxh "Karo (Ethiopia)" so disabled for now
+                        key = key.replaceAll(" language.*", ""); // change "Bihari languages" to "Bihari"
                         fos.write((key+"\t"+tag+"\n").getBytes("UTF-8"));
                     }
                 }
diff --git a/README.md b/README.md
@@ -5,14 +5,18 @@ Some parts are ported directly from the C converter (such as the ANSEL Charset a
 
 # Updating to new versions of GEDCOM
 
-The file `edu/virginia/ged5to7/GedcomDefinitions.java` contains preprocessed copies of the TSV files from <https://github.com/FamilySearch/GEDCOM/tree/main/extracted-files>. When a new (minor or major) version of the spec is released, updates to those files will need to be incorporated by running
+The file `edu/virginia/ged5to7/config/` contains copies of the TSV files
+from <https://github.com/FamilySearch/GEDCOM/>,
+<https://github.com/fhiso/legacy-format/>,
+and <https://www.iana.org/assignments/language-subtag-registry/language-subtag-registry>.
+These can be updated by running
 
 ```bash
 javac DownloadDefinitions.java
 java DownloadDefinitions
 ```
 
-The above will overwrite the file `edu/virginia/ged5to7/GedcomDefinitions.java` with an updated version.
+The above will overwrite the files in `edu/virginia/ged5to7/config/` with updated versions.
 
 `DownloadDefinitions.java` is otherwise unneeded, and should not be included in distributions of the ged5to7 package.
 

Original file line number	Diff line number	Diff line change
`@@ -36,6 +36,8 @@ private static void downloadIANALanguageSubtagRegistery(String filename) {`
`36`	`36`	`else if (line.startsWith("Subtag: ")) tag = line.substring(8);`
`37`	`37`	`else if (isLang && line.startsWith("Description: ")) {`
`38`	`38`	`String key = line.substring(13);`
	`39`	`+ // key = key.replaceAll(" \\(.*", ""); // change "Modern Greek (1453-)" to "Modern Greek" but also conflates arr "Karo (Brazil)" and kxh "Karo (Ethiopia)" so disabled for now`
	`40`	`+ key = key.replaceAll(" language.*", ""); // change "Bihari languages" to "Bihari"`
`39`	`41`	`fos.write((key+"\t"+tag+"\n").getBytes("UTF-8"));`
`40`	`42`	`}`
`41`	`43`	`}`