better documented 'str/normalize-utf'

jlangch · Mar 26, 2024 · 9b834a9 · 9b834a9
1 parent 2cfec8b
commit 9b834a9
Showing 1 changed file with 9 additions and 7 deletions.
diff --git a/src/main/java/com/github/jlangch/venice/impl/functions/StringFunctions.java b/src/main/java/com/github/jlangch/venice/impl/functions/StringFunctions.java
@@ -2894,7 +2894,7 @@ public VncVal apply(final VncList args) {
                     .doc(
                     	"Normalizes an UTF string.\n\n" +
                     	"On MacOS umlauts like ä are just encoded as 'a' plus the combining diaresis\n" +
-                    	"character. Therefore an 'ä' in Java and an 'ä' from a MacOS filename are\n" +
+                    	"character  ̈. Therefore an 'ä' in Java and an 'ä' from a MacOS filename are\n" +
                     	"different!\n\n" +
                     	"This function normalizes UTF strings to simplify processing.\n\n" +
                     	"The _form_ argument is one of:\n"+
@@ -2909,19 +2909,17 @@ public VncVal apply(final VncList args) {
                     	" ;; 1: \"ü\"          prints to \"ü\"                                   \n" +
                     	" ;; 2: \"u\\u0308\"   prints to \"ü\"                                   \n" +
                        	"                                                                        \n" +
-                        "The statement:                                                          \n" +
-                        "«If it looks like a duck and quacks like a duck, then it probably is a  \n" +
-                        "duck» is WRONG here!                                                    \n" +
+                        "«If it looks like a duck and quacks like a duck, then it probably is a duck» is definitely WRONG here!                                                    \n" +
                     	"                                                                        \n" +
-                    	";; u with combining diaresis char: \u0308                               \n" +
+                    	";; u with combining diaresis char: \\u0308 ( ̈)                          \n" +
                     	"(println \"u\\u0308\")                                                  \n" +
                     	";; => ü   (actually prints as ü on a terminal)                          \n" +
                     	"                                                                        \n" +
                     	";; ü: \\u00FC                                                           \n" +
                     	"(println \"\\u00FC\")                                                   \n" +
                     	";; => ü                                                                 \n" +
                     	"                                                                        \n" +
-                    	";; combined u with diaresis character                                   \n" +
+                    	";; u with combining diaresis character  ̈                                \n" +
                     	"(h/dump (bytebuf-from-string \"u\\u0308\"))                             \n" +
                     	";; 00000000: 75cc 88                                  u..               \n" +
                     	"                                                                        \n" +
@@ -2933,9 +2931,13 @@ public VncVal apply(final VncList args) {
                     	"(h/dump (bytebuf-from-string \"\\u00FC\"))                              \n" +
                     	";; 00000000: c3bc                                     ..                \n" +
                     	"                                                                        \n" +
-                    	";; u with combined diaresis character normalized                        \n" +
+                    	";; u with combined diaresis character normalized to get a standard ü    \n" +
                     	"(h/dump (bytebuf-from-string (str/normalize-utf \"u\\u0308\" :NFC)))    \n" +
                     	";; 00000000: c3bc                                     ..                \n" +
+                    	"                                                                        \n" +
+                    	";; the reverse (decomposition)                                          \n" +
+                    	"(h/dump (bytebuf-from-string (str/normalize-utf \"\\u00FC\" :NFD)))     \n" +
+                    	";; 00000000: 75cc 88                                  u..               \n" +
                     	"```                                                                     ")
                     .build()
         ) {