std: Rename str::Normalizations to str::Decompositions

The Normalizations iterator has been renamed to Decompositions.
It does not currently include all forms of Unicode normalization,
but only encompasses decompositions.
If implemented recomposition would likely be a separate iterator
which works on the result of this one.

[breaking-change]

src/etc/unicode.py

@@ -256,13 +256,13 @@ def format_table_content(f, content, indent):
             line = " "*indent + chunk
     f.write(line)
 
-def emit_core_decomp_module(f, canon, compat):
+def emit_core_norm_module(f, canon, compat):
     canon_keys = canon.keys()
     canon_keys.sort()
 
     compat_keys = compat.keys()
     compat_keys.sort()
-    f.write("pub mod decompose {\n");
+    f.write("pub mod normalization {\n");
     f.write("    use option::Option;\n");
     f.write("    use option::{Some, None};\n");
     f.write("    use slice::ImmutableVector;\n");
@@ -401,8 +401,8 @@ def emit_core_decomp_module(f, canon, compat):
 
 """)
 
-def emit_std_decomp_module(f, combine):
-    f.write("pub mod decompose {\n");
+def emit_std_norm_module(f, combine):
+    f.write("pub mod normalization {\n");
     f.write("    use option::{Some, None};\n");
     f.write("    use slice::ImmutableVector;\n");
 
@@ -467,7 +467,7 @@ def gen_core_unicode():
         emit_bsearch_range_table(rf);
         emit_property_module(rf, "general_category", gencats)
 
-        emit_core_decomp_module(rf, canon_decomp, compat_decomp)
+        emit_core_norm_module(rf, canon_decomp, compat_decomp)
 
         derived = load_properties("DerivedCoreProperties.txt",
                 ["XID_Start", "XID_Continue", "Alphabetic", "Lowercase", "Uppercase"])
@@ -485,7 +485,7 @@ def gen_std_unicode():
     with open(r, "w") as rf:
         # Preamble
         rf.write(preamble)
-        emit_std_decomp_module(rf, combines)
+        emit_std_norm_module(rf, combines)
 
 gen_core_unicode()
 gen_std_unicode()

src/libcore/char.rs

@@ -30,9 +30,9 @@ use iter::{Iterator, range_step};
 use unicode::{derived_property, property, general_category, conversions};
 
 /// Returns the canonical decomposition of a character.
-pub use unicode::decompose::decompose_canonical;
+pub use unicode::normalization::decompose_canonical;
 /// Returns the compatibility decomposition of a character.
-pub use unicode::decompose::decompose_compatible;
+pub use unicode::normalization::decompose_compatible;
 
 #[cfg(not(test))] use cmp::{Eq, Ord, TotalEq, TotalOrd, Ordering};
 #[cfg(not(test))] use default::Default;

src/libcore/unicode.rs

@@ -104,7 +104,7 @@ pub mod general_category {
 
 }
 
-pub mod decompose {
+pub mod normalization {
     use option::Option;
     use option::{Some, None};
     use slice::ImmutableVector;

src/libstd/str.rs

@@ -228,25 +228,25 @@ fn canonical_sort(comb: &mut [(char, u8)]) {
 }
 
 #[deriving(Clone)]
-enum NormalizationForm {
-    NFD,
-    NFKD
+enum DecompositionType {
+    Canonical,
+    Compatible
 }
 
-/// External iterator for a string's normalization's characters.
+/// External iterator for a string's decomposition's characters.
 /// Use with the `std::iter` module.
 #[deriving(Clone)]
-pub struct Normalizations<'a> {
-    kind: NormalizationForm,
+pub struct Decompositions<'a> {
+    kind: DecompositionType,
     iter: Chars<'a>,
     buffer: Vec<(char, u8)>,
     sorted: bool
 }
 
-impl<'a> Iterator<char> for Normalizations<'a> {
+impl<'a> Iterator<char> for Decompositions<'a> {
     #[inline]
     fn next(&mut self) -> Option<char> {
-        use unicode::decompose::canonical_combining_class;
+        use unicode::normalization::canonical_combining_class;
 
         match self.buffer.as_slice().head() {
             Some(&(c, 0)) => {
@@ -262,8 +262,8 @@ impl<'a> Iterator<char> for Normalizations<'a> {
         }
 
         let decomposer = match self.kind {
-            NFD => char::decompose_canonical,
-            NFKD => char::decompose_compatible
+            Canonical => char::decompose_canonical,
+            Compatible => char::decompose_compatible
         };
 
         if !self.sorted {
@@ -887,24 +887,24 @@ pub trait StrAllocating: Str {
     /// An Iterator over the string in Unicode Normalization Form D
     /// (canonical decomposition).
     #[inline]
-    fn nfd_chars<'a>(&'a self) -> Normalizations<'a> {
-        Normalizations {
+    fn nfd_chars<'a>(&'a self) -> Decompositions<'a> {
+        Decompositions {
             iter: self.as_slice().chars(),
             buffer: Vec::new(),
             sorted: false,
-            kind: NFD
+            kind: Canonical
         }
     }
 
     /// An Iterator over the string in Unicode Normalization Form KD
     /// (compatibility decomposition).
     #[inline]
-    fn nfkd_chars<'a>(&'a self) -> Normalizations<'a> {
-        Normalizations {
+    fn nfkd_chars<'a>(&'a self) -> Decompositions<'a> {
+        Decompositions {
             iter: self.as_slice().chars(),
             buffer: Vec::new(),
             sorted: false,
-            kind: NFKD
+            kind: Compatible
         }
     }
 }

src/libstd/unicode.rs

@@ -12,7 +12,7 @@
 
 #![allow(missing_doc, non_uppercase_statics)]
 
-pub mod decompose {
+pub mod normalization {
     use option::{Some, None};
     use slice::ImmutableVector;