ciscorn · July 25, 2024 06:24 · Sep 27, 2021 · Sep 27, 2021 · Sep 27, 2021 · Sep 27, 2021
diff --git a/unicode_normalization.md b/unicode_normalization.md
@@ -1,4 +1,4 @@
-# How to normalize Unicode strings in Python / Go / Rust
+# Normalizing Unicode strings in Python / Go / Rust
 
 NFC, NFD, NFKC, NFKD
 

diff --git a/unicode_normalization.md b/unicode_normalization.md
@@ -1,4 +1,4 @@
-# Unicode normalization in Python / Go / Rust
+# How to normalize Unicode strings in Python / Go / Rust
 
 NFC, NFD, NFKC, NFKD
 

diff --git a/unicode_normalization.md b/unicode_normalization.md
@@ -37,7 +37,7 @@ conv_and_print("NFKD")
 
 ## Go
 
-You can use [golang.org/x/text/unicode/norm](https://pkg.go.dev/golang.org/x/text/unicode/norm) package.
+You can use the [golang.org/x/text/unicode/norm](https://pkg.go.dev/golang.org/x/text/unicode/norm) package.
 
 ```go
 package main
@@ -61,7 +61,7 @@ func main() {
 
 ## Rust
 
-You can use [unicode-normalization](https://crates.io/crates/unicode-normalization) crate.
+You can use the [unicode-normalization](https://crates.io/crates/unicode-normalization) crate.
 
 ```rust
 fn main() {

diff --git a/unicode_normalization.md b/unicode_normalization.md
@@ -37,7 +37,7 @@ conv_and_print("NFKD")
 
 ## Go
 
-You can use golang.org/x/text/unicode/norm package.
+You can use [golang.org/x/text/unicode/norm](https://pkg.go.dev/golang.org/x/text/unicode/norm) package.
 
 ```go
 package main

diff --git a/unicode_normalization.md b/unicode_normalization.md
@@ -37,6 +37,8 @@ conv_and_print("NFKD")
 
 ## Go
 
+You can use golang.org/x/text/unicode/norm package.
+
 ```go
 package main
 
@@ -59,6 +61,8 @@ func main() {
 
 ## Rust
 
+You can use [unicode-normalization](https://crates.io/crates/unicode-normalization) crate.
+
 ```rust
 fn main() {
     use unicode_normalization::UnicodeNormalization;

diff --git a/unicode_normalization.md b/unicode_normalization.md
@@ -2,7 +2,7 @@
 
 NFC, NFD, NFKC, NFKD
 
-source:
+input:
 ```
 ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿
 ```

diff --git a/unicode_normalization.md b/unicode_normalization.md
@@ -2,12 +2,16 @@
 
 NFC, NFD, NFKC, NFKD
 
+source:
+```
+ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿
 ```
-source: ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿
 
 result:
-NFC: ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿ (45 bytes)
-NFD: ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿ (50 bytes)
+
+```
+NFC : ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿ (45 bytes)
+NFD : ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿ (50 bytes)
 NFKC: it’säå(1−2)ドブロク株式会社 (41 bytes)
 NFKD: it’säå(1−2)ドブロク株式会社 (49 bytes)
 ```

diff --git a/unicode_normalization.md b/unicode_normalization.md
@@ -2,6 +2,16 @@
 
 NFC, NFD, NFKC, NFKD
 
+```
+source: ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿
+
+result:
+NFC: ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿ (45 bytes)
+NFD: ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿ (50 bytes)
+NFKC: it’säå(1−2)ドブロク株式会社 (41 bytes)
+NFKD: it’säå(1−2)ドブロク株式会社 (49 bytes)
+```
+
 ## Python
 
 ```python

diff --git a/unicode_normalization.md b/unicode_normalization.md
@@ -2,6 +2,8 @@
 
 NFC, NFD, NFKC, NFKD
 
+## Python
+
 ```python
 import unicodedata
 
@@ -19,6 +21,8 @@ conv_and_print("NFKD")
 
 ```
 
+## Go
+
 ```go
 package main
 
@@ -39,6 +43,8 @@ func main() {
 
 ```
 
+## Rust
+
 ```rust
 fn main() {
     use unicode_normalization::UnicodeNormalization;

diff --git a/unicode_normalization.md b/unicode_normalization.md
@@ -0,0 +1,53 @@
+# Unicode normalization in Python / Go / Rust
+
+NFC, NFD, NFKC, NFKD
+
+```python
+import unicodedata
+
+
+def conv_and_print(form):
+    src = "ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿"
+    norm = unicodedata.normalize(form, src)
+    print(f"{form}: {norm} ({len(norm.encode('utf-8'))} bytes)")
+
+
+conv_and_print("NFC")
+conv_and_print("NFD")
+conv_and_print("NFKC")
+conv_and_print("NFKD")
+
+```
+
+```go
+package main
+
+import (
+	"fmt"
+
+	"golang.org/x/text/unicode/norm"
+)
+
+func main() {
+	src := "ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿"
+	forms := map[string]norm.Form{"NFC": norm.NFC, "NFD": norm.NFD, "NFKC": norm.NFKC, "NFKD": norm.NFKD}
+	for name, form := range forms {
+		norm := form.String(src)
+		fmt.Printf("%s: %v (%v bytes)\n", name, norm, len(norm))
+	}
+}
+
+```
+
+```rust
+fn main() {
+    use unicode_normalization::UnicodeNormalization;
+
+    let s = "ｉｔ’ｓäå（１−2)ドﾌﾞﾛク㍿";
+    let print = |form, norm: &str| println!("{}: {} ({} bytes)", form, norm, norm.len());
+    print("NFC", &s.nfc().collect::<String>());
+    print("NFD", &s.nfd().collect::<String>());
+    print("NFKC", &s.nfkc().collect::<String>());
+    print("NFKD", &s.nfkd().collect::<String>());
+}
+```