1 | use std::path::Path; |
2 | |
3 | use crate::{ |
4 | common::{Codepoint, CodepointIter, UcdFile, UcdFileByCodepoint}, |
5 | error::Error, |
6 | }; |
7 | |
8 | /// A single row in the `Jamo.txt` file. |
9 | /// |
10 | /// The `Jamo.txt` file defines the `Jamo_Short_Name` property. |
11 | #[derive (Clone, Debug, Default, Eq, PartialEq)] |
12 | pub struct JamoShortName { |
13 | /// The codepoint corresponding to this row. |
14 | pub codepoint: Codepoint, |
15 | /// The actual "Jamo Short Name." This string contains at most 3 bytes and |
16 | /// may be empty. |
17 | pub name: String, |
18 | } |
19 | |
20 | impl UcdFile for JamoShortName { |
21 | fn relative_file_path() -> &'static Path { |
22 | Path::new("Jamo.txt" ) |
23 | } |
24 | } |
25 | |
26 | impl UcdFileByCodepoint for JamoShortName { |
27 | fn codepoints(&self) -> CodepointIter { |
28 | self.codepoint.into_iter() |
29 | } |
30 | } |
31 | |
32 | impl std::str::FromStr for JamoShortName { |
33 | type Err = Error; |
34 | |
35 | fn from_str(line: &str) -> Result<JamoShortName, Error> { |
36 | let re_parts: &Regex = regex!( |
37 | r"(?x) |
38 | ^ |
39 | (?P<codepoint>[A-Z0-9]+); |
40 | \s* |
41 | (?P<name>[A-Z]*) |
42 | " , |
43 | ); |
44 | |
45 | let caps: Captures<'_> = match re_parts.captures(haystack:line.trim()) { |
46 | Some(caps: Captures<'_>) => caps, |
47 | None => return err!("invalid Jamo_Short_name line" ), |
48 | }; |
49 | Ok(JamoShortName { |
50 | codepoint: caps["codepoint" ].parse()?, |
51 | name: caps.name("name" ).unwrap().as_str().to_string(), |
52 | }) |
53 | } |
54 | } |
55 | |
56 | #[cfg (test)] |
57 | mod tests { |
58 | use super::JamoShortName; |
59 | |
60 | #[test ] |
61 | fn parse1() { |
62 | let line = "1164; YAE # HANGUL JUNGSEONG YAE \n" ; |
63 | let row: JamoShortName = line.parse().unwrap(); |
64 | assert_eq!(row.codepoint, 0x1164); |
65 | assert_eq!(row.name, "YAE" ); |
66 | } |
67 | |
68 | #[test ] |
69 | fn parse2() { |
70 | let line = "110B; # HANGUL CHOSEONG IEUNG \n" ; |
71 | let row: JamoShortName = line.parse().unwrap(); |
72 | assert_eq!(row.codepoint, 0x110B); |
73 | assert_eq!(row.name, "" ); |
74 | } |
75 | } |
76 | |