-
-
Notifications
You must be signed in to change notification settings - Fork 21
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
ucd-parse: add support for parsing files under 'extracted/'
Closes #46
- Loading branch information
1 parent
865cf3e
commit c61ae95
Showing
14 changed files
with
828 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,61 @@ | ||
use std::path::Path; | ||
use std::str::FromStr; | ||
|
||
use crate::common::{ | ||
parse_codepoint_association, CodepointIter, Codepoints, UcdFile, | ||
UcdFileByCodepoint, | ||
}; | ||
use crate::error::Error; | ||
|
||
/// A single row in the `extracted/DerivedBidiClass.txt` file. | ||
/// | ||
/// This file gives the derived values of the Bidi_Class property. | ||
#[derive(Clone, Debug, Default, Eq, PartialEq)] | ||
pub struct DerivedBidiClass { | ||
/// The codepoint or codepoint range for this entry. | ||
pub codepoints: Codepoints, | ||
/// The derived Bidi_Class of the codepoints in this entry. | ||
pub bidi_class: String, | ||
} | ||
|
||
impl UcdFile for DerivedBidiClass { | ||
fn relative_file_path() -> &'static Path { | ||
Path::new("extracted/DerivedBidiClass.txt") | ||
} | ||
} | ||
|
||
impl UcdFileByCodepoint for DerivedBidiClass { | ||
fn codepoints(&self) -> CodepointIter { | ||
self.codepoints.into_iter() | ||
} | ||
} | ||
|
||
impl FromStr for DerivedBidiClass { | ||
type Err = Error; | ||
|
||
fn from_str(line: &str) -> Result<DerivedBidiClass, Error> { | ||
let (codepoints, bidi_class) = parse_codepoint_association(line)?; | ||
Ok(DerivedBidiClass { codepoints, bidi_class: bidi_class.to_string() }) | ||
} | ||
} | ||
|
||
#[cfg(test)] | ||
mod tests { | ||
use super::DerivedBidiClass; | ||
|
||
#[test] | ||
fn parse_single() { | ||
let line = "00B5 ; L # L& MICRO SIGN\n"; | ||
let row: DerivedBidiClass = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, 0x00B5); | ||
assert_eq!(row.bidi_class, "L"); | ||
} | ||
|
||
#[test] | ||
fn parse_range() { | ||
let line = "0030..0039 ; EN # Nd [10] DIGIT ZERO..DIGIT NINE\n"; | ||
let row: DerivedBidiClass = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, (0x0030, 0x0039)); | ||
assert_eq!(row.bidi_class, "EN"); | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,66 @@ | ||
use std::path::Path; | ||
use std::str::FromStr; | ||
|
||
use crate::common::{ | ||
parse_codepoint_association, CodepointIter, Codepoints, UcdFile, | ||
UcdFileByCodepoint, | ||
}; | ||
use crate::error::Error; | ||
|
||
/// A single row in the `extracted/DerivedBinaryProperties.txt` file. | ||
/// | ||
/// This file indicates whether a codepoint has the Bidi_Mirrored property. | ||
#[derive(Clone, Debug, Default, Eq, PartialEq)] | ||
pub struct DerivedBinaryProperties { | ||
/// The codepoint or codepoint range for this entry. | ||
pub codepoints: Codepoints, | ||
/// The derived property of the codepoints in this entry. Currently, | ||
/// this is always the always the string "Bidi_Mirrored". | ||
pub property: String, | ||
} | ||
|
||
impl UcdFile for DerivedBinaryProperties { | ||
fn relative_file_path() -> &'static Path { | ||
Path::new("extracted/DerivedBinaryProperties.txt") | ||
} | ||
} | ||
|
||
impl UcdFileByCodepoint for DerivedBinaryProperties { | ||
fn codepoints(&self) -> CodepointIter { | ||
self.codepoints.into_iter() | ||
} | ||
} | ||
|
||
impl FromStr for DerivedBinaryProperties { | ||
type Err = Error; | ||
|
||
fn from_str(line: &str) -> Result<DerivedBinaryProperties, Error> { | ||
let (codepoints, property) = parse_codepoint_association(line)?; | ||
Ok(DerivedBinaryProperties { | ||
codepoints, | ||
property: property.to_string(), | ||
}) | ||
} | ||
} | ||
|
||
#[cfg(test)] | ||
mod tests { | ||
use super::DerivedBinaryProperties; | ||
|
||
#[test] | ||
fn parse_single() { | ||
let line = | ||
"0028 ; Bidi_Mirrored # Ps LEFT PARENTHESIS\n"; | ||
let row: DerivedBinaryProperties = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, 0x0028); | ||
assert_eq!(row.property, "Bidi_Mirrored"); | ||
} | ||
|
||
#[test] | ||
fn parse_range() { | ||
let line = "2A3C..2A3E ; Bidi_Mirrored # Sm [3] INTERIOR PRODUCT..Z NOTATION RELATIONAL COMPOSITION\n"; | ||
let row: DerivedBinaryProperties = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, (0x2A3C, 0x2A3E)); | ||
assert_eq!(row.property, "Bidi_Mirrored"); | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,65 @@ | ||
use std::path::Path; | ||
use std::str::FromStr; | ||
|
||
use crate::common::{ | ||
parse_codepoint_association, CodepointIter, Codepoints, UcdFile, | ||
UcdFileByCodepoint, | ||
}; | ||
use crate::error::Error; | ||
|
||
/// A single row in the `extracted/DerivedCombiningClass.txt` file. | ||
/// | ||
/// This file gives the derived values of the Canonical_Combining_Class | ||
/// property. | ||
#[derive(Clone, Debug, Default, Eq, PartialEq)] | ||
pub struct DerivedCombiningClass { | ||
/// The codepoint or codepoint range for this entry. | ||
pub codepoints: Codepoints, | ||
/// The derived Canonical_Combining_Class of the codepoints in this entry. | ||
pub combining_class: String, | ||
} | ||
|
||
impl UcdFile for DerivedCombiningClass { | ||
fn relative_file_path() -> &'static Path { | ||
Path::new("extracted/DerivedCombiningClass.txt") | ||
} | ||
} | ||
|
||
impl UcdFileByCodepoint for DerivedCombiningClass { | ||
fn codepoints(&self) -> CodepointIter { | ||
self.codepoints.into_iter() | ||
} | ||
} | ||
|
||
impl FromStr for DerivedCombiningClass { | ||
type Err = Error; | ||
|
||
fn from_str(line: &str) -> Result<DerivedCombiningClass, Error> { | ||
let (codepoints, combining_class) = parse_codepoint_association(line)?; | ||
Ok(DerivedCombiningClass { | ||
codepoints, | ||
combining_class: combining_class.to_string(), | ||
}) | ||
} | ||
} | ||
|
||
#[cfg(test)] | ||
mod tests { | ||
use super::DerivedCombiningClass; | ||
|
||
#[test] | ||
fn parse_single() { | ||
let line = "0020 ; 0 # Zs SPACE\n"; | ||
let row: DerivedCombiningClass = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, 0x0020); | ||
assert_eq!(row.combining_class, "0"); | ||
} | ||
|
||
#[test] | ||
fn parse_range() { | ||
let line = "1DD1..1DF5 ; 230 # Mn [37] COMBINING UR ABOVE..COMBINING UP TACK ABOVE\n"; | ||
let row: DerivedCombiningClass = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, (0x1DD1, 0x1DF5)); | ||
assert_eq!(row.combining_class, "230"); | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,66 @@ | ||
use std::path::Path; | ||
use std::str::FromStr; | ||
|
||
use crate::common::{ | ||
parse_codepoint_association, CodepointIter, Codepoints, UcdFile, | ||
UcdFileByCodepoint, | ||
}; | ||
use crate::error::Error; | ||
|
||
/// A single row in the `extracted/DerivedCombiningClass.txt` file. | ||
/// | ||
/// This file gives the derived values of the Decomposition_Type | ||
/// property. | ||
#[derive(Clone, Debug, Default, Eq, PartialEq)] | ||
pub struct DerivedDecompositionType { | ||
/// The codepoint or codepoint range for this entry. | ||
pub codepoints: Codepoints, | ||
/// The derived Decomposition_Type of the codepoints in this entry. | ||
pub decomposition_type: String, | ||
} | ||
|
||
impl UcdFile for DerivedDecompositionType { | ||
fn relative_file_path() -> &'static Path { | ||
Path::new("extracted/DerivedDecompositionType.txt") | ||
} | ||
} | ||
|
||
impl UcdFileByCodepoint for DerivedDecompositionType { | ||
fn codepoints(&self) -> CodepointIter { | ||
self.codepoints.into_iter() | ||
} | ||
} | ||
|
||
impl FromStr for DerivedDecompositionType { | ||
type Err = Error; | ||
|
||
fn from_str(line: &str) -> Result<DerivedDecompositionType, Error> { | ||
let (codepoints, decomposition_type) = | ||
parse_codepoint_association(line)?; | ||
Ok(DerivedDecompositionType { | ||
codepoints, | ||
decomposition_type: decomposition_type.to_string(), | ||
}) | ||
} | ||
} | ||
|
||
#[cfg(test)] | ||
mod tests { | ||
use super::DerivedDecompositionType; | ||
|
||
#[test] | ||
fn parse_single() { | ||
let line = "00A0 ; Nobreak # Zs NO-BREAK SPACE\n"; | ||
let row: DerivedDecompositionType = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, 0x00A0); | ||
assert_eq!(row.decomposition_type, "Nobreak"); | ||
} | ||
|
||
#[test] | ||
fn parse_range() { | ||
let line = "3070..3071 ; Canonical # Lo [2] HIRAGANA LETTER BA..HIRAGANA LETTER PA\n"; | ||
let row: DerivedDecompositionType = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, (0x3070, 0x3071)); | ||
assert_eq!(row.decomposition_type, "Canonical"); | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,66 @@ | ||
use std::path::Path; | ||
use std::str::FromStr; | ||
|
||
use crate::common::{ | ||
parse_codepoint_association, CodepointIter, Codepoints, UcdFile, | ||
UcdFileByCodepoint, | ||
}; | ||
use crate::error::Error; | ||
|
||
/// A single row in the `extracted/DerivedEastAsianWidth.txt` file. | ||
/// | ||
/// This file gives the derived values of the East_Asian_Width | ||
/// property. | ||
#[derive(Clone, Debug, Default, Eq, PartialEq)] | ||
pub struct DerivedEastAsianWidth { | ||
/// The codepoint or codepoint range for this entry. | ||
pub codepoints: Codepoints, | ||
/// The derived East_Asian_Width of the codepoints in this entry. | ||
pub east_asian_width: String, | ||
} | ||
|
||
impl UcdFile for DerivedEastAsianWidth { | ||
fn relative_file_path() -> &'static Path { | ||
Path::new("extracted/DerivedEastAsianWidth.txt") | ||
} | ||
} | ||
|
||
impl UcdFileByCodepoint for DerivedEastAsianWidth { | ||
fn codepoints(&self) -> CodepointIter { | ||
self.codepoints.into_iter() | ||
} | ||
} | ||
|
||
impl FromStr for DerivedEastAsianWidth { | ||
type Err = Error; | ||
|
||
fn from_str(line: &str) -> Result<DerivedEastAsianWidth, Error> { | ||
let (codepoints, east_asian_width) = | ||
parse_codepoint_association(line)?; | ||
Ok(DerivedEastAsianWidth { | ||
codepoints, | ||
east_asian_width: east_asian_width.to_string(), | ||
}) | ||
} | ||
} | ||
|
||
#[cfg(test)] | ||
mod tests { | ||
use super::DerivedEastAsianWidth; | ||
|
||
#[test] | ||
fn parse_single() { | ||
let line = "00A0 ; N # Zs NO-BREAK SPACE\n"; | ||
let row: DerivedEastAsianWidth = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, 0x00A0); | ||
assert_eq!(row.east_asian_width, "N"); | ||
} | ||
|
||
#[test] | ||
fn parse_range() { | ||
let line = "FF10..FF19 ; F # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE\n"; | ||
let row: DerivedEastAsianWidth = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, (0xFF10, 0xFF19)); | ||
assert_eq!(row.east_asian_width, "F"); | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,65 @@ | ||
use std::path::Path; | ||
use std::str::FromStr; | ||
|
||
use crate::common::{ | ||
parse_codepoint_association, CodepointIter, Codepoints, UcdFile, | ||
UcdFileByCodepoint, | ||
}; | ||
use crate::error::Error; | ||
|
||
/// A single row in the `extracted/DerivedGeneralCategory.txt` file. | ||
/// | ||
/// This file gives the derived values of the General_Category property. | ||
#[derive(Clone, Debug, Default, Eq, PartialEq)] | ||
pub struct DerivedGeneralCategory { | ||
/// The codepoint or codepoint range for this entry. | ||
pub codepoints: Codepoints, | ||
/// The derived General_Category of the codepoints in this entry. | ||
pub general_category: String, | ||
} | ||
|
||
impl UcdFile for DerivedGeneralCategory { | ||
fn relative_file_path() -> &'static Path { | ||
Path::new("extracted/DerivedGeneralCategory.txt") | ||
} | ||
} | ||
|
||
impl UcdFileByCodepoint for DerivedGeneralCategory { | ||
fn codepoints(&self) -> CodepointIter { | ||
self.codepoints.into_iter() | ||
} | ||
} | ||
|
||
impl FromStr for DerivedGeneralCategory { | ||
type Err = Error; | ||
|
||
fn from_str(line: &str) -> Result<DerivedGeneralCategory, Error> { | ||
let (codepoints, general_category) = | ||
parse_codepoint_association(line)?; | ||
Ok(DerivedGeneralCategory { | ||
codepoints, | ||
general_category: general_category.to_string(), | ||
}) | ||
} | ||
} | ||
|
||
#[cfg(test)] | ||
mod tests { | ||
use super::DerivedGeneralCategory; | ||
|
||
#[test] | ||
fn parse_single() { | ||
let line = "04D9 ; Ll # CYRILLIC SMALL LETTER SCHWA\n"; | ||
let row: DerivedGeneralCategory = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, 0x04D9); | ||
assert_eq!(row.general_category, "Ll"); | ||
} | ||
|
||
#[test] | ||
fn parse_range() { | ||
let line = "0660..0669 ; Nd # [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE"; | ||
let row: DerivedGeneralCategory = line.parse().unwrap(); | ||
assert_eq!(row.codepoints, (0x0660, 0x0669)); | ||
assert_eq!(row.general_category, "Nd"); | ||
} | ||
} |
Oops, something went wrong.