aboutsummaryrefslogtreecommitdiff
path: root/utf8parse
diff options
context:
space:
mode:
Diffstat (limited to 'utf8parse')
-rw-r--r--utf8parse/Cargo.toml15
l---------utf8parse/LICENSE-APACHE1
l---------utf8parse/LICENSE-MIT1
-rw-r--r--utf8parse/src/lib.rs132
-rw-r--r--utf8parse/src/types.rs100
-rw-r--r--utf8parse/tests/UTF-8-demo.txt212
-rw-r--r--utf8parse/tests/utf-8-demo.rs31
7 files changed, 0 insertions, 492 deletions
diff --git a/utf8parse/Cargo.toml b/utf8parse/Cargo.toml
deleted file mode 100644
index 71ea44b..0000000
--- a/utf8parse/Cargo.toml
+++ /dev/null
@@ -1,15 +0,0 @@
-[package]
-authors = ["Joe Wilm <joe@jwilm.com>", "Christian Duerr <contact@christianduerr.com>"]
-description = "Table-driven UTF-8 parser"
-documentation = "https://docs.rs/utf8parse/"
-repository = "https://github.com/alacritty/vte"
-keywords = ["utf8", "parse", "table"]
-categories = ["parsing", "no-std"]
-license = "Apache-2.0 OR MIT"
-version = "0.2.2"
-name = "utf8parse"
-edition = "2018"
-
-[features]
-nightly = []
-default = []
diff --git a/utf8parse/LICENSE-APACHE b/utf8parse/LICENSE-APACHE
deleted file mode 120000
index 965b606..0000000
--- a/utf8parse/LICENSE-APACHE
+++ /dev/null
@@ -1 +0,0 @@
-../LICENSE-APACHE \ No newline at end of file
diff --git a/utf8parse/LICENSE-MIT b/utf8parse/LICENSE-MIT
deleted file mode 120000
index 76219eb..0000000
--- a/utf8parse/LICENSE-MIT
+++ /dev/null
@@ -1 +0,0 @@
-../LICENSE-MIT \ No newline at end of file
diff --git a/utf8parse/src/lib.rs b/utf8parse/src/lib.rs
deleted file mode 100644
index 093de81..0000000
--- a/utf8parse/src/lib.rs
+++ /dev/null
@@ -1,132 +0,0 @@
-//! A table-driven UTF-8 Parser
-//!
-//! This module implements a table-driven UTF-8 parser which should
-//! theoretically contain the minimal number of branches (1). The only branch is
-//! on the `Action` returned from unpacking a transition.
-#![deny(clippy::all, clippy::if_not_else, clippy::enum_glob_use)]
-#![cfg_attr(all(feature = "nightly", test), feature(test))]
-#![no_std]
-
-use core::char;
-
-mod types;
-
-use types::{Action, State};
-
-/// Handles codepoint and invalid sequence events from the parser.
-pub trait Receiver {
- /// Called whenever a codepoint is parsed successfully
- fn codepoint(&mut self, _: char);
-
- /// Called when an invalid_sequence is detected
- fn invalid_sequence(&mut self);
-}
-
-/// A parser for Utf8 Characters
-///
-/// Repeatedly call `advance` with bytes to emit Utf8 characters
-#[derive(Clone, Default, PartialEq, Eq, Debug)]
-pub struct Parser {
- point: u32,
- state: State,
-}
-
-/// Continuation bytes are masked with this value.
-const CONTINUATION_MASK: u8 = 0b0011_1111;
-
-impl Parser {
- /// Create a new Parser
- pub fn new() -> Parser {
- Parser { point: 0, state: State::Ground }
- }
-
- /// Advance the parser
- ///
- /// The provider receiver will be called whenever a codepoint is completed or an invalid
- /// sequence is detected.
- pub fn advance<R>(&mut self, receiver: &mut R, byte: u8)
- where
- R: Receiver,
- {
- let (state, action) = self.state.advance(byte);
- self.perform_action(receiver, byte, action);
- self.state = state;
- }
-
- fn perform_action<R>(&mut self, receiver: &mut R, byte: u8, action: Action)
- where
- R: Receiver,
- {
- match action {
- Action::InvalidSequence => {
- self.point = 0;
- receiver.invalid_sequence();
- },
- Action::EmitByte => {
- receiver.codepoint(byte as char);
- },
- Action::SetByte1 => {
- let point = self.point | ((byte & CONTINUATION_MASK) as u32);
- let c = unsafe { char::from_u32_unchecked(point) };
- self.point = 0;
-
- receiver.codepoint(c);
- },
- Action::SetByte2 => {
- self.point |= ((byte & CONTINUATION_MASK) as u32) << 6;
- },
- Action::SetByte2Top => {
- self.point |= ((byte & 0b0001_1111) as u32) << 6;
- },
- Action::SetByte3 => {
- self.point |= ((byte & CONTINUATION_MASK) as u32) << 12;
- },
- Action::SetByte3Top => {
- self.point |= ((byte & 0b0000_1111) as u32) << 12;
- },
- Action::SetByte4 => {
- self.point |= ((byte & 0b0000_0111) as u32) << 18;
- },
- }
- }
-}
-
-#[cfg(all(feature = "nightly", test))]
-mod benches {
- extern crate std;
- extern crate test;
-
- use super::{Parser, Receiver};
-
- use self::test::{black_box, Bencher};
-
- static UTF8_DEMO: &[u8] = include_bytes!("../tests/UTF-8-demo.txt");
-
- impl Receiver for () {
- fn codepoint(&mut self, c: char) {
- black_box(c);
- }
-
- fn invalid_sequence(&mut self) {}
- }
-
- #[bench]
- fn parse_bench_utf8_demo(b: &mut Bencher) {
- let mut parser = Parser::new();
-
- b.iter(|| {
- for byte in UTF8_DEMO {
- parser.advance(&mut (), *byte);
- }
- })
- }
-
- #[bench]
- fn std_string_parse_utf8(b: &mut Bencher) {
- b.iter(|| {
- for c in std::str::from_utf8(UTF8_DEMO).unwrap().chars() {
- black_box(c);
- }
- });
- }
-}
diff --git a/utf8parse/src/types.rs b/utf8parse/src/types.rs
deleted file mode 100644
index 8a52c67..0000000
--- a/utf8parse/src/types.rs
+++ /dev/null
@@ -1,100 +0,0 @@
-//! Types supporting the UTF-8 parser
-
-/// Action to take when receiving a byte
-#[derive(Debug, Copy, Clone)]
-pub enum Action {
- /// Unexpected byte; sequence is invalid
- InvalidSequence = 0,
- /// Received valid 7-bit ASCII byte which can be directly emitted.
- EmitByte = 1,
- /// Set the bottom continuation byte
- SetByte1 = 2,
- /// Set the 2nd-from-last continuation byte
- SetByte2 = 3,
- /// Set the 2nd-from-last byte which is part of a two byte sequence
- SetByte2Top = 4,
- /// Set the 3rd-from-last continuation byte
- SetByte3 = 5,
- /// Set the 3rd-from-last byte which is part of a three byte sequence
- SetByte3Top = 6,
- /// Set the top byte of a four byte sequence.
- SetByte4 = 7,
-}
-
-/// States the parser can be in.
-///
-/// There is a state for each initial input of the 3 and 4 byte sequences since
-/// the following bytes are subject to different conditions than a tail byte.
-#[allow(non_camel_case_types)]
-#[derive(Debug, Default, Copy, Clone, PartialEq, Eq)]
-pub enum State {
- /// Ground state; expect anything
- #[default]
- Ground = 0,
- /// 3 tail bytes
- Tail3 = 1,
- /// 2 tail bytes
- Tail2 = 2,
- /// 1 tail byte
- Tail1 = 3,
- /// UTF8-3 starting with E0
- U3_2_e0 = 4,
- /// UTF8-3 starting with ED
- U3_2_ed = 5,
- /// UTF8-4 starting with F0
- Utf8_4_3_f0 = 6,
- /// UTF8-4 starting with F4
- Utf8_4_3_f4 = 7,
-}
-
-impl State {
- /// Advance the parser state.
- ///
- /// This takes the current state and input byte into consideration, to determine the next state
- /// and any action that should be taken.
- #[inline]
- pub fn advance(self, byte: u8) -> (State, Action) {
- match self {
- State::Ground => match byte {
- 0x00..=0x7f => (State::Ground, Action::EmitByte),
- 0xc2..=0xdf => (State::Tail1, Action::SetByte2Top),
- 0xe0 => (State::U3_2_e0, Action::SetByte3Top),
- 0xe1..=0xec => (State::Tail2, Action::SetByte3Top),
- 0xed => (State::U3_2_ed, Action::SetByte3Top),
- 0xee..=0xef => (State::Tail2, Action::SetByte3Top),
- 0xf0 => (State::Utf8_4_3_f0, Action::SetByte4),
- 0xf1..=0xf3 => (State::Tail3, Action::SetByte4),
- 0xf4 => (State::Utf8_4_3_f4, Action::SetByte4),
- _ => (State::Ground, Action::InvalidSequence),
- },
- State::U3_2_e0 => match byte {
- 0xa0..=0xbf => (State::Tail1, Action::SetByte2),
- _ => (State::Ground, Action::InvalidSequence),
- },
- State::U3_2_ed => match byte {
- 0x80..=0x9f => (State::Tail1, Action::SetByte2),
- _ => (State::Ground, Action::InvalidSequence),
- },
- State::Utf8_4_3_f0 => match byte {
- 0x90..=0xbf => (State::Tail2, Action::SetByte3),
- _ => (State::Ground, Action::InvalidSequence),
- },
- State::Utf8_4_3_f4 => match byte {
- 0x80..=0x8f => (State::Tail2, Action::SetByte3),
- _ => (State::Ground, Action::InvalidSequence),
- },
- State::Tail3 => match byte {
- 0x80..=0xbf => (State::Tail2, Action::SetByte3),
- _ => (State::Ground, Action::InvalidSequence),
- },
- State::Tail2 => match byte {
- 0x80..=0xbf => (State::Tail1, Action::SetByte2),
- _ => (State::Ground, Action::InvalidSequence),
- },
- State::Tail1 => match byte {
- 0x80..=0xbf => (State::Ground, Action::SetByte1),
- _ => (State::Ground, Action::InvalidSequence),
- },
- }
- }
-}
diff --git a/utf8parse/tests/UTF-8-demo.txt b/utf8parse/tests/UTF-8-demo.txt
deleted file mode 100644
index 4363f27..0000000
--- a/utf8parse/tests/UTF-8-demo.txt
+++ /dev/null
@@ -1,212 +0,0 @@
-
-UTF-8 encoded sample plain-text file
-‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾
-
-Markus Kuhn [ˈmaʳkʊs kuːn] <http://www.cl.cam.ac.uk/~mgk25/> — 2002-07-25
-
-
-The ASCII compatible UTF-8 encoding used in this plain-text file
-is defined in Unicode, ISO 10646-1, and RFC 2279.
-
-
-Using Unicode/UTF-8, you can write in emails and source code things such as
-
-Mathematics and sciences:
-
- ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫
- ⎪⎢⎜│a²+b³ ⎟⎥⎪
- ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪
- ⎪⎢⎜⎷ c₈ ⎟⎥⎪
- ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬
- ⎪⎢⎜ ∞ ⎟⎥⎪
- ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪
- ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪
- 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭
-
-Linguistics and dictionaries:
-
- ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn
- Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ]
-
-APL:
-
- ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈
-
-Nicer typography in plain text files:
-
- ╔══════════════════════════════════════════╗
- ║ ║
- ║ • ‘single’ and “double” quotes ║
- ║ ║
- ║ • Curly apostrophes: “We’ve been here” ║
- ║ ║
- ║ • Latin-1 apostrophe and accents: '´` ║
- ║ ║
- ║ • ‚deutsche‘ „Anführungszeichen“ ║
- ║ ║
- ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║
- ║ ║
- ║ • ASCII safety test: 1lI|, 0OD, 8B ║
- ║ ╭─────────╮ ║
- ║ • the euro symbol: │ 14.95 € │ ║
- ║ ╰─────────╯ ║
- ╚══════════════════════════════════════════╝
-
-Combining characters:
-
- STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑
-
-Greek (in Polytonic):
-
- The Greek anthem:
-
- Σὲ γνωρίζω ἀπὸ τὴν κόψη
- τοῦ σπαθιοῦ τὴν τρομερή,
- σὲ γνωρίζω ἀπὸ τὴν ὄψη
- ποὺ μὲ βία μετράει τὴ γῆ.
-
- ᾿Απ᾿ τὰ κόκκαλα βγαλμένη
- τῶν ῾Ελλήνων τὰ ἱερά
- καὶ σὰν πρῶτα ἀνδρειωμένη
- χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά!
-
- From a speech of Demosthenes in the 4th century BC:
-
- Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι,
- ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς
- λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ
- τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿
- εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ
- πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν
- οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι,
- οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν
- ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον
- τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι
- γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν
- προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους
- σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ
- τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ
- τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς
- τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον.
-
- Δημοσθένους, Γ´ ᾿Ολυνθιακὸς
-
-Georgian:
-
- From a Unicode conference invitation:
-
- გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო
- კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს,
- ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს
- ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი,
- ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება
- ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში,
- ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში.
-
-Russian:
-
- From a Unicode conference invitation:
-
- Зарегистрируйтесь сейчас на Десятую Международную Конференцию по
- Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии.
- Конференция соберет широкий круг экспертов по вопросам глобального
- Интернета и Unicode, локализации и интернационализации, воплощению и
- применению Unicode в различных операционных системах и программных
- приложениях, шрифтах, верстке и многоязычных компьютерных системах.
-
-Thai (UCS Level 2):
-
- Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese
- classic 'San Gua'):
-
- [----------------------------|------------------------]
- ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่
- สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา
- ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา
- โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ
- เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ
- ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ
- พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้
- ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ
-
- (The above is a two-column text. If combining characters are handled
- correctly, the lines of the second column should be aligned with the
- | character above.)
-
-Ethiopian:
-
- Proverbs in the Amharic language:
-
- ሰማይ አይታረስ ንጉሥ አይከሰስ።
- ብላ ካለኝ እንደአባቴ በቆመጠኝ።
- ጌጥ ያለቤቱ ቁምጥና ነው።
- ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው።
- የአፍ ወለምታ በቅቤ አይታሽም።
- አይጥ በበላ ዳዋ ተመታ።
- ሲተረጉሙ ይደረግሙ።
- ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል።
- ድር ቢያብር አንበሳ ያስር።
- ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም።
- እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም።
- የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ።
- ሥራ ከመፍታት ልጄን ላፋታት።
- ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል።
- የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ።
- ተንጋሎ ቢተፉ ተመልሶ ባፉ።
- ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው።
- እግርህን በፍራሽህ ልክ ዘርጋ።
-
-Runes:
-
- ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ
-
- (Old English, which transcribed into Latin reads 'He cwaeth that he
- bude thaem lande northweardum with tha Westsae.' and means 'He said
- that he lived in the northern land near the Western Sea.')
-
-Braille:
-
- ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌
-
- ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞
- ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎
- ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂
- ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙
- ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑
- ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲
-
- ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲
-
- ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹
- ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞
- ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕
- ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹
- ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎
- ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎
- ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳
- ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞
- ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲
-
- (The first couple of paragraphs of "A Christmas Carol" by Dickens)
-
-Compact font selection example text:
-
- ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789
- abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ
- –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд
- ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა
-
-Greetings in various languages:
-
- Hello world, Καλημέρα κόσμε, コンニチハ
-
-Box drawing alignment tests: █
- ▉
- ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳
- ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳
- ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳
- ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳
- ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎
- ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏
- ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█
- ▝▀▘▙▄▟
diff --git a/utf8parse/tests/utf-8-demo.rs b/utf8parse/tests/utf-8-demo.rs
deleted file mode 100644
index 51df492..0000000
--- a/utf8parse/tests/utf-8-demo.rs
+++ /dev/null
@@ -1,31 +0,0 @@
-use utf8parse::{Parser, Receiver};
-
-static UTF8_DEMO: &[u8] = include_bytes!("UTF-8-demo.txt");
-
-#[derive(Debug, PartialEq)]
-struct StringWrapper(String);
-
-impl Receiver for StringWrapper {
- fn codepoint(&mut self, c: char) {
- self.0.push(c);
- }
-
- fn invalid_sequence(&mut self) {}
-}
-
-#[test]
-fn utf8parse_test() {
- let mut parser = Parser::new();
-
- // utf8parse implementation
- let mut actual = StringWrapper(String::new());
-
- for byte in UTF8_DEMO {
- parser.advance(&mut actual, *byte)
- }
-
- // standard library implementation
- let expected = String::from_utf8_lossy(UTF8_DEMO);
-
- assert_eq!(actual.0, expected);
-}
generated by cgit (git 2.34.1) at 2025-07-24 07:19:19 +0000