emk

To use these templates, you'll need to create a new Anki "note type" with the following fields:

• Sound
• Time
• Source
• Image
• Target: line
• Base: line
• Target: line before
• Base: line before

emk

pub trait Nothing<'a> {
    fn nothing(&'a mut self) -> ();

    fn twice_nothing(&'a mut self) -> () {
        { self.nothing(); }
        { self.nothing(); }
    }
}

// This works.

emk

pub trait StreamingIterator<'a, T> {
    /// Return either the next item in the sequence, or `None` if all items
    /// have been consumed.
    fn next(&'a mut self) -> Option<T>;

    /// Hey, it compiles.
    fn reduce<S>(&'a mut self, init: S, r: |S,T| -> S) -> S {
        let mut sum = init;
        //streaming_for!(v in self, {
        //    sum = r(sum, v);

emk

impl<'a,T: Buffer+'a> Buffer for ChunkBuffer<'a,T> {
    fn fill_buf<'a>(&'a mut self) -> IoResult<&'a [u8]> {
        if self.buffer.as_slice().contains_slice(self.boundary.as_slice()) {
            // Exit 1: Valid data in our local buffer.
            Ok(self.buffer.as_slice())
        } else if self.buffer.len() > 0 {
            // Exit 2: Add some more data to our local buffer so that it's
            // valid (see invariants for top_up).
            self.top_up()
        } else {

emk

Some benchmark results, for:

1. Setting up a MemReader.
2. Setting up a MemReader and reading 130 tokens as sentences (with lots of String and Vector).
3. Reading 1 token, with no copies or allocations.

test conll::memreader_overhead         ... bench:       195 ns/iter (+/- 22) = 22394 MB/s
test conll::sentence_reader_iter_bench ... bench:    269884 ns/iter (+/- 40269) = 16 MB/s
test conll::token_from_str_bench ... bench: 99 ns/iter (+/- 24) = 313 MB/s

emk

#!/usr/bin/env ruby
#
# Convert `MElt -tdL` output into *.conllx format.  Usage:
#
#     melt2conllx < input.melt > output.conllx
#
# Input should be one line per sentence, formatted like:
#
#     Durant/P/durant le/DET/le trajet/NC/trajet qui/PROREL/qui
#

emk

pub struct Emitter<R,K: Hash + Eq + Clone,V: Copy,MR: MapReduce<R,K,V>> {
    results: HashMap<K,V>
}

impl<R,K: Hash + Eq + Clone,V: Copy,MR: MapReduce<R,K,V>> Emitter<R,K,V,MR> {
    fn new() -> Emitter<R,K,V,MR> {
        Emitter{results: HashMap::with_capacity(25000)}
    }

    #[inline]

emk

    Updating git repository `https://github.com/reem/rust-unsafe-any.git`
Unable to update https://github.com/reem/rust-unsafe-any.git#75cff194

Caused by:
  failed to clone into: /tmp/cargo_ASPp/.cargo/git/db/rust-unsafe-any-3633b05955fd77c7

Caused by:
  [16] The SSL certificate is invalid

emk

-- Using Lexique 3 from http://lexique.org/ with SQLite 3.
--
-- On the command line, to remove header and extract the first 10 columns.
-- iconv -f ISO-8859-15 -t UTF-8 Lexique380/Bases+Scripts/Lexique380.txt | tail -n+2 | cut -f 1-10 > lexique1-10.txt

-- Set up our original data table.  This is pretty raw.
PRAGMA encoding = "UTF-8";
CREATE TABLE lexique (
ortho TEXT,
phon TEXT,

emk

-- Generated from Lexique 3. For raw data & Creative Commons License, see: http://lexique.org/
-- Note that this word list has some peculiarities, because it was intended for use by language
-- processing software.
être
avoir
je
de
ne
pas
le