Skip to content

Pinyin fixes #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
camelCaseD wants to merge 7 commits into
base: master
Choose a base branch
from
Open

Pinyin fixes #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
d69c439
Update index.js
camelCaseD Dec 14, 2014
0d39c31
Add test for 'ü/v' conversion
camelCaseD Dec 14, 2014
6ec9b38
Add support for 'ü/v'
camelCaseD Dec 14, 2014
c5454a0
Update database as of 12-22-2014 from mdbg
camelCaseD Dec 24, 2014
10c2d11
Disable logging
camelCaseD Dec 24, 2014
4d1b7c0
Update pinyin in DB to be all lowercased
camelCaseD Dec 24, 2014
824d5d4
Fix pinyin pretifying
camelCaseD Jan 4, 2015
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file modified db/cc-cedict.sqlite
View file
Open in desktop
Binary file not shown.
Binary file added db/cc-cedict_old.sqlite
View file
Open in desktop
Binary file not shown.
52 changes: 34 additions & 18 deletions index.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,8 @@ var path = require('path');
var Sequelize = require('sequelize');
var sequelize = new Sequelize(null, null, null, {
dialect: 'sqlite',
storage: path.join(__dirname, './db/cc-cedict.sqlite')
storage: path.join(__dirname, './db/cc-cedict.sqlite'),
logging: false
});

var Word = sequelize.define('Word', {
Expand Down Expand Up @@ -42,7 +43,7 @@ module.exports.searchByChinese = function(str, cb){
var results = [];
_.each(words, function(word){
var pronunciation = word.pronunciation;
var prettified = pinyin.prettify(pronunciation.slice(1, pronunciation.length - 1));
var prettified = pinyin.prettify(pronunciation.slice(1, pronunciation.length - 1).replace(/u\:/g, "v"));
results.push({
traditional: word.traditional,
simplified: word.simplified,
Expand All @@ -62,10 +63,25 @@ module.exports.searchByPinyin = function(str, cb) {
_.each(parts, function(part) {
var numeric = part.replace(/\D/g,'');

// Convert ü/v to u: as used in dictionary
var newPart = [];
var umlat = false;
_.each(part.split(""), function(char) {
if (char === "ü" || char === "v") {
newPart.push("u");
newPart.push(":");
umlat = true;
} else {
newPart.push(char);
}
});
if (umlat)
newStr.push(newPart.join(""));

if (numeric === "") {
part += "5";
newStr.push(part);
} else {
} else if (!umlat) {
newStr.push(part);
}
});
Expand All @@ -77,21 +93,21 @@ module.exports.searchByPinyin = function(str, cb) {
};

Word
.findAll(query)
.then(function(words) {
var results = [];
_.each(words, function(word) {
var pronunciation = word.pronunciation;
var prettified = pinyin.prettify(pronunciation.slice(1, pronunciation.length - 1));
results.push({
traditional: word.traditional,
simplified: word.simplified,
pronunciation: prettified,
definitions: word.definitions
});
});
cb(results);
.findAll(query)
.then(function(words) {
var results = [];

_.each(words, function(word) {
var pronunciation = word.pronunciation;
var prettified = pinyin.prettify(pronunciation.slice(1, pronunciation.length - 1).replace(/u\:/g, "v"));
Copy link
Owner

@johnheroy johnheroy Mar 6, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please fix the whitespace here

results.push({
traditional: word.traditional,
simplified: word.simplified,
pronunciation: prettified,
definitions: word.definitions
});
});
cb(results);
});
}

Expand Down
5 changes: 3 additions & 2 deletions parser/dictionary-parser.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,8 @@ var fs = require('fs');
// defined db config
var sequelize = new Sequelize(null, null, null, {
dialect: 'sqlite',
storage: '../db/cc-cedict.sqlite'
storage: '../db/cc-cedict.sqlite',
logging: false
});

// create a sqlite database with every entry
Expand Down Expand Up @@ -48,7 +49,7 @@ fs.readFile('../src/cc-cedict.txt', 'UTF-8', function(err, data){
var simplified = spaceSplit[1];

var regex = /\[(.*?)\]/;
var pronunciation = line.match(regex)[0];
var pronunciation = line.match(regex)[0].toLowerCase();

var slashSplit = line.split('/');
var defs = slashSplit.slice(1, slashSplit.length - 1).join('; ');
Expand Down
Loading