Skip to content

add raw option functionality #33

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
liudonghua123 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

add raw option functionality #33

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
38 changes: 23 additions & 15 deletions lib/Segment.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -228,21 +228,29 @@ Segment.prototype.doSegment = function (text, options) {
options = options || {};
var ret = [];

// 将文本按照换行符分割成多段，并逐一分词
text.replace(/\r/g, '\n').split(/(\n|\s)+/).forEach(function (section) {
var section = section.trim();
if (section.length < 1) return;
// ======================================
// 分词
var sret = me.tokenizer.split(section, me.modules.tokenizer);

// 优化
sret = me.optimizer.doOptimize(sret, me.modules.optimizer);

// ======================================
// 连接分词结果
if (sret.length > 0) ret = ret.concat(sret);
});
// 判断是否是raw，即不去除换行，空格，保留原格式
if (options.raw) {
var rret = me.tokenizer.split(text, me.modules.tokenizer);
rret = me.optimizer.doOptimize(rret, me.modules.optimizer);
if (rret.length > 0) ret = ret.concat(rret);
}
else {
// 将文本按照换行符分割成多段，并逐一分词
text.replace(/\r/g, '\n').split(/(\n|\s)+/).forEach(function (section) {
var section = section.trim();
if (section.length < 1) return;
// ======================================
// 分词
var sret = me.tokenizer.split(section, me.modules.tokenizer);

// 优化
sret = me.optimizer.doOptimize(sret, me.modules.optimizer);

// ======================================
// 连接分词结果
if (sret.length > 0) ret = ret.concat(sret);
});
}

// 去除标点符号
if (options.stripPunctuation) {
Expand Down
5 changes: 1 addition & 4 deletions lib/module/PunctuationTokenizer.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,10 +46,7 @@ exports.split = function (words) {
if (sw.c > lastc) {
ret.push({w: word.w.substr(lastc, sw.c - lastc)});
}
// 忽略空格
if (sw.w != ' ') {
ret.push({w: sw.w, p: POSTAG.D_W});
}
ret.push({w: sw.w, p: POSTAG.D_W});
lastc = sw.c + sw.w.length;
}
var lastsw = stopinfo[stopinfo.length - 1];
Expand Down