WordCount and Summary support CJK Language

* add global `hasCJKLanguage` flag, if true, turn on auto-detecting CJKLanguage
 * add `isCJKLanguage` frontmatter to force specify whether is CJKLanguage or not
 * For .Summary: If isCJKLanguage is true, use the runes as basis for truncation, else keep as today.
 * For WordCount: If isCJKLanguage is true, use the runes as basis for calculation, else keep as today.
 * Unexport RuneCount

Fixes #1377
This commit is contained in:
coderzh
2015-09-03 18:22:20 +08:00
committed by Bjørn Erik Pedersen
parent 2c045ac449
commit 823334875d
5 changed files with 247 additions and 93 deletions

View File

@@ -1,10 +1,11 @@
package helpers
import (
"github.com/stretchr/testify/assert"
"html/template"
"strings"
"testing"
"github.com/stretchr/testify/assert"
)
const tstHTMLContent = "<!DOCTYPE html><html><head><script src=\"http://two/foobar.js\"></script></head><body><nav><ul><li hugo-nav=\"section_0\"></li><li hugo-nav=\"section_1\"></li></ul></nav><article>content <a href=\"http://two/foobar\">foobar</a>. Follow up</article><p>This is some text.<br>And some more.</p></body></html>"
@@ -54,8 +55,6 @@ func TestTruncateWordsToWholeSentence(t *testing.T) {
{"a b c", "a b c", 12, false},
{"a b c", "a b c", 3, false},
{"a", "a", 1, false},
{"Hello 中国", "Hello 中", 2, true},
{"Hello 中国", "Hello 中国", 3, false},
{"This is a sentence.", "This is a sentence.", 5, false},
{"This is also a sentence!", "This is also a sentence!", 1, false},
{"To be. Or not to be. That's the question.", "To be.", 1, true},
@@ -72,3 +71,36 @@ func TestTruncateWordsToWholeSentence(t *testing.T) {
}
}
}
func TestTruncateWordsByRune(t *testing.T) {
type test struct {
input, expected string
max int
truncated bool
}
data := []test{
{"", "", 1, false},
{"a b c", "a b c", 12, false},
{"a b c", "a b c", 3, false},
{"a", "a", 1, false},
{"Hello 中国", "", 0, true},
{"这是中文,全中文。", "这是中文,", 5, true},
{"Hello 中国", "Hello 中", 2, true},
{"Hello 中国", "Hello 中国", 3, false},
{"Hello中国 Good 好的", "Hello中国 Good 好", 9, true},
{"This is a sentence.", "This is", 2, true},
{"This is also a sentence!", "This", 1, true},
{"To be. Or not to be. That's the question.", "To be. Or not", 4, true},
{" \nThis is not a sentence\n ", "This is not", 3, true},
}
for i, d := range data {
output, truncated := TruncateWordsByRune(strings.Fields(d.input), d.max)
if d.expected != output {
t.Errorf("Test %d failed. Expected %q got %q", i, d.expected, output)
}
if d.truncated != truncated {
t.Errorf("Test %d failed. Expected truncated=%t got %t", i, d.truncated, truncated)
}
}
}